experiment: llm_moe_hard_hpc
kind: llm_moe
seed: 1
n_replicates: 1

# The HARD-benchmark firm-up (L40S). The easy families saturated 7B at 1.00 (strings/arith), so the
# 7B moe/directed nulls could not distinguish "refinements don't help at scale" from "tasks too easy".
# This run uses the HARDER task variant (hard: true) — longer lists + multi-step ops, Caesar ciphers /
# letter transforms, multi-step & larger arithmetic — so 7B is NOT saturated and routing vs fusion has
# real headroom to separate. Trains fresh HARD specialists (cached as spec_*_hard). Same operators as
# moe_hpc; the question: does the 0.5B ordering (union > fusion) reappear at 7B once fusion can no
# longer trivially compose to the ceiling?

base_model: Qwen/Qwen2.5-7B-Instruct
hard: true
families: [lists, strings, arith]
n_train: 800
n_test: 200
n_route: 48
epochs: 3
lora: {r: 16, alpha: 32}
operators: [soup, ties, moe_oracle, moe_learned, max_merge]

output: {dir: results/llm_moe_hard_hpc}