walterg777's picture
πŸ•οΈπŸˆοΈ
d22de13 verified
metadata
license: apache-2.0
base_model: google/vit-base-patch16-224
tags:
  - image-classification
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: vit-base-oxford-iiit-pets
    results: []

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: 0.1883
  • Accuracy: 0.9540

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 5

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.3824 1.0 370 0.2976 0.9310
0.1977 2.0 740 0.2266 0.9378
0.1885 3.0 1110 0.2039 0.9378
0.1288 4.0 1480 0.1941 0.9405
0.1368 5.0 1850 0.1894 0.9418

Framework versions

  • Transformers 4.40.1
  • Pytorch 2.2.1+cu121
  • Datasets 2.19.0
  • Tokenizers 0.19.1