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/MARBERT](https://huggingface.co/UBC-NLP/MARBERT) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5506
-- Macro F1: 0.7395
-- Accuracy: 0.7517
-- Precision: 0.7448
-- Recall: 0.7365
+- Loss: 0.3192
+- Macro F1: 0.8548
+- Accuracy: 0.8604
+- Precision: 0.8576
+- Recall: 0.8526
 
 ## Model description
 
@@ -54,9 +54,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Macro F1 | Accuracy | Precision | Recall |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:---------:|:------:|
-| 0.5315        | 1.0   | 1597 | 0.5147          | 0.7276   | 0.7324   | 0.7264    | 0.7320 |
-| 0.3905        | 2.0   | 3194 | 0.5506          | 0.7395   | 0.7517   | 0.7448    | 0.7365 |
-| 0.2456        | 3.0   | 4791 | 0.8136          | 0.7317   | 0.7443   | 0.7369    | 0.7289 |
+| 0.4936        | 1.0   | 1597 | 0.3589          | 0.8364   | 0.8431   | 0.8401    | 0.8337 |
+| 0.3431        | 2.0   | 3194 | 0.3192          | 0.8548   | 0.8604   | 0.8576    | 0.8526 |
+| 0.233         | 3.0   | 4791 | 0.3914          | 0.8502   | 0.8547   | 0.8495    | 0.8509 |
 
 
 ### Framework versions