Update README.md

README.md

@@ -3,8 +3,17 @@
 
 This model is a fine-tuned version of distilbert-base-cased on SQuAD dataset. It achieves the following results on the evaluation set:
 
-- Train Loss: 0.9725
-- Validation Loss: 1.1196
+- Train Loss: 0.9125
+- Validation Loss: 1.0106
 - Epoch: 2
-- Training Accuracy: 0.7309
-- Validation Accuracy: 0.7013
+- Training Accuracy: 0.7709
+- Validation Accuracy: 0.7613
+
+After using regularization and finetuning our model, here’s how it is performing:
+
+- Train Loss: 0.7615
+- Validation Loss: 0.6138
+- Epoch: 4
+- Training Accuracy: 0.8102
+- Validation Accuracy: 0.8210
+