experiment: llm_curriculum_v5
seed: 3
n_replicates: 1
source_config:
  experiment: llm_curriculum_v5
  kind: llm_curriculum
  base_model: Qwen/Qwen2.5-1.5B
  seed: 3
  families:
  - mnli
  - arc
  - hellaswag
  - squad
  - boolq
  - winogrande
  lineages: 3
  generations: 6
  arms:
  - isolated
  baselines:
  - sequential
  - single_shot_merge
  - joint
  n_new: 300
  n_replay: 150
  n_test: 60
  n_val: 20
  epochs: 3
  lr: 0.0001
  ancestor_depth: 3
  operator: linear
  merge_weights:
  - - 0.5
    - 0.5
  - - 0.3
    - 0.7
  - - 0.7
    - 0.3
  baseline_weights:
  - - 0.333
    - 0.333
    - 0.334
  - - 0.5
    - 0.25
    - 0.25
  - - 0.25
    - 0.5
    - 0.25
  - - 0.25
    - 0.25
    - 0.5
  max_new_tokens: 48
  batch_size: 48
  train_batch_size: 4
  train_max_len: 512
  resume: true
  lora:
    r: 16
    alpha: 32
  output:
    dir: results/llm_curriculum_v5/s3_isolated
  n_replicates: 1