# Calibration stage B (prereg §4, gates C2 / C3 / C5) over the 12 families chosen from stage A.
# Run three times with stage: transmission | cross | consensus (see Makefile `llm-society-calib`).
# Families = stage-A pass-2 option 1 (L=9, gate 0.41; prereg §4a) — pending GG's go.
experiment: llm_society_v2_calib_b
kind: llm_society_calib
stage: transmission
base_model: Qwen/Qwen2.5-0.5B-Instruct
seed: 1
families: [strings, setops, numtheory, mixedtoken, digits, alphabet, prime, wordlen, roman]
# C2: examples-per-family k and epochs to sweep; probe_families are the three whose retention is
# measured (spread across answer types: list / word / int).
probe_families: [setops, alphabet, digits]   # list / letter / integer answers
ks: [25, 50, 100, 150]
epochs_grid: [2, 3]
# C3: the two-founder cross (union-distil vs best-of-6 linear-merge-distil)
cross: [setops, alphabet]
k_inherit: 100
epochs: 3
n_candidates: 6
n_test: 100
n_probe: 10
spec_train: 1200
spec_epochs: 3
lora: {r: 16, alpha: 32}
output: {dir: results/llm_society_v2_calib_b}