Model save

.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 +1,58 @@
+---
+base_model: Qwen/Qwen2.5-1.5B-Instruct
+library_name: transformers
+model_name: Qwen2.5-1.5B-Open-R1-Distill
+tags:
+- generated_from_trainer
+- trl
+- sft
+licence: license
+---
+
+# Model Card for Qwen2.5-1.5B-Open-R1-Distill
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="tyfeng1997/Qwen2.5-1.5B-Open-R1-Distill", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/bofeng1997-ty/huggingface/runs/u6kvpc0n) 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 0.15.0.dev0
+- Transformers: 4.49.0.dev0
+- Pytorch: 2.5.1
+- Datasets: 3.2.0
+- Tokenizers: 0.21.0
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<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
+}

all_results.json

@@ -0,0 +1,8 @@
+{
+    "total_flos": 6.955833048956928e+17,
+    "train_loss": 0.8332233665607593,
+    "train_runtime": 5910.2876,
+    "train_samples": 16610,
+    "train_samples_per_second": 3.659,
+    "train_steps_per_second": 0.114
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-1.5B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0.dev0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.1,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.49.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50e315471741fda1b862abd07df84ee482088d1dd6b16d4399d720abfd500b3e
+size 3087467144

special_tokens_map.json

@@ -0,0 +1,25 @@
+{
+  "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": "<|im_end|>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "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
+    }
+  },
+  "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 tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|im_end|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "total_flos": 6.955833048956928e+17,
+    "train_loss": 0.8332233665607593,
+    "train_runtime": 5910.2876,
+    "train_samples": 16610,
+    "train_samples_per_second": 3.659,
+    "train_steps_per_second": 0.114
+}

trainer_state.json

@@ -0,0 +1,1176 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9988901220865705,
+  "eval_steps": 100,
+  "global_step": 675,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.007399186089530152,
+      "grad_norm": 2.6875,
+      "learning_rate": 1.4705882352941177e-06,
+      "loss": 1.0889,
+      "mean_token_accuracy": 0.7125268097914184,
+      "step": 5
+    },
+    {
+      "epoch": 0.014798372179060304,
+      "grad_norm": 2.484375,
+      "learning_rate": 2.9411764705882355e-06,
+      "loss": 1.0968,
+      "mean_token_accuracy": 0.7092195795245753,
+      "step": 10
+    },
+    {
+      "epoch": 0.022197558268590455,
+      "grad_norm": 2.09375,
+      "learning_rate": 4.411764705882353e-06,
+      "loss": 1.0965,
+      "mean_token_accuracy": 0.7104868683246498,
+      "step": 15
+    },
+    {
+      "epoch": 0.029596744358120607,
+      "grad_norm": 1.765625,
+      "learning_rate": 5.882352941176471e-06,
+      "loss": 1.0875,
+      "mean_token_accuracy": 0.7121812060803538,
+      "step": 20
+    },
+    {
+      "epoch": 0.03699593044765076,
+      "grad_norm": 1.6484375,
+      "learning_rate": 7.352941176470589e-06,
+      "loss": 1.04,
+      "mean_token_accuracy": 0.7208183657495422,
+      "step": 25
+    },
+    {
+      "epoch": 0.04439511653718091,
+      "grad_norm": 1.2109375,
+      "learning_rate": 8.823529411764707e-06,
+      "loss": 1.0122,
+      "mean_token_accuracy": 0.7265688926848266,
+      "step": 30
+    },
+    {
+      "epoch": 0.05179430262671106,
+      "grad_norm": 1.0390625,
+      "learning_rate": 1.0294117647058823e-05,
+      "loss": 1.0279,
+      "mean_token_accuracy": 0.7183522238886227,
+      "step": 35
+    },
+    {
+      "epoch": 0.059193488716241215,
+      "grad_norm": 0.84375,
+      "learning_rate": 1.1764705882352942e-05,
+      "loss": 0.986,
+      "mean_token_accuracy": 0.7276039645930008,
+      "step": 40
+    },
+    {
+      "epoch": 0.06659267480577137,
+      "grad_norm": 0.84765625,
+      "learning_rate": 1.323529411764706e-05,
+      "loss": 0.9595,
+      "mean_token_accuracy": 0.7319873327389332,
+      "step": 45
+    },
+    {
+      "epoch": 0.07399186089530152,
+      "grad_norm": 0.828125,
