End of training

README.md

@@ -32,7 +32,7 @@ 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: 0.4822
+- Loss: 0.4930
 - Accuracy: 0.8210
 
 ## Model description
@@ -65,14 +65,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.4892        | 1.16  | 150  | 0.5660          | 0.7271   |
-| 0.4346        | 2.33  | 300  | 0.4475          | 0.7860   |
-| 0.4072        | 3.49  | 450  | 0.4499          | 0.7882   |
-| 0.312         | 4.65  | 600  | 0.5289          | 0.7598   |
-| 0.2913        | 5.81  | 750  | 0.4868          | 0.8100   |
-| 0.2389        | 6.98  | 900  | 0.4596          | 0.8079   |
-| 0.2176        | 8.14  | 1050 | 0.4642          | 0.8210   |
-| 0.183         | 9.3   | 1200 | 0.4822          | 0.8210   |
+| 0.4846        | 1.16  | 150  | 0.5930          | 0.7118   |
+| 0.4383        | 2.33  | 300  | 0.4550          | 0.7751   |
+| 0.3695        | 3.49  | 450  | 0.4941          | 0.7838   |
+| 0.314         | 4.65  | 600  | 0.5041          | 0.7795   |
+| 0.2717        | 5.81  | 750  | 0.4721          | 0.8057   |
+| 0.2261        | 6.98  | 900  | 0.4459          | 0.8079   |
+| 0.1931        | 8.14  | 1050 | 0.5161          | 0.7904   |
+| 0.1703        | 9.3   | 1200 | 0.4930          | 0.8210   |
 
 
 ### Framework versions