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: 0.0023
+- Loss: 0.1263
 
 ## Model description
 
@@ -45,14 +45,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 4.0099        | 1.0   | 1    | 0.8184          |
-| 4.56          | 2.0   | 2    | 3.3040          |
-| 1.5113        | 3.0   | 3    | 1.2078          |
-| 0.7524        | 4.0   | 4    | 4.8746          |
-| 1.4234        | 5.0   | 5    | 1.1674          |
-| 1.1193        | 6.0   | 6    | 1.0348          |
-| 1.2568        | 7.0   | 7    | 6.5308          |
-| 0.6211        | 8.0   | 8    | 1.6560          |
+| 5.856         | 1.0   | 1    | 2.9724          |
+| 2.7669        | 2.0   | 2    | 1.4216          |
+| 1.8836        | 3.0   | 3    | 0.0375          |
+| 1.6632        | 4.0   | 4    | 1.7060          |
+| 0.6377        | 5.0   | 5    | 0.0568          |
+| 1.174         | 6.0   | 6    | 0.0019          |
+| 1.9664        | 7.0   | 7    | 1.0716          |
+| 1.3273        | 8.0   | 8    | 0.0034          |
 
 
 ### Framework versions