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/distilroberta_multiple_choice](https://huggingface.co/irfanamal/distilroberta_multiple_choice) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.4282
-- Accuracy: 0.35
+- Loss: 1.1865
+- Accuracy: 0.45
 
 ## Model description
 
@@ -49,17 +49,12 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.4689        | 1.0   | 12   | 1.3175          | 0.4      |
-| 1.3887        | 2.0   | 24   | 1.3284          | 0.4      |
-| 1.3604        | 3.0   | 36   | 1.3423          | 0.4      |
-| 1.2581        | 4.0   | 48   | 1.3595          | 0.4      |
-| 1.2564        | 5.0   | 60   | 1.3679          | 0.4      |
-| 1.1925        | 6.0   | 72   | 1.3653          | 0.4      |
-| 1.1833        | 7.0   | 84   | 1.3678          | 0.4      |
-| 1.1222        | 8.0   | 96   | 1.3909          | 0.4      |
-| 1.1168        | 9.0   | 108  | 1.3946          | 0.4      |
-| 1.0463        | 10.0  | 120  | 1.4138          | 0.4      |
-| 1.0468        | 11.0  | 132  | 1.4282          | 0.35     |
+| 1.2224        | 1.0   | 12   | 1.1496          | 0.55     |
+| 1.1583        | 2.0   | 24   | 1.1524          | 0.55     |
+| 1.048         | 3.0   | 36   | 1.1579          | 0.55     |
+| 0.9627        | 4.0   | 48   | 1.1684          | 0.5      |
+| 0.9622        | 5.0   | 60   | 1.1902          | 0.45     |
+| 0.9237        | 6.0   | 72   | 1.1865          | 0.45     |
 
 
 ### Framework versions