Update README.md

README.md

@@ -219,16 +219,21 @@ Test Samples:
 
 ## Training History
 
-Training curves are available in:
+The model was trained in two stages:
 
-training/
+1. Classifier training with the EfficientNet-B0 backbone frozen.
+2. Fine-tuning of the final feature blocks.
+
+### Phase 1
+
+![Phase 1 Training Loss](training/phase1_loss.png)
 
-Contents:
+### Phase 2
 
-- train_loss.png
-- validation_loss.png
-- learning_curve.png
+![Phase 2 Fine-Tuning Loss](training/phase2_loss.png)
 
+The epoch-level training history is available in
+`training/training_history.json`.
 ---
 
 ## Explainability