vit-brain-tumor

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

• Loss: 0.4552
• Accuracy: 0.8571

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: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.6298	1.0	1478	0.6281	0.7495
0.5911	2.0	2956	0.5900	0.7920
0.5705	3.0	4434	0.5593	0.8103
0.5091	4.0	5912	0.5358	0.8237
0.5124	5.0	7390	0.5169	0.8343
0.4631	6.0	8868	0.5029	0.8467
0.4834	7.0	10346	0.4907	0.8515
0.4724	8.0	11824	0.4804	0.8541
0.4702	9.0	13302	0.4715	0.8549
0.4162	10.0	14780	0.4653	0.8570
0.4664	11.0	16258	0.4603	0.8602
0.469	12.0	17736	0.4565	0.8610
0.4299	13.0	19214	0.4539	0.8621
0.4191	14.0	20692	0.4522	0.8621
0.4652	15.0	22170	0.4517	0.8623

Framework versions

• Transformers 4.50.0
• Pytorch 2.6.0+cu124
• Datasets 3.4.1
• Tokenizers 0.21.1