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: 0.5625

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: 1.3383
Accuracy: 0.5625

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	1.6519	0.3312
No log	2.0	160	1.4509	0.4125
No log	3.0	240	1.3641	0.5062
No log	4.0	320	1.2676	0.5875
No log	5.0	400	1.2718	0.5188
No log	6.0	480	1.2250	0.5125
1.2828	7.0	560	1.1933	0.55
1.2828	8.0	640	1.1538	0.575
1.2828	9.0	720	1.2479	0.55
1.2828	10.0	800	1.2487	0.575
1.2828	11.0	880	1.2418	0.5938
1.2828	12.0	960	1.1514	0.6062
0.5147	13.0	1040	1.2563	0.5563
0.5147	14.0	1120	1.2933	0.5813
0.5147	15.0	1200	1.2857	0.5813
0.5147	16.0	1280	1.3044	0.575
0.5147	17.0	1360	1.4134	0.5687
0.5147	18.0	1440	1.3277	0.5875
0.2675	19.0	1520	1.2963	0.575
0.2675	20.0	1600	1.2049	0.6125

Framework versions

Transformers 4.33.2
Pytorch 2.0.1+cu118
Datasets 2.14.5
Tokenizers 0.13.3