Upload folder using huggingface_hub

README.md

@@ -0,0 +1,179 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: FourOhFour/Vapor_7B
+tags:
+- generated_from_trainer
+model-index:
+- name: outputs/out
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.4.1`
+```yaml
+base_model: FourOhFour/Vapor_7B
+model_type: AutoModelForCausalLM
+tokenizer_type: AutoTokenizer
+
+load_in_8bit: false
+load_in_4bit: false
+strict: false
+
+datasets:
+  - path: anthracite-org/stheno-filtered-v1.1
+    type: sharegpt
+    conversation: chatml
+  - path: Epiculous/SynthRP-Gens-v1.1-Filtered-n-Cleaned
+    type: sharegpt
+    conversation: chatml
+  - path: ResplendentAI/bluemoon
+    type: sharegpt
+    conversation: chatml
+  - path: openerotica/freedom-rp
+    type: sharegpt
+    conversation: chatml
+  - path: anthracite-org/nopm_claude_writing_fixed
+    type: sharegpt
+    conversation: chatml
+  - path: MinervaAI/Aesir-Preview
+    type: sharegpt
+    conversation: chatml
+  - path: NewEden/c2-prefixed
+    type: sharegpt
+    conversation: chatml
+
+chat_template: chatml
+
+val_set_size: 0.01
+output_dir: ./outputs/out
+
+adapter:
+lora_r:
+lora_alpha:
+lora_dropout:
+lora_target_linear:
+
+sequence_len: 8192
+# sequence_len: 32768
+sample_packing: true
+eval_sample_packing: false
+pad_to_sequence_len: true
+
+plugins:
+  - axolotl.integrations.liger.LigerPlugin
+liger_rope: true
+liger_rms_norm: true
+liger_swiglu: true
+liger_fused_linear_cross_entropy: true
+
+wandb_project: smoke7B
+wandb_entity:
+wandb_watch:
+wandb_name: smoke7B
+wandb_log_model:
+
+gradient_accumulation_steps: 32
+micro_batch_size: 1
+num_epochs: 2
+optimizer: adamw_bnb_8bit
+lr_scheduler: cosine
+learning_rate: 0.00001
+weight_decay: 0.05
+
+train_on_inputs: false
+group_by_length: false
+bf16: auto
+fp16:
+tf32: true
+
+gradient_checkpointing: true
+early_stopping_patience:
+resume_from_checkpoint: /workspace/axolotl/outputs/out/checkpoint-137
+auto_resume_from_checkpoints: true
+local_rank:
+logging_steps: 1
+xformers_attention:
+flash_attention: true
+
+warmup_ratio: 0.1
+evals_per_epoch: 4
+eval_table_size:
+eval_max_new_tokens: 128
+saves_per_epoch: 2
+
+debug:
+deepspeed:
+fsdp:
+fsdp_config:
+
+special_tokens:
+  pad_token: <pad>
+
+
+```
+
+</details><br>
+
+# outputs/out
+
+This model is a fine-tuned version of [FourOhFour/Vapor_7B](https://huggingface.co/FourOhFour/Vapor_7B) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.4023
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1e-05
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
+- gradient_accumulation_steps: 32
+- total_train_batch_size: 64
+- total_eval_batch_size: 2
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 54
+- num_epochs: 2
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 1.539         | 0.0037 | 1    | 1.5559          |
+| 1.562         | 0.2528 | 69   | 1.4611          |
+| 1.4928        | 0.5056 | 138  | 1.4304          |
+| 1.4968        | 0.7583 | 207  | 1.4155          |
+| 1.4817        | 1.0108 | 276  | 1.4075          |
+| 1.4637        | 1.2640 | 345  | 1.4038          |
+| 1.4701        | 1.5171 | 414  | 1.4026          |
+| 1.4657        | 1.7703 | 483  | 1.4023          |
+
+
+### Framework versions
+
+- Transformers 4.45.0.dev0
+- Pytorch 2.4.0+cu121
+- Datasets 2.21.0
+- Tokenizers 0.19.1

added_tokens.json

@@ -0,0 +1,25 @@
+{
+  "</tool_call>": 151658,
+  "<pad>": 151665,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "FourOhFour/Vapor_7B",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.0.dev0",
+  "use_cache": false,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.45.0.dev0"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67c7f5676a5ceee32f391e89de2c640cd0a90ff6e1565a4b64bf76343eaf525c
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3689970c531613dadc77b3b8face7971209cbe945d50ef2637e28cb5b2e98a7
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59d86027ae9023bc9dcc996a3686c3f2627bfb07e1992439d05e27499cc4b3f2
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db06fb89f0c58dea8415c80807be4faba7a250c809460c4d793e1fe56470c653
+size 1089994880

model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "total_size": 15231233024
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00003-of-00004.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,215 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<pad>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,3919 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0014906547414286,
+  "eval_steps": 69,
+  "global_step": 546,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.003663423010875787,
+      "grad_norm": 1.5390625,
+      "learning_rate": 1.8518518518518518e-07,
+      "loss": 1.539,
+      "step": 1
+    },
+    {
+      "epoch": 0.003663423010875787,
+      "eval_loss": 1.5559252500534058,
+      "eval_runtime": 86.4411,
+      "eval_samples_per_second": 8.966,
+      "eval_steps_per_second": 4.489,
+      "step": 1
+    },
+    {
+      "epoch": 0.007326846021751574,
+      "grad_norm": 1.6796875,
+      "learning_rate": 3.7037037037037036e-07,
+      "loss": 1.6519,
+      "step": 2
+    },
+    {
+      "epoch": 0.010990269032627361,
+      "grad_norm": 1.6015625,
+      "learning_rate": 5.555555555555555e-07,
+      "loss": 1.6261,
+      "step": 3
+    },
+    {
+      "epoch": 0.014653692043503148,
+      "grad_norm": 1.5625,
+      "learning_rate": 7.407407407407407e-07,
+      "loss": 1.6201,
+      "step": 4
+    },
+    {
+      "epoch": 0.018317115054378934,
+      "grad_norm": 1.5078125,
+      "learning_rate": 9.259259259259259e-07,
+      "loss": 1.6406,
+      "step": 5
+    },
+    {
+      "epoch": 0.021980538065254723,
+      "grad_norm": 1.484375,
+      "learning_rate": 1.111111111111111e-06,
+      "loss": 1.6432,
+      "step": 6
+    },
+    {
+      "epoch": 0.025643961076130508,
+      "grad_norm": 1.5,
+      "learning_rate": 1.2962962962962962e-06,
+      "loss": 1.6198,
+      "step": 7
+    },
+    {
+      "epoch": 0.029307384087006297,
+      "grad_norm": 1.4453125,
+      "learning_rate": 1.4814814814814815e-06,
+      "loss": 1.6053,
+      "step": 8
+    },
+    {
+      "epoch": 0.03297080709788208,
+      "grad_norm": 1.4609375,
+      "learning_rate": 1.6666666666666667e-06,
+      "loss": 1.5996,
+      "step": 9
+    },
+    {
+      "epoch": 0.03663423010875787,
+      "grad_norm": 1.359375,
+      "learning_rate": 1.8518518518518519e-06,
+      "loss": 1.5756,
+      "step": 10
+    },
+    {
+      "epoch": 0.04029765311963366,
+      "grad_norm": 1.3046875,
+      "learning_rate": 2.037037037037037e-06,
+      "loss": 1.6125,
+      "step": 11
+    },
+    {
+      "epoch": 0.043961076130509445,
+      "grad_norm": 1.296875,
+      "learning_rate": 2.222222222222222e-06,
+      "loss": 1.6129,
+      "step": 12
+    },
+    {
+      "epoch": 0.04762449914138523,
+      "grad_norm": 1.265625,
+      "learning_rate": 2.4074074074074075e-06,
+      "loss": 1.6614,
+      "step": 13
+    },
+    {
+      "epoch": 0.051287922152261016,
+      "grad_norm": 1.5546875,
+      "learning_rate": 2.5925925925925925e-06,
+      "loss": 1.5732,
+      "step": 14
+    },
+    {
+      "epoch": 0.05495134516313681,
+      "grad_norm": 1.2578125,
+      "learning_rate": 2.7777777777777783e-06,
+      "loss": 1.6096,
+      "step": 15
+    },
+    {
+      "epoch": 0.058614768174012594,
+      "grad_norm": 1.109375,
+      "learning_rate": 2.962962962962963e-06,
+      "loss": 1.6093,
+      "step": 16
+    },
+    {
+      "epoch": 0.06227819118488838,
+      "grad_norm": 1.1328125,
+      "learning_rate": 3.1481481481481483e-06,
+      "loss": 1.5846,
+      "step": 17
+    },
+    {
+      "epoch": 0.06594161419576416,
+      "grad_norm": 1.03125,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 1.6201,
+      "step": 18
+    },
+    {
+      "epoch": 0.06960503720663995,
+      "grad_norm": 1.15625,
+      "learning_rate": 3.5185185185185187e-06,
+      "loss": 1.6206,
+      "step": 19
+    },
+    {
+      "epoch": 0.07326846021751574,
+      "grad_norm": 1.09375,
+      "learning_rate": 3.7037037037037037e-06,
+      "loss": 1.6238,
+      "step": 20
+    },
+    {
+      "epoch": 0.07693188322839153,
+      "grad_norm": 1.21875,
+      "learning_rate": 3.88888888888889e-06,
+      "loss": 1.6347,
+      "step": 21
+    },
+    {
+      "epoch": 0.08059530623926732,
+      "grad_norm": 1.0390625,
+      "learning_rate": 4.074074074074074e-06,
+      "loss": 1.6516,
+      "step": 22
+    },
+    {
+      "epoch": 0.0842587292501431,
+      "grad_norm": 1.078125,
+      "learning_rate": 4.2592592592592596e-06,
+      "loss": 1.6333,
+      "step": 23
+    },
+    {
+      "epoch": 0.08792215226101889,
+      "grad_norm": 0.98046875,
+      "learning_rate": 4.444444444444444e-06,
+      "loss": 1.6349,
+      "step": 24
+    },
+    {
+      "epoch": 0.09158557527189468,
+      "grad_norm": 0.9609375,
+      "learning_rate": 4.62962962962963e-06,
+      "loss": 1.6026,
+      "step": 25
+    },
+    {
+      "epoch": 0.09524899828277046,
+      "grad_norm": 0.93359375,
+      "learning_rate": 4.814814814814815e-06,
+      "loss": 1.5571,
+      "step": 26
+    },
+    {
+      "epoch": 0.09891242129364625,
+      "grad_norm": 0.9609375,
+      "learning_rate": 5e-06,
+      "loss": 1.582,
+      "step": 27
+    },
+    {
+      "epoch": 0.10257584430452203,
+      "grad_norm": 0.97265625,
+      "learning_rate": 5.185185185185185e-06,
+      "loss": 1.6034,
+      "step": 28
+    },
+    {
+      "epoch": 0.10623926731539783,
+      "grad_norm": 0.93359375,
+      "learning_rate": 5.370370370370371e-06,
+      "loss": 1.5796,
+      "step": 29
+    },
+    {
+      "epoch": 0.10990269032627362,
+      "grad_norm": 0.9140625,
+      "learning_rate": 5.555555555555557e-06,
+      "loss": 1.5657,
+      "step": 30
+    },
+    {
+      "epoch": 0.1135661133371494,
+      "grad_norm": 0.91015625,
+      "learning_rate": 5.740740740740741e-06,
+      "loss": 1.6262,
+      "step": 31
+    },
+    {
+      "epoch": 0.11722953634802519,
+      "grad_norm": 0.95703125,
+      "learning_rate": 5.925925925925926e-06,
+      "loss": 1.5697,
+      "step": 32
+    },
+    {
+      "epoch": 0.12089295935890097,
+      "grad_norm": 0.85546875,
+      "learning_rate": 6.111111111111112e-06,
+      "loss": 1.5783,
+      "step": 33
+    },
+    {
+      "epoch": 0.12455638236977676,
+      "grad_norm": 0.83203125,
+      "learning_rate": 6.296296296296297e-06,
+      "loss": 1.5434,
+      "step": 34
+    },
+    {
+      "epoch": 0.12821980538065256,
+      "grad_norm": 0.83203125,
+      "learning_rate": 6.481481481481482e-06,
+      "loss": 1.4929,
+      "step": 35
+    },
+    {
+      "epoch": 0.13188322839152833,
+      "grad_norm": 0.83984375,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 1.5474,
+      "step": 36
+    },
+    {
+      "epoch": 0.13554665140240413,
+      "grad_norm": 0.79296875,
+      "learning_rate": 6.851851851851853e-06,
+      "loss": 1.5836,
+      "step": 37
+    },
+    {
+      "epoch": 0.1392100744132799,
+      "grad_norm": 0.91015625,
+      "learning_rate": 7.0370370370370375e-06,
+      "loss": 1.5739,
+      "step": 38
+    },
+    {
+      "epoch": 0.1428734974241557,
+      "grad_norm": 0.78515625,
+      "learning_rate": 7.222222222222223e-06,
+      "loss": 1.5365,
+      "step": 39
+    },
+    {
+      "epoch": 0.14653692043503147,
+      "grad_norm": 0.82421875,
+      "learning_rate": 7.4074074074074075e-06,
+      "loss": 1.5932,
+      "step": 40
+    },
+    {
+      "epoch": 0.15020034344590727,
+      "grad_norm": 0.80078125,
+      "learning_rate": 7.592592592592594e-06,
+      "loss": 1.5309,
+      "step": 41
+    },
+    {
+      "epoch": 0.15386376645678307,
+      "grad_norm": 0.8203125,
+      "learning_rate": 7.77777777777778e-06,
+      "loss": 1.5373,
+      "step": 42
+    },
+    {
+      "epoch": 0.15752718946765884,
+      "grad_norm": 0.78125,
+      "learning_rate": 7.962962962962963e-06,
+      "loss": 1.5511,
+      "step": 43
+    },
+    {
+      "epoch": 0.16119061247853464,
+      "grad_norm": 0.83203125,
+      "learning_rate": 8.148148148148148e-06,
+      "loss": 1.5749,
+      "step": 44
+    },
+    {
+      "epoch": 0.1648540354894104,
+      "grad_norm": 1.375,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 1.5303,
+      "step": 45
+    },
+    {
