experiment: llm_curriculum_v5_calib
seed: 1
n_replicates: 1
source_config:
  experiment: llm_curriculum_v5_calib
  kind: llm_curriculum
  base_model: Qwen/Qwen2.5-1.5B
  seed: 1
  families:
  - gsm8k
  - mbpp
  - boolq
  - mnli
  - sst2
  - csqa
  - arc
  - winogrande
  - squad
  - nq_open
  - hellaswag
  lineages: 11
  generations: 1
  arms:
  - isolated
  baselines: []
  n_new: 300
  n_replay: 0
  n_test: 60
  n_val: 20
  epochs: 3
  lr: 0.0001
  max_new_tokens: 48
  batch_size: 24
  train_batch_size: 2
  train_max_len: 512
  lora:
    r: 16
    alpha: 32
  output:
    dir: results/llm_curriculum_v5_calib
  n_replicates: 1