config.json

{
  "num_classes": 100,
  "img_size": 32,
  "patch_size": 4,
  "visual_dim": 512,
  "geom_dim": 256,
  "k_simplex": 4,
  "depth": 8,
  "num_heads": 8,
  "mlp_ratio": 4.0,
  "dropout": 0.0,
  "num_geom_tokens": 8,
  "pe_levels": 12,
  "pe_features_per_level": 2,
  "pe_smooth_tau": 0.25,
  "simplex_init_method": "regular",
  "simplex_init_scale": 1.0,
  "batch_size": 512,
  "num_epochs": 150,
  "learning_rate": 0.0001,
  "weight_decay": 0.005,
  "warmup_epochs": 10,
  "task_loss_weight": 0.5,
  "flow_loss_weight": 1.5,
  "coherence_loss_weight": 0.5,
  "multiscale_loss_weight": 0.3,
  "use_adaptive_augmentation": false,
  "overfit_threshold": 0.05,
  "augmentation_cooldown_epochs": 5,
  "min_accuracy_for_augmentation": 0.45,
  "mixup_alpha": 0.2,
  "cutmix_alpha": 1.0,
  "use_cutmix_schedule": true,
  "cutmix_schedule": [
    [
      0,
      0.2
    ],
    [
      20,
      0.5
    ],
    [
      40,
      1.0
    ],
    [
      60,
      1.2
    ],
    [
      80,
      1.5
    ],
    [
      100,
      1.8
    ],
    [
      120,
      2.0
    ]
  ],
  "device": "cuda",
  "num_workers": 4,
  "pin_memory": true,
  "save_dir": "./checkpoints_dualstream",
  "save_every": 10,
  "use_safetensors": true,
  "timestamp_dirs": true,
  "push_to_hub": true,
  "hub_model_id": "AbstractPhil/vit-beatrix-dualstream",
  "hub_model_name": "beatrix-trainC-chaos-native",
  "hub_upload_best_only": true,
  "hub_upload_every_n_epochs": 10,
  "use_tensorboard": true,
  "log_dir": "./logs_dualstream",
  "log_every": 50,
  "monitor_stream_health": true,
  "log_stream_norms": true
}