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: 0.2066
Accuracy: 0.9405

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
0.3465	1.0	370	0.2699	0.9405
0.2149	2.0	740	0.2013	0.9499
0.1667	3.0	1110	0.1827	0.9621
0.1452	4.0	1480	0.1661	0.9621
0.1392	5.0	1850	0.1623	0.9648

Framework versions

Transformers 4.50.0
Pytorch 2.6.0+cu124
Datasets 3.4.1
Tokenizers 0.21.1

Zero-Shot Classification Evaluation

Model used: openai/clip-vit-large-patch14
Dataset: Oxford-IIIT Pet (subset)
Evaluation method: Hugging Face pipeline("zero-shot-image-classification")

Accuracy: 88.00%
Precision: 87.68%
Recall: 88.00%

pereilea/vit-base-oxford-iiit-pets

vit-base-oxford-iiit-pets

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Zero-Shot Classification Evaluation

pereilea/
vit-base-oxford-iiit-pets