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: 2.5534
+- Loss: 2.2370
 
 ## Model description
 
@@ -46,9 +46,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 2.9021        | 1.0   | 12   | 2.6918          |
-| 2.7152        | 2.0   | 24   | 2.5909          |
-| 2.6445        | 3.0   | 36   | 2.5104          |
+| 2.398         | 1.0   | 13   | 2.2849          |
+| 2.3637        | 2.0   | 26   | 2.2650          |
+| 2.3326        | 3.0   | 39   | 2.1898          |
 
 
 ### Framework versions