Update README.md

README.md

@@ -14,4 +14,14 @@ Based on the "google/mt5-small" pre-trained model. Fine-tuned it on Hindi to Eng
 - batch size = 16
 - learning rate = 5e-4
 - number of batches = int(np.ceil(len(dataset) / batch size))
-- n_warmup_steps = int(number of epochs * number of batches * 0.01)
+- n_warmup_steps = int(number of epochs * number of batches * 0.01)
+
+### Training Loss
+
+![loss.png](./h2e_loss.png)
+
+### Examples
+
+![example_1.png](./h2e_example1.png)
+![example_2.png](./h2e_example2.png)
+![example_3.png](./h2e_example3.png)