vit-base-oxford-iiit-pets

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

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: 0.1985
• 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

Framework versions

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

---

🧠 Zero-Shot Classification (CLIP)

This evaluation compares the fine-tuned ViT model to a zero-shot approach using openai/clip-vit-base-patch32.
The model was evaluated on 100 samples from the Oxford-IIIT Pet dataset.

🔢 Zero-Shot Metrics

Evaluation notebook: oxford_pets_zero_shot.ipynb