vit-xray-pneumonia-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: 0.0867
• Accuracy: 0.9700

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: 16
• eval_batch_size: 16
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 64
• 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
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 15
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
2.0067	0.9882	63	0.2101	0.9313
0.8054	1.9882	126	0.1542	0.9519
0.7482	2.9882	189	0.1328	0.9451
0.6	3.9882	252	0.1121	0.9588
0.5436	4.9882	315	0.1295	0.9494
0.4978	5.9882	378	0.1167	0.9605
0.4683	6.9882	441	0.1033	0.9622
0.4701	7.9882	504	0.1176	0.9579
0.3527	8.9882	567	0.1119	0.9571
0.3545	9.9882	630	0.0990	0.9639
0.3264	10.9882	693	0.0838	0.9717
0.3305	11.9882	756	0.0733	0.9734
0.2702	12.9882	819	0.0834	0.9717
0.2764	13.9882	882	0.0763	0.9734
0.286	14.9882	945	0.0867	0.9700

Framework versions

• Transformers 4.47.1
• Pytorch 2.5.1+cu121
• Datasets 3.2.0
• Tokenizers 0.21.0