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: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
+library_name: transformers
+model_name: Qwen2.5-1.5B-Open-R1-GRPO
+tags:
+- generated_from_trainer
+- trl
+- grpo
+licence: license
+---
+
+# Model Card for Qwen2.5-1.5B-Open-R1-GRPO
+
+This model is a fine-tuned version of [deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B).
+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="qgallouedec/Qwen2.5-1.5B-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/huggingface/huggingface/runs/01bzzj29) 
+
+
+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: 4.48.2
+- 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}}
+}
+```

all_results.json

@@ -0,0 +1,8 @@
+{
+    "total_flos": 0.0,
+    "train_loss": 0.014327551128428614,
+    "train_runtime": 37261.3403,
+    "train_samples": 72441,
+    "train_samples_per_second": 1.944,
+    "train_steps_per_second": 0.004
+}

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "deepseek-ai/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": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.48.2",
+  "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": "4.48.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eceff82baa18ea8138916ad6afee457705462ee3fc073919f7b6dfa2faed606e
+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 +1,196 @@
+{
+  "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｜>'}}{% 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｜>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "total_flos": 0.0,
+    "train_loss": 0.014327551128428614,
+    "train_runtime": 37261.3403,
+    "train_samples": 72441,
+    "train_samples_per_second": 1.944,
+    "train_steps_per_second": 0.004
+}

