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: R1-Qwen-1.5B-Simple-RL-QAT
+tags:
+- generated_from_trainer
+- trl
+- grpo
+licence: license
+---
+
+# Model Card for R1-Qwen-1.5B-Simple-RL-QAT
+
+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="superdocker/R1-Qwen-1.5B-Simple-RL-QAT", 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/superdocker/huggingface/runs/s5bapey3) 
+
+
+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: 4.49.0
+- Pytorch: 2.5.1
+- Datasets: 3.4.1
+- 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}}
+}
+```

all_results.json

@@ -0,0 +1,8 @@
+{
+    "total_flos": 0.0,
+    "train_loss": 8962.659198401161,
+    "train_runtime": 130047.8561,
+    "train_samples": 7500,
+    "train_samples_per_second": 0.058,
+    "train_steps_per_second": 0.001
+}

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "/raid/LLM/deepseek-r1-distill-qwen-1.5b",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "max_position_embeddings": 131072,
+  "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": 10000,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0",
+  "use_cache": false,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 151646,
+  "do_sample": true,
+  "eos_token_id": 151643,
+  "temperature": 0.6,
+  "top_p": 0.95,
+  "transformers_version": "4.49.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d057d060852eeb646ed52ada58c4f95f9229b752950c057f015cb15f0f15af1
+size 3554214752

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "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:a4256422650d141f228fe954acee98679da412984c29a569877eefd3af69315a
+size 11422959

tokenizer_config.json

@@ -0,0 +1,195 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<｜User｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151645": {
+      "content": "<｜Assistant｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151646": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|EOT|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151648": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151649": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "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
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin��>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜><think>\\n'}}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 16384,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizerFast",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "total_flos": 0.0,
+    "train_loss": 8962.659198401161,
+    "train_runtime": 130047.8561,
+    "train_samples": 7500,
+    "train_samples_per_second": 0.058,
+    "train_steps_per_second": 0.001
+}

