初始化项目，由ModelHub XC社区提供模型

Model: cameronphchen/Qwen2.5-1.5B-Open-R1-GRPO Source: Original Platform
2026-04-28 19:10:53 +08:00
commit a671ad582c
15 changed files with 152115 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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
--- a/README.md
+++ b/README.md
@@ -0,0 +1,68 @@
+---
+base_model: Qwen/Qwen2.5-1.5B-Instruct
+library_name: transformers
+model_name: Qwen2.5-1.5B-Open-R1-GRPO
+tags:
+- generated_from_trainer
+- trl
+- grpo
+licence: license
+---
+
+# Model Card for Qwen2.5-1.5B-Open-R1-GRPO
+
+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="cameronphchen/Qwen2.5-1.5B-Open-R1-GRPO", 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/need-ai/open-r1-basic-cameronchen/runs/vg27qwkt) 
+
+
+This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300).
+
+### Framework versions
+
+- TRL: 0.16.0.dev0
+- Transformers: 4.49.0
+- Pytorch: 2.5.1
+- Datasets: 3.3.2
+- Tokenizers: 0.21.0
+
+## Citations
+
+Cite GRPO as:
+
+```bibtex
+@article{zhihong2024deepseekmath,
+    title        = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}},
+    author       = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo},
+    year         = 2024,
+    eprint       = {arXiv:2402.03300},
+}
+
+```
+
+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}}
+}
+```
--- a/added_tokens.json
+++ b/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
+}
--- a/all_results.json
+++ b/all_results.json
@@ -0,0 +1,8 @@
+{
+    "total_flos": 0.0,
+    "train_loss": 0.11724991016089917,
+    "train_runtime": 482.6536,
+    "train_samples": 16,
+    "train_samples_per_second": 0.332,
+    "train_steps_per_second": 0.021
+}
--- a/config.json
+++ b/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": 32768,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}
--- a/generation_config.json
+++ b/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"
+}
--- a/merges.txt
+++ b/merges.txt
--- a/model.safetensors
+++ b/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57dee797864c204dab65b36fa5182e63d23b15d54977de2d995ebba5b0372254
+size 3087467144
--- a/special_tokens_map.json
+++ b/special_tokens_map.json
@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
--- a/tokenizer.json
+++ b/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5eee858c5123a4279c3e1f7b81247343f356ac767940b2692a928ad929543214
+size 11422063
--- a/tokenizer_config.json
+++ b/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": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}
--- a/train_results.json
+++ b/train_results.json
@@ -0,0 +1,8 @@
+{
+    "total_flos": 0.0,
+    "train_loss": 0.11724991016089917,
+    "train_runtime": 482.6536,
+    "train_samples": 16,
+    "train_samples_per_second": 0.332,
+    "train_steps_per_second": 0.021
+}
--- a/trainer_state.json
+++ b/trainer_state.json
@@ -0,0 +1,291 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "eval_steps": 1,
+  "global_step": 10,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.472108991167676,
+      "learning_rate": 2e-05,
+      "loss": 0.0368,
+      "step": 1
+    },
+    {
+      "epoch": 1.0,
+      "eval_clip_ratio": 0.0,
+      "eval_completion_length": 573.25,
+      "eval_kl": 0.0,
+      "eval_loss": 0.022564562037587166,
+      "eval_reward": 0.25,
+      "eval_reward_std": 0.28867512941360474,
+      "eval_rewards/accuracy_reward_math": 0.0,
+      "eval_rewards/accuracy_reward_staging": 0.0,
+      "eval_rewards/format_reward": 0.125,
+      "eval_rewards/format_reward_staging": 0.125,
+      "eval_runtime": 10.3415,
+      "eval_samples_per_second": 1.547,
+      "eval_steps_per_second": 0.097,
+      "step": 1
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.5030364342093353,
