meta:
  model_name: vit_huge
  embed_dim: 1280
  load_checkpoint: true
  checkpoint_folder: experiment_logs/vith14.224-bs.128-ep.300/
  read_checkpoint: jepa-ep300.pth.tar
  use_bfloat16: true
  num_classes: 182

data:
  batch_size: 128
  root_path: ./wilds_data
  num_workers: 10
  pin_mem: true
  crop_size: 224
  crop_scale: [0.3, 1.0]
  use_random_resized_crop: false
  use_horizontal_flip: false
  use_color_distortion: false
  color_jitter_strength: 0.0
  use_gaussian_blur: false

mask:
  patch_size: 14

optimization:
  optimizer: adamw # 'adamw' or 'sgd'
  freeze_weights: true # true for linear probing, false for full fine-tuning
  epochs: 300 # can be set higher if early_stopping
  lr: 5.0e-4
  weight_decay: 1.0e-2
  use_cosine_schedule: true
  start_lr: 0.0001
  final_lr: 1.0e-06
  warmup: 5
  ipe_scale: 1.0
  early_stopping:
    enabled: true
    patience: 10
    min_delta: 1.0e-4
    min_epochs: 15
    restore_best_weights: true

validation:
  eval_every: 1

logging:
  folder: experiment_logs/supervised-vith14.224-bs.128-ep.300-lp/
  write_tag: linear_probe