Skip to content

[misc] feat: add weight decay option in config #611

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

Merged
PeterSH6 merged 1 commit into from
Mar 15, 2025
Merged

[misc] feat: add weight decay option in config #611

Show file tree
Hide file tree
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: 2 additions & 0 deletions verl/trainer/config/ppo_megatron_trainer.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -42,6 +42,7 @@ actor_rollout_ref:
min_lr_ratio: null # only useful for warmup with cosine
warmup_style: constant # select from constant/cosine
total_training_steps: -1 # must be override by program
weight_decay: 0.01
megatron:
tensor_model_parallel_size: 4
pipeline_model_parallel_size: 1
Expand Down Expand Up @@ -106,6 +107,7 @@ critic:
min_lr_ratio: null # only useful for warmup with cosine
warmup_style: constant # select from constant/cosine
total_training_steps: -1 # must be override by program
weight_decay: 0.01
model:
path: ~/models/deepseek-llm-7b-chat
tokenizer_path: ${actor_rollout_ref.model.path}
Expand Down
2 changes: 2 additions & 0 deletions verl/trainer/config/ppo_trainer.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -46,6 +46,7 @@ actor_rollout_ref:
min_lr_ratio: null # only useful for warmup with cosine
warmup_style: constant # select from constant/cosine
total_training_steps: -1 # must be override by program
weight_decay: 0.01
fsdp_config:
wrap_policy:
# transformer_layer_cls_to_wrap: None
Expand Down Expand Up @@ -109,6 +110,7 @@ critic:
min_lr_ratio: null # only useful for warmup with cosine
warmup_style: constant # select from constant/cosine
total_training_steps: -1 # must be override by program
weight_decay: 0.01
model:
path: ~/models/deepseek-llm-7b-chat
tokenizer_path: ${actor_rollout_ref.model.path}
Expand Down