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 [distilbert-base-multilingual-cased](https://huggingface.co/distilbert-base-multilingual-cased) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0673
-- Precision: 0.9190
-- Recall: 0.9173
-- F1: 0.9182
-- Accuracy: 0.9756
+- Loss: 0.0455
+- Precision: 0.9460
+- Recall: 0.9475
+- F1: 0.9467
+- Accuracy: 0.9873
 
 ## Model description
 
@@ -48,14 +48,17 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 2
+- num_epochs: 5
 
 ### Training results
 
 | Training Loss | Epoch | Step  | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.085         | 1.0   | 8122  | 0.0768          | 0.9077    | 0.9022 | 0.9049 | 0.9720   |
-| 0.0558        | 2.0   | 16244 | 0.0673          | 0.9190    | 0.9173 | 0.9182 | 0.9756   |
+| 0.0755        | 1.0   | 3025  | 0.0610          | 0.9243    | 0.9204 | 0.9223 | 0.9813   |
+| 0.0448        | 2.0   | 6050  | 0.0500          | 0.9362    | 0.9400 | 0.9381 | 0.9854   |
+| 0.0317        | 3.0   | 9075  | 0.0444          | 0.9436    | 0.9424 | 0.9430 | 0.9865   |
+| 0.0237        | 4.0   | 12100 | 0.0445          | 0.9498    | 0.9418 | 0.9457 | 0.9872   |
+| 0.0183        | 5.0   | 15125 | 0.0455          | 0.9460    | 0.9475 | 0.9467 | 0.9873   |
 
 
 ### Framework versions