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/distilbert_multiple_choice](https://huggingface.co/irfanamal/distilbert_multiple_choice) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.1067
-- Accuracy: 0.6
+- Loss: 1.2270
+- Accuracy: 0.45
 
 ## Model description
 
@@ -49,17 +49,12 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.2754        | 1.0   | 12   | 1.1916          | 0.55     |
-| 1.142         | 2.0   | 24   | 1.1608          | 0.55     |
-| 1.0688        | 3.0   | 36   | 1.1239          | 0.55     |
-| 0.9401        | 4.0   | 48   | 1.1163          | 0.55     |
-| 0.9029        | 5.0   | 60   | 1.1077          | 0.6      |
-| 0.7597        | 6.0   | 72   | 1.0713          | 0.6      |
-| 0.7811        | 7.0   | 84   | 1.0723          | 0.6      |
-| 0.7215        | 8.0   | 96   | 1.1225          | 0.6      |
-| 0.6318        | 9.0   | 108  | 1.1065          | 0.6      |
-| 0.6308        | 10.0  | 120  | 1.0958          | 0.6      |
-| 0.6369        | 11.0  | 132  | 1.1067          | 0.6      |
+| 1.2942        | 1.0   | 12   | 1.2255          | 0.5      |
+| 1.2394        | 2.0   | 24   | 1.2289          | 0.5      |
+| 1.2116        | 3.0   | 36   | 1.2436          | 0.5      |
+| 1.0957        | 4.0   | 48   | 1.2457          | 0.5      |
+| 1.0705        | 5.0   | 60   | 1.2316          | 0.45     |
+| 0.993         | 6.0   | 72   | 1.2270          | 0.45     |
 
 
 ### Framework versions