Update README.md

README.md

@@ -42,6 +42,14 @@ This model is designed to:
 60
 ```
 
+## Benchmark Results
+
+We evaluated the model using a set of 1000 randomly generated math expressions to assess its performance. Here are the results:
+
+- **Accuracy**: 0.70% (This reflects how many of the model's answers matched the expected results.)
+- **Average Inference Time**: 0.1460 seconds per question (This measures the average time the model took to generate an answer for each question.)
+
+---
 
 ## Training Data
 
@@ -58,7 +66,7 @@ No duplicate expressions were used, ensuring the model learns unique patterns.
 
 ## Fine-Tuning
 
-This model was fine-tuned from the `distilgpt2` base model for 10 epochs. 
+This model was fine-tuned from the `distilgpt2` base model for 100 epochs.
 
 ---