trainer_state.json

@@ -0,0 +1,244 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9964664310954063,
+  "eval_steps": 100,
+  "global_step": 141,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "completion_length": 850.0869255065918,
+      "epoch": 0.0706713780918728,
+      "grad_norm": 0.0022115861294292796,
+      "kl": 0.003094172477722168,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.0001,
+      "reward": 0.29531251308508216,
+      "reward_std": 0.19793715761043132,
+      "rewards/accuracy_reward": 0.29531251308508216,
+      "rewards/format_reward": 0.0,
+      "step": 10
+    },
+    {
+      "completion_length": 744.1211002349853,
+      "epoch": 0.1413427561837456,
+      "grad_norm": 0.003696289903221297,
+      "kl": 0.018381881713867187,
+      "learning_rate": 1.9922392066001724e-05,
+      "loss": 0.0007,
+      "reward": 0.48858819287270305,
+      "reward_std": 0.2174148814752698,
+      "rewards/accuracy_reward": 0.48858819287270305,
+      "rewards/format_reward": 0.0,
+      "step": 20
+    },
+    {
+      "completion_length": 713.0984733581543,
+      "epoch": 0.21201413427561838,
+      "grad_norm": 0.0024686855149483843,
+      "kl": 0.02651519775390625,
+      "learning_rate": 1.9308737486442045e-05,
+      "loss": 0.0011,
+      "reward": 0.5330636397004127,
+      "reward_std": 0.2213304042816162,
+      "rewards/accuracy_reward": 0.5330636397004127,
+      "rewards/format_reward": 0.0,
+      "step": 30
+    },
+    {
+      "completion_length": 709.7984985351562,
+      "epoch": 0.2826855123674912,
+      "grad_norm": 0.007778931793156943,
+      "kl": 0.06893463134765625,
+      "learning_rate": 1.811938005715857e-05,
+      "loss": 0.0028,
+      "reward": 0.5337611852213741,
+      "reward_std": 0.233057678071782,
+      "rewards/accuracy_reward": 0.5337611852213741,
+      "rewards/format_reward": 0.0,
+      "step": 40
+    },
+    {
+      "completion_length": 694.2912990570069,
+      "epoch": 0.35335689045936397,
+      "grad_norm": 0.005119559728567491,
+      "kl": 0.180267333984375,
+      "learning_rate": 1.6427876096865394e-05,
+      "loss": 0.0072,
+      "reward": 0.5083984619006514,
+      "reward_std": 0.2548479220829904,
+      "rewards/accuracy_reward": 0.5083984619006514,
+      "rewards/format_reward": 0.0,
+      "step": 50
+    },
+    {
+      "completion_length": 665.2431941986084,
+      "epoch": 0.42402826855123676,
+      "grad_norm": 0.008723708066027886,
+      "kl": 0.339019775390625,
+      "learning_rate": 1.4338837391175582e-05,
+      "loss": 0.0136,
+      "reward": 0.49467078112065793,
+      "reward_std": 0.25909726731479166,
+      "rewards/accuracy_reward": 0.49467078112065793,
+      "rewards/format_reward": 0.0,
+      "step": 60
+    },
+    {
+      "completion_length": 701.4673881530762,
+      "epoch": 0.49469964664310956,
+      "grad_norm": 0.0075081355308690345,
+      "kl": 0.332379150390625,
+      "learning_rate": 1.1981461431993978e-05,
+      "loss": 0.0133,
+      "reward": 0.44556363597512244,
+      "reward_std": 0.24962579645216465,
+      "rewards/accuracy_reward": 0.44556363597512244,
+      "rewards/format_reward": 0.0,
+      "step": 70
+    },
+    {
+      "completion_length": 710.1393180847168,
+      "epoch": 0.5653710247349824,
+      "grad_norm": 0.0033178540730168207,
+      "kl": 0.35029296875,
+      "learning_rate": 9.501541143393028e-06,
+      "loss": 0.014,
+      "reward": 0.4244698856025934,
+      "reward_std": 0.24767237259075045,
+      "rewards/accuracy_reward": 0.4244698856025934,
+      "rewards/format_reward": 0.0,
+      "step": 80
+    },
+    {
+      "completion_length": 699.833821105957,
+      "epoch": 0.6360424028268551,
+      "grad_norm": 0.003957101265408949,
+      "kl": 0.36490478515625,
+      "learning_rate": 7.052448255890958e-06,
+      "loss": 0.0146,
+      "reward": 0.4340122971683741,
+      "reward_std": 0.24540567621588708,
+      "rewards/accuracy_reward": 0.4340122971683741,
+      "rewards/format_reward": 0.0,
+      "step": 90
+    },
+    {
+      "completion_length": 682.0039073944092,
+      "epoch": 0.7067137809187279,
+      "grad_norm": 0.004813844603096353,
+      "kl": 0.3904541015625,
+      "learning_rate": 4.78564796620502e-06,
+      "loss": 0.0156,
+      "reward": 0.4361049311235547,
+      "reward_std": 0.2509981536306441,
+      "rewards/accuracy_reward": 0.4361049311235547,
+      "rewards/format_reward": 0.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.7067137809187279,
+      "eval_completion_length": 691.6812744140625,
+      "eval_kl": 0.45751953125,
+      "eval_loss": 0.01872875541448593,
+      "eval_reward": 0.431919664144516,
+      "eval_reward_std": 0.2369636967778206,
+      "eval_rewards/accuracy_reward": 0.431919664144516,
+      "eval_rewards/format_reward": 0.0,
+      "eval_runtime": 59.8849,
+      "eval_samples_per_second": 1.653,
+      "eval_steps_per_second": 0.017,
+      "step": 100
+    },
+    {
+      "completion_length": 663.3428577423095,
+      "epoch": 0.7773851590106007,
+      "grad_norm": 0.006247088903073629,
+      "kl": 0.381396484375,
+      "learning_rate": 2.8413315074028157e-06,
+      "loss": 0.0152,
+      "reward": 0.45943082477897407,
+      "reward_std": 0.24997999798506498,
+      "rewards/accuracy_reward": 0.45943082477897407,
+      "rewards/format_reward": 0.0,
+      "step": 110
+    },
+    {
+      "completion_length": 595.9743253707886,
+      "epoch": 0.8480565371024735,
+      "grad_norm": 0.020585142096098717,
+      "kl": 0.5493408203125,
+      "learning_rate": 1.339745962155613e-06,
+      "loss": 0.022,
+      "reward": 0.4173270294442773,
+      "reward_std": 0.2547059410251677,
+      "rewards/accuracy_reward": 0.4173270294442773,
+      "rewards/format_reward": 0.0,
+      "step": 120
+    },
+    {
+      "completion_length": 495.40225582122804,
+      "epoch": 0.9187279151943463,
+      "grad_norm": 0.06438517297446601,
+      "kl": 0.87666015625,
+      "learning_rate": 3.7375753049987974e-07,
+      "loss": 0.0351,
+      "reward": 0.34868863206356765,
+      "reward_std": 0.2646566031500697,
+      "rewards/accuracy_reward": 0.34868863206356765,
+      "rewards/format_reward": 0.0,
+      "step": 130
+    },
+    {
+      "completion_length": 463.35523929595945,
+      "epoch": 0.9893992932862191,
+      "grad_norm": 0.016874489295012295,
+      "kl": 1.010009765625,
+      "learning_rate": 3.1081799918375454e-09,
+      "loss": 0.0404,
+      "reward": 0.3240513550117612,
+      "reward_std": 0.2695816809311509,
+      "rewards/accuracy_reward": 0.3240513550117612,
+      "rewards/format_reward": 0.0,
+      "step": 140
+    },
+    {
+      "completion_length": 454.1158103942871,
+      "epoch": 0.9964664310954063,
+      "kl": 1.02001953125,
+      "reward": 0.3373326016589999,
+      "reward_std": 0.27406518068164587,
+      "rewards/accuracy_reward": 0.3373326016589999,
+      "rewards/format_reward": 0.0,
+      "step": 141,
+      "total_flos": 0.0,
+      "train_loss": 0.014327551128428614,
+      "train_runtime": 37261.3403,
+      "train_samples_per_second": 1.944,
+      "train_steps_per_second": 0.004
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 141,
+  "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": 32,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ad6ccbc783747f38b4f99fbf439a3579c209df18cc08e6e2a9a7e10f88d2908
+size 7416