Update README.md

README.md

@@ -59,6 +59,18 @@ Post-training quantization was applied using PyTorch's built-in quantization fra
 
 A well-trained language model should have a perplexity closer to 10–50, depending on the dataset and domain and our model's perplexity score is 32.4.
 
+## 🔧 Fine-Tuning Details
+
+### Dataset
+The **Bookcorpus** dataset was used for training and evaluation. The dataset consists of **texts**.
+
+### Training Configuration
+- **Number of epochs**: 3
+- **Batch size**: 8  
+- **Learning rate**: 5e-5  
+- **Evaluation strategy**: steps
+
+
 ## 📂 Repository Structure
 
 ```