update model card README.md

README.md

@@ -14,7 +14,7 @@ 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: 2.4616
+- Loss: 4.6041
 
 ## Model description
 
@@ -46,9 +46,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 2.8578        | 1.0   | 16   | 2.6376          |
-| 2.645         | 2.0   | 32   | 2.5315          |
-| 2.5764        | 3.0   | 48   | 2.4952          |
+| 5.4216        | 1.0   | 10   | 4.7782          |
+| 4.8573        | 2.0   | 20   | 4.7080          |
+| 4.6729        | 3.0   | 30   | 4.5648          |
 
 
 ### Framework versions