update model card README.md

README.md

@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [irfanamal/electra_multiple_choice](https://huggingface.co/irfanamal/electra_multiple_choice) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.4297
-- Accuracy: 0.5
+- Loss: 1.4339
+- Accuracy: 0.3
 
 ## Model description
 
@@ -49,13 +49,12 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.173         | 1.0   | 12   | 1.2925          | 0.4      |
-| 0.9095        | 2.0   | 24   | 1.2696          | 0.45     |
-| 0.8365        | 3.0   | 36   | 1.3071          | 0.45     |
-| 0.7269        | 4.0   | 48   | 1.3577          | 0.45     |
-| 0.6143        | 5.0   | 60   | 1.3832          | 0.45     |
-| 0.4929        | 6.0   | 72   | 1.4062          | 0.45     |
-| 0.5534        | 7.0   | 84   | 1.4297          | 0.5      |
+| 1.2087        | 1.0   | 12   | 1.3288          | 0.35     |
+| 1.1047        | 2.0   | 24   | 1.3350          | 0.35     |
+| 1.0488        | 3.0   | 36   | 1.3800          | 0.35     |
+| 0.9056        | 4.0   | 48   | 1.4077          | 0.35     |
+| 0.8572        | 5.0   | 60   | 1.4096          | 0.35     |
+| 0.7495        | 6.0   | 72   | 1.4339          | 0.3      |
 
 
 ### Framework versions