Model logs

Review model logs to debug deployment or operation issues.

When you deploy your own model, we provide comprehensive logging for that model's deployment and operations to help you debug any issues.
To view logs, go to the "Logs" tab of a model's page. Logs are separated into two collapsible sections:
Build logs are generated when you first deploy your model to Baseten and detail the steps for provisioning infrastructure for the model.
Deployment and prediction logs record activity on your model, including HTTP response codes and any errors or warnings during model invocation.
Model log filters
You can search the logs for exactly what you need with three tools:
The search field, which accepts regular expressions, filters logs that match the input.
The date picker bounds the time range of deployment and prediction logs
Log entries are color-coded by to their log level (ERROR, WARNING, DEBUG, INFO) according to Python's standard logging levels.
 

MANAGING MODELS - Previous

Model resources

Next - MANAGING MODELS

Model metrics

Last modified 1mo ago