+      "learning_rate": 1.9396926207859085e-05,
+      "loss": -0.0324,
+      "step": 2
+    },
+    {
+      "epoch": 2.0,
+      "eval_clip_ratio": 0.0,
+      "eval_completion_length": 476.625,
+      "eval_kl": 2.46875,
+      "eval_loss": 0.14496715366840363,
+      "eval_reward": 0.75,
+      "eval_reward_std": 0.7673887014389038,
+      "eval_rewards/accuracy_reward_math": 0.0,
+      "eval_rewards/accuracy_reward_staging": 0.0,
+      "eval_rewards/format_reward": 0.375,
+      "eval_rewards/format_reward_staging": 0.375,
+      "eval_runtime": 9.814,
+      "eval_samples_per_second": 1.63,
+      "eval_steps_per_second": 0.102,
+      "step": 2
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 23.95943994129872,
+      "learning_rate": 1.766044443118978e-05,
+      "loss": 0.0685,
+      "step": 3
+    },
+    {
+      "epoch": 3.0,
+      "eval_clip_ratio": 0.0,
+      "eval_completion_length": 544.375,
+      "eval_kl": 63.25,
+      "eval_loss": 1.4514538049697876,
+      "eval_reward": 1.125,
+      "eval_reward_std": 0.7886751294136047,
+      "eval_rewards/accuracy_reward_math": 0.0,
+      "eval_rewards/accuracy_reward_staging": 0.0,
+      "eval_rewards/format_reward": 0.625,
+      "eval_rewards/format_reward_staging": 0.5,
+      "eval_runtime": 10.8975,
+      "eval_samples_per_second": 1.468,
+      "eval_steps_per_second": 0.092,
+      "step": 3
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 40.3897041999098,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.1064,
+      "step": 4
+    },
+    {
+      "epoch": 4.0,
+      "eval_clip_ratio": 0.0,
+      "eval_completion_length": 490.1875,
+      "eval_kl": 1.453125,
+      "eval_loss": 0.18356087803840637,
+      "eval_reward": 1.375,
+      "eval_reward_std": 0.7427992820739746,
+      "eval_rewards/accuracy_reward_math": 0.0,
+      "eval_rewards/accuracy_reward_staging": 0.0,
+      "eval_rewards/format_reward": 0.75,
+      "eval_rewards/format_reward_staging": 0.625,
+      "eval_runtime": 9.682,
+      "eval_samples_per_second": 1.653,
+      "eval_steps_per_second": 0.103,
+      "step": 4
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 617.8779151304285,
+      "learning_rate": 1.1736481776669307e-05,
+      "loss": 0.4202,
+      "step": 5
+    },
+    {
+      "epoch": 5.0,
+      "eval_clip_ratio": 0.0,
+      "eval_completion_length": 579.5,
+      "eval_kl": 0.208984375,
+      "eval_loss": 0.23663775622844696,
+      "eval_reward": 1.25,
+      "eval_reward_std": 0.9082483053207397,
+      "eval_rewards/accuracy_reward_math": 0.0,
+      "eval_rewards/accuracy_reward_staging": 0.0,
+      "eval_rewards/format_reward": 0.75,
+      "eval_rewards/format_reward_staging": 0.5,
+      "eval_runtime": 10.2564,
+      "eval_samples_per_second": 1.56,
+      "eval_steps_per_second": 0.097,
+      "step": 5
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.9504042286680588,
+      "learning_rate": 8.263518223330698e-06,
+      "loss": 0.0833,
+      "step": 6
+    },
+    {
+      "epoch": 6.0,
+      "eval_clip_ratio": 0.0,
+      "eval_completion_length": 532.4375,
+      "eval_kl": 0.208984375,
+      "eval_loss": 0.25171786546707153,
+      "eval_reward": 1.0,
+      "eval_reward_std": 0.8643567562103271,
+      "eval_rewards/accuracy_reward_math": 0.0,
+      "eval_rewards/accuracy_reward_staging": 0.0,
+      "eval_rewards/format_reward": 0.5,
+      "eval_rewards/format_reward_staging": 0.5,
+      "eval_runtime": 10.0367,
+      "eval_samples_per_second": 1.594,
+      "eval_steps_per_second": 0.1,
+      "step": 6
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 0.8737839403793075,
+      "learning_rate": 5.000000000000003e-06,
