Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,73 @@
+---
+library_name: transformers
+license: other
+base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: reasoning-multilingual-R1-Llama-70B-train
+  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. -->
+
+# reasoning-multilingual-R1-Llama-70B-train
+
+This model is a fine-tuned version of [deepseek-ai/DeepSeek-R1-Distill-Qwen-7B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B) on the reasoning-multilingual-R1-Llama-70B-train dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5135
+
+## 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: 8
+- total_train_batch_size: 8
+- total_eval_batch_size: 8
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.01
+- num_epochs: 3.0
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.5539        | 0.3158 | 6    | 0.3874          |
+| 0.5069        | 0.6316 | 12   | 0.4255          |
+| 0.5634        | 0.9474 | 18   | 0.4700          |
+| 0.7207        | 1.2632 | 24   | 0.5061          |
+| 0.6525        | 1.5789 | 30   | 0.5270          |
+| 0.7435        | 1.8947 | 36   | 0.5325          |
+| 0.7488        | 2.2105 | 42   | 0.5383          |
+| 0.5786        | 2.5263 | 48   | 0.5181          |
+| 0.7325        | 2.8421 | 54   | 0.5146          |
+
+
+### Framework versions
+
+- Transformers 4.46.1
+- Pytorch 2.6.0.dev20241113+rocm6.2
+- Datasets 3.1.0
+- Tokenizers 0.20.3

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.5134892463684082,
+    "eval_runtime": 0.8691,
+    "eval_samples_per_second": 2.301,
+    "eval_steps_per_second": 1.151,
+    "total_flos": 8.713084645618483e+16,
+    "train_loss": 0.597966728503244,
+    "train_runtime": 375.3657,
+    "train_samples_per_second": 1.183,
+    "train_steps_per_second": 0.152
+}

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "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": 10000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": false,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.5134892463684082,
+    "eval_runtime": 0.8691,
+    "eval_samples_per_second": 2.301,
+    "eval_steps_per_second": 1.151
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 151646,
+  "do_sample": true,
+  "eos_token_id": 151643,
+  "temperature": 0.6,
+  "top_p": 0.95,
+  "transformers_version": "4.46.1"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbf0fa5ee60a1611f9d36b43b45693ef29c5e4f269c34c9cc925c35c79270739
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4dc633052f92d4f76912364e36b93746ec905f2f84eb381103b949c123b243d
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64d1b9b8c2a51bd09b78b006916c36f7d9d3844f09fa9db1b069654a9ff04e4e
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6de8a7fe503fc5d5efa8e47c5dc9ce40e333790c29ad13ab3b10b14ea02c1cf
+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"
+  }
+}

runs/Feb06_19-06-36_amd-G262-ZO0-00/events.out.tfevents.1738869203.amd-G262-ZO0-00.62856.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd23a096c3ed8f05739277ef23818812da868f5068609196643a3a7053a08023
+size 20084

runs/Feb06_19-06-36_amd-G262-ZO0-00/events.out.tfevents.1738869602.amd-G262-ZO0-00.62856.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa4dc5d466f95590aed19d951b6298c7d0f36206638421930221955141af8be5
+size 354

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02643f00207dfc5ed248992486bde04314c21dca556bf65ce520690962b8db63
+size 11422965

tokenizer_config.json

@@ -0,0 +1,204 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<｜User｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151645": {
