update model card README.md

README.md

@@ -17,8 +17,8 @@ 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 an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8415
-- Accuracy: 0.7111
+- Loss: nan
+- Accuracy: 0.12
 
 ## Model description
 
@@ -52,9 +52,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 0.97  | 7    | 0.9445          | 0.6311   |
-| 0.9786        | 1.93  | 14   | 0.8769          | 0.6578   |
-| 0.8386        | 2.9   | 21   | 0.8415          | 0.7111   |
+| No log        | 0.97  | 7    | nan             | 0.12     |
+| 0.0           | 1.93  | 14   | nan             | 0.12     |
+| 0.0           | 2.9   | 21   | nan             | 0.12     |
 
 
 ### Framework versions