Update README.md

README.md

@@ -19,11 +19,18 @@ This model is a fine-tuned version of `meta-llama/Llama-3.2-1B`, adapted using D
 - **License:** MIT  
 - **Finetuned from model:** meta-llama/Llama-3.2-1B
 
-### Model Sources
+## Training Hyperparameters
+
+- **Training regime:** Mixed precision (fp16)
+- **Learning rate:** 2e-4
+- **Batch size:** 8
+- **Number of epochs:** 3
+- **Optimizer:** AdamW with 8-bit precision
+- **Max sequence length:** 512 tokens
+- **Warmup steps:** 100
+- **Weight decay:** 0.01
+
 
-- **Repository:** [Link to the Hugging Face model repo]  
-- **Paper [optional]:** [If applicable, link to related research or documentation]  
-- **Demo [optional]:** [If a demo exists, provide a link]
 
 ## Uses