From 0f0b1fba152eee20c9840e08c502447fd613b6aa Mon Sep 17 00:00:00 2001 From: Datta Nimmaturi Date: Mon, 17 Nov 2025 12:09:36 +0530 Subject: [PATCH] Do not force set beta to 0 for DAPO (#3604) --- unsloth/models/rl.py | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/unsloth/models/rl.py b/unsloth/models/rl.py index ad7099eee7..3618e55825 100644 --- a/unsloth/models/rl.py +++ b/unsloth/models/rl.py @@ -814,10 +814,9 @@ def _patch_trl_rl_trainers(trainer_file = "grpo_trainer"): " if epsilon_high != 0.28:\n" " print('Unsloth: The DAPO paper recommends `epsilon_high = 0.28` - we will set it.')\n" " if beta != 0.0:\n" - " print('Unsloth: The DAPO paper recommends setting `beta = 0.0` to remove the KL term - we will set it.')\n" + " print(f'[WARNING] Unsloth: The DAPO paper recommends setting `beta = 0.0` to remove the KL term - You have set it to {beta}.')\n" " mask_truncated_completions = True\n" " epsilon_high = 0.28\n" - " beta = 0.0\n" "\n" ) extra_args += check_dr_grpo