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 [jojoUla/bert-large-cased-sigir-support-refute-no-label-40](https://huggingface.co/jojoUla/bert-large-cased-sigir-support-refute-no-label-40) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6554
+- Loss: 0.2556
 
 ## Model description
 
@@ -45,14 +45,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 5.424         | 1.0   | 1    | 5.3297          |
-| 3.3621        | 2.0   | 2    | 3.1007          |
-| 3.1843        | 3.0   | 3    | 0.4243          |
-| 2.555         | 4.0   | 4    | 2.3959          |
-| 1.7995        | 5.0   | 5    | 12.0424         |
-| 2.4944        | 6.0   | 6    | 1.1042          |
-| 1.683         | 7.0   | 7    | 2.1571          |
-| 1.5222        | 8.0   | 8    | 1.9592          |
+| 5.2686        | 1.0   | 1    | 1.5761          |
+| 4.586         | 2.0   | 2    | 2.6971          |
+| 3.0052        | 3.0   | 3    | 2.8083          |
+| 2.5195        | 4.0   | 4    | 2.7170          |
+| 1.9023        | 5.0   | 5    | 4.1353          |
+| 1.4805        | 6.0   | 6    | 1.5381          |
+| 1.9009        | 7.0   | 7    | 0.2836          |
+| 1.5726        | 8.0   | 8    | 0.3140          |
 
 
 ### Framework versions