experiment: llm_curriculum_g2
seed: 1
n_replicates: 1
source_config:
  experiment: llm_curriculum_g2
  kind: llm_curriculum
  base_model: Qwen/Qwen2.5-1.5B
  seed: 1
  families:
  - strings
  - setops
  - numtheory
  - mixedtoken
  - digits
  - alphabet
  - prime
  - wordlen
  - roman
  lineages: 1
  generations: 9
  arms:
  - isolated
  baselines: []
  n_new: 300
  n_replay: 0
  n_test: 60
  n_val: 30
  epochs: 3
  lr: 0.0001
  max_new_tokens: 32
  batch_size: 32
  train_batch_size: 2
  train_max_len: 448
  lora:
    r: 16
    alpha: 32
  output:
    dir: results/llm_curriculum_g2
  n_replicates: 1