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: 2.4919
+- Loss: 0.0321
 
 ## Model description
 
@@ -45,14 +45,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 4.5876        | 1.0   | 1    | 5.2566          |
-| 2.273         | 2.0   | 2    | 1.2774          |
-| 3.1481        | 3.0   | 3    | 0.1172          |
-| 1.0273        | 4.0   | 4    | 3.0407          |
-| 0.4384        | 5.0   | 5    | 0.1983          |
-| 0.6047        | 6.0   | 6    | 0.2636          |
-| 1.3883        | 7.0   | 7    | 0.9396          |
-| 1.0778        | 8.0   | 8    | 2.1954          |
+| 4.7535        | 1.0   | 1    | 1.5970          |
+| 3.3407        | 2.0   | 2    | 1.3329          |
+| 2.0305        | 3.0   | 3    | 0.8160          |
+| 1.9057        | 4.0   | 4    | 0.0579          |
+| 1.2441        | 5.0   | 5    | 0.0013          |
+| 1.8458        | 6.0   | 6    | 1.5072          |
+| 2.7407        | 7.0   | 7    | 7.4155          |
+| 0.4888        | 8.0   | 8    | 0.0002          |
 
 
 ### Framework versions