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 the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0441
-- Precision: 0.9987
-- Recall: 0.9926
-- F1: 0.9956
-- Accuracy: 0.9915
+- Loss: 0.5512
+- Precision: 0.8868
+- Recall: 0.9048
+- F1: 0.8957
+- Accuracy: 0.8321
 
 ## Model description
 
@@ -54,11 +54,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| No log        | 1.0   | 317  | 0.3098          | 0.9246    | 0.8867 | 0.9053 | 0.8574   |
-| 0.3357        | 2.0   | 634  | 0.3024          | 0.9402    | 0.8906 | 0.9147 | 0.8724   |
-| 0.3357        | 3.0   | 951  | 0.5501          | 0.8635    | 0.9512 | 0.9052 | 0.8468   |
-| 0.18          | 4.0   | 1268 | 0.5822          | 0.8872    | 0.9375 | 0.9117 | 0.8604   |
-| 0.0489        | 5.0   | 1585 | 0.6994          | 0.8932    | 0.9473 | 0.9194 | 0.8724   |
+| No log        | 1.0   | 130  | 0.4901          | 0.875     | 0.8422 | 0.8583 | 0.7744   |
+| No log        | 2.0   | 260  | 0.4580          | 0.8877    | 0.8663 | 0.8769 | 0.8026   |
+| No log        | 3.0   | 390  | 0.4147          | 0.8725    | 0.9519 | 0.9105 | 0.8482   |
+| 0.3926        | 4.0   | 520  | 0.4996          | 0.8776    | 0.9198 | 0.8982 | 0.8308   |
+| 0.3926        | 5.0   | 650  | 0.6170          | 0.8777    | 0.8824 | 0.88   | 0.8048   |
 
 
 ### Framework versions