experiment: llm_moe_hard
kind: llm_moe
seed: 1
n_replicates: 1

# Local 0.5B SMOKE for the hard benchmark: confirms the harder task variant (hard: true) runs
# end-to-end — trains fresh hard specialists (cached as spec_*_hard), the verifier still scores them,
# routing/fusion operators execute. 0.5B will score low on these harder tasks (that is expected; the
# calibrated comparison is the 7B moe_hard_hpc run). Kept small for speed.

base_model: Qwen/Qwen2.5-0.5B-Instruct
hard: true
families: [lists, strings, arith]
n_train: 400
n_test: 80
n_route: 32
epochs: 3
lora: {r: 16, alpha: 32}
operators: [soup, ties, moe_oracle, moe_learned, max_merge]

output: {dir: results/llm_moe_hard}