update model card README.md

README.md

@@ -19,11 +19,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6047
-- Accuracy: 0.7713
-- Precision: 0.7719
-- Recall: 0.7713
-- F1: 0.7703
+- Loss: 0.5817
+- Accuracy: 0.7753
+- Precision: 0.7757
+- Recall: 0.7753
+- F1: 0.7745
 
 ## Model description
 
@@ -56,12 +56,15 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1     |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
-| 0.7978        | 1.0   | 1595 | 0.7782          | 0.6953   | 0.7191    | 0.6953 | 0.6926 |
-| 0.5526        | 2.0   | 3190 | 0.6951          | 0.7229   | 0.7398    | 0.7229 | 0.7233 |
-| 0.4904        | 3.0   | 4785 | 0.6390          | 0.7388   | 0.7530    | 0.7388 | 0.7366 |
-| 0.4307        | 4.0   | 6380 | 0.6047          | 0.7713   | 0.7719    | 0.7713 | 0.7703 |
+| Training Loss | Epoch | Step  | Validation Loss | Accuracy | Precision | Recall | F1     |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|:---------:|:------:|:------:|
+| 0.7758        | 1.0   | 1595  | 0.7691          | 0.7069   | 0.7256    | 0.7069 | 0.7052 |
+| 0.5496        | 2.0   | 3190  | 0.6961          | 0.7255   | 0.7441    | 0.7255 | 0.7252 |
+| 0.4856        | 3.0   | 4785  | 0.6451          | 0.7368   | 0.7562    | 0.7368 | 0.7328 |
+| 0.4257        | 4.0   | 6380  | 0.5817          | 0.7753   | 0.7757    | 0.7753 | 0.7745 |
+| 0.351         | 5.0   | 7975  | 0.6637          | 0.7633   | 0.7717    | 0.7633 | 0.7637 |
+| 0.2551        | 6.0   | 9570  | 0.7646          | 0.7696   | 0.7738    | 0.7696 | 0.7699 |
+| 0.1845        | 7.0   | 11165 | 0.8529          | 0.7674   | 0.7730    | 0.7674 | 0.7680 |
 
 
 ### Framework versions