vit-base-beans / README.md
leejw51's picture
update model card README.md
abbbe24
metadata
license: apache-2.0
tags:
  - image-classification
  - vision
  - generated_from_trainer
datasets:
  - beans
metrics:
  - accuracy
model-index:
  - name: vit-base-beans
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: beans
          type: beans
          config: default
          split: validation
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.9849624060150376

vit-base-beans

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

  • Loss: 0.0875
  • Accuracy: 0.9850

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: 2e-05
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 1337
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 5.0

Training results

Training Loss Epoch Step Accuracy Validation Loss
0.2574 1.0 130 0.9624 0.2307
0.2785 2.0 260 0.9925 0.1109
0.1496 3.0 390 0.9699 0.1109
0.0916 4.0 520 0.9850 0.0875
0.1489 5.0 650 0.9774 0.0886

Framework versions

  • Transformers 4.28.0.dev0
  • Pytorch 2.0.0+cu117
  • Datasets 2.10.1
  • Tokenizers 0.13.2