How to reproduce the EPR's result on break dataset?

I try run this command: python run.py dataset=break dpr_epochs=120 gpus=4 partition=killable no_slurm=True time="24h" but it does not run well and give the following output and stops:

run.py:219: UserWarning: 
The version_base parameter is not specified.
Please specify a compatability version level, or None.
Will assume defaults for version 1.1
  @hydra.main(config_path=None, config_name="config")
/remote-home/xnli/anaconda3/envs/channel/lib/python3.8/site-packages/hydra/_internal/hydra.py:119: UserWarning: Future Hydra versions will no longer change working directory at job runtime by default.
See https://hydra.cc/docs/next/upgrades/1.1_to_1.2/changes_to_job_working_dir/ for more information.
  ret = run_job(

OhadRubin / EPR

How to reproduce the EPR's result on break dataset? #4