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: 0.0592
-- Precision: 0.9333
-- Recall: 0.9510
-- F1: 0.9421
-- Accuracy: 0.9862
+- Loss: 0.0614
+- Precision: 0.9377
+- Recall: 0.9505
+- F1: 0.9441
+- 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 |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.0759        | 1.0   | 1756 | 0.0605          | 0.9128    | 0.9374 | 0.9249 | 0.9830   |
-| 0.0359        | 2.0   | 3512 | 0.0644          | 0.9325    | 0.9468 | 0.9396 | 0.9854   |
-| 0.0226        | 3.0   | 5268 | 0.0592          | 0.9333    | 0.9510 | 0.9421 | 0.9862   |
+| 0.0758        | 1.0   | 1756 | 0.0640          | 0.9107    | 0.9355 | 0.9230 | 0.9820   |
+| 0.0361        | 2.0   | 3512 | 0.0643          | 0.9319    | 0.9446 | 0.9382 | 0.9854   |
+| 0.0198        | 3.0   | 5268 | 0.0614          | 0.9377    | 0.9505 | 0.9441 | 0.9866   |
 
 
 ### Framework versions