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

Loss: 0.6396
Accuracy: 0.8129

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: 5e-05
train_batch_size: 32
eval_batch_size: 32
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 128
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 0.1
num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
3.0573	1.0	27	2.4570	0.3181
1.7846	2.0	54	1.5515	0.5738
1.1565	3.0	81	1.1433	0.6923
0.9072	4.0	108	0.9290	0.7599
0.7047	5.0	135	0.8275	0.7713
0.5929	6.0	162	0.7542	0.7900
0.4999	7.0	189	0.7017	0.8025
0.4561	8.0	216	0.6734	0.8077
0.4057	9.0	243	0.6553	0.8150
0.4048	10.0	270	0.6396	0.8129

Framework versions

Transformers 5.5.4
Pytorch 2.10.0+cu128
Datasets 4.8.4
Tokenizers 0.22.2

aidenshindel/vit.vit-base-patch16-224-finetuned-SkinDisease

vit.vit-base-patch16-224-finetuned-SkinDisease

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

aidenshindel/
vit.vit-base-patch16-224-finetuned-SkinDisease