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: 0.58125

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: 1.5857
Accuracy: 0.5813

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: 8
eval_batch_size: 8
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	80	1.4085	0.5062
No log	2.0	160	1.5462	0.5062
No log	3.0	240	1.5687	0.525
No log	4.0	320	1.5465	0.5625
No log	5.0	400	1.7599	0.5
No log	6.0	480	1.8047	0.5312
0.244	7.0	560	1.8441	0.525
0.244	8.0	640	1.7620	0.5375
0.244	9.0	720	1.5618	0.5563
0.244	10.0	800	1.8267	0.5125
0.244	11.0	880	1.5343	0.6
0.244	12.0	960	1.8340	0.5375
0.237	13.0	1040	1.7273	0.575
0.237	14.0	1120	1.7158	0.5563
0.237	15.0	1200	1.6075	0.55
0.237	16.0	1280	1.6131	0.5687
0.237	17.0	1360	1.8439	0.55
0.237	18.0	1440	1.9079	0.5188
0.1695	19.0	1520	1.7325	0.5687
0.1695	20.0	1600	1.5776	0.5938

Framework versions

Transformers 4.33.2
Pytorch 2.0.1+cu118
Datasets 2.14.5
Tokenizers 0.13.3