+      "epoch": 0.1685174585002862,
+      "grad_norm": 0.8203125,
+      "learning_rate": 8.518518518518519e-06,
+      "loss": 1.6222,
+      "step": 46
+    },
+    {
+      "epoch": 0.17218088151116198,
+      "grad_norm": 0.87109375,
+      "learning_rate": 8.703703703703705e-06,
+      "loss": 1.5169,
+      "step": 47
+    },
+    {
+      "epoch": 0.17584430452203778,
+      "grad_norm": 0.8671875,
+      "learning_rate": 8.888888888888888e-06,
+      "loss": 1.5518,
+      "step": 48
+    },
+    {
+      "epoch": 0.17950772753291355,
+      "grad_norm": 0.8359375,
+      "learning_rate": 9.074074074074075e-06,
+      "loss": 1.5487,
+      "step": 49
+    },
+    {
+      "epoch": 0.18317115054378935,
+      "grad_norm": 0.8515625,
+      "learning_rate": 9.25925925925926e-06,
+      "loss": 1.5546,
+      "step": 50
+    },
+    {
+      "epoch": 0.18683457355466515,
+      "grad_norm": 0.78125,
+      "learning_rate": 9.444444444444445e-06,
+      "loss": 1.5225,
+      "step": 51
+    },
+    {
+      "epoch": 0.19049799656554092,
+      "grad_norm": 0.73046875,
+      "learning_rate": 9.62962962962963e-06,
+      "loss": 1.5685,
+      "step": 52
+    },
+    {
+      "epoch": 0.19416141957641672,
+      "grad_norm": 0.73828125,
+      "learning_rate": 9.814814814814815e-06,
+      "loss": 1.5496,
+      "step": 53
+    },
+    {
+      "epoch": 0.1978248425872925,
+      "grad_norm": 0.83984375,
+      "learning_rate": 1e-05,
+      "loss": 1.4815,
+      "step": 54
+    },
+    {
+      "epoch": 0.2014882655981683,
+      "grad_norm": 0.71484375,
+      "learning_rate": 9.999898068580346e-06,
+      "loss": 1.5171,
+      "step": 55
+    },
+    {
+      "epoch": 0.20515168860904406,
+      "grad_norm": 0.7734375,
+      "learning_rate": 9.999592278477389e-06,
+      "loss": 1.5559,
+      "step": 56
+    },
+    {
+      "epoch": 0.20881511161991986,
+      "grad_norm": 0.76171875,
+      "learning_rate": 9.999082642158972e-06,
+      "loss": 1.5364,
+      "step": 57
+    },
+    {
+      "epoch": 0.21247853463079566,
+      "grad_norm": 0.76171875,
+      "learning_rate": 9.998369180404283e-06,
+      "loss": 1.5392,
+      "step": 58
+    },
+    {
+      "epoch": 0.21614195764167143,
+      "grad_norm": 0.7109375,
+      "learning_rate": 9.997451922302987e-06,
+      "loss": 1.5376,
+      "step": 59
+    },
+    {
+      "epoch": 0.21980538065254723,
+      "grad_norm": 0.765625,
+      "learning_rate": 9.99633090525405e-06,
+      "loss": 1.5128,
+      "step": 60
+    },
+    {
+      "epoch": 0.223468803663423,
+      "grad_norm": 0.78515625,
+      "learning_rate": 9.99500617496422e-06,
+      "loss": 1.4922,
+      "step": 61
+    },
+    {
+      "epoch": 0.2271322266742988,
+      "grad_norm": 0.75,
+      "learning_rate": 9.993477785446151e-06,
+      "loss": 1.5314,
+      "step": 62
+    },
+    {
+      "epoch": 0.23079564968517458,
+      "grad_norm": 0.78515625,
+      "learning_rate": 9.991745799016206e-06,
+      "loss": 1.5243,
+      "step": 63
+    },
+    {
+      "epoch": 0.23445907269605037,
+      "grad_norm": 0.73828125,
+      "learning_rate": 9.989810286291923e-06,
+      "loss": 1.5216,
+      "step": 64
+    },
+    {
+      "epoch": 0.23812249570692615,
+      "grad_norm": 0.76953125,
+      "learning_rate": 9.987671326189123e-06,
+      "loss": 1.4933,
+      "step": 65
+    },
+    {
+      "epoch": 0.24178591871780195,
+      "grad_norm": 0.73828125,
+      "learning_rate": 9.985329005918702e-06,
+      "loss": 1.5784,
+      "step": 66
+    },
+    {
+      "epoch": 0.24544934172867774,
+      "grad_norm": 0.73046875,
+      "learning_rate": 9.982783420983075e-06,
+      "loss": 1.5277,
+      "step": 67
+    },
+    {
+      "epoch": 0.24911276473955352,
+      "grad_norm": 0.765625,
+      "learning_rate": 9.980034675172274e-06,
+      "loss": 1.5479,
+      "step": 68
+    },
+    {
+      "epoch": 0.2527761877504293,
+      "grad_norm": 0.75390625,
+      "learning_rate": 9.977082880559725e-06,
+      "loss": 1.562,
+      "step": 69
+    },
+    {
+      "epoch": 0.2527761877504293,
+      "eval_loss": 1.4610767364501953,
+      "eval_runtime": 86.5737,
+      "eval_samples_per_second": 8.952,
+      "eval_steps_per_second": 4.482,
+      "step": 69
+    },
+    {
+      "epoch": 0.2564396107613051,
+      "grad_norm": 0.7421875,
+      "learning_rate": 9.973928157497675e-06,
+      "loss": 1.5046,
+      "step": 70
+    },
+    {
+      "epoch": 0.26010303377218086,
+      "grad_norm": 0.828125,
+      "learning_rate": 9.970570634612282e-06,
+      "loss": 1.5485,
+      "step": 71
+    },
+    {
+      "epoch": 0.26376645678305666,
+      "grad_norm": 0.73046875,
+      "learning_rate": 9.967010448798376e-06,
+      "loss": 1.5255,
+      "step": 72
+    },
+    {
+      "epoch": 0.26742987979393246,
+      "grad_norm": 0.73828125,
+      "learning_rate": 9.963247745213876e-06,
+      "loss": 1.5434,
+      "step": 73
+    },
+    {
+      "epoch": 0.27109330280480826,
+      "grad_norm": 0.85546875,
+      "learning_rate": 9.959282677273869e-06,
+      "loss": 1.5317,
+      "step": 74
+    },
+    {
+      "epoch": 0.27475672581568406,
+      "grad_norm": 0.74609375,
+      "learning_rate": 9.955115406644357e-06,
+      "loss": 1.5696,
+      "step": 75
+    },
+    {
+      "epoch": 0.2784201488265598,
+      "grad_norm": 0.91015625,
+      "learning_rate": 9.950746103235663e-06,
+      "loss": 1.59,
+      "step": 76
+    },
+    {
+      "epoch": 0.2820835718374356,
+      "grad_norm": 1.0703125,
+      "learning_rate": 9.946174945195508e-06,
+      "loss": 1.4958,
+      "step": 77
+    },
+    {
+      "epoch": 0.2857469948483114,
+      "grad_norm": 0.76171875,
+      "learning_rate": 9.941402118901743e-06,
+      "loss": 1.5623,
+      "step": 78
+    },
+    {
+      "epoch": 0.2894104178591872,
+      "grad_norm": 0.78125,
+      "learning_rate": 9.936427818954753e-06,
+      "loss": 1.5951,
+      "step": 79
+    },
+    {
+      "epoch": 0.29307384087006294,
+      "grad_norm": 0.734375,
+      "learning_rate": 9.931252248169518e-06,
+      "loss": 1.5174,
+      "step": 80
+    },
+    {
+      "epoch": 0.29673726388093874,
+      "grad_norm": 0.74609375,
+      "learning_rate": 9.92587561756735e-06,
+      "loss": 1.5268,
+      "step": 81
+    },
+    {
+      "epoch": 0.30040068689181454,
+      "grad_norm": 0.78125,
+      "learning_rate": 9.920298146367287e-06,
+      "loss": 1.5133,
+      "step": 82
+    },
+    {
+      "epoch": 0.30406410990269034,
+      "grad_norm": 0.73046875,
+      "learning_rate": 9.91452006197715e-06,
+      "loss": 1.4929,
+      "step": 83
+    },
+    {
+      "epoch": 0.30772753291356614,
+      "grad_norm": 0.77734375,
+      "learning_rate": 9.908541599984276e-06,
+      "loss": 1.4949,
+      "step": 84
+    },
+    {
+      "epoch": 0.3113909559244419,
+      "grad_norm": 0.73046875,
+      "learning_rate": 9.902363004145914e-06,
+      "loss": 1.5007,
+      "step": 85
+    },
+    {
+      "epoch": 0.3150543789353177,
+      "grad_norm": 0.7734375,
+      "learning_rate": 9.895984526379282e-06,
+      "loss": 1.5442,
+      "step": 86
+    },
+    {
+      "epoch": 0.3187178019461935,
+      "grad_norm": 0.83203125,
+      "learning_rate": 9.889406426751296e-06,
+      "loss": 1.4796,
+      "step": 87
+    },
+    {
+      "epoch": 0.3223812249570693,
+      "grad_norm": 0.8125,
+      "learning_rate": 9.882628973467972e-06,
+      "loss": 1.5317,
+      "step": 88
+    },
+    {
+      "epoch": 0.326044647967945,
+      "grad_norm": 0.7421875,
+      "learning_rate": 9.875652442863483e-06,
+      "loss": 1.511,
+      "step": 89
+    },
+    {
+      "epoch": 0.3297080709788208,
+      "grad_norm": 0.8046875,
+      "learning_rate": 9.868477119388897e-06,
+      "loss": 1.5016,
+      "step": 90
+    },
+    {
+      "epoch": 0.3333714939896966,
+      "grad_norm": 0.76953125,
+      "learning_rate": 9.861103295600574e-06,
+      "loss": 1.5879,
+      "step": 91
+    },
+    {
+      "epoch": 0.3370349170005724,
+      "grad_norm": 0.859375,
+      "learning_rate": 9.853531272148248e-06,
+      "loss": 1.5265,
+      "step": 92
+    },
+    {
+      "epoch": 0.3406983400114482,
+      "grad_norm": 0.75,
+      "learning_rate": 9.84576135776276e-06,
+      "loss": 1.5244,
+      "step": 93
+    },
+    {
+      "epoch": 0.34436176302232396,
+      "grad_norm": 0.74609375,
+      "learning_rate": 9.837793869243468e-06,
+      "loss": 1.5531,
+      "step": 94
+    },
+    {
+      "epoch": 0.34802518603319976,
+      "grad_norm": 0.75390625,
+      "learning_rate": 9.829629131445342e-06,
+      "loss": 1.5195,
+      "step": 95
+    },
+    {
+      "epoch": 0.35168860904407556,
+      "grad_norm": 0.7109375,
+      "learning_rate": 9.821267477265705e-06,
+      "loss": 1.54,
+      "step": 96
+    },
+    {
+      "epoch": 0.35535203205495136,
+      "grad_norm": 0.67578125,
+      "learning_rate": 9.812709247630671e-06,
+      "loss": 1.4454,
+      "step": 97
+    },
+    {
+      "epoch": 0.3590154550658271,
+      "grad_norm": 0.765625,
+      "learning_rate": 9.803954791481239e-06,
+      "loss": 1.4574,
+      "step": 98
+    },
+    {
+      "epoch": 0.3626788780767029,
+      "grad_norm": 0.73828125,
+      "learning_rate": 9.795004465759067e-06,
+      "loss": 1.5201,
+      "step": 99
+    },
+    {
+      "epoch": 0.3663423010875787,
+      "grad_norm": 0.73828125,
+      "learning_rate": 9.785858635391913e-06,
+      "loss": 1.4939,
+      "step": 100
+    },
+    {
+      "epoch": 0.3700057240984545,
+      "grad_norm": 0.6953125,
+      "learning_rate": 9.776517673278772e-06,
+      "loss": 1.5067,
+      "step": 101
+    },
+    {
+      "epoch": 0.3736691471093303,
+      "grad_norm": 0.75390625,
+      "learning_rate": 9.766981960274653e-06,
+      "loss": 1.4932,
+      "step": 102
+    },
+    {
+      "epoch": 0.37733257012020605,
+      "grad_norm": 0.78125,
+      "learning_rate": 9.757251885175063e-06,
+      "loss": 1.4845,
+      "step": 103
+    },
+    {
+      "epoch": 0.38099599313108184,
+      "grad_norm": 0.7109375,
+      "learning_rate": 9.747327844700147e-06,
+      "loss": 1.5307,
+      "step": 104
+    },
+    {
+      "epoch": 0.38465941614195764,
+      "grad_norm": 0.75390625,
+      "learning_rate": 9.737210243478522e-06,
+      "loss": 1.4548,
+      "step": 105
+    },
+    {
+      "epoch": 0.38832283915283344,
+      "grad_norm": 0.72265625,
+      "learning_rate": 9.726899494030768e-06,
+      "loss": 1.4711,
+      "step": 106
+    },
+    {
+      "epoch": 0.39198626216370924,
+      "grad_norm": 0.70703125,
+      "learning_rate": 9.716396016752616e-06,
+      "loss": 1.4636,
+      "step": 107
+    },
+    {
+      "epoch": 0.395649685174585,
+      "grad_norm": 0.7421875,
+      "learning_rate": 9.705700239897809e-06,
+      "loss": 1.499,
+      "step": 108
+    },
+    {
+      "epoch": 0.3993131081854608,
+      "grad_norm": 0.77734375,
+      "learning_rate": 9.694812599560632e-06,
+      "loss": 1.5242,
+      "step": 109
+    },
+    {
+      "epoch": 0.4029765311963366,
+      "grad_norm": 0.75390625,
+      "learning_rate": 9.68373353965814e-06,
+      "loss": 1.5273,
+      "step": 110
+    },
+    {
+      "epoch": 0.4066399542072124,
+      "grad_norm": 0.71875,
+      "learning_rate": 9.672463511912056e-06,
+      "loss": 1.5333,
+      "step": 111
+    },
+    {
+      "epoch": 0.41030337721808813,
+      "grad_norm": 0.703125,
+      "learning_rate": 9.66100297583035e-06,
+      "loss": 1.4781,
+      "step": 112
+    },
+    {
+      "epoch": 0.4139668002289639,
+      "grad_norm": 0.69921875,
+      "learning_rate": 9.649352398688506e-06,
+      "loss": 1.5159,
+      "step": 113
+    },
+    {
+      "epoch": 0.4176302232398397,
+      "grad_norm": 0.703125,
+      "learning_rate": 9.637512255510475e-06,
+      "loss": 1.5112,
+      "step": 114
+    },
+    {
+      "epoch": 0.4212936462507155,
+      "grad_norm": 0.79296875,
+      "learning_rate": 9.625483029049295e-06,
+      "loss": 1.5399,
+      "step": 115
+    },
+    {
+      "epoch": 0.4249570692615913,
+      "grad_norm": 0.73828125,
+      "learning_rate": 9.613265209767417e-06,
+      "loss": 1.521,
+      "step": 116
+    },
+    {
+      "epoch": 0.42862049227246707,
+      "grad_norm": 0.7265625,
+      "learning_rate": 9.600859295816708e-06,
+      "loss": 1.4956,
+      "step": 117
+    },
+    {
