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: 0.0673
-- Precision: 0.9447
-- Recall: 0.9505
-- F1: 0.9476
-- Accuracy: 0.9868
+- Loss: 0.0621
+- Precision: 0.9396
+- Recall: 0.9456
+- F1: 0.9426
+- Accuracy: 0.9861
 
 ## Model description
 
@@ -55,9 +55,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.0287        | 1.0   | 1756 | 0.0691          | 0.9364    | 0.9389 | 0.9376 | 0.9849   |
-| 0.0225        | 2.0   | 3512 | 0.0689          | 0.9427    | 0.9448 | 0.9438 | 0.9857   |
-| 0.013         | 3.0   | 5268 | 0.0673          | 0.9447    | 0.9505 | 0.9476 | 0.9868   |
+| 0.0835        | 1.0   | 1756 | 0.0716          | 0.9167    | 0.9283 | 0.9225 | 0.9808   |
+| 0.0369        | 2.0   | 3512 | 0.0679          | 0.9394    | 0.9387 | 0.9391 | 0.9850   |
+| 0.0263        | 3.0   | 5268 | 0.0621          | 0.9396    | 0.9456 | 0.9426 | 0.9861   |
 
 
 ### Framework versions