Update README.md

README.md

@@ -155,10 +155,10 @@ and tokenized with a maximum length of 512 for inputs and 256 for responses usin
 - **LR Scheduler:** Cosine scheduler with a warmup ratio of 10%  
 - **Quantization:** 4-bit NF4 (with double quantization) using `torch.bfloat16`  
 - **LoRA Parameters:**  
-- **Rank (r):** 32  
-- **Alpha:** 64  
-- **Dropout:** 0.1  
-- **Target Modules:** `["q", "v"]`  
+  **Rank (r):** 32  
+  **Alpha:** 64  
+  **Dropout:** 0.1  
+  **Target Modules:** `["q", "v"]`  
 - **Checkpointing:**  
   Model saved at the end of every epoch  
   Early stopping with a patience of 2 epochs based on evaluation loss