+      "epoch": 0.43228391528334287,
+      "grad_norm": 0.7109375,
+      "learning_rate": 9.588265793018141e-06,
+      "loss": 1.4859,
+      "step": 118
+    },
+    {
+      "epoch": 0.43594733829421867,
+      "grad_norm": 0.68359375,
+      "learning_rate": 9.575485214841158e-06,
+      "loss": 1.4867,
+      "step": 119
+    },
+    {
+      "epoch": 0.43961076130509447,
+      "grad_norm": 0.85546875,
+      "learning_rate": 9.562518082382751e-06,
+      "loss": 1.488,
+      "step": 120
+    },
+    {
+      "epoch": 0.4432741843159702,
+      "grad_norm": 0.79296875,
+      "learning_rate": 9.54936492434621e-06,
+      "loss": 1.5129,
+      "step": 121
+    },
+    {
+      "epoch": 0.446937607326846,
+      "grad_norm": 0.7578125,
+      "learning_rate": 9.536026277019562e-06,
+      "loss": 1.5484,
+      "step": 122
+    },
+    {
+      "epoch": 0.4506010303377218,
+      "grad_norm": 0.71875,
+      "learning_rate": 9.522502684253709e-06,
+      "loss": 1.5017,
+      "step": 123
+    },
+    {
+      "epoch": 0.4542644533485976,
+      "grad_norm": 0.73828125,
+      "learning_rate": 9.508794697440257e-06,
+      "loss": 1.4869,
+      "step": 124
+    },
+    {
+      "epoch": 0.4579278763594734,
+      "grad_norm": 0.7578125,
+      "learning_rate": 9.494902875489031e-06,
+      "loss": 1.5279,
+      "step": 125
+    },
+    {
+      "epoch": 0.46159129937034915,
+      "grad_norm": 0.7109375,
+      "learning_rate": 9.480827784805278e-06,
+      "loss": 1.506,
+      "step": 126
+    },
+    {
+      "epoch": 0.46525472238122495,
+      "grad_norm": 0.7578125,
+      "learning_rate": 9.466569999266595e-06,
+      "loss": 1.4857,
+      "step": 127
+    },
+    {
+      "epoch": 0.46891814539210075,
+      "grad_norm": 0.69140625,
+      "learning_rate": 9.452130100199504e-06,
+      "loss": 1.5652,
+      "step": 128
+    },
+    {
+      "epoch": 0.47258156840297655,
+      "grad_norm": 0.75,
+      "learning_rate": 9.437508676355774e-06,
+      "loss": 1.5093,
+      "step": 129
+    },
+    {
+      "epoch": 0.4762449914138523,
+      "grad_norm": 0.75,
+      "learning_rate": 9.422706323888398e-06,
+      "loss": 1.4592,
+      "step": 130
+    },
+    {
+      "epoch": 0.4799084144247281,
+      "grad_norm": 0.734375,
+      "learning_rate": 9.407723646327299e-06,
+      "loss": 1.4626,
+      "step": 131
+    },
+    {
+      "epoch": 0.4835718374356039,
+      "grad_norm": 0.68359375,
+      "learning_rate": 9.392561254554712e-06,
+      "loss": 1.5082,
+      "step": 132
+    },
+    {
+      "epoch": 0.4872352604464797,
+      "grad_norm": 0.703125,
+      "learning_rate": 9.377219766780288e-06,
+      "loss": 1.5389,
+      "step": 133
+    },
+    {
+      "epoch": 0.4908986834573555,
+      "grad_norm": 0.66015625,
+      "learning_rate": 9.361699808515877e-06,
+      "loss": 1.4567,
+      "step": 134
+    },
+    {
+      "epoch": 0.49456210646823123,
+      "grad_norm": 0.6796875,
+      "learning_rate": 9.346002012550027e-06,
+      "loss": 1.4903,
+      "step": 135
+    },
+    {
+      "epoch": 0.49822552947910703,
+      "grad_norm": 0.69921875,
+      "learning_rate": 9.330127018922195e-06,
+      "loss": 1.5068,
+      "step": 136
+    },
+    {
+      "epoch": 0.5018889524899828,
+      "grad_norm": 0.6953125,
+      "learning_rate": 9.314075474896631e-06,
+      "loss": 1.5039,
+      "step": 137
+    },
+    {
+      "epoch": 0.5055523755008586,
+      "grad_norm": 0.7265625,
+      "learning_rate": 9.297848034936007e-06,
+      "loss": 1.4928,
+      "step": 138
+    },
+    {
+      "epoch": 0.5055523755008586,
+      "eval_loss": 1.4303784370422363,
+      "eval_runtime": 86.5297,
+      "eval_samples_per_second": 8.956,
+      "eval_steps_per_second": 4.484,
+      "step": 138
+    },
+    {
+      "epoch": 0.5092157985117344,
+      "grad_norm": 0.734375,
+      "learning_rate": 9.281445360674717e-06,
+      "loss": 1.5562,
+      "step": 139
+    },
+    {
+      "epoch": 0.5128792215226102,
+      "grad_norm": 0.6875,
+      "learning_rate": 9.264868120891913e-06,
+      "loss": 1.4492,
+      "step": 140
+    },
+    {
+      "epoch": 0.516542644533486,
+      "grad_norm": 0.69140625,
+      "learning_rate": 9.24811699148423e-06,
+      "loss": 1.4349,
+      "step": 141
+    },
+    {
+      "epoch": 0.5202060675443617,
+      "grad_norm": 0.67578125,
+      "learning_rate": 9.231192655438222e-06,
+      "loss": 1.479,
+      "step": 142
+    },
+    {
+      "epoch": 0.5238694905552376,
+      "grad_norm": 0.765625,
+      "learning_rate": 9.214095802802533e-06,
+      "loss": 1.5113,
+      "step": 143
+    },
+    {
+      "epoch": 0.5275329135661133,
+      "grad_norm": 0.75,
+      "learning_rate": 9.196827130659752e-06,
+      "loss": 1.5157,
+      "step": 144
+    },
+    {
+      "epoch": 0.5311963365769892,
+      "grad_norm": 0.69921875,
+      "learning_rate": 9.179387343097978e-06,
+      "loss": 1.4772,
+      "step": 145
+    },
+    {
+      "epoch": 0.5348597595878649,
+      "grad_norm": 0.74609375,
+      "learning_rate": 9.161777151182137e-06,
+      "loss": 1.5372,
+      "step": 146
+    },
+    {
+      "epoch": 0.5385231825987407,
+      "grad_norm": 0.6796875,
+      "learning_rate": 9.143997272924974e-06,
+      "loss": 1.4623,
+      "step": 147
+    },
+    {
+      "epoch": 0.5421866056096165,
+      "grad_norm": 0.7109375,
+      "learning_rate": 9.12604843325778e-06,
+      "loss": 1.5204,
+      "step": 148
+    },
+    {
+      "epoch": 0.5458500286204923,
+      "grad_norm": 0.72265625,
+      "learning_rate": 9.10793136400084e-06,
+      "loss": 1.5264,
+      "step": 149
+    },
+    {
+      "epoch": 0.5495134516313681,
+      "grad_norm": 0.796875,
+      "learning_rate": 9.089646803833589e-06,
+      "loss": 1.467,
+      "step": 150
+    },
+    {
+      "epoch": 0.5531768746422439,
+      "grad_norm": 0.6875,
+      "learning_rate": 9.071195498264497e-06,
+      "loss": 1.4847,
+      "step": 151
+    },
+    {
+      "epoch": 0.5568402976531196,
+      "grad_norm": 0.71875,
+      "learning_rate": 9.052578199600675e-06,
+      "loss": 1.4867,
+      "step": 152
+    },
+    {
+      "epoch": 0.5605037206639955,
+      "grad_norm": 0.73828125,
+      "learning_rate": 9.033795666917191e-06,
+      "loss": 1.49,
+      "step": 153
+    },
+    {
+      "epoch": 0.5641671436748712,
+      "grad_norm": 0.70703125,
+      "learning_rate": 9.014848666026138e-06,
+      "loss": 1.4984,
+      "step": 154
+    },
+    {
+      "epoch": 0.5678305666857469,
+      "grad_norm": 0.82421875,
+      "learning_rate": 8.995737969445395e-06,
+      "loss": 1.4957,
+      "step": 155
+    },
+    {
+      "epoch": 0.5714939896966228,
+      "grad_norm": 0.70703125,
+      "learning_rate": 8.976464356367133e-06,
+      "loss": 1.4975,
+      "step": 156
+    },
+    {
+      "epoch": 0.5751574127074985,
+      "grad_norm": 0.7578125,
+      "learning_rate": 8.957028612626051e-06,
+      "loss": 1.5144,
+      "step": 157
+    },
+    {
+      "epoch": 0.5788208357183744,
+      "grad_norm": 0.69140625,
+      "learning_rate": 8.937431530667329e-06,
+      "loss": 1.4688,
+      "step": 158
+    },
+    {
+      "epoch": 0.5824842587292501,
+      "grad_norm": 0.796875,
+      "learning_rate": 8.917673909514321e-06,
+      "loss": 1.4647,
+      "step": 159
+    },
+    {
+      "epoch": 0.5861476817401259,
+      "grad_norm": 0.69140625,
+      "learning_rate": 8.897756554735976e-06,
+      "loss": 1.5029,
+      "step": 160
+    },
+    {
+      "epoch": 0.5898111047510017,
+      "grad_norm": 0.71875,
+      "learning_rate": 8.877680278413995e-06,
+      "loss": 1.4559,
+      "step": 161
+    },
+    {
+      "epoch": 0.5934745277618775,
+      "grad_norm": 0.7265625,
+      "learning_rate": 8.857445899109716e-06,
+      "loss": 1.4876,
+      "step": 162
+    },
+    {
+      "epoch": 0.5971379507727533,
+      "grad_norm": 0.71484375,
+      "learning_rate": 8.83705424183074e-06,
+      "loss": 1.5204,
+      "step": 163
+    },
+    {
+      "epoch": 0.6008013737836291,
+      "grad_norm": 0.75390625,
+      "learning_rate": 8.8165061379973e-06,
+      "loss": 1.5099,
+      "step": 164
+    },
+    {
+      "epoch": 0.6044647967945048,
+      "grad_norm": 0.8203125,
+      "learning_rate": 8.795802425408352e-06,
+      "loss": 1.5189,
+      "step": 165
+    },
+    {
+      "epoch": 0.6081282198053807,
+      "grad_norm": 0.67578125,
+      "learning_rate": 8.774943948207427e-06,
+      "loss": 1.4384,
+      "step": 166
+    },
+    {
+      "epoch": 0.6117916428162564,
+      "grad_norm": 0.7109375,
+      "learning_rate": 8.753931556848195e-06,
+      "loss": 1.4618,
+      "step": 167
+    },
+    {
+      "epoch": 0.6154550658271323,
+      "grad_norm": 0.69140625,
+      "learning_rate": 8.732766108059814e-06,
+      "loss": 1.4531,
+      "step": 168
+    },
+    {
+      "epoch": 0.619118488838008,
+      "grad_norm": 0.71875,
+      "learning_rate": 8.711448464811978e-06,
+      "loss": 1.4737,
+      "step": 169
+    },
+    {
+      "epoch": 0.6227819118488838,
+      "grad_norm": 0.69921875,
+      "learning_rate": 8.689979496279747e-06,
+      "loss": 1.4604,
+      "step": 170
+    },
+    {
+      "epoch": 0.6264453348597596,
+      "grad_norm": 0.7734375,
+      "learning_rate": 8.668360077808093e-06,
+      "loss": 1.488,
+      "step": 171
+    },
+    {
+      "epoch": 0.6301087578706354,
+      "grad_norm": 0.8828125,
+      "learning_rate": 8.646591090876225e-06,
+      "loss": 1.4882,
+      "step": 172
+    },
+    {
+      "epoch": 0.6337721808815112,
+      "grad_norm": 0.76953125,
+      "learning_rate": 8.62467342306164e-06,
+      "loss": 1.4495,
+      "step": 173
+    },
+    {
+      "epoch": 0.637435603892387,
+      "grad_norm": 0.6953125,
+      "learning_rate": 8.602607968003935e-06,
+      "loss": 1.4671,
+      "step": 174
+    },
+    {
+      "epoch": 0.6410990269032627,
+      "grad_norm": 0.71484375,
+      "learning_rate": 8.580395625368377e-06,
+      "loss": 1.4682,
+      "step": 175
+    },
+    {
+      "epoch": 0.6447624499141386,
+      "grad_norm": 0.7734375,
+      "learning_rate": 8.558037300809209e-06,
+      "loss": 1.5226,
+      "step": 176
+    },
+    {
+      "epoch": 0.6484258729250143,
+      "grad_norm": 0.73046875,
+      "learning_rate": 8.535533905932739e-06,
+      "loss": 1.4958,
+      "step": 177
+    },
+    {
+      "epoch": 0.65208929593589,
+      "grad_norm": 0.85546875,
+      "learning_rate": 8.512886358260162e-06,
+      "loss": 1.4589,
+      "step": 178
+    },
+    {
+      "epoch": 0.6557527189467659,
+      "grad_norm": 0.6796875,
+      "learning_rate": 8.490095581190149e-06,
+      "loss": 1.4966,
+      "step": 179
+    },
+    {
+      "epoch": 0.6594161419576416,
+      "grad_norm": 0.73046875,
+      "learning_rate": 8.467162503961209e-06,
+      "loss": 1.4866,
+      "step": 180
+    },
+    {
+      "epoch": 0.6630795649685175,
+      "grad_norm": 0.6953125,
+      "learning_rate": 8.444088061613788e-06,
+      "loss": 1.4029,
+      "step": 181
+    },
+    {
+      "epoch": 0.6667429879793932,
+      "grad_norm": 0.7421875,
+      "learning_rate": 8.420873194952153e-06,
+      "loss": 1.4235,
+      "step": 182
+    },
+    {
+      "epoch": 0.670406410990269,
+      "grad_norm": 0.72265625,
+      "learning_rate": 8.39751885050603e-06,
+      "loss": 1.5138,
+      "step": 183
+    },
+    {
+      "epoch": 0.6740698340011448,
+      "grad_norm": 0.734375,
+      "learning_rate": 8.37402598049201e-06,
+      "loss": 1.4258,
+      "step": 184
+    },
+    {
+      "epoch": 0.6777332570120206,
+      "grad_norm": 0.6875,
+      "learning_rate": 8.350395542774737e-06,
+      "loss": 1.5137,
+      "step": 185
+    },
+    {
+      "epoch": 0.6813966800228964,
+      "grad_norm": 0.76171875,
+      "learning_rate": 8.326628500827826e-06,
+      "loss": 1.5015,
+      "step": 186
+    },
+    {
+      "epoch": 0.6850601030337722,
+      "grad_norm": 0.74609375,
+      "learning_rate": 8.302725823694619e-06,
+      "loss": 1.4839,
+      "step": 187
+    },
+    {
+      "epoch": 0.6887235260446479,
+      "grad_norm": 0.69921875,
+      "learning_rate": 8.278688485948634e-06,
+      "loss": 1.479,
+      "step": 188
+    },
+    {
+      "epoch": 0.6923869490555238,
+      "grad_norm": 0.69921875,
+      "learning_rate": 8.254517467653858e-06,
+      "loss": 1.5126,
