swin-brain-abnormalities-classification-fold1

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: 0.1102
• Accuracy: 0.9607

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
0.9214	0.9714	17	0.7237	0.7249
0.5441	2.0	35	0.3606	0.8523
0.3592	2.9714	52	0.2474	0.9024
0.2732	4.0	70	0.2265	0.9173
0.2283	4.9714	87	0.1731	0.9404
0.1865	6.0	105	0.1808	0.9309
0.185	6.9714	122	0.1703	0.9201
0.1597	8.0	140	0.1262	0.9485
0.1545	8.9714	157	0.1375	0.9472
0.1237	10.0	175	0.1133	0.9580
0.1165	10.9714	192	0.1299	0.9512
0.1086	12.0	210	0.1118	0.9634
0.1129	12.9714	227	0.1101	0.9580
0.0898	14.0	245	0.1089	0.9607
0.0811	14.5714	255	0.1102	0.9607

Framework versions

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