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/liderek269/huggingface/runs/bhfd7may) 
+[<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/liderek269/huggingface/runs/nhvgepdj) 
 
 
 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).
@@ -37,7 +37,7 @@ This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing
 - TRL: 0.16.0
 - Transformers: 4.50.0
 - Pytorch: 2.5.1
-- Datasets: 3.3.2
+- Datasets: 3.5.0
 - Tokenizers: 0.21.1
 
 ## Citations

all_results.json

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 0.0013266473286907086,
-    "train_runtime": 29207.3586,
-    "train_samples": 6113,
-    "train_samples_per_second": 0.209,
-    "train_steps_per_second": 0.013
+    "train_loss": 0.008742584363342477,
+    "train_runtime": 54338.7365,
+    "train_samples": 7500,
+    "train_samples_per_second": 0.138,
+    "train_steps_per_second": 0.009
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 0.0013266473286907086,
-    "train_runtime": 29207.3586,
-    "train_samples": 6113,
-    "train_samples_per_second": 0.209,
-    "train_steps_per_second": 0.013
+    "train_loss": 0.008742584363342477,
+    "train_runtime": 54338.7365,
+    "train_samples": 7500,
+    "train_samples_per_second": 0.138,
+    "train_steps_per_second": 0.009
 }