ML Generator View

Overview

ML Generator View is the project-level workspace for inspecting persisted ML generator results from executed training runs, comparing versions, and promoting a validated default version for downstream generation flows.

Open it from the top navigation via ML-Gen.

Only models with completed/persisted training appear with versions and statistics in this view.

ML Generator View: generator list, version panel, and quality metrics

Main Areas

Sidebar: Generator List

• Search generators by name.
• Select a generator to load its details.
• See current default version and update timestamp.

Detail Pane

• Header row: choose a specific version, set selected version as default, delete selected version.
• Headline cards:
• dataset sizes (train/holdout/synthetic),
• utility score,
• privacy score.
• A conditional "Attention required" status callout, shown when quality checks warn or fail, or when there are additional notes even on a pass.
• KPI metrics (accuracy, univariate/bivariate/trivariate signals, NN distances).
• Top drift table with column-wise KL/JS drift indicators.

Top Actions

• Download report: download the HTML QA report for the selected version.

Relationship to Database View and DSL

Typical flow:

1. Create ML training model artifacts from Database View → Configure model.
2. Execute the generated DSL model so <ml-train> runs and persists model versions.
3. Validate outcome in ML Generator View.
4. Reuse the approved model version by following the EE-owned ml-train reference.

Note

Training can be long-running. Runtime sizing should match workload (rows/features), and some setups may require higher-end resources, including GPU-enabled workers.

For full flow guidance, see ML Generator from Database Metadata.