experiment: llm_moe_hard_seeds
kind: llm_moe
seed: 1
seeds: [1, 2, 3]
n_replicates: 1

# Multi-seed 0.5B union-vs-fusion on the HARD benchmark (the headroom regime where the ordering
# matters). Fixed test sets; training seed varies; hard specialists cache per-seed
# (spec_<family>_hard_s<seed>). Companion to the single-seed llm_moe_hard and the 7B HPC runs.

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]

output: {dir: results/llm_moe_hard_seeds}