swin-brain-abnormalities-classification

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: 0.1303
• Accuracy: 0.9661

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: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.7845	0.9639	20	0.5746	0.7661
0.4587	1.9759	41	0.2931	0.8780
0.3004	2.9880	62	0.2784	0.8949
0.2379	4.0	83	0.1557	0.9356
0.1845	4.9639	103	0.1520	0.9492
0.1445	5.9759	124	0.1450	0.9525
0.1557	6.9880	145	0.1189	0.9525
0.1503	8.0	166	0.1201	0.9559
0.1446	8.9639	186	0.1279	0.9627
0.1368	9.9759	207	0.1393	0.9593
0.111	10.9880	228	0.1771	0.9627
0.118	12.0	249	0.1591	0.9627
0.099	12.9639	269	0.1527	0.9593
0.0888	13.9759	290	0.1668	0.9559
0.0768	14.9880	311	0.1303	0.9661
0.0776	16.0	332	0.1430	0.9661
0.0853	16.9639	352	0.1605	0.9593
0.07	17.9759	373	0.1659	0.9593
0.0705	18.9880	394	0.1455	0.9593
0.0712	19.2771	400	0.1451	0.9593

Framework versions

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