swin-tiny-patch4-window7-224-finetuned-skin-cancer

This model is a fine-tuned version of microsoft/swin-tiny-patch4-window7-224 on the imagefolder dataset. It achieves the following results on the evaluation set:

• Loss: 0.3211
• Accuracy: 0.8772

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: 64
• eval_batch_size: 64
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 256
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.8717	0.9929	35	0.8160	0.6916
0.6289	1.9858	70	0.5764	0.8034
0.4878	2.9787	105	0.4994	0.8174
0.4392	4.0	141	0.4301	0.8493
0.3867	4.9929	176	0.4034	0.8573
0.3653	5.9858	211	0.3476	0.8693
0.3359	6.9787	246	0.3681	0.8643
0.2865	8.0	282	0.3578	0.8653
0.3041	8.9929	317	0.3245	0.8792
0.2869	9.9291	350	0.3211	0.8772

Framework versions

• Transformers 4.45.1
• Pytorch 2.4.0
• Datasets 3.0.1
• Tokenizers 0.20.0