trainer_state.json

@@ -0,0 +1,393 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.997867803837953,
+  "eval_steps": 100,
+  "global_step": 117,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 970.990234375,
+      "epoch": 0.008528784648187633,
+      "grad_norm": 5149.8681640625,
+      "kl": 108.171875,
+      "learning_rate": 2.5e-07,
+      "loss": 4.2554,
+      "reward": 0.04296875,
+      "reward_std": 0.08174194628372788,
+      "rewards/accuracy_reward": 0.04296875,
+      "rewards/format_reward": 0.0,
+      "step": 1
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 958.310546875,
+      "epoch": 0.042643923240938165,
+      "grad_norm": 172.85690307617188,
+      "kl": 18.325897216796875,
+      "learning_rate": 1.25e-06,
+      "loss": 0.7551,
+      "reward": 0.0498046875,
+      "reward_std": 0.08129667222965509,
+      "rewards/accuracy_reward": 0.0498046875,
+      "rewards/format_reward": 0.0,
+      "step": 5
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 976.34921875,
+      "epoch": 0.08528784648187633,
+      "grad_norm": 480.36053466796875,
+      "kl": 25.84681396484375,
+      "learning_rate": 2.5e-06,
+      "loss": 1.012,
+      "reward": 0.033984375,
+      "reward_std": 0.06525826780125499,
+      "rewards/accuracy_reward": 0.033984375,
+      "rewards/format_reward": 0.0,
+      "step": 10
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 958.119921875,
+      "epoch": 0.1279317697228145,
+      "grad_norm": 73.20281982421875,
+      "kl": 5242973.483386231,
+      "learning_rate": 2.993961440992859e-06,
+      "loss": 209719.025,
+      "reward": 0.05390625,
+      "reward_std": 0.09599261675029994,
+      "rewards/accuracy_reward": 0.05390625,
+      "rewards/format_reward": 0.0,
+      "step": 15
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 968.887890625,
+      "epoch": 0.17057569296375266,
+      "grad_norm": 6133.8427734375,
+      "kl": 101.4647705078125,
+      "learning_rate": 2.957235057439301e-06,
+      "loss": 3.494,
+      "reward": 0.040625,
+      "reward_std": 0.07280914252623916,
+      "rewards/accuracy_reward": 0.040625,
+      "rewards/format_reward": 0.0,
+      "step": 20
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 966.09453125,
+      "epoch": 0.21321961620469082,
+      "grad_norm": 42.56804656982422,
+      "kl": 3.52724609375,
+      "learning_rate": 2.887956450710995e-06,
+      "loss": 0.1737,
+      "reward": 0.043359375,
+      "reward_std": 0.08650039257481694,
+      "rewards/accuracy_reward": 0.043359375,
+      "rewards/format_reward": 0.0,
+      "step": 25
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 964.712890625,
+      "epoch": 0.255863539445629,
+      "grad_norm": 22.991064071655273,
+      "kl": 9.3487060546875,
+      "learning_rate": 2.7876731904027993e-06,
+      "loss": 0.4194,
+      "reward": 0.043359375,
+      "reward_std": 0.0765833955258131,
+      "rewards/accuracy_reward": 0.043359375,
+      "rewards/format_reward": 0.0,
+      "step": 30
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 966.508203125,
+      "epoch": 0.29850746268656714,
+      "grad_norm": 0.8270885348320007,
+      "kl": 1.1582275390625,
+      "learning_rate": 2.6586254388368995e-06,
+      "loss": 0.0603,
+      "reward": 0.032421875,
+      "reward_std": 0.06923360293731093,
+      "rewards/accuracy_reward": 0.032421875,
+      "rewards/format_reward": 0.0,
+      "step": 35
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 950.016015625,
+      "epoch": 0.3411513859275053,
+      "grad_norm": 1.6428107023239136,
+      "kl": 0.749462890625,
+      "learning_rate": 2.5036959095382875e-06,
+      "loss": 0.0448,
+      "reward": 0.0375,
+      "reward_std": 0.07326922472566366,
+      "rewards/accuracy_reward": 0.0375,
+      "rewards/format_reward": 0.0,
+      "step": 40
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 939.1578125,
+      "epoch": 0.3837953091684435,
+      "grad_norm": 0.9584478139877319,
+      "kl": 0.4450439453125,
+      "learning_rate": 2.3263454721781537e-06,
+      "loss": 0.0335,
+      "reward": 0.0328125,
+      "reward_std": 0.06661374988034367,
+      "rewards/accuracy_reward": 0.0328125,
+      "rewards/format_reward": 0.0,
+      "step": 45
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 913.96171875,
+      "epoch": 0.42643923240938164,
+      "grad_norm": 6.290709018707275,
+      "kl": 0.7226806640625,
+      "learning_rate": 2.1305358424643485e-06,
+      "loss": 0.0474,
+      "reward": 0.037890625,
+      "reward_std": 0.06831033481284976,
+      "rewards/accuracy_reward": 0.037890625,
+      "rewards/format_reward": 0.0,
+      "step": 50
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 918.1359375,
+      "epoch": 0.4690831556503198,
+      "grad_norm": 17.22686195373535,
+      "kl": 2.5564208984375,
+      "learning_rate": 1.9206410839590043e-06,
+      "loss": 0.1184,
+      "reward": 0.02421875,
+      "reward_std": 0.051806316059082744,
+      "rewards/accuracy_reward": 0.02421875,
+      "rewards/format_reward": 0.0,
+      "step": 55
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 926.554296875,
+      "epoch": 0.511727078891258,
+      "grad_norm": 0.19467273354530334,
+      "kl": 0.2774169921875,
+      "learning_rate": 1.7013498987264833e-06,
+      "loss": 0.0223,
+      "reward": 0.03046875,
+      "reward_std": 0.05941885020583868,
+      "rewards/accuracy_reward": 0.03046875,
+      "rewards/format_reward": 0.0,
+      "step": 60
