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: 2.2829
+- Loss: 0.0557
 
 ## Model description
 
@@ -45,14 +45,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 5.6524        | 1.0   | 1    | 0.9023          |
-| 1.7626        | 2.0   | 2    | 2.0067          |
-| 2.2705        | 3.0   | 3    | 0.6913          |
-| 1.3273        | 4.0   | 4    | 0.3372          |
-| 0.8194        | 5.0   | 5    | 0.0007          |
-| 2.2196        | 6.0   | 6    | 0.0028          |
-| 0.8229        | 7.0   | 7    | 0.0386          |
-| 1.0868        | 8.0   | 8    | 0.0035          |
+| 5.8023        | 1.0   | 1    | 1.0160          |
+| 3.4406        | 2.0   | 2    | 2.2347          |
+| 1.6101        | 3.0   | 3    | 5.3486          |
+| 0.9624        | 4.0   | 4    | 0.0428          |
+| 1.3386        | 5.0   | 5    | 1.7937          |
+| 1.0396        | 6.0   | 6    | 0.5378          |
+| 1.1581        | 7.0   | 7    | 2.4873          |
+| 1.4557        | 8.0   | 8    | 1.1439          |
 
 
 ### Framework versions