Training complete

README.md

@@ -21,11 +21,11 @@ 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: 0.0467
-- Precision: 0.8120
-- Recall: 0.8640
-- F1: 0.8372
-- Accuracy: 0.9861
+- Loss: 0.0252
+- Precision: 0.7999
+- Recall: 0.8551
+- F1: 0.8266
+- Accuracy: 0.9922
 
 ## Model description
 
@@ -56,9 +56,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.0959        | 1.0   | 766  | 0.0454          | 0.7838    | 0.8669 | 0.8232 | 0.9849   |
-| 0.0337        | 2.0   | 1532 | 0.0419          | 0.8160    | 0.8550 | 0.8351 | 0.9862   |
-| 0.0247        | 3.0   | 2298 | 0.0467          | 0.8120    | 0.8640 | 0.8372 | 0.9861   |
+| 0.0178        | 1.0   | 773  | 0.0253          | 0.7972    | 0.8418 | 0.8189 | 0.9921   |
+| 0.0156        | 2.0   | 1546 | 0.0234          | 0.8027    | 0.8575 | 0.8292 | 0.9923   |
+| 0.0114        | 3.0   | 2319 | 0.0252          | 0.7999    | 0.8551 | 0.8266 | 0.9922   |
 
 
 ### Framework versions