Model save

README.md

@@ -1,11 +1,9 @@
 ---
 base_model: Qwen/Qwen2.5-3B-Instruct
-datasets: knoveleng/open-rs
 library_name: transformers
 model_name: OpenRS-GRPO
 tags:
 - generated_from_trainer
-- open-r1
 - trl
 - grpo
 licence: license
@@ -13,7 +11,7 @@ licence: license
 
 # Model Card for OpenRS-GRPO
 
-This model is a fine-tuned version of [Qwen/Qwen2.5-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-3B-Instruct) on the [knoveleng/open-rs](https://huggingface.co/datasets/knoveleng/open-rs) dataset.
+This model is a fine-tuned version of [Qwen/Qwen2.5-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-3B-Instruct).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start
@@ -29,7 +27,7 @@ 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/sonicdog00-korea-university/openrs/runs/a58uqy2c) 
+[<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/sonicdog00-korea-university/openrs/runs/ij7w3i5o) 
 
 
 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).

all_results.json

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 0.0171143918884336,
-    "train_runtime": 25348.2037,
+    "train_loss": 0.01467308583567501,
+    "train_runtime": 25494.6867,
     "train_samples": 7000,
-    "train_samples_per_second": 1.42,
+    "train_samples_per_second": 1.412,
     "train_steps_per_second": 0.02
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 0.0171143918884336,
-    "train_runtime": 25348.2037,
+    "train_loss": 0.01467308583567501,
+    "train_runtime": 25494.6867,
     "train_samples": 7000,
-    "train_samples_per_second": 1.42,
+    "train_samples_per_second": 1.412,
     "train_steps_per_second": 0.02
 }