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

# Repetitions and Resume

> Repeat runs for uncertainty and resume interrupted executions safely

## Repeat a run

Use `run.repeat(n)` to execute the same run configuration multiple times.
`n` is the **total number of runs**, including the base run.

```python theme={"theme":{"light":"github-light","dark":"github-dark"}}
base_run = dataset.eval(predict, workers=8)
base_run = base_run.score([exact_match, accuracy], column_map=...)

run_collection = base_run.repeat(5)
all_runs = run_collection.to_list()
```

In this example, `all_runs` contains 5 total runs, not 5 additional runs.

Each repeated run:

* Reuses the same task
* Shares the same backend eval id context
* Can inherit evaluation plans

## Run-level metrics over repeated runs

```python theme={"theme":{"light":"github-light","dark":"github-dark"}}
@ze.evaluation(mode="run", outputs=["accuracy_mean", "accuracy_n"])
def accuracy_over_repeats(all_runs):
    vals = [r.metrics["accuracy"] for r in all_runs if "accuracy" in r.metrics]
    return {
        "accuracy_mean": (sum(vals) / len(vals)) if vals else 0.0,
        "accuracy_n": len(vals),
    }

aggregate = all_runs[0]
aggregate.run_metrics([accuracy_over_repeats], all_runs=all_runs)
print(aggregate.metrics)
```

Run-level metrics only make sense after repeated runs because they aggregate over
`all_runs`, not over rows from a single run.

## Resume interrupted runs

Resume from an existing run and skip already completed rows:

```python theme={"theme":{"light":"github-light","dark":"github-dark"}}
resumed = base_run.resume(
    resume=ze.ResumeConfig(mode="force", skip_completed=True),
)
```

You can also provide resume behavior in initial `dataset.eval(...)` calls.

## Resume modes

<Tabs>
  <Tab title="auto">
    Attempt resume when possible. Safe default for most workflows.
  </Tab>

  <Tab title="force">
    Explicitly enforce resume behavior. Best when you know prior results exist.
  </Tab>

  <Tab title="fresh">Ignore previous progress and execute as a clean run.</Tab>
</Tabs>

## Requirements for skip-completed

When `skip_completed=True`, each row needs stable identity (`row_id` or `id`) so the SDK can detect already-finished rows.

<Warning>
  If rows do not include stable identifiers, resume with skip-completed may fail
  or behave unexpectedly.
</Warning>

```python theme={"theme":{"light":"github-light","dark":"github-dark"}}
# Good: stable row identity
{"row_id": "q1", "question": "...", "answer": "..."}

# Risky: no stable row identity
{"question": "...", "answer": "..."}
```