README.md

metadata

license: apache-2.0
tags:
  - image-classification
  - vision
  - generated_from_trainer
datasets:
  - cifar10
metrics:
  - accuracy
model-index:
  - name: cifar10_outputs
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: cifar10
          type: cifar10
          args: plain_text
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.991421568627451
      - task:
          type: image-classification
          name: Image Classification
        dataset:
          name: cifar10
          type: cifar10
          config: plain_text
          split: test
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.9674
            verified: true
          - name: Precision Macro
            type: precision
            value: 0.9679512973887299
            verified: true
          - name: Precision Micro
            type: precision
            value: 0.9674
            verified: true
          - name: Precision Weighted
            type: precision
            value: 0.9679512973887299
            verified: true
          - name: Recall Macro
            type: recall
            value: 0.9673999999999999
            verified: true
          - name: Recall Micro
            type: recall
            value: 0.9674
            verified: true
          - name: Recall Weighted
            type: recall
            value: 0.9674
            verified: true
          - name: F1 Macro
            type: f1
            value: 0.9674620969256708
            verified: true
          - name: F1 Micro
            type: f1
            value: 0.9674000000000001
            verified: true
          - name: F1 Weighted
            type: f1
            value: 0.967462096925671
            verified: true
          - name: loss
            type: loss
            value: 0.1527363657951355
            verified: true

cifar10_outputs

This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the cifar10 dataset. It achieves the following results on the evaluation set:

• Loss: 0.0806
• Accuracy: 0.9914

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: 0.0001
• train_batch_size: 17
• eval_batch_size: 17
• seed: 1337
• distributed_type: IPU
• gradient_accumulation_steps: 128
• total_train_batch_size: 8704
• total_eval_batch_size: 272
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.25
• num_epochs: 100.0
• training precision: Mixed Precision

Training results

Framework versions

• Transformers 4.18.0
• Pytorch 1.10.0+cpu
• Datasets 2.3.3.dev0
• Tokenizers 0.12.1