_base_: ../_base_/default.yaml model: reasoning_effort: medium train: batch_size: 40 accumulation: 1 gradient: minibatch_size: 8 merge_batch_size: 8 optimizer: learning_rate: 4 env: name: officeqa skill_init: skillopt/envs/officeqa/skills/initial.md split_mode: split_dir split_dir: data/officeqa_split data_dirs: - data/officeqa_docs_official workers: 4 max_tool_turns: 24 max_completion_tokens: 16384 search_mode: offline max_queries_per_turn: 4 search_api_url: http://apisix.westus2.cloudapp.azure.com/search_tool/search search_auth_env: OFFICEQA_CUSTOM_SEARCH_AUTH search_provider: duckduckgo search_max_num_results: 4 search_timeout_seconds: 20 limit: 0