update model card README.md

README.md

@@ -16,8 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.9261
-- Accuracy: 0.6047
+- Loss: 0.9630
+- Accuracy: 0.6057
 
 ## Model description
 
@@ -49,15 +49,15 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step  | Validation Loss | Accuracy |
 |:-------------:|:-----:|:-----:|:---------------:|:--------:|
-| 1.0487        | 0.33  | 5000  | 0.9778          | 0.5702   |
-| 0.9462        | 0.67  | 10000 | 0.9667          | 0.5825   |
-| 0.9574        | 1.0   | 15000 | 0.9546          | 0.5887   |
-| 0.8893        | 1.33  | 20000 | 0.9406          | 0.5888   |
-| 0.8936        | 1.67  | 25000 | 0.9222          | 0.5988   |
-| 0.8702        | 2.0   | 30000 | 0.9261          | 0.6047   |
-| 0.781         | 2.33  | 35000 | 0.9569          | 0.6007   |
-| 0.7598        | 2.67  | 40000 | 0.9737          | 0.5952   |
-| 0.7603        | 3.0   | 45000 | 0.9668          | 0.6023   |
+| 1.0561        | 0.33  | 5000  | 0.9954          | 0.567    |
+| 0.948         | 0.67  | 10000 | 0.9641          | 0.5862   |
+| 0.9557        | 1.0   | 15000 | 0.9605          | 0.589    |
+| 0.8891        | 1.33  | 20000 | 0.9420          | 0.5875   |
+| 0.8889        | 1.67  | 25000 | 0.9397          | 0.592    |
+| 0.8777        | 2.0   | 30000 | 0.9236          | 0.6042   |
+| 0.778         | 2.33  | 35000 | 0.9612          | 0.5972   |
+| 0.7589        | 2.67  | 40000 | 0.9728          | 0.5995   |
+| 0.7593        | 3.0   | 45000 | 0.9630          | 0.6057   |
 
 
 ### Framework versions