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-Open-R1-GRPO-FC
+tags:
+- generated_from_trainer
+- trl
+- grpo
+licence: license
+---
+
+# Model Card for Qwen2.5-1.5B-Open-R1-GRPO-FC
+
+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="WSX/Qwen2.5-1.5B-Open-R1-GRPO-FC", 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/wsx/grpo/runs/lbc30dxe) 
+
+
+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.dev0
+- Pytorch: 2.5.1
+- Datasets: 3.3.0
+- 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": 0.03583788637523226,
+    "train_runtime": 2626.6322,
+    "train_samples": 5854,
+    "train_samples_per_second": 2.229,
+    "train_steps_per_second": 0.008
+}

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.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:d6aa4f0d49d1115fe2462601004a18972d9796ca76bcc3f14cc52e4f8c132d21
+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": 0.03583788637523226,
+    "train_runtime": 2626.6322,
+    "train_samples": 5854,
+    "train_samples_per_second": 2.229,
+    "train_steps_per_second": 0.008
+}

trainer_state.json

@@ -0,0 +1,372 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9617486338797814,
+  "eval_steps": 100,
+  "global_step": 22,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "completion_length": 55.38151168823242,
+      "epoch": 0.04371584699453552,
+      "grad_norm": 1.8832329750159524,
+      "kl": 0.0,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": -0.0,
+      "reward": 0.1412797785596922,
+      "reward_std": 0.24435854516923428,
+      "rewards/cosine_scaled_reward": 0.0033253214314754587,
+      "rewards/fc_accuracy_reward": 0.041536460601491854,
+      "rewards/format_reward": 0.09895833616610616,
+      "rewards/repetition_penalty_reward": -0.0025403407926205546,
+      "step": 1
+    },
+    {
+      "completion_length": 51.39323043823242,
+      "epoch": 0.08743169398907104,
+      "grad_norm": 1.7270200711131631,
+      "kl": 0.0,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": -0.0,
+      "reward": 0.14538411921239458,
+      "reward_std": 0.26959792035631835,
+      "rewards/cosine_scaled_reward": 0.011377881150110625,
+      "rewards/fc_accuracy_reward": 0.04414062711293809,
+      "rewards/format_reward": 0.09375000128056854,
+      "rewards/repetition_penalty_reward": -0.0038843913443997735,
+      "step": 2
+    },
+    {
+      "completion_length": 59.415366649627686,
+      "epoch": 0.13114754098360656,
+      "grad_norm": 11.794409102437369,
+      "kl": 0.108245849609375,
+      "learning_rate": 2e-05,
+      "loss": 0.0043,
+      "reward": 0.48175731860101223,
+      "reward_std": 0.6101971380412579,
+      "rewards/cosine_scaled_reward": 0.07848096883390099,
+      "rewards/fc_accuracy_reward": 0.1334635487291962,
+      "rewards/format_reward": 0.27473959140479565,
+      "rewards/repetition_penalty_reward": -0.004926790039462503,
+      "step": 3
+    },
+    {
+      "completion_length": 38.11979293823242,
+      "epoch": 0.17486338797814208,
+      "grad_norm": 14.648541660401936,
+      "kl": 0.699951171875,
+      "learning_rate": 1.9863613034027224e-05,
+      "loss": 0.028,
+      "reward": 0.5874797012656927,
+      "reward_std": 0.4514363035559654,
+      "rewards/cosine_scaled_reward": 0.03601911471923813,
+      "rewards/fc_accuracy_reward": 0.08763021184131503,
+      "rewards/format_reward": 0.4648437611758709,
+      "rewards/repetition_penalty_reward": -0.0010133983323612483,
+      "step": 4
+    },
+    {
+      "completion_length": 52.250000953674316,
