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

remove duplicate 340b params #454

Merged
merged 1 commit into from
Jan 7, 2025
Merged

remove duplicate 340b params #454

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
2 changes: 0 additions & 2 deletions launcher_scripts/conf/training/nemotron/nemotron_340b.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -135,7 +135,6 @@ model:
defer_embedding_wgrad_compute: True
wgrad_deferral_limit: 22
cross_entropy_loss_fusion: True
enable_vboost: True
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Where is enable_vboost defined if this is removed?

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

defined in launcher_scripts/conf/config.yaml...

the one defined above is under model key which is redundant as vboost is used outside the scope of model

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

the main issue was with duplicated ub_tp_comm_overlap key which caused jobs to crash

ub_tp_comm_overlap: True
apply_rope_fusion: True
deteministic_mode: False
Expand All @@ -161,7 +160,6 @@ model:
fp8_amax_history_len: 1024 # Number of steps for which amax history is recorded per tensor
fp8_amax_compute_algo: max # 'most_recent' or 'max'. Algorithm for computing amax from history
fp8_wgrad: True
ub_tp_comm_overlap: False

optim:
name: mcore_distributed_optim
Expand Down
Loading