search

tubo213 / kaggle-child-mind-institute-detect-sleep-states

MIT License
115 stars 85 forks source link

Running run/prepare_data.py killed #45

Closed riow1983 closed 10 months ago

riow1983 commented 10 months ago

It must not be an issue but is a question. I encountered an intermediate killing operation before finishing the task:

$ rye run python run/prepare_data.py -m phase=train,test

[2023-11-12 23:53:26,135][HYDRA] Launching 2 jobs locally [2023-11-12 23:53:26,135][HYDRA] #0 : phase=train Killed

No other error messages appeared. It might be my environmental issue. But do we have a minimum requirement for e.g., RAM of an environment that runs this command? FYI: the spec of my environment: g4dn.xlarge (AWS instance) - 4 cores - 16 GB RAM - 1 GPU - 40Gi Disk

tubo213 commented 10 months ago

@riow1983

I think it is due to lack of RAM. Try running with a large amount of RAM (about 32 GB)

riow1983 commented 10 months ago

Thanks! Will do.

tubo213 commented 10 months ago

@riow1983

Please comment on Disscussion for a summary, as exchanges on github may fall under the category of private sharing.

riow1983 commented 10 months ago

@tubo213 Thanks. Done: https://www.kaggle.com/competitions/child-mind-institute-detect-sleep-states/discussion/452940#2531150