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 +1,67 @@
+---
+library_name: transformers
+model_name: Qwen2.5-1.5B-Knowledge-R1-GRPO
+tags:
+- generated_from_trainer
+- trl
+- grpo
+licence: license
+---
+
+# Model Card for Qwen2.5-1.5B-Knowledge-R1-GRPO
+
+This model is a fine-tuned version of [None](https://huggingface.co/None).
+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="hzy/Qwen2.5-1.5B-Knowledge-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/hzy312/20250213_r1_reproduction_Qwen2.5-7B-Instruct/runs/7260141089.64907-a1c86941-d0dc-49fe-9efb-9e462fccb34f) 
+
+
+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: 4.50.0.dev0
+- Pytorch: 2.5.1
+- Datasets: 3.3.1
+- 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": 0.8091914746710049,
+    "train_runtime": 1407.163,
+    "train_samples": 3000,
+    "train_samples_per_second": 2.132,
+    "train_steps_per_second": 0.066
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "/mnt/hzy/huggingface/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": "4.50.0.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": "4.50.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bbfad1ec560c3061a084c3e784781846e972117cf0fb461baeccabd352e9f9a
+size 3554214752

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": 0.8091914746710049,
+    "train_runtime": 1407.163,
+    "train_samples": 3000,
+    "train_samples_per_second": 2.132,
+    "train_steps_per_second": 0.066
+}

