experiment:
  name: controller_103m
  seed: 1
  mode: prisme
  model: from_checkpoint
  checkpoint: experiments/runs/editor_pilot_103m_lr3e4_seed01_20261030021200/checkpoint
  labels:
    train: experiments/runs/labels_103m_seed01_20261030034314/labels_train.pt
    calib: experiments/runs/labels_103m_seed01_20261030034314/labels_calib.pt
  train:
    steps: 1500
    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: 250
    seq_len: 512
  lambda_grid:
  - 0.0
  - 0.01
  - 0.03
  - 0.1
  - 0.3
  kappa_grid:
  - 0.0
  - 0.5
  sweep_batches: 6
  max_budget: 8
  selection_rule: max_loss_reduction_per_ops
  model_overrides: {}
model:
  name: prisme_103m
  vocab_size: 32768
  d_model: 768
  n_layers: 12
  n_heads: 12
  n_kv_heads: 3
  ffn_width: 2048
  max_seq_len: 4096
  rope_theta: 10000.0
  norm_eps: 1.0e-05
  tie_embeddings: true
  init_std: 0.02
  use_workspace: true
  w: 256
  ffn_w: 768
  n_slots: 16
  n_editor_blocks: 2
  n_editor_heads: 4
  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: 8.851566314697266
  controller_hidden: 0
  ctrl_input: h
  ctrl_use_entropy: true
  lambda_cost: 0.0
  kappa_risk: 0.0
  dense_writes: false