Brain-Tumor-Classification

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: 0.0872
• Accuracy: 0.9758

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: 16

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.2074	1.0	44	0.8060	0.8128
0.4897	2.0	88	0.3008	0.9274
0.2462	3.0	132	0.2464	0.9331
0.1937	4.0	176	0.1918	0.9502
0.1523	5.0	220	0.1699	0.9502
0.1371	6.0	264	0.1372	0.9644
0.1104	7.0	308	0.1121	0.9708
0.1097	8.0	352	0.1220	0.9651
0.1015	9.0	396	0.1053	0.9737
0.0841	10.0	440	0.1142	0.9708
0.0839	11.0	484	0.1073	0.9708
0.0771	12.0	528	0.1156	0.9665
0.074	13.0	572	0.1203	0.9644
0.0652	14.0	616	0.0706	0.9858
0.0694	15.0	660	0.0984	0.9744
0.0596	16.0	704	0.0872	0.9758

Framework versions

• Transformers 4.38.1
• Pytorch 2.1.2
• Datasets 2.18.0
• Tokenizers 0.15.2