skin_decease

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: 0.0680
• Accuracy: 0.9872

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: 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: 8
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.2359	0.8621	100	0.2427	0.9744
0.086	1.7241	200	0.1178	0.9872
0.0435	2.5862	300	0.0801	0.9872
0.0312	3.4483	400	0.0748	0.9872
0.023	4.3103	500	0.0715	0.9872
0.0197	5.1724	600	0.0696	0.9872
0.0174	6.0345	700	0.0687	0.9872
0.0161	6.8966	800	0.0684	0.9872
0.0151	7.7586	900	0.0680	0.9872

Framework versions

• Transformers 4.43.2
• Pytorch 2.2.1+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1