topic Re: AutoML runs fail after 5 seconds in Data Engineering

AutoML runs fail after 5 seconds

Qwetroman — Mon, 15 May 2023 17:27:06 GMT

Hi everyone

I am exploring automl, and I met a strange problem - after I launch a classification experiment on my personal newly created cluster (screenshot attached) it successfully performs data exploration, but after that, all runs fail after approximately 5 seconds (screenshot attached).

In the source notebook, there are no signs of the error message, just very long text (HTML file attached)

Is it something with the data I upload? Or anything else?

Thanks in advance

Re: AutoML runs fail after 5 seconds

swethaNandan — Wed, 14 Jun 2023 17:29:33 GMT

Hi Qwetroman,

we can see the following error message in the notebook - ExecutionTimeoutError: Execution timed out before any trials could be successfully run. Please increase the timeout for AutoML to run some trials.

What's the size of the dataset?

Starting in 12.0, AutoML trains on a larger fraction of the data, meaning training will take longer.

Some options here are to increase the timeout and/or to sample the dataset before training.