# The composition campaign, seed 1 (prereg v3, amended after the generation-0 sweep of 2026-09-07).
#
# Arms. The gen-0 sweep found that the merge *weighting* dominates the operator: the a-priori 0.5/0.5
# blend fails under both operators (surplus -0.020 cat, -0.093 linear) while a selected weight passes
# (+0.080 linear at 0.2/0.8, +0.027 cat at 0.3/0.7). Weights are therefore chosen each generation on a
# disjoint validation split (E10, directed recombination) in every arm, and the operator is an
# explicit per-arm setting:
#   dry      — linear operator, no grounding      [H2, H3, H5: does composition survive drift?]
#   grounded — linear operator, g = 0.10          [H4: does immigration arrest it?]
#   dry_cat  — concatenation operator, no grounding [H6, revised: does the operator ordering hold
#              across generations, or only at gen 0?]
experiment: llm_compose
kind: llm_compose
base_model: Qwen/Qwen2.5-1.5B
seed: 1
generations: 6
arms:
- dry
- grounded
- dry_cat
g: 0.1
n_hard: 150
n_gsm8k: 150
n_mbpp: 100
n_probe: 60
k_inherit: 300
epochs: 3
conf_gate: 0.85
spec_train: 1200
spec_epochs: 3
max_new_tokens: 320
batch_size: 16
score_batch_size: 4
train_batch_size: 2
train_max_len: 448
resume: true
lora:
  r: 16
  alpha: 32
output:
  dir: results/llm_compose/s1
arm_ops:
  dry: linear
  grounded: linear
  dry_cat: cat
n_hard_val: 60
merge_weights:
- - 0.5
  - 0.5
- - 0.3
  - 0.7
- - 0.2
  - 0.8
- - 0.1
  - 0.9