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

experience:
  augmentation_factor: 1
  gamma: 1.0
  n_step: 4
  positive_quantile: 0.7

model:
  patch_size: 16
  n_heads: 4
  n_layers: 3
  mlp_ratio: 3
  policy_d_model: 96
  value_d_model: 64
  max_text_tokens: 64
  max_action_tokens: 32
  action_start_token_id: 269
  dropout: 0.0
  value_bins: 201
  value_min: -1.0
  value_max: 0.0

train:
  base_steps: 300
  value_steps: 400
  mixed_steps: 300
  recap_steps: 700
  batch_size: 4
  learning_rate: 0.001
  value_learning_rate: 0.001
  weight_decay: 0.0
  grad_clip_norm: 1.0
  token_loss_weight: 1.0
  flow_loss_weight: 2.0
  value_loss_weight: 1.0
  log_every: 20

recap:
  condition_dropout: 0.3
  cfg_beta: 2.0
  force_interventions_positive: true

inference:
  flow_steps: 10
  cfg_beta: 2.0