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

Jump to bottom

Fixed string literal error #338

Open
wants to merge 2 commits into
base: main
Choose a base branch
from
Open

Fixed string literal error #338

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
7cc3e81
Fixed string literal error
SulRash Oct 6, 2024
96069eb
Added changelog
SulRash Oct 6, 2024
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
2 changes: 2 additions & 0 deletions CHANGELOG.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,6 +21,8 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/)

### Bug Fixes

- Changed class comment under `RegressionRewardModelDataset` such that the warning comment: "WARNING: It's recommended to preprocess..." is now "WARNING: It is recommended to preprocess". Allows for wider compatiblity by fixing a syntax error due ot an unterminated string literal bug caused by the ' character when running code.

## NVIDIA NeMo-Aligner 0.5.0

### New Features and Optimizations
Expand Down
2 changes: 1 addition & 1 deletion nemo_aligner/data/nlp/datasets.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -454,7 +454,7 @@ class RegressionRewardModelDataset(RewardModelDataset):
we should set missing attributes to model.regression.loss_mask_val(according to training_rm.yaml)
in the dataset files so that their losses are masked. At least one attribute should be present for each sample.

WARNING: It's recommended to preprocess your data in advance to ensure all samples are within self.seq_length.
WARNING: It is recommended to preprocess your data in advance to ensure all samples are within self.seq_length.
Otherwise if all samples in a batch are longer than self.seq_length, you may get NaN loss.
"""

Expand Down
Loading