Model save

README.md

@@ -0,0 +1,68 @@
+---
+base_model: Qwen/Qwen2.5-0.5B
+library_name: transformers
+model_name: Qwen2.5-0.5B-Open-R1-Code-GRPO
+tags:
+- generated_from_trainer
+- trl
+- grpo
+licence: license
+---
+
+# Model Card for Qwen2.5-0.5B-Open-R1-Code-GRPO
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-0.5B](https://huggingface.co/Qwen/Qwen2.5-0.5B).
+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="js2025/Qwen2.5-0.5B-Open-R1-Code-GRPO", 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: 0.16.0.dev0
+- Transformers: 4.49.0
+- Pytorch: 2.5.1
+- Datasets: 3.4.0
+- 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}}
+}
+```

all_results.json

@@ -0,0 +1,8 @@
+{
+    "total_flos": 0.0,
+    "train_loss": 0.009309468648439179,
+    "train_runtime": 366.3401,
+    "train_samples": 16,
+    "train_samples_per_second": 0.044,
+    "train_steps_per_second": 0.011
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.49.0"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "total_flos": 0.0,
+    "train_loss": 0.009309468648439179,
+    "train_runtime": 366.3401,
+    "train_samples": 16,
+    "train_samples_per_second": 0.044,
+    "train_steps_per_second": 0.011
+}

trainer_state.json

@@ -0,0 +1,102 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 4,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 912.75,
+      "epoch": 0.25,
+      "grad_norm": 1.1149588823318481,
+      "kl": 0.0,
+      "learning_rate": 1e-06,
+      "loss": 0.0475,
+      "reward": 0.125,
+      "reward_std": 0.1767766922712326,
+      "rewards/accuracy_reward": 0.125,
+      "rewards/format_reward": 0.0,
+      "rewards/tag_count_reward": 0.0,
+      "step": 1
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1019.5,
+      "epoch": 0.5,
+      "grad_norm": 0.8432132005691528,
+      "kl": 0.0,
+      "learning_rate": 7.75e-07,
+      "loss": -0.0102,
+      "reward": 0.125,
+      "reward_std": 0.1767766922712326,
+      "rewards/accuracy_reward": 0.125,
+      "rewards/format_reward": 0.0,
+      "rewards/tag_count_reward": 0.0,
+      "step": 2
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 578.25,
+      "epoch": 0.75,
+      "grad_norm": 0.027600621804594994,
+      "kl": 0.0020586252212524414,
+      "learning_rate": 3.250000000000001e-07,
+      "loss": 0.0,
+      "reward": 0.0,
+      "reward_std": 0.0,
+      "rewards/accuracy_reward": 0.0,
+      "rewards/format_reward": 0.0,
+      "rewards/tag_count_reward": 0.0,
+      "step": 3
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1318.5,
+      "epoch": 1.0,
+      "grad_norm": 0.005318487994372845,
+      "kl": 8.308887481689453e-05,
+      "learning_rate": 1e-07,
+      "loss": 0.0,
+      "reward": 0.0,
+      "reward_std": 0.0,
+      "rewards/accuracy_reward": 0.0,
+      "rewards/format_reward": 0.0,
+      "rewards/tag_count_reward": 0.0,
+      "step": 4
+    },
+    {
+      "epoch": 1.0,
+      "step": 4,
+      "total_flos": 0.0,
+      "train_loss": 0.009309468648439179,
+      "train_runtime": 366.3401,
+      "train_samples_per_second": 0.044,
+      "train_steps_per_second": 0.011
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 4,
+  "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": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}