+      "epoch": 0.2185792349726776,
+      "grad_norm": 100.60498858646368,
+      "kl": 2.2119140625,
+      "learning_rate": 1.9458172417006347e-05,
+      "loss": 0.0885,
+      "reward": 0.9119658470153809,
+      "reward_std": 0.36017190758138895,
+      "rewards/cosine_scaled_reward": -0.0071425273454224225,
+      "rewards/fc_accuracy_reward": 0.1251302184537053,
+      "rewards/format_reward": 0.7968750223517418,
+      "rewards/repetition_penalty_reward": -0.0028968810474907514,
+      "step": 5
+    },
+    {
+      "completion_length": 50.07161593437195,
+      "epoch": 0.26229508196721313,
+      "grad_norm": 8.772560705415271,
+      "kl": 0.6322021484375,
+      "learning_rate": 1.879473751206489e-05,
+      "loss": 0.0253,
+      "reward": 0.9710917063057423,
+      "reward_std": 0.23025251599028707,
+      "rewards/cosine_scaled_reward": -0.023823014635127038,
+      "rewards/fc_accuracy_reward": 0.11028647376224399,
+      "rewards/format_reward": 0.8880208507180214,
+      "rewards/repetition_penalty_reward": -0.003392611884919461,
+      "step": 6
+    },
+    {
+      "completion_length": 43.58724069595337,
+      "epoch": 0.30601092896174864,
+      "grad_norm": 8.583339840836018,
+      "kl": 0.90576171875,
+      "learning_rate": 1.789140509396394e-05,
+      "loss": 0.0362,
+      "reward": 0.9109659418463707,
+      "reward_std": 0.29892468452453613,
+      "rewards/cosine_scaled_reward": -0.018059035908663645,
+      "rewards/fc_accuracy_reward": 0.10651042824611068,
+      "rewards/format_reward": 0.8242187723517418,
+      "rewards/repetition_penalty_reward": -0.0017042156287061516,
+      "step": 7
+    },
+    {
+      "completion_length": 37.54166793823242,
+      "epoch": 0.34972677595628415,
+      "grad_norm": 18.463648975355095,
+      "kl": 1.037353515625,
+      "learning_rate": 1.6772815716257414e-05,
+      "loss": 0.0415,
+      "reward": 0.8660313636064529,
+      "reward_std": 0.33177425526082516,
+      "rewards/cosine_scaled_reward": -0.01570813774014823,
+      "rewards/fc_accuracy_reward": 0.09778647031635046,
+      "rewards/format_reward": 0.7851562760770321,
+      "rewards/repetition_penalty_reward": -0.0012032546765112784,
+      "step": 8
+    },
+    {
+      "completion_length": 31.50520920753479,
+      "epoch": 0.39344262295081966,
+      "grad_norm": 3.3269416154208553,
+      "kl": 1.053466796875,
+      "learning_rate": 1.5469481581224274e-05,
+      "loss": 0.0422,
+      "reward": 0.6192201878875494,
+      "reward_std": 0.419193297624588,
+      "rewards/cosine_scaled_reward": -0.011210447875782847,
+      "rewards/fc_accuracy_reward": 0.07591146510094404,
+      "rewards/format_reward": 0.5559896025806665,
+      "rewards/repetition_penalty_reward": -0.0014704558852827176,
+      "step": 9
+    },
+    {
+      "completion_length": 33.796876072883606,
+      "epoch": 0.4371584699453552,
+      "grad_norm": 2.107401637313207,
+      "kl": 0.7822265625,
+      "learning_rate": 1.4016954246529697e-05,
+      "loss": 0.0313,
+      "reward": 1.0176529847085476,
+      "reward_std": 0.22293917182832956,
+      "rewards/cosine_scaled_reward": -0.009169983572064666,
+      "rewards/fc_accuracy_reward": 0.12968751369044185,
+      "rewards/format_reward": 0.8971354365348816,
+      "rewards/repetition_penalty_reward": 0.0,
+      "step": 10
+    },
+    {
+      "completion_length": 41.14974093437195,
+      "epoch": 0.4808743169398907,
+      "grad_norm": 1.4402921474481505,
+      "kl": 0.679931640625,
