training_config.json

{
  "run_name": "5expert_3scale",
  "run_number": null,
  "dataset": "cifar100",
  "image_size": 32,
  "batch_size": 128,
  "num_workers": 4,
  "epochs": 200,
  "warmup_epochs": 20,
  "learning_rate": 0.0005,
  "weight_decay": 0.1,
  "betas": [
    0.9,
    0.999
  ],
  "scheduler": "cosine",
  "min_lr": 1e-06,
  "ce_weight": 1.0,
  "cayley_weight": 0.01,
  "contrast_weight": 0.5,
  "scale_ce_weight": 0.1,
  "gradient_clip": 1.0,
  "label_smoothing": 0.1,
  "use_augmentation": true,
  "mixup_alpha": 0.3,
  "cutmix_alpha": 1.0,
  "save_interval": 10,
  "output_dir": "./checkpoints/cifar100",
  "resume_from": null,
  "use_tensorboard": true,
  "log_interval": 50,
  "push_to_hub": true,
  "hub_repo_id": "AbstractPhil/geovit-david-beans",
  "hub_private": false,
  "hub_append_run": true,
  "device": "cuda"
}