Model save

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: 0.0456
-- Precision: 0.8864
-- Recall: 0.9534
-- F1: 0.9187
-- Accuracy: 0.9910
+- Loss: 0.0022
+- Precision: 0.9774
+- Recall: 0.9686
+- F1: 0.9730
+- Accuracy: 0.9992
 
 ## Model description
 
@@ -56,9 +56,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.0738        | 1.0   | 629  | 0.0417          | 0.9075    | 0.9545 | 0.9304 | 0.9907   |
-| 0.0313        | 2.0   | 1258 | 0.0461          | 0.8817    | 0.9565 | 0.9176 | 0.9897   |
-| 0.0146        | 3.0   | 1887 | 0.0456          | 0.8864    | 0.9534 | 0.9187 | 0.9910   |
+| 0.0073        | 1.0   | 751  | 0.0025          | 0.9649    | 0.9675 | 0.9662 | 0.9990   |
+| 0.0013        | 2.0   | 1502 | 0.0022          | 0.9812    | 0.9609 | 0.9709 | 0.9992   |
+| 0.001         | 3.0   | 2253 | 0.0022          | 0.9774    | 0.9686 | 0.9730 | 0.9992   |
 
 
 ### Framework versions