gaglileoo/vit-flower-classifier

vit-flowers-recognition

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

Loss: 0.1351
Accuracy: 0.9655

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: 0.0003
• train_batch_size: 16
• eval_batch_size: 8
• optimizer: adamw_torch
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Training Loss	Epoch	Validation Loss	Accuracy
0.1133	1.0	0.1167	0.9651
0.0885	2.0	0.1160	0.9628
0.0488	3.0	0.1163	0.9628
0.0467	4.0	0.1166	0.9605
0.0475	5.0	0.1164	0.9605

Framework versions

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