Model save

README.md

@@ -24,13 +24,13 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.8993647609495152
+      value: 0.9883021390374331
     - name: Precision
       type: precision
-      value: 0.914936979126043
+      value: 0.9883071765108582
     - name: Recall
       type: recall
-      value: 0.8993647609495152
+      value: 0.9883021390374331
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -40,11 +40,11 @@ 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: 0.2879
-- Accuracy: 0.8994
-- Precision: 0.9149
-- Recall: 0.8994
-- Confusion Matrix: [[1506, 5], [296, 1184]]
+- Loss: 0.0394
+- Accuracy: 0.9883
+- Precision: 0.9883
+- Recall: 0.9883
+- Confusion Matrix: [[1497, 15], [20, 1460]]
 
 ## Model description
 
@@ -78,9 +78,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | Confusion Matrix         |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------------------------:|
-| 0.0727        | 1.0   | 374  | 0.2915          | 0.9057   | 0.9199    | 0.9057 | [[1508, 3], [279, 1201]] |
-| 0.0635        | 2.0   | 748  | 0.1764          | 0.9305   | 0.9379    | 0.9305 | [[1505, 6], [202, 1278]] |
-| 0.0396        | 3.0   | 1122 | 0.2879          | 0.8994   | 0.9149    | 0.8994 | [[1506, 5], [296, 1184]] |
+| 0.1107        | 1.0   | 374  | 0.0641          | 0.9786   | 0.9787    | 0.9786 | [[1488, 24], [40, 1440]] |
+| 0.1079        | 2.0   | 748  | 0.0560          | 0.9773   | 0.9776    | 0.9773 | [[1498, 14], [54, 1426]] |
+| 0.0624        | 3.0   | 1122 | 0.0394          | 0.9883   | 0.9883    | 0.9883 | [[1497, 15], [20, 1460]] |
 
 
 ### Framework versions