update model card README.md

README.md

@@ -21,7 +21,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.6047227926078029
+      value: 0.5852156057494866
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -31,8 +31,8 @@ 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 pokemon-classification dataset.
 It achieves the following results on the evaluation set:
-- Loss: 4.3322
-- Accuracy: 0.6047
+- Loss: 4.3447
+- Accuracy: 0.5852
 
 ## Model description
 
@@ -66,9 +66,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 4.7523        | 1.0   | 61   | 4.7318          | 0.2197   |
-| 4.459         | 2.0   | 122  | 4.4401          | 0.5380   |
-| 4.2805        | 3.0   | 183  | 4.3322          | 0.6047   |
+| 4.7732        | 1.0   | 61   | 4.7448          | 0.1992   |
+| 4.443         | 2.0   | 122  | 4.4606          | 0.4897   |
+| 4.2705        | 3.0   | 183  | 4.3447          | 0.5852   |
 
 
 ### Framework versions