Skip to content

feat(task): use MetaMathQA (exp_metamath_p02) as the default expert group #193

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
isabella618033 wants to merge 1 commit into
base: master
Choose a base branch
from
Open

feat(task): use MetaMathQA (exp_metamath_p02) as the default expert group #193

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: 1 addition & 1 deletion connito/shared/config.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -484,7 +484,7 @@ class TaskCfg(BaseConfig):
_LOCKED_FIELDS: ClassVar[frozenset[str]] = frozenset({
"expert_group_name", "helper_group_id", "routing_mode",
})
expert_group_name: str = "exp_math"
expert_group_name: str = "exp_metamath_p02"
load_all_expert_groups: bool = False
base_path: Path = Path("expert_groups")
path: Path | None = None
Expand Down
2 changes: 1 addition & 1 deletion expert_groups/exp_metamath_p02/config.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
group_id: -1 # sentinel: not assigned to a functioning slot (would clash with exp_math=0 if left at the default)
group_id: 3 # active trainable slot for the MetaMathQA expert group (distinct from exp_math=0, helper exp_c4_p02=2)
# MetaMathQA-SFT ESFT-Token @ p=0.2
# Auto-generated from ESFT-Token @ p=0.2 profiling.
# Total experts across 26 MoE layers: 146
Expand Down
Loading