Edit model card

fashion-images-perspectives-vit-huge-patch14-224-in21k

This model is a fine-tuned version of google/vit-huge-patch14-224-in21k on the touchtech/fashion-images-perspectives dataset. It achieves the following results on the evaluation set:

  • Loss: 0.2604
  • Accuracy: 0.9150

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: 2e-05
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 1337
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 5.0

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.5932 1.0 3042 0.3863 0.8889
0.4286 2.0 6084 0.4201 0.8642
0.3628 3.0 9126 0.2820 0.9101
0.3183 4.0 12168 0.2604 0.9150
0.2648 5.0 15210 0.2710 0.9150

Framework versions

  • Transformers 4.33.0.dev0
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.4
  • Tokenizers 0.13.3
Downloads last month
15

Finetuned from

Evaluation results

  • Accuracy on touchtech/fashion-images-perspectives
    self-reported
    0.915