{
"model_type": "vit",
  "model_args": {
      "decoder_depth": 8,
      "decoder_embed_dim": 512,
      "decoder_num_heads": 16,
      "depth": 12,
      "embed_dim": 768,
      "img_size": 224,
      "in_chans": 6,
      "num_frames": 3,
      "num_heads": 12,
      "patch_size": 16,
      "tubelet_size": 1
    },
    "train_params": {
      "bands": [
        "B02",
        "B03",
        "B04",
        "B05",
        "B06",
        "B07"
      ],
      "data_mean": [
        775.2290211032589,
        1080.992780391705,
        1228.5855250417867,
        2497.2022620507532,
        2204.2139147975554,
        1610.8324823273745
      ],
      "data_std": [
        1281.526139861424,
        1270.0297974547493,
        1399.4802505642526,
        1368.3446143747644,
        1291.6764008585435,
        1154.505683480695
      ],
      "mask_ratio": 0.75,
      "random_cropping": true
    }
  }