End of training

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: 0.7835
-- Accuracy: 0.8936
+- Loss: 0.8088
+- Accuracy: 0.8511
 
 ## Model description
 
@@ -52,9 +52,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss | Accuracy |
 |:-------------:|:------:|:----:|:---------------:|:--------:|
-| No log        | 0.8889 | 6    | 0.9527          | 0.7021   |
-| 0.9921        | 1.9259 | 13   | 0.8188          | 0.8936   |
-| 0.9921        | 2.6667 | 18   | 0.7835          | 0.8936   |
+| No log        | 0.8889 | 6    | 0.9810          | 0.6596   |
+| 1.0184        | 1.9259 | 13   | 0.8452          | 0.8085   |
+| 1.0184        | 2.6667 | 18   | 0.8088          | 0.8511   |
 
 
 ### Framework versions

runs/Jul30_20-41-34_fedora/events.out.tfevents.1722352296.fedora.12677.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9abe335af3dc0d9dd262ce315d4d0c835d184dddf9ea54bdf9b1a001558cd05
-size 5809
+oid sha256:6df6e25a37ccfabe063095b503e1b1a8e0585fe5b7468192131778ab06e85e8e
+size 6474