update model card README.md

README.md

@@ -18,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the swag dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.0401
-- Accuracy: 0.6117
+- Loss: 0.6045
+- Accuracy: 0.7960
 
 ## Model description
 
@@ -44,15 +44,14 @@ 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: 3
+- num_epochs: 2
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 32   | 1.0224          | 0.5845   |
-| No log        | 2.0   | 64   | 0.9723          | 0.6218   |
-| No log        | 3.0   | 96   | 1.0401          | 0.6117   |
+| 0.7494        | 1.0   | 4597 | 0.5942          | 0.7716   |
+| 0.3499        | 2.0   | 9194 | 0.6045          | 0.7960   |
 
 
 ### Framework versions