From 48b2fc48fb752415be43a73b771fc4443f5f9ffa Mon Sep 17 00:00:00 2001 From: Howard Liberty Date: Thu, 18 Apr 2024 13:07:15 -0700 Subject: [PATCH] Update src/transformers/training_args.py Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com> --- src/transformers/training_args.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/src/transformers/training_args.py b/src/transformers/training_args.py index 8605d697b1655a..9680ed4c4606b9 100644 --- a/src/transformers/training_args.py +++ b/src/transformers/training_args.py @@ -515,7 +515,7 @@ class TrainingArguments: ensure they are the same across all ranks after initialization - cpu_ram_efficient_loading (`bool`, *optional*, defaults to `False`) If `True`, only the first process loads the pretrained model checkpoint while all other processes - have empty weights. When this setting is `True`, `sync_module_states` also must to be `True`, + have empty weights. When this setting as `True`, `sync_module_states` also must to be `True`, otherwise all the processes except the main process would have random weights leading to unexpected behaviour during training. - activation_checkpointing (`bool`, *optional*, defaults to `False`):