Model save

README.md

@@ -18,12 +18,12 @@ model-index:
       name: imagefolder
       type: imagefolder
       config: default
-      split: train
+      split: validation
       args: default
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.9507407407407408
+      value: 0.17777777777777778
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -33,8 +33,8 @@ 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 the imagefolder dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1480
-- Accuracy: 0.9507
+- Loss: 2.9909
+- Accuracy: 0.1778
 
 ## Model description
 
@@ -66,11 +66,11 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch  | Step | Validation Loss | Accuracy |
-|:-------------:|:------:|:----:|:---------------:|:--------:|
-| 0.4418        | 0.9895 | 47   | 0.2409          | 0.9196   |
-| 0.2514        | 2.0    | 95   | 0.1633          | 0.9463   |
-| 0.1907        | 2.9684 | 141  | 0.1480          | 0.9507   |
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| No log        | 0.8   | 2    | 3.1216          | 0.0722   |
+| No log        | 2.0   | 5    | 3.0048          | 0.1694   |
+| No log        | 2.4   | 6    | 2.9909          | 0.1778   |
 
 
 ### Framework versions