update model card README.md

README.md

@@ -19,11 +19,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [gaunernst/bert-small-uncased](https://huggingface.co/gaunernst/bert-small-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0566
-- Precision: 0.9814
-- Recall: 0.9869
-- F1: 0.9842
-- Accuracy: 0.9872
+- Loss: 0.0186
+- Precision: 0.9941
+- Recall: 0.9952
+- F1: 0.9946
+- Accuracy: 0.9963
 
 ## Model description
 
@@ -54,9 +54,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| No log        | 1.0   | 250  | 0.0687          | 0.9768    | 0.9807 | 0.9788 | 0.9832   |
-| 0.2661        | 2.0   | 500  | 0.0572          | 0.9826    | 0.9861 | 0.9843 | 0.9873   |
-| 0.2661        | 3.0   | 750  | 0.0566          | 0.9814    | 0.9869 | 0.9842 | 0.9872   |
+| 0.0277        | 1.0   | 2500 | 0.0190          | 0.9929    | 0.9939 | 0.9934 | 0.9956   |
+| 0.0137        | 2.0   | 5000 | 0.0180          | 0.9935    | 0.9951 | 0.9943 | 0.9960   |
+| 0.0095        | 3.0   | 7500 | 0.0186          | 0.9941    | 0.9952 | 0.9946 | 0.9963   |
 
 
 ### Framework versions