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](https://huggingface.co/aubmindlab/bert-base-arabertv02) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2667
-- Macro F1: 0.8831
-- Accuracy: 0.8867
-- Precision: 0.8826
-- Recall: 0.8837
+- Loss: 0.1603
+- Macro F1: 0.9387
+- Accuracy: 0.9410
+- Precision: 0.9415
+- Recall: 0.9363
 
 ## Model description
 
@@ -54,9 +54,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Macro F1 | Accuracy | Precision | Recall |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:---------:|:------:|
-| 0.296         | 1.0   | 798  | 0.2754          | 0.8729   | 0.8786   | 0.8795    | 0.8684 |
-| 0.2126        | 2.0   | 1596 | 0.2667          | 0.8831   | 0.8867   | 0.8826    | 0.8837 |
-| 0.1719        | 3.0   | 2394 | 0.3204          | 0.8780   | 0.8815   | 0.8768    | 0.8794 |
+| 0.3283        | 1.0   | 798  | 0.1603          | 0.9387   | 0.9410   | 0.9415    | 0.9363 |
+| 0.2274        | 2.0   | 1596 | 0.1826          | 0.9254   | 0.9271   | 0.9225    | 0.9298 |
 
 
 ### Framework versions