update model card README.md

README.md

@@ -16,8 +16,8 @@ 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 None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1375
-- Accuracy: 0.9286
+- Loss: 0.2051
+- Accuracy: 0.9388
 
 ## Model description
 
@@ -42,14 +42,17 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 4
+- num_epochs: 10
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.3926        | 2.0   | 100  | 0.2469          | 0.8980   |
-| 0.0904        | 4.0   | 200  | 0.1375          | 0.9286   |
+| 0.5025        | 2.0   | 100  | 0.3267          | 0.8776   |
+| 0.204         | 4.0   | 200  | 0.2941          | 0.9082   |
+| 0.1425        | 6.0   | 300  | 0.3407          | 0.9082   |
+| 0.091         | 8.0   | 400  | 0.1722          | 0.9592   |
+| 0.0328        | 10.0  | 500  | 0.2051          | 0.9388   |
 
 
 ### Framework versions