+      "content": "<｜Assistant｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151646": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|EOT|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151648": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151649": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "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": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>'}}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "legacy": true,
+  "model_max_length": 16384,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 8.713084645618483e+16,
+    "train_loss": 0.597966728503244,
+    "train_runtime": 375.3657,
+    "train_samples_per_second": 1.183,
+    "train_steps_per_second": 0.152
+}

trainer_log.jsonl

@@ -0,0 +1,67 @@
+{"current_steps": 1, "total_steps": 57, "loss": 0.5234, "lr": 1e-05, "epoch": 0.05263157894736842, "percentage": 1.75, "elapsed_time": "0:00:08", "remaining_time": "0:08:21"}
+{"current_steps": 2, "total_steps": 57, "loss": 0.4781, "lr": 9.992134075089085e-06, "epoch": 0.10526315789473684, "percentage": 3.51, "elapsed_time": "0:00:41", "remaining_time": "0:19:05"}
+{"current_steps": 3, "total_steps": 57, "loss": 0.5327, "lr": 9.968561049466214e-06, "epoch": 0.15789473684210525, "percentage": 5.26, "elapsed_time": "0:00:45", "remaining_time": "0:13:47"}
+{"current_steps": 4, "total_steps": 57, "loss": 0.4726, "lr": 9.92935509259118e-06, "epoch": 0.21052631578947367, "percentage": 7.02, "elapsed_time": "0:00:50", "remaining_time": "0:11:06"}
+{"current_steps": 5, "total_steps": 57, "loss": 0.4571, "lr": 9.874639560909118e-06, "epoch": 0.2631578947368421, "percentage": 8.77, "elapsed_time": "0:00:54", "remaining_time": "0:09:27"}
+{"current_steps": 6, "total_steps": 57, "loss": 0.5539, "lr": 9.804586609725499e-06, "epoch": 0.3157894736842105, "percentage": 10.53, "elapsed_time": "0:00:58", "remaining_time": "0:08:20"}
+{"current_steps": 6, "total_steps": 57, "eval_loss": 0.3873564898967743, "epoch": 0.3157894736842105, "percentage": 10.53, "elapsed_time": "0:00:59", "remaining_time": "0:08:28"}
+{"current_steps": 7, "total_steps": 57, "loss": 0.3949, "lr": 9.719416651541839e-06, "epoch": 0.3684210526315789, "percentage": 12.28, "elapsed_time": "0:01:04", "remaining_time": "0:07:38"}
+{"current_steps": 8, "total_steps": 57, "loss": 0.5256, "lr": 9.619397662556434e-06, "epoch": 0.42105263157894735, "percentage": 14.04, "elapsed_time": "0:01:08", "remaining_time": "0:06:59"}
+{"current_steps": 9, "total_steps": 57, "loss": 0.4265, "lr": 9.504844339512096e-06, "epoch": 0.47368421052631576, "percentage": 15.79, "elapsed_time": "0:01:12", "remaining_time": "0:06:28"}
+{"current_steps": 10, "total_steps": 57, "loss": 0.6413, "lr": 9.376117109543769e-06, "epoch": 0.5263157894736842, "percentage": 17.54, "elapsed_time": "0:01:17", "remaining_time": "0:06:02"}
+{"current_steps": 11, "total_steps": 57, "loss": 0.5344, "lr": 9.233620996141421e-06, "epoch": 0.5789473684210527, "percentage": 19.3, "elapsed_time": "0:01:21", "remaining_time": "0:05:40"}
+{"current_steps": 12, "total_steps": 57, "loss": 0.5069, "lr": 9.077804344796302e-06, "epoch": 0.631578947368421, "percentage": 21.05, "elapsed_time": "0:01:25", "remaining_time": "0:05:21"}
+{"current_steps": 12, "total_steps": 57, "eval_loss": 0.42546606063842773, "epoch": 0.631578947368421, "percentage": 21.05, "elapsed_time": "0:01:26", "remaining_time": "0:05:24"}
+{"current_steps": 13, "total_steps": 57, "loss": 0.5058, "lr": 8.90915741234015e-06, "epoch": 0.6842105263157895, "percentage": 22.81, "elapsed_time": "0:01:30", "remaining_time": "0:05:07"}
+{"current_steps": 14, "total_steps": 57, "loss": 0.4587, "lr": 8.728210824415829e-06, "epoch": 0.7368421052631579, "percentage": 24.56, "elapsed_time": "0:01:35", "remaining_time": "0:04:52"}
