update model card README.md

README.md

@@ -18,8 +18,8 @@ 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 the glue dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4536
-- Matthews Correlation: 0.6174
+- Loss: 0.4211
+- Matthews Correlation: 0.6279
 
 ## Model description
 
@@ -55,11 +55,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
 |:-------------:|:-----:|:----:|:---------------:|:--------------------:|
-| 0.4355        | 1.0   | 133  | 0.4116          | 0.5817               |
-| 0.2367        | 2.0   | 266  | 0.4111          | 0.6028               |
-| 0.1584        | 3.0   | 399  | 0.4536          | 0.6174               |
-| 0.2278        | 4.0   | 532  | 0.4890          | 0.6116               |
-| 0.2258        | 5.0   | 665  | 0.5586          | 0.5995               |
+| 0.4218        | 1.0   | 133  | 0.4236          | 0.5243               |
+| 0.2077        | 2.0   | 266  | 0.3970          | 0.5930               |
+| 0.184         | 3.0   | 399  | 0.4211          | 0.6279               |
+| 0.1807        | 4.0   | 532  | 0.4854          | 0.6197               |
+| 0.1405        | 5.0   | 665  | 0.5693          | 0.5968               |
 
 
 ### Framework versions