Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[DataCollatorForCompletionOnlyLM] Warn on identical eos_token_id and pad_token_id #988

Merged
merged 1 commit into from
Nov 14, 2023
Merged

[DataCollatorForCompletionOnlyLM] Warn on identical eos_token_id and pad_token_id #988

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 8 additions & 0 deletions trl/trainer/utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -99,6 +99,14 @@ def __init__(
# The user already provides the token ids
self.response_token_ids = response_template

if not self.mlm and self.instruction_template and self.tokenizer.pad_token_id == self.tokenizer.eos_token_id:
warnings.warn(
"The pad_token_id and eos_token_id values of this tokenizer are identical. "
"If you are planning for multi-turn training, "
"it can result in the model continuously generating questions and answers without eos token. "
"To avoid this, set the pad_token_id to a different value."
)

self.ignore_index = ignore_index

def torch_call(self, examples: List[Union[List[int], Any, Dict[str, Any]]]) -> Dict[str, Any]:
Expand Down
Loading