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 +1,72 @@
+---
+base_model: Gensyn/Qwen2.5-1.5B-Instruct
+library_name: transformers
+model_name: Qwen2.5-1.5B-Instruct-Gensyn-Swarm-thriving_miniature_crane
+tags:
+- generated_from_trainer
+- rl-swarm
+- grpo
+- gensyn
+- I am thriving miniature crane
+- unsloth
+- trl
+licence: license
+---
+
+# Model Card for Qwen2.5-1.5B-Instruct-Gensyn-Swarm-thriving_miniature_crane
+
+This model is a fine-tuned version of [Gensyn/Qwen2.5-1.5B-Instruct](https://huggingface.co/Gensyn/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="Pastu9999/Qwen2.5-1.5B-Instruct-Gensyn-Swarm-thriving_miniature_crane", 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: 4.48.2
+- Pytorch: 2.5.1
+- Datasets: 3.6.0
+- 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}}
+}
+```

adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Gensyn/Qwen2.5-1.5B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "v_proj",
+    "q_proj",
+    "up_proj",
+    "gate_proj",
+    "k_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e997295884d9a4c0e4c8f5733b7420b3450f1ae210739caa2d07d8e929272c5
+size 73911112

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": 7.256088053964049e-07,
+    "train_runtime": 879.7266,
+    "train_samples": 17,
+    "train_samples_per_second": 0.364,
+    "train_steps_per_second": 0.023
+}

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": 7.256088053964049e-07,
+    "train_runtime": 879.7266,
+    "train_samples": 17,
+    "train_samples_per_second": 0.364,
+    "train_steps_per_second": 0.023
+}

