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: 0.0587
-- Precision: 0.9328
-- Recall: 0.9492
-- F1: 0.9409
-- Accuracy: 0.9863
+- Loss: 0.0631
+- Precision: 0.9315
+- Recall: 0.9498
+- F1: 0.9406
+- Accuracy: 0.9862
 
 ## Model description
 
@@ -55,9 +55,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.0775        | 1.0   | 1756 | 0.0667          | 0.9031    | 0.9337 | 0.9182 | 0.9820   |
-| 0.0363        | 2.0   | 3512 | 0.0655          | 0.9360    | 0.9470 | 0.9414 | 0.9852   |
-| 0.0245        | 3.0   | 5268 | 0.0587          | 0.9328    | 0.9492 | 0.9409 | 0.9863   |
+| 0.0738        | 1.0   | 1756 | 0.0722          | 0.8916    | 0.9317 | 0.9112 | 0.9798   |
+| 0.0326        | 2.0   | 3512 | 0.0713          | 0.9336    | 0.9472 | 0.9404 | 0.9850   |
+| 0.0232        | 3.0   | 5268 | 0.0631          | 0.9315    | 0.9498 | 0.9406 | 0.9862   |
 
 
 ### Framework versions