End of training

.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 +1,71 @@
+---
+base_model: Gensyn/Qwen2.5-0.5B-Instruct
+library_name: transformers
+model_name: Qwen2.5-0.5B-Instruct-Gensyn-Swarm-reptilian_strong_gull
+tags:
+- generated_from_trainer
+- rl-swarm
+- grpo
+- gensyn
+- I am reptilian strong gull
+- trl
+licence: license
+---
+
+# Model Card for Qwen2.5-0.5B-Instruct-Gensyn-Swarm-reptilian_strong_gull
+
+This model is a fine-tuned version of [Gensyn/Qwen2.5-0.5B-Instruct](https://huggingface.co/Gensyn/Qwen2.5-0.5B-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="MajorJalud/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-reptilian_strong_gull", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+ 
+
+
+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: 0.15.2
+- Transformers: 4.51.0
+- Pytorch: 2.5.1+cu121
+- Datasets: 3.5.0
+- Tokenizers: 0.21.1
+
+## 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": 1.3341661542654037e-05,
+    "train_runtime": 1161.9841,
+    "train_samples": 177,
+    "train_samples_per_second": 0.551,
+    "train_steps_per_second": 0.034
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 896,
+  "initializer_range": 0.02,
+  "intermediate_size": 4864,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 14,
+  "num_hidden_layers": 24,
+  "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": "float32",
+  "transformers_version": "4.51.0",
+  "use_cache": true,
+  "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": "4.51.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47258c29a19d8b27491a7f624ea1b94aaf92c48a79f23b2fd067d5cf60821acb
+size 1976163472

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 +1,208 @@
+{
+  "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
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "total_flos": 0.0,
+    "train_loss": 1.3341661542654037e-05,
+    "train_runtime": 1161.9841,
+    "train_samples": 177,
+    "train_samples_per_second": 0.551,
+    "train_steps_per_second": 0.034
+}

trainer_state.json

@@ -0,0 +1,423 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.768361581920904,
+  "eval_steps": 500,
+  "global_step": 40,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "completion_length": 395.1875,
+      "epoch": 0.0903954802259887,
+      "grad_norm": 12.909080505371094,
+      "kl": 0.0,
+      "learning_rate": 2.5e-07,
+      "loss": 0.0,
+      "reward": 0.741524099605158,
+      "reward_std": 0.8750434047542512,
+      "rewards/concensus_correctness_reward_func": 0.04931249842047691,
+      "rewards/consensus_reward_func": 0.0,
+      "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.0,
+      "rewards/question_recreation_reward_func": 0.38252410243148915,
+      "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.30968749942258,
+      "step": 2
+    },
+    {
+      "completion_length": 368.4375,
+      "epoch": 0.1807909604519774,
+      "grad_norm": 98.61309814453125,
+      "kl": 0.0015454311651410535,
+      "learning_rate": 4.991461232516674e-07,
+      "loss": 0.0,
+      "reward": 0.7231733221560717,
+      "reward_std": 0.6990197440609336,
+      "rewards/concensus_correctness_reward_func": 0.06006250157952309,
+      "rewards/consensus_reward_func": 0.0625,
+      "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.0625,
+      "rewards/question_recreation_reward_func": 0.349392062285915,
+      "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.18871875389595516,
+      "step": 4
+    },
+    {
+      "completion_length": 413.59375,
+      "epoch": 0.2711864406779661,
+      "grad_norm": 5.511989593505859,
+      "kl": 0.0014776097959838808,
+      "learning_rate": 4.923500664848326e-07,
+      "loss": 0.0,
+      "reward": 0.8283879230730236,
+      "reward_std": 0.9614059533923864,
+      "rewards/concensus_correctness_reward_func": 0.0,
+      "rewards/consensus_reward_func": 0.0,
+      "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.1875,
+      "rewards/question_recreation_reward_func": 0.4520754173863679,
