update model card README.md

README.md

@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [neuralmind/bert-base-portuguese-cased](https://huggingface.co/neuralmind/bert-base-portuguese-cased) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.0377
+- Loss: 0.8132
 
 ## Model description
 
@@ -39,15 +39,27 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 3
+- num_epochs: 15
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| 1.3035        | 1.0   | 2079 | 1.1031          |
-| 1.1463        | 2.0   | 4158 | 1.0337          |
-| 1.0595        | 3.0   | 6237 | 1.0484          |
+| Training Loss | Epoch | Step  | Validation Loss |
+|:-------------:|:-----:|:-----:|:---------------:|
+| 1.3167        | 1.0   | 2079  | 1.1163          |
+| 1.1683        | 2.0   | 4158  | 1.0594          |
+| 1.0648        | 3.0   | 6237  | 1.0501          |
+| 1.0228        | 4.0   | 8316  | 0.9693          |
+| 0.9662        | 5.0   | 10395 | 0.9847          |
+| 0.9422        | 6.0   | 12474 | 0.9556          |
+| 0.8696        | 7.0   | 14553 | 0.8978          |
+| 0.7856        | 8.0   | 16632 | nan             |
+| 0.7849        | 9.0   | 18711 | 0.9192          |
+| 0.7559        | 10.0  | 20790 | 0.8536          |
+| 0.7564        | 11.0  | 22869 | 0.9230          |
+| 0.7641        | 12.0  | 24948 | 0.8852          |
+| 0.7007        | 13.0  | 27027 | 0.8616          |
+| 0.7139        | 14.0  | 29106 | 0.8419          |
+| 0.6543        | 15.0  | 31185 | 0.8460          |
 
 
 ### Framework versions