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: 1.2277
+- Loss: 1.8704
 
 ## Model description
 
@@ -45,19 +45,19 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 5.5675        | 1.0   | 1    | 1.3549          |
-| 2.2284        | 2.0   | 2    | 18.2791         |
-| 2.2965        | 3.0   | 3    | 4.0393          |
-| 1.9673        | 4.0   | 4    | 0.9920          |
-| 1.786         | 5.0   | 5    | 0.1229          |
-| 1.5902        | 6.0   | 6    | 0.0084          |
-| 0.3822        | 7.0   | 7    | 0.0350          |
-| 1.7314        | 8.0   | 8    | 0.0067          |
+| 3.3031        | 1.0   | 1    | 4.8955          |
+| 1.3131        | 2.0   | 2    | 2.3064          |
+| 2.3224        | 3.0   | 3    | 2.9597          |
+| 1.0301        | 4.0   | 4    | 2.3126          |
+| 1.4955        | 5.0   | 5    | 1.6768          |
+| 0.6759        | 6.0   | 6    | 5.2817          |
+| 0.6935        | 7.0   | 7    | 2.5742          |
+| 1.4726        | 8.0   | 8    | 0.1827          |
 
 
 ### Framework versions
 
 - Transformers 4.30.2
 - Pytorch 2.0.1+cu118
-- Datasets 2.13.0
+- Datasets 2.13.1
 - Tokenizers 0.13.3