You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
@@ -32,12 +33,15 @@ class BootstrapFewShotWithRandomSearch(BootstrapFewShot):
32
33
33
34
**Parameters:**
34
35
-`metric` (_callable_, _optional_): Metric function to evaluate examples during bootstrapping. Defaults to `None`.
35
-
-`teacher_settings` (_dict_, _optional_): Settings for teacher predictor. Defaults to empty dictionary.
36
+
-`teacher_settings` (_dict_, _optional_): Settings for teacher predictor. Defaults to an empty dictionary.
36
37
-`max_bootstrapped_demos` (_int_, _optional_): Maximum number of bootstrapped demonstrations per predictor. Defaults to 4.
37
38
-`max_labeled_demos` (_int_, _optional_): Maximum number of labeled demonstrations per predictor. Defaults to 16.
38
39
-`max_rounds` (_int_, _optional_): Maximum number of bootstrapping rounds. Defaults to 1.
39
-
-`num_candidate_programs` (_int_): Number of candidate programs to generate during random search.
40
-
-`num_threads` (_int_): Number of threads used for evaluation during random search.
40
+
-`num_candidate_programs` (_int_): Number of candidate programs to generate during random search. Defaults to 16.
41
+
-`num_threads` (_int_): Number of threads used for evaluation during random search. Defaults to 6.
42
+
-`max_errors` (_int_): Maximum errors permitted during evaluation. Halts run with the latest error message. Defaults to 10. Configure to 1 if no evaluation run error is desired.
43
+
-`stop_at_score` (_float_, _optional_): Score threshold for random search to stop early. Defaults to `None`.
44
+
-`metric_threshold` (_float_, _optional_): Score threshold for metric to determine successful example. Defaults to `None`.
0 commit comments