update model card README.md

README.md

@@ -17,9 +17,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [xlm-roberta-large](https://huggingface.co/xlm-roberta-large) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0842
-- Accuracy: 0.9791
-- F1: 0.9791
+- Loss: 0.0610
+- Accuracy: 0.9777
+- F1: 0.9777
 
 ## Model description
 
@@ -52,15 +52,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
-| 1.252         | 0.5   | 39   | 0.6815          | 0.5288   | 0.3962 |
-| 0.727         | 1.0   | 78   | 0.1220          | 0.9647   | 0.9646 |
-| 0.2545        | 1.5   | 117  | 0.0908          | 0.9751   | 0.9751 |
-| 0.1242        | 2.0   | 156  | 0.0785          | 0.9791   | 0.9791 |
-| 0.1242        | 2.5   | 195  | 0.0773          | 0.9699   | 0.9699 |
-| 0.0866        | 3.0   | 234  | 0.0718          | 0.9817   | 0.9817 |
-| 0.0636        | 3.5   | 273  | 0.0827          | 0.9699   | 0.9699 |
-| 0.0467        | 4.0   | 312  | 0.0658          | 0.9777   | 0.9777 |
-| 0.0426        | 4.5   | 351  | 0.0842          | 0.9791   | 0.9791 |
+| 1.0581        | 0.5   | 39   | 0.6855          | 0.5079   | 0.3506 |
+| 0.7217        | 1.0   | 78   | 0.2164          | 0.9293   | 0.9292 |
+| 0.4239        | 1.5   | 117  | 0.1141          | 0.9686   | 0.9686 |
+| 0.1448        | 2.0   | 156  | 0.0929          | 0.9660   | 0.9660 |
+| 0.1448        | 2.5   | 195  | 0.0677          | 0.9777   | 0.9777 |
+| 0.103         | 3.0   | 234  | 0.0933          | 0.9751   | 0.9751 |
+| 0.0826        | 3.5   | 273  | 0.0723          | 0.9764   | 0.9764 |
+| 0.0598        | 4.0   | 312  | 0.0610          | 0.9777   | 0.9777 |
 
 
 ### Framework versions