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: 2.6628
+- Loss: 0.2461
 
 ## Model description
 
@@ -45,14 +45,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 4.372         | 1.0   | 1    | 2.1727          |
-| 2.9936        | 2.0   | 2    | 3.2877          |
-| 3.3115        | 3.0   | 3    | 0.0187          |
-| 2.1034        | 4.0   | 4    | 0.1890          |
-| 1.7194        | 5.0   | 5    | 0.3163          |
-| 1.3922        | 6.0   | 6    | 3.4289          |
-| 1.8781        | 7.0   | 7    | 2.9822          |
-| 1.2223        | 8.0   | 8    | 0.8932          |
+| 4.4677        | 1.0   | 1    | 1.7034          |
+| 2.322         | 2.0   | 2    | 0.9972          |
+| 1.7215        | 3.0   | 3    | 2.8752          |
+| 2.0592        | 4.0   | 4    | 3.6726          |
+| 1.0544        | 5.0   | 5    | 0.2337          |
+| 0.6115        | 6.0   | 6    | 0.0557          |
+| 2.0499        | 7.0   | 7    | 0.6719          |
+| 1.425         | 8.0   | 8    | 3.5276          |
 
 
 ### Framework versions