From c1c37c49a6d680cb3c784ab9cdba73e01be75595 Mon Sep 17 00:00:00 2001 From: Daniel Han Date: Sun, 22 Sep 2024 22:48:35 -0700 Subject: [PATCH] Update tokenizer_utils.py --- unsloth/tokenizer_utils.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/unsloth/tokenizer_utils.py b/unsloth/tokenizer_utils.py index b8f710b2c5..89e62c717a 100644 --- a/unsloth/tokenizer_utils.py +++ b/unsloth/tokenizer_utils.py @@ -916,7 +916,7 @@ def fix_untrained_tokens(model, tokenizer, train_dataset, eps = 1e-16): if bad_not_trainable: raise ValueError( - 'Unsloth: Untrained tokens found, but embed_tokens & lm_head not trainable, causing NaNs. '\ + f'Unsloth: Untrained tokens for [{where_untrained_set}] found, but embed_tokens & lm_head not trainable, causing NaNs. '\ 'Restart then add `embed_tokens` & `lm_head` to '\ '`FastLanguageModel.get_peft_model(target_modules = [..., "embed_tokens", "lm_head",]). `'\ 'Are you using the `base` model? Instead, use the `instruct` version to silence this warning.',