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: 1.6332
-- Accuracy: 0.87
+- Loss: 0.9285
+- Accuracy: 0.905
 
 ## Model description
 
@@ -52,9 +52,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 2.6598        | 0.99  | 62   | 2.5169          | 0.791    |
-| 1.7918        | 2.0   | 125  | 1.7823          | 0.873    |
-| 1.5743        | 2.98  | 186  | 1.6332          | 0.87     |
+| 1.2297        | 0.99  | 62   | 1.2591          | 0.899    |
+| 0.9027        | 2.0   | 125  | 0.9801          | 0.911    |
+| 0.8192        | 2.98  | 186  | 0.9285          | 0.905    |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:876afad9c5335fb9a0cf5bb0029ac8b68451d905043d3c066edc5a992874ce95
+oid sha256:86d6314de4b4ccd6150fce1dbdfb4ac3685199d40d13c5ff4dcdd99b8dd2ce45
 size 343528508