From 9f354c14476201eaa84b5f9c45b71fabbdbd0aff Mon Sep 17 00:00:00 2001 From: Seth Weidman Date: Wed, 19 Feb 2025 02:12:07 -0800 Subject: [PATCH] Update rl_replacements.py (#1754) Fix typo in comment: know -> now. This was printed when running the Llama3.1_(8B)-GRPO.ipynb example notebook, so I'd expect others to run into it as well. --- unsloth/models/rl_replacements.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/unsloth/models/rl_replacements.py b/unsloth/models/rl_replacements.py index 5fa4ec5a4f..c8caa1b585 100644 --- a/unsloth/models/rl_replacements.py +++ b/unsloth/models/rl_replacements.py @@ -268,7 +268,7 @@ def grpo_trainer_fix_batch_size(RLTrainer_source, RLConfig_source): check_batch_size = \ "div = per_device_train_batch_size // num_generations\n"\ "if div * num_generations != per_device_train_batch_size:\n"\ - " print('Unsloth: We know expect `per_device_train_batch_size` to be a multiple of `num_generations`.\\n"\ + " print('Unsloth: We now expect `per_device_train_batch_size` to be a multiple of `num_generations`.\\n"\ "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" return check_batch_size