+      "step": 189
+    },
+    {
+      "epoch": 0.6960503720663995,
+      "grad_norm": 0.67578125,
+      "learning_rate": 8.230213754324773e-06,
+      "loss": 1.4236,
+      "step": 190
+    },
+    {
+      "epoch": 0.6997137950772754,
+      "grad_norm": 0.6953125,
+      "learning_rate": 8.205778336886182e-06,
+      "loss": 1.4576,
+      "step": 191
+    },
+    {
+      "epoch": 0.7033772180881511,
+      "grad_norm": 0.68359375,
+      "learning_rate": 8.1812122116328e-06,
+      "loss": 1.4378,
+      "step": 192
+    },
+    {
+      "epoch": 0.7070406410990269,
+      "grad_norm": 0.7421875,
+      "learning_rate": 8.156516380188635e-06,
+      "loss": 1.4678,
+      "step": 193
+    },
+    {
+      "epoch": 0.7107040641099027,
+      "grad_norm": 0.734375,
+      "learning_rate": 8.131691849466154e-06,
+      "loss": 1.4711,
+      "step": 194
+    },
+    {
+      "epoch": 0.7143674871207785,
+      "grad_norm": 0.65625,
+      "learning_rate": 8.106739631625216e-06,
+      "loss": 1.4751,
+      "step": 195
+    },
+    {
+      "epoch": 0.7180309101316542,
+      "grad_norm": 0.8046875,
+      "learning_rate": 8.081660744031818e-06,
+      "loss": 1.4802,
+      "step": 196
+    },
+    {
+      "epoch": 0.7216943331425301,
+      "grad_norm": 0.6953125,
+      "learning_rate": 8.056456209216609e-06,
+      "loss": 1.4942,
+      "step": 197
+    },
+    {
+      "epoch": 0.7253577561534058,
+      "grad_norm": 0.6875,
+      "learning_rate": 8.031127054833192e-06,
+      "loss": 1.4993,
+      "step": 198
+    },
+    {
+      "epoch": 0.7290211791642817,
+      "grad_norm": 0.71484375,
+      "learning_rate": 8.005674313616231e-06,
+      "loss": 1.4589,
+      "step": 199
+    },
+    {
+      "epoch": 0.7326846021751574,
+      "grad_norm": 0.6953125,
+      "learning_rate": 7.98009902333935e-06,
+      "loss": 1.535,
+      "step": 200
+    },
+    {
+      "epoch": 0.7363480251860332,
+      "grad_norm": 0.6953125,
+      "learning_rate": 7.954402226772804e-06,
+      "loss": 1.4564,
+      "step": 201
+    },
+    {
+      "epoch": 0.740011448196909,
+      "grad_norm": 0.75390625,
+      "learning_rate": 7.928584971640974e-06,
+      "loss": 1.5054,
+      "step": 202
+    },
+    {
+      "epoch": 0.7436748712077847,
+      "grad_norm": 0.74609375,
+      "learning_rate": 7.90264831057965e-06,
+      "loss": 1.4671,
+      "step": 203
+    },
+    {
+      "epoch": 0.7473382942186606,
+      "grad_norm": 0.8046875,
+      "learning_rate": 7.876593301093104e-06,
+      "loss": 1.4747,
+      "step": 204
+    },
+    {
+      "epoch": 0.7510017172295363,
+      "grad_norm": 0.79296875,
+      "learning_rate": 7.850421005510977e-06,
+      "loss": 1.4493,
+      "step": 205
+    },
+    {
+      "epoch": 0.7546651402404121,
+      "grad_norm": 0.71875,
+      "learning_rate": 7.824132490944968e-06,
+      "loss": 1.4558,
+      "step": 206
+    },
+    {
+      "epoch": 0.758328563251288,
+      "grad_norm": 0.7265625,
+      "learning_rate": 7.797728829245321e-06,
+      "loss": 1.4968,
+      "step": 207
+    },
+    {
+      "epoch": 0.758328563251288,
+      "eval_loss": 1.4155006408691406,
+      "eval_runtime": 86.4267,
+      "eval_samples_per_second": 8.967,
+      "eval_steps_per_second": 4.489,
+      "step": 207
+    },
+    {
+      "epoch": 0.7619919862621637,
+      "grad_norm": 0.67578125,
+      "learning_rate": 7.771211096957125e-06,
+      "loss": 1.5118,
+      "step": 208
+    },
+    {
+      "epoch": 0.7656554092730395,
+      "grad_norm": 0.7109375,
+      "learning_rate": 7.744580375276416e-06,
+      "loss": 1.4467,
+      "step": 209
+    },
+    {
+      "epoch": 0.7693188322839153,
+      "grad_norm": 0.72265625,
+      "learning_rate": 7.717837750006106e-06,
+      "loss": 1.434,
+      "step": 210
+    },
+    {
+      "epoch": 0.772982255294791,
+      "grad_norm": 0.68359375,
+      "learning_rate": 7.690984311511695e-06,
+      "loss": 1.4912,
+      "step": 211
+    },
+    {
+      "epoch": 0.7766456783056669,
+      "grad_norm": 0.75390625,
+      "learning_rate": 7.664021154676828e-06,
+      "loss": 1.4985,
+      "step": 212
+    },
+    {
+      "epoch": 0.7803091013165426,
+      "grad_norm": 0.6953125,
+      "learning_rate": 7.636949378858647e-06,
+      "loss": 1.4642,
+      "step": 213
+    },
+    {
+      "epoch": 0.7839725243274185,
+      "grad_norm": 0.78125,
+      "learning_rate": 7.609770087842969e-06,
+      "loss": 1.5051,
+      "step": 214
+    },
+    {
+      "epoch": 0.7876359473382942,
+      "grad_norm": 0.7265625,
+      "learning_rate": 7.582484389799279e-06,
+      "loss": 1.4656,
+      "step": 215
+    },
+    {
+      "epoch": 0.79129937034917,
+      "grad_norm": 0.75,
+      "learning_rate": 7.555093397235553e-06,
+      "loss": 1.4589,
+      "step": 216
+    },
+    {
+      "epoch": 0.7949627933600458,
+      "grad_norm": 0.74609375,
+      "learning_rate": 7.527598226952895e-06,
+      "loss": 1.499,
+      "step": 217
+    },
+    {
+      "epoch": 0.7986262163709216,
+      "grad_norm": 0.71484375,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 1.4684,
+      "step": 218
+    },
+    {
+      "epoch": 0.8022896393817973,
+      "grad_norm": 0.7109375,
+      "learning_rate": 7.472299841627452e-06,
+      "loss": 1.488,
+      "step": 219
+    },
+    {
+      "epoch": 0.8059530623926732,
+      "grad_norm": 0.6953125,
+      "learning_rate": 7.444498881241835e-06,
+      "loss": 1.5102,
+      "step": 220
+    },
+    {
+      "epoch": 0.8096164854035489,
+      "grad_norm": 0.6875,
+      "learning_rate": 7.4165982523596945e-06,
+      "loss": 1.4967,
+      "step": 221
+    },
+    {
+      "epoch": 0.8132799084144248,
+      "grad_norm": 0.7109375,
+      "learning_rate": 7.388599092561315e-06,
+      "loss": 1.4965,
+      "step": 222
+    },
+    {
+      "epoch": 0.8169433314253005,
+      "grad_norm": 0.7265625,
+      "learning_rate": 7.360502543444339e-06,
+      "loss": 1.4254,
+      "step": 223
+    },
+    {
+      "epoch": 0.8206067544361763,
+      "grad_norm": 0.6953125,
+      "learning_rate": 7.3323097505772225e-06,
+      "loss": 1.4696,
+      "step": 224
+    },
+    {
+      "epoch": 0.8242701774470521,
+      "grad_norm": 0.69921875,
+      "learning_rate": 7.304021863452525e-06,
+      "loss": 1.4695,
+      "step": 225
+    },
+    {
+      "epoch": 0.8279336004579279,
+      "grad_norm": 0.69140625,
+      "learning_rate": 7.2756400354400445e-06,
+      "loss": 1.4825,
+      "step": 226
+    },
+    {
+      "epoch": 0.8315970234688037,
+      "grad_norm": 0.69921875,
+      "learning_rate": 7.24716542373979e-06,
+      "loss": 1.4858,
+      "step": 227
+    },
+    {
+      "epoch": 0.8352604464796795,
+      "grad_norm": 0.72265625,
+      "learning_rate": 7.218599189334799e-06,
+      "loss": 1.4415,
+      "step": 228
+    },
+    {
+      "epoch": 0.8389238694905552,
+      "grad_norm": 0.765625,
+      "learning_rate": 7.189942496943803e-06,
+      "loss": 1.4819,
+      "step": 229
+    },
+    {
+      "epoch": 0.842587292501431,
+      "grad_norm": 0.6953125,
+      "learning_rate": 7.161196514973735e-06,
+      "loss": 1.4335,
+      "step": 230
+    },
+    {
+      "epoch": 0.8462507155123068,
+      "grad_norm": 0.6875,
+      "learning_rate": 7.132362415472099e-06,
+      "loss": 1.4494,
+      "step": 231
+    },
+    {
+      "epoch": 0.8499141385231826,
+      "grad_norm": 0.7265625,
+      "learning_rate": 7.1034413740791705e-06,
+      "loss": 1.4306,
+      "step": 232
+    },
+    {
+      "epoch": 0.8535775615340584,
+      "grad_norm": 0.69140625,
+      "learning_rate": 7.0744345699800755e-06,
+      "loss": 1.4598,
+      "step": 233
+    },
+    {
+      "epoch": 0.8572409845449341,
+      "grad_norm": 0.73046875,
+      "learning_rate": 7.045343185856701e-06,
+      "loss": 1.4681,
+      "step": 234
+    },
+    {
+      "epoch": 0.86090440755581,
+      "grad_norm": 0.6953125,
+      "learning_rate": 7.016168407839478e-06,
+      "loss": 1.4952,
+      "step": 235
+    },
+    {
+      "epoch": 0.8645678305666857,
+      "grad_norm": 0.66796875,
+      "learning_rate": 6.986911425459028e-06,
+      "loss": 1.4403,
+      "step": 236
+    },
+    {
+      "epoch": 0.8682312535775615,
+      "grad_norm": 0.73828125,
+      "learning_rate": 6.957573431597646e-06,
+      "loss": 1.4945,
+      "step": 237
+    },
+    {
+      "epoch": 0.8718946765884373,
+      "grad_norm": 0.7578125,
+      "learning_rate": 6.92815562244068e-06,
+      "loss": 1.4798,
+      "step": 238
+    },
+    {
+      "epoch": 0.8755580995993131,
+      "grad_norm": 0.69921875,
+      "learning_rate": 6.898659197427748e-06,
+      "loss": 1.4269,
+      "step": 239
+    },
+    {
+      "epoch": 0.8792215226101889,
+      "grad_norm": 0.703125,
+      "learning_rate": 6.869085359203844e-06,
+      "loss": 1.4421,
+      "step": 240
+    },
+    {
+      "epoch": 0.8828849456210647,
+      "grad_norm": 0.7109375,
+      "learning_rate": 6.839435313570293e-06,
+      "loss": 1.4389,
+      "step": 241
+    },
+    {
+      "epoch": 0.8865483686319404,
+      "grad_norm": 0.70703125,
+      "learning_rate": 6.80971026943559e-06,
+      "loss": 1.4923,
+      "step": 242
+    },
+    {
+      "epoch": 0.8902117916428163,
+      "grad_norm": 0.65234375,
+      "learning_rate": 6.779911438766117e-06,
+      "loss": 1.4152,
+      "step": 243
+    },
+    {
+      "epoch": 0.893875214653692,
+      "grad_norm": 0.6796875,
+      "learning_rate": 6.750040036536718e-06,
+      "loss": 1.446,
+      "step": 244
+    },
+    {
+      "epoch": 0.8975386376645679,
+      "grad_norm": 0.69140625,
+      "learning_rate": 6.72009728068117e-06,
+      "loss": 1.4097,
+      "step": 245
+    },
+    {
+      "epoch": 0.9012020606754436,
+      "grad_norm": 0.6875,
+      "learning_rate": 6.690084392042514e-06,
+      "loss": 1.4293,
+      "step": 246
+    },
+    {
+      "epoch": 0.9048654836863194,
+      "grad_norm": 0.6953125,
+      "learning_rate": 6.6600025943232935e-06,
+      "loss": 1.464,
+      "step": 247
+    },
+    {
+      "epoch": 0.9085289066971952,
+      "grad_norm": 0.7421875,
+      "learning_rate": 6.629853114035643e-06,
+      "loss": 1.4908,
+      "step": 248
+    },
+    {
+      "epoch": 0.912192329708071,
+      "grad_norm": 0.7109375,
+      "learning_rate": 6.599637180451295e-06,
+      "loss": 1.4942,
+      "step": 249
+    },
+    {
+      "epoch": 0.9158557527189468,
+      "grad_norm": 0.734375,
+      "learning_rate": 6.569356025551454e-06,
+      "loss": 1.4677,
+      "step": 250
+    },
+    {
+      "epoch": 0.9195191757298226,
+      "grad_norm": 0.67578125,
+      "learning_rate": 6.539010883976562e-06,
+      "loss": 1.4457,
+      "step": 251
+    },
+    {
+      "epoch": 0.9231825987406983,
+      "grad_norm": 0.703125,
+      "learning_rate": 6.508602992975963e-06,
+      "loss": 1.4622,
+      "step": 252
+    },
+    {
+      "epoch": 0.9268460217515742,
+      "grad_norm": 0.65625,
+      "learning_rate": 6.478133592357455e-06,
+      "loss": 1.4319,
+      "step": 253
+    },
+    {
+      "epoch": 0.9305094447624499,
+      "grad_norm": 0.703125,
+      "learning_rate": 6.447603924436744e-06,
+      "loss": 1.453,
+      "step": 254
+    },
+    {
+      "epoch": 0.9341728677733258,
+      "grad_norm": 0.70703125,
+      "learning_rate": 6.417015233986786e-06,
+      "loss": 1.4239,
+      "step": 255
+    },
+    {
+      "epoch": 0.9378362907842015,
+      "grad_norm": 0.79296875,
+      "learning_rate": 6.38636876818704e-06,
+      "loss": 1.4798,
+      "step": 256
+    },
+    {
+      "epoch": 0.9414997137950772,
+      "grad_norm": 0.79296875,
+      "learning_rate": 6.3556657765726116e-06,
+      "loss": 1.4944,
+      "step": 257
+    },
+    {
+      "epoch": 0.9451631368059531,
+      "grad_norm": 0.7421875,
+      "learning_rate": 6.32490751098331e-06,
+      "loss": 1.4843,
+      "step": 258
+    },
+    {
+      "epoch": 0.9488265598168288,
+      "grad_norm": 0.67578125,
+      "learning_rate": 6.294095225512604e-06,
+      "loss": 1.495,
+      "step": 259
+    },
+    {
+      "epoch": 0.9524899828277046,
+      "grad_norm": 0.68359375,
+      "learning_rate": 6.263230176456497e-06,
+      "loss": 1.4301,
+      "step": 260
+    },
+    {
+      "epoch": 0.9561534058385804,
+      "grad_norm": 0.74609375,
+      "learning_rate": 6.232313622262297e-06,
