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/araelectra-base-discriminator](https://huggingface.co/aubmindlab/araelectra-base-discriminator) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5165
-- Macro F1: 0.8697
-- Accuracy: 0.8744
-- Precision: 0.8714
-- Recall: 0.8682
+- Loss: 0.1317
+- Macro F1: 0.9489
+- Accuracy: 0.9505
+- Precision: 0.9488
+- Recall: 0.9490
 
 ## Model description
 
@@ -54,10 +54,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Macro F1 | Accuracy | Precision | Recall |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:---------:|:------:|
-| 0.3422        | 1.0   | 798  | 0.3336          | 0.8589   | 0.8615   | 0.8563    | 0.8652 |
-| 0.216         | 2.0   | 1597 | 0.3460          | 0.8658   | 0.8714   | 0.8705    | 0.8624 |
-| 0.1504        | 3.0   | 2395 | 0.5448          | 0.8485   | 0.8568   | 0.8609    | 0.8420 |
-| 0.0914        | 4.0   | 3192 | 0.5165          | 0.8697   | 0.8744   | 0.8714    | 0.8682 |
+| 0.3788        | 1.0   | 798  | 0.1687          | 0.9453   | 0.9473   | 0.9480    | 0.9431 |
+| 0.2273        | 2.0   | 1597 | 0.1876          | 0.9200   | 0.9239   | 0.9306    | 0.9134 |
+| 0.1611        | 3.0   | 2395 | 0.1317          | 0.9489   | 0.9505   | 0.9488    | 0.9490 |
+| 0.0972        | 4.0   | 3192 | 0.1685          | 0.9484   | 0.9501   | 0.9489    | 0.9479 |
 
 
 ### Framework versions