+      "learning_rate": 1.2454854871407993e-05,
+      "loss": 0.0272,
+      "reward": 1.216365858912468,
+      "reward_std": 0.3025409309193492,
+      "rewards/cosine_scaled_reward": 0.02841056811303133,
+      "rewards/fc_accuracy_reward": 0.266666691750288,
+      "rewards/format_reward": 0.9244791828095913,
+      "rewards/repetition_penalty_reward": -0.003190596245985944,
+      "step": 11
+    },
+    {
+      "completion_length": 50.187501549720764,
+      "epoch": 0.5245901639344263,
+      "grad_norm": 1.342044356039293,
+      "kl": 0.669921875,
+      "learning_rate": 1.0825793454723325e-05,
+      "loss": 0.0268,
+      "reward": 1.4612180143594742,
+      "reward_std": 0.18933531921356916,
+      "rewards/cosine_scaled_reward": 0.10955476562958211,
+      "rewards/fc_accuracy_reward": 0.4023437798023224,
+      "rewards/format_reward": 0.9544271007180214,
+      "rewards/repetition_penalty_reward": -0.0051076257368549705,
+      "step": 12
+    },
+    {
+      "completion_length": 36.83073055744171,
+      "epoch": 0.5683060109289617,
+      "grad_norm": 0.9018777370229832,
+      "kl": 0.653076171875,
+      "learning_rate": 9.174206545276678e-06,
+      "loss": 0.0262,
+      "reward": 1.5253793448209763,
+      "reward_std": 0.13951857259962708,
+      "rewards/cosine_scaled_reward": 0.13023585244081914,
+      "rewards/fc_accuracy_reward": 0.4156250189989805,
+      "rewards/format_reward": 0.9817708469927311,
+      "rewards/repetition_penalty_reward": -0.002252384554594755,
+      "step": 13
+    },
+    {
+      "completion_length": 31.886719346046448,
+      "epoch": 0.6120218579234973,
+      "grad_norm": 0.9179618159859205,
+      "kl": 0.79296875,
+      "learning_rate": 7.545145128592009e-06,
+      "loss": 0.0317,
+      "reward": 1.558693140745163,
+      "reward_std": 0.07319424720481038,
+      "rewards/cosine_scaled_reward": 0.1392532378085889,
+      "rewards/fc_accuracy_reward": 0.42864586040377617,
+      "rewards/format_reward": 0.9921875074505806,
+      "rewards/repetition_penalty_reward": -0.001393431652104482,
+      "step": 14
+    },
+    {
+      "completion_length": 31.346355080604553,
+      "epoch": 0.6557377049180327,
+      "grad_norm": 1.009971914727988,
+      "kl": 0.93505859375,
+      "learning_rate": 5.983045753470308e-06,
+      "loss": 0.0374,
+      "reward": 1.5804978013038635,
+      "reward_std": 0.08376341307302937,
+      "rewards/cosine_scaled_reward": 0.1469495526398532,
+      "rewards/fc_accuracy_reward": 0.4442708622664213,
+      "rewards/format_reward": 0.9895833432674408,
+      "rewards/repetition_penalty_reward": -0.00030594062991440296,
+      "step": 15
+    },
+    {
+      "completion_length": 26.658854842185974,
+      "epoch": 0.6994535519125683,
+      "grad_norm": 0.9299064645773841,
+      "kl": 1.033935546875,
+      "learning_rate": 4.530518418775734e-06,
+      "loss": 0.0413,
+      "reward": 1.5300041437149048,
+      "reward_std": 0.0824247582568205,
+      "rewards/cosine_scaled_reward": 0.11685306887375191,
+      "rewards/fc_accuracy_reward": 0.4248698279261589,
+      "rewards/format_reward": 0.9882812574505806,
+      "rewards/repetition_penalty_reward": 0.0,
+      "step": 16
+    },
+    {
+      "completion_length": 36.76823031902313,
+      "epoch": 0.7431693989071039,
+      "grad_norm": 2.1900606434093626,
+      "kl": 1.2373046875,
+      "learning_rate": 3.2271842837425917e-06,
+      "loss": 0.0496,
+      "reward": 1.5113726258277893,
+      "reward_std": 0.1698010341024201,
