update model card README.md

README.md

@@ -19,11 +19,11 @@ 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: 0.6272
-- Accuracy: 0.8549
-- F1: 0.8558
-- Precision: 0.8590
-- Recall: 0.8549
+- Loss: 0.4526
+- Accuracy: 0.8756
+- F1: 0.8760
+- Precision: 0.8781
+- Recall: 0.8756
 
 ## Model description
 
@@ -55,10 +55,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Precision | Recall |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
-| 0.4385        | 1.0   | 626  | 0.4796          | 0.8290   | 0.8273 | 0.8726    | 0.8290 |
-| 0.3573        | 2.0   | 1252 | 0.4745          | 0.8549   | 0.8581 | 0.8651    | 0.8549 |
-| 0.1444        | 3.0   | 1878 | 0.6086          | 0.8394   | 0.8406 | 0.8440    | 0.8394 |
-| 0.0055        | 4.0   | 2504 | 0.6272          | 0.8549   | 0.8558 | 0.8590    | 0.8549 |
+| 0.1259        | 1.0   | 626  | 0.3835          | 0.8342   | 0.8404 | 0.8538    | 0.8342 |
+| 0.156         | 2.0   | 1252 | 0.3702          | 0.8756   | 0.8658 | 0.8652    | 0.8756 |
+| 0.0349        | 3.0   | 1878 | 0.4699          | 0.8705   | 0.8715 | 0.8771    | 0.8705 |
+| 0.0005        | 4.0   | 2504 | 0.4526          | 0.8756   | 0.8760 | 0.8781    | 0.8756 |
 
 
 ### Framework versions