Training complete

README.md

@@ -17,9 +17,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model was trained from scratch on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0256
-- Bleu: 82.3881
-- Gen Len: 17.3021
+- Loss: 0.0164
+- Bleu: 98.0177
+- Gen Len: 18.9479
 
 ## Model description
 
@@ -50,8 +50,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Bleu    | Gen Len |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
-| No log        | 1.0   | 440  | 0.0373          | 83.1115 | 17.5208 |
-| 0.0384        | 2.0   | 880  | 0.0256          | 82.3881 | 17.3021 |
+| No log        | 1.0   | 440  | 0.0256          | 91.6073 | 18.7812 |
+| 0.0383        | 2.0   | 880  | 0.0164          | 98.0177 | 18.9479 |
 
 
 ### Framework versions