Model save

README.md

@@ -17,9 +17,9 @@ 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: 0.1100
-- Accuracy: 0.9780
-- Confusion Matrix: [[62, 4], [1, 160]]
+- Loss: 0.1137
+- Accuracy: 0.9692
+- Confusion Matrix: [[60, 6], [1, 160]]
 
 ## Model description
 
@@ -51,8 +51,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss | Accuracy | Confusion Matrix    |
 |:-------------:|:------:|:----:|:---------------:|:--------:|:-------------------:|
-| 0.1306        | 1.7544 | 100  | 0.1536          | 0.9736   | [[60, 6], [0, 161]] |
-| 0.0912        | 3.5088 | 200  | 0.1100          | 0.9780   | [[62, 4], [1, 160]] |
+| 0.1251        | 1.7544 | 100  | 0.1513          | 0.9692   | [[59, 7], [0, 161]] |
+| 0.0895        | 3.5088 | 200  | 0.1137          | 0.9692   | [[60, 6], [1, 160]] |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5508e4cc3a84fc66b316ef26728a4bc0816baf69cbd4721aae7099255fbef0f
+oid sha256:e9d92f743b75ab5c1ad7aafe4664965ff25823f047f832bc6648de1e166aa60b
 size 343223968