update model card README.md

README.md

@@ -19,7 +19,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.9856
+      value: 0.9863
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -29,8 +29,8 @@ 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 cifar10 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0998
-- Accuracy: 0.9856
+- Loss: 0.0999
+- Accuracy: 0.9863
 
 ## Model description
 
@@ -64,9 +64,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.4007        | 1.0   | 390  | 0.1963          | 0.9807   |
-| 0.2976        | 2.0   | 780  | 0.1169          | 0.9854   |
-| 0.2538        | 3.0   | 1170 | 0.0998          | 0.9856   |
+| 0.3897        | 1.0   | 390  | 0.2083          | 0.9757   |
+| 0.3045        | 2.0   | 780  | 0.1175          | 0.986    |
+| 0.2524        | 3.0   | 1170 | 0.0999          | 0.9863   |
 
 
 ### Framework versions