swin-brain-abnormalities-classification-fold3

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

• Loss: 0.1552
• Accuracy: 0.9566

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.9031	0.9714	17	0.6752	0.7286
0.5553	2.0	35	0.3278	0.8806
0.3599	2.9714	52	0.2776	0.8942
0.3013	4.0	70	0.1906	0.9281
0.2276	4.9714	87	0.1999	0.9335
0.1906	6.0	105	0.1566	0.9430
0.1736	6.9714	122	0.1731	0.9403
0.1593	8.0	140	0.1662	0.9444
0.1318	8.9714	157	0.1761	0.9417
0.1117	10.0	175	0.1714	0.9403
0.1335	10.9714	192	0.1594	0.9525
0.0996	12.0	210	0.1820	0.9417
0.0954	12.9714	227	0.1528	0.9539
0.0913	14.0	245	0.1547	0.9566
0.0878	14.5714	255	0.1552	0.9566

Framework versions

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