+{"current_steps": 15, "total_steps": 57, "loss": 0.614, "lr": 8.535533905932739e-06, "epoch": 0.7894736842105263, "percentage": 26.32, "elapsed_time": "0:01:39", "remaining_time": "0:04:38"}
+{"current_steps": 16, "total_steps": 57, "loss": 0.644, "lr": 8.331732889760021e-06, "epoch": 0.8421052631578947, "percentage": 28.07, "elapsed_time": "0:01:43", "remaining_time": "0:04:26"}
+{"current_steps": 17, "total_steps": 57, "loss": 0.5248, "lr": 8.117449009293668e-06, "epoch": 0.8947368421052632, "percentage": 29.82, "elapsed_time": "0:01:48", "remaining_time": "0:04:14"}
+{"current_steps": 18, "total_steps": 57, "loss": 0.5634, "lr": 7.89335648089903e-06, "epoch": 0.9473684210526315, "percentage": 31.58, "elapsed_time": "0:01:52", "remaining_time": "0:04:04"}
+{"current_steps": 18, "total_steps": 57, "eval_loss": 0.47000423073768616, "epoch": 0.9473684210526315, "percentage": 31.58, "elapsed_time": "0:01:53", "remaining_time": "0:04:05"}
+{"current_steps": 19, "total_steps": 57, "loss": 0.655, "lr": 7.660160382576683e-06, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:01:57", "remaining_time": "0:03:55"}
+{"current_steps": 20, "total_steps": 57, "loss": 0.5225, "lr": 7.4185944355261996e-06, "epoch": 1.0526315789473684, "percentage": 35.09, "elapsed_time": "0:02:02", "remaining_time": "0:03:46"}
+{"current_steps": 21, "total_steps": 57, "loss": 0.5764, "lr": 7.169418695587791e-06, "epoch": 1.1052631578947367, "percentage": 36.84, "elapsed_time": "0:02:06", "remaining_time": "0:03:36"}
+{"current_steps": 22, "total_steps": 57, "loss": 0.5878, "lr": 6.913417161825449e-06, "epoch": 1.1578947368421053, "percentage": 38.6, "elapsed_time": "0:02:10", "remaining_time": "0:03:28"}
+{"current_steps": 23, "total_steps": 57, "loss": 0.6382, "lr": 6.651395309775837e-06, "epoch": 1.2105263157894737, "percentage": 40.35, "elapsed_time": "0:02:15", "remaining_time": "0:03:19"}
+{"current_steps": 24, "total_steps": 57, "loss": 0.7207, "lr": 6.384177557124247e-06, "epoch": 1.263157894736842, "percentage": 42.11, "elapsed_time": "0:02:19", "remaining_time": "0:03:11"}
+{"current_steps": 24, "total_steps": 57, "eval_loss": 0.5061320066452026, "epoch": 1.263157894736842, "percentage": 42.11, "elapsed_time": "0:02:20", "remaining_time": "0:03:13"}
+{"current_steps": 25, "total_steps": 57, "loss": 0.5727, "lr": 6.112604669781572e-06, "epoch": 1.3157894736842106, "percentage": 43.86, "elapsed_time": "0:02:24", "remaining_time": "0:03:05"}
+{"current_steps": 26, "total_steps": 57, "loss": 0.6236, "lr": 5.837531116523683e-06, "epoch": 1.368421052631579, "percentage": 45.61, "elapsed_time": "0:02:29", "remaining_time": "0:02:57"}
+{"current_steps": 27, "total_steps": 57, "loss": 0.5477, "lr": 5.559822380516539e-06, "epoch": 1.4210526315789473, "percentage": 47.37, "elapsed_time": "0:02:33", "remaining_time": "0:02:50"}
+{"current_steps": 28, "total_steps": 57, "loss": 0.7404, "lr": 5.2803522361859596e-06, "epoch": 1.4736842105263157, "percentage": 49.12, "elapsed_time": "0:02:37", "remaining_time": "0:02:43"}
+{"current_steps": 29, "total_steps": 57, "loss": 0.5133, "lr": 5e-06, "epoch": 1.526315789473684, "percentage": 50.88, "elapsed_time": "0:02:42", "remaining_time": "0:02:36"}
+{"current_steps": 30, "total_steps": 57, "loss": 0.6525, "lr": 4.719647763814041e-06, "epoch": 1.5789473684210527, "percentage": 52.63, "elapsed_time": "0:02:46", "remaining_time": "0:02:29"}
+{"current_steps": 30, "total_steps": 57, "eval_loss": 0.5270132422447205, "epoch": 1.5789473684210527, "percentage": 52.63, "elapsed_time": "0:02:47", "remaining_time": "0:02:30"}
