_base_: ../_base_/default.yaml

model:
  reasoning_effort: medium

train:
  train_size: 400
  batch_size: 40
  accumulation: 1

gradient:
  minibatch_size: 8
  merge_batch_size: 8

optimizer:
  learning_rate: 4

evaluation:
  sel_env_num: 0
  test_env_num: 0

env:
  name: searchqa
  skill_init: skillopt/envs/searchqa/skills/initial.md
  split_mode: split_dir
  split_dir: data/searchqa_split
  data_path: ""
  split_output_dir: ""
  max_turns: 1
  max_completion_tokens: 16384
  workers: 24
  limit: 0