Edit model card

fashion_classification_model

This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the fashion_mnist dataset. It achieves the following results on the evaluation set:

  • Loss: 1.0461
  • Accuracy: 0.792

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: 5e-05
  • train_batch_size: 16
  • eval_batch_size: 16
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 64
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 3

Training results

Training Loss Epoch Step Validation Loss Accuracy
1.285 0.99 62 1.2299 0.718
1.2002 2.0 125 1.2043 0.744
1.0345 2.98 186 1.0461 0.792

Framework versions

  • Transformers 4.31.0.dev0
  • Pytorch 2.0.1+cu118
  • Datasets 2.13.1
  • Tokenizers 0.13.3
Downloads last month
6

Dataset used to train sehee-lim/fashion_classification_model

Space using sehee-lim/fashion_classification_model 1

Evaluation results