Closed Innixma closed 1 year ago
Currently to run 3 frameworks h2oautoml, autogluon, autogluon:latest:
python3 runbenchmark.py h2oautoml validation 1h4c -m aws python3 runbenchmark.py autogluon validation 1h4c -m aws python3 runbenchmark.py autogluon:latest validation 1h4c -m aws
Ideally:
python3 runbenchmark.py [h2oautoml, autogluon, autogluon:latest] validation 1h4c -m aws
Benefits of the new logic is that compute can be used when using multiple instances more effectively (for example, running instances on both h2o and autogluon at the same time within the same runbenchmark.py call.
Duplicate of https://github.com/openml/automlbenchmark/issues/169
Currently to run 3 frameworks h2oautoml, autogluon, autogluon:latest:
Ideally:
Benefits of the new logic is that compute can be used when using multiple instances more effectively (for example, running instances on both h2o and autogluon at the same time within the same runbenchmark.py call.