_base_: ../_base_/default.yaml

model:
  reasoning_effort: medium

train:
  batch_size: 20
  accumulation: 1

gradient:
  minibatch_size: 4
  merge_batch_size: 8

optimizer:
  learning_rate: 4

evaluation:
  sel_env_num: 0
  test_env_num: 0

env:
  name: swebench
  skill_init: reflact/envs/swebench/skills/initial.md
  split_mode: ratio
  split_ratio: "2:1:7"
  split_dir: ""
  data_path: ""
  split_output_dir: ""
  dataset_name: lite
  hf_split: test
  workers: 8
  eval_workers: 8
  step_limit: 50
  cost_limit: 3.0
  timeout_per_instance: 600
  limit: 0