End of training

README.md

@@ -33,7 +33,7 @@ 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 imagefolder dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.9515
+- Loss: 1.9752
 - Accuracy: 0.3063
 
 ## Model description
@@ -68,9 +68,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 2.0646        | 1.0   | 10   | 2.0364          | 0.2      |
-| 1.9776        | 2.0   | 20   | 1.9918          | 0.2687   |
-| 1.9046        | 3.0   | 30   | 1.9485          | 0.2812   |
+| 2.0584        | 1.0   | 10   | 2.0231          | 0.275    |
+| 1.9785        | 2.0   | 20   | 1.9722          | 0.3063   |
+| 1.9134        | 3.0   | 30   | 1.9484          | 0.275    |
 
 
 ### Framework versions