Model save

README.md

@@ -1,6 +1,5 @@
 ---
 base_model: Qwen/Qwen2.5-Math-1.5B
-datasets: math
 library_name: transformers
 model_name: Qwen2.5-Math-1.5B-GRPO
 tags:
@@ -12,7 +11,7 @@ licence: license
 
 # Model Card for Qwen2.5-Math-1.5B-GRPO
 
-This model is a fine-tuned version of [Qwen/Qwen2.5-Math-1.5B](https://huggingface.co/Qwen/Qwen2.5-Math-1.5B) on the [math](https://huggingface.co/datasets/math) dataset.
+This model is a fine-tuned version of [Qwen/Qwen2.5-Math-1.5B](https://huggingface.co/Qwen/Qwen2.5-Math-1.5B).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start
@@ -28,7 +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/yifeizuo2029-northwestern-university/BRiTER/runs/dstyzbbl) 
+[<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/yifeizuo2029-northwestern-university/BRiTER/runs/8ofeqojr) 
 
 
 This model was trained with SFT.

all_results.json

@@ -1,7 +1,7 @@
 {
-    "total_flos": 1.3768541467574272e+16,
-    "train_loss": 0.5140652489444988,
-    "train_runtime": 284.5417,
-    "train_samples_per_second": 13.882,
-    "train_steps_per_second": 1.736
+    "total_flos": 3.216438415536947e+16,
+    "train_loss": 0.6463175455729167,
+    "train_runtime": 630.4846,
+    "train_samples_per_second": 15.663,
+    "train_steps_per_second": 0.119
 }

train_results.json

@@ -1,7 +1,7 @@
 {
-    "total_flos": 1.3768541467574272e+16,
-    "train_loss": 0.5140652489444988,
-    "train_runtime": 284.5417,
-    "train_samples_per_second": 13.882,
-    "train_steps_per_second": 1.736
+    "total_flos": 3.216438415536947e+16,
+    "train_loss": 0.6463175455729167,
+    "train_runtime": 630.4846,
+    "train_samples_per_second": 15.663,
+    "train_steps_per_second": 0.119
 }