update model card README.md

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.944
+      value: 0.89
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +32,8 @@ 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 the food101 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8639
-- Accuracy: 0.944
+- Loss: 2.1839
+- Accuracy: 0.89
 
 ## Model description
 
@@ -67,9 +67,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 3.0782        | 0.99  | 35   | 2.4007          | 0.822    |
-| 1.3449        | 1.99  | 70   | 1.1722          | 0.904    |
-| 0.9413        | 2.98  | 105  | 0.8639          | 0.944    |
+| 3.5351        | 0.99  | 35   | 3.1080          | 0.84     |
+| 2.5064        | 1.99  | 70   | 2.3774          | 0.872    |
+| 2.2501        | 2.98  | 105  | 2.1839          | 0.89     |
 
 
 ### Framework versions