trainer_state.json

@@ -0,0 +1,282 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.992,
+  "eval_steps": 100,
+  "global_step": 93,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "completion_length": 83.49553909301758,
+      "epoch": 0.05333333333333334,
+      "grad_norm": 2.946824789047241,
+      "kl": 0.026171875,
+      "learning_rate": 1e-05,
+      "loss": 0.0504,
+      "reward": 1.0073841661214828,
+      "reward_std": 0.3887816868722439,
+      "rewards/accuracy_reward": 0.14845555564388632,
+      "rewards/format_reward": 0.8589286029338836,
+      "step": 5
+    },
+    {
+      "completion_length": 63.945538711547854,
+      "epoch": 0.10666666666666667,
+      "grad_norm": 1.571755290031433,
+      "kl": 0.2385009765625,
+      "learning_rate": 2e-05,
+      "loss": 0.0558,
+      "reward": 1.2769583702087401,
+      "reward_std": 0.32510815411806104,
+      "rewards/accuracy_reward": 0.34570833705365656,
+      "rewards/format_reward": 0.9312500298023224,
+      "step": 10
+    },
+    {
+      "completion_length": 118.45268440246582,
+      "epoch": 0.16,
+      "grad_norm": 1.153508186340332,
+      "kl": 0.22421875,
+      "learning_rate": 1.9821451197042028e-05,
+      "loss": 0.074,
+      "reward": 1.3446466624736786,
+      "reward_std": 0.17655574008822442,
+      "rewards/accuracy_reward": 0.37143233343958854,
+      "rewards/format_reward": 0.9732143223285675,
+      "step": 15
+    },
+    {
+      "completion_length": 72.2758960723877,
+      "epoch": 0.21333333333333335,
+      "grad_norm": 1.0410367250442505,
+      "kl": 0.249658203125,
+      "learning_rate": 1.9292180723175656e-05,
+      "loss": 0.0812,
+      "reward": 1.3081952214241028,
+      "reward_std": 0.15275245811790228,
+      "rewards/accuracy_reward": 0.3278380483388901,
+      "rewards/format_reward": 0.9803571730852128,
+      "step": 20
+    },
+    {
+      "completion_length": 82.00714645385742,
+      "epoch": 0.26666666666666666,
+      "grad_norm": 3.899296283721924,
+      "kl": 0.328662109375,
+      "learning_rate": 1.8431088700310846e-05,
+      "loss": 0.1017,
+      "reward": 1.2941585779190063,
+      "reward_std": 0.19304655976593493,
+      "rewards/accuracy_reward": 0.32005139868706467,
+      "rewards/format_reward": 0.9741071671247482,
+      "step": 25
+    },
+    {
+      "completion_length": 77.67946739196778,
+      "epoch": 0.32,
+      "grad_norm": 1.397476315498352,
+      "kl": 2.7615234375,
+      "learning_rate": 1.7268924518431437e-05,
+      "loss": 0.251,
+      "reward": 1.3103554368019104,
+      "reward_std": 0.15524439504370094,
+      "rewards/accuracy_reward": 0.33535538613796234,
+      "rewards/format_reward": 0.9750000327825546,
+      "step": 30
+    },
+    {
+      "completion_length": 79.3669677734375,
+      "epoch": 0.37333333333333335,
+      "grad_norm": 122074.0,
+      "kl": 51.05595703125,
+      "learning_rate": 1.5847188782240473e-05,
+      "loss": 7.1564,
+      "reward": 1.327359426021576,
+      "reward_std": 0.164985740929842,
+      "rewards/accuracy_reward": 0.35771650820970535,
+      "rewards/format_reward": 0.9696428775787354,
+      "step": 35
+    },
+    {
+      "completion_length": 76.49107475280762,
+      "epoch": 0.4266666666666667,
+      "grad_norm": 1.5084730386734009,
+      "kl": 1.08857421875,
+      "learning_rate": 1.421665133450184e-05,
+      "loss": 0.2492,
+      "reward": 1.26935233771801,
+      "reward_std": 0.2393886812031269,
+      "rewards/accuracy_reward": 0.3220308694988489,
+      "rewards/format_reward": 0.9473214626312256,
+      "step": 40
+    },
+    {
+      "completion_length": 60.37143115997314,
+      "epoch": 0.48,
+      "grad_norm": 5.504000663757324,
+      "kl": 0.9216796875,
+      "learning_rate": 1.2435538277109919e-05,
+      "loss": 0.257,
+      "reward": 1.1870483577251434,
+      "reward_std": 0.365088003128767,
+      "rewards/accuracy_reward": 0.3245483174920082,
+      "rewards/format_reward": 0.8625000417232513,
+      "step": 45
+    },
+    {
+      "completion_length": 77.00178890228271,
+      "epoch": 0.5333333333333333,
+      "grad_norm": 13.98648738861084,
+      "kl": 1.57734375,
+      "learning_rate": 1.0567452730930743e-05,
+      "loss": 0.4099,
+      "reward": 1.2545486301183701,
+      "reward_std": 0.3059411861002445,
+      "rewards/accuracy_reward": 0.3581200173124671,
+      "rewards/format_reward": 0.8964286118745803,
+      "step": 50
+    },
+    {
+      "completion_length": 102.69554042816162,
+      "epoch": 0.5866666666666667,
+      "grad_norm": 3.6652588844299316,
+      "kl": 1.3572265625,
+      "learning_rate": 8.67910358358298e-06,
+      "loss": 0.2785,
+      "reward": 1.2746213912963866,
+      "reward_std": 0.22128227204084397,
+      "rewards/accuracy_reward": 0.36212137453258036,
+      "rewards/format_reward": 0.9125000447034836,
+      "step": 55
+    },
+    {
+      "completion_length": 49.54285945892334,
+      "epoch": 0.64,
+      "grad_norm": 5.973795413970947,
+      "kl": 0.57060546875,
+      "learning_rate": 6.837923331031761e-06,
+      "loss": 0.1544,
+      "reward": 1.3531022787094116,
+      "reward_std": 0.15567359821870924,
+      "rewards/accuracy_reward": 0.38167363181710245,
+      "rewards/format_reward": 0.9714285969734192,
+      "step": 60
+    },
+    {
+      "completion_length": 52.60535907745361,
+      "epoch": 0.6933333333333334,
+      "grad_norm": 258.8158874511719,
+      "kl": 1.1435546875,
+      "learning_rate": 5.109660079301668e-06,
+      "loss": 0.2287,
+      "reward": 1.369783765077591,
+      "reward_std": 0.22403131760656833,
+      "rewards/accuracy_reward": 0.41174802035093305,
+      "rewards/format_reward": 0.9580357491970062,
+      "step": 65
+    },
+    {
+      "completion_length": 60.183038330078126,
+      "epoch": 0.7466666666666667,
+      "grad_norm": 19.724451065063477,
+      "kl": 9.8796875,
+      "learning_rate": 3.5560296953512296e-06,
+      "loss": 1.3277,
+      "reward": 1.2982603132724762,
+      "reward_std": 0.1867620149627328,
+      "rewards/accuracy_reward": 0.34022452123463154,
+      "rewards/format_reward": 0.9580357611179352,
+      "step": 70
+    },
+    {
+      "completion_length": 67.0285737991333,
+      "epoch": 0.8,
+      "grad_norm": 12.512688636779785,
+      "kl": 2.2923828125,
+      "learning_rate": 2.2325119482391466e-06,
+      "loss": 0.3679,
+      "reward": 1.3391007900238037,
+      "reward_std": 0.19398864060640336,
+      "rewards/accuracy_reward": 0.3801721505820751,
+      "rewards/format_reward": 0.9589286029338837,
+      "step": 75
+    },
+    {
+      "completion_length": 59.462503051757814,
+      "epoch": 0.8533333333333334,
+      "grad_norm": 10.946759223937988,
+      "kl": 1.1609375,
+      "learning_rate": 1.1863693398535115e-06,
+      "loss": 0.3028,
+      "reward": 1.2912298798561097,
+      "reward_std": 0.23379612043499948,
+      "rewards/accuracy_reward": 0.3439084179699421,
+      "rewards/format_reward": 0.9473214656114578,
+      "step": 80
+    },
+    {
+      "completion_length": 62.05714569091797,
+      "epoch": 0.9066666666666666,
+      "grad_norm": 2.7115020751953125,
+      "kl": 24.92548828125,
+      "learning_rate": 4.549593722844492e-07,
+      "loss": 3.2784,
+      "reward": 1.3244690299034119,
+      "reward_std": 0.2418539199978113,
+      "rewards/accuracy_reward": 0.37625470347702505,
+      "rewards/format_reward": 0.948214316368103,
+      "step": 85
+    },
+    {
+      "completion_length": 63.81518135070801,
+      "epoch": 0.96,
+      "grad_norm": 18.27069854736328,
+      "kl": 1.3669921875,
+      "learning_rate": 6.440052036815081e-08,
+      "loss": 0.2765,
+      "reward": 1.24473577439785,
+      "reward_std": 0.2036956178024411,
+      "rewards/accuracy_reward": 0.2938428785651922,
+      "rewards/format_reward": 0.9508928924798965,
+      "step": 90
+    },
+    {
+      "completion_length": 61.40922896067301,
+      "epoch": 0.992,
+      "kl": 0.8439127604166666,
+      "reward": 1.329135666290919,
+      "reward_std": 0.2243182628105084,
+      "rewards/accuracy_reward": 0.3752665625264247,
+      "rewards/format_reward": 0.9538690745830536,
+      "step": 93,
+      "total_flos": 0.0,
+      "train_loss": 0.8091914746710049,
+      "train_runtime": 1407.163,
+      "train_samples_per_second": 2.132,
+      "train_steps_per_second": 0.066
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 93,
+  "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": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62b47b3bbecd063f96dea1c33c6cceea384a2eef478b060909a45bec14f92a0f
+size 7544