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: 0.0612
-- Precision: 0.9380
-- Recall: 0.9525
-- F1: 0.9452
-- Accuracy: 0.9870
+- Loss: 0.0616
+- Precision: 0.9350
+- Recall: 0.9510
+- F1: 0.9429
+- Accuracy: 0.9866
 
 ## Model description
 
@@ -55,9 +55,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.0734        | 1.0   | 1756 | 0.0637          | 0.9100    | 0.9357 | 0.9227 | 0.9829   |
-| 0.0348        | 2.0   | 3512 | 0.0605          | 0.9380    | 0.9497 | 0.9438 | 0.9866   |
-| 0.0205        | 3.0   | 5268 | 0.0612          | 0.9380    | 0.9525 | 0.9452 | 0.9870   |
+| 0.073         | 1.0   | 1756 | 0.0665          | 0.9079    | 0.9327 | 0.9201 | 0.9808   |
+| 0.0333        | 2.0   | 3512 | 0.0639          | 0.9359    | 0.9488 | 0.9423 | 0.9862   |
+| 0.0211        | 3.0   | 5268 | 0.0616          | 0.9350    | 0.9510 | 0.9429 | 0.9866   |
 
 
 ### Framework versions