Skip to content

Latest commit

 

History

History

README.md

Running MLE Bench with Curie

Directory Structure

The mle_bench directory contains several benchmark tasks from MLE Bench:

Each task directory contains:

Setup and Installation

1. Install MLE Benchmark

  • Setup kaggle credential ~/.kaggle/kaggle.json
  • Install correct sqlite version (to fix the bug in mle-bench)
conda create --name sqlite3-49-0 python=3.11
conda activate sqlite3-49-0
conda install sqlite=3.49
  • Install mlebench
git clone https://github.com/openai/mle-bench.git
cd mle-bench
git lfs fetch --all
git lfs pull
pip install -e .

2. Download Dataset

Run mlebench prepare with the specific task ID:

conda activate sqlite3-49-0  
mlebench prepare -c <task-id>  # e.g., dog-breed-identification

The data will be saved to $HOME/.cache/mle-bench/data.

Running Curie on MLE Bench Tasks

1. Select a Task

Choose one of the available tasks from the MLE-Bench (E.g. siim-isic-melanoma-classification).

2. Run Curie

Use the following command format:

cd Curie/
python3 -m curie.main -f benchmark/mle_bench/<task-dir>/<task>-question.txt --dataset_dir <abd_path_to_dataset> --task_config curie/configs/mle_config.json 

Additional Information

Question Generation

MLE Bench provides description.md for each problem. We use the following prompt to convert the description into a research question:

Convert this Kaggle competition into a question to the ai agent (be concise): introduce the problem, goal, and all necessary details to guide the agent to find the best performing model/configuration: 
<description.md>