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: 0.0003
+- Loss: 0.0104
 
 ## Model description
 
@@ -45,14 +45,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 5.3857        | 1.0   | 1    | 3.0882          |
-| 4.1825        | 2.0   | 2    | 0.0805          |
-| 2.3611        | 3.0   | 3    | 0.1889          |
-| 2.257         | 4.0   | 4    | 0.7902          |
-| 1.22          | 5.0   | 5    | 0.3643          |
-| 0.8419        | 6.0   | 6    | 0.8103          |
-| 1.0713        | 7.0   | 7    | 0.5821          |
-| 1.4332        | 8.0   | 8    | 1.9611          |
+| 4.202         | 1.0   | 1    | 2.8692          |
+| 3.013         | 2.0   | 2    | 0.5282          |
+| 1.4989        | 3.0   | 3    | 2.8251          |
+| 0.9224        | 4.0   | 4    | 0.0666          |
+| 1.5338        | 5.0   | 5    | 0.0742          |
+| 0.758         | 6.0   | 6    | 0.0476          |
+| 1.3746        | 7.0   | 7    | 2.8224          |
+| 1.1452        | 8.0   | 8    | 0.0024          |
 
 
 ### Framework versions