update model card README.md

README.md

@@ -15,13 +15,11 @@ model-index:
     dataset:
       name: imagefolder
       type: imagefolder
-      config: default
-      split: train
       args: default
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.8955223880597015
+      value: 0.4864864864864865
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -31,8 +29,8 @@ 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: 0.6056
-- Accuracy: 0.8955
+- Loss: 1.3826
+- Accuracy: 0.4865
 
 ## Model description
 
@@ -66,14 +64,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 0.84  | 4    | 1.1199          | 0.6269   |
-| No log        | 1.84  | 8    | 0.7175          | 0.8657   |
-| 1.2191        | 2.84  | 12   | 0.6056          | 0.8955   |
+| No log        | 0.9   | 7    | 1.4323          | 0.4865   |
+| 1.5843        | 1.9   | 14   | 1.3999          | 0.4865   |
+| 1.5007        | 2.9   | 21   | 1.3826          | 0.4865   |
 
 
 ### Framework versions
 
-- Transformers 4.24.0
-- Pytorch 1.12.1+cu113
-- Datasets 2.7.1
-- Tokenizers 0.13.2
+- Transformers 4.20.1
+- Pytorch 1.11.0+cu102
+- Datasets 2.4.0
+- Tokenizers 0.12.1