update model card README.md

flan-t5-base-en-pt/README.md

@@ -17,9 +17,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.2318
-- Bleu: 13.1208
-- Gen Len: 16.9234
+- Loss: 1.2060
+- Bleu: 14.0032
+- Gen Len: 16.7274
 
 ## 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   | 293  | 1.2708          | 11.9107 | 16.9042 |
-| 1.7903        | 2.0   | 586  | 1.2318          | 13.1208 | 16.9234 |
+| 1.8709        | 1.0   | 587  | 1.2549          | 11.8816 | 16.8925 |
+| 1.487         | 2.0   | 1174 | 1.2060          | 14.0032 | 16.7274 |
 
 
 ### Framework versions