Model save

README.md

@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on an unknown dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.5650
 - Accuracy: 0.9699
-- Loss: 0.5646
 
 ## Model description
 
@@ -47,11 +47,11 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Accuracy | Validation Loss |
-|:-------------:|:-----:|:----:|:--------:|:---------------:|
-| 0.9886        | 1.0   | 17   | 0.9248   | 0.7758          |
-| 0.7226        | 2.0   | 34   | 0.9549   | 0.6198          |
-| 0.6041        | 3.0   | 51   | 0.9699   | 0.5646          |
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.9886        | 1.0   | 17   | 0.7759          | 0.9248   |
+| 0.7228        | 2.0   | 34   | 0.6195          | 0.9549   |
+| 0.6046        | 3.0   | 51   | 0.5650          | 0.9699   |
 
 
 ### Framework versions