Content

Hyperparameter tuning is a crucial part of a machine learning workflow. This presentation explores how the Slurm job manager can facilitate this step, even for smaller models that do not require full HPC cluster capabilities. 

We will cover key Slurm features, such as job arrays, which can be utilized to enable scalable and efficient hyperparameter scans across multiple compute nodes.

Access:

To access the event, click on the following link: 

Big Blue Button Link <https://webconf.hrz.uni-marburg.de/n/rooms/hsy-cmh-knb-ndw/join> 

Access Code: kw7i98