Model save

README.md

@@ -27,7 +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/need-ai/open-r1-basic/runs/7i8b38ab) 
+[<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/need-ai/open-r1-basic/runs/pgz4a1a7) 
 
 
 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": 0.7732266664505005,
-    "train_runtime": 7747.2937,
-    "train_samples": 8,
-    "train_samples_per_second": 0.207,
-    "train_steps_per_second": 0.052
+    "train_loss": 28.542118145277026,
+    "train_runtime": 53552.9796,
+    "train_samples": 20,
+    "train_samples_per_second": 0.149,
+    "train_steps_per_second": 0.037
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 0.7732266664505005,
-    "train_runtime": 7747.2937,
-    "train_samples": 8,
-    "train_samples_per_second": 0.207,
-    "train_steps_per_second": 0.052
+    "train_loss": 28.542118145277026,
+    "train_runtime": 53552.9796,
+    "train_samples": 20,
+    "train_samples_per_second": 0.149,
+    "train_steps_per_second": 0.037
 }