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 [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3149
-- Accuracy: 0.9007
-- F1: 0.8892
+- Loss: 0.5042
+- Accuracy: 0.8135
+- F1: 0.8127
 
 ## Model description
 
@@ -50,8 +50,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
-| 0.3541        | 1.0   | 479  | 0.3105          | 0.8995   | 0.8808 |
-| 0.232         | 2.0   | 958  | 0.3149          | 0.9007   | 0.8892 |
+| 0.7267        | 1.0   | 215  | 0.5443          | 0.7832   | 0.7833 |
+| 0.4548        | 2.0   | 430  | 0.5042          | 0.8135   | 0.8127 |
 
 
 ### Framework versions