We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent 4d9dc3d commit b397753Copy full SHA for b397753
1 file changed
sieves/tests/tasks/predictive/test_summarization.py
@@ -164,10 +164,10 @@ def test_evaluation(batch_runtime) -> None:
164
165
# 2. No overlap
166
doc_none = Doc(text="The quick brown fox jumps over the lazy dog.")
167
- doc_none.results["sum"] = Result(summary="The weather is nice today.", score=1.0)
+ doc_none.results["sum"] = Result(summary="A ball is a sphere.", score=1.0)
168
doc_none.gold["sum"] = Result(summary="Fast fox jumps dog.", score=1.0)
169
report_none = task.evaluate([doc_none], judge=batch_runtime.model)
170
- assert report_none.metrics[task.metric] < 0.6
+ assert report_none.metrics[task.metric] <= 0.5
171
172
# 3. Partial overlap
173
doc_partial = Doc(text="The quick brown fox jumps over the lazy dog.")
0 commit comments