# Generation-0 gate for the composition experiment (prereg v3 §4: C1 base, C3 specialists,
# C4 replication). Trains the two founders and measures everything at t=0 without iterating.
#
# Base choice (C1, measured 2026-09-07): Qwen2.5-1.5B **base, not Instruct**. Zero-shot GSM-Hard
# program-aided: Instruct-1.5B 0.500, Instruct-3B 0.417, base-3B 0.633 — all far too strong, since a
# base that already has the skills makes the specialists' contribution vacuous. Base-1.5B scores
# 0.067, within noise of the 0.059 Llama-2-7B starting point in LoRA Soups (COLING 2025), so the
# published composition effect has room to appear.
experiment: llm_compose_gate
kind: llm_compose
base_model: Qwen/Qwen2.5-1.5B
seed: 1
generations: 0            # gate only: train founders, measure t=0, stop
arms: [dry]
n_hard: 150               # composed target (GSM8k-Hard, program-aided) — SE ~0.04
n_gsm8k: 100              # math own-skill probe
n_mbpp: 80                # code own-skill probe (execution-verified)
n_probe: 40               # shared prompts for rho
k_inherit: 300
epochs: 3
conf_gate: 0.85
g: 0.10
spec_train: 1200
spec_epochs: 3
max_new_tokens: 320
batch_size: 16
score_batch_size: 4
train_batch_size: 2       # 16 GB A4000; the fp32 logit upcast at vocab 152k is the constraint
train_max_len: 448
lora: {r: 16, alpha: 32}
output: {dir: results/llm_compose_gate}