+{"current_steps": 31, "total_steps": 57, "loss": 0.538, "lr": 4.4401776194834615e-06, "epoch": 1.631578947368421, "percentage": 54.39, "elapsed_time": "0:02:51", "remaining_time": "0:02:23"}
+{"current_steps": 32, "total_steps": 57, "loss": 0.6714, "lr": 4.162468883476319e-06, "epoch": 1.6842105263157894, "percentage": 56.14, "elapsed_time": "0:02:55", "remaining_time": "0:02:17"}
+{"current_steps": 33, "total_steps": 57, "loss": 0.7117, "lr": 3.887395330218429e-06, "epoch": 1.736842105263158, "percentage": 57.89, "elapsed_time": "0:03:00", "remaining_time": "0:02:11"}
+{"current_steps": 34, "total_steps": 57, "loss": 0.5645, "lr": 3.6158224428757538e-06, "epoch": 1.7894736842105263, "percentage": 59.65, "elapsed_time": "0:03:04", "remaining_time": "0:02:04"}
+{"current_steps": 35, "total_steps": 57, "loss": 0.716, "lr": 3.3486046902241663e-06, "epoch": 1.8421052631578947, "percentage": 61.4, "elapsed_time": "0:03:08", "remaining_time": "0:01:58"}
+{"current_steps": 36, "total_steps": 57, "loss": 0.7435, "lr": 3.0865828381745515e-06, "epoch": 1.8947368421052633, "percentage": 63.16, "elapsed_time": "0:03:13", "remaining_time": "0:01:52"}
+{"current_steps": 36, "total_steps": 57, "eval_loss": 0.5324785113334656, "epoch": 1.8947368421052633, "percentage": 63.16, "elapsed_time": "0:03:14", "remaining_time": "0:01:53"}
+{"current_steps": 37, "total_steps": 57, "loss": 0.7309, "lr": 2.83058130441221e-06, "epoch": 1.9473684210526314, "percentage": 64.91, "elapsed_time": "0:03:18", "remaining_time": "0:01:47"}
+{"current_steps": 38, "total_steps": 57, "loss": 0.5396, "lr": 2.5814055644738013e-06, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:03:22", "remaining_time": "0:01:41"}
+{"current_steps": 39, "total_steps": 57, "loss": 0.6829, "lr": 2.339839617423318e-06, "epoch": 2.0526315789473686, "percentage": 68.42, "elapsed_time": "0:03:27", "remaining_time": "0:01:35"}
+{"current_steps": 40, "total_steps": 57, "loss": 0.5327, "lr": 2.1066435191009717e-06, "epoch": 2.1052631578947367, "percentage": 70.18, "elapsed_time": "0:03:31", "remaining_time": "0:01:29"}
+{"current_steps": 41, "total_steps": 57, "loss": 0.532, "lr": 1.8825509907063328e-06, "epoch": 2.1578947368421053, "percentage": 71.93, "elapsed_time": "0:03:35", "remaining_time": "0:01:24"}
+{"current_steps": 42, "total_steps": 57, "loss": 0.7488, "lr": 1.6682671102399806e-06, "epoch": 2.2105263157894735, "percentage": 73.68, "elapsed_time": "0:03:40", "remaining_time": "0:01:18"}
+{"current_steps": 42, "total_steps": 57, "eval_loss": 0.5383380055427551, "epoch": 2.2105263157894735, "percentage": 73.68, "elapsed_time": "0:03:41", "remaining_time": "0:01:18"}
+{"current_steps": 43, "total_steps": 57, "loss": 0.5959, "lr": 1.4644660940672628e-06, "epoch": 2.263157894736842, "percentage": 75.44, "elapsed_time": "0:03:45", "remaining_time": "0:01:13"}
+{"current_steps": 44, "total_steps": 57, "loss": 0.5717, "lr": 1.2717891755841722e-06, "epoch": 2.3157894736842106, "percentage": 77.19, "elapsed_time": "0:03:49", "remaining_time": "0:01:07"}
+{"current_steps": 45, "total_steps": 57, "loss": 0.682, "lr": 1.0908425876598512e-06, "epoch": 2.3684210526315788, "percentage": 78.95, "elapsed_time": "0:03:54", "remaining_time": "0:01:02"}
+{"current_steps": 46, "total_steps": 57, "loss": 0.6275, "lr": 9.221956552036992e-07, "epoch": 2.4210526315789473, "percentage": 80.7, "elapsed_time": "0:03:58", "remaining_time": "0:00:57"}
+{"current_steps": 47, "total_steps": 57, "loss": 0.6225, "lr": 7.663790038585794e-07, "epoch": 2.473684210526316, "percentage": 82.46, "elapsed_time": "0:04:02", "remaining_time": "0:00:51"}
+{"current_steps": 48, "total_steps": 57, "loss": 0.5786, "lr": 6.238828904562316e-07, "epoch": 2.526315789473684, "percentage": 84.21, "elapsed_time": "0:04:07", "remaining_time": "0:00:46"}
