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: 2.2235
+- Loss: 1.9145
 - Accuracy: 0.9605
 
 ## Model description
@@ -64,9 +64,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 40   | 2.5150          | 0.9605   |
-| No log        | 2.0   | 80   | 1.7614          | 0.9605   |
-| No log        | 3.0   | 120  | 1.4963          | 0.9605   |
+| No log        | 1.0   | 40   | 1.9285          | 0.9605   |
+| No log        | 2.0   | 80   | 1.6904          | 0.9605   |
+| No log        | 3.0   | 120  | 1.6333          | 0.9605   |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:004a105ad25b83746ab1a1b699fe6ee12aeccec623cd4a85d7f82da040df8d4a
+oid sha256:65d4b8275684d1d04608cc2590826183ed1df2172f5c06ead672f8e165c7ab8a
 size 343287149