metadata

license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
  - generated_from_trainer
datasets:
  - food101
model-index:
  - name: food-image-classification
    results: []

food-image-classification

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:

eval_loss: 0.7651
eval_accuracy: 0.8156
eval_runtime: 154.1129
eval_samples_per_second: 98.305
eval_steps_per_second: 6.145
epoch: 26.4
step: 25000

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: 500

Framework versions

Transformers 4.37.0
Pytorch 2.1.2
Datasets 2.1.0
Tokenizers 0.15.1