Mazen Amria
update model card README.md
a633ab2
|
raw
history blame
1.06 kB
metadata
tags:
  - generated_from_trainer
datasets:
  - cifar100
model-index:
  - name: swin-tiny-finetuned-cifar100
    results: []

swin-tiny-finetuned-cifar100

This model was trained from scratch on the cifar100 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: 4e-05
  • train_batch_size: 16
  • eval_batch_size: 16
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 64
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 20

Framework versions

  • Transformers 4.20.1
  • Pytorch 1.11.0
  • Datasets 2.1.0
  • Tokenizers 0.12.1