+{"current_steps": 48, "total_steps": 57, "eval_loss": 0.5181117057800293, "epoch": 2.526315789473684, "percentage": 84.21, "elapsed_time": "0:04:08", "remaining_time": "0:00:46"}
+{"current_steps": 49, "total_steps": 57, "loss": 0.6937, "lr": 4.951556604879049e-07, "epoch": 2.5789473684210527, "percentage": 85.96, "elapsed_time": "0:04:12", "remaining_time": "0:00:41"}
+{"current_steps": 50, "total_steps": 57, "loss": 0.675, "lr": 3.8060233744356634e-07, "epoch": 2.6315789473684212, "percentage": 87.72, "elapsed_time": "0:04:16", "remaining_time": "0:00:35"}
+{"current_steps": 51, "total_steps": 57, "loss": 0.676, "lr": 2.8058334845816214e-07, "epoch": 2.6842105263157894, "percentage": 89.47, "elapsed_time": "0:04:20", "remaining_time": "0:00:30"}
+{"current_steps": 52, "total_steps": 57, "loss": 0.6332, "lr": 1.9541339027450256e-07, "epoch": 2.736842105263158, "percentage": 91.23, "elapsed_time": "0:04:25", "remaining_time": "0:00:25"}
+{"current_steps": 53, "total_steps": 57, "loss": 0.6212, "lr": 1.253604390908819e-07, "epoch": 2.7894736842105265, "percentage": 92.98, "elapsed_time": "0:04:29", "remaining_time": "0:00:20"}
+{"current_steps": 54, "total_steps": 57, "loss": 0.7325, "lr": 7.064490740882057e-08, "epoch": 2.8421052631578947, "percentage": 94.74, "elapsed_time": "0:04:34", "remaining_time": "0:00:15"}
+{"current_steps": 54, "total_steps": 57, "eval_loss": 0.5145716667175293, "epoch": 2.8421052631578947, "percentage": 94.74, "elapsed_time": "0:04:34", "remaining_time": "0:00:15"}
+{"current_steps": 55, "total_steps": 57, "loss": 0.5281, "lr": 3.143895053378698e-08, "epoch": 2.8947368421052633, "percentage": 96.49, "elapsed_time": "0:04:52", "remaining_time": "0:00:10"}
+{"current_steps": 56, "total_steps": 57, "loss": 0.7652, "lr": 7.865924910916977e-09, "epoch": 2.9473684210526314, "percentage": 98.25, "elapsed_time": "0:04:56", "remaining_time": "0:00:05"}
+{"current_steps": 57, "total_steps": 57, "loss": 0.66, "lr": 0.0, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:05:01", "remaining_time": "0:00:00"}
+{"current_steps": 57, "total_steps": 57, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:06:13", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,513 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 6,
+  "global_step": 57,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05263157894736842,
+      "grad_norm": 211.82034301757812,
+      "learning_rate": 1e-05,
+      "loss": 0.5234,
+      "step": 1
+    },
+    {
+      "epoch": 0.10526315789473684,
+      "grad_norm": 330236.46875,
+      "learning_rate": 9.992134075089085e-06,
+      "loss": 0.4781,
+      "step": 2
+    },
+    {
+      "epoch": 0.15789473684210525,
+      "grad_norm": 3773.773681640625,
+      "learning_rate": 9.968561049466214e-06,
+      "loss": 0.5327,
+      "step": 3
+    },
+    {
+      "epoch": 0.21052631578947367,
+      "grad_norm": 8766.265625,
+      "learning_rate": 9.92935509259118e-06,
+      "loss": 0.4726,
+      "step": 4
+    },
+    {
+      "epoch": 0.2631578947368421,
+      "grad_norm": 633.0609130859375,
+      "learning_rate": 9.874639560909118e-06,
+      "loss": 0.4571,
+      "step": 5
+    },
+    {
+      "epoch": 0.3157894736842105,
+      "grad_norm": 609995.625,
+      "learning_rate": 9.804586609725499e-06,
+      "loss": 0.5539,
+      "step": 6
+    },
+    {
+      "epoch": 0.3157894736842105,
+      "eval_loss": 0.3873564898967743,
+      "eval_runtime": 0.8662,
+      "eval_samples_per_second": 2.309,
+      "eval_steps_per_second": 1.154,
+      "step": 6
+    },
+    {
+      "epoch": 0.3684210526315789,
