update model card README.md

README.md

@@ -16,8 +16,8 @@ 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: 0.6406
-- Accuracy: 0.7559
+- Loss: 0.4676
+- Accuracy: 0.8368
 
 ## Model description
 
@@ -45,15 +45,22 @@ 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: 10
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.0456        | 1.0   | 10   | 0.7554          | 0.7377   |
-| 0.6468        | 2.0   | 20   | 0.6761          | 0.7552   |
-| 0.573         | 3.0   | 30   | 0.6406          | 0.7559   |
+| 0.5347        | 1.0   | 10   | 0.6032          | 0.7845   |
+| 0.4686        | 2.0   | 20   | 0.5631          | 0.7908   |
+| 0.388         | 3.0   | 30   | 0.5040          | 0.8067   |
+| 0.3164        | 4.0   | 40   | 0.4808          | 0.8162   |
+| 0.29          | 5.0   | 50   | 0.4786          | 0.8185   |
+| 0.2268        | 6.0   | 60   | 0.4634          | 0.8320   |
+| 0.2065        | 7.0   | 70   | 0.4707          | 0.8360   |
+| 0.1681        | 8.0   | 80   | 0.4635          | 0.8296   |
+| 0.1425        | 9.0   | 90   | 0.4795          | 0.8376   |
+| 0.1452        | 10.0  | 100  | 0.4676          | 0.8368   |
 
 
 ### Framework versions