_base_: ../_base_/default.yaml

model:
  reasoning_effort: medium

train:
  batch_size: 10
  accumulation: 1

gradient:
  minibatch_size: 8
  merge_batch_size: 8

optimizer:
  learning_rate: 4

env:
  name: sealqa
  skill_init: skillopt/envs/sealqa/skills/initial.md
  split_dir: data/sealqa_split
  workers: 4
  max_tool_turns: 12
  limit: 0