Skip to content

docs: drop dangling Dr.GRPO custom-reducer example reference #2096

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
zhuzilin merged 1 commit into from
Jun 18, 2026
Merged

docs: drop dangling Dr.GRPO custom-reducer example reference #2096

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: 0 additions & 2 deletions docs/en/get_started/customization.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -298,8 +298,6 @@ def get_pg_loss_reducer(
- Dr.GRPO: Divide by a constant instead of effective token count
- Custom loss normalization strategies

**Example**: `examples/DrGRPO/custom_reducer.py:get_pg_loss_reducer`

---

### 12. Reward Post-Processing (`--custom-reward-post-process-path`)
Expand Down
2 changes: 0 additions & 2 deletions docs/zh/get_started/customization.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -298,8 +298,6 @@ def get_pg_loss_reducer(
- Dr.GRPO：除以常数而非有效 token 数
- 自定义损失归一化策略

**示例**: `examples/DrGRPO/custom_reducer.py:get_pg_loss_reducer`

---

### 12. 奖励后处理 (`--custom-reward-post-process-path`)
Expand Down
2 changes: 1 addition & 1 deletion slime/utils/arguments.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1050,7 +1050,7 @@ def add_algo_arguments(parser):
"--custom-pg-loss-reducer-function-path",
type=str,
default=None,
help="Path to a custom reducer function for pg_loss only. When set, pg_loss will use this custom reducer while other metrics (pg_clipfrac, ppo_kl, entropy_loss, etc.) still use the default sum_of_sample_mean. (e.g., examples/Dr.GRPO/custom_reducer.py:get_pg_loss_reducer).",
help="Path to a custom reducer function for pg_loss only. When set, pg_loss will use this custom reducer while other metrics (pg_clipfrac, ppo_kl, entropy_loss, etc.) still use the default sum_of_sample_mean.",
)

parser.add_argument(
Expand Down
Loading