Model save

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.7880986937590712
+      value: 0.8084179970972424
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +32,8 @@ 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: 0.5690
-- Accuracy: 0.7881
+- Loss: 0.5213
+- Accuracy: 0.8084
 
 ## Model description
 
@@ -61,15 +61,17 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 3
+- num_epochs: 5
 
 ### Training results
 
 | Training Loss | Epoch | Step | Accuracy | Validation Loss |
 |:-------------:|:-----:|:----:|:--------:|:---------------:|
 | 0.8849        | 1.0   | 97   | 0.6836   | 0.8586          |
-| 0.7461        | 2.0   | 194  | 0.6177   | 0.7678          |
-| 0.6429        | 3.0   | 291  | 0.5690   | 0.7881          |
+| 0.7461        | 2.0   | 194  | 0.7678   | 0.6177          |
+| 0.6429        | 3.0   | 291  | 0.7881   | 0.5690          |
+| 0.6522        | 4.0   | 388  | 0.5325   | 0.7968          |
+| 0.6189        | 5.0   | 485  | 0.5213   | 0.8084          |
 
 
 ### Framework versions