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

Loss: 1.1693
Accuracy: 0.6689
Precision: 0.5100
Recall: 0.6689
F1: 0.5368

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: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 100
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
1.1467	1.0	321	1.1693	0.6689	0.5100	0.6689	0.5368
1.1338	2.0	642	1.1693	0.6689	0.5100	0.6689	0.5368
1.1328	3.0	963	1.1693	0.6689	0.5100	0.6689	0.5368
1.1331	4.0	1284	1.1693	0.6689	0.5100	0.6689	0.5368
1.1325	5.0	1605	1.1693	0.6689	0.5100	0.6689	0.5368
1.1333	6.0	1926	1.1693	0.6689	0.5100	0.6689	0.5368
1.1332	7.0	2247	1.1693	0.6689	0.5100	0.6689	0.5368
1.1327	8.0	2568	1.1693	0.6689	0.5100	0.6689	0.5368
1.1341	9.0	2889	1.1693	0.6689	0.5100	0.6689	0.5368
1.1328	10.0	3210	1.1693	0.6689	0.5100	0.6689	0.5368
1.1328	11.0	3531	1.1693	0.6689	0.5100	0.6689	0.5368

Framework versions

Transformers 4.39.0.dev0
Pytorch 2.2.1+cu121
Datasets 2.18.0
Tokenizers 0.15.2

sharren/vit-lr-exponential

vit-lr-exponential

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

sharren/
vit-lr-exponential