tristers-at-square
tristers-at-square
> Hi, thank you for raising the issue. From your code snippet, it seems you are not using distributed training? Using Rabit to sync across an AWS cluster to do...
From the logging output:
Things I've tried: - running with a different eval metric - running without callbacks - running on a single node without Rabit - running with different configurations of nthread (1,...
> Thanks for using LightGBM. > > Early stopping is not currently supported in the Dask interface. You can subscribe to #3712 to be notified when that work is picked...