experiment: llm_directed_hard_seeds
kind: llm_directed
seed: 1
seeds: [1, 2, 3]
n_replicates: 1

# Multi-seed 0.5B directed sex on the HARD benchmark (offspring selection pays off exactly where the
# default soup is suboptimal). Fixed test/val sets; training + Dirichlet-offspring seed varies; reuses
# the per-seed hard specialists trained by llm_moe_hard_seeds when present.

base_model: Qwen/Qwen2.5-0.5B-Instruct
hard: true
families: [lists, strings, arith]
n_train: 400
n_test: 80
n_val: 60
n_candidates: 16
concentration: 0.5
epochs: 3
lora: {r: 16, alpha: 32}

output: {dir: results/llm_directed_hard_seeds}