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 [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3278
-- Precision: 0.6571
-- Recall: 0.7048
-- F1: 0.6801
-- Accuracy: 0.9146
+- Loss: 0.3872
+- Precision: 0.6667
+- Recall: 0.7066
+- F1: 0.6861
+- Accuracy: 0.9163
 
 ## Model description
 
@@ -54,11 +54,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.4057        | 1.81  | 500  | 0.2584          | 0.6036    | 0.6608 | 0.6309 | 0.9103   |
-| 0.1855        | 3.62  | 1000 | 0.2765          | 0.618     | 0.6806 | 0.6478 | 0.9160   |
-| 0.1137        | 5.43  | 1500 | 0.3278          | 0.6571    | 0.7048 | 0.6801 | 0.9146   |
-| 0.0703        | 7.25  | 2000 | 0.3700          | 0.6356    | 0.7070 | 0.6694 | 0.9139   |
-| 0.0476        | 9.06  | 2500 | 0.3865          | 0.6471    | 0.7026 | 0.6737 | 0.9167   |
+| 0.4118        | 1.75  | 500  | 0.2787          | 0.6316    | 0.6694 | 0.6499 | 0.9120   |
+| 0.189         | 3.5   | 1000 | 0.2962          | 0.6798    | 0.7107 | 0.6949 | 0.9177   |
+| 0.1168        | 5.24  | 1500 | 0.3403          | 0.6503    | 0.7107 | 0.6792 | 0.9130   |
+| 0.0734        | 6.99  | 2000 | 0.3491          | 0.6673    | 0.7169 | 0.6912 | 0.9169   |
+| 0.0469        | 8.74  | 2500 | 0.3872          | 0.6667    | 0.7066 | 0.6861 | 0.9163   |
 
 
 ### Framework versions