+      "learning_rate": 1.4705882352941179e-05,
+      "loss": 0.9236,
+      "mean_token_accuracy": 0.7399783950265117,
+      "step": 50
+    },
+    {
+      "epoch": 0.08139104698483167,
+      "grad_norm": 0.73828125,
+      "learning_rate": 1.6176470588235296e-05,
+      "loss": 0.9343,
+      "mean_token_accuracy": 0.7348416256431625,
+      "step": 55
+    },
+    {
+      "epoch": 0.08879023307436182,
+      "grad_norm": 0.7109375,
+      "learning_rate": 1.7647058823529414e-05,
+      "loss": 0.9254,
+      "mean_token_accuracy": 0.7385374999726644,
+      "step": 60
+    },
+    {
+      "epoch": 0.09618941916389197,
+      "grad_norm": 0.6953125,
+      "learning_rate": 1.911764705882353e-05,
+      "loss": 0.9063,
+      "mean_token_accuracy": 0.741349676895516,
+      "step": 65
+    },
+    {
+      "epoch": 0.10358860525342212,
+      "grad_norm": 0.63671875,
+      "learning_rate": 1.9999464266898485e-05,
+      "loss": 0.8649,
+      "mean_token_accuracy": 0.7525428841059651,
+      "step": 70
+    },
+    {
+      "epoch": 0.11098779134295228,
+      "grad_norm": 0.671875,
+      "learning_rate": 1.9993437928712977e-05,
+      "loss": 0.8608,
+      "mean_token_accuracy": 0.7526847546264352,
+      "step": 75
+    },
+    {
+      "epoch": 0.11838697743248243,
+      "grad_norm": 0.69921875,
+      "learning_rate": 1.998071963486563e-05,
+      "loss": 0.862,
+      "mean_token_accuracy": 0.7518434589905822,
+      "step": 80
+    },
+    {
+      "epoch": 0.12578616352201258,
+      "grad_norm": 0.6640625,
+      "learning_rate": 1.9961317901970953e-05,
+      "loss": 0.8682,
+      "mean_token_accuracy": 0.7497427297772263,
+      "step": 85
+    },
+    {
+      "epoch": 0.13318534961154274,
+      "grad_norm": 0.6328125,
+      "learning_rate": 1.993524572210807e-05,
+      "loss": 0.8585,
+      "mean_token_accuracy": 0.7517300278547048,
+      "step": 90
+    },
+    {
+      "epoch": 0.14058453570107288,
+      "grad_norm": 0.78515625,
+      "learning_rate": 1.990252055412077e-05,
+      "loss": 0.8397,
+      "mean_token_accuracy": 0.7565752356334744,
+      "step": 95
+    },
+    {
+      "epoch": 0.14798372179060304,
+      "grad_norm": 0.66796875,
+      "learning_rate": 1.9863164311926433e-05,
+      "loss": 0.8532,
+      "mean_token_accuracy": 0.7522277875945481,
+      "step": 100
+    },
+    {
+      "epoch": 0.14798372179060304,
+      "eval_loss": 0.881839394569397,
+      "eval_mean_token_accuracy": 0.7427007802750561,
+      "eval_runtime": 10.0645,
+      "eval_samples_per_second": 12.817,
+      "eval_steps_per_second": 3.279,
+      "step": 100
+    },
+    {
+      "epoch": 0.15538290788013318,
+      "grad_norm": 0.65625,
+      "learning_rate": 1.981720334984174e-05,
+      "loss": 0.8617,
+      "mean_token_accuracy": 0.750136008754142,
+      "step": 105
+    },
+    {
+      "epoch": 0.16278209396966334,
+      "grad_norm": 0.6953125,
+      "learning_rate": 1.9764668444934853e-05,
+      "loss": 0.8502,
+      "mean_token_accuracy": 0.7535309864229933,
+      "step": 110
+    },
+    {
+      "epoch": 0.1701812800591935,
+      "grad_norm": 0.6328125,
+      "learning_rate": 1.970559477641606e-05,
+      "loss": 0.838,
+      "mean_token_accuracy": 0.7564989407619159,
+      "step": 115
+    },
+    {
+      "epoch": 0.17758046614872364,
+      "grad_norm": 0.6796875,
+      "learning_rate": 1.9640021902080523e-05,
+      "loss": 0.8519,
+      "mean_token_accuracy": 0.7530597966776801,
+      "step": 120
+    },
+    {
+      "epoch": 0.1849796522382538,
+      "grad_norm": 0.64453125,
+      "learning_rate": 1.9567993731818988e-05,
+      "loss": 0.8262,
+      "mean_token_accuracy": 0.7578173164655706,
+      "step": 125
+    },
+    {
+      "epoch": 0.19237883832778394,
+      "grad_norm": 0.65234375,
+      "learning_rate": 1.9489558498214197e-05,
+      "loss": 0.8448,
+      "mean_token_accuracy": 0.7532515140156795,
+      "step": 130
+    },
+    {
+      "epoch": 0.1997780244173141,
+      "grad_norm": 0.63671875,
+      "learning_rate": 1.9404768724242667e-05,
+      "loss": 0.829,
+      "mean_token_accuracy": 0.7569637453783504,
+      "step": 135
+    },
+    {
+      "epoch": 0.20717721050684423,
+      "grad_norm": 0.671875,
+      "learning_rate": 1.931368118810346e-05,
