1. pip install -r requirements.txt
2. Read through the command in commands_BO_full.sh and BO_runs_LLM_joint_optimization.py
3. To run the code, need to have access to our servers.
4. commands_BO_run_all.sh contains the script to run.

Deprecated; ignore.

1. To get the data, first create a data folder in the home repo.
2. Download the train zip file from https://www.kaggle.com/c/dogs-vs-cats/data?select=train.zip
3. Download the fashion-mnist data from https://github.com/zalandoresearch/fashion-mnist/tree/master/data/fashion
4. Unzip the data where necessary and make sure the data folder is in this structure (cats contain all cats pictures, dogs contain all dogs pictures)
5. run the code in data_mixing_simple.ipynb to run a simple BO iteration.