in progress

turbo-llm · Oct 29, 2024 · 9914764 · 9914764
1 parent f5a7d1d
commit 9914764
Showing 1 changed file with 1 addition and 1 deletion.
diff --git a/turbo_alignment/settings/pipelines/train/reinforce.py b/turbo_alignment/settings/pipelines/train/reinforce.py
@@ -18,7 +18,7 @@ class REINFORCETrainerSettings(TrainerSettings):
     kl_coef: float = 0.05
     mean_baseline_coef: float = 0.1
 
-    num_generations: int = 1
+    num_generations: int = 3
     num_samples_for_reward_stats: int = 0
 
     non_eos_penalty: bool = True