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