Edit model card

my_awesome_food_model

This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the food101 dataset. It achieves the following results on the evaluation set:

  • Loss: 1.5535
  • Accuracy: 0.919

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
2.6646 0.99 62 2.4866 0.845
1.8188 1.99 124 1.7292 0.898
1.5637 2.99 186 1.5535 0.919

Framework versions

  • Transformers 4.26.0
  • Pytorch 1.13.1
  • Datasets 2.8.0
  • Tokenizers 0.13.2
Downloads last month
2

Dataset used to train StephenSKelley/my_awesome_food_model

Evaluation results