vap:
  arch: mono
  batch_size: 64
  num_workers: 16
  max_epochs: 5
  lr: 0.001
  weight_decay: 0.01
  warmup_ratio: 0.1
  min_lr: 0.0001
  precision: bf16-mixed
  gradient_clip_val: 1.0
  accumulate_grad_batches: 1
  matmul_precision: high
  limit_train_batches: 1.0
  limit_val_batches: 1.0
  limit_test_batches: 1.0
  early_stopping_patience: 0
  source: npy
  swap_channels: false
  projection_window:
    bin_sec:
    - 1.4
    - 0.6
    - 0.6
    - 1.4
    num_hist_bins: 2
    frame_hz: 25
    threshold: 0.5
    mode: role_relative
    cut_center_frame: false
  temporal:
    d_model: 256
    m_ff: 3
    n_heads: 4
    n_layers: 4
    dropout: 0.1
    activation: GELU
    causal: true
    pos_encoding: alibi
    ffn: mlp
    norm: layer
    max_frames: 4096