README.md

metadata

license: apache-2.0
tags:
  - image-classification
  - generated_from_trainer
datasets:
  - cifar10
model-index:
  - name: vit-base-patch16-224-cifar10
    results:
      - task:
          type: image-classification
          name: Image Classification
        dataset:
          name: cifar10
          type: cifar10
          config: plain_text
          split: test
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.1004
            verified: true
          - name: Precision Macro
            type: precision
            value: 0.07725693204097324
            verified: true
          - name: Precision Micro
            type: precision
            value: 0.1004
            verified: true
          - name: Precision Weighted
            type: precision
            value: 0.07725693204097323
            verified: true
          - name: Recall Macro
            type: recall
            value: 0.1004
            verified: true
          - name: Recall Micro
            type: recall
            value: 0.1004
            verified: true
          - name: Recall Weighted
            type: recall
            value: 0.1004
            verified: true
          - name: F1 Macro
            type: f1
            value: 0.07942008420616108
            verified: true
          - name: F1 Micro
            type: f1
            value: 0.1004
            verified: true
          - name: F1 Weighted
            type: f1
            value: 0.07942008420616108
            verified: true
          - name: loss
            type: loss
            value: 2.3154706954956055
            verified: true

vit-base-patch16-224-cifar10

This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the cifar10 dataset.

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: 3.0

Framework versions

• Transformers 4.19.0.dev0
• Pytorch 1.10.1
• Datasets 2.1.0
• Tokenizers 0.12.1