# Phase 6 (tiny scale): value controller fit on logged labels; (lambda, kappa) tuned on calibration rollouts.
name: controller_p4
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,
        max_seq_len: 320, w: 64, ffn_w: 192, n_slots: 16, n_editor_heads: 2, r_max: 8}
checkpoint: CHECKPOINT_DIR
labels: {train: LABELS_TRAIN, calib: LABELS_CALIB}
train: {steps: 3000, lr: 1.0e-3, 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