README.md

metadata

license: apache-2.0
base_model: google/vit-base-patch16-224
tags:
  - image-classification
  - generated_from_trainer
datasets:
  - cifar10-lt
metrics:
  - accuracy
  - f1
model-index:
  - name: cifar10-lt
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: cifar10-lt
          type: cifar10-lt
          config: r-10
          split: test
          args: r-10
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.9659
          - name: F1
            type: f1
            value: 0.9660399066727052

cifar10-lt

This model is a fine-tuned version of google/vit-base-patch16-224 on the cifar10-lt dataset. It achieves the following results on the evaluation set:

• Loss: 0.1132
• Accuracy: 0.9659
• F1: 0.9660

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: 32
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3

Training results

Framework versions

• Transformers 4.33.3
• Pytorch 2.0.1+cu118
• Datasets 2.14.5
• Tokenizers 0.13.3