Update README.md

README.md

@@ -17,8 +17,8 @@ base_model:
 - **Base Model**: Qwen2.5-7B-Instructions  
 - **Fine-tuned with GRPO and LoRa (Low-Rank Adaptation)**   
 - **Context Window**: 4096 tokens  
-- **The first model was fine-tuned on an L4 GPU for 50 hours and achieved a score of 51/100 on the gsm8k-tr dataset.
-    After additional fine-tuning on an A1000 GPU for 10 more hours, its score improved to 57/100 on the same dataset.**
+- **The first model was fine-tuned on an L4 GPU for 50 hours and achieved a score of 51/100(answer) on the gsm8k-tr dataset.
+    After additional fine-tuning on an A1000 GPU for 10 more hours, its score improved to 57/100(answer) on the same dataset.**
 
 ## Usage