End of training

README.md

@@ -21,10 +21,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1125
-- Precision: 0.9051
-- Recall: 0.9192
-- F1: 0.9121
+- Loss: 0.1154
+- Precision: 0.9026
+- Recall: 0.9210
+- F1: 0.9117
 - Accuracy: 0.9827
 
 ## Model description
@@ -57,9 +57,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.0473        | 1.0   | 878  | 0.0407          | 0.9256    | 0.9390 | 0.9323 | 0.9891   |
-| 0.0199        | 2.0   | 1756 | 0.0386          | 0.9433    | 0.9481 | 0.9457 | 0.9909   |
-| 0.0126        | 3.0   | 2634 | 0.0367          | 0.9444    | 0.9527 | 0.9485 | 0.9914   |
+| 0.0456        | 1.0   | 878  | 0.0421          | 0.9238    | 0.9340 | 0.9289 | 0.9886   |
+| 0.0206        | 2.0   | 1756 | 0.0388          | 0.9450    | 0.9490 | 0.9470 | 0.9907   |
+| 0.0131        | 3.0   | 2634 | 0.0371          | 0.9435    | 0.9517 | 0.9476 | 0.9913   |
 
 
 ### Framework versions