Score unparseable answers without aborting batches
This commit is contained in:
@@ -84,6 +84,23 @@ class PipelineTests(unittest.TestCase):
|
||||
)
|
||||
self.assertIn("A compact behavioral problem.", (output / "rendered.jsonl").read_text())
|
||||
|
||||
def test_unparseable_solver_output_is_scored_without_stopping_batch(self):
|
||||
renderer = QueueClient([{"problem": "A compact behavioral problem."}])
|
||||
solver = QueueClient(["The response ended before its final label."])
|
||||
with tempfile.TemporaryDirectory() as directory:
|
||||
output = Path(directory)
|
||||
summary = run_evaluation(
|
||||
renderer=renderer,
|
||||
solver=solver,
|
||||
count=1,
|
||||
length="short",
|
||||
seed=1,
|
||||
output_dir=output,
|
||||
)
|
||||
self.assertEqual(summary["parsed"], 0)
|
||||
self.assertEqual(summary["correct"], 0)
|
||||
self.assertIn('"parse_error":', (output / "results.jsonl").read_text())
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
|
||||
Reference in New Issue
Block a user