+      "loss": 1.5314,
+      "step": 261
+    },
+    {
+      "epoch": 0.9598168288494562,
+      "grad_norm": 0.69140625,
+      "learning_rate": 6.2013468234773034e-06,
+      "loss": 1.4744,
+      "step": 262
+    },
+    {
+      "epoch": 0.963480251860332,
+      "grad_norm": 0.67578125,
+      "learning_rate": 6.170331042697425e-06,
+      "loss": 1.4152,
+      "step": 263
+    },
+    {
+      "epoch": 0.9671436748712078,
+      "grad_norm": 0.73828125,
+      "learning_rate": 6.139267544515689e-06,
+      "loss": 1.4507,
+      "step": 264
+    },
+    {
+      "epoch": 0.9708070978820835,
+      "grad_norm": 0.6796875,
+      "learning_rate": 6.10815759547068e-06,
+      "loss": 1.4621,
+      "step": 265
+    },
+    {
+      "epoch": 0.9744705208929594,
+      "grad_norm": 0.6953125,
+      "learning_rate": 6.077002463994908e-06,
+      "loss": 1.4759,
+      "step": 266
+    },
+    {
+      "epoch": 0.9781339439038351,
+      "grad_norm": 0.70703125,
+      "learning_rate": 6.045803420363085e-06,
+      "loss": 1.5047,
+      "step": 267
+    },
+    {
+      "epoch": 0.981797366914711,
+      "grad_norm": 0.76171875,
+      "learning_rate": 6.014561736640334e-06,
+      "loss": 1.446,
+      "step": 268
+    },
+    {
+      "epoch": 0.9854607899255867,
+      "grad_norm": 0.76953125,
+      "learning_rate": 5.983278686630327e-06,
+      "loss": 1.4742,
+      "step": 269
+    },
+    {
+      "epoch": 0.9891242129364625,
+      "grad_norm": 0.703125,
+      "learning_rate": 5.951955545823342e-06,
+      "loss": 1.4837,
+      "step": 270
+    },
+    {
+      "epoch": 0.9927876359473383,
+      "grad_norm": 0.7421875,
+      "learning_rate": 5.920593591344264e-06,
+      "loss": 1.4585,
+      "step": 271
+    },
+    {
+      "epoch": 0.9964510589582141,
+      "grad_norm": 0.67578125,
+      "learning_rate": 5.8891941019005095e-06,
+      "loss": 1.4889,
+      "step": 272
+    },
+    {
+      "epoch": 1.00011448196909,
+      "grad_norm": 0.7265625,
+      "learning_rate": 5.857758357729892e-06,
+      "loss": 1.5012,
+      "step": 273
+    },
+    {
+      "epoch": 1.00343997248022,
+      "grad_norm": 0.6875,
+      "learning_rate": 5.826287640548425e-06,
+      "loss": 1.4676,
+      "step": 274
+    },
+    {
+      "epoch": 1.0071092764591216,
+      "grad_norm": 0.6875,
+      "learning_rate": 5.794783233498062e-06,
+      "loss": 1.4632,
+      "step": 275
+    },
+    {
+      "epoch": 1.0107785804380232,
+      "grad_norm": 0.734375,
+      "learning_rate": 5.763246421094373e-06,
+      "loss": 1.4817,
+      "step": 276
+    },
+    {
+      "epoch": 1.0107785804380232,
+      "eval_loss": 1.4074798822402954,
+      "eval_runtime": 86.3869,
+      "eval_samples_per_second": 8.971,
+      "eval_steps_per_second": 4.491,
+      "step": 276
+    },
+    {
+      "epoch": 1.0144478844169247,
+      "grad_norm": 0.69140625,
+      "learning_rate": 5.731678489174186e-06,
+      "loss": 1.3825,
+      "step": 277
+    },
+    {
+      "epoch": 1.0181171883958262,
+      "grad_norm": 0.75,
+      "learning_rate": 5.7000807248431466e-06,
+      "loss": 1.4202,
+      "step": 278
+    },
+    {
+      "epoch": 1.0217864923747277,
+      "grad_norm": 0.7578125,
+      "learning_rate": 5.668454416423243e-06,
+      "loss": 1.4907,
+      "step": 279
+    },
+    {
+      "epoch": 1.0254557963536293,
+      "grad_norm": 0.70703125,
+      "learning_rate": 5.636800853400285e-06,
+      "loss": 1.4115,
+      "step": 280
+    },
+    {
+      "epoch": 1.0291251003325306,
+      "grad_norm": 0.7421875,
+      "learning_rate": 5.605121326371316e-06,
+      "loss": 1.4316,
+      "step": 281
+    },
+    {
+      "epoch": 1.032794404311432,
+      "grad_norm": 0.69140625,
+      "learning_rate": 5.573417126992004e-06,
+      "loss": 1.4734,
+      "step": 282
+    },
+    {
+      "epoch": 1.0364637082903336,
+      "grad_norm": 0.69140625,
+      "learning_rate": 5.5416895479239665e-06,
+      "loss": 1.4181,
+      "step": 283
+    },
+    {
+      "epoch": 1.0401330122692352,
+      "grad_norm": 0.70703125,
+      "learning_rate": 5.509939882782077e-06,
+      "loss": 1.5014,
+      "step": 284
+    },
+    {
+      "epoch": 1.0438023162481367,
+      "grad_norm": 0.67578125,
+      "learning_rate": 5.478169426081712e-06,
+      "loss": 1.4454,
+      "step": 285
+    },
+    {
+      "epoch": 1.0474716202270382,
+      "grad_norm": 0.71875,
+      "learning_rate": 5.446379473185972e-06,
+      "loss": 1.4678,
+      "step": 286
+    },
+    {
+      "epoch": 1.0511409242059397,
+      "grad_norm": 0.671875,
+      "learning_rate": 5.41457132025287e-06,
+      "loss": 1.4437,
+      "step": 287
+    },
+    {
+      "epoch": 1.0548102281848413,
+      "grad_norm": 0.69140625,
+      "learning_rate": 5.38274626418248e-06,
+      "loss": 1.4636,
+      "step": 288
+    },
+    {
+      "epoch": 1.0584795321637426,
+      "grad_norm": 0.6953125,
+      "learning_rate": 5.3509056025640575e-06,
+      "loss": 1.4414,
+      "step": 289
+    },
+    {
+      "epoch": 1.062148836142644,
+      "grad_norm": 0.75390625,
+      "learning_rate": 5.319050633623141e-06,
+      "loss": 1.5076,
+      "step": 290
+    },
+    {
+      "epoch": 1.0658181401215456,
+      "grad_norm": 0.671875,
+      "learning_rate": 5.287182656168618e-06,
+      "loss": 1.4199,
+      "step": 291
+    },
+    {
+      "epoch": 1.0694874441004472,
+      "grad_norm": 0.7421875,
+      "learning_rate": 5.255302969539753e-06,
+      "loss": 1.4788,
+      "step": 292
+    },
+    {
+      "epoch": 1.0731567480793487,
+      "grad_norm": 0.71875,
+      "learning_rate": 5.22341287355324e-06,
+      "loss": 1.4889,
+      "step": 293
+    },
+    {
+      "epoch": 1.0768260520582502,
+      "grad_norm": 0.6875,
+      "learning_rate": 5.191513668450178e-06,
+      "loss": 1.4079,
+      "step": 294
+    },
+    {
+      "epoch": 1.0804953560371517,
+      "grad_norm": 0.71875,
+      "learning_rate": 5.1596066548430725e-06,
+      "loss": 1.5113,
+      "step": 295
+    },
+    {
+      "epoch": 1.0841646600160533,
+      "grad_norm": 0.6796875,
+      "learning_rate": 5.127693133662801e-06,
+      "loss": 1.4427,
+      "step": 296
+    },
+    {
+      "epoch": 1.0878339639949548,
+      "grad_norm": 0.70703125,
+      "learning_rate": 5.095774406105572e-06,
+      "loss": 1.4381,
+      "step": 297
+    },
+    {
+      "epoch": 1.091503267973856,
+      "grad_norm": 0.6875,
+      "learning_rate": 5.06385177357987e-06,
+      "loss": 1.4975,
+      "step": 298
+    },
+    {
+      "epoch": 1.0951725719527576,
+      "grad_norm": 0.6953125,
+      "learning_rate": 5.031926537653396e-06,
+      "loss": 1.4333,
+      "step": 299
+    },
+    {
+      "epoch": 1.0988418759316592,
+      "grad_norm": 0.66015625,
+      "learning_rate": 5e-06,
+      "loss": 1.4498,
+      "step": 300
+    },
+    {
+      "epoch": 1.1025111799105607,
+      "grad_norm": 0.67578125,
+      "learning_rate": 4.968073462346605e-06,
+      "loss": 1.428,
+      "step": 301
+    },
+    {
+      "epoch": 1.1061804838894622,
+      "grad_norm": 0.69140625,
+      "learning_rate": 4.936148226420133e-06,
+      "loss": 1.5139,
+      "step": 302
+    },
+    {
+      "epoch": 1.1098497878683637,
+      "grad_norm": 0.70703125,
+      "learning_rate": 4.90422559389443e-06,
+      "loss": 1.4781,
+      "step": 303
+    },
+    {
+      "epoch": 1.1135190918472653,
+      "grad_norm": 0.73828125,
+      "learning_rate": 4.8723068663372005e-06,
+      "loss": 1.5284,
+      "step": 304
+    },
+    {
+      "epoch": 1.1171883958261668,
+      "grad_norm": 0.765625,
+      "learning_rate": 4.84039334515693e-06,
+      "loss": 1.4669,
+      "step": 305
+    },
+    {
+      "epoch": 1.120857699805068,
+      "grad_norm": 0.7265625,
+      "learning_rate": 4.808486331549824e-06,
+      "loss": 1.4945,
+      "step": 306
+    },
+    {
+      "epoch": 1.1245270037839696,
+      "grad_norm": 0.67578125,
+      "learning_rate": 4.776587126446761e-06,
+      "loss": 1.5031,
+      "step": 307
+    },
+    {
+      "epoch": 1.1281963077628712,
+      "grad_norm": 0.6875,
+      "learning_rate": 4.744697030460248e-06,
+      "loss": 1.4379,
+      "step": 308
+    },
+    {
+      "epoch": 1.1318656117417727,
+      "grad_norm": 0.68359375,
+      "learning_rate": 4.712817343831384e-06,
+      "loss": 1.4564,
+      "step": 309
+    },
+    {
+      "epoch": 1.1355349157206742,
+      "grad_norm": 0.703125,
+      "learning_rate": 4.680949366376858e-06,
+      "loss": 1.4879,
+      "step": 310
+    },
+    {
+      "epoch": 1.1392042196995757,
+      "grad_norm": 0.6953125,
+      "learning_rate": 4.649094397435944e-06,
+      "loss": 1.5162,
+      "step": 311
+    },
+    {
+      "epoch": 1.1428735236784773,
+      "grad_norm": 0.73828125,
+      "learning_rate": 4.617253735817522e-06,
+      "loss": 1.4739,
+      "step": 312
+    },
+    {
+      "epoch": 1.1465428276573788,
+      "grad_norm": 0.73046875,
+      "learning_rate": 4.585428679747133e-06,
+      "loss": 1.4835,
+      "step": 313
+    },
+    {
+      "epoch": 1.1502121316362803,
+      "grad_norm": 0.71484375,
+      "learning_rate": 4.553620526814029e-06,
+      "loss": 1.414,
+      "step": 314
+    },
+    {
+      "epoch": 1.1538814356151819,
+      "grad_norm": 0.734375,
+      "learning_rate": 4.521830573918289e-06,
+      "loss": 1.4474,
+      "step": 315
+    },
+    {
+      "epoch": 1.1575507395940832,
+      "grad_norm": 0.69140625,
+      "learning_rate": 4.490060117217925e-06,
+      "loss": 1.428,
+      "step": 316
+    },
+    {
+      "epoch": 1.1612200435729847,
+      "grad_norm": 0.66796875,
+      "learning_rate": 4.458310452076034e-06,
+      "loss": 1.4305,
+      "step": 317
+    },
+    {
+      "epoch": 1.1648893475518862,
+      "grad_norm": 0.70703125,
+      "learning_rate": 4.426582873007999e-06,
+      "loss": 1.4561,
+      "step": 318
+    },
+    {
+      "epoch": 1.1685586515307878,
+      "grad_norm": 0.71484375,
+      "learning_rate": 4.3948786736286866e-06,
+      "loss": 1.4406,
+      "step": 319
+    },
+    {
+      "epoch": 1.1722279555096893,
+      "grad_norm": 0.671875,
+      "learning_rate": 4.363199146599717e-06,
+      "loss": 1.4912,
+      "step": 320
+    },
+    {
+      "epoch": 1.1758972594885908,
+      "grad_norm": 0.68359375,
+      "learning_rate": 4.331545583576758e-06,
+      "loss": 1.4481,
+      "step": 321
+    },
+    {
+      "epoch": 1.1795665634674923,
+      "grad_norm": 0.7421875,
+      "learning_rate": 4.299919275156857e-06,
+      "loss": 1.4796,
+      "step": 322
+    },
+    {
+      "epoch": 1.1832358674463936,
+      "grad_norm": 0.6796875,
+      "learning_rate": 4.2683215108258145e-06,
+      "loss": 1.5001,
+      "step": 323
+    },
+    {
+      "epoch": 1.1869051714252952,
+      "grad_norm": 0.67578125,
+      "learning_rate": 4.236753578905627e-06,
+      "loss": 1.4334,
+      "step": 324
+    },
+    {
+      "epoch": 1.1905744754041967,
+      "grad_norm": 0.6875,
+      "learning_rate": 4.205216766501941e-06,
+      "loss": 1.5136,
+      "step": 325
+    },
+    {
+      "epoch": 1.1942437793830982,
+      "grad_norm": 0.6796875,
+      "learning_rate": 4.173712359451576e-06,
+      "loss": 1.5047,
+      "step": 326
+    },
+    {
+      "epoch": 1.1979130833619998,
+      "grad_norm": 0.6484375,
+      "learning_rate": 4.142241642270109e-06,
+      "loss": 1.4266,
+      "step": 327
+    },
+    {
+      "epoch": 1.2015823873409013,
+      "grad_norm": 0.71484375,
+      "learning_rate": 4.110805898099492e-06,
+      "loss": 1.5102,
+      "step": 328
+    },
+    {
+      "epoch": 1.2052516913198028,
+      "grad_norm": 0.70703125,
+      "learning_rate": 4.079406408655737e-06,
+      "loss": 1.4405,
+      "step": 329
+    },
+    {
+      "epoch": 1.2089209952987043,
+      "grad_norm": 0.70703125,
+      "learning_rate": 4.048044454176658e-06,
+      "loss": 1.4366,
+      "step": 330
+    },
+    {
+      "epoch": 1.2125902992776059,
+      "grad_norm": 0.74609375,
+      "learning_rate": 4.016721313369674e-06,
+      "loss": 1.4686,
+      "step": 331
+    },
+    {
+      "epoch": 1.2162596032565074,
+      "grad_norm": 0.7109375,
+      "learning_rate": 3.985438263359667e-06,
+      "loss": 1.4541,
+      "step": 332
+    },
+    {
+      "epoch": 1.2199289072354087,
+      "grad_norm": 0.6875,
+      "learning_rate": 3.954196579636918e-06,