+      "loss": 0.8496,
+      "mean_token_accuracy": 0.7527783892103799,
+      "step": 140
+    },
+    {
+      "epoch": 0.2145763965963744,
+      "grad_norm": 0.63671875,
+      "learning_rate": 1.92163568851975e-05,
+      "loss": 0.8098,
+      "mean_token_accuracy": 0.763142965097514,
+      "step": 145
+    },
+    {
+      "epoch": 0.22197558268590456,
+      "grad_norm": 0.6171875,
+      "learning_rate": 1.911286098728296e-05,
+      "loss": 0.8311,
+      "mean_token_accuracy": 0.7559205422083072,
+      "step": 150
+    },
+    {
+      "epoch": 0.2293747687754347,
+      "grad_norm": 0.65234375,
+      "learning_rate": 1.900326279883392e-05,
+      "loss": 0.821,
+      "mean_token_accuracy": 0.7603623572543372,
+      "step": 155
+    },
+    {
+      "epoch": 0.23677395486496486,
+      "grad_norm": 0.64453125,
+      "learning_rate": 1.8887635710631716e-05,
+      "loss": 0.8415,
+      "mean_token_accuracy": 0.7539029955264388,
+      "step": 160
+    },
+    {
+      "epoch": 0.244173140954495,
+      "grad_norm": 0.640625,
+      "learning_rate": 1.8766057150619865e-05,
+      "loss": 0.8194,
+      "mean_token_accuracy": 0.7596525949906076,
+      "step": 165
+    },
+    {
+      "epoch": 0.25157232704402516,
+      "grad_norm": 0.65625,
+      "learning_rate": 1.8638608532055635e-05,
+      "loss": 0.8499,
+      "mean_token_accuracy": 0.7507423157399387,
+      "step": 170
+    },
+    {
+      "epoch": 0.2589715131335553,
+      "grad_norm": 0.66015625,
+      "learning_rate": 1.8505375198992856e-05,
+      "loss": 0.7937,
+      "mean_token_accuracy": 0.7674289833041605,
+      "step": 175
+    },
+    {
+      "epoch": 0.2663706992230855,
+      "grad_norm": 0.67578125,
+      "learning_rate": 1.836644636913258e-05,
+      "loss": 0.8262,
+      "mean_token_accuracy": 0.7575025006251728,
+      "step": 180
+    },
+    {
+      "epoch": 0.2737698853126156,
+      "grad_norm": 0.65234375,
+      "learning_rate": 1.8221915074079764e-05,
+      "loss": 0.8255,
+      "mean_token_accuracy": 0.7579806168918822,
+      "step": 185
+    },
+    {
+      "epoch": 0.28116907140214575,
+      "grad_norm": 0.60546875,
+      "learning_rate": 1.8071878097046064e-05,
+      "loss": 0.8127,
+      "mean_token_accuracy": 0.7618292969891692,
+      "step": 190
+    },
+    {
+      "epoch": 0.2885682574916759,
+      "grad_norm": 0.61328125,
+      "learning_rate": 1.7916435908040413e-05,
+      "loss": 0.82,
+      "mean_token_accuracy": 0.7576332974355414,
+      "step": 195
+    },
+    {
+      "epoch": 0.2959674435812061,
+      "grad_norm": 0.6640625,
+      "learning_rate": 1.7755692596590778e-05,
+      "loss": 0.8239,
+      "mean_token_accuracy": 0.7585159504436572,
+      "step": 200
+    },
+    {
+      "epoch": 0.2959674435812061,
+      "eval_loss": 0.8516884446144104,
+      "eval_mean_token_accuracy": 0.7486177381969057,
+      "eval_runtime": 10.1332,
+      "eval_samples_per_second": 12.73,
+      "eval_steps_per_second": 3.257,
+      "step": 200
+    },
+    {
+      "epoch": 0.30336662967073624,
+      "grad_norm": 0.640625,
+      "learning_rate": 1.7589755802042188e-05,
+      "loss": 0.8333,
+      "mean_token_accuracy": 0.755667467160024,
+      "step": 205
+    },
+    {
+      "epoch": 0.31076581576026635,
+      "grad_norm": 0.6484375,
+      "learning_rate": 1.7418736641477636e-05,
+      "loss": 0.8076,
+      "mean_token_accuracy": 0.7622239278052717,
+      "step": 210
+    },
+    {
+      "epoch": 0.3181650018497965,
+      "grad_norm": 0.6640625,
+      "learning_rate": 1.7242749635310222e-05,
+      "loss": 0.8258,
+      "mean_token_accuracy": 0.7563272214656106,
+      "step": 215
+    },
+    {
+      "epoch": 0.3255641879393267,
+      "grad_norm": 0.625,
+      "learning_rate": 1.7061912630596252e-05,
+      "loss": 0.808,
+      "mean_token_accuracy": 0.7622835124784312,
+      "step": 220
+    },
+    {
+      "epoch": 0.33296337402885684,
+      "grad_norm": 0.6015625,
+      "learning_rate": 1.6876346722120747e-05,
+      "loss": 0.8376,
+      "mean_token_accuracy": 0.7545975719101803,
+      "step": 225
+    },
+    {
+      "epoch": 0.340362560118387,
+      "grad_norm": 0.64453125,
+      "learning_rate": 1.6686176171308125e-05,
