Edit model card

my_awesome_fashion_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: 0.8596
  • Accuracy: 0.785

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
1.3171 0.99 62 1.1960 0.755
0.947 2.0 125 0.8729 0.801
0.8346 2.98 186 0.8596 0.785

Framework versions

  • Transformers 4.30.2
  • Pytorch 2.0.1+cu118
  • Datasets 2.13.0
  • Tokenizers 0.13.3
Downloads last month
6

Dataset used to train kkkkkgsp/my_awesome_fashion_model

Evaluation results