Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in / Register
Toggle navigation
Menu
Open sidebar
gaoqiong
lm-evaluation-harness
Commits
1e4e058c
Commit
1e4e058c
authored
Jun 24, 2024
by
Yu Shi Jie
Browse files
mmlu-pro: added continuation and flan_cot_zeroshot
parent
23bd3449
Changes
32
Show whitespace changes
Inline
Side-by-side
Showing
12 changed files
with
72 additions
and
0 deletions
+72
-0
lm_eval/tasks/mmlu_pro/flan_cot_zeroshot/mmlu_pro_chemistry.yaml
.../tasks/mmlu_pro/flan_cot_zeroshot/mmlu_pro_chemistry.yaml
+6
-0
lm_eval/tasks/mmlu_pro/flan_cot_zeroshot/mmlu_pro_computer_science.yaml
...mmlu_pro/flan_cot_zeroshot/mmlu_pro_computer_science.yaml
+6
-0
lm_eval/tasks/mmlu_pro/flan_cot_zeroshot/mmlu_pro_economics.yaml
.../tasks/mmlu_pro/flan_cot_zeroshot/mmlu_pro_economics.yaml
+6
-0
lm_eval/tasks/mmlu_pro/flan_cot_zeroshot/mmlu_pro_engineering.yaml
...asks/mmlu_pro/flan_cot_zeroshot/mmlu_pro_engineering.yaml
+6
-0
lm_eval/tasks/mmlu_pro/flan_cot_zeroshot/mmlu_pro_health.yaml
...val/tasks/mmlu_pro/flan_cot_zeroshot/mmlu_pro_health.yaml
+6
-0
lm_eval/tasks/mmlu_pro/flan_cot_zeroshot/mmlu_pro_history.yaml
...al/tasks/mmlu_pro/flan_cot_zeroshot/mmlu_pro_history.yaml
+6
-0
lm_eval/tasks/mmlu_pro/flan_cot_zeroshot/mmlu_pro_law.yaml
lm_eval/tasks/mmlu_pro/flan_cot_zeroshot/mmlu_pro_law.yaml
+6
-0
lm_eval/tasks/mmlu_pro/flan_cot_zeroshot/mmlu_pro_math.yaml
lm_eval/tasks/mmlu_pro/flan_cot_zeroshot/mmlu_pro_math.yaml
+6
-0
lm_eval/tasks/mmlu_pro/flan_cot_zeroshot/mmlu_pro_other.yaml
lm_eval/tasks/mmlu_pro/flan_cot_zeroshot/mmlu_pro_other.yaml
+6
-0
lm_eval/tasks/mmlu_pro/flan_cot_zeroshot/mmlu_pro_philosophy.yaml
...tasks/mmlu_pro/flan_cot_zeroshot/mmlu_pro_philosophy.yaml
+6
-0
lm_eval/tasks/mmlu_pro/flan_cot_zeroshot/mmlu_pro_physics.yaml
...al/tasks/mmlu_pro/flan_cot_zeroshot/mmlu_pro_physics.yaml
+6
-0
lm_eval/tasks/mmlu_pro/flan_cot_zeroshot/mmlu_pro_psychology.yaml
...tasks/mmlu_pro/flan_cot_zeroshot/mmlu_pro_psychology.yaml
+6
-0
No files found.
lm_eval/tasks/mmlu_pro/flan_cot_zeroshot/mmlu_pro_chemistry.yaml
0 → 100644
View file @
1e4e058c
"
dataset_name"
:
"
math"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
math.
\n\
\n
"
"
group"
:
"
mmlu_pro_flan_cot_zeroshot_stem"
"
include"
:
"
_mmlu_pro_flan_cot_zeroshot_template_yaml"
"
task"
:
"
mmlu_pro_flan_cot_zeroshot_chemistry"
\ No newline at end of file
lm_eval/tasks/mmlu_pro/flan_cot_zeroshot/mmlu_pro_computer_science.yaml
0 → 100644
View file @
1e4e058c
"
dataset_name"
:
"
computer_science"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
computer_science.