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 899.465234375,
+      "epoch": 0.5543710021321961,
+      "grad_norm": 0.3655730187892914,
+      "kl": 0.3230712890625,
+      "learning_rate": 1.4775608894771048e-06,
+      "loss": 0.0251,
+      "reward": 0.033203125,
+      "reward_std": 0.06403546240180731,
+      "rewards/accuracy_reward": 0.033203125,
+      "rewards/format_reward": 0.0,
+      "step": 65
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 917.436328125,
+      "epoch": 0.5970149253731343,
+      "grad_norm": 0.2492106854915619,
+      "kl": 0.293310546875,
+      "learning_rate": 1.2542731328772936e-06,
+      "loss": 0.0277,
+      "reward": 0.02578125,
+      "reward_std": 0.055067837610840796,
+      "rewards/accuracy_reward": 0.02578125,
+      "rewards/format_reward": 0.0,
+      "step": 70
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 909.30859375,
+      "epoch": 0.6396588486140725,
+      "grad_norm": 2.718404531478882,
+      "kl": 0.3013916015625,
+      "learning_rate": 1.036474508437579e-06,
+      "loss": 0.0231,
+      "reward": 0.0328125,
+      "reward_std": 0.06329943230375648,
+      "rewards/accuracy_reward": 0.0328125,
+      "rewards/format_reward": 0.0,
+      "step": 75
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 912.4890625,
+      "epoch": 0.6823027718550106,
+      "grad_norm": 0.30672064423561096,
+      "kl": 0.372900390625,
+      "learning_rate": 8.290302775265509e-07,
+      "loss": 0.0301,
+      "reward": 0.048828125,
+      "reward_std": 0.08031583921983838,
+      "rewards/accuracy_reward": 0.048828125,
+      "rewards/format_reward": 0.0,
+      "step": 80
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 928.358203125,
+      "epoch": 0.7249466950959488,
+      "grad_norm": 0.3099748492240906,
+      "kl": 0.2901123046875,
+      "learning_rate": 6.3657440147149e-07,
+      "loss": 0.0265,
+      "reward": 0.034375,
+      "reward_std": 0.06373528819531202,
+      "rewards/accuracy_reward": 0.034375,
+      "rewards/format_reward": 0.0,
+      "step": 85
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 933.30234375,
+      "epoch": 0.767590618336887,
+      "grad_norm": 0.22397631406784058,
+      "kl": 0.2540771484375,
+      "learning_rate": 4.63406026519703e-07,
+      "loss": 0.0234,
+      "reward": 0.0328125,
+      "reward_std": 0.06618089880794287,
+      "rewards/accuracy_reward": 0.0328125,
+      "rewards/format_reward": 0.0,
+      "step": 90
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 925.9453125,
+      "epoch": 0.8102345415778252,
+      "grad_norm": 2.046766519546509,
+      "kl": 0.7256103515625,
+      "learning_rate": 3.133934480154885e-07,
+      "loss": 0.0453,
+      "reward": 0.03984375,
+      "reward_std": 0.07409646594896913,
+      "rewards/accuracy_reward": 0.03984375,
+      "rewards/format_reward": 0.0,
+      "step": 95
+    },
+    {
+      "epoch": 0.8528784648187633,
+      "grad_norm": 3.6699347496032715,
+      "learning_rate": 1.8988769907430552e-07,
+      "loss": 0.0264,
+      "step": 100
+    },
+    {
+      "epoch": 0.8528784648187633,
+      "eval_clip_ratio": 0.0,
+      "eval_completion_length": 919.21535,
+      "eval_kl": 0.7742375,
+      "eval_loss": 0.038456786423921585,
+      "eval_reward": 0.04495,
+      "eval_reward_std": 0.08059001454114914,
+      "eval_rewards/accuracy_reward": 0.04495,
+      "eval_rewards/format_reward": 0.0,
+      "eval_runtime": 50297.2291,
+      "eval_samples_per_second": 0.099,
+      "eval_steps_per_second": 0.002,
+      "step": 100
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 931.1998046875,
+      "epoch": 0.8955223880597015,
+      "grad_norm": 0.6975847482681274,
+      "kl": 0.38209228515625,
+      "learning_rate": 9.564769404039419e-08,
+      "loss": 0.0303,
+      "reward": 0.045703125,
+      "reward_std": 0.08059242363087833,
+      "rewards/accuracy_reward": 0.045703125,
+      "rewards/format_reward": 0.0,
+      "step": 105
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 931.4921875,
+      "epoch": 0.9381663113006397,
+      "grad_norm": 5.085315227508545,
+      "kl": 0.3639404296875,
+      "learning_rate": 3.277859889929147e-08,
+      "loss": 0.0291,
+      "reward": 0.03671875,
+      "reward_std": 0.0733986516483128,
+      "rewards/accuracy_reward": 0.03671875,
+      "rewards/format_reward": 0.0,
+      "step": 110
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 937.898828125,
+      "epoch": 0.9808102345415778,
+      "grad_norm": 0.3364603817462921,
+      "kl": 0.2610107421875,
+      "learning_rate": 2.684805348397268e-09,
+      "loss": 0.0206,
+      "reward": 0.041796875,
+      "reward_std": 0.07050482770428061,
+      "rewards/accuracy_reward": 0.041796875,
+      "rewards/format_reward": 0.0,
+      "step": 115
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 911.7675857543945,
+      "epoch": 0.997867803837953,
+      "kl": 0.24102783203125,
+      "reward": 0.0439453125,
+      "reward_std": 0.08275857008993626,
+      "rewards/accuracy_reward": 0.0439453125,
+      "rewards/format_reward": 0.0,
+      "step": 117,
+      "total_flos": 0.0,
+      "train_loss": 8962.659198401161,
+      "train_runtime": 130047.8561,
+      "train_samples_per_second": 0.058,
+      "train_steps_per_second": 0.001
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 117,
+  "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": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48e2219698298f124f88531b663cd37185126589e112bdb59b8b3c24284a6e21
+size 7992