update model card README.md

README.md

@@ -17,11 +17,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [aubmindlab/bert-base-arabertv02-twitter](https://huggingface.co/aubmindlab/bert-base-arabertv02-twitter) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1520
-- F1: 0.8272
-- F1 Macro: 0.7762
-- Roc Auc: 0.8875
-- Accuracy: 0.7926
+- Loss: 0.1569
+- F1: 0.8398
+- F1 Macro: 0.7742
+- Roc Auc: 0.9021
+- Accuracy: 0.8073
 
 ## Model description
 
@@ -52,11 +52,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | F1     | F1 Macro | Roc Auc | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:--------:|:-------:|:--------:|
-| 0.1702        | 1.0   | 507  | 0.1520          | 0.8272 | 0.7762   | 0.8875  | 0.7926   |
-| 0.0938        | 2.0   | 1014 | 0.1566          | 0.8450 | 0.7742   | 0.9014  | 0.8198   |
-| 0.0562        | 3.0   | 1521 | 0.1799          | 0.8340 | 0.7650   | 0.8973  | 0.8045   |
-| 0.0318        | 4.0   | 2028 | 0.2022          | 0.8546 | 0.7775   | 0.9108  | 0.8275   |
-| 0.0183        | 5.0   | 2535 | 0.2451          | 0.8397 | 0.7660   | 0.9030  | 0.8122   |
+| 0.0988        | 1.0   | 507  | 0.1569          | 0.8398 | 0.7742   | 0.9021  | 0.8073   |
+| 0.056         | 2.0   | 1014 | 0.2023          | 0.8267 | 0.7610   | 0.8938  | 0.7912   |
+| 0.0358        | 3.0   | 1521 | 0.1959          | 0.8529 | 0.7889   | 0.9089  | 0.8275   |
+| 0.0204        | 4.0   | 2028 | 0.2132          | 0.8496 | 0.7971   | 0.9079  | 0.8226   |
+| 0.0157        | 5.0   | 2535 | 0.2288          | 0.8434 | 0.7789   | 0.9047  | 0.8163   |
 
 
 ### Framework versions