+      "grad_norm": 578.82763671875,
+      "learning_rate": 9.719416651541839e-06,
+      "loss": 0.3949,
+      "step": 7
+    },
+    {
+      "epoch": 0.42105263157894735,
+      "grad_norm": 227617.40625,
+      "learning_rate": 9.619397662556434e-06,
+      "loss": 0.5256,
+      "step": 8
+    },
+    {
+      "epoch": 0.47368421052631576,
+      "grad_norm": 785.8093872070312,
+      "learning_rate": 9.504844339512096e-06,
+      "loss": 0.4265,
+      "step": 9
+    },
+    {
+      "epoch": 0.5263157894736842,
+      "grad_norm": 354838.09375,
+      "learning_rate": 9.376117109543769e-06,
+      "loss": 0.6413,
+      "step": 10
+    },
+    {
+      "epoch": 0.5789473684210527,
+      "grad_norm": 3835.27197265625,
+      "learning_rate": 9.233620996141421e-06,
+      "loss": 0.5344,
+      "step": 11
+    },
+    {
+      "epoch": 0.631578947368421,
+      "grad_norm": 4633.39013671875,
+      "learning_rate": 9.077804344796302e-06,
+      "loss": 0.5069,
+      "step": 12
+    },
+    {
+      "epoch": 0.631578947368421,
+      "eval_loss": 0.42546606063842773,
+      "eval_runtime": 0.8681,
+      "eval_samples_per_second": 2.304,
+      "eval_steps_per_second": 1.152,
+      "step": 12
+    },
+    {
+      "epoch": 0.6842105263157895,
+      "grad_norm": 2101.546142578125,
+      "learning_rate": 8.90915741234015e-06,
+      "loss": 0.5058,
+      "step": 13
+    },
+    {
+      "epoch": 0.7368421052631579,
+      "grad_norm": 175295.453125,
+      "learning_rate": 8.728210824415829e-06,
+      "loss": 0.4587,
+      "step": 14
+    },
+    {
+      "epoch": 0.7894736842105263,
+      "grad_norm": 3184.1103515625,
+      "learning_rate": 8.535533905932739e-06,
+      "loss": 0.614,
+      "step": 15
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "grad_norm": 496073.1875,
+      "learning_rate": 8.331732889760021e-06,
+      "loss": 0.644,
+      "step": 16
+    },
+    {
+      "epoch": 0.8947368421052632,
+      "grad_norm": 11245.0107421875,
+      "learning_rate": 8.117449009293668e-06,
+      "loss": 0.5248,
+      "step": 17
+    },
+    {
+      "epoch": 0.9473684210526315,
+      "grad_norm": 600.7078857421875,
+      "learning_rate": 7.89335648089903e-06,
+      "loss": 0.5634,
+      "step": 18
+    },
+    {
+      "epoch": 0.9473684210526315,
+      "eval_loss": 0.47000423073768616,
+      "eval_runtime": 0.8698,
+      "eval_samples_per_second": 2.299,
+      "eval_steps_per_second": 1.15,
+      "step": 18
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1067464.375,
+      "learning_rate": 7.660160382576683e-06,
+      "loss": 0.655,
+      "step": 19
+    },
+    {
+      "epoch": 1.0526315789473684,
+      "grad_norm": 7849.232421875,
+      "learning_rate": 7.4185944355261996e-06,
+      "loss": 0.5225,
+      "step": 20
+    },
+    {
+      "epoch": 1.1052631578947367,
+      "grad_norm": 5074.62060546875,
+      "learning_rate": 7.169418695587791e-06,
+      "loss": 0.5764,
+      "step": 21
+    },
+    {
+      "epoch": 1.1578947368421053,
+      "grad_norm": 755949.375,
+      "learning_rate": 6.913417161825449e-06,
+      "loss": 0.5878,
+      "step": 22
+    },
+    {
+      "epoch": 1.2105263157894737,
+      "grad_norm": 1128.499267578125,
+      "learning_rate": 6.651395309775837e-06,
+      "loss": 0.6382,
+      "step": 23
+    },
+    {
+      "epoch": 1.263157894736842,
+      "grad_norm": 955.5560913085938,
+      "learning_rate": 6.384177557124247e-06,
+      "loss": 0.7207,
+      "step": 24
+    },
+    {
+      "epoch": 1.263157894736842,
+      "eval_loss": 0.5061320066452026,
+      "eval_runtime": 0.8698,
+      "eval_samples_per_second": 2.299,
