update model card README.md

README.md

@@ -32,7 +32,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on the imagefolder dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6744
+- Loss: 0.7675
 - Accuracy: 0.8182
 
 ## Model description
@@ -64,11 +64,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.0099        | 3.57  | 50   | 0.6155          | 0.8182   |
-| 0.0007        | 7.14  | 100  | 0.7441          | 0.7576   |
-| 0.0004        | 10.71 | 150  | 0.6925          | 0.8182   |
-| 0.0003        | 14.29 | 200  | 0.6793          | 0.8182   |
-| 0.0003        | 17.86 | 250  | 0.6744          | 0.8182   |
+| 0.004         | 3.57  | 50   | 1.0744          | 0.7576   |
+| 0.0005        | 7.14  | 100  | 0.8182          | 0.7879   |
+| 0.0004        | 10.71 | 150  | 0.7808          | 0.7879   |
+| 0.0003        | 14.29 | 200  | 0.7710          | 0.8182   |
+| 0.0003        | 17.86 | 250  | 0.7675          | 0.8182   |
 
 
 ### Framework versions