Model save

README.md

@@ -0,0 +1,68 @@
+---
+base_model: Qwen/Qwen2.5-0.5B-Instruct
+library_name: transformers
+model_name: OpenRS-GRPO
+tags:
+- generated_from_trainer
+- trl
+- grpo
+licence: license
+---
+
+# Model Card for OpenRS-GRPO
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-0.5B-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="NTQuoc/OpenRS-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: 5.8.0.dev0
+- Pytorch: 2.5.1
+- Datasets: 4.8.3
+- Tokenizers: 0.22.2
+
+## 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": -1.862645149230957e-08,
+    "train_runtime": 166.9767,
+    "train_samples": 7000,
+    "train_samples_per_second": 0.144,
+    "train_steps_per_second": 0.006
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "total_flos": 0.0,
+    "train_loss": -1.862645149230957e-08,
+    "train_runtime": 166.9767,
+    "train_samples": 7000,
+    "train_samples_per_second": 0.144,
+    "train_steps_per_second": 0.006
+}

trainer_state.json

@@ -0,0 +1,56 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.0005714285714285715,
+  "eval_steps": 500,
+  "global_step": 1,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 512.0,
+      "epoch": 0.0005714285714285715,
+      "kl": 0.0,
+      "learning_rate": 0.0,
+      "loss": -1.862645149230957e-08,
+      "reward": -0.0564242850523442,
+      "reward_std": 0.12631838279776275,
+      "rewards/cosine_scaled_reward": -0.0282121425261721,
+      "rewards/format_reward": 0.0,
+      "step": 1
+    },
+    {
+      "epoch": 0.0005714285714285715,
+      "step": 1,
+      "total_flos": 0.0,
+      "train_loss": -1.862645149230957e-08,
+      "train_runtime": 166.9767,
+      "train_samples_per_second": 0.144,
+      "train_steps_per_second": 0.006
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 1,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 50,
+  "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": 3,
+  "trial_name": null,
+  "trial_params": null
+}

training_metrics.txt

@@ -0,0 +1,6 @@
+total_size_before (MB): 959.07
+total_size_after (MB): 950.68
+total_time (seconds): 171.42
+ram_peak (MB): 2923.48
+ram_consump (MB): 979.67
+disk_storage (MB): 323.85