vit-base-brain-dementia-detection

This model is a fine-tuned version of google/vit-base-patch16-224-in21k on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.2613
• Accuracy: 0.9461

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: 2e-05
• train_batch_size: 16
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.728	1.9531	500	0.7510	0.6660
0.2752	3.9062	1000	0.4706	0.8311
0.1104	5.8594	1500	0.2167	0.9336
0.0297	7.8125	2000	0.2228	0.9424
0.009	9.7656	2500	0.1474	0.9668
0.006	11.7188	3000	0.1493	0.9648
0.0049	13.6719	3500	0.1507	0.9668
0.0038	15.625	4000	0.1553	0.9668
0.0033	17.5781	4500	0.1585	0.9658
0.0029	19.5312	5000	0.1605	0.9658

Framework versions

• Transformers 4.42.4
• Pytorch 2.3.1+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1