Update README.md

README.md

@@ -37,10 +37,9 @@ tags:
 - **Batch Size**: 128  
 - **Hardware**: Single GPU (NVIDIA GeForce RTX 3090)
 
-### Impair and Repair Specifics
+### SALUN Specifics
 - **Gradient Clipping**: 1.0  
-- **Impair Learning Rate**: 2e-4  
-- **Tarun-Samples-Per-Class**: 1000  
+- **Threshold**: 0.1    
 
 ### Algorithm
 The **SALUN (Saliency Unlearning)** algorithm was used for inexact unlearning. This method involves impairing the influence of a specific class and fine-tuning the model to regain its accuracy for the remaining classes.