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 [ltgoslo/norbert2](https://huggingface.co/ltgoslo/norbert2) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 3.6093
+- Loss: 3.2772
 
 ## Model description
 
@@ -45,9 +45,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 4.3959        | 1.0   | 106  | 3.5901          |
-| 3.8083        | 2.0   | 212  | 3.6968          |
-| 3.6499        | 3.0   | 318  | 3.5943          |
+| 3.8646        | 1.0   | 422  | 3.4388          |
+| 3.4359        | 2.0   | 844  | 3.3152          |
+| 3.3084        | 3.0   | 1266 | 3.3755          |
 
 
 ### Framework versions