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: 0.0001
+- Loss: 0.0178
 
 ## Model description
 
@@ -45,14 +45,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 5.3574        | 1.0   | 1    | 2.0493          |
-| 1.1306        | 2.0   | 2    | 0.0032          |
-| 2.4487        | 3.0   | 3    | 0.3463          |
-| 1.3105        | 4.0   | 4    | 0.1352          |
-| 2.0474        | 5.0   | 5    | nan             |
-| 1.1318        | 6.0   | 6    | 0.0024          |
-| 0.74          | 7.0   | 7    | 0.0170          |
-| 2.1852        | 8.0   | 8    | 0.0031          |
+| 3.763         | 1.0   | 1    | 0.9977          |
+| 3.0541        | 2.0   | 2    | 1.9084          |
+| 2.3172        | 3.0   | 3    | 0.7321          |
+| 1.186         | 4.0   | 4    | 0.0251          |
+| 1.1306        | 5.0   | 5    | 7.8174          |
+| 1.176         | 6.0   | 6    | 1.2156          |
+| 1.1765        | 7.0   | 7    | 0.1448          |
+| 0.9389        | 8.0   | 8    | 1.0339          |
 
 
 ### Framework versions