+      "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.18881250091362745,
+      "step": 6
+    },
+    {
+      "completion_length": 341.5625,
+      "epoch": 0.3615819209039548,
+      "grad_norm": 6.719244956970215,
+      "kl": 0.0043463728070491925,
+      "learning_rate": 4.789433316637643e-07,
+      "loss": 0.0,
+      "reward": 0.7259982999530621,
+      "reward_std": 0.848314385744743,
+      "rewards/concensus_correctness_reward_func": 0.0,
+      "rewards/consensus_reward_func": 0.0,
+      "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.3125,
+      "rewards/question_recreation_reward_func": 0.2496545419562608,
+      "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.16384375654160976,
+      "step": 8
+    },
+    {
+      "completion_length": 382.28125,
+      "epoch": 0.4519774011299435,
+      "grad_norm": 5.959508895874023,
+      "kl": 0.0068417362053878605,
+      "learning_rate": 4.592916195656321e-07,
+      "loss": 0.0,
+      "reward": 0.5442365016788244,
+      "reward_std": 0.8550017900124658,
+      "rewards/concensus_correctness_reward_func": 0.0,
+      "rewards/consensus_reward_func": 0.0625,
+      "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.1875,
+      "rewards/question_recreation_reward_func": 0.33914274349808693,
+      "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": -0.04490623530000448,
+      "step": 10
+    },
+    {
+      "completion_length": 345.9375,
+      "epoch": 0.5423728813559322,
+      "grad_norm": 50.09251022338867,
+      "kl": 0.013233292467702995,
+      "learning_rate": 4.339309776682829e-07,
+      "loss": 0.0,
+      "reward": 1.0947998807241675,
+      "reward_std": 0.8173792412999319,
+      "rewards/concensus_correctness_reward_func": 0.05431250110268593,
+      "rewards/consensus_reward_func": 0.0,
+      "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.0625,
+      "rewards/question_recreation_reward_func": 0.4228936360159423,
+      "rewards/soft_format_reward_func": 0.015625,
+      "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.5394687503576279,
+      "step": 12
+    },
+    {
+      "completion_length": 299.5,
+      "epoch": 0.632768361581921,
+      "grad_norm": 7.578136444091797,
+      "kl": 0.008452887726889458,
+      "learning_rate": 4.0355317817241697e-07,
+      "loss": 0.0,
+      "reward": 0.8402107721194625,
+      "reward_std": 0.5287668243981898,
+      "rewards/concensus_correctness_reward_func": 0.0,
+      "rewards/consensus_reward_func": 0.0,
+      "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.1875,
+      "rewards/question_recreation_reward_func": 0.4160232492722571,
+      "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.23668749257922173,
+      "step": 14
+    },
+    {
+      "completion_length": 336.3125,
+      "epoch": 0.7231638418079096,
+      "grad_norm": 11.147196769714355,
+      "kl": 0.005027780563978013,
+      "learning_rate": 3.689868482592684e-07,
+      "loss": 0.0,
+      "reward": 0.645062399096787,
+      "reward_std": 0.7169937930302694,
+      "rewards/concensus_correctness_reward_func": 0.0,
+      "rewards/consensus_reward_func": 0.0,
+      "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.125,
+      "rewards/question_recreation_reward_func": 0.40240614488720894,
+      "rewards/soft_format_reward_func": 0.015625,
+      "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.10203125467523932,
+      "step": 16
+    },
+    {
+      "completion_length": 392.03125,
+      "epoch": 0.8135593220338984,
+      "grad_norm": 5.5867919921875,
+      "kl": 0.012430467017111368,
+      "learning_rate": 3.3117486730117087e-07,
+      "loss": 0.0,
+      "reward": 0.8209520971868187,
+      "reward_std": 0.6172742367780302,
+      "rewards/concensus_correctness_reward_func": 0.0,
+      "rewards/consensus_reward_func": 0.0,
+      "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.125,
+      "rewards/question_recreation_reward_func": 0.35198333975858986,
+      "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.34396874718368053,
