imageclassification

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: 1.1467
• 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: 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	1.8113	0.35
No log	2.0	80	1.5533	0.3937
No log	3.0	120	1.4193	0.4688
No log	4.0	160	1.3237	0.5687
No log	5.0	200	1.2989	0.4938
No log	6.0	240	1.2901	0.5
No log	7.0	280	1.2380	0.5625
No log	8.0	320	1.1773	0.6125
No log	9.0	360	1.2149	0.5625
No log	10.0	400	1.2280	0.5312
No log	11.0	440	1.2326	0.5625
No log	12.0	480	1.1488	0.5875
1.0601	13.0	520	1.1597	0.6062
1.0601	14.0	560	1.1953	0.5563
1.0601	15.0	600	1.2011	0.55
1.0601	16.0	640	1.2294	0.55
1.0601	17.0	680	1.1972	0.5687
1.0601	18.0	720	1.3043	0.525
1.0601	19.0	760	1.2796	0.525
1.0601	20.0	800	1.1781	0.5813

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu121
• Datasets 2.17.0
• Tokenizers 0.15.2