+      "loss": 0.8189,
+      "mean_token_accuracy": 0.7589312621258506,
+      "step": 230
+    },
+    {
+      "epoch": 0.3477617462079171,
+      "grad_norm": 0.62109375,
+      "learning_rate": 1.6491528323012412e-05,
+      "loss": 0.8323,
+      "mean_token_accuracy": 0.7551743560659628,
+      "step": 235
+    },
+    {
+      "epoch": 0.3551609322974473,
+      "grad_norm": 0.65625,
+      "learning_rate": 1.6292533520242663e-05,
+      "loss": 0.8379,
+      "mean_token_accuracy": 0.7538607275907119,
+      "step": 240
+    },
+    {
+      "epoch": 0.36256011838697744,
+      "grad_norm": 0.625,
+      "learning_rate": 1.6089325016880737e-05,
+      "loss": 0.8343,
+      "mean_token_accuracy": 0.7548026042130938,
+      "step": 245
+    },
+    {
+      "epoch": 0.3699593044765076,
+      "grad_norm": 0.64453125,
+      "learning_rate": 1.588203888844982e-05,
+      "loss": 0.8046,
+      "mean_token_accuracy": 0.761888865074052,
+      "step": 250
+    },
+    {
+      "epoch": 0.37735849056603776,
+      "grad_norm": 0.67578125,
+      "learning_rate": 1.5670813940993504e-05,
+      "loss": 0.8276,
+      "mean_token_accuracy": 0.7575759893795071,
+      "step": 255
+    },
+    {
+      "epoch": 0.38475767665556787,
+      "grad_norm": 0.64453125,
+      "learning_rate": 1.5455791618126407e-05,
+      "loss": 0.8104,
+      "mean_token_accuracy": 0.760050321922496,
+      "step": 260
+    },
+    {
+      "epoch": 0.39215686274509803,
+      "grad_norm": 0.6328125,
+      "learning_rate": 1.5237115906318565e-05,
+      "loss": 0.8353,
+      "mean_token_accuracy": 0.7543203597663848,
+      "step": 265
+    },
+    {
+      "epoch": 0.3995560488346282,
+      "grad_norm": 0.6484375,
+      "learning_rate": 1.5014933238477069e-05,
+      "loss": 0.8199,
+      "mean_token_accuracy": 0.7586679634011008,
+      "step": 270
+    },
+    {
+      "epoch": 0.40695523492415836,
+      "grad_norm": 0.68359375,
+      "learning_rate": 1.4789392395889468e-05,
+      "loss": 0.7905,
+      "mean_token_accuracy": 0.7671787987556499,
+      "step": 275
+    },
+    {
+      "epoch": 0.41435442101368847,
+      "grad_norm": 0.671875,
+      "learning_rate": 1.4560644408594602e-05,
+      "loss": 0.8026,
+      "mean_token_accuracy": 0.7626319857465419,
+      "step": 280
+    },
+    {
+      "epoch": 0.42175360710321863,
+      "grad_norm": 0.62890625,
+      "learning_rate": 1.432884245424761e-05,
+      "loss": 0.8075,
+      "mean_token_accuracy": 0.7607413128108793,
+      "step": 285
+    },
+    {
+      "epoch": 0.4291527931927488,
+      "grad_norm": 0.64453125,
+      "learning_rate": 1.4094141755546816e-05,
+      "loss": 0.8187,
+      "mean_token_accuracy": 0.7589368335212423,
+      "step": 290
+    },
+    {
+      "epoch": 0.43655197928227896,
+      "grad_norm": 0.65234375,
+      "learning_rate": 1.3856699476291176e-05,
+      "loss": 0.8192,
+      "mean_token_accuracy": 0.7591432161550824,
+      "step": 295
+    },
+    {
+      "epoch": 0.4439511653718091,
+      "grad_norm": 0.59375,
+      "learning_rate": 1.3616674616137902e-05,
+      "loss": 0.8041,
+      "mean_token_accuracy": 0.7629979478188578,
+      "step": 300
+    },
+    {
+      "epoch": 0.4439511653718091,
+      "eval_loss": 0.8405057191848755,
+      "eval_mean_token_accuracy": 0.7510059552661275,
+      "eval_runtime": 10.064,
+      "eval_samples_per_second": 12.818,
+      "eval_steps_per_second": 3.279,
+      "step": 300
+    },
+    {
+      "epoch": 0.4513503514613392,
+      "grad_norm": 0.57421875,
+      "learning_rate": 1.3374227904130724e-05,
+      "loss": 0.7818,
+      "mean_token_accuracy": 0.7675685003663603,
+      "step": 305
+    },
+    {
+      "epoch": 0.4587495375508694,
+      "grad_norm": 0.6171875,
+      "learning_rate": 1.3129521691070108e-05,
+      "loss": 0.8151,
+      "mean_token_accuracy": 0.760285985649892,
+      "step": 310
+    },
+    {
+      "epoch": 0.46614872364039955,
+      "grad_norm": 0.609375,
+      "learning_rate": 1.2882719840797473e-05,
+      "loss": 0.8498,
+      "mean_token_accuracy": 0.7496549590236475,
+      "step": 315
+    },
+    {
+      "epoch": 0.4735479097299297,
+      "grad_norm": 0.62109375,
+      "learning_rate": 1.2633987620466229e-05,
