update model card README.md

README.md

@@ -14,8 +14,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5998
-- Rmse: 0.6425
+- Loss: 0.6126
+- Rmse: 0.6362
 
 ## Model description
 
@@ -49,7 +49,7 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Rmse   |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| 0.6437        | 4.0   | 500  | 0.5998          | 0.6425 |
+| 0.6393        | 4.0   | 500  | 0.6126          | 0.6362 |
 
 
 ### Framework versions