vit-base-oxford-iiit-pets

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

• Loss: 0.1900
• Accuracy: 0.9378

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
• 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: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.392	1.0	370	0.3019	0.9269
0.2013	2.0	740	0.2306	0.9405
0.1777	3.0	1110	0.2113	0.9378
0.1426	4.0	1480	0.1980	0.9432
0.1458	5.0	1850	0.1972	0.9445

Framework versions

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

Zero-Shot Evaluation

A comparison model was evaluated using openai/clip-vit-base-patch32 on the Oxford-IIIT Pet dataset.

Ergebnisse (Zero-Shot):

• Accuracy: 88.00%
• Precision (macro): 87.68%
• Recall (macro): 88.00%

Although the model was not trained on the dataset, it shows remarkable performance.