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: 0.2023
Accuracy: 0.9459
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
0.3878
1.0
370
0.2921
0.9215
0.2188
2.0
740
0.2260
0.9269
0.1832
3.0
1110
0.2136
0.9283
0.14
4.0
1480
0.2050
0.9323
0.1322
5.0
1850
0.2030
0.9323
Framework versions
Transformers 4.50.0
Pytorch 2.6.0+cu124
Datasets 3.4.1
Tokenizers 0.21.1
Oxford-Pet dataset using a zero-shot classification model
used model:
checkpoint = "openai/clip-vit-large-patch14"
detector = pipeline(model=checkpoint, task="zero-shot-image-classification")
