DATA:
  BANDS: [B02, B03, B04, B05, B06, B07]
  INPUT_SIZE: [4, 224, 224]
  MASK_RATIO: 0.75
  MEAN: [1087.0, 1342.0, 1433.0, 2734.0, 1958.0, 1363.0]
  STD: [2248.0, 2179.0, 2178.0, 1850.0, 1242.0, 1049.0]
MODEL:
  COORDS_DROP_RATE: 0.1
  COORDS_ENCODING: [time, location]
  COORDS_SCALE_LEARN: true
  DECODER_DEPTH: 8
  DECODER_EMBED_DIM: 512
  DECODER_NUM_HEADS: 16
  DEPTH: 24
  DROP_CHANNELS_RATE: 0.0
  EMBED_DIM: 1024
  MLP_RATIO: 4.0
  NAME: vit_l
  NORM_PIX_LOSS: false
  NUM_HEADS: 16
  PATCH_SIZE: [1, 16, 16]