metadata

license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
  - generated_from_trainer
datasets:
  - food101
metrics:
  - accuracy
model-index:
  - name: vit-base-patch16-224-in21k-food101-16-7
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: food101
          type: food101
          config: default
          split: validation
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.9080396039603961

vit-base-patch16-224-in21k-food101-16-7

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: 0.3600
Accuracy: 0.9080

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: 7

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.9168	1.0	1183	1.6711	0.8177
0.9489	2.0	2367	0.6971	0.8659
0.6068	3.0	3551	0.4862	0.8894
0.5981	4.0	4735	0.4238	0.8948
0.6099	5.0	5918	0.3905	0.8994
0.4873	6.0	7102	0.3715	0.9028
0.459	7.0	8281	0.3600	0.9080

Framework versions

Transformers 4.34.1
Pytorch 2.1.0+cu118
Datasets 2.14.6
Tokenizers 0.14.1