+      "eval_steps_per_second": 1.15,
+      "step": 24
+    },
+    {
+      "epoch": 1.3157894736842106,
+      "grad_norm": 10727177.0,
+      "learning_rate": 6.112604669781572e-06,
+      "loss": 0.5727,
+      "step": 25
+    },
+    {
+      "epoch": 1.368421052631579,
+      "grad_norm": 835351.6875,
+      "learning_rate": 5.837531116523683e-06,
+      "loss": 0.6236,
+      "step": 26
+    },
+    {
+      "epoch": 1.4210526315789473,
+      "grad_norm": 24849.080078125,
+      "learning_rate": 5.559822380516539e-06,
+      "loss": 0.5477,
+      "step": 27
+    },
+    {
+      "epoch": 1.4736842105263157,
+      "grad_norm": 1144.915283203125,
+      "learning_rate": 5.2803522361859596e-06,
+      "loss": 0.7404,
+      "step": 28
+    },
+    {
+      "epoch": 1.526315789473684,
+      "grad_norm": 43178.171875,
+      "learning_rate": 5e-06,
+      "loss": 0.5133,
+      "step": 29
+    },
+    {
+      "epoch": 1.5789473684210527,
+      "grad_norm": 105640.3828125,
+      "learning_rate": 4.719647763814041e-06,
+      "loss": 0.6525,
+      "step": 30
+    },
+    {
+      "epoch": 1.5789473684210527,
+      "eval_loss": 0.5270132422447205,
+      "eval_runtime": 0.8703,
+      "eval_samples_per_second": 2.298,
+      "eval_steps_per_second": 1.149,
+      "step": 30
+    },
+    {
+      "epoch": 1.631578947368421,
+      "grad_norm": 2033.227783203125,
+      "learning_rate": 4.4401776194834615e-06,
+      "loss": 0.538,
+      "step": 31
+    },
+    {
+      "epoch": 1.6842105263157894,
+      "grad_norm": 679948.1875,
+      "learning_rate": 4.162468883476319e-06,
+      "loss": 0.6714,
+      "step": 32
+    },
+    {
+      "epoch": 1.736842105263158,
+      "grad_norm": 220607.5,
+      "learning_rate": 3.887395330218429e-06,
+      "loss": 0.7117,
+      "step": 33
+    },
+    {
+      "epoch": 1.7894736842105263,
+      "grad_norm": 13599.486328125,
+      "learning_rate": 3.6158224428757538e-06,
+      "loss": 0.5645,
+      "step": 34
+    },
+    {
+      "epoch": 1.8421052631578947,
+      "grad_norm": 651100.1875,
+      "learning_rate": 3.3486046902241663e-06,
+      "loss": 0.716,
+      "step": 35
+    },
+    {
+      "epoch": 1.8947368421052633,
+      "grad_norm": 575592.1875,
+      "learning_rate": 3.0865828381745515e-06,
+      "loss": 0.7435,
+      "step": 36
+    },
+    {
+      "epoch": 1.8947368421052633,
+      "eval_loss": 0.5324785113334656,
+      "eval_runtime": 0.8699,
+      "eval_samples_per_second": 2.299,
+      "eval_steps_per_second": 1.149,
+      "step": 36
+    },
+    {
+      "epoch": 1.9473684210526314,
+      "grad_norm": 163141.171875,
+      "learning_rate": 2.83058130441221e-06,
+      "loss": 0.7309,
+      "step": 37
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 3034.2685546875,
+      "learning_rate": 2.5814055644738013e-06,
+      "loss": 0.5396,
+      "step": 38
+    },
+    {
+      "epoch": 2.0526315789473686,
+      "grad_norm": 124152.5,
+      "learning_rate": 2.339839617423318e-06,
+      "loss": 0.6829,
+      "step": 39
+    },
+    {
+      "epoch": 2.1052631578947367,
+      "grad_norm": 3723410.75,
+      "learning_rate": 2.1066435191009717e-06,
+      "loss": 0.5327,
+      "step": 40
+    },
+    {
+      "epoch": 2.1578947368421053,
+      "grad_norm": 539427.625,
+      "learning_rate": 1.8825509907063328e-06,
+      "loss": 0.532,
+      "step": 41
+    },
+    {
+      "epoch": 2.2105263157894735,
+      "grad_norm": 20275.404296875,
+      "learning_rate": 1.6682671102399806e-06,
+      "loss": 0.7488,
+      "step": 42
+    },
+    {
+      "epoch": 2.2105263157894735,
+      "eval_loss": 0.5383380055427551,
