topic Re: How do we log without a dbfs for MLFlow models. in Machine Learning

How do we log without a dbfs for MLFlow models.

Djay101 — Tue, 17 Sep 2024 15:46:30 GMT

Hi Databricks Team,

We are planning a UC Migration for a customer who currently has around 500 experiments, each with multiple runs. These experiments are registered and MLflow is logging to DBFS locations. However, we have not found any documentation or case studies on upgrading experiments registered on DBFS to use Volumes or External Locations as part of UC Migration.

Could you provide any guidance or support on how to handle this migration effectively?

Re: How do we log without a dbfs for MLFlow models.

rahuja — Mon, 13 Jan 2025 14:13:21 GMT

Any updates on this? We want to get rid of DBFS and I want to know how will MLFlow logging be affected by this?

Re: How do we log without a dbfs for MLFlow models.

Alberto_Umana — Mon, 13 Jan 2025 14:27:05 GMT

Hi @rahuja / @Djay101,

Do you have any account team contact for your Databricks subscription? I think this kind of migration requires more analysis based on your use-case. I could not find a straight-forward way to perform this migration, perhaps the account team can guide you through the process in an automated way.