data:
  protocol: synthetic_sevir
  # Reference dataset: official SEVIR VIL (earthformer_sevir_v1.yaml) uses
  # 384x384 frames at 5-minute intervals, seq_len = 25 (13 input + 12 output),
  # "sequent" sampling with stride 12, single channel. The small spatial shape
  # below is intentionally the default for CPU smoke verification.
  input_length: 13
  output_length: 12
  height: 32
  width: 32
  channels: 1
  frame_interval_minutes: 5
  normalization: unit
  data_dir: data/synthetic_sevir
  train_samples: 8
  val_samples: 2
  test_samples: 2
  train_npz: data/synthetic_sevir/train.npz
  val_npz: data/synthetic_sevir/val.npz
  test_npz: data/synthetic_sevir/test.npz
  fallback_if_missing: true

model:
  dims: [4, 8]
  depths: [1, 1]
  heads: 1
  pattern: [[2, 4, 4]]
  num_global_vectors: 1
  ff_ratio: 2.0
  dropout: 0.0

train:
  seed: 42
  # Training always starts from a randomly initialized model (from scratch).
  # The --resume flag only restores a locally trained checkpoint for continued
  # training; no official pretrained Earthformer weights are ever downloaded.
  batch_size: 1
  epochs: 5
  validation_steps: 1
  # Per-epoch validation computes only cheap MSE/MAE (the training loss is
  # already MSE). Enable this to also compute SSIM/CSI every epoch; the
  # authoritative full evaluation lives in script/result.py.
  compute_full_metrics: false
  learning_rate: 0.001
  weight_decay: 0.00001
  # Trained weights for inference are saved here as earthformer.pt.
  output_dir: data/checkpoint

dataloader:
  num_workers: 0
  pin_memory: false

distributed:
  backend: auto