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: 0.59375

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: 1.3020
Accuracy: 0.5938

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	1.3711	0.4313
No log	2.0	160	1.2946	0.5188
No log	3.0	240	1.1760	0.5563
No log	4.0	320	1.3317	0.5
No log	5.0	400	1.3201	0.4938
No log	6.0	480	1.2809	0.5375
0.8929	7.0	560	1.3645	0.5
0.8929	8.0	640	1.2415	0.5563
0.8929	9.0	720	1.4341	0.5125
0.8929	10.0	800	1.3027	0.5625
0.8929	11.0	880	1.3131	0.5813
0.8929	12.0	960	1.4144	0.525
0.3836	13.0	1040	1.3987	0.5563
0.3836	14.0	1120	1.3167	0.5938
0.3836	15.0	1200	1.3588	0.6
0.3836	16.0	1280	1.2747	0.625
0.3836	17.0	1360	1.4555	0.575
0.3836	18.0	1440	1.3795	0.5875
0.2078	19.0	1520	1.5430	0.525
0.2078	20.0	1600	1.4164	0.5813

Framework versions

Transformers 4.33.2
Pytorch 2.0.1+cu118
Datasets 2.14.5
Tokenizers 0.13.3