+      "loss": 0.8157,
+      "mean_token_accuracy": 0.7595543121832427,
+      "step": 320
+    },
+    {
+      "epoch": 0.4809470958194599,
+      "grad_norm": 0.6171875,
+      "learning_rate": 1.2383491589873122e-05,
+      "loss": 0.814,
+      "mean_token_accuracy": 0.76055377418819,
+      "step": 325
+    },
+    {
+      "epoch": 0.48834628190899,
+      "grad_norm": 0.63671875,
+      "learning_rate": 1.213139948992394e-05,
+      "loss": 0.8059,
+      "mean_token_accuracy": 0.762236279277402,
+      "step": 330
+    },
+    {
+      "epoch": 0.49574546799852015,
+      "grad_norm": 0.640625,
+      "learning_rate": 1.187788013030837e-05,
+      "loss": 0.8162,
+      "mean_token_accuracy": 0.7582854817990154,
+      "step": 335
+    },
+    {
+      "epoch": 0.5031446540880503,
+      "grad_norm": 0.69140625,
+      "learning_rate": 1.1623103276459086e-05,
+      "loss": 0.8289,
+      "mean_token_accuracy": 0.7563345353903344,
+      "step": 340
+    },
+    {
+      "epoch": 0.5105438401775805,
+      "grad_norm": 0.6015625,
+      "learning_rate": 1.1367239535870913e-05,
+      "loss": 0.8231,
+      "mean_token_accuracy": 0.7566890854096104,
+      "step": 345
+    },
+    {
+      "epoch": 0.5179430262671106,
+      "grad_norm": 0.6640625,
+      "learning_rate": 1.1110460243856051e-05,
+      "loss": 0.812,
+      "mean_token_accuracy": 0.7598966873380734,
+      "step": 350
+    },
+    {
+      "epoch": 0.5253422123566408,
+      "grad_norm": 0.69140625,
+      "learning_rate": 1.085293734881197e-05,
+      "loss": 0.8096,
+      "mean_token_accuracy": 0.7606711478473765,
+      "step": 355
+    },
+    {
+      "epoch": 0.532741398446171,
+      "grad_norm": 0.59765625,
+      "learning_rate": 1.0594843297078736e-05,
+      "loss": 0.7989,
+      "mean_token_accuracy": 0.7642786153243144,
+      "step": 360
+    },
+    {
+      "epoch": 0.540140584535701,
+      "grad_norm": 0.6015625,
+      "learning_rate": 1.0336350917462925e-05,
+      "loss": 0.8056,
+      "mean_token_accuracy": 0.762532315275268,
+      "step": 365
+    },
+    {
+      "epoch": 0.5475397706252312,
+      "grad_norm": 0.61328125,
+      "learning_rate": 1.0077633305505402e-05,
+      "loss": 0.816,
+      "mean_token_accuracy": 0.7593420425977142,
+      "step": 370
+    },
+    {
+      "epoch": 0.5549389567147613,
+      "grad_norm": 0.61328125,
+      "learning_rate": 9.818863707570476e-06,
+      "loss": 0.8133,
+      "mean_token_accuracy": 0.7596080670861823,
+      "step": 375
+    },
+    {
+      "epoch": 0.5623381428042915,
+      "grad_norm": 0.640625,
+      "learning_rate": 9.560215404834094e-06,
+      "loss": 0.7919,
+      "mean_token_accuracy": 0.7654578983098163,
+      "step": 380
+    },
+    {
+      "epoch": 0.5697373288938217,
+      "grad_norm": 0.5703125,
+      "learning_rate": 9.30186159724869e-06,
+      "loss": 0.7816,
+      "mean_token_accuracy": 0.7673245483787857,
+      "step": 385
+    },
+    {
+      "epoch": 0.5771365149833518,
+      "grad_norm": 0.6015625,
+      "learning_rate": 9.043975287562443e-06,
+      "loss": 0.7992,
+      "mean_token_accuracy": 0.7633096954215505,
+      "step": 390
+    },
+    {
+      "epoch": 0.584535701072882,
+      "grad_norm": 0.61328125,
+      "learning_rate": 8.786729165470584e-06,
+      "loss": 0.7998,
+      "mean_token_accuracy": 0.7631908193656377,
+      "step": 395
+    },
+    {
+      "epoch": 0.5919348871624122,
+      "grad_norm": 0.6171875,
+      "learning_rate": 8.530295491976338e-06,
+      "loss": 0.8126,
+      "mean_token_accuracy": 0.7598241210604321,
+      "step": 400
+    },
+    {
+      "epoch": 0.5919348871624122,
+      "eval_loss": 0.8360142707824707,
+      "eval_mean_token_accuracy": 0.7517478887246488,
+      "eval_runtime": 10.03,
+      "eval_samples_per_second": 12.861,
+      "eval_steps_per_second": 3.29,
+      "step": 400
+    },
+    {
+      "epoch": 0.5993340732519423,
+      "grad_norm": 0.6328125,
+      "learning_rate": 8.274845984038916e-06,
+      "loss": 0.7969,
+      "mean_token_accuracy": 0.7641834896121918,
+      "step": 405
+    },
+    {
+      "epoch": 0.6067332593414725,
+      "grad_norm": 0.640625,
+      "learning_rate": 8.020551699585843e-06,
+      "loss": 0.7947,
