experiment:
  name: controller_p4_hent
  seed: 1
  mode: prisme
  model:
    name: tiny_p4
    vocab_size: 128
    d_model: 192
    n_layers: 4
    n_heads: 6
    n_kv_heads: 2
    ffn_width: 512
    readout_zero_init: false
    readout_init_std: 0.2
    readout_scale: 5.251
    max_seq_len: 320
    w: 64
    ffn_w: 192
    n_slots: 16
    n_editor_heads: 2
    r_max: 8
  checkpoint: experiments/runs/p4_editor_v1_Ustd02_seed01_20261029235050/checkpoint
  labels:
    train: experiments/runs/labels_p4_seed01_20261030000543/labels_train.pt
    calib: experiments/runs/labels_p4_seed01_20261030000543/labels_calib.pt
  train:
    steps: 3000
    lr: 0.001
    weight_decay: 0.01
    alpha: 1.0
    beta: 0.5
    gamma: 0.1
    huber_delta: 0.1
    log_every: 100
    eval_every: 1000
    seq_len: 320
  lambda_grid:
  - 0.0
  - 0.01
  - 0.03
  - 0.1
  - 0.3
  kappa_grid:
  - 0.0
  - 0.5
  sweep_batches: 10
  max_budget: 8
  selection_rule: max_loss_reduction_per_ops
  model_overrides:
    ctrl_input: h
    ctrl_use_entropy: true
model:
  name: tiny_p4
  vocab_size: 128
  d_model: 192
  n_layers: 4
  n_heads: 6
  n_kv_heads: 2
  ffn_width: 512
  max_seq_len: 320
  rope_theta: 10000.0
  norm_eps: 1.0e-05
  tie_embeddings: true
  init_std: 0.02
  use_workspace: true
  w: 64
  ffn_w: 192
  n_slots: 16
  n_editor_blocks: 2
  n_editor_heads: 2
  r_max: 8
  eta_max: 0.25
  clip_c: 1.0
  clip_eps: 1.0e-06
  readout_zero_init: false
  readout_init_std: 0.2
  readout_scale: 5.251
  controller_hidden: 0
  ctrl_input: h
  ctrl_use_entropy: true
  lambda_cost: 0.0
  kappa_risk: 0.0
  dense_writes: false