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: Tim
+tags:
+- generated_from_trainer
+- trl
+- grpo
+licence: license
+---
+
+# Model Card for Tim
+
+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="luohy/Tim", 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/autonomous-nlp/huggingface/runs/4if8qrvd) 
+
+
+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: 3.1.0
+- 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 +1,26 @@
+{
+  "</Thought>": 151666,
+  "</tool_call>": 151658,
+  "<Thought>": 151665,
+  "<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": 0.0001987359993598567,
+    "train_runtime": 7692.2558,
+    "train_samples": 7500,
+    "train_samples_per_second": 0.975,
+    "train_steps_per_second": 0.01
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "/home/hongyin/LLaMA-Factory/saves/thread_model/sft_exp",
+  "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 sha256:20dacd751d781773cde1a674ef4ac9dd979a59cba07cd0593e780a5a81689d56
+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 sha256:3fdc9523c99c2553ba2bba5a884baceb10cce106883ce1c7fa415496eb83994b
+size 11422436

tokenizer_config.json

@@ -0,0 +1,225 @@
+{
+  "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
+    },
+    "151665": {
+      "content": "<Thought>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</Thought>",
+      "lstrip": false,
+      "normalized": true,
+      "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": 2048,
+  "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": 0.0001987359993598567,
+    "train_runtime": 7692.2558,
+    "train_samples": 7500,
+    "train_samples_per_second": 0.975,
+    "train_steps_per_second": 0.01
+}