+      "eval_runtime": 0.8703,
+      "eval_samples_per_second": 2.298,
+      "eval_steps_per_second": 1.149,
+      "step": 42
+    },
+    {
+      "epoch": 2.263157894736842,
+      "grad_norm": 505885.78125,
+      "learning_rate": 1.4644660940672628e-06,
+      "loss": 0.5959,
+      "step": 43
+    },
+    {
+      "epoch": 2.3157894736842106,
+      "grad_norm": 74390.25,
+      "learning_rate": 1.2717891755841722e-06,
+      "loss": 0.5717,
+      "step": 44
+    },
+    {
+      "epoch": 2.3684210526315788,
+      "grad_norm": 1850279.375,
+      "learning_rate": 1.0908425876598512e-06,
+      "loss": 0.682,
+      "step": 45
+    },
+    {
+      "epoch": 2.4210526315789473,
+      "grad_norm": 7982978.5,
+      "learning_rate": 9.221956552036992e-07,
+      "loss": 0.6275,
+      "step": 46
+    },
+    {
+      "epoch": 2.473684210526316,
+      "grad_norm": 132265160.0,
+      "learning_rate": 7.663790038585794e-07,
+      "loss": 0.6225,
+      "step": 47
+    },
+    {
+      "epoch": 2.526315789473684,
+      "grad_norm": 96502.90625,
+      "learning_rate": 6.238828904562316e-07,
+      "loss": 0.5786,
+      "step": 48
+    },
+    {
+      "epoch": 2.526315789473684,
+      "eval_loss": 0.5181117057800293,
+      "eval_runtime": 0.8701,
+      "eval_samples_per_second": 2.299,
+      "eval_steps_per_second": 1.149,
+      "step": 48
+    },
+    {
+      "epoch": 2.5789473684210527,
+      "grad_norm": 697082.1875,
+      "learning_rate": 4.951556604879049e-07,
+      "loss": 0.6937,
+      "step": 49
+    },
+    {
+      "epoch": 2.6315789473684212,
+      "grad_norm": 43987.10546875,
+      "learning_rate": 3.8060233744356634e-07,
+      "loss": 0.675,
+      "step": 50
+    },
+    {
+      "epoch": 2.6842105263157894,
+      "grad_norm": 47614.27734375,
+      "learning_rate": 2.8058334845816214e-07,
+      "loss": 0.676,
+      "step": 51
+    },
+    {
+      "epoch": 2.736842105263158,
+      "grad_norm": 79889032.0,
+      "learning_rate": 1.9541339027450256e-07,
+      "loss": 0.6332,
+      "step": 52
+    },
+    {
+      "epoch": 2.7894736842105265,
+      "grad_norm": 1658783.125,
+      "learning_rate": 1.253604390908819e-07,
+      "loss": 0.6212,
+      "step": 53
+    },
+    {
+      "epoch": 2.8421052631578947,
+      "grad_norm": 1998786.75,
+      "learning_rate": 7.064490740882057e-08,
+      "loss": 0.7325,
+      "step": 54
+    },
+    {
+      "epoch": 2.8421052631578947,
+      "eval_loss": 0.5145716667175293,
+      "eval_runtime": 0.871,
+      "eval_samples_per_second": 2.296,
+      "eval_steps_per_second": 1.148,
+      "step": 54
+    },
+    {
+      "epoch": 2.8947368421052633,
+      "grad_norm": 58182.7734375,
+      "learning_rate": 3.143895053378698e-08,
+      "loss": 0.5281,
+      "step": 55
+    },
+    {
+      "epoch": 2.9473684210526314,
+      "grad_norm": 854980864.0,
+      "learning_rate": 7.865924910916977e-09,
+      "loss": 0.7652,
+      "step": 56
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 4794.498046875,
+      "learning_rate": 0.0,
+      "loss": 0.66,
+      "step": 57
+    },
+    {
+      "epoch": 3.0,
+      "step": 57,
+      "total_flos": 8.713084645618483e+16,
+      "train_loss": 0.597966728503244,
+      "train_runtime": 375.3657,
+      "train_samples_per_second": 1.183,
+      "train_steps_per_second": 0.152
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 57,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 57,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 8.713084645618483e+16,
+  "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 sha256:670106e7415f8c706b417b6d321f986b824c8d292dfb90d8eaddadff0b554f77
+size 7160