Model save

README.md

@@ -1,6 +1,6 @@
 ---
 license: apache-2.0
-base_model: mansee/swin-tiny-patch4-window7-224
+base_model: mansee/swin-tiny-patch4-window7-224-img_orientation
 tags:
 - generated_from_trainer
 datasets:
@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.7400272758267985
+      value: 0.7797476986021139
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -30,10 +30,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # swin-tiny-patch4-window7-224-img_orientation
 
-This model is a fine-tuned version of [mansee/swin-tiny-patch4-window7-224](https://huggingface.co/mansee/swin-tiny-patch4-window7-224) on the imagefolder dataset.
+This model is a fine-tuned version of [mansee/swin-tiny-patch4-window7-224-img_orientation](https://huggingface.co/mansee/swin-tiny-patch4-window7-224-img_orientation) on the imagefolder dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4306
-- Accuracy: 0.7400
+- Loss: 0.3966
+- Accuracy: 0.7797
 
 ## Model description
 
@@ -61,15 +61,17 @@ 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: 5
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.632         | 1.0   | 412  | 0.5021          | 0.7063   |
-| 0.576         | 2.0   | 825  | 0.4507          | 0.7269   |
-| 0.5102        | 3.0   | 1236 | 0.4306          | 0.7400   |
+| 0.4741        | 1.0   | 412  | 0.4774          | 0.7346   |
+| 0.4958        | 2.0   | 825  | 0.4403          | 0.7569   |
+| 0.473         | 3.0   | 1237 | 0.4093          | 0.7659   |
+| 0.4476        | 4.0   | 1650 | 0.4011          | 0.7734   |
+| 0.4093        | 4.99  | 2060 | 0.3966          | 0.7797   |
 
 
 ### Framework versions