seed: 7
device: auto
output_dir: outputs/overfit

data:
  source_manifest: ../../alpamayo/alpamayo-qwen05b-validation/data/processed/overfit_manifest.jsonl
  num_variants: 4
  image_size: 64
  action_horizon: 16

model:
  d_model: 96
  n_heads: 4
  n_layers: 3
  mlp_ratio: 3
  patch_size: 16
  max_text_tokens: 64
  dropout: 0.0

train:
  pretrain_steps: 300
  posttrain_steps: 500
  batch_size: 4
  learning_rate: 0.001
  weight_decay: 0.0
  grad_clip_norm: 1.0
  semantic_loss_weight: 1.0
  flow_loss_weight: 2.0
  log_every: 20

inference:
  flow_steps: 10