+      "loss": 0.1363,
+      "step": 7
+    },
+    {
+      "epoch": 7.0,
+      "eval_clip_ratio": 0.0,
+      "eval_completion_length": 618.0,
+      "eval_kl": 0.12353515625,
+      "eval_loss": 0.12567630410194397,
+      "eval_reward": 0.875,
+      "eval_reward_std": 0.5684809684753418,
+      "eval_rewards/accuracy_reward_math": 0.0,
+      "eval_rewards/accuracy_reward_staging": 0.0,
+      "eval_rewards/format_reward": 0.625,
+      "eval_rewards/format_reward_staging": 0.25,
+      "eval_runtime": 11.9883,
+      "eval_samples_per_second": 1.335,
+      "eval_steps_per_second": 0.083,
+      "step": 7
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 0.9960909069556698,
+      "learning_rate": 2.339555568810221e-06,
+      "loss": 0.1077,
+      "step": 8
+    },
+    {
+      "epoch": 8.0,
+      "eval_clip_ratio": 0.0,
+      "eval_completion_length": 522.5625,
+      "eval_kl": 0.220703125,
+      "eval_loss": 0.17136843502521515,
+      "eval_reward": 1.125,
+      "eval_reward_std": 0.7427992820739746,
+      "eval_rewards/accuracy_reward_math": 0.0,
+      "eval_rewards/accuracy_reward_staging": 0.0,
+      "eval_rewards/format_reward": 0.75,
+      "eval_rewards/format_reward_staging": 0.375,
+      "eval_runtime": 9.9314,
+      "eval_samples_per_second": 1.611,
+      "eval_steps_per_second": 0.101,
+      "step": 8
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 1.4868290469557222,
+      "learning_rate": 6.030737921409169e-07,
+      "loss": 0.0948,
+      "step": 9
+    },
+    {
+      "epoch": 9.0,
+      "eval_clip_ratio": 0.0,
+      "eval_completion_length": 449.9375,
+      "eval_kl": 0.2080078125,
+      "eval_loss": 0.18853142857551575,
+      "eval_reward": 1.625,
+      "eval_reward_std": 0.4330126941204071,
+      "eval_rewards/accuracy_reward_math": 0.0,
+      "eval_rewards/accuracy_reward_staging": 0.0,
+      "eval_rewards/format_reward": 0.875,
+      "eval_rewards/format_reward_staging": 0.75,
+      "eval_runtime": 9.7136,
+      "eval_samples_per_second": 1.647,
+      "eval_steps_per_second": 0.103,
+      "step": 9
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 1.247559086562991,
+      "learning_rate": 0.0,
+      "loss": 0.1509,
+      "step": 10
+    },
+    {
+      "epoch": 10.0,
+      "eval_clip_ratio": 0.0,
+      "eval_completion_length": 586.6875,
+      "eval_kl": 0.1611328125,
+      "eval_loss": 0.21008853614330292,
+      "eval_reward": 1.0,
+      "eval_reward_std": 0.843070387840271,
+      "eval_rewards/accuracy_reward_math": 0.0,
+      "eval_rewards/accuracy_reward_staging": 0.0,
+      "eval_rewards/format_reward": 0.6875,
+      "eval_rewards/format_reward_staging": 0.3125,
+      "eval_runtime": 9.7606,
+      "eval_samples_per_second": 1.639,
+      "eval_steps_per_second": 0.102,
+      "step": 10
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 563.915625,
+      "epoch": 10.0,
+      "kl": 0.9728057861328125,
+      "reward": 3.8234375,
+      "reward_std": 4.318631359934807,
+      "rewards/accuracy_reward_math": 0.028125,
+      "rewards/accuracy_reward_staging": 0.0,
+      "rewards/format_reward": 0.6015625,
+      "rewards/format_reward_staging": 0.409375,
+      "step": 10,
+      "total_flos": 0.0,
+      "train_loss": 0.11724991016089917,
+      "train_runtime": 482.6536,
+      "train_samples_per_second": 0.332,
+      "train_steps_per_second": 0.021
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 10,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}
--- a/training_args.bin
+++ b/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e05aafa3cf4d88a830a1a8a12474710cbb2e09eae420a8eb3d7020123578b969
+size 8568
--- a/vocab.json
+++ b/vocab.json