update model card README.md

README.md

@@ -2,7 +2,6 @@
 license: apache-2.0
 base_model: google/vit-base-patch16-224
 tags:
-- image-classification
 - generated_from_trainer
 datasets:
 - imagefolder
@@ -15,7 +14,7 @@ model-index:
       name: Image Classification
       type: image-classification
     dataset:
-      name: temp
+      name: imagefolder
       type: imagefolder
       config: default
       split: validation
@@ -31,9 +30,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # vit-base
 
-This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on the temp dataset.
+This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on the imagefolder dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7729
+- Loss: 1.1401
 - Accuracy: 0.75
 
 ## Model description
@@ -54,18 +53,22 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0002
-- train_batch_size: 16
+- train_batch_size: 4
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 50
+- num_epochs: 10
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.0           | 50.0  | 100  | 0.7729          | 0.75     |
+| 0.1567        | 2.0   | 20   | 0.9874          | 0.75     |
+| 0.0007        | 4.0   | 40   | 0.9885          | 0.75     |
+| 0.0004        | 6.0   | 60   | 1.1331          | 0.75     |
+| 0.0003        | 8.0   | 80   | 1.1414          | 0.75     |
+| 0.0003        | 10.0  | 100  | 1.1401          | 0.75     |
 
 
 ### Framework versions