Training complete

README.md

@@ -20,11 +20,11 @@ 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 an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7183
-- Precision: 0.9519
-- Recall: 0.7709
-- F1: 0.8519
-- Accuracy: 0.9585
+- Loss: 0.4684
+- Precision: 0.9637
+- Recall: 0.8694
+- F1: 0.9141
+- Accuracy: 0.9707
 
 ## Model description
 
@@ -55,9 +55,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step  | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.0085        | 1.0   | 32820 | 0.6301          | 0.9513    | 0.7626 | 0.8466 | 0.9579   |
-| 0.0029        | 2.0   | 65640 | 0.7099          | 0.9487    | 0.7704 | 0.8503 | 0.9580   |
-| 0.0005        | 3.0   | 98460 | 0.7183          | 0.9519    | 0.7709 | 0.8519 | 0.9585   |
+| 0.0073        | 1.0   | 32820 | 0.4230          | 0.9568    | 0.8651 | 0.9086 | 0.9700   |
+| 0.0037        | 2.0   | 65640 | 0.4553          | 0.9618    | 0.8690 | 0.9130 | 0.9707   |
+| 0.0004        | 3.0   | 98460 | 0.4684          | 0.9637    | 0.8694 | 0.9141 | 0.9707   |
 
 
 ### Framework versions