+      "mean_token_accuracy": 0.7647268750819378,
+      "step": 410
+    },
+    {
+      "epoch": 0.6141324454310025,
+      "grad_norm": 0.6015625,
+      "learning_rate": 7.76758292296659e-06,
+      "loss": 0.8189,
+      "mean_token_accuracy": 0.7590364557167671,
+      "step": 415
+    },
+    {
+      "epoch": 0.6215316315205327,
+      "grad_norm": 0.62109375,
+      "learning_rate": 7.5161090509242005e-06,
+      "loss": 0.7909,
+      "mean_token_accuracy": 0.7652537080968896,
+      "step": 420
+    },
+    {
+      "epoch": 0.6289308176100629,
+      "grad_norm": 0.6171875,
+      "learning_rate": 7.2662984791613186e-06,
+      "loss": 0.8315,
+      "mean_token_accuracy": 0.7542246739417179,
+      "step": 425
+    },
+    {
+      "epoch": 0.636330003699593,
+      "grad_norm": 0.640625,
+      "learning_rate": 7.01831848957653e-06,
+      "loss": 0.8369,
+      "mean_token_accuracy": 0.7534853977571128,
+      "step": 430
+    },
+    {
+      "epoch": 0.6437291897891232,
+      "grad_norm": 0.6171875,
+      "learning_rate": 6.772335138246548e-06,
+      "loss": 0.805,
+      "mean_token_accuracy": 0.762450890454431,
+      "step": 435
+    },
+    {
+      "epoch": 0.6511283758786534,
+      "grad_norm": 0.55859375,
+      "learning_rate": 6.528513144229256e-06,
+      "loss": 0.8104,
+      "mean_token_accuracy": 0.7604143982203317,
+      "step": 440
+    },
+    {
+      "epoch": 0.6585275619681835,
+      "grad_norm": 0.61328125,
+      "learning_rate": 6.287015779262064e-06,
+      "loss": 0.8269,
+      "mean_token_accuracy": 0.7558118968129715,
+      "step": 445
+    },
+    {
+      "epoch": 0.6659267480577137,
+      "grad_norm": 0.65234375,
+      "learning_rate": 6.048004758429451e-06,
+      "loss": 0.809,
+      "mean_token_accuracy": 0.7604383536426794,
+      "step": 450
+    },
+    {
+      "epoch": 0.6733259341472438,
+      "grad_norm": 0.57421875,
+      "learning_rate": 5.811640131872867e-06,
+      "loss": 0.803,
+      "mean_token_accuracy": 0.7631231626902106,
+      "step": 455
+    },
+    {
+      "epoch": 0.680725120236774,
+      "grad_norm": 0.62109375,
+      "learning_rate": 5.578080177615575e-06,
+      "loss": 0.7905,
+      "mean_token_accuracy": 0.7664996560842343,
+      "step": 460
+    },
+    {
+      "epoch": 0.6881243063263041,
+      "grad_norm": 0.59765625,
+      "learning_rate": 5.347481295574141e-06,
+      "loss": 0.817,
+      "mean_token_accuracy": 0.7598457909368685,
+      "step": 465
+    },
+    {
+      "epoch": 0.6955234924158342,
+      "grad_norm": 0.5859375,
+      "learning_rate": 5.119997902827584e-06,
+      "loss": 0.7838,
+      "mean_token_accuracy": 0.7681530254729145,
+      "step": 470
+    },
+    {
+      "epoch": 0.7029226785053644,
+      "grad_norm": 0.59765625,
+      "learning_rate": 4.8957823302142916e-06,
+      "loss": 0.8152,
+      "mean_token_accuracy": 0.7589711080063637,
+      "step": 475
+    },
+    {
+      "epoch": 0.7103218645948945,
+      "grad_norm": 0.6328125,
+      "learning_rate": 4.674984720325961e-06,
+      "loss": 0.764,
+      "mean_token_accuracy": 0.7731734311479281,
+      "step": 480
+    },
+    {
+      "epoch": 0.7177210506844247,
+      "grad_norm": 0.59375,
+      "learning_rate": 4.457752926966888e-06,
+      "loss": 0.7956,
+      "mean_token_accuracy": 0.7651409385185983,
+      "step": 485
+    },
+    {
+      "epoch": 0.7251202367739549,
+      "grad_norm": 0.6015625,
+      "learning_rate": 4.244232416145839e-06,
+      "loss": 0.8124,
+      "mean_token_accuracy": 0.7599823785557752,
+      "step": 490
+    },
+    {
+      "epoch": 0.732519422863485,
+      "grad_norm": 0.609375,
+      "learning_rate": 4.0345661686669745e-06,
+      "loss": 0.8049,
+      "mean_token_accuracy": 0.7629141672631095,
+      "step": 495
+    },
+    {
+      "epoch": 0.7399186089530152,
+      "grad_norm": 0.6015625,
+      "learning_rate": 3.828894584384867e-06,
+      "loss": 0.8044,
+      "mean_token_accuracy": 0.7619363832608415,
+      "step": 500
+    },
+    {
+      "epoch": 0.7399186089530152,
+      "eval_loss": 0.8346704840660095,
+      "eval_mean_token_accuracy": 0.7520572347969028,
+      "eval_runtime": 10.0654,
+      "eval_samples_per_second": 12.816,
+      "eval_steps_per_second": 3.279,
