update model card README.md

README.md

@@ -15,8 +15,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model was trained from scratch on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7716
-- Bleu: 13.1062
+- Loss: 0.7470
+- Bleu: 13.6896
 - Gen Len: 17.8687
 
 ## Model description
@@ -44,17 +44,15 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 160
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 5
+- num_epochs: 3
 
 ### Training results
 
-| Training Loss | Epoch | Step  | Validation Loss | Bleu    | Gen Len |
-|:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|
-| 0.856         | 1.0   | 9641  | 0.8368          | 12.1924 | 17.8903 |
-| 0.8281        | 2.0   | 19282 | 0.8107          | 12.5703 | 17.8566 |
-| 0.8017        | 3.0   | 28923 | 0.7904          | 12.7893 | 17.8793 |
-| 0.7788        | 4.0   | 38564 | 0.7779          | 13.0086 | 17.8712 |
-| 0.7673        | 5.0   | 48205 | 0.7716          | 13.1062 | 17.8687 |
+| Training Loss | Epoch | Step  | Bleu    | Gen Len | Validation Loss |
+|:-------------:|:-----:|:-----:|:-------:|:-------:|:---------------:|
+| 0.722         | 1.0   | 9641  | 13.3667 | 17.8985 | 0.7757          |
+| 0.7098        | 2.0   | 19282 | 13.5842 | 17.8765 | 0.7571          |
+| 0.7028        | 3.0   | 28923 | 0.7470  | 13.6896 | 17.8687         |
 
 
 ### Framework versions