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: 2.4201
-- Accuracy: 0.695
+- Loss: 2.5156
+- Accuracy: 0.715
 
 ## Model description
 
@@ -52,9 +52,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 4.3112        | 0.96  | 12   | 3.4092          | 0.7      |
-| 3.1011        | 2.0   | 25   | 2.5908          | 0.695    |
-| 2.5328        | 2.88  | 36   | 2.4201          | 0.695    |
+| 4.2745        | 0.96  | 12   | 3.4188          | 0.74     |
+| 3.1492        | 2.0   | 25   | 2.6873          | 0.7      |
+| 2.6294        | 2.88  | 36   | 2.5156          | 0.715    |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e84012a42b7264147f476bfbc794385210e21e46e8f06e1186dd0e341c1f4a7
+oid sha256:38d7078e2fc6f39070f3cad8c872fa1ffb5d52a2e5b534fd427105426f611957
 size 343528508