Model save

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.8235294117647058
+      value: 0.9215686274509803
 ---
 
 <!-- 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: 0.4261
-- Accuracy: 0.8235
+- Loss: 0.2238
+- Accuracy: 0.9216
 
 ## Model description
 
@@ -61,16 +61,20 @@ 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: 5
+- num_epochs: 10
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 0.8   | 3    | 0.6160          | 0.6765   |
-| No log        | 1.87  | 7    | 0.5526          | 0.7157   |
-| 0.5689        | 2.93  | 11   | 0.4532          | 0.8137   |
-| 0.5689        | 4.0   | 15   | 0.4261          | 0.8235   |
+| No log        | 0.8   | 3    | 0.6505          | 0.5980   |
+| No log        | 1.87  | 7    | 0.5601          | 0.6961   |
+| 0.5923        | 2.93  | 11   | 0.4470          | 0.7941   |
+| 0.5923        | 4.0   | 15   | 0.3706          | 0.8235   |
+| 0.5923        | 4.8   | 18   | 0.3413          | 0.8431   |
+| 0.3003        | 5.87  | 22   | 0.2637          | 0.8922   |
+| 0.3003        | 6.93  | 26   | 0.2387          | 0.9118   |
+| 0.1648        | 8.0   | 30   | 0.2238          | 0.9216   |
 
 
 ### Framework versions