Skip to content

Fix typo in doc and check selector #437

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
pan-x-c merged 2 commits into from
Dec 12, 2025
Merged

Fix typo in doc and check selector #437

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
1d19ea4
fix typo
hiyuchang Dec 12, 2025
fb56e89
fix import
hiyuchang Dec 12, 2025
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: 1 addition & 1 deletion docs/sphinx_doc/source/tutorial/align_with_verl.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -60,7 +60,7 @@ To match the default training setup of veRL, we set `synchronizer.sync_style=fix
| `data.max_response_length` | `model.max_response_tokens` | - |
| `data.filter_overlong_prompts` | `model.enable_prompt_truncation` | Explained later |
| `data.truncation` | - | Equivalent to `right` |
| `data.shuffle` | `buffer.explorer_input.taskset.task_selector.selector_type:random` | Taskset-specific |
| `data.shuffle` | `buffer.explorer_input.taskset.task_selector.selector_type:shuffle` | Taskset-specific |

💡 Detailed explanation:

Expand Down
2 changes: 1 addition & 1 deletion docs/sphinx_doc/source_zh/tutorial/align_with_verl.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -60,7 +60,7 @@ Trinity-RFT 根据功能将强化微调的大量参数分为几个部分，例
| `data.max_response_length` | `model.max_response_tokens` | - |
| `data.filter_overlong_prompts` | `model.enable_prompt_truncation` | 稍后说明 |
| `data.truncation` | - | 等同于 `right` |
| `data.shuffle` | `buffer.explorer_input.taskset.task_selector.selector_type:random` | Taskset-specific |
| `data.shuffle` | `buffer.explorer_input.taskset.task_selector.selector_type:shuffle` | Taskset-specific |

💡 详细说明：

Expand Down
9 changes: 9 additions & 0 deletions trinity/common/config.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -932,6 +932,15 @@ def _check_explorer_input(self) -> None:
set_if_none(taskset.rollout_args, "max_tokens", self.model.max_response_tokens)
set_if_none(taskset.format, "chat_template", self.model.custom_chat_template)

# check if selector is supported
from trinity.buffer.selector import SELECTORS

selector = SELECTORS.get(taskset.task_selector.selector_type)
if selector is None:
raise ValueError(
f"Selector {taskset.task_selector.selector_type} is not supported."
)

for idx, dataset in enumerate(explorer_input.eval_tasksets):
if not dataset.path:
raise ValueError(f"Eval dataset [{dataset}]'s path is not configured.")
Expand Down