+      "rewards/cosine_scaled_reward": 0.13497130031464621,
+      "rewards/fc_accuracy_reward": 0.42135421000421047,
+      "rewards/format_reward": 0.9557291828095913,
+      "rewards/repetition_penalty_reward": -0.0006820437265560031,
+      "step": 17
+    },
+    {
+      "completion_length": 49.17057418823242,
+      "epoch": 0.7868852459016393,
+      "grad_norm": 0.9898074648849621,
+      "kl": 1.117431640625,
+      "learning_rate": 2.1085949060360654e-06,
+      "loss": 0.0448,
+      "reward": 1.5271190851926804,
+      "reward_std": 0.16099856700748205,
+      "rewards/cosine_scaled_reward": 0.13386501389322802,
+      "rewards/fc_accuracy_reward": 0.4380208794027567,
+      "rewards/format_reward": 0.9570312723517418,
+      "rewards/repetition_penalty_reward": -0.0017980517004616559,
+      "step": 18
+    },
+    {
+      "completion_length": 50.75651168823242,
+      "epoch": 0.8306010928961749,
+      "grad_norm": 0.8055862276983312,
+      "kl": 1.159423828125,
+      "learning_rate": 1.2052624879351105e-06,
+      "loss": 0.0465,
+      "reward": 1.496125541627407,
+      "reward_std": 0.1544362655840814,
+      "rewards/cosine_scaled_reward": 0.11817182961385697,
+      "rewards/fc_accuracy_reward": 0.4263021294027567,
+      "rewards/format_reward": 0.9570312723517418,
+      "rewards/repetition_penalty_reward": -0.00537964966497384,
+      "step": 19
+    },
+    {
+      "completion_length": 40.93099093437195,
+      "epoch": 0.8743169398907104,
+      "grad_norm": 8.98525804041065,
+      "kl": 1.443359375,
+      "learning_rate": 5.418275829936537e-07,
+      "loss": 0.0578,
+      "reward": 1.53387813270092,
+      "reward_std": 0.09519629355054349,
+      "rewards/cosine_scaled_reward": 0.1257812106050551,
+      "rewards/fc_accuracy_reward": 0.43723963014781475,
+      "rewards/format_reward": 0.9739583544433117,
+      "rewards/repetition_penalty_reward": -0.003101027221418917,
+      "step": 20
+    },
+    {
+      "completion_length": 30.914063453674316,
+      "epoch": 0.9180327868852459,
+      "grad_norm": 1.3501653057736693,
+      "kl": 1.30712890625,
+      "learning_rate": 1.3638696597277678e-07,
+      "loss": 0.0524,
+      "reward": 1.5729020088911057,
+      "reward_std": 0.04961471362184966,
+      "rewards/cosine_scaled_reward": 0.13885675882920623,
+      "rewards/fc_accuracy_reward": 0.4460937939584255,
+      "rewards/format_reward": 0.9895833432674408,
+      "rewards/repetition_penalty_reward": -0.0016318318084813654,
+      "step": 21
+    },
+    {
+      "completion_length": 36.44921946525574,
+      "epoch": 0.9617486338797814,
+      "grad_norm": 1.2523038963374014,
+      "kl": 1.23388671875,
+      "learning_rate": 0.0,
+      "loss": 0.0495,
+      "reward": 1.538924165070057,
+      "reward_std": 0.0849971016177733,
+      "rewards/cosine_scaled_reward": 0.1276409742422402,
+      "rewards/fc_accuracy_reward": 0.43411462008953094,
+      "rewards/format_reward": 0.9804687686264515,
+      "rewards/repetition_penalty_reward": -0.0033001738775055856,
+      "step": 22
+    },
+    {
+      "epoch": 0.9617486338797814,
+      "step": 22,
+      "total_flos": 0.0,
+      "train_loss": 0.03583788637523226,
+      "train_runtime": 2626.6322,
+      "train_samples_per_second": 2.229,
+      "train_steps_per_second": 0.008
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 22,
+  "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": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d753786459e95abbd80d9bc92e977007c556821ad62ba03f5ac7fcc319d0e625
+size 7672