vit-base-brain-tumor-detection3

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: 0.3419
• Accuracy: 0.9406

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: 1e-05
• train_batch_size: 16
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 1000
• num_epochs: 60
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.0048	7.8125	500	0.2337	0.9473
0.0012	15.625	1000	0.1950	0.9531
0.0007	23.4375	1500	0.1927	0.9580
0.0004	31.25	2000	0.1970	0.9629
0.0003	39.0625	2500	0.2040	0.9629
0.0002	46.875	3000	0.2114	0.9629
0.0002	54.6875	3500	0.2171	0.9648

Framework versions

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