metadata

license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: image_classification
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: imagefolder
          type: imagefolder
          config: default
          split: train
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.5375

image_classification

This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the imagefolder dataset. It achieves the following results on the evaluation set:

Loss: 1.2530
Accuracy: 0.5375

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 5e-05
train_batch_size: 16
eval_batch_size: 16
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	40	1.9208	0.25
No log	2.0	80	1.5773	0.425
No log	3.0	120	1.4861	0.4188
No log	4.0	160	1.4287	0.4813
No log	5.0	200	1.3897	0.5
No log	6.0	240	1.3243	0.525
No log	7.0	280	1.3144	0.5125
No log	8.0	320	1.3149	0.4688
No log	9.0	360	1.3041	0.475
No log	10.0	400	1.2425	0.55
No log	11.0	440	1.3743	0.4813
No log	12.0	480	1.3849	0.4688
1.0637	13.0	520	1.2804	0.5437
1.0637	14.0	560	1.3975	0.4875
1.0637	15.0	600	1.3569	0.525
1.0637	16.0	640	1.3928	0.5
1.0637	17.0	680	1.3665	0.5
1.0637	18.0	720	1.3320	0.5188
1.0637	19.0	760	1.3358	0.5
1.0637	20.0	800	1.3064	0.5312

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu121
Datasets 2.17.0
Tokenizers 0.15.2