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: 0.2461
• Accuracy: 0.9273

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
0.928	0.9892	23	0.6080	0.7705
0.508	1.9785	46	0.2402	0.9162
0.3178	2.9677	69	0.2121	0.9246
0.2338	4.0	93	0.2045	0.9363
0.1788	4.9892	116	0.2443	0.9296
0.1675	5.9785	139	0.1457	0.9430
0.155	6.9677	162	0.1708	0.9514
0.1316	8.0	186	0.1555	0.9531
0.1099	8.9892	209	0.1732	0.9531
0.1121	9.9785	232	0.1358	0.9581
0.1007	10.9677	255	0.2155	0.9514
0.0951	12.0	279	0.1506	0.9648
0.0841	12.9892	302	0.1921	0.9531
0.0778	13.9785	325	0.2041	0.9531
0.0768	14.8387	345	0.1909	0.9548

Framework versions

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