+      "loss": 1.4657,
+      "step": 333
+    },
+    {
+      "epoch": 1.2235982112143102,
+      "grad_norm": 0.734375,
+      "learning_rate": 3.922997536005094e-06,
+      "loss": 1.3919,
+      "step": 334
+    },
+    {
+      "epoch": 1.2272675151932118,
+      "grad_norm": 0.71484375,
+      "learning_rate": 3.891842404529321e-06,
+      "loss": 1.4672,
+      "step": 335
+    },
+    {
+      "epoch": 1.2309368191721133,
+      "grad_norm": 0.69140625,
+      "learning_rate": 3.860732455484314e-06,
+      "loss": 1.4108,
+      "step": 336
+    },
+    {
+      "epoch": 1.2346061231510148,
+      "grad_norm": 0.69921875,
+      "learning_rate": 3.829668957302576e-06,
+      "loss": 1.4663,
+      "step": 337
+    },
+    {
+      "epoch": 1.2382754271299163,
+      "grad_norm": 0.671875,
+      "learning_rate": 3.7986531765226965e-06,
+      "loss": 1.4127,
+      "step": 338
+    },
+    {
+      "epoch": 1.2419447311088179,
+      "grad_norm": 0.71875,
+      "learning_rate": 3.7676863777377055e-06,
+      "loss": 1.4151,
+      "step": 339
+    },
+    {
+      "epoch": 1.2456140350877192,
+      "grad_norm": 0.765625,
+      "learning_rate": 3.7367698235435036e-06,
+      "loss": 1.4531,
+      "step": 340
+    },
+    {
+      "epoch": 1.2492833390666207,
+      "grad_norm": 0.6953125,
+      "learning_rate": 3.705904774487396e-06,
+      "loss": 1.4463,
+      "step": 341
+    },
+    {
+      "epoch": 1.2529526430455222,
+      "grad_norm": 0.68359375,
+      "learning_rate": 3.675092489016693e-06,
+      "loss": 1.4502,
+      "step": 342
+    },
+    {
+      "epoch": 1.2566219470244238,
+      "grad_norm": 0.703125,
+      "learning_rate": 3.6443342234273905e-06,
+      "loss": 1.4793,
+      "step": 343
+    },
+    {
+      "epoch": 1.2602912510033253,
+      "grad_norm": 0.75390625,
+      "learning_rate": 3.61363123181296e-06,
+      "loss": 1.5136,
+      "step": 344
+    },
+    {
+      "epoch": 1.2639605549822268,
+      "grad_norm": 0.6875,
+      "learning_rate": 3.582984766013215e-06,
+      "loss": 1.4637,
+      "step": 345
+    },
+    {
+      "epoch": 1.2639605549822268,
+      "eval_loss": 1.4037530422210693,
+      "eval_runtime": 86.5383,
+      "eval_samples_per_second": 8.956,
+      "eval_steps_per_second": 4.484,
+      "step": 345
+    },
+    {
+      "epoch": 1.2676298589611283,
+      "grad_norm": 0.6875,
+      "learning_rate": 3.5523960755632573e-06,
+      "loss": 1.5192,
+      "step": 346
+    },
+    {
+      "epoch": 1.2712991629400299,
+      "grad_norm": 0.6875,
+      "learning_rate": 3.5218664076425455e-06,
+      "loss": 1.4695,
+      "step": 347
+    },
+    {
+      "epoch": 1.2749684669189314,
+      "grad_norm": 0.6953125,
+      "learning_rate": 3.4913970070240388e-06,
+      "loss": 1.4707,
+      "step": 348
+    },
+    {
+      "epoch": 1.278637770897833,
+      "grad_norm": 0.6640625,
+      "learning_rate": 3.460989116023439e-06,
+      "loss": 1.4646,
+      "step": 349
+    },
+    {
+      "epoch": 1.2823070748767345,
+      "grad_norm": 0.734375,
+      "learning_rate": 3.4306439744485453e-06,
+      "loss": 1.4668,
+      "step": 350
+    },
+    {
+      "epoch": 1.2859763788556358,
+      "grad_norm": 0.6875,
+      "learning_rate": 3.400362819548706e-06,
+      "loss": 1.4729,
+      "step": 351
+    },
+    {
+      "epoch": 1.2896456828345373,
+      "grad_norm": 0.6796875,
+      "learning_rate": 3.3701468859643583e-06,
+      "loss": 1.4596,
+      "step": 352
+    },
+    {
+      "epoch": 1.2933149868134388,
+      "grad_norm": 0.72265625,
+      "learning_rate": 3.3399974056767095e-06,
+      "loss": 1.4346,
+      "step": 353
+    },
+    {
+      "epoch": 1.2969842907923403,
+      "grad_norm": 0.69921875,
+      "learning_rate": 3.309915607957487e-06,
+      "loss": 1.432,
+      "step": 354
+    },
+    {
+      "epoch": 1.3006535947712419,
+      "grad_norm": 0.68359375,
+      "learning_rate": 3.2799027193188316e-06,
+      "loss": 1.3905,
+      "step": 355
+    },
+    {
+      "epoch": 1.3043228987501434,
+      "grad_norm": 0.703125,
+      "learning_rate": 3.249959963463283e-06,
+      "loss": 1.4609,
+      "step": 356
+    },
+    {
+      "epoch": 1.3079922027290447,
+      "grad_norm": 0.6796875,
+      "learning_rate": 3.2200885612338846e-06,
+      "loss": 1.4484,
+      "step": 357
+    },
+    {
+      "epoch": 1.3116615067079462,
+      "grad_norm": 0.6796875,
+      "learning_rate": 3.19028973056441e-06,
+      "loss": 1.4393,
+      "step": 358
+    },
+    {
+      "epoch": 1.3153308106868478,
+      "grad_norm": 0.71875,
+      "learning_rate": 3.160564686429709e-06,
+      "loss": 1.4205,
+      "step": 359
+    },
+    {
+      "epoch": 1.3190001146657493,
+      "grad_norm": 0.65234375,
+      "learning_rate": 3.1309146407961565e-06,
+      "loss": 1.4736,
+      "step": 360
+    },
+    {
+      "epoch": 1.3226694186446508,
+      "grad_norm": 0.6875,
+      "learning_rate": 3.1013408025722515e-06,
+      "loss": 1.4501,
+      "step": 361
+    },
+    {
+      "epoch": 1.3263387226235523,
+      "grad_norm": 0.640625,
+      "learning_rate": 3.0718443775593233e-06,
+      "loss": 1.4038,
+      "step": 362
+    },
+    {
+      "epoch": 1.3300080266024539,
+      "grad_norm": 0.72265625,
+      "learning_rate": 3.0424265684023556e-06,
+      "loss": 1.4786,
+      "step": 363
+    },
+    {
+      "epoch": 1.3336773305813554,
+      "grad_norm": 0.71875,
+      "learning_rate": 3.0130885745409744e-06,
+      "loss": 1.4944,
+      "step": 364
+    },
+    {
+      "epoch": 1.337346634560257,
+      "grad_norm": 0.72265625,
+      "learning_rate": 2.9838315921605237e-06,
+      "loss": 1.4274,
+      "step": 365
+    },
+    {
+      "epoch": 1.3410159385391585,
+      "grad_norm": 0.71875,
+      "learning_rate": 2.9546568141433007e-06,
+      "loss": 1.4483,
+      "step": 366
+    },
+    {
+      "epoch": 1.34468524251806,
+      "grad_norm": 0.6953125,
+      "learning_rate": 2.9255654300199253e-06,
+      "loss": 1.4838,
+      "step": 367
+    },
+    {
+      "epoch": 1.3483545464969613,
+      "grad_norm": 0.66796875,
+      "learning_rate": 2.8965586259208295e-06,
+      "loss": 1.4264,
+      "step": 368
+    },
+    {
+      "epoch": 1.3520238504758628,
+      "grad_norm": 0.69140625,
+      "learning_rate": 2.8676375845279013e-06,
+      "loss": 1.4688,
+      "step": 369
+    },
+    {
+      "epoch": 1.3556931544547643,
+      "grad_norm": 0.71484375,
+      "learning_rate": 2.838803485026265e-06,
+      "loss": 1.4343,
+      "step": 370
+    },
+    {
+      "epoch": 1.3593624584336659,
+      "grad_norm": 0.671875,
+      "learning_rate": 2.810057503056198e-06,
+      "loss": 1.4511,
+      "step": 371
+    },
+    {
+      "epoch": 1.3630317624125674,
+      "grad_norm": 0.67578125,
+      "learning_rate": 2.781400810665201e-06,
+      "loss": 1.4483,
+      "step": 372
+    },
+    {
+      "epoch": 1.366701066391469,
+      "grad_norm": 0.73046875,
+      "learning_rate": 2.7528345762602125e-06,
+      "loss": 1.4168,
+      "step": 373
+    },
+    {
+      "epoch": 1.3703703703703702,
+      "grad_norm": 0.74609375,
+      "learning_rate": 2.724359964559958e-06,
+      "loss": 1.4603,
+      "step": 374
+    },
+    {
+      "epoch": 1.3740396743492718,
+      "grad_norm": 0.69140625,
+      "learning_rate": 2.695978136547476e-06,
+      "loss": 1.5096,
+      "step": 375
+    },
+    {
+      "epoch": 1.3777089783281733,
+      "grad_norm": 0.6875,
+      "learning_rate": 2.6676902494227795e-06,
+      "loss": 1.4904,
+      "step": 376
+    },
+    {
+      "epoch": 1.3813782823070748,
+      "grad_norm": 0.69140625,
+      "learning_rate": 2.639497456555663e-06,
+      "loss": 1.4747,
+      "step": 377
+    },
+    {
+      "epoch": 1.3850475862859764,
+      "grad_norm": 0.7109375,
+      "learning_rate": 2.611400907438685e-06,
+      "loss": 1.4133,
+      "step": 378
+    },
+    {
+      "epoch": 1.3887168902648779,
+      "grad_norm": 0.69140625,
+      "learning_rate": 2.583401747640307e-06,
+      "loss": 1.5062,
+      "step": 379
+    },
+    {
+      "epoch": 1.3923861942437794,
+      "grad_norm": 0.7109375,
+      "learning_rate": 2.555501118758167e-06,
+      "loss": 1.4598,
+      "step": 380
+    },
+    {
+      "epoch": 1.396055498222681,
+      "grad_norm": 0.703125,
+      "learning_rate": 2.527700158372548e-06,
+      "loss": 1.5289,
+      "step": 381
+    },
+    {
+      "epoch": 1.3997248022015825,
+      "grad_norm": 0.7578125,
+      "learning_rate": 2.5000000000000015e-06,
+      "loss": 1.4476,
+      "step": 382
+    },
+    {
+      "epoch": 1.403394106180484,
+      "grad_norm": 0.6796875,
+      "learning_rate": 2.472401773047107e-06,
+      "loss": 1.4792,
+      "step": 383
+    },
+    {
+      "epoch": 1.4070634101593855,
+      "grad_norm": 0.67578125,
+      "learning_rate": 2.4449066027644473e-06,
+      "loss": 1.4892,
+      "step": 384
+    },
+    {
+      "epoch": 1.4107327141382868,
+      "grad_norm": 0.6796875,
+      "learning_rate": 2.4175156102007237e-06,
+      "loss": 1.4466,
+      "step": 385
+    },
+    {
+      "epoch": 1.4144020181171884,
+      "grad_norm": 0.6484375,
+      "learning_rate": 2.3902299121570332e-06,
+      "loss": 1.4712,
+      "step": 386
+    },
+    {
+      "epoch": 1.4180713220960899,
+      "grad_norm": 0.69140625,
+      "learning_rate": 2.363050621141354e-06,
+      "loss": 1.4384,
+      "step": 387
+    },
+    {
+      "epoch": 1.4217406260749914,
+      "grad_norm": 0.69140625,
+      "learning_rate": 2.3359788453231723e-06,
+      "loss": 1.4767,
+      "step": 388
+    },
+    {
+      "epoch": 1.425409930053893,
+      "grad_norm": 0.70703125,
+      "learning_rate": 2.309015688488305e-06,
+      "loss": 1.4331,
+      "step": 389
+    },
+    {
+      "epoch": 1.4290792340327945,
+      "grad_norm": 0.734375,
+      "learning_rate": 2.282162249993895e-06,
+      "loss": 1.4562,
+      "step": 390
+    },
+    {
+      "epoch": 1.4327485380116958,
+      "grad_norm": 0.6875,
+      "learning_rate": 2.2554196247235843e-06,
+      "loss": 1.4585,
+      "step": 391
+    },
+    {
+      "epoch": 1.4364178419905973,
+      "grad_norm": 0.72265625,
+      "learning_rate": 2.228788903042877e-06,
+      "loss": 1.4396,
+      "step": 392
+    },
+    {
+      "epoch": 1.4400871459694988,
+      "grad_norm": 0.703125,
+      "learning_rate": 2.20227117075468e-06,
+      "loss": 1.4184,
+      "step": 393
+    },
+    {
+      "epoch": 1.4437564499484004,
+      "grad_norm": 0.67578125,
+      "learning_rate": 2.175867509055033e-06,
+      "loss": 1.4734,
+      "step": 394
+    },
+    {
+      "epoch": 1.4474257539273019,
+      "grad_norm": 0.703125,
+      "learning_rate": 2.149578994489024e-06,
+      "loss": 1.4194,
+      "step": 395
+    },
+    {
+      "epoch": 1.4510950579062034,
+      "grad_norm": 0.69921875,
+      "learning_rate": 2.1234066989068972e-06,
+      "loss": 1.4408,
+      "step": 396
+    },
+    {
+      "epoch": 1.454764361885105,
+      "grad_norm": 0.6484375,
+      "learning_rate": 2.0973516894203507e-06,
+      "loss": 1.4546,
+      "step": 397
+    },
+    {
+      "epoch": 1.4584336658640065,
+      "grad_norm": 0.6875,
+      "learning_rate": 2.071415028359026e-06,
+      "loss": 1.4392,
+      "step": 398
+    },
+    {
+      "epoch": 1.462102969842908,
+      "grad_norm": 0.7109375,
+      "learning_rate": 2.045597773227199e-06,
+      "loss": 1.4277,
+      "step": 399
+    },
+    {
+      "epoch": 1.4657722738218095,
+      "grad_norm": 0.68359375,
+      "learning_rate": 2.019900976660651e-06,
+      "loss": 1.4296,
+      "step": 400
+    },
+    {
+      "epoch": 1.469441577800711,
+      "grad_norm": 0.73046875,
+      "learning_rate": 1.994325686383769e-06,
+      "loss": 1.5095,
+      "step": 401
+    },
+    {
+      "epoch": 1.4731108817796124,
+      "grad_norm": 0.69140625,
+      "learning_rate": 1.9688729451668116e-06,
+      "loss": 1.4765,
+      "step": 402
+    },
+    {
+      "epoch": 1.4767801857585139,
+      "grad_norm": 0.703125,
+      "learning_rate": 1.943543790783392e-06,
+      "loss": 1.5502,
+      "step": 403
+    },
+    {
+      "epoch": 1.4804494897374154,
+      "grad_norm": 0.6640625,
+      "learning_rate": 1.9183392559681812e-06,
+      "loss": 1.5307,
+      "step": 404
+    },
+    {
+      "epoch": 1.484118793716317,
