Add downstream eval to puzzletron v2 - #2104

Open

grzegorz-k-karch wants to merge 15 commits into

feature/puzzletron_v2from

gkarch/add_downstream_eval

Commits on Jul 29, 2026

added downstream evaluation
grzegorz-k-karch
committed
d938fc6
added yaml for nano eval
grzegorz-k-karch
committed
e482491

Commits on Aug 4, 2026

Label downstream evaluation dashboard stages
grzegorz-k-karch
committed
6560173

Commits on Aug 6, 2026

nano/smoke pipeline works with downstream eval
grzegorz-k-karch
committed
afbb964

Commits on Aug 7, 2026

📝 Add docstrings to `gkarch/add_downstream_eval` (#2105)
coderabbitai[bot]
authored
380527f
Merge branch 'feature/puzzletron_v2' into gkarch/add_downstream_eval
grzegorz-k-karch
committed
275ca3d
fix: CodeRabbit auto-fixes for PR #2104 (#2106)

coderabbitai[bot]
and
CodeRabbit
authored
3798b10
drop docstring churn
grzegorz-k-karch
committed
5728584
undid changes not related to evaluation
grzegorz-k-karch
committed
5ac513e
fix: validate lmms-eval task completion
grzegorz-k-karch
committed
05b273d
fix: align lmms metric suggestions
grzegorz-k-karch
committed
e74f362
fix: guard lmms-eval reserved args
grzegorz-k-karch
committed
e1c13f7

Commits on Aug 8, 2026

fix: clean up lmms-eval process group
grzegorz-k-karch
committed
a899538
docs: pin lmms-eval example version
grzegorz-k-karch
committed
57ccb99
fix: isolate lmms-eval dependency pin
grzegorz-k-karch
committed
7e990d1