experiment: llm_directed_hard_hpc
kind: llm_directed
seed: 1
n_replicates: 1

# Directed sex on the HARD benchmark (L40S). On the easy families the 7B soup already composed to the
# ceiling, so offspring selection had no headroom (directed ≈ soup). This run uses the harder task
# variant (hard: true), where the uniform soup should be well below saturation — the regime in which
# breeding + selection can actually improve on the default blend. Reuses the spec_*_hard specialists
# trained by moe_hard_hpc if present. The fair test the easy 7B null could not provide.

base_model: Qwen/Qwen2.5-7B-Instruct
hard: true
families: [lists, strings, arith]
n_train: 800
n_val: 100
n_test: 200
n_candidates: 24
concentration: 0.5
epochs: 3
lora: {r: 16, alpha: 32}

output: {dir: results/llm_directed_hard_hpc}