Model save

README.md

@@ -1,10 +1,8 @@
 ---
-datasets: open-r1/OpenR1-Math-220k
 library_name: transformers
 model_name: Qwen2.5-1.5B-Open-R1-GRPO
 tags:
 - generated_from_trainer
-- open-r1
 - trl
 - grpo
 licence: license
@@ -12,7 +10,7 @@ licence: license
 
 # Model Card for Qwen2.5-1.5B-Open-R1-GRPO
 
-This model is a fine-tuned version of [None](https://huggingface.co/None) on the [open-r1/OpenR1-Math-220k](https://huggingface.co/datasets/open-r1/OpenR1-Math-220k) dataset.
+This model is a fine-tuned version of [None](https://huggingface.co/None).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start
@@ -28,7 +26,7 @@ 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/kawamuramasaki/open-r1/runs/p1aly7g1) 
+[<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/kawamuramasaki/open-r1/runs/jxm7gcj0) 
 
 
 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": 0.04007197510112119,
-    "train_runtime": 111902.1384,
+    "train_loss": 0.08076191042202922,
+    "train_runtime": 127083.2818,
     "train_samples": 93733,
-    "train_samples_per_second": 0.838,
-    "train_steps_per_second": 0.03
+    "train_samples_per_second": 0.738,
+    "train_steps_per_second": 0.026
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 0.04007197510112119,
-    "train_runtime": 111902.1384,
+    "train_loss": 0.08076191042202922,
+    "train_runtime": 127083.2818,
     "train_samples": 93733,
-    "train_samples_per_second": 0.838,
-    "train_steps_per_second": 0.03
+    "train_samples_per_second": 0.738,
+    "train_steps_per_second": 0.026
 }