How to Log and Inspect XGBoost Model Training Metadata

1 min
Kamil Kaczmarek
21st April, 2022

What will you learn?

Hhow you can log and inspect XGBoost model training metadata in Neptune.

  • 01:16

    Connecting to Neptune and creating a run

  • 01:34

    Uploading the source files to Neptune

  • 02:42

    Data versioning the data stored in the S3 bucket

  • 03:54

    Downloading the data from the S3 bucket

  • 04:50

    For download do we need the read or the read/write access to the S3 bucket?

  • 05:38

    Can we use Neptune to track our raw data processing in the S3?

  • 06:21

    Uploading the sample data frame to Neptune

  • 07:25

    Creating a callback to keep track of the XGBoost training

  • 08:27

    What metadata does the callback keep track of in the XGBoost training?

  • 09:14

    Downloading the model from Neptune

  • 09:53

    What will the results look like in the Neptune UI?

Important: This video was created in February 2022. For the most up-to-date code examples, please refer to the Neptune-XGBoost integration docs

Other useful resources

Read also the docs on XGBoost integration.

Couldn’t find the use case you were looking for?

Just get in touch, and our ML team will create a custom demo for you.