update model card README.md

README.md

@@ -1,11 +1,9 @@
 ---
 license: apache-2.0
 tags:
-- image-classification
-- vision
 - generated_from_trainer
 datasets:
-- mnist
+- imagefolder
 metrics:
 - accuracy
 model-index:
@@ -15,15 +13,15 @@ model-index:
       name: Image Classification
       type: image-classification
     dataset:
-      name: mnist
-      type: mnist
-      config: mnist
+      name: imagefolder
+      type: imagefolder
+      config: default
       split: train
-      args: mnist
+      args: default
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.9947777777777778
+      value: 0.8308823529411765
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -31,10 +29,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # vit-base-mnist
 
-This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the mnist dataset.
+This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the imagefolder dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0236
-- Accuracy: 0.9948
+- Loss: 0.6891
+- Accuracy: 0.8309
 
 ## Model description
 
@@ -63,13 +61,13 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step  | Validation Loss | Accuracy |
-|:-------------:|:-----:|:-----:|:---------------:|:--------:|
-| 0.379         | 1.0   | 6375  | 0.0506          | 0.9896   |
-| 0.3384        | 2.0   | 12750 | 0.0362          | 0.9906   |
-| 0.3605        | 3.0   | 19125 | 0.0313          | 0.9923   |
-| 0.3252        | 4.0   | 25500 | 0.0262          | 0.9938   |
-| 0.2885        | 5.0   | 31875 | 0.0236          | 0.9948   |
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 1.9053        | 1.0   | 289  | 1.3241          | 0.7108   |
+| 1.3293        | 2.0   | 578  | 0.9333          | 0.7892   |
+| 1.1251        | 3.0   | 867  | 0.7989          | 0.7843   |
+| 0.9837        | 4.0   | 1156 | 0.6956          | 0.8186   |
+| 0.999         | 5.0   | 1445 | 0.6891          | 0.8309   |
 
 
 ### Framework versions