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
+tags:
+- generated_from_trainer
+- trl
+- grpo
+licence: license
+---
+
+# Model Card for Qwen2.5-1.5B-Instruct-Open-R1-GRPO
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="schwamaths/Qwen2.5-1.5B-Instruct-Open-R1-GRPO", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/zwt963/huggingface/runs/qf6r4ry3) 
+
+
+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": 0.007735961908474564,
+    "train_runtime": 2204.9615,
+    "train_samples": 891,
+    "train_samples_per_second": 4.041,
+    "train_steps_per_second": 0.036
+}

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:bcd36eb3e7cb0d3f525d6098036ca449aaf11a2be8091ebc57e69010cb9f99ab
+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": 0.007735961908474564,
+    "train_runtime": 2204.9615,
+    "train_samples": 891,
+    "train_samples_per_second": 4.041,
+    "train_steps_per_second": 0.036
+}

trainer_state.json

@@ -0,0 +1,258 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "eval_steps": 10,
+  "global_step": 80,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "completion_length": 91.19632097482682,
+      "epoch": 1.25,
+      "grad_norm": 1.1969395875930786,
+      "kl": 0.1442023515701294,
+      "learning_rate": 1.9961946980917457e-05,
+      "loss": 0.0211,
+      "reward": 1.1485491564497352,
+      "reward_std": 0.3577419674023986,
+      "rewards/accuracy_reward": 0.3771205507218838,
+      "rewards/format_reward": 0.7714285938069224,
+      "step": 10
+    },
+    {
+      "epoch": 1.25,
+      "eval_completion_length": 41.17280626296997,
+      "eval_kl": 9.25634765625,
+      "eval_loss": 0.3707638382911682,
+      "eval_reward": 1.5239955931901932,
+      "eval_reward_std": 0.11370187811553478,
+      "eval_rewards/accuracy_reward": 0.5267857350409031,
+      "eval_rewards/format_reward": 0.997209832072258,
+      "eval_runtime": 17.0057,
+      "eval_samples_per_second": 13.113,
+      "eval_steps_per_second": 0.47,
+      "step": 10
+    },
+    {
+      "completion_length": 77.98214609622956,
+      "epoch": 2.5,
+      "grad_norm": 0.38055306673049927,
+      "kl": 0.1487640380859375,
+      "learning_rate": 1.866025403784439e-05,
+      "loss": 0.0059,
+      "reward": 1.5377232797443867,
+      "reward_std": 0.112967933062464,
+      "rewards/accuracy_reward": 0.5417410933063366,
+      "rewards/format_reward": 0.9959821529686451,
+      "step": 20
+    },
+    {
+      "epoch": 2.5,
+      "eval_completion_length": 74.35160541534424,
+      "eval_kl": 79363.1533203125,
+      "eval_loss": 3201.5810546875,
+      "eval_reward": 1.4969618618488312,
+      "eval_reward_std": 0.11330691166222095,
+      "eval_rewards/accuracy_reward": 0.4997520036995411,
+      "eval_rewards/format_reward": 0.997209832072258,
+      "eval_runtime": 16.492,
+      "eval_samples_per_second": 13.522,
+      "eval_steps_per_second": 0.485,
+      "step": 20
+    },
+    {
+      "completion_length": 68.95022611618042,
+      "epoch": 3.75,
+      "grad_norm": 0.411288321018219,
+      "kl": 0.2060882568359375,
+      "learning_rate": 1.573576436351046e-05,
+      "loss": 0.0081,
+      "reward": 1.601116143167019,
+      "reward_std": 0.09683309164829552,
+      "rewards/accuracy_reward": 0.6053571676835418,
+      "rewards/format_reward": 0.9957589406520129,
+      "step": 30
+    },
+    {
+      "epoch": 3.75,
+      "eval_completion_length": 80.51895523071289,
+      "eval_kl": 1.675048828125,
+      "eval_loss": 0.06678587198257446,
+      "eval_reward": 1.5466683954000473,
+      "eval_reward_std": 0.08276130817830563,
+      "eval_rewards/accuracy_reward": 0.5472263805568218,
+      "eval_rewards/format_reward": 0.9994419664144516,
+      "eval_runtime": 18.4204,
+      "eval_samples_per_second": 12.106,
+      "eval_steps_per_second": 0.434,
+      "step": 30
+    },
+    {
+      "completion_length": 86.34196748733521,
+      "epoch": 5.0,
+      "grad_norm": 0.30611079931259155,
+      "kl": 0.15224609375,
+      "learning_rate": 1.1736481776669307e-05,
+      "loss": 0.006,
+      "reward": 1.7011161364614964,
+      "reward_std": 0.05814310675486922,
+      "rewards/accuracy_reward": 0.7026785946451127,
+      "rewards/format_reward": 0.9984375044703484,
+      "step": 40
+    },
+    {
+      "epoch": 5.0,
+      "eval_completion_length": 95.69973850250244,
+      "eval_kl": 1.921630859375,
+      "eval_loss": 0.07705733180046082,
+      "eval_reward": 1.5726687014102936,
