increase a lot performance with italian base bert!

README.md

@@ -19,9 +19,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [dbmdz/bert-base-italian-xxl-uncased](https://huggingface.co/dbmdz/bert-base-italian-xxl-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.2742
-- Accuracy: 0.7993
-- F1: 0.7894
+- Loss: 0.5546
+- Accuracy: 0.9877
+- F1: 0.9876
 
 ## Model description
 
@@ -52,8 +52,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
-| No log        | 1.0   | 16   | 1.4882          | 0.6241   | 0.5970 |
-| No log        | 2.0   | 32   | 1.2742          | 0.7993   | 0.7894 |
+| No log        | 1.0   | 29   | 0.9305          | 0.9571   | 0.9561 |
+| No log        | 2.0   | 58   | 0.5546          | 0.9877   | 0.9876 |
 
 
 ### Framework versions