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: 1.7634
+- Loss: 1.7511
 
 ## Model description
 
@@ -45,14 +45,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 5.8184        | 1.0   | 1    | 2.0723          |
-| 2.1708        | 2.0   | 2    | 0.0000          |
-| 1.6403        | 3.0   | 3    | 0.3167          |
-| 1.6512        | 4.0   | 4    | 1.9003          |
-| 1.2028        | 5.0   | 5    | 1.3098          |
-| 1.8082        | 6.0   | 6    | 0.1321          |
-| 1.8193        | 7.0   | 7    | 0.0014          |
-| 0.8956        | 8.0   | 8    | 4.0855          |
+| 6.7149        | 1.0   | 1    | 0.0433          |
+| 1.7639        | 2.0   | 2    | 3.6486          |
+| 1.2813        | 3.0   | 3    | 1.5894          |
+| 1.8562        | 4.0   | 4    | 1.0965          |
+| 1.1457        | 5.0   | 5    | 1.0543          |
+| 0.6527        | 6.0   | 6    | 1.1125          |
+| 0.5567        | 7.0   | 7    | nan             |
+| 2.6637        | 8.0   | 8    | 0.0519          |
 
 
 ### Framework versions