README.md

metadata

license: apache-2.0
tags:
  - image-classification
  - vision
  - generated_from_trainer
datasets:
  - mnist
metrics:
  - accuracy
base_model: google/vit-base-patch16-224-in21k
model-index:
  - name: mnist-digit-classification-2022-09-04
    results:
      - task:
          type: image-classification
          name: Image Classification
        dataset:
          name: mnist
          type: mnist
          config: mnist
          split: train
          args: mnist
        metrics:
          - type: accuracy
            value: 0.9923333333333333
            name: Accuracy

mnist-digit-classification-2022-09-04

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

• Loss: 0.0319
• Accuracy: 0.9923

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: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5.0

Training results

Framework versions

• Transformers 4.22.0.dev0
• Pytorch 1.12.1+cu102
• Datasets 2.4.0
• Tokenizers 0.12.1