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 +1,68 @@
+---
+base_model: Qwen/Qwen2.5-1.5B-Instruct
+library_name: transformers
+model_name: Qwen2.5-1.5B-Instruct-Open-R1-GRPO-gsm8k2
+tags:
+- generated_from_trainer
+- trl
+- grpo
+licence: license
+---
+
+# Model Card for Qwen2.5-1.5B-Instruct-Open-R1-GRPO-gsm8k2
+
+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="ununtrium/Qwen2.5-1.5B-Instruct-Open-R1-GRPO-gsm8k2", 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/re10749484/huggingface/runs/eoffmxv4) 
+
+
+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: 0.15.0.dev0
+- Transformers: 4.49.0.dev0
+- Pytorch: 2.5.1
+- Datasets: 3.2.0
+- 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}}
+}
+```

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": 0.0,
+    "train_loss": 0.0854370246613116,
+    "train_runtime": 2996.315,
+    "train_samples": 7473,
+    "train_samples_per_second": 2.494,
+    "train_steps_per_second": 0.022
+}

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 sha256:3c9fce895df90bd9ce7e965ec31b37418ac2b0363fc5f8b70cfa7d3ffa29567c
+size 3087467144

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
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5eee858c5123a4279c3e1f7b81247343f356ac767940b2692a928ad929543214
+size 11422063

tokenizer_config.json

@@ -0,0 +1,209 @@
+{
+  "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|>",
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "total_flos": 0.0,
+    "train_loss": 0.0854370246613116,
+    "train_runtime": 2996.315,
+    "train_samples": 7473,
+    "train_samples_per_second": 2.494,
+    "train_steps_per_second": 0.022
+}

