karim155
/

swin-tiny-patch4-window7-224-finetuned

@@ -21,11 +21,11 @@ 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 None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.0150
-- Accuracy: 0.5582
-- Precision: 0.6432
-- Recall: 0.5582
-- F1: 0.5799
 ## Model description
@@ -59,21 +59,21 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch  | Step | Validation Loss | Accuracy | Precision | Recall | F1     |
 |:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
-| 1.1775        | 0.9846 | 32   | 1.0874          | 0.3600   | 0.6471    | 0.3600 | 0.3554 |
-| 1.1165        | 2.0    | 65   | 1.0633          | 0.4379   | 0.6194    | 0.4379 | 0.4705 |
-| 0.9901        | 2.9846 | 97   | 1.0061          | 0.4995   | 0.6327    | 0.4995 | 0.5200 |
-| 0.9606        | 4.0    | 130  | 0.9967          | 0.3994   | 0.6477    | 0.3994 | 0.4159 |
-| 0.8326        | 4.9846 | 162  | 0.9942          | 0.4841   | 0.6228    | 0.4841 | 0.5036 |
-| 0.824         | 6.0    | 195  | 0.9646          | 0.4937   | 0.6523    | 0.4937 | 0.5250 |
-| 0.7647        | 6.9846 | 227  | 1.0272          | 0.5669   | 0.6401    | 0.5669 | 0.5827 |
-| 0.7682        | 8.0    | 260  | 1.0007          | 0.5101   | 0.6531    | 0.5101 | 0.5371 |
-| 0.721         | 8.9846 | 292  | 1.0121          | 0.5515   | 0.6464    | 0.5515 | 0.5744 |
-| 0.6878        | 9.8462 | 320  | 1.0150          | 0.5582   | 0.6432    | 0.5582 | 0.5799 |
 ### Framework versions
 - Transformers 4.44.2
 - Pytorch 2.4.0+cu121
-- Datasets 2.21.0
 - Tokenizers 0.19.1

 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 None dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.9034
+- Accuracy: 0.6660
+- Precision: 0.6546
+- Recall: 0.6660
+- F1: 0.6519
 ## Model description
 | Training Loss | Epoch  | Step | Validation Loss | Accuracy | Precision | Recall | F1     |
 |:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
+| 1.0809        | 0.9846 | 32   | 1.0485          | 0.5833   | 0.5506    | 0.5833 | 0.5627 |
+| 1.0052        | 2.0    | 65   | 1.0600          | 0.5727   | 0.5941    | 0.5727 | 0.5170 |
+| 0.9429        | 2.9846 | 97   | 0.9755          | 0.6160   | 0.5878    | 0.6160 | 0.5837 |
+| 0.9497        | 4.0    | 130  | 0.9318          | 0.6497   | 0.6458    | 0.6497 | 0.6313 |
+| 0.8807        | 4.9846 | 162  | 0.9541          | 0.6304   | 0.6321    | 0.6304 | 0.6200 |
+| 0.8089        | 6.0    | 195  | 0.9556          | 0.6266   | 0.6270    | 0.6266 | 0.6150 |
+| 0.801         | 6.9846 | 227  | 0.9050          | 0.6603   | 0.6512    | 0.6603 | 0.6472 |
+| 0.7753        | 8.0    | 260  | 0.9134          | 0.6506   | 0.6440    | 0.6506 | 0.6440 |
+| 0.6986        | 8.9846 | 292  | 0.9138          | 0.6554   | 0.6468    | 0.6554 | 0.6436 |
+| 0.7107        | 9.8462 | 320  | 0.9034          | 0.6660   | 0.6546    | 0.6660 | 0.6519 |
 ### Framework versions
 - Transformers 4.44.2
 - Pytorch 2.4.0+cu121
+- Datasets 3.0.0
 - Tokenizers 0.19.1