update model card README.md

README.md

@@ -17,9 +17,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [DaNLP/da-bert-hatespeech-detection](https://huggingface.co/DaNLP/da-bert-hatespeech-detection) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2219
-- Accuracy: 0.9625
-- F1: 0.2105
+- Loss: 0.1816
+- Accuracy: 0.9667
+- F1: 0.3548
 
 ## Model description
 
@@ -50,9 +50,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
-| No log        | 1.0   | 150  | 0.1116          | 0.9700   | 0.1818 |
-| No log        | 2.0   | 300  | 0.1649          | 0.9609   | 0.2295 |
-| No log        | 3.0   | 450  | 0.2219          | 0.9625   | 0.2105 |
+| No log        | 1.0   | 150  | 0.1128          | 0.9667   | 0.2    |
+| No log        | 2.0   | 300  | 0.1666          | 0.9684   | 0.2963 |
+| No log        | 3.0   | 450  | 0.1816          | 0.9667   | 0.3548 |
 
 
 ### Framework versions