This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the ahishamm/isic_binary__enhanced_balanced dataset. It achieves the following results on the evaluation set:

Loss: 0.1585
Accuracy: 0.9458
Recall: 0.9458
F1: 0.9458
Precision: 0.9458

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: 0.0002
train_batch_size: 16
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 4
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Recall	F1	Precision
0.4477	0.27	50	0.5296	0.7444	0.7444	0.7444	0.7444
0.3011	0.54	100	0.3341	0.8722	0.8722	0.8722	0.8722
0.3254	0.82	150	0.3987	0.7903	0.7903	0.7903	0.7903
0.2986	1.09	200	0.3169	0.8694	0.8694	0.8694	0.8694
0.3341	1.36	250	0.3114	0.8597	0.8597	0.8597	0.8597
0.2659	1.63	300	0.2607	0.8833	0.8833	0.8833	0.8833
0.1987	1.9	350	0.2100	0.9111	0.9111	0.9111	0.9111
0.3515	2.17	400	0.2369	0.9097	0.9097	0.9097	0.9097
0.1316	2.45	450	0.2714	0.9014	0.9014	0.9014	0.9014
0.2213	2.72	500	0.1714	0.9361	0.9361	0.9361	0.9361
0.1115	2.99	550	0.1585	0.9458	0.9458	0.9458	0.9458
0.0377	3.26	600	0.2058	0.9403	0.9403	0.9403	0.9403
0.0779	3.53	650	0.2187	0.9375	0.9375	0.9375	0.9375
0.0444	3.8	700	0.2140	0.9389	0.9389	0.9389	0.9389

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu118
Datasets 2.15.0
Tokenizers 0.15.0

ahishamm/vit-base-16-thesis-demo-ISIC-binary-class

vit-base-16-thesis-demo-ISIC-binary-class

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

ahishamm/
vit-base-16-thesis-demo-ISIC-binary-class