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 [UBC-NLP/ARBERT](https://huggingface.co/UBC-NLP/ARBERT) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4956
-- Macro F1: 0.7629
-- Accuracy: 0.7752
-- Precision: 0.7737
-- Recall: 0.7584
+- Loss: 0.4693
+- Macro F1: 0.7725
+- Accuracy: 0.7821
+- Precision: 0.7781
+- Recall: 0.7693
 
 ## Model description
 
@@ -48,15 +48,15 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 32
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 7
+- num_epochs: 5
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Macro F1 | Accuracy | Precision | Recall |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:---------:|:------:|
-| 0.5033        | 1.0   | 1597 | 0.4831          | 0.7507   | 0.7543   | 0.7495    | 0.7554 |
-| 0.3858        | 2.0   | 3194 | 0.4956          | 0.7629   | 0.7752   | 0.7737    | 0.7584 |
-| 0.2675        | 3.0   | 4791 | 0.5964          | 0.7593   | 0.7712   | 0.7685    | 0.7552 |
+| 0.5049        | 1.0   | 1597 | 0.4705          | 0.7588   | 0.7680   | 0.7623    | 0.7566 |
+| 0.3867        | 2.0   | 3194 | 0.4693          | 0.7725   | 0.7821   | 0.7781    | 0.7693 |
+| 0.2613        | 3.0   | 4791 | 0.6281          | 0.7573   | 0.7671   | 0.7618    | 0.7547 |
 
 
 ### Framework versions