Skip to content

Fix typo: num_generation -> num_generations #842

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

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Fix typo: num_generation -> num_generations #842

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
4 changes: 2 additions & 2 deletions chapters/en/chapter12/4.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -90,7 +90,7 @@ training_args = GRPOConfig(
# Essential parameters
output_dir="output",
num_train_epochs=3,
num_generation=4, # Number of completions to generate for each prompt
num_generations=4, # Number of completions to generate for each prompt
per_device_train_batch_size=4, # We want to get all generations in one device batch
# Optional but useful
gradient_accumulation_steps=2,
Expand All @@ -101,7 +101,7 @@ training_args = GRPOConfig(
)
```

The `num_generation` parameter is particularly important for GRPO as it defines the group size - how many different completions the model will generate for each prompt. This is a key differentiator from other RL methods:
The `num_generations` parameter is particularly important for GRPO as it defines the group size - how many different completions the model will generate for each prompt. This is a key differentiator from other RL methods:

- Too small (e.g., 2-3): May not provide enough diversity for meaningful comparisons
- Recommended (4-16): Provides good balance between diversity and computational efficiency
Expand Down