update model card README.md

README.md

@@ -16,8 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [prajjwal1/bert-tiny](https://huggingface.co/prajjwal1/bert-tiny) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5395
-- Accuracy: 0.785
+- Loss: 0.5475
+- Accuracy: 0.7933
 
 ## Model description
 
@@ -48,9 +48,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.5167        | 1.0   | 1500 | 0.4749          | 0.7767   |
-| 0.3814        | 2.0   | 3000 | 0.5141          | 0.785    |
-| 0.3376        | 3.0   | 4500 | 0.5395          | 0.785    |
+| 0.5168        | 1.0   | 1500 | 0.4738          | 0.7733   |
+| 0.3809        | 2.0   | 3000 | 0.5253          | 0.7917   |
+| 0.3372        | 3.0   | 4500 | 0.5475          | 0.7933   |
 
 
 ### Framework versions