Model save

README.md

@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [microsoft/swin-base-patch4-window7-224-in22k](https://huggingface.co/microsoft/swin-base-patch4-window7-224-in22k) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0054
-- Accuracy: 0.9980
+- Loss: 0.0068
+- Accuracy: 0.9983
 
 ## Model description
 
@@ -44,17 +44,20 @@ 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: 8
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 1147 | 0.0769          | 0.9750   |
-| No log        | 2.0   | 2294 | 0.0221          | 0.9917   |
-| No log        | 3.0   | 3441 | 0.0157          | 0.9956   |
-| No log        | 4.0   | 4588 | 0.0074          | 0.9973   |
-| 0.1493        | 5.0   | 5735 | 0.0054          | 0.9980   |
+| No log        | 1.0   | 1147 | 0.0708          | 0.9768   |
+| No log        | 2.0   | 2294 | 0.0423          | 0.9871   |
+| No log        | 3.0   | 3441 | 0.0128          | 0.9963   |
+| No log        | 4.0   | 4588 | 0.0155          | 0.9951   |
+| No log        | 5.0   | 5735 | 0.0075          | 0.9980   |
+| No log        | 6.0   | 6882 | 0.0090          | 0.9979   |
+| No log        | 7.0   | 8029 | 0.0075          | 0.9976   |
+| 0.1295        | 8.0   | 9176 | 0.0068          | 0.9983   |
 
 
 ### Framework versions