+      "eval_reward_std": 0.08731811679899693,
+      "eval_rewards/accuracy_reward": 0.5726686716079712,
+      "eval_rewards/format_reward": 1.0,
+      "eval_runtime": 27.6097,
+      "eval_samples_per_second": 8.077,
+      "eval_steps_per_second": 0.29,
+      "step": 40
+    },
+    {
+      "completion_length": 88.07578473091125,
+      "epoch": 6.25,
+      "grad_norm": 0.186005100607872,
+      "kl": 0.138330078125,
+      "learning_rate": 7.411809548974792e-06,
+      "loss": 0.0056,
+      "reward": 1.7131697207689285,
+      "reward_std": 0.046526999399065974,
+      "rewards/accuracy_reward": 0.7152902040630579,
+      "rewards/format_reward": 0.997879472374916,
+      "step": 50
+    },
+    {
+      "epoch": 6.25,
+      "eval_completion_length": 82.68043422698975,
+      "eval_kl": 0.50927734375,
+      "eval_loss": 0.020424507558345795,
+      "eval_reward": 1.5327174961566925,
+      "eval_reward_std": 0.06632188148796558,
+      "eval_rewards/accuracy_reward": 0.5343915484845638,
+      "eval_rewards/format_reward": 0.9983258992433548,
+      "eval_runtime": 22.0694,
+      "eval_samples_per_second": 10.104,
+      "eval_steps_per_second": 0.362,
+      "step": 50
+    },
+    {
+      "completion_length": 82.71183357238769,
+      "epoch": 7.5,
+      "grad_norm": 0.21738964319229126,
+      "kl": 0.133831787109375,
+      "learning_rate": 3.5721239031346067e-06,
+      "loss": 0.0054,
+      "reward": 1.7395090013742447,
+      "reward_std": 0.03326362115330994,
+      "rewards/accuracy_reward": 0.7408482428640127,
+      "rewards/format_reward": 0.9986607193946838,
+      "step": 60
+    },
+    {
+      "epoch": 7.5,
+      "eval_completion_length": 85.38940906524658,
+      "eval_kl": 0.82177734375,
+      "eval_loss": 0.033002614974975586,
+      "eval_reward": 1.538297861814499,
+      "eval_reward_std": 0.053902728483080864,
+      "eval_rewards/accuracy_reward": 0.5399719178676605,
+      "eval_rewards/format_reward": 0.9983258992433548,
+      "eval_runtime": 24.6306,
+      "eval_samples_per_second": 9.054,
+      "eval_steps_per_second": 0.325,
+      "step": 60
+    },
+    {
+      "completion_length": 87.68672251701355,
+      "epoch": 8.75,
+      "grad_norm": 0.16990460455417633,
+      "kl": 0.12266845703125,
+      "learning_rate": 9.369221296335007e-07,
+      "loss": 0.0049,
+      "reward": 1.7386161454021931,
+      "reward_std": 0.025158090936020016,
+      "rewards/accuracy_reward": 0.739843780361116,
+      "rewards/format_reward": 0.9987723261117936,
+      "step": 70
+    },
+    {
+      "epoch": 8.75,
+      "eval_completion_length": 88.4438066482544,
+      "eval_kl": 1.0899658203125,
+      "eval_loss": 0.043835245072841644,
+      "eval_reward": 1.5355076640844345,
+      "eval_reward_std": 0.05012673186138272,
+      "eval_rewards/accuracy_reward": 0.5355076231062412,
+      "eval_rewards/format_reward": 1.0,
+      "eval_runtime": 23.079,
+      "eval_samples_per_second": 9.662,
+      "eval_steps_per_second": 0.347,
+      "step": 70
+    },
+    {
+      "completion_length": 87.12489142417908,
+      "epoch": 10.0,
+      "grad_norm": 0.18827787041664124,
+      "kl": 0.1228912353515625,
+      "learning_rate": 0.0,
+      "loss": 0.0049,
+      "reward": 1.7418527446687222,
+      "reward_std": 0.028121343860402704,
+      "rewards/accuracy_reward": 0.7435268083587289,
+      "rewards/format_reward": 0.9983258992433548,
+      "step": 80
+    },
+    {
+      "epoch": 10.0,
+      "eval_completion_length": 89.6388931274414,
+      "eval_kl": 0.638916015625,
+      "eval_loss": 0.025608114898204803,
+      "eval_reward": 1.533275529742241,
+      "eval_reward_std": 0.07100645918399096,
+      "eval_rewards/accuracy_reward": 0.5360656566917896,
+      "eval_rewards/format_reward": 0.997209832072258,
+      "eval_runtime": 26.5482,
+      "eval_samples_per_second": 8.4,
+      "eval_steps_per_second": 0.301,
+      "step": 80
+    },
+    {
+      "epoch": 10.0,
+      "step": 80,
+      "total_flos": 0.0,
+      "train_loss": 0.007735961908474564,
+      "train_runtime": 2204.9615,
+      "train_samples_per_second": 4.041,
+      "train_steps_per_second": 0.036
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 80,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "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": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7997b82e14676fde33a3d08444edb9eaa791adab6c2582967d3283951b34decf
+size 7224