update model card README.md

README.md

@@ -19,11 +19,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0256
-- Precision: 0.9288
-- Recall: 0.9485
-- F1: 0.9386
-- Accuracy: 0.9942
+- Loss: 0.0247
+- Precision: 0.9269
+- Recall: 0.9509
+- F1: 0.9387
+- Accuracy: 0.9945
 
 ## Model description
 
@@ -54,9 +54,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.0814        | 1.0   | 843  | 0.0278          | 0.8902    | 0.9286 | 0.9090 | 0.9919   |
-| 0.0156        | 2.0   | 1686 | 0.0225          | 0.9254    | 0.9436 | 0.9344 | 0.9937   |
-| 0.0074        | 3.0   | 2529 | 0.0256          | 0.9288    | 0.9485 | 0.9386 | 0.9942   |
+| 0.0744        | 1.0   | 843  | 0.0266          | 0.8945    | 0.9293 | 0.9116 | 0.9920   |
+| 0.016         | 2.0   | 1686 | 0.0239          | 0.9279    | 0.9446 | 0.9362 | 0.9942   |
+| 0.0075        | 3.0   | 2529 | 0.0247          | 0.9269    | 0.9509 | 0.9387 | 0.9945   |
 
 
 ### Framework versions