+      "step": 18
+    },
+    {
+      "completion_length": 405.40625,
+      "epoch": 0.903954802259887,
+      "grad_norm": 10.691946029663086,
+      "kl": 0.023764009936712682,
+      "learning_rate": 2.911486475701835e-07,
+      "loss": 0.0,
+      "reward": 0.9620864443713799,
+      "reward_std": 0.9047976815054426,
+      "rewards/concensus_correctness_reward_func": 0.06006250157952309,
+      "rewards/consensus_reward_func": 0.125,
+      "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.0625,
+      "rewards/question_recreation_reward_func": 0.3515239374828525,
+      "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.3629999961704016,
+      "step": 20
+    },
+    {
+      "completion_length": 355.09375,
+      "epoch": 0.9943502824858758,
+      "grad_norm": 9.022045135498047,
+      "kl": 0.011749600758776069,
+      "learning_rate": 2.5e-07,
+      "loss": 0.0,
+      "reward": 0.8011306787375361,
+      "reward_std": 0.8571250168606639,
+      "rewards/concensus_correctness_reward_func": 0.08168750256299973,
+      "rewards/consensus_reward_func": 0.0625,
+      "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.125,
+      "rewards/question_recreation_reward_func": 0.2845681729959324,
+      "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.2473749965429306,
+      "step": 22
+    },
+    {
+      "completion_length": 425.3333333333333,
+      "epoch": 1.0451977401129944,
+      "grad_norm": 6.792358875274658,
+      "kl": 0.023303805540005367,
+      "learning_rate": 2.0885135242981647e-07,
+      "loss": 0.0,
+      "reward": 1.2106047636932797,
+      "reward_std": 0.9797517756621043,
+      "rewards/concensus_correctness_reward_func": 0.252000007364485,
+      "rewards/consensus_reward_func": 0.0,
+      "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.2222222222222222,
+      "rewards/question_recreation_reward_func": 0.35054915419055355,
+      "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.3858333399726285,
+      "step": 24
+    },
+    {
+      "completion_length": 413.03125,
+      "epoch": 1.1355932203389831,
+      "grad_norm": 5.693543434143066,
+      "kl": 0.014714884586283006,
+      "learning_rate": 1.6882513269882913e-07,
+      "loss": 0.0,
+      "reward": 0.6772605418227613,
+      "reward_std": 1.0779747616034001,
+      "rewards/concensus_correctness_reward_func": 0.12224999815225601,
+      "rewards/consensus_reward_func": 0.0,
+      "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.0625,
+      "rewards/question_recreation_reward_func": 0.30310428922530264,
+      "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.1894062329083681,
+      "step": 26
+    },
+    {
+      "completion_length": 363.65625,
+      "epoch": 1.2259887005649717,
+      "grad_norm": 6.607933044433594,
+      "kl": 0.017230025347089395,
+      "learning_rate": 1.310131517407316e-07,
+      "loss": 0.0,
+      "reward": 0.9144510291516781,
+      "reward_std": 1.2254647206282243,
+      "rewards/concensus_correctness_reward_func": 0.0,
+      "rewards/consensus_reward_func": 0.0,
+      "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.1875,
+      "rewards/question_recreation_reward_func": 0.4910760330967605,
+      "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.015625,
+      "rewards/xmlcount_reward_func": 0.22024998906999826,
+      "step": 28
+    },
+    {
+      "completion_length": 383.0625,
+      "epoch": 1.3163841807909604,
+      "grad_norm": 36.09029769897461,
+      "kl": 0.024213542863435578,
+      "learning_rate": 9.644682182758304e-08,
+      "loss": 0.0,
+      "reward": 1.0125777404755354,
+      "reward_std": 1.0347315426915884,
+      "rewards/concensus_correctness_reward_func": 0.08168750256299973,
+      "rewards/consensus_reward_func": 0.125,
+      "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.0,
+      "rewards/question_recreation_reward_func": 0.3353589882608503,
+      "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.015625,
+      "rewards/xmlcount_reward_func": 0.45490624010562897,
