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: 1.2542
• Accuracy: 0.5375

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: 0.0001
• 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: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	40	1.7657	0.3187
No log	2.0	80	1.6332	0.3063
No log	3.0	120	1.4587	0.4625
No log	4.0	160	1.4618	0.3812
No log	5.0	200	1.2944	0.5312
No log	6.0	240	1.3633	0.4562
No log	7.0	280	1.4372	0.3937
No log	8.0	320	1.2895	0.5563
No log	9.0	360	1.2892	0.525
No log	10.0	400	1.2596	0.5375
No log	11.0	440	1.3227	0.5188
No log	12.0	480	1.3231	0.5125
1.0624	13.0	520	1.2873	0.5312
1.0624	14.0	560	1.3093	0.5125
1.0624	15.0	600	1.2294	0.5563

Framework versions

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