trainer_state.json

@@ -0,0 +1,259 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9984,
+  "eval_steps": 10000,
+  "global_step": 78,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "advantage": 2.050441083312035,
+      "completion_length": 549.2318519592285,
+      "epoch": 0.064,
+      "grad_norm": 0.3377276062965393,
+      "kl": 0.00016334056854248047,
+      "learning_rate": 1.875e-06,
+      "loss": 0.0,
+      "reward": 1.4327381163835526,
+      "reward_std": 0.2913255948573351,
+      "rewards/accuracy_reward": 0.43273810148239134,
+      "rewards/format_reward": 1.0,
+      "step": 5
+    },
+    {
+      "advantage": 1.8731657922267915,
+      "completion_length": 535.2622138977051,
+      "epoch": 0.128,
+      "grad_norm": 0.2055761218070984,
+      "kl": 0.001010751724243164,
+      "learning_rate": 2.993961440992859e-06,
+      "loss": 0.0,
+      "reward": 1.500892886519432,
+      "reward_std": 0.25598252601921556,
+      "rewards/accuracy_reward": 0.5008928671479225,
+      "rewards/format_reward": 1.0,
+      "step": 10
+    },
+    {
+      "advantage": 1.8132987678050996,
+      "completion_length": 546.9449508666992,
+      "epoch": 0.192,
+      "grad_norm": 0.22043277323246002,
+      "kl": 0.00526275634765625,
+      "learning_rate": 2.9265847744427307e-06,
+      "loss": 0.0002,
+      "reward": 1.535119077563286,
+      "reward_std": 0.23049755450338125,
+      "rewards/accuracy_reward": 0.5351190570741892,
+      "rewards/format_reward": 1.0,
+      "step": 15
+    },
+    {
+      "advantage": 1.9496307998895646,
+      "completion_length": 559.6901908874512,
+      "epoch": 0.256,
+      "grad_norm": 0.18047218024730682,
+      "kl": 0.006356048583984375,
+      "learning_rate": 2.7876731904027993e-06,
+      "loss": 0.0003,
+      "reward": 1.5279762238264083,
+      "reward_std": 0.21949078943580388,
+      "rewards/accuracy_reward": 0.5279762007296085,
+      "rewards/format_reward": 1.0,
+      "step": 20
+    },
+    {
+      "advantage": 1.9445811256766319,
+      "completion_length": 561.3247123718262,
+      "epoch": 0.32,
+      "grad_norm": 0.17815344035625458,
+      "kl": 0.00570068359375,
+      "learning_rate": 2.584192295741087e-06,
+      "loss": 0.0002,
+      "reward": 1.5446428924798965,
+      "reward_std": 0.23059090217575431,
+      "rewards/accuracy_reward": 0.5446428753435612,
+      "rewards/format_reward": 1.0,
+      "step": 25
+    },
+    {
+      "advantage": 1.7600619524717331,
+      "completion_length": 547.6345359802247,
+      "epoch": 0.384,
+      "grad_norm": 0.18666820228099823,
+      "kl": 0.00573883056640625,
+      "learning_rate": 2.3263454721781537e-06,
+      "loss": 0.0002,
+      "reward": 1.5431547909975052,
+      "reward_std": 0.21657919492572547,
+      "rewards/accuracy_reward": 0.5431547746062279,
+      "rewards/format_reward": 1.0,
+      "step": 30
+    },
+    {
+      "advantage": 1.7993007361888886,
+      "completion_length": 546.9157859802247,
+      "epoch": 0.448,
+      "grad_norm": 0.1700781136751175,
+      "kl": 0.00593109130859375,
+      "learning_rate": 2.027062236122014e-06,
+      "loss": 0.0002,
+      "reward": 1.5273809880018234,
+      "reward_std": 0.2096662785857916,
+      "rewards/accuracy_reward": 0.5273809637874365,
+      "rewards/format_reward": 1.0,
+      "step": 35
+    },
+    {
+      "advantage": 1.896444058418274,
+      "completion_length": 552.3208389282227,
+      "epoch": 0.512,
+      "grad_norm": 0.1920849233865738,
+      "kl": 0.005233001708984375,
+      "learning_rate": 1.7013498987264833e-06,
+      "loss": 0.0002,
+      "reward": 1.5434524178504945,
+      "reward_std": 0.22238524220883846,
+      "rewards/accuracy_reward": 0.5434523917734623,
+      "rewards/format_reward": 1.0,
+      "step": 40
+    },
+    {
+      "advantage": 1.870384192466736,
+      "completion_length": 558.927098083496,
+      "epoch": 0.576,
+      "grad_norm": 0.18718139827251434,
+      "kl": 0.0053081512451171875,
+      "learning_rate": 1.3655410366448499e-06,
+      "loss": 0.0002,
+      "reward": 1.5154762089252471,
+      "reward_std": 0.21234574727714062,
+      "rewards/accuracy_reward": 0.5154761992394924,
+      "rewards/format_reward": 1.0,
+      "step": 45
+    },
+    {
+      "advantage": 1.9293582290410995,
+      "completion_length": 554.5389984130859,
+      "epoch": 0.64,
+      "grad_norm": 0.2384500652551651,
+      "kl": 0.0057861328125,
+      "learning_rate": 1.036474508437579e-06,
+      "loss": 0.0002,
+      "reward": 1.5339285999536514,
+      "reward_std": 0.2257133638486266,
+      "rewards/accuracy_reward": 0.5339285805821419,
+      "rewards/format_reward": 1.0,
+      "step": 50
+    },
+    {
+      "advantage": 1.9427187949419022,
+      "completion_length": 556.450008392334,
+      "epoch": 0.704,
+      "grad_norm": 0.19755816459655762,
+      "kl": 0.005307769775390625,
+      "learning_rate": 7.30651083891141e-07,
+      "loss": 0.0002,
+      "reward": 1.5452381312847137,
+      "reward_std": 0.2197699649259448,
+      "rewards/accuracy_reward": 0.545238108932972,
+      "rewards/format_reward": 1.0,
+      "step": 55
+    },
+    {
+      "advantage": 1.8897637754678727,
+      "completion_length": 560.4640045166016,
+      "epoch": 0.768,
+      "grad_norm": 0.24272561073303223,
+      "kl": 0.005287933349609375,
+      "learning_rate": 4.63406026519703e-07,
+      "loss": 0.0002,
+      "reward": 1.525297647714615,
+      "reward_std": 0.24526160284876825,
+      "rewards/accuracy_reward": 0.5252976305782795,
+      "rewards/format_reward": 1.0,
+      "step": 60
+    },
+    {
+      "advantage": 1.9503421396017075,
+      "completion_length": 557.6199478149414,
+      "epoch": 0.832,
+      "grad_norm": 0.18535475432872772,
+      "kl": 0.005422210693359375,
+      "learning_rate": 2.48140119418046e-07,
+      "loss": 0.0002,
+      "reward": 1.517559552192688,
+      "reward_std": 0.21927062328904867,
+      "rewards/accuracy_reward": 0.5175595372915268,
+      "rewards/format_reward": 1.0,
+      "step": 65
+    },
+    {
+      "advantage": 1.9777270182967186,
+      "completion_length": 550.9339363098145,
+      "epoch": 0.896,
+      "grad_norm": 0.23573845624923706,
+      "kl": 0.00623931884765625,
+      "learning_rate": 9.564769404039419e-08,
+      "loss": 0.0002,
+      "reward": 1.5324405014514924,
+      "reward_std": 0.22246364038437605,
+      "rewards/accuracy_reward": 0.5324404895305633,
+      "rewards/format_reward": 1.0,
+      "step": 70
+    },
+    {
+      "advantage": 1.8454515248537064,
+      "completion_length": 566.992268371582,
+      "epoch": 0.96,
+      "grad_norm": 0.18028907477855682,
+      "kl": 0.00513458251953125,
+      "learning_rate": 1.357535734809795e-08,
+      "loss": 0.0002,
+      "reward": 1.515476217865944,
+      "reward_std": 0.22508260188624263,
+      "rewards/accuracy_reward": 0.5154761977493763,
+      "rewards/format_reward": 1.0,
+      "step": 75
+    },
+    {
+      "advantage": 2.0446028262376785,
+      "completion_length": 550.128978729248,
+      "epoch": 0.9984,
+      "kl": 0.005794525146484375,
+      "reward": 1.536210338274638,
+      "reward_std": 0.22843041829764843,
+      "rewards/accuracy_reward": 0.5362103283405304,
+      "rewards/format_reward": 1.0,
+      "step": 78,
+      "total_flos": 0.0,
+      "train_loss": 0.0001987359993598567,
+      "train_runtime": 7692.2558,
+      "train_samples_per_second": 0.975,
+      "train_steps_per_second": 0.01
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 78,
+  "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": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34634245ce5f9d48b7d43206a578590dbebe2cf55f6bcef09d862ed523bc452b
+size 7160