Parametrizing the sampling evals from the CLI #926
clefourrier
merged
41 commits into
main
from
clem-fix-870
defined a sampling type for metrics, works for cli, now needs to port…
ead5bdbd
rm useless case
8eece330
updated tests
8c5e5fb3
fix test
ed0a02bd
added conversion for normalizations
73947068
first pass transforming Hynek's metric functions into classes like th…
732c4887
imports
c0654c76
removed single token evals since we no longer have the feature, added…
a6e271a4
keep on making metrics more adjustable
511d0e69
updating test suite given the new names
bc4bb7ef
manual update of file
5d85a6e8
manual update of file
917fb791
fix mcc single token
a367d73e
now metrics are em
404d00f8
some fixs for tests
f9057504
rm trivia qa outdated
82b3fe9c
removed dumdum enum overwrite
5c4f9ab6
clefourrier
commented
on 2025-08-19
clefourrier
commented
on 2025-08-19
clefourrier
commented
on 2025-08-19
clefourrier
commented
on 2025-08-19
clefourrier
commented
on 2025-08-19
clefourrier
commented
on 2025-08-19
clefourrier
commented
on 2025-08-19
clefourrier
commented
on 2025-08-19
clefourrier
commented
on 2025-08-19
clefourrier
commented
on 2025-08-19
fix test
c31a39ff
rm a space
75419c1c
cleaner loop
915943f0
test
d047766f
better json encoder + a small naming fix
9e295109
new names
054c6d56
fix test
cc305815
Merge branch 'main' into clem-fix-870
8fd32a28
up doc
3dd79e2f
clefourrier
commented
on 2025-08-20
reorg
a07cde11
enforce correct classes
61506917
fix
5805b304
forgot to update extended tasks
ac5e0424
fix multilingual again
2cde9016
updated
e8274c97
NathanHB
commented
on 2025-08-20
fix
e043030e
clefourrier
commented
on 2025-08-20
Apply suggestions from code review
31d7d787
review comments
aeabbf9a
Merge branch 'main' into clem-fix-870
5ae3a8a1
fix dco
90f6b375
style
af2cd81c
doc
2f2dcfb2
updated quick tour
b1039e35
NathanHB
approved these changes
on 2025-08-21
Merge branch 'main' into clem-fix-870
98c80d45
Login to write a write a comment.
Login via GitHub