trainer_state.json

@@ -0,0 +1,245 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9887640449438202,
+  "eval_steps": 100,
+  "global_step": 66,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "completion_length": 133.09732789993285,
+      "epoch": 0.0749063670411985,
+      "grad_norm": 1.5293161678134963,
+      "kl": 0.023732519149780272,
+      "learning_rate": 1.4285714285714287e-05,
+      "loss": 0.001,
+      "reward": 1.653250901401043,
+      "reward_std": 0.6752304386347532,
+      "rewards/accuracy_reward": 0.5250000260770321,
+      "rewards/cosine_scaled_reward": 0.34640559698455037,
+      "rewards/format_reward": 0.7250000283122062,
+      "rewards/reasoning_steps_reward": 0.056845242623239756,
+      "step": 5
+    },
+    {
+      "completion_length": 102.5696473121643,
+      "epoch": 0.149812734082397,
+      "grad_norm": 1.3144666712389457,
+      "kl": 0.15343170166015624,
+      "learning_rate": 1.9872683547213446e-05,
+      "loss": 0.0061,
+      "reward": 1.7395714558660984,
+      "reward_std": 0.6690045401453972,
+      "rewards/accuracy_reward": 0.5000000222586095,
+      "rewards/cosine_scaled_reward": 0.40504757558394433,
+      "rewards/format_reward": 0.8053571842610836,
+      "rewards/reasoning_steps_reward": 0.02916666897945106,
+      "step": 10
+    },
+    {
+      "completion_length": 68.31875326633454,
+      "epoch": 0.2247191011235955,
+      "grad_norm": 1.690644929593771,
+      "kl": 0.4529541015625,
+      "learning_rate": 1.9106347728549134e-05,
+      "loss": 0.0181,
+      "reward": 1.5209994725883007,
+      "reward_std": 0.4919801800744608,
+      "rewards/accuracy_reward": 0.3375000160187483,
+      "rewards/cosine_scaled_reward": 0.30939229315263217,
+      "rewards/format_reward": 0.8714286126196384,
+      "rewards/reasoning_steps_reward": 0.0026785717345774174,
+      "step": 15
+    },
+    {
+      "completion_length": 27.072322607040405,
+      "epoch": 0.299625468164794,
+      "grad_norm": 5.038040476887466,
+      "kl": 0.86884765625,
+      "learning_rate": 1.7698339834299064e-05,
+      "loss": 0.0348,
+      "reward": 1.3508709453046321,
+      "reward_std": 0.2549172870512848,
+      "rewards/accuracy_reward": 0.19553572423756121,
+      "rewards/cosine_scaled_reward": 0.1919423281069612,
+      "rewards/format_reward": 0.9633928693830967,
+      "rewards/reasoning_steps_reward": 0.0,
+      "step": 20
+    },
+    {
+      "completion_length": 19.96160795688629,
+      "epoch": 0.37453183520599254,
+      "grad_norm": 0.7209085060337556,
+      "kl": 1.62548828125,
+      "learning_rate": 1.5747874102144073e-05,
+      "loss": 0.065,
+      "reward": 1.1604069240391255,
+      "reward_std": 0.1543787806871933,
+      "rewards/accuracy_reward": 0.09196429010480642,
+      "rewards/cosine_scaled_reward": 0.08987116043572314,
+      "rewards/format_reward": 0.9785714387893677,
+      "rewards/reasoning_steps_reward": 0.0,
+      "step": 25
+    },
+    {
+      "completion_length": 14.525000703334808,
+      "epoch": 0.449438202247191,
+      "grad_norm": 1.0679577003741414,
+      "kl": 2.248828125,
+      "learning_rate": 1.3392388661180303e-05,
+      "loss": 0.0899,
+      "reward": 1.0422519214451313,
+      "reward_std": 0.07961238992461403,
+      "rewards/accuracy_reward": 0.028571429941803218,
+      "rewards/cosine_scaled_reward": 0.02707329906115774,
+      "rewards/format_reward": 0.9866071492433548,
+      "rewards/reasoning_steps_reward": 0.0,
+      "step": 30
+    },
+    {
+      "completion_length": 16.882143712043764,
+      "epoch": 0.5243445692883895,
+      "grad_norm": 1.9915464242130758,
+      "kl": 2.50048828125,
+      "learning_rate": 1.0797861055530832e-05,
+      "loss": 0.1,
+      "reward": 1.0598101012408734,
+      "reward_std": 0.08466785513780906,
+      "rewards/accuracy_reward": 0.03660714449360967,
+      "rewards/cosine_scaled_reward": 0.03391720272193197,
+      "rewards/format_reward": 0.9892857186496258,
+      "rewards/reasoning_steps_reward": 0.0,
+      "step": 35
+    },
+    {
+      "completion_length": 17.50357232093811,
+      "epoch": 0.599250936329588,
+      "grad_norm": 0.6015571750593173,
+      "kl": 2.02138671875,
+      "learning_rate": 8.147112759128859e-06,
+      "loss": 0.0808,
+      "reward": 1.0429342821240426,
+      "reward_std": 0.08854535985910843,
+      "rewards/accuracy_reward": 0.027678572665899993,
+      "rewards/cosine_scaled_reward": 0.025969939603237437,
+      "rewards/format_reward": 0.9892857193946838,
+      "rewards/reasoning_steps_reward": 0.0,
+      "step": 40
+    },
+    {
+      "completion_length": 17.032143676280974,
+      "epoch": 0.6741573033707865,
+      "grad_norm": 1.5617783259086722,
+      "kl": 9.1677734375,
+      "learning_rate": 5.626926795411447e-06,
+      "loss": 0.3657,
+      "reward": 1.0205947622656821,
+      "reward_std": 0.04966565851066207,
+      "rewards/accuracy_reward": 0.016071429289877415,
+      "rewards/cosine_scaled_reward": 0.013451844768133015,
+      "rewards/format_reward": 0.9910714328289032,
+      "rewards/reasoning_steps_reward": 0.0,
+      "step": 45
+    },
+    {
+      "completion_length": 24.61875115633011,
+      "epoch": 0.7490636704119851,
+      "grad_norm": 12.921102363021035,
+      "kl": 2.09052734375,
+      "learning_rate": 3.414886209349615e-06,
+      "loss": 0.0836,
+      "reward": 1.0334184400737285,
+      "reward_std": 0.07184715992339079,
+      "rewards/accuracy_reward": 0.026785715483129025,
+      "rewards/cosine_scaled_reward": 0.02270410436904058,
+      "rewards/format_reward": 0.9839285790920258,
+      "rewards/reasoning_steps_reward": 0.0,
+      "step": 50
+    },
+    {
+      "completion_length": 37.971430158615114,
+      "epoch": 0.8239700374531835,
+      "grad_norm": 0.7983120982012815,
+      "kl": 2.83486328125,
+      "learning_rate": 1.6668608091748495e-06,
+      "loss": 0.1137,
+      "reward": 1.026642444729805,
+      "reward_std": 0.09744821136546307,
+      "rewards/accuracy_reward": 0.028571429941803218,
+      "rewards/cosine_scaled_reward": 0.024261438589019236,
+      "rewards/format_reward": 0.9732142984867096,
+      "rewards/reasoning_steps_reward": 0.0005952381528913975,
+      "step": 55
+    },
+    {
+      "completion_length": 47.03750244379044,
+      "epoch": 0.898876404494382,
+      "grad_norm": 0.413637391163457,
+      "kl": 1.8755859375,
+      "learning_rate": 5.060239153161872e-07,
+      "loss": 0.075,
+      "reward": 1.005486535280943,
+      "reward_std": 0.12288255607795691,
+      "rewards/accuracy_reward": 0.026785715576261283,
+      "rewards/cosine_scaled_reward": 0.02066505177790532,
+      "rewards/format_reward": 0.9571428760886193,
+      "rewards/reasoning_steps_reward": 0.0008928572293370962,
+      "step": 60
+    },
+    {
+      "completion_length": 41.104466354846956,
+      "epoch": 0.9737827715355806,
+      "grad_norm": 0.8917372735425451,
+      "kl": 1.94501953125,
+      "learning_rate": 1.4173043232380557e-08,
+      "loss": 0.0778,
+      "reward": 1.0319705478847028,
+      "reward_std": 0.12593294799758042,
+      "rewards/accuracy_reward": 0.03571428749710322,
+      "rewards/cosine_scaled_reward": 0.030184772261418403,
+      "rewards/format_reward": 0.9660714447498322,
+      "rewards/reasoning_steps_reward": 0.0,
+      "step": 65
+    },
+    {
+      "completion_length": 23.01785808801651,
+      "epoch": 0.9887640449438202,
+      "kl": 1.99560546875,
+      "reward": 1.0267603546380997,
+      "reward_std": 0.08640075298319516,
+      "rewards/accuracy_reward": 0.022321429569274187,
+      "rewards/cosine_scaled_reward": 0.01783171975694131,
+      "rewards/format_reward": 0.9866071492433548,
+      "rewards/reasoning_steps_reward": 0.0,
+      "step": 66,
+      "total_flos": 0.0,
+      "train_loss": 0.0854370246613116,
+      "train_runtime": 2996.315,
+      "train_samples_per_second": 2.494,
+      "train_steps_per_second": 0.022
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 66,
+  "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": 0.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd4858d59e8b2dadbe249a2a1fbffa22325707b632aa7a528cffbb09885c21e2
+size 7544