Model save

README.md

@@ -26,7 +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/kcyxuh8j) 
+[<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/krwn86nu) 
 
 
 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).
@@ -34,9 +34,9 @@ This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing
 ### Framework versions
 
 - TRL: 0.16.0.dev0
-- Transformers: 4.49.0.dev0
+- Transformers: 4.49.0
 - Pytorch: 2.5.1
-- Datasets: 3.3.0
+- Datasets: 3.3.2
 - Tokenizers: 0.21.0
 
 ## Citations

all_results.json

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 0.27599951057092365,
-    "train_runtime": 58865.7657,
-    "train_samples": 72441,
-    "train_samples_per_second": 1.231,
-    "train_steps_per_second": 0.01
+    "train_loss": 0.05178338478773718,
+    "train_runtime": 159624.3158,
+    "train_samples": 93733,
+    "train_samples_per_second": 0.587,
+    "train_steps_per_second": 0.021
 }

generation_config.json

@@ -10,5 +10,5 @@
   "temperature": 0.7,
   "top_k": 20,
   "top_p": 0.8,
-  "transformers_version": "4.49.0.dev0"
+  "transformers_version": "4.49.0"
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 0.27599951057092365,
-    "train_runtime": 58865.7657,
-    "train_samples": 72441,
-    "train_samples_per_second": 1.231,
-    "train_steps_per_second": 0.01
+    "train_loss": 0.05178338478773718,
+    "train_runtime": 159624.3158,
+    "train_samples": 93733,
+    "train_samples_per_second": 0.587,
+    "train_steps_per_second": 0.021
 }