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: 0.56875

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: 1.2152
Accuracy: 0.5687

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	1.3484	0.5437
No log	2.0	80	1.3268	0.4875
No log	3.0	120	1.2463	0.5437
No log	4.0	160	1.2361	0.5563
No log	5.0	200	1.2089	0.5813
No log	6.0	240	1.2544	0.525
No log	7.0	280	1.1947	0.5563
No log	8.0	320	1.2502	0.5188
No log	9.0	360	1.3415	0.4938
No log	10.0	400	1.1336	0.6
No log	11.0	440	1.2716	0.5437
No log	12.0	480	1.4631	0.5
0.6882	13.0	520	1.3970	0.5563
0.6882	14.0	560	1.2654	0.5188
0.6882	15.0	600	1.2498	0.575
0.6882	16.0	640	1.2655	0.5938
0.6882	17.0	680	1.3577	0.55
0.6882	18.0	720	1.2711	0.5813
0.6882	19.0	760	1.3127	0.5687
0.6882	20.0	800	1.2478	0.575

Framework versions

Transformers 4.33.2
Pytorch 2.0.1+cu118
Datasets 2.14.5
Tokenizers 0.13.3