# Base diffusion configuration
# Provides default values for diffusion training and inference

# Device and compilation settings
compile: false
device: cpu
precision: 'fp32'
seed: 42
checkpoint_path: ''

# Model configuration defaults
model:
  model: 'DiT-S'                    # Default to smaller model
  noise_schedule: 'linear'          # Default noise schedule
  l1_loss: false                    # Use MSE loss by default
  diffusion_steps: 1000             # Standard diffusion steps
  max_diffusion_step: 1000          # Full diffusion by default
  context_size: 128                 # Default context size

# Data configuration defaults
data:
  train_dataset_path: ''            # Must be specified in child configs
  start: 0
  end: 1000                         # Small default dataset
  shuffle: true
  seq_len: 64                       # Default sequence length
  stride: 8                         # Default stride
  cycle_length: 32                  # Default cycle length
  beatmap_class: false              # Disable by default
  difficulty_class: false           # Disable by default
  mapper_class: false               # Disable by default
  descriptor_class: false           # Disable by default
  circle_size_class: false          # Disable by default
  class_dropout_prob: 0.1           # Conservative dropout
  diff_dropout_prob: 0.1
  mapper_dropout_prob: 0.1
  descriptor_dropout_prob: 0.1
  cs_dropout_prob: 0.1
  descriptors_path: ''              # Must be specified in child configs
  mappers_path: ''                  # Must be specified in child configs
  num_diff_classes: 10              # Default number of classes
  max_diff: 10                      # Default max difficulty
  num_cs_classes: 10                # Default number of CS classes
  double_time_prob: 0.0             # Disable by default
  distance_std: 0.05                # Conservative noise

# Dataloader defaults
dataloader:
  num_workers: 2                    # Conservative default

# Optimizer defaults
optim:
  name: adamw
  base_lr: 1e-4                     # Conservative learning rate
  batch_size: 32                    # Small default batch size
  total_steps: 100000               # Default training steps
  warmup_steps: 5000                # Default warmup
  lr_scheduler: linear              # Simple scheduler
  weight_decay: 0.01                # Light regularization
  grad_acc: 1                       # No gradient accumulation by default
  gradient_clip: 1.0                # Gradient clipping
  final_cosine: 1e-6                # Final learning rate

# Checkpoint defaults
checkpoint:
  every_steps: 10000                # Save every 10k steps

# Logging defaults
logging:
  log_with: 'tensorboard'           # Default to tensorboard
  every_steps: 100                  # Log every 100 steps
  mode: 'offline'                   # Offline by default

# Hydra defaults
hydra:
  job:
    chdir: false                    # Don't change directory by default