Update README.md

README.md

@@ -71,4 +71,10 @@ print(response[0]["generated_text"].split("<s>Bot: ")[-1])
 ```
 
 ## Training & Data:
-The training was done on 1 NVIDIA DGX using DeepSpeed ZeRO 3 for three epochs on roughly 4GB of carefully selected translation data. It is a full finetune of all of the model parameters. 
+The training was done on 1 NVIDIA DGX using DeepSpeed ZeRO 3 for three epochs on roughly 4GB of carefully selected translation data. It is a full finetune of all of the model parameters. 
+
+| Epoch | Training Loss | Evaluation Loss |
+|-------|---------------|-----------------|
+| 1     | 1.309         | 1.281           |
+| 2     | 1.161         | 1.242           |
+| 3     | 1.053         | 1.219           |