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: 0.2038
- Accuracy: 0.9445
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 |
|---|---|---|---|---|
| 0.373 | 1.0 | 370 | 0.2732 | 0.9337 |
| 0.2127 | 2.0 | 740 | 0.2148 | 0.9405 |
| 0.1801 | 3.0 | 1110 | 0.1918 | 0.9445 |
| 0.1448 | 4.0 | 1480 | 0.1857 | 0.9472 |
| 0.1308 | 5.0 | 1850 | 0.1814 | 0.9445 |
Framework versions
- Transformers 4.50.0
- Pytorch 2.6.0+cu124
- Datasets 3.4.1
- Tokenizers 0.21.1
Zero-Shot Evaluation
- Model used:
openai/clip-vit-large-patch14 - Dataset: Oxford-IIIT-Pets (
pcuenq/oxford-pets) - Accuracy: 0.8800
- Precision: 0.8768
- Recall: 0.8800
The zero-shot evaluation was done using Hugging Face Transformers and the CLIP model on the Oxford-Pet dataset.