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: 2.3101
+- Loss: 1.6429
 
 ## Model description
 
@@ -45,14 +45,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 5.2296        | 1.0   | 1    | 9.0748          |
-| 3.7879        | 2.0   | 2    | 0.5271          |
-| 1.3906        | 3.0   | 3    | 5.6264          |
-| 1.6614        | 4.0   | 4    | 0.0000          |
-| 2.2196        | 5.0   | 5    | 0.7507          |
-| 1.3947        | 6.0   | 6    | 0.1923          |
-| 1.8374        | 7.0   | 7    | nan             |
-| 2.0788        | 8.0   | 8    | 3.4238          |
+| 5.0753        | 1.0   | 1    | 3.6309          |
+| 3.8577        | 2.0   | 2    | 0.1828          |
+| 2.1979        | 3.0   | 3    | 7.6078          |
+| 1.9962        | 4.0   | 4    | 2.4116          |
+| 0.8496        | 5.0   | 5    | 1.9875          |
+| 1.2794        | 6.0   | 6    | 0.5662          |
+| 1.0065        | 7.0   | 7    | 1.5597          |
+| 1.9355        | 8.0   | 8    | 1.1750          |
 
 
 ### Framework versions