data:
  batch_size: 16
  color_jitter_strength: 0.0
  crop_scale:
    - 1.0
    - 1.0
  crop_size: 448
  num_workers: 10
  pin_mem: true
  root_path: ./wilds_data
  use_color_distortion: false
  use_gaussian_blur: false
  use_horizontal_flip: false
  use_random_resized_crop: false
logging:
  folder: experiment_logs/vith16.448-bs.128-ep.300/
  write_tag: jepa
mask:
  allow_overlap: false
  aspect_ratio:
    - 0.75
    - 1.5
  enc_mask_scale:
    - 0.85
    - 1.0
  min_keep: 10
  num_enc_masks: 1
  num_pred_masks: 4
  patch_size: 16
  pred_mask_scale:
    - 0.15
    - 0.2
meta:
  copy_data: false
  load_checkpoint: false
  model_name: vit_huge
  pred_depth: 12
  pred_emb_dim: 384
  read_checkpoint: null
  use_bfloat16: true
  use_gradient_checkpointing: true
optimization:
  gradient_accumulation_steps: 32
  ema:
    - 0.996
    - 1.0
  epochs: 300
  final_lr: 1.0e-06
  final_weight_decay: 0.4
  ipe_scale: 1.0
  lr: 0.001
  start_lr: 0.0001
  warmup: 15
  wd_schedule: linear
  weight_decay: 0.04