Model save

README.md

@@ -0,0 +1,68 @@
+---
+base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
+library_name: transformers
+model_name: DeepSeek-R1-Distill-Qwen-1.5B-GRPO_code_code
+tags:
+- generated_from_trainer
+- trl
+- grpo
+licence: license
+---
+
+# Model Card for DeepSeek-R1-Distill-Qwen-1.5B-GRPO_code_code
+
+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="Seongyun/DeepSeek-R1-Distill-Qwen-1.5B-GRPO_code_code", 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/minjuseo/huggingface/runs/9p4vhzdw) 
+
+
+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: 3.3.1
+- 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": 0.011042823908584458,
+    "train_runtime": 4637.2308,
+    "train_samples": 1001,
+    "train_samples_per_second": 0.216,
+    "train_steps_per_second": 0.008
+}

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"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "total_flos": 0.0,
+    "train_loss": 0.011042823908584458,
+    "train_runtime": 4637.2308,
+    "train_samples": 1001,
+    "train_samples_per_second": 0.216,
+    "train_steps_per_second": 0.008
+}

trainer_state.json

@@ -0,0 +1,100 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9790209790209791,
+  "eval_steps": 500,
+  "global_step": 35,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1954.0179138183594,
+      "epoch": 0.027972027972027972,
+      "grad_norm": 0.06958208978176117,
+      "kl": 0.0,
+      "learning_rate": 5e-06,
+      "loss": 0.0105,
+      "reward": 0.1316964365541935,
+      "reward_std": 0.09034644812345505,
+      "rewards/code_reward": 0.1316964365541935,
+      "step": 1
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1942.4365810818142,
+      "epoch": 0.27972027972027974,
+      "grad_norm": 0.09030569344758987,
+      "kl": 0.010952697859870063,
+      "learning_rate": 1.8386870970865488e-05,
+      "loss": 0.0078,
+      "reward": 0.14115640407221186,
+      "reward_std": 0.07494163533879651,
+      "rewards/code_reward": 0.14115640407221186,
+      "step": 10
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1886.2473937988282,
+      "epoch": 0.5594405594405595,
+      "grad_norm": 0.09897836297750473,
+      "kl": 0.0487396240234375,
+      "learning_rate": 1.0544157480451586e-05,
+      "loss": 0.0126,
+      "reward": 0.16140213604085146,
+      "reward_std": 0.07699124878272415,
+      "rewards/code_reward": 0.16140213604085146,
+      "step": 20
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1932.8143585205078,
+      "epoch": 0.8391608391608392,
+      "grad_norm": 0.08572351187467575,
+      "kl": 0.09188232421875,
+      "learning_rate": 3.1308804546987615e-06,
+      "loss": 0.0135,
+      "reward": 0.13120310104131933,
+      "reward_std": 0.07072200049005914,
+      "rewards/code_reward": 0.13120310104131933,
+      "step": 30
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1913.047674560547,
+      "epoch": 0.9790209790209791,
+      "kl": 0.1061767578125,
+      "reward": 0.1406746106222272,
+      "reward_std": 0.06878119893372059,
+      "rewards/code_reward": 0.1406746106222272,
+      "step": 35,
+      "total_flos": 0.0,
+      "train_loss": 0.011042823908584458,
+      "train_runtime": 4637.2308,
+      "train_samples_per_second": 0.216,
+      "train_steps_per_second": 0.008
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 35,
+  "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": 4,
+  "trial_name": null,
+  "trial_params": null
+}