vit-brain-tumour

This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the Simezu/brain-tumour-MRI-scan dataset. It achieves the following results on the evaluation set:

• Loss: 0.0309
• Accuracy: 0.9925

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: 0.0002
• 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
• num_epochs: 4
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.227	0.4255	100	0.3067	0.8910
0.0659	0.8511	200	0.1109	0.9627
0.0404	1.2766	300	0.0900	0.9776
0.05	1.7021	400	0.1082	0.9748
0.006	2.1277	500	0.0374	0.9888
0.0147	2.5532	600	0.0541	0.9888
0.0105	2.9787	700	0.0359	0.9907
0.0032	3.4043	800	0.0392	0.9907
0.0055	3.8298	900	0.0309	0.9925

Framework versions

• Transformers 4.42.4
• Pytorch 2.3.1+cu121
• Datasets 2.21.0
• Tokenizers 0.19.1