> ## Documentation Index
> Fetch the complete documentation index at: https://docs.galileo.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Step 2 — Test set

> Pick or upload the labelled dataset Luna Studio will evaluate the fine-tuned metric against.

The test set is the **ground truth** for the run. After training, Luna Studio scores the resulting metric against this dataset and reports F1, AUC-ROC, and other result metrics on the Run details page.

<Frame caption="Step 2 — pick an existing test set or add a new one">
  <img src="https://mintcdn.com/v2galileo/-aQkdd7oOglUYIo1/images/luna-studio/runs/new-run-test-set.png?fit=max&auto=format&n=-aQkdd7oOglUYIo1&q=85&s=cc1f7b4b85f4c158b1691bef7d1f60f1" alt="Test set step" width="1024" height="659" data-path="images/luna-studio/runs/new-run-test-set.png" />
</Frame>

## Pick an existing test set

The **Test set** select shows test sets you've already added to this org. Each option includes a row count and source label, e.g. `rag-eval-dataset-v2 — 320 rows · Uploaded`.

Type into the select to filter by name.

## Add a new test set

If you don't have one yet, click the dropdown's **Add new test set** action. The **Add test set** modal opens.

<Frame caption="Add test set modal opened from Step 2 — same flow as the Datasets page">
  <img src="https://mintcdn.com/v2galileo/-aQkdd7oOglUYIo1/images/luna-studio/runs/new-run-add-test-set.png?fit=max&auto=format&n=-aQkdd7oOglUYIo1&q=85&s=be7113e733ba9517acd53806b8af0278" alt="Add test set modal" width="1024" height="659" data-path="images/luna-studio/runs/new-run-add-test-set.png" />
</Frame>

The modal title is **Add test set** with the subtitle "Test sets are curated labelled examples used to evaluate your metric." Three sources are available — see [Add a dataset](/luna-studio/ui/datasets/add-a-dataset) for a complete reference.

<CardGroup cols={3}>
  <Card title="Upload from local" icon="upload">
    Drag-and-drop a `.csv` or `.jsonl` file.
  </Card>

  <Card title="Fetch from URL" icon="link">
    Paste an `http://`, `https://`, `s3://`, or `gs://` URL.
  </Card>

  <Card title="Import from Galileo" icon="cloud-arrow-down">
    Browse datasets in your connected Galileo workspace.
  </Card>
</CardGroup>

Required columns: depends on the metric's input type, for more details see [Prerequisites](/luna-studio/ui/prerequisites).

<Note>Importing from Galileo requires an active [Galileo integration](/luna-studio/ui/integrations/galileo). If one isn't configured, Luna Studio prompts you to add it inline before the import panel appears.</Note>

## Validation

Luna Studio runs validation on the test set to ensure it meets the required schema / format / content rules.
If there are any validation errors, they will be highlighted (See example below).

<Frame caption="Step 2 with a validation error — the flow blocks Next until the schema is valid">
  <img src="https://mintcdn.com/v2galileo/-aQkdd7oOglUYIo1/images/luna-studio/runs/new-run-test-set-error.png?fit=max&auto=format&n=-aQkdd7oOglUYIo1&q=85&s=3b719385afe2e59efee5d94f0045cb47" alt="Test set validation error" width="1024" height="659" data-path="images/luna-studio/runs/new-run-test-set-error.png" />
</Frame>

## Dataset preview

If validation completes, you should see a preview of the test set rows.

The preview is paginated so you can inspect rows without leaving the run creation flow.

<Tip>Use the **Calculate F1 score** button to see the F1 score of your LLM-as-judge prompt on the selected test set. This is your benchmark score which Luna Studio will aim to achieve with a Luna metric.</Tip>

## Where to go next

<CardGroup cols={2}>
  <Card title="Step 3 — Training set" icon="dumbbell" href="/luna-studio/ui/runs/new-run/step-3-training-set">
    Generate from the test set, or upload your own.
  </Card>

  <Card title="Add a dataset" icon="database" href="/luna-studio/ui/datasets/add-a-dataset">
    Reference for all three dataset sources.
  </Card>
</CardGroup>