+      "grad_norm": 0.7109375,
+      "learning_rate": 1.8932603683747858e-06,
+      "loss": 1.4203,
+      "step": 405
+    },
+    {
+      "epoch": 1.4877880976952185,
+      "grad_norm": 0.703125,
+      "learning_rate": 1.8683081505338468e-06,
+      "loss": 1.4446,
+      "step": 406
+    },
+    {
+      "epoch": 1.49145740167412,
+      "grad_norm": 0.69921875,
+      "learning_rate": 1.8434836198113642e-06,
+      "loss": 1.4736,
+      "step": 407
+    },
+    {
+      "epoch": 1.4951267056530213,
+      "grad_norm": 0.671875,
+      "learning_rate": 1.8187877883672024e-06,
+      "loss": 1.4205,
+      "step": 408
+    },
+    {
+      "epoch": 1.4987960096319228,
+      "grad_norm": 0.69140625,
+      "learning_rate": 1.7942216631138188e-06,
+      "loss": 1.4663,
+      "step": 409
+    },
+    {
+      "epoch": 1.5024653136108244,
+      "grad_norm": 0.7109375,
+      "learning_rate": 1.7697862456752273e-06,
+      "loss": 1.4042,
+      "step": 410
+    },
+    {
+      "epoch": 1.5061346175897259,
+      "grad_norm": 0.7265625,
+      "learning_rate": 1.745482532346145e-06,
+      "loss": 1.4556,
+      "step": 411
+    },
+    {
+      "epoch": 1.5098039215686274,
+      "grad_norm": 0.71875,
+      "learning_rate": 1.7213115140513687e-06,
+      "loss": 1.477,
+      "step": 412
+    },
+    {
+      "epoch": 1.513473225547529,
+      "grad_norm": 0.64453125,
+      "learning_rate": 1.6972741763053835e-06,
+      "loss": 1.4345,
+      "step": 413
+    },
+    {
+      "epoch": 1.5171425295264305,
+      "grad_norm": 0.70703125,
+      "learning_rate": 1.6733714991721738e-06,
+      "loss": 1.4701,
+      "step": 414
+    },
+    {
+      "epoch": 1.5171425295264305,
+      "eval_loss": 1.4025633335113525,
+      "eval_runtime": 86.4313,
+      "eval_samples_per_second": 8.967,
+      "eval_steps_per_second": 4.489,
+      "step": 414
+    },
+    {
+      "epoch": 1.520811833505332,
+      "grad_norm": 0.71484375,
+      "learning_rate": 1.649604457225266e-06,
+      "loss": 1.4382,
+      "step": 415
+    },
+    {
+      "epoch": 1.5244811374842335,
+      "grad_norm": 0.66796875,
+      "learning_rate": 1.6259740195079903e-06,
+      "loss": 1.4168,
+      "step": 416
+    },
+    {
+      "epoch": 1.528150441463135,
+      "grad_norm": 0.67578125,
+      "learning_rate": 1.6024811494939723e-06,
+      "loss": 1.4085,
+      "step": 417
+    },
+    {
+      "epoch": 1.5318197454420366,
+      "grad_norm": 0.67578125,
+      "learning_rate": 1.5791268050478487e-06,
+      "loss": 1.3977,
+      "step": 418
+    },
+    {
+      "epoch": 1.5354890494209381,
+      "grad_norm": 0.71484375,
+      "learning_rate": 1.555911938386213e-06,
+      "loss": 1.472,
+      "step": 419
+    },
+    {
+      "epoch": 1.5391583533998394,
+      "grad_norm": 0.6953125,
+      "learning_rate": 1.532837496038792e-06,
+      "loss": 1.4904,
+      "step": 420
+    },
+    {
+      "epoch": 1.542827657378741,
+      "grad_norm": 0.65625,
+      "learning_rate": 1.509904418809852e-06,
+      "loss": 1.4428,
+      "step": 421
+    },
+    {
+      "epoch": 1.5464969613576425,
+      "grad_norm": 0.6875,
+      "learning_rate": 1.4871136417398407e-06,
+      "loss": 1.4436,
+      "step": 422
+    },
+    {
+      "epoch": 1.550166265336544,
+      "grad_norm": 0.72265625,
+      "learning_rate": 1.4644660940672628e-06,
+      "loss": 1.4498,
+      "step": 423
+    },
+    {
+      "epoch": 1.5538355693154455,
+      "grad_norm": 0.703125,
+      "learning_rate": 1.4419626991907925e-06,
+      "loss": 1.4447,
+      "step": 424
+    },
+    {
+      "epoch": 1.5575048732943468,
+      "grad_norm": 0.6796875,
+      "learning_rate": 1.4196043746316252e-06,
+      "loss": 1.4668,
+      "step": 425
+    },
+    {
+      "epoch": 1.5611741772732484,
+      "grad_norm": 0.71875,
+      "learning_rate": 1.3973920319960654e-06,
+      "loss": 1.4628,
+      "step": 426
+    },
+    {
+      "epoch": 1.56484348125215,
+      "grad_norm": 0.6796875,
+      "learning_rate": 1.3753265769383605e-06,
+      "loss": 1.4474,
+      "step": 427
+    },
+    {
+      "epoch": 1.5685127852310514,
+      "grad_norm": 0.7421875,
+      "learning_rate": 1.3534089091237757e-06,
+      "loss": 1.5121,
+      "step": 428
+    },
+    {
+      "epoch": 1.572182089209953,
+      "grad_norm": 0.7421875,
+      "learning_rate": 1.3316399221919075e-06,
+      "loss": 1.4867,
+      "step": 429
+    },
+    {
+      "epoch": 1.5758513931888545,
+      "grad_norm": 0.6640625,
+      "learning_rate": 1.310020503720254e-06,
+      "loss": 1.4734,
+      "step": 430
+    },
+    {
+      "epoch": 1.579520697167756,
+      "grad_norm": 0.6953125,
+      "learning_rate": 1.2885515351880217e-06,
+      "loss": 1.4975,
+      "step": 431
+    },
+    {
+      "epoch": 1.5831900011466575,
+      "grad_norm": 0.71484375,
+      "learning_rate": 1.2672338919401866e-06,
+      "loss": 1.4988,
+      "step": 432
+    },
+    {
+      "epoch": 1.586859305125559,
+      "grad_norm": 0.6640625,
+      "learning_rate": 1.2460684431518055e-06,
+      "loss": 1.4176,
+      "step": 433
+    },
+    {
+      "epoch": 1.5905286091044606,
+      "grad_norm": 0.671875,
+      "learning_rate": 1.2250560517925747e-06,
+      "loss": 1.485,
+      "step": 434
+    },
+    {
+      "epoch": 1.5941979130833621,
+      "grad_norm": 0.7265625,
+      "learning_rate": 1.2041975745916474e-06,
+      "loss": 1.5118,
+      "step": 435
+    },
+    {
+      "epoch": 1.5978672170622636,
+      "grad_norm": 0.68359375,
+      "learning_rate": 1.183493862002702e-06,
+      "loss": 1.4962,
+      "step": 436
+    },
+    {
+      "epoch": 1.601536521041165,
+      "grad_norm": 0.71875,
+      "learning_rate": 1.1629457581692616e-06,
+      "loss": 1.4537,
+      "step": 437
+    },
+    {
+      "epoch": 1.6052058250200665,
+      "grad_norm": 0.6953125,
+      "learning_rate": 1.1425541008902852e-06,
+      "loss": 1.4817,
+      "step": 438
+    },
+    {
+      "epoch": 1.608875128998968,
+      "grad_norm": 0.7109375,
+      "learning_rate": 1.1223197215860065e-06,
+      "loss": 1.4836,
+      "step": 439
+    },
+    {
+      "epoch": 1.6125444329778695,
+      "grad_norm": 0.65234375,
+      "learning_rate": 1.1022434452640252e-06,
+      "loss": 1.4107,
+      "step": 440
+    },
+    {
+      "epoch": 1.616213736956771,
+      "grad_norm": 0.671875,
+      "learning_rate": 1.0823260904856791e-06,
+      "loss": 1.4774,
+      "step": 441
+    },
+    {
+      "epoch": 1.6198830409356724,
+      "grad_norm": 0.671875,
+      "learning_rate": 1.0625684693326727e-06,
+      "loss": 1.4588,
+      "step": 442
+    },
+    {
+      "epoch": 1.623552344914574,
+      "grad_norm": 0.6875,
+      "learning_rate": 1.0429713873739505e-06,
+      "loss": 1.4889,
+      "step": 443
+    },
+    {
+      "epoch": 1.6272216488934754,
+      "grad_norm": 0.68359375,
+      "learning_rate": 1.0235356436328675e-06,
+      "loss": 1.4724,
+      "step": 444
+    },
+    {
+      "epoch": 1.630890952872377,
+      "grad_norm": 0.671875,
+      "learning_rate": 1.0042620305546069e-06,
+      "loss": 1.4209,
+      "step": 445
+    },
+    {
+      "epoch": 1.6345602568512785,
+      "grad_norm": 0.70703125,
+      "learning_rate": 9.851513339738627e-07,
+      "loss": 1.4596,
+      "step": 446
+    },
+    {
+      "epoch": 1.63822956083018,
+      "grad_norm": 0.77734375,
+      "learning_rate": 9.662043330828086e-07,
+      "loss": 1.4493,
+      "step": 447
+    },
+    {
+      "epoch": 1.6418988648090815,
+      "grad_norm": 0.6640625,
+      "learning_rate": 9.474218003993275e-07,
+      "loss": 1.4586,
+      "step": 448
+    },
+    {
+      "epoch": 1.645568168787983,
+      "grad_norm": 0.6875,
+      "learning_rate": 9.288045017355035e-07,
+      "loss": 1.4519,
+      "step": 449
+    },
+    {
+      "epoch": 1.6492374727668846,
+      "grad_norm": 0.6796875,
+      "learning_rate": 9.10353196166412e-07,
+      "loss": 1.4053,
+      "step": 450
+    },
+    {
+      "epoch": 1.6529067767457861,
+      "grad_norm": 0.66796875,
+      "learning_rate": 8.920686359991615e-07,
+      "loss": 1.452,
+      "step": 451
+    },
+    {
+      "epoch": 1.6565760807246876,
+      "grad_norm": 0.67578125,
+      "learning_rate": 8.739515667422211e-07,
+      "loss": 1.4608,
+      "step": 452
+    },
+    {
+      "epoch": 1.6602453847035892,
+      "grad_norm": 0.73828125,
+      "learning_rate": 8.560027270750276e-07,
+      "loss": 1.4702,
+      "step": 453
+    },
+    {
+      "epoch": 1.6639146886824907,
+      "grad_norm": 0.7109375,
+      "learning_rate": 8.382228488178639e-07,
+      "loss": 1.4405,
+      "step": 454
+    },
+    {
+      "epoch": 1.667583992661392,
+      "grad_norm": 0.6796875,
+      "learning_rate": 8.206126569020234e-07,
+      "loss": 1.4379,
+      "step": 455
+    },
+    {
+      "epoch": 1.6712532966402935,
+      "grad_norm": 0.7265625,
+      "learning_rate": 8.031728693402502e-07,
+      "loss": 1.4604,
+      "step": 456
+    },
+    {
+      "epoch": 1.674922600619195,
+      "grad_norm": 0.71484375,
+      "learning_rate": 7.859041971974668e-07,
+      "loss": 1.4493,
+      "step": 457
+    },
+    {
+      "epoch": 1.6785919045980966,
+      "grad_norm": 0.7109375,
+      "learning_rate": 7.6880734456178e-07,
+      "loss": 1.4538,
+      "step": 458
+    },
+    {
+      "epoch": 1.682261208576998,
+      "grad_norm": 0.66015625,
+      "learning_rate": 7.518830085157735e-07,
+      "loss": 1.4081,
+      "step": 459
+    },
+    {
+      "epoch": 1.6859305125558994,
+      "grad_norm": 0.69140625,
+      "learning_rate": 7.351318791080881e-07,
+      "loss": 1.4211,
+      "step": 460
+    },
+    {
+      "epoch": 1.689599816534801,
+      "grad_norm": 0.70703125,
+      "learning_rate": 7.185546393252835e-07,
+      "loss": 1.4536,
+      "step": 461
+    },
+    {
+      "epoch": 1.6932691205137025,
+      "grad_norm": 0.6953125,
+      "learning_rate": 7.021519650639952e-07,
+      "loss": 1.4332,
+      "step": 462
+    },
+    {
+      "epoch": 1.696938424492604,
+      "grad_norm": 0.6953125,
+      "learning_rate": 6.859245251033697e-07,
+      "loss": 1.4219,
+      "step": 463
+    },
+    {
+      "epoch": 1.7006077284715055,
+      "grad_norm": 0.671875,
+      "learning_rate": 6.698729810778065e-07,
+      "loss": 1.4141,
+      "step": 464
+    },
+    {
+      "epoch": 1.704277032450407,
+      "grad_norm": 0.68359375,
+      "learning_rate": 6.539979874499747e-07,
+      "loss": 1.4131,
+      "step": 465
+    },
+    {
+      "epoch": 1.7079463364293086,
+      "grad_norm": 0.69140625,
+      "learning_rate": 6.383001914841252e-07,
+      "loss": 1.423,
+      "step": 466
+    },
+    {
+      "epoch": 1.7116156404082101,
+      "grad_norm": 0.68359375,
+      "learning_rate": 6.227802332197125e-07,
+      "loss": 1.4103,
+      "step": 467
+    },
+    {
+      "epoch": 1.7152849443871117,
+      "grad_norm": 0.70703125,
+      "learning_rate": 6.074387454452891e-07,
+      "loss": 1.4348,
+      "step": 468
+    },
+    {
+      "epoch": 1.7189542483660132,
+      "grad_norm": 0.69921875,
+      "learning_rate": 5.922763536727023e-07,
+      "loss": 1.4247,
+      "step": 469
+    },
+    {
+      "epoch": 1.7226235523449147,
+      "grad_norm": 0.71875,
+      "learning_rate": 5.772936761116027e-07,
+      "loss": 1.4569,
+      "step": 470
+    },
+    {
+      "epoch": 1.7262928563238162,
+      "grad_norm": 0.703125,
+      "learning_rate": 5.624913236442287e-07,
+      "loss": 1.5117,
+      "step": 471
+    },
+    {
+      "epoch": 1.7299621603027175,
+      "grad_norm": 0.66015625,
+      "learning_rate": 5.478698998004967e-07,
+      "loss": 1.3924,
+      "step": 472
+    },
+    {
+      "epoch": 1.733631464281619,
+      "grad_norm": 0.7421875,
+      "learning_rate": 5.334300007334065e-07,
+      "loss": 1.4718,
+      "step": 473
+    },
+    {
+      "epoch": 1.7373007682605206,
+      "grad_norm": 0.6953125,
+      "learning_rate": 5.191722151947227e-07,
+      "loss": 1.4761,
+      "step": 474
+    },
+    {
+      "epoch": 1.7409700722394221,
+      "grad_norm": 0.75,
+      "learning_rate": 5.050971245109709e-07,
+      "loss": 1.526,
+      "step": 475
+    },
+    {
+      "epoch": 1.7446393762183234,
+      "grad_norm": 0.6640625,
+      "learning_rate": 4.91205302559743e-07,
+      "loss": 1.4963,
+      "step": 476
+    },
+    {
