Improve optimization

2025-10-31 16:04:28 +05:30
parent a9655c8d31
commit a24e6eba96
4 changed files with 24 additions and 7 deletions
@@ -17,9 +17,11 @@ max_response_length = 100

 max_kl_divergence = 0.5

-kl_score_shape = 5.0
+kl_score_shape = 3.0

-n_trials = 100
+n_trials = 200
+
+n_startup_trials = 60

 refusal_markers = [
    "sorry",