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: 1.2311
-- Accuracy: 0.35
+- Loss: 1.3015
+- Accuracy: 0.4
 
 ## Model description
 
@@ -43,14 +43,20 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 2
+- num_epochs: 100
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.3821        | 1.0   | 12   | 1.2296          | 0.35     |
-| 1.3471        | 2.0   | 24   | 1.2311          | 0.35     |
+| 1.3814        | 1.0   | 12   | 1.2339          | 0.35     |
+| 1.3208        | 2.0   | 24   | 1.2381          | 0.35     |
+| 1.3387        | 3.0   | 36   | 1.2284          | 0.4      |
+| 1.2083        | 4.0   | 48   | 1.2504          | 0.4      |
+| 1.1881        | 5.0   | 60   | 1.2781          | 0.4      |
+| 1.0885        | 6.0   | 72   | 1.2886          | 0.4      |
+| 1.1656        | 7.0   | 84   | 1.2927          | 0.4      |
+| 0.997         | 8.0   | 96   | 1.3015          | 0.4      |
 
 
 ### Framework versions