+      "step": 30
+    },
+    {
+      "completion_length": 393.1875,
+      "epoch": 1.4067796610169492,
+      "grad_norm": 6.0061211585998535,
+      "kl": 0.011017081997124478,
+      "learning_rate": 6.60690223317171e-08,
+      "loss": 0.0,
+      "reward": 0.7806991545949131,
+      "reward_std": 0.603456055308925,
+      "rewards/concensus_correctness_reward_func": 0.0,
+      "rewards/consensus_reward_func": 0.0,
+      "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.125,
+      "rewards/question_recreation_reward_func": 0.3696991458127741,
+      "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.2859999978682026,
+      "step": 32
+    },
+    {
+      "completion_length": 363.125,
+      "epoch": 1.497175141242938,
+      "grad_norm": 7.000294208526611,
+      "kl": 0.028806680522393435,
+      "learning_rate": 4.0708380434367864e-08,
+      "loss": 0.0,
+      "reward": 0.6306989183649421,
+      "reward_std": 0.756230047903955,
+      "rewards/concensus_correctness_reward_func": 0.0,
+      "rewards/consensus_reward_func": 0.0,
+      "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.0,
+      "rewards/question_recreation_reward_func": 0.3588239252567291,
+      "rewards/soft_format_reward_func": 0.015625,
+      "rewards/strict_format_reward_func": 0.015625,
+      "rewards/xmlcount_reward_func": 0.24062499590218067,
+      "step": 34
+    },
+    {
+      "completion_length": 362.4375,
+      "epoch": 1.5875706214689265,
+      "grad_norm": 5.333078861236572,
+      "kl": 0.01488372879975941,
+      "learning_rate": 2.1056668336235623e-08,
+      "loss": 0.0,
+      "reward": 1.0692353853955865,
+      "reward_std": 0.9510939496103674,
+      "rewards/concensus_correctness_reward_func": 0.0,
+      "rewards/consensus_reward_func": 0.0,
+      "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.1875,
+      "rewards/question_recreation_reward_func": 0.437985401134938,
+      "rewards/soft_format_reward_func": 0.015625,
+      "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.42812499590218067,
+      "step": 36
+    },
+    {
+      "completion_length": 349.09375,
+      "epoch": 1.6779661016949152,
+      "grad_norm": 7.353602409362793,
+      "kl": 0.031051357771502808,
+      "learning_rate": 7.649933515167406e-09,
+      "loss": 0.0,
+      "reward": 0.9717537448741496,
+      "reward_std": 1.3127705492661335,
+      "rewards/concensus_correctness_reward_func": 0.08875000104308128,
+      "rewards/consensus_reward_func": 0.0625,
+      "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.125,
+      "rewards/question_recreation_reward_func": 0.40912871854379773,
+      "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.015625,
+      "rewards/xmlcount_reward_func": 0.27074999641627073,
+      "step": 38
+    },
+    {
+      "completion_length": 367.3125,
+      "epoch": 1.768361581920904,
+      "grad_norm": 6.507040977478027,
+      "kl": 0.02251754200551659,
+      "learning_rate": 8.538767483325383e-10,
+      "loss": 0.0,
+      "reward": 0.918883009813726,
+      "reward_std": 0.6078527495847084,
+      "rewards/concensus_correctness_reward_func": 0.0,
+      "rewards/consensus_reward_func": 0.0625,
+      "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.0,
+      "rewards/question_recreation_reward_func": 0.33338301815092564,
+      "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.015625,
+      "rewards/xmlcount_reward_func": 0.5073749935254455,
+      "step": 40
+    },
+    {
+      "epoch": 1.768361581920904,
+      "step": 40,
+      "total_flos": 0.0,
+      "train_loss": 1.3341661542654037e-05,
+      "train_runtime": 1161.9841,
+      "train_samples_per_second": 0.551,
+      "train_steps_per_second": 0.034
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 40,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 25,
+  "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": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7557ab5508c275e373c89cfd74d9aa7b697afc16215e520afd9296af7a39473b
+size 5944