Hugging Face's logo

yfh
/
food

Image Classification
Transformers
PyTorch
vit
Generated from Trainer
Inference Endpoints
Model card Files Community
food / README.md
yfh's picture
yfh
End of training
3463ca9
preview code
|
raw
history blame contribute delete
1.28 kB
metadata
license: apache-2.0
base_model: google/vit-base-patch16-224
tags:
  - generated_from_trainer
datasets:
  - food101
model-index:
  - name: food
    results: []

food

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

  • eval_loss: 0.6313
  • eval_accuracy: 0.856
  • eval_runtime: 739.9774
  • eval_samples_per_second: 1.351
  • eval_steps_per_second: 0.085
  • epoch: 0.15
  • step: 38

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
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 3

Framework versions

  • Transformers 4.34.0
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.5
  • Tokenizers 0.14.0