0 / 0
Managing data for model evaluations in watsonx.governance
Last updated: Oct 03, 2024
Managing data for model evaluations in watsonx.governance

To enable model evaluations, you must prepare your data for logging to generate insights.

You must provide your model data to watsonx.governance in a format that it supports to enable model evaluations. Watsonx.governance processes your model transactions and logs the data in the watsonx.governance data mart. The data mart is the logging database that stores the data that is used for model evaluations. The following sections describe the different types of data that watsonx.governance logs for model evaluations:

Payload data

Payload data contains the input and output transactions for your deployment. watsonx.governance must receive payload data from your model that it stores in a payload logging table. The table includes timestamp and ID columns to identify each scoring request that you send to watsonx.governance as shown in the following example:

Python SDK sample output of payload logging table

You must send scoring requests to provide watsonx.governance with a log of your model transactions. For more information, see Managing payload data.

Feedback data

Feedback data is labeled data that matches the structure of training data and includes known model outcomes that are compared to your model predictions to measure the accuracy of your model. Watsonx.governance uses feedback data to enable you to configure quality evaluations. You must upload feedback data regularly to watsonx.governance to continuously measure the accuracy of your model predictions. For more information, see Managing feedback data.

Learn more

Generative AI search and answer
These answers are generated by a large language model in watsonx.ai based on content from the product documentation. Learn more