+      "epoch": 1.748308680197225,
+      "grad_norm": 0.703125,
+      "learning_rate": 4.77497315746292e-07,
+      "loss": 1.5114,
+      "step": 477
+    },
+    {
+      "epoch": 1.7519779841761265,
+      "grad_norm": 0.69921875,
+      "learning_rate": 4.639737229804403e-07,
+      "loss": 1.456,
+      "step": 478
+    },
+    {
+      "epoch": 1.755647288155028,
+      "grad_norm": 0.734375,
+      "learning_rate": 4.5063507565379195e-07,
+      "loss": 1.4133,
+      "step": 479
+    },
+    {
+      "epoch": 1.7593165921339295,
+      "grad_norm": 0.69921875,
+      "learning_rate": 4.374819176172501e-07,
+      "loss": 1.4294,
+      "step": 480
+    },
+    {
+      "epoch": 1.762985896112831,
+      "grad_norm": 0.71484375,
+      "learning_rate": 4.245147851588438e-07,
+      "loss": 1.3787,
+      "step": 481
+    },
+    {
+      "epoch": 1.7666552000917326,
+      "grad_norm": 0.671875,
+      "learning_rate": 4.1173420698186027e-07,
+      "loss": 1.4484,
+      "step": 482
+    },
+    {
+      "epoch": 1.7703245040706341,
+      "grad_norm": 0.7265625,
+      "learning_rate": 3.9914070418329123e-07,
+      "loss": 1.4657,
+      "step": 483
+    },
+    {
+      "epoch": 1.7703245040706341,
+      "eval_loss": 1.4023281335830688,
+      "eval_runtime": 86.4904,
+      "eval_samples_per_second": 8.961,
+      "eval_steps_per_second": 4.486,
+      "step": 483
+    },
+    {
+      "epoch": 1.7739938080495357,
+      "grad_norm": 0.66015625,
+      "learning_rate": 3.8673479023258464e-07,
+      "loss": 1.4335,
+      "step": 484
+    },
+    {
+      "epoch": 1.7776631120284372,
+      "grad_norm": 0.6953125,
+      "learning_rate": 3.7451697095070736e-07,
+      "loss": 1.4129,
+      "step": 485
+    },
+    {
+      "epoch": 1.7813324160073387,
+      "grad_norm": 0.66015625,
+      "learning_rate": 3.6248774448952695e-07,
+      "loss": 1.3978,
+      "step": 486
+    },
+    {
+      "epoch": 1.7850017199862402,
+      "grad_norm": 0.83984375,
+      "learning_rate": 3.506476013114946e-07,
+      "loss": 1.4322,
+      "step": 487
+    },
+    {
+      "epoch": 1.7886710239651418,
+      "grad_norm": 0.671875,
+      "learning_rate": 3.3899702416965166e-07,
+      "loss": 1.4127,
+      "step": 488
+    },
+    {
+      "epoch": 1.792340327944043,
+      "grad_norm": 0.69921875,
+      "learning_rate": 3.2753648808794505e-07,
+      "loss": 1.418,
+      "step": 489
+    },
+    {
+      "epoch": 1.7960096319229446,
+      "grad_norm": 0.67578125,
+      "learning_rate": 3.1626646034186084e-07,
+      "loss": 1.4601,
+      "step": 490
+    },
+    {
+      "epoch": 1.7996789359018461,
+      "grad_norm": 0.66015625,
+      "learning_rate": 3.05187400439369e-07,
+      "loss": 1.4585,
+      "step": 491
+    },
+    {
+      "epoch": 1.8033482398807477,
+      "grad_norm": 0.65625,
+      "learning_rate": 2.942997601021924e-07,
+      "loss": 1.4127,
+      "step": 492
+    },
+    {
+      "epoch": 1.807017543859649,
+      "grad_norm": 0.66796875,
+      "learning_rate": 2.8360398324738415e-07,
+      "loss": 1.437,
+      "step": 493
+    },
+    {
+      "epoch": 1.8106868478385505,
+      "grad_norm": 0.6875,
+      "learning_rate": 2.7310050596923323e-07,
+      "loss": 1.4759,
+      "step": 494
+    },
+    {
+      "epoch": 1.814356151817452,
+      "grad_norm": 0.703125,
+      "learning_rate": 2.6278975652147875e-07,
+      "loss": 1.4243,
+      "step": 495
+    },
+    {
+      "epoch": 1.8180254557963536,
+      "grad_norm": 0.6796875,
+      "learning_rate": 2.5267215529985346e-07,
+      "loss": 1.4361,
+      "step": 496
+    },
+    {
+      "epoch": 1.821694759775255,
+      "grad_norm": 0.66796875,
+      "learning_rate": 2.427481148249383e-07,
+      "loss": 1.4993,
+      "step": 497
+    },
+    {
+      "epoch": 1.8253640637541566,
+      "grad_norm": 0.6796875,
+      "learning_rate": 2.330180397253473e-07,
+      "loss": 1.4303,
+      "step": 498
+    },
+    {
+      "epoch": 1.8290333677330581,
+      "grad_norm": 0.71875,
+      "learning_rate": 2.2348232672122937e-07,
+      "loss": 1.4701,
+      "step": 499
+    },
+    {
+      "epoch": 1.8327026717119597,
+      "grad_norm": 0.70703125,
+      "learning_rate": 2.141413646080881e-07,
+      "loss": 1.4679,
+      "step": 500
+    },
+    {
+      "epoch": 1.8363719756908612,
+      "grad_norm": 0.71484375,
+      "learning_rate": 2.049955342409349e-07,
+      "loss": 1.4148,
+      "step": 501
+    },
+    {
+      "epoch": 1.8400412796697627,
+      "grad_norm": 0.6875,
+      "learning_rate": 1.9604520851876196e-07,
+      "loss": 1.4347,
+      "step": 502
+    },
+    {
+      "epoch": 1.8437105836486642,
+      "grad_norm": 0.6875,
+      "learning_rate": 1.8729075236932903e-07,
+      "loss": 1.4295,
+      "step": 503
+    },
+    {
+      "epoch": 1.8473798876275658,
+      "grad_norm": 0.734375,
+      "learning_rate": 1.787325227342951e-07,
+      "loss": 1.4682,
+      "step": 504
+    },
+    {
+      "epoch": 1.8510491916064673,
+      "grad_norm": 0.69140625,
+      "learning_rate": 1.7037086855465902e-07,
+      "loss": 1.4757,
+      "step": 505
+    },
+    {
+      "epoch": 1.8547184955853686,
+      "grad_norm": 0.6953125,
+      "learning_rate": 1.6220613075653201e-07,
+      "loss": 1.5042,
+      "step": 506
+    },
+    {
+      "epoch": 1.8583877995642701,
+      "grad_norm": 0.69921875,
+      "learning_rate": 1.542386422372405e-07,
+      "loss": 1.4796,
+      "step": 507
+    },
+    {
+      "epoch": 1.8620571035431717,
+      "grad_norm": 0.703125,
+      "learning_rate": 1.4646872785175182e-07,
+      "loss": 1.4894,
+      "step": 508
+    },
+    {
+      "epoch": 1.8657264075220732,
+      "grad_norm": 0.71875,
+      "learning_rate": 1.388967043994266e-07,
+      "loss": 1.4937,
+      "step": 509
+    },
+    {
+      "epoch": 1.8693957115009745,
+      "grad_norm": 0.71875,
+      "learning_rate": 1.3152288061110518e-07,
+      "loss": 1.4662,
+      "step": 510
+    },
+    {
+      "epoch": 1.873065015479876,
+      "grad_norm": 0.66015625,
+      "learning_rate": 1.243475571365177e-07,
+      "loss": 1.4787,
+      "step": 511
+    },
+    {
+      "epoch": 1.8767343194587776,
+      "grad_norm": 0.70703125,
+      "learning_rate": 1.1737102653202825e-07,
+      "loss": 1.4981,
+      "step": 512
+    },
+    {
+      "epoch": 1.880403623437679,
+      "grad_norm": 0.65625,
+      "learning_rate": 1.1059357324870456e-07,
+      "loss": 1.4118,
+      "step": 513
+    },
+    {
+      "epoch": 1.8840729274165806,
+      "grad_norm": 0.6953125,
+      "learning_rate": 1.0401547362071939e-07,
+      "loss": 1.4272,
+      "step": 514
+    },
+    {
+      "epoch": 1.8877422313954821,
+      "grad_norm": 0.66015625,
+      "learning_rate": 9.763699585408737e-08,
+      "loss": 1.4569,
+      "step": 515
+    },
+    {
+      "epoch": 1.8914115353743837,
+      "grad_norm": 0.75390625,
+      "learning_rate": 9.145840001572537e-08,
+      "loss": 1.4603,
+      "step": 516
+    },
+    {
+      "epoch": 1.8950808393532852,
+      "grad_norm": 0.69921875,
+      "learning_rate": 8.547993802285215e-08,
+      "loss": 1.4544,
+      "step": 517
+    },
+    {
+      "epoch": 1.8987501433321867,
+      "grad_norm": 0.65625,
+      "learning_rate": 7.970185363271432e-08,
+      "loss": 1.4413,
+      "step": 518
+    },
+    {
+      "epoch": 1.9024194473110883,
+      "grad_norm": 0.7109375,
+      "learning_rate": 7.41243824326504e-08,
+      "loss": 1.464,
+      "step": 519
+    },
+    {
+      "epoch": 1.9060887512899898,
+      "grad_norm": 0.69140625,
+      "learning_rate": 6.8747751830483e-08,
+      "loss": 1.4288,
+      "step": 520
+    },
+    {
+      "epoch": 1.9097580552688913,
+      "grad_norm": 0.65234375,
+      "learning_rate": 6.357218104524832e-08,
+      "loss": 1.4477,
+      "step": 521
+    },
+    {
+      "epoch": 1.9134273592477928,
+      "grad_norm": 0.73046875,
+      "learning_rate": 5.8597881098257924e-08,
+      "loss": 1.4375,
+      "step": 522
+    },
+    {
+      "epoch": 1.9170966632266941,
+      "grad_norm": 0.7578125,
+      "learning_rate": 5.382505480449274e-08,
+      "loss": 1.477,
+      "step": 523
+    },
+    {
+      "epoch": 1.9207659672055957,
+      "grad_norm": 0.68359375,
+      "learning_rate": 4.925389676433745e-08,
+      "loss": 1.4289,
+      "step": 524
+    },
+    {
+      "epoch": 1.9244352711844972,
+      "grad_norm": 0.6328125,
+      "learning_rate": 4.48845933556441e-08,
+      "loss": 1.4622,
+      "step": 525
+    },
+    {
+      "epoch": 1.9281045751633987,
+      "grad_norm": 0.671875,
+      "learning_rate": 4.071732272613149e-08,
+      "loss": 1.4519,
+      "step": 526
+    },
+    {
+      "epoch": 1.9317738791423,
+      "grad_norm": 0.67578125,
+      "learning_rate": 3.675225478612432e-08,
+      "loss": 1.4413,
+      "step": 527
+    },
+    {
+      "epoch": 1.9354431831212016,
+      "grad_norm": 0.88671875,
+      "learning_rate": 3.2989551201624836e-08,
+      "loss": 1.4628,
+      "step": 528
+    },
+    {
+      "epoch": 1.939112487100103,
+      "grad_norm": 0.68359375,
+      "learning_rate": 2.9429365387719232e-08,
+      "loss": 1.4706,
+      "step": 529
+    },
+    {
+      "epoch": 1.9427817910790046,
+      "grad_norm": 0.6796875,
+      "learning_rate": 2.6071842502326526e-08,
+      "loss": 1.4369,
+      "step": 530
+    },
+    {
+      "epoch": 1.9464510950579061,
+      "grad_norm": 0.7734375,
+      "learning_rate": 2.2917119440275524e-08,
+      "loss": 1.4531,
+      "step": 531
+    },
+    {
+      "epoch": 1.9501203990368077,
+      "grad_norm": 0.69140625,
+      "learning_rate": 1.996532482772595e-08,
+      "loss": 1.4549,
+      "step": 532
+    },
+    {
+      "epoch": 1.9537897030157092,
+      "grad_norm": 0.65625,
+      "learning_rate": 1.7216579016925415e-08,
+      "loss": 1.4083,
+      "step": 533
+    },
+    {
+      "epoch": 1.9574590069946107,
+      "grad_norm": 0.6796875,
+      "learning_rate": 1.4670994081297796e-08,
+      "loss": 1.4555,
+      "step": 534
+    },
+    {
+      "epoch": 1.9611283109735123,
+      "grad_norm": 0.671875,
+      "learning_rate": 1.2328673810877989e-08,
+      "loss": 1.4682,
+      "step": 535
+    },
+    {
+      "epoch": 1.9647976149524138,
+      "grad_norm": 0.6484375,
+      "learning_rate": 1.0189713708078086e-08,
+      "loss": 1.4423,
+      "step": 536
+    },
+    {
+      "epoch": 1.9684669189313153,
+      "grad_norm": 0.73828125,
+      "learning_rate": 8.254200983794369e-09,
+      "loss": 1.4146,
+      "step": 537
+    },
+    {
+      "epoch": 1.9721362229102168,
+      "grad_norm": 0.6875,
+      "learning_rate": 6.5222145538501595e-09,
+      "loss": 1.433,
+      "step": 538
+    },
+    {
+      "epoch": 1.9758055268891184,
+      "grad_norm": 0.66015625,
+      "learning_rate": 4.9938250357806085e-09,
+      "loss": 1.4467,
+      "step": 539
+    },
+    {
+      "epoch": 1.9794748308680197,
+      "grad_norm": 0.6875,
+      "learning_rate": 3.669094745950008e-09,
+      "loss": 1.4049,
+      "step": 540
+    },
+    {
+      "epoch": 1.9831441348469212,
+      "grad_norm": 0.65234375,
+      "learning_rate": 2.548077697014373e-09,
+      "loss": 1.4835,
+      "step": 541
+    },
+    {
+      "epoch": 1.9868134388258227,
+      "grad_norm": 0.671875,
+      "learning_rate": 1.6308195957182028e-09,
+      "loss": 1.4528,
+      "step": 542
+    },
+    {
+      "epoch": 1.9904827428047243,
+      "grad_norm": 0.7109375,
+      "learning_rate": 9.173578410281992e-10,
+      "loss": 1.4519,
+      "step": 543
+    },
+    {
+      "epoch": 1.9941520467836256,
+      "grad_norm": 0.671875,
+      "learning_rate": 4.0772152261336906e-10,
+      "loss": 1.4406,
+      "step": 544
+    },
+    {
+      "epoch": 1.997821350762527,
+      "grad_norm": 0.7265625,
+      "learning_rate": 1.0193141965486597e-10,
+      "loss": 1.4137,
+      "step": 545
+    },
+    {
+      "epoch": 2.0014906547414286,
+      "grad_norm": 0.703125,
+      "learning_rate": 0.0,
+      "loss": 1.4424,
+      "step": 546
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 546,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 137,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.2144265254892732e+19,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2629d03f8cfdaa9cd645a0ce9ebf1c262561700d6e7e7e0434fc1b65708b3c42
+size 6136