README.md

metadata

tags:
  - generated_from_trainer
datasets:
  - cifar100
metrics:
  - accuracy
model-index:
  - name: swin-tiny-patch4-window7-224-cifar_100f_from_10
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: cifar100
          type: cifar100
          config: cifar100
          split: train
          args: cifar100
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.5582

swin-tiny-patch4-window7-224-cifar_100f_from_10

This model was trained from scratch on the cifar100 dataset. It achieves the following results on the evaluation set:

• Loss: 2.1818
• Accuracy: 0.5582

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: 32
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 128
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
3.4964	1.0	351	3.1548	0.3374
2.8648	2.0	703	2.3713	0.524
2.758	2.99	1053	2.1818	0.5582

Framework versions

• Transformers 4.30.1
• Pytorch 2.0.1+cu118
• Datasets 2.12.0
• Tokenizers 0.13.3