trainer_state.json

@@ -0,0 +1,232 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 20,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "completion_length": 273.09375,
+      "epoch": 0.47058823529411764,
+      "grad_norm": 0.600865364074707,
+      "kl": 0.0008881491157808341,
+      "learning_rate": 4.965903258506806e-07,
+      "loss": 0.0,
+      "reward": 3.5266263484954834,
+      "reward_std": 2.8597480207681656,
+      "rewards/concensus_correctness_reward_func": 1.3701249994337559,
+      "rewards/consensus_reward_func": 0.4375,
+      "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.625,
+      "rewards/question_recreation_reward_func": 0.6300325468182564,
+      "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.015625,
+      "rewards/xmlcount_reward_func": 0.44834374263882637,
+      "step": 2
+    },
+    {
+      "completion_length": 246.03125,
+      "epoch": 0.9411764705882353,
+      "grad_norm": 0.5436103940010071,
+      "kl": 0.00089954834402306,
+      "learning_rate": 4.698684378016222e-07,
+      "loss": 0.0,
+      "reward": 4.55771266669035,
+      "reward_std": 3.4289634227752686,
+      "rewards/concensus_correctness_reward_func": 2.681749999523163,
+      "rewards/consensus_reward_func": 0.6875,
+      "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.25,
+      "rewards/question_recreation_reward_func": 0.5445562116801739,
+      "rewards/soft_format_reward_func": 0.015625,
+      "rewards/strict_format_reward_func": 0.046875,
+      "rewards/xmlcount_reward_func": 0.33140625339001417,
+      "step": 4
+    },
+    {
+      "completion_length": 244.65,
+      "epoch": 1.2352941176470589,
+      "grad_norm": 0.4586993157863617,
+      "kl": 0.0008338470594026149,
+      "learning_rate": 4.193203929064353e-07,
+      "loss": 0.0,
+      "reward": 2.124562442302704,
+      "reward_std": 1.3526578456163407,
+      "rewards/concensus_correctness_reward_func": 0.2,
+      "rewards/consensus_reward_func": 0.1,
+      "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.6,
+      "rewards/question_recreation_reward_func": 0.7809624433517456,
+      "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.443599995970726,
+      "step": 6
+    },
+    {
+      "completion_length": 297.09375,
+      "epoch": 1.7058823529411766,
+      "grad_norm": 0.502598226070404,
+      "kl": 0.0007695755630265921,
+      "learning_rate": 3.5042385616324236e-07,
+      "loss": 0.0,
+      "reward": 2.9820514023303986,
+      "reward_std": 3.2139550247229636,
+      "rewards/concensus_correctness_reward_func": 1.3648125007748604,
+      "rewards/consensus_reward_func": 0.4375,
+      "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.375,
+      "rewards/question_recreation_reward_func": 0.5220512766391039,
+      "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.046875,
+      "rewards/xmlcount_reward_func": 0.23581249662674963,
+      "step": 8
+    },
+    {
+      "completion_length": 305.75,
+      "epoch": 2.0,
+      "grad_norm": 0.15842241048812866,
+      "kl": 0.0008145646541379392,
+      "learning_rate": 2.706448363680831e-07,
+      "loss": 0.0,
+      "reward": 2.692780375480652,
+      "reward_std": 2.7954183399677275,
+      "rewards/concensus_correctness_reward_func": 1.1,
+      "rewards/consensus_reward_func": 0.5,
+      "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.4,
+      "rewards/question_recreation_reward_func": 0.6437303602695466,
+      "rewards/soft_format_reward_func": 0.025,
+      "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.024050001055002213,
+      "step": 10
+    },
+    {
+      "completion_length": 290.71875,
+      "epoch": 2.4705882352941178,
+      "grad_norm": 0.6278821229934692,
+      "kl": 0.0008684814747539349,
+      "learning_rate": 1.886286282148002e-07,
+      "loss": 0.0,
+      "reward": 3.573274150490761,
+      "reward_std": 4.03030751645565,
+      "rewards/concensus_correctness_reward_func": 1.968249998986721,
+      "rewards/consensus_reward_func": 0.5625,
+      "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.125,
+      "rewards/question_recreation_reward_func": 0.6497116237878799,
+      "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.2678124960511923,
+      "step": 12
+    },
+    {
+      "completion_length": 267.375,
+      "epoch": 2.9411764705882355,
+      "grad_norm": 0.5482789278030396,
+      "kl": 0.0009392677238793112,
+      "learning_rate": 1.1326296046939333e-07,
+      "loss": 0.0,
+      "reward": 1.7004917487502098,
+      "reward_std": 1.2563396487385035,
+      "rewards/concensus_correctness_reward_func": 0.06012500077486038,
+      "rewards/consensus_reward_func": 0.25,
+      "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.4375,
+      "rewards/question_recreation_reward_func": 0.5942417420446873,
+      "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.03125,
+      "rewards/xmlcount_reward_func": 0.32737500313669443,
+      "step": 14
+    },
+    {
+      "completion_length": 301.3,
+      "epoch": 3.235294117647059,
+      "grad_norm": 0.4986811578273773,
+      "kl": 0.0007466266164556145,
+      "learning_rate": 5.271487265090163e-08,
+      "loss": 0.0,
+      "reward": 6.155379509925842,
+      "reward_std": 4.6481368243694305,
+      "rewards/concensus_correctness_reward_func": 4.0,
+      "rewards/consensus_reward_func": 0.6,
+      "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.5,
+      "rewards/question_recreation_reward_func": 0.6659793496131897,
+      "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.38940000236034394,
+      "step": 16
+    },
+    {
+      "completion_length": 305.4375,
+      "epoch": 3.7058823529411766,
+      "grad_norm": 0.498955637216568,
+      "kl": 0.000753754866309464,
+      "learning_rate": 1.3545689574841341e-08,
+      "loss": 0.0,
+      "reward": 2.0631681233644485,
+      "reward_std": 2.531194042414427,
+      "rewards/concensus_correctness_reward_func": 0.8016875013709068,
+      "rewards/consensus_reward_func": 0.1875,
+      "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.25,
+      "rewards/question_recreation_reward_func": 0.742636825889349,
+      "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.08134375233203173,
+      "step": 18
+    },
+    {
+      "completion_length": 267.05,
+      "epoch": 4.0,
+      "grad_norm": 0.25652796030044556,
+      "kl": 0.0010063352179713546,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "reward": 1.545077133178711,
+      "reward_std": 1.4410690546035767,
+      "rewards/concensus_correctness_reward_func": 0.1343999981880188,
+      "rewards/consensus_reward_func": 0.4,
+      "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.0,
+      "rewards/question_recreation_reward_func": 0.7192271590232849,
+      "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.05,
+      "rewards/xmlcount_reward_func": 0.24144999980926513,
+      "step": 20
+    },
+    {
+      "epoch": 4.0,
+      "step": 20,
+      "total_flos": 0.0,
+      "train_loss": 7.256088053964049e-07,
+      "train_runtime": 879.7266,
+      "train_samples_per_second": 0.364,
+      "train_steps_per_second": 0.023
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 20,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "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": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e82dd8db99f3b4e251878c6becbb31a09d314943ae02f724958eeb2f22eacfff
+size 5944