+      "step": 500
+    },
+    {
+      "epoch": 0.7473177950425454,
+      "grad_norm": 0.58984375,
+      "learning_rate": 3.62735538818787e-06,
+      "loss": 0.8114,
+      "mean_token_accuracy": 0.7598190169187282,
+      "step": 505
+    },
+    {
+      "epoch": 0.7547169811320755,
+      "grad_norm": 0.68359375,
+      "learning_rate": 3.4300835377726904e-06,
+      "loss": 0.8084,
+      "mean_token_accuracy": 0.7615245232527742,
+      "step": 510
+    },
+    {
+      "epoch": 0.7621161672216056,
+      "grad_norm": 0.62890625,
+      "learning_rate": 3.2372111332720045e-06,
+      "loss": 0.8095,
+      "mean_token_accuracy": 0.7603961895824873,
+      "step": 515
+    },
+    {
+      "epoch": 0.7695153533111357,
+      "grad_norm": 0.59375,
+      "learning_rate": 3.048867328795588e-06,
+      "loss": 0.8042,
+      "mean_token_accuracy": 0.7623402252899881,
+      "step": 520
+    },
+    {
+      "epoch": 0.7769145394006659,
+      "grad_norm": 0.609375,
+      "learning_rate": 2.865178245944218e-06,
+      "loss": 0.8271,
+      "mean_token_accuracy": 0.7549774230762811,
+      "step": 525
+    },
+    {
+      "epoch": 0.7843137254901961,
+      "grad_norm": 0.65625,
+      "learning_rate": 2.686266889354211e-06,
+      "loss": 0.8194,
+      "mean_token_accuracy": 0.758641096847443,
+      "step": 530
+    },
+    {
+      "epoch": 0.7917129115797262,
+      "grad_norm": 0.62109375,
+      "learning_rate": 2.5122530643292274e-06,
+      "loss": 0.8073,
+      "mean_token_accuracy": 0.7621044001910408,
+      "step": 535
+    },
+    {
+      "epoch": 0.7991120976692564,
+      "grad_norm": 0.6015625,
+      "learning_rate": 2.3432532966144526e-06,
+      "loss": 0.8052,
+      "mean_token_accuracy": 0.7617640022033555,
+      "step": 540
+    },
+    {
+      "epoch": 0.8065112837587866,
+      "grad_norm": 0.625,
+      "learning_rate": 2.1793807543668857e-06,
+      "loss": 0.7953,
+      "mean_token_accuracy": 0.7650752920265742,
+      "step": 545
+    },
+    {
+      "epoch": 0.8139104698483167,
+      "grad_norm": 0.6640625,
+      "learning_rate": 2.0207451723739633e-06,
+      "loss": 0.8164,
+      "mean_token_accuracy": 0.7590261856765735,
+      "step": 550
+    },
+    {
+      "epoch": 0.8213096559378469,
+      "grad_norm": 0.62890625,
+      "learning_rate": 1.8674527785713247e-06,
+      "loss": 0.8165,
+      "mean_token_accuracy": 0.7591550173948883,
+      "step": 555
+    },
+    {
+      "epoch": 0.8287088420273769,
+      "grad_norm": 0.625,
+      "learning_rate": 1.7196062229088606e-06,
+      "loss": 0.7974,
+      "mean_token_accuracy": 0.7655606222993903,
+      "step": 560
+    },
+    {
+      "epoch": 0.8361080281169071,
+      "grad_norm": 0.640625,
+      "learning_rate": 1.577304508612717e-06,
+      "loss": 0.8188,
+      "mean_token_accuracy": 0.7584306394217425,
+      "step": 565
+    },
+    {
+      "epoch": 0.8435072142064373,
+      "grad_norm": 0.6015625,
+      "learning_rate": 1.4406429258892762e-06,
+      "loss": 0.7987,
+      "mean_token_accuracy": 0.7638594187341397,
+      "step": 570
+    },
+    {
+      "epoch": 0.8509064002959674,
+      "grad_norm": 0.63671875,
+      "learning_rate": 1.3097129881154936e-06,
+      "loss": 0.8031,
+      "mean_token_accuracy": 0.7634847826956948,
+      "step": 575
+    },
+    {
+      "epoch": 0.8583055863854976,
+      "grad_norm": 0.73046875,
+      "learning_rate": 1.1846023705583442e-06,
+      "loss": 0.8056,
+      "mean_token_accuracy": 0.761539622884949,
+      "step": 580
+    },
+    {
+      "epoch": 0.8657047724750278,
+      "grad_norm": 0.62109375,
+      "learning_rate": 1.065394851664394e-06,
+      "loss": 0.8049,
+      "mean_token_accuracy": 0.7617745412749592,
+      "step": 585
+    },
+    {
+      "epoch": 0.8731039585645579,
+      "grad_norm": 0.69921875,
+      "learning_rate": 9.521702569588199e-07,
+      "loss": 0.7982,
+      "mean_token_accuracy": 0.7640860770793427,
+      "step": 590
+    },
+    {
+      "epoch": 0.8805031446540881,
+      "grad_norm": 0.56640625,
+      "learning_rate": 8.450044055914497e-07,
+      "loss": 0.7844,
+      "mean_token_accuracy": 0.7681888388454224,
+      "step": 595
+    },
+    {
+      "epoch": 0.8879023307436182,
