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: 0.1142
-- Precision: 0.8979
-- Recall: 0.9222
-- F1: 0.9099
-- Accuracy: 0.9774
+- Loss: 0.0827
+- Precision: 0.9363
+- Recall: 0.9541
+- F1: 0.9451
+- Accuracy: 0.9843
 
 ## Model description
 
@@ -55,9 +55,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step  | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.0369        | 1.0   | 32820 | 0.0649          | 0.8974    | 0.9037 | 0.9005 | 0.9772   |
-| 0.015         | 2.0   | 65640 | 0.0902          | 0.9130    | 0.9055 | 0.9092 | 0.9777   |
-| 0.0057        | 3.0   | 98460 | 0.1142          | 0.8979    | 0.9222 | 0.9099 | 0.9774   |
+| 0.0371        | 1.0   | 32820 | 0.0475          | 0.9322    | 0.9416 | 0.9369 | 0.9836   |
+| 0.016         | 2.0   | 65640 | 0.0666          | 0.9414    | 0.9458 | 0.9436 | 0.9841   |
+| 0.0051        | 3.0   | 98460 | 0.0827          | 0.9363    | 0.9541 | 0.9451 | 0.9843   |
 
 
 ### Framework versions