melanoma-isic2019-multiclass – AI Model by oscar2525mv | AlphaNeural AI

You can deploy this model and start earning money today!

oscar2525mv/
melanoma-isic2019-multiclass

like

0

image-classification

generated_from_trainer

google/vit-base-patch16-384

endpoints_compatible

Views

No views yet

melanoma-isic2019-multiclass

This model is a fine-tuned version of google/vit-base-patch16-384 on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.2977
Auc Macro: 0.9701
Accuracy: 0.8883

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: 2e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 32
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 5
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Auc Macro	Accuracy
2.7555	1.0	713	0.4393	0.9382	0.8157
1.7951	2.0	1426	0.3502	0.9577	0.8406
1.1444	3.0	2139	0.3266	0.9635	0.8528
0.9036	4.0	2852	0.3070	0.9685	0.8840
0.647	5.0	3565	0.2977	0.9701	0.8883

Framework versions

Transformers 4.57.3
Pytorch 2.6.0+cu124
Datasets 4.4.2
Tokenizers 0.22.1