Repetitions and Resume

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()

@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)

resumed = base_run.resume(
    resume=ze.ResumeConfig(mode="force", skip_completed=True),
)

# Good: stable row identity
{"row_id": "q1", "question": "...", "answer": "..."}

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