From 19d6ff7862bf7da63449c8257cde41cbcc83f1b1 Mon Sep 17 00:00:00 2001 From: Daniel Han Date: Wed, 28 May 2025 05:26:01 -0700 Subject: [PATCH] Update rl.py --- unsloth/models/rl.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/unsloth/models/rl.py b/unsloth/models/rl.py index c909eb6a5e..48a8b00481 100644 --- a/unsloth/models/rl.py +++ b/unsloth/models/rl.py @@ -511,7 +511,7 @@ def _patch_trl_rl_trainers(trainer_file = "grpo_trainer"): "We will change the batch size of ' + str(per_device_train_batch_size) + ' to the `num_generations` of ' + str(num_generations))\n"\ " per_device_train_batch_size = num_generations\n"\ "\n" - extra_args += check_dr_grpo + extra_args += check_num_generations pass # Edit config with anything extra