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: 1.4041
• Accuracy: 0.6062

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: 64
• eval_batch_size: 64
• 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	10	1.8541	0.325
No log	2.0	20	1.6601	0.4062
No log	3.0	30	1.5194	0.525
No log	4.0	40	1.4041	0.6062
No log	5.0	50	1.3033	0.5813
No log	6.0	60	1.2836	0.5687
No log	7.0	70	1.2508	0.575
No log	8.0	80	1.2026	0.5938
No log	9.0	90	1.2077	0.5875
No log	10.0	100	1.1930	0.575
No log	11.0	110	1.2111	0.5687
No log	12.0	120	1.1794	0.5875
No log	13.0	130	1.2007	0.5938
No log	14.0	140	1.1854	0.5875
No log	15.0	150	1.1905	0.5875

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu121
• Datasets 2.16.1
• Tokenizers 0.15.1