# The curriculum society campaign, seed 1 (prereg v4, v5 curriculum — tasks/prereg-llm-society-v4.md on the dev branch).
# Runs all four arms then the three matched-budget baselines. The PBS array (hpc/llm_curriculum.pbs)
# derives one (seed, arm) config per element from this template for seeds 2-3.
#
# Six real-dataset families selected by calibration (§8a): five pass C1 at >= 0.60, winogrande (0.57)
# is the sixth under the recorded amendment. L = 3 lineages, G = 6 generations; the cyclic Latin square
# gives complementarity 1.0 at generation 2 and 0.0 at generation 6 (H6 tests the shape).
#
# Arms:  isolated (no recombination) · society (decorrelated contemporary) · society_dry (contemporary,
#        self-generated replay) · seed_bank (own ancestor at t-3 — temporal complementarity)
# Baselines at matched examples:  sequential · single_shot_merge · joint
experiment: llm_curriculum_v5
kind: llm_curriculum
base_model: Qwen/Qwen2.5-1.5B      # base, not Instruct: measured 0.011 on these families untrained
seed: 1
families: [mnli, arc, hellaswag, squad, boolq, winogrande]
lineages: 3
generations: 6
arms: [isolated, society, society_dry, seed_bank]
baselines: [sequential, single_shot_merge, joint]
n_new: 300                # founder/acquisition budget that passed C1 (1200 destabilised training)
n_replay: 150             # fixed TOTAL, split across families seen: protection thins as the curriculum grows
n_test: 60                # per family, from the TEST split — reporting only
n_val: 20                 # per family, from the TRAIN split — merge-weight selection only
epochs: 3
lr: 1.0e-4                # continued-training rate (fresh founders use train_lora_on_tasks' 2e-4)
ancestor_depth: 3
operator: linear
merge_weights: [[0.5, 0.5], [0.3, 0.7], [0.7, 0.3]]
baseline_weights: [[0.333, 0.333, 0.334], [0.5, 0.25, 0.25], [0.25, 0.5, 0.25], [0.25, 0.25, 0.5]]
max_new_tokens: 48
batch_size: 24
train_batch_size: 2
train_max_len: 512
resume: true
lora: {r: 16, alpha: 32}
output: {dir: results/llm_curriculum_v5/s1}