{
  "data_config": "configs/scannetpp/iphone/data.json",
  "data_overrides": {
    "num_views": 8,
    "sampling_range": 32,
    "eval_num_frames": 32,
    "batch_size": 16,
    "num_workers": 8
  },
  "model": {
    "embed_dim": 384,
    "num_heads": 6,
    "num_layers": 8,
    "predict_points": false,
    "encoder_name": "dinov2_vitb14",
    "image_size": 224
  },
  "loss": {
    "camera": 5.0,
    "depth": 1.0
  },
  "training": {
    "epochs": 40,
    "learning_rate": 0.001,
    "weight_decay": 0.01,
    "output_dir": "outputs/vggt_overfit",
    "overfit_scenes": 1,
    "overfit_steps_per_epoch": 25,
    "min_lr_ratio": 0.05,
    "log_every": 10,
    "warmup_epochs": 0,
    "overfit_epochs": 40,
    "overfit_learning_rate": 0.001
  },
  "data": {
    "root": "data/scannetpp/processed",
    "eval_root": "data/scannetpp/prepared_eval",
    "eval_num_frames": 32,
    "split_file": "configs/scannetpp/iphone/scene_splits.json",
    "num_views": 8,
    "sampling_range": 32,
    "image_size": 224,
    "batch_size": 16,
    "num_workers": 8,
    "seed": 825
  },
  "run": {
    "overfit": true,
    "overfit_scenes": 1,
    "steps_per_epoch": 25,
    "max_val_batches": null,
    "world_size": 1,
    "precision": "bf16"
  }
}
