experiment: llm_compose
seed: 1
n_replicates: 1
source_config:
  experiment: llm_compose
  kind: llm_compose
  base_model: Qwen/Qwen2.5-1.5B
  seed: 1
  generations: 6
  arms:
  - dry
  - grounded
  - dry_cat
  g: 0.1
  n_hard: 150
  n_gsm8k: 150
  n_mbpp: 100
  n_probe: 60
  k_inherit: 300
  epochs: 3
  conf_gate: 0.85
  spec_train: 1200
  spec_epochs: 3
  max_new_tokens: 320
  batch_size: 16
  score_batch_size: 4
  train_batch_size: 2
  train_max_len: 448
  resume: true
  lora:
    r: 16
    alpha: 32
  output:
    dir: results/llm_compose/s1
  arm_ops:
    dry: linear
    grounded: linear
    dry_cat: cat
  n_hard_val: 60
  merge_weights:
  - - 0.5
    - 0.5
  - - 0.3
    - 0.7
  - - 0.2
    - 0.8
  - - 0.1
    - 0.9
  n_replicates: 1