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: 0.5402
+- Loss: 0.8265
 
 ## Model description
 
@@ -45,14 +45,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 4.4528        | 1.0   | 1    | 0.6911          |
-| 2.531         | 2.0   | 2    | 0.5715          |
-| 2.9755        | 3.0   | 3    | 1.0198          |
-| 2.5659        | 4.0   | 4    | 0.2358          |
-| 1.8365        | 5.0   | 5    | 0.0755          |
-| 0.9817        | 6.0   | 6    | 1.9245          |
-| 2.1606        | 7.0   | 7    | 0.7996          |
-| 1.3627        | 8.0   | 8    | 0.0545          |
+| 5.4909        | 1.0   | 1    | 2.0830          |
+| 2.5276        | 2.0   | 2    | 1.2075          |
+| 2.1681        | 3.0   | 3    | 3.7812          |
+| 2.423         | 4.0   | 4    | 0.0068          |
+| 1.2367        | 5.0   | 5    | 2.8448          |
+| 1.1856        | 6.0   | 6    | 0.6549          |
+| 0.6514        | 7.0   | 7    | 0.0322          |
+| 0.8557        | 8.0   | 8    | 0.6694          |
 
 
 ### Framework versions