update model card README.md

README.md

@@ -13,11 +13,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 # translation-en-pt-t5-finetuned-Duolingo
 
-This model is a fine-tuned version of [unicamp-dl/translation-en-pt-t5](https://huggingface.co/unicamp-dl/translation-en-pt-t5) on an unknown dataset.
+This model was trained from scratch on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7436
-- Bleu: 39.7994
-- Gen Len: 8.978
+- Loss: 0.7362
+- Bleu: 39.4725
+- Gen Len: 9.002
 
 ## Model description
 
@@ -49,10 +49,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step  | Validation Loss | Bleu    | Gen Len |
 |:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|
-| 0.7259        | 0.24  | 9000  | 0.7897          | 39.2919 | 8.912   |
-| 0.6407        | 0.48  | 18000 | 0.7575          | 39.9964 | 8.898   |
-| 0.614         | 0.72  | 27000 | 0.7465          | 39.725  | 8.952   |
-| 0.6           | 0.96  | 36000 | 0.7436          | 39.7994 | 8.978   |
+| 0.5429        | 0.24  | 9000  | 0.7461          | 39.4744 | 9.0     |
+| 0.5302        | 0.48  | 18000 | 0.7431          | 39.7559 | 8.97    |
+| 0.5309        | 0.72  | 27000 | 0.7388          | 39.6751 | 8.998   |
+| 0.5336        | 0.96  | 36000 | 0.7362          | 39.4725 | 9.002   |
 
 
 ### Framework versions