End of training

README.md

@@ -18,8 +18,8 @@ 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: 1.6812
-- Accuracy: 0.894
+- Loss: 1.6179
+- Accuracy: 0.893
 
 ## Model description
 
@@ -53,9 +53,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 2.7458        | 0.992 | 62   | 2.5679          | 0.842    |
-| 1.8566        | 2.0   | 125  | 1.8382          | 0.877    |
-| 1.6682        | 2.976 | 186  | 1.6812          | 0.894    |
+| 2.7196        | 0.992 | 62   | 2.5023          | 0.832    |
+| 1.8192        | 2.0   | 125  | 1.7635          | 0.888    |
+| 1.5884        | 2.976 | 186  | 1.6179          | 0.893    |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8aa0c3c39040687e44e9b8475ecf9a5395dbcb56453342c16a457f46e6e4f634
+oid sha256:ba2153f16139dfcebfa9c9950983678896b77424af76370894f90b3fe1839a04
 size 343528508