+      "grad_norm": 0.65625,
+      "learning_rate": 7.439690595656013e-07,
+      "loss": 0.8012,
+      "mean_token_accuracy": 0.7632812679282144,
+      "step": 600
+    },
+    {
+      "epoch": 0.8879023307436182,
+      "eval_loss": 0.8345086574554443,
+      "eval_mean_token_accuracy": 0.7520681013468922,
+      "eval_runtime": 10.0917,
+      "eval_samples_per_second": 12.783,
+      "eval_steps_per_second": 3.27,
+      "step": 600
+    },
+    {
+      "epoch": 0.8953015168331484,
+      "grad_norm": 0.60546875,
+      "learning_rate": 6.491318756837417e-07,
+      "loss": 0.8106,
+      "mean_token_accuracy": 0.7612582206970016,
+      "step": 605
+    },
+    {
+      "epoch": 0.9027007029226785,
+      "grad_norm": 0.62890625,
+      "learning_rate": 5.605563602421149e-07,
+      "loss": 0.7911,
+      "mean_token_accuracy": 0.7655656508689518,
+      "step": 610
+    },
+    {
+      "epoch": 0.9100998890122086,
+      "grad_norm": 0.65625,
+      "learning_rate": 4.783018265047179e-07,
+      "loss": 0.7894,
+      "mean_token_accuracy": 0.7661501144437494,
+      "step": 615
+    },
+    {
+      "epoch": 0.9174990751017388,
+      "grad_norm": 0.62890625,
+      "learning_rate": 4.024233549850509e-07,
+      "loss": 0.7596,
+      "mean_token_accuracy": 0.7753985135806752,
+      "step": 620
+    },
+    {
+      "epoch": 0.9248982611912689,
+      "grad_norm": 0.62890625,
+      "learning_rate": 3.329717565622825e-07,
+      "loss": 0.8101,
+      "mean_token_accuracy": 0.761036204015425,
+      "step": 625
+    },
+    {
+      "epoch": 0.9322974472807991,
+      "grad_norm": 0.6484375,
+      "learning_rate": 2.6999353845651113e-07,
+      "loss": 0.792,
+      "mean_token_accuracy": 0.7660421700585999,
+      "step": 630
+    },
+    {
+      "epoch": 0.9396966333703293,
+      "grad_norm": 0.61328125,
+      "learning_rate": 2.1353087308590314e-07,
+      "loss": 0.7908,
+      "mean_token_accuracy": 0.7660176922625442,
+      "step": 635
+    },
+    {
+      "epoch": 0.9470958194598594,
+      "grad_norm": 0.58984375,
+      "learning_rate": 1.6362156982656085e-07,
+      "loss": 0.8095,
+      "mean_token_accuracy": 0.7614060535470332,
+      "step": 640
+    },
+    {
+      "epoch": 0.9544950055493896,
+      "grad_norm": 0.625,
+      "learning_rate": 1.2029904969404482e-07,
+      "loss": 0.789,
+      "mean_token_accuracy": 0.7670061354894862,
+      "step": 645
+    },
+    {
+      "epoch": 0.9618941916389198,
+      "grad_norm": 0.62109375,
+      "learning_rate": 8.359232296349163e-08,
+      "loss": 0.7812,
+      "mean_token_accuracy": 0.7682785852402595,
+      "step": 650
+    },
+    {
+      "epoch": 0.9692933777284499,
+      "grad_norm": 0.5859375,
+      "learning_rate": 5.3525969743324356e-08,
+      "loss": 0.8167,
+      "mean_token_accuracy": 0.7597556839292564,
+      "step": 655
+    },
+    {
+      "epoch": 0.97669256381798,
+      "grad_norm": 0.578125,
+      "learning_rate": 3.012012351554017e-08,
+      "loss": 0.7868,
+      "mean_token_accuracy": 0.766402887185296,
+      "step": 660
+    },
+    {
+      "epoch": 0.9840917499075101,
+      "grad_norm": 0.66015625,
+      "learning_rate": 1.3390457653639221e-08,
+      "loss": 0.8048,
+      "mean_token_accuracy": 0.7627934682349665,
+      "step": 665
+    },
+    {
+      "epoch": 0.9914909359970403,
+      "grad_norm": 0.66015625,
+      "learning_rate": 3.3481749271768726e-09,
+      "loss": 0.7971,
+      "mean_token_accuracy": 0.7637863893274557,
+      "step": 670
+    },
+    {
+      "epoch": 0.9988901220865705,
+      "grad_norm": 0.66015625,
+      "learning_rate": 0.0,
+      "loss": 0.8261,
+      "mean_token_accuracy": 0.7560044389949291,
+      "step": 675
+    },
+    {
+      "epoch": 0.9988901220865705,
+      "step": 675,
+      "total_flos": 6.955833048956928e+17,
+      "train_loss": 0.8332233665607593,
+      "train_runtime": 5910.2876,
+      "train_samples_per_second": 3.659,
+      "train_steps_per_second": 0.114
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 675,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.955833048956928e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca480cca08c980f684263ceeed9d413ea62ac19d89ccd00d99458485610b9809
+size 6008