Model save

README.md

@@ -18,8 +18,8 @@ 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 an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0172
-- Accuracy: 0.9905
+- Loss: 0.0377
+- Accuracy: 1.0
 
 ## Model description
 
@@ -47,14 +47,18 @@ 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: 20
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.803         | 1.0   | 15   | 0.1343          | 0.9619   |
-| 0.0409        | 2.0   | 30   | 0.0172          | 0.9905   |
+| Training Loss | Epoch  | Step | Validation Loss | Accuracy |
+|:-------------:|:------:|:----:|:---------------:|:--------:|
+| No log        | 0.9333 | 7    | 1.0901          | 0.6415   |
+| 1.2435        | 2.0    | 15   | 0.4266          | 0.8585   |
+| 0.5378        | 2.9333 | 22   | 0.1524          | 0.9528   |
+| 0.1747        | 4.0    | 30   | 0.0747          | 0.9717   |
+| 0.1747        | 4.9333 | 37   | 0.0865          | 0.9623   |
+| 0.0905        | 6.0    | 45   | 0.0377          | 1.0      |
 
 
 ### Framework versions