| # path to the task data directory | |
| data_dir: null | |
| # either provide a path to a plaintext file describing the task | |
| desc_file: null | |
| # or provide the task goal (and optionally evaluation information) as arguments | |
| goal: null | |
| eval: null | |
| log_dir: logs | |
| workspace_dir: workspaces | |
| # whether to unzip any archives in the data directory | |
| preprocess_data: True | |
| # whether to copy the data to the workspace directory (otherwise it will be symlinked) | |
| # copying is recommended to prevent the agent from accidentally modifying the original data | |
| copy_data: True | |
| exp_name: null # a random experiment name will be generated if not provided | |
| # settings for code execution | |
| exec: | |
| timeout: 3600 | |
| agent_file_name: runfile.py | |
| format_tb_ipython: False | |
| generate_report: True | |
| # LLM settings for final report from journal | |
| report: | |
| model: gpt-4-turbo | |
| temp: 1.0 | |
| # agent hyperparams | |
| agent: | |
| # how many improvement iterations to run | |
| steps: 20 | |
| # whether to instruct the agent to use CV (set to 1 to disable) | |
| k_fold_validation: 5 | |
| # whether to instruct the agent to generate a prediction function | |
| expose_prediction: False | |
| # whether to provide the agent with a preview of the data | |
| data_preview: True | |
| # LLM settings for coding | |
| code: | |
| model: gpt-4-turbo | |
| temp: 0.5 | |
| # LLM settings for evaluating program output / tracebacks | |
| feedback: | |
| model: gpt-4-turbo | |
| temp: 0.5 | |
| # hyperparameters for the tree search | |
| search: | |
| max_debug_depth: 3 | |
| debug_prob: 0.5 | |
| num_drafts: 5 | |