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/bert_multiple_choice](https://huggingface.co/irfanamal/bert_multiple_choice) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.4764
-- Accuracy: 0.53
+- Loss: 1.1939
+- Accuracy: 0.4
 
 ## Model description
 
@@ -47,16 +47,17 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step  | Validation Loss | Accuracy |
-|:-------------:|:-----:|:-----:|:---------------:|:--------:|
-| 1.365         | 1.0   | 1713  | 1.3182          | 0.485    |
-| 1.2475        | 2.0   | 3426  | 1.2630          | 0.485    |
-| 1.1336        | 3.0   | 5139  | 1.2537          | 0.49     |
-| 1.012         | 4.0   | 6852  | 1.2563          | 0.5      |
-| 0.89          | 5.0   | 8565  | 1.2743          | 0.51     |
-| 0.7699        | 6.0   | 10278 | 1.3385          | 0.51     |
-| 0.6614        | 7.0   | 11991 | 1.3663          | 0.515    |
-| 0.5717        | 8.0   | 13704 | 1.4764          | 0.53     |
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 1.2306        | 1.0   | 12   | 1.1937          | 0.45     |
+| 1.1243        | 2.0   | 24   | 1.1896          | 0.4      |
+| 1.0706        | 3.0   | 36   | 1.1906          | 0.45     |
+| 0.9598        | 4.0   | 48   | 1.1842          | 0.4      |
+| 0.8738        | 5.0   | 60   | 1.1924          | 0.4      |
+| 0.7774        | 6.0   | 72   | 1.1853          | 0.45     |
+| 0.8232        | 7.0   | 84   | 1.1934          | 0.45     |
+| 0.6855        | 8.0   | 96   | 1.1903          | 0.4      |
+| 0.6606        | 9.0   | 108  | 1.1939          | 0.4      |
 
 
 ### Framework versions