Model save

README.md

@@ -25,16 +25,16 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.9340658097220965
+      value: 0.9281026523037929
     - name: Precision
       type: precision
-      value: 0.9434178845400079
+      value: 0.9313185681527962
     - name: Recall
       type: recall
-      value: 0.9741973720348661
+      value: 0.9804564969138033
     - name: F1
       type: f1
-      value: 0.9585606087544003
+      value: 0.9552560419131316
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -44,12 +44,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the imagefolder dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1603
-- Accuracy: 0.9341
-- Precision: 0.9434
-- Recall: 0.9742
-- F1: 0.9586
-- Roc Auc: 0.9778
+- Loss: 0.1696
+- Accuracy: 0.9281
+- Precision: 0.9313
+- Recall: 0.9805
+- F1: 0.9553
+- Roc Auc: 0.9777
 
 ## Model description
 
@@ -83,7 +83,7 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1     | Roc Auc |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|:-------:|
-| 0.193         | 1.0   | 1381 | 0.1603          | 0.9341   | 0.9434    | 0.9742 | 0.9586 | 0.9778  |
+| 0.1834        | 1.0   | 1381 | 0.1696          | 0.9281   | 0.9313    | 0.9805 | 0.9553 | 0.9777  |
 
 
 ### Framework versions