\n\
\n
"
"
group"
:
"
mmlu_pro_flan_cot_zeroshot_stem"
"
include"
:
"
_mmlu_pro_flan_cot_zeroshot_template_yaml"
"
task"
:
"
mmlu_pro_flan_cot_zeroshot_computer_science"
lm_eval/tasks/mmlu_pro/flan_cot_zeroshot/mmlu_pro_economics.yaml
0 → 100644
View file @
1e4e058c
"
dataset_name"
:
"
economics"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
economics.
\n\
\n
"
"
group"
:
"
mmlu_pro_flan_cot_zeroshot_social_sciences"
"
include"
:
"
_mmlu_pro_flan_cot_zeroshot_template_yaml"
"
task"
:
"
mmlu_pro_flan_cot_zeroshot_economics"
lm_eval/tasks/mmlu_pro/flan_cot_zeroshot/mmlu_pro_engineering.yaml
0 → 100644
View file @
1e4e058c
"
dataset_name"
:
"
engineering"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
engineering.
\n\
\n
"
"
group"
:
"
mmlu_pro_flan_cot_zeroshot_stem"
"
include"
:
"
_mmlu_pro_flan_cot_zeroshot_template_yaml"
"
task"
:
"
mmlu_pro_flan_cot_zeroshot_engineering"
lm_eval/tasks/mmlu_pro/flan_cot_zeroshot/mmlu_pro_health.yaml
0 → 100644
View file @
1e4e058c
"
dataset_name"
:
"
health"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
health.
\n\
\n
"
"
group"
:
"
mmlu_pro_flan_cot_zeroshot_other"
"
include"
:
"
_mmlu_pro_flan_cot_zeroshot_template_yaml"
"
task"
:
"
mmlu_pro_flan_cot_zeroshot_health"
lm_eval/tasks/mmlu_pro/flan_cot_zeroshot/mmlu_pro_history.yaml
0 → 100644
View file @
1e4e058c
"
dataset_name"
:
"
history"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
history.
\n\
\n
"
"
group"
:
"
mmlu_pro_flan_cot_zeroshot_humanities"
"
include"
:
"
_mmlu_pro_flan_cot_zeroshot_template_yaml"
"
task"
:
"
mmlu_pro_flan_cot_zeroshot_history"
lm_eval/tasks/mmlu_pro/flan_cot_zeroshot/mmlu_pro_law.yaml
0 → 100644
View file @
1e4e058c
"
dataset_name"
:
"
law"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
law.
\n\
\n
"
"
group"
:
"
mmlu_pro_flan_cot_zeroshot_humanities"
"
include"
:
"
_mmlu_pro_flan_cot_zeroshot_template_yaml"
"
task"
:
"
mmlu_pro_flan_cot_zeroshot_law"
lm_eval/tasks/mmlu_pro/flan_cot_zeroshot/mmlu_pro_math.yaml
0 → 100644
View file @
1e4e058c
"
dataset_name"
:
"
math"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
math.
\n\
\n
"
"
group"
:
"
mmlu_pro_flan_cot_zeroshot_stem"
"
include"
:
"
_mmlu_pro_flan_cot_zeroshot_template_yaml"
"
task"
:
"
mmlu_pro_flan_cot_zeroshot_math"
lm_eval/tasks/mmlu_pro/flan_cot_zeroshot/mmlu_pro_other.yaml
0 → 100644
View file @
1e4e058c
"
dataset_name"
:
"
other"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
other.
\n\
\n
"
"
group"
:
"
mmlu_pro_flan_cot_zeroshot_other"
"
include"
:
"
_mmlu_pro_flan_cot_zeroshot_template_yaml"
"
task"
:
"
mmlu_pro_flan_cot_zeroshot_other"
lm_eval/tasks/mmlu_pro/flan_cot_zeroshot/mmlu_pro_philosophy.yaml
0 → 100644
View file @
1e4e058c
"
dataset_name"
:
"
philosophy"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
philosophy.
\n\
\n
"
"
group"
:
"
mmlu_pro_flan_cot_zeroshot_humanities"
"
include"
:
"
_mmlu_pro_flan_cot_zeroshot_template_yaml"
"
task"
:
"
mmlu_pro_flan_cot_zeroshot_philosophy"
lm_eval/tasks/mmlu_pro/flan_cot_zeroshot/mmlu_pro_physics.yaml
0 → 100644
View file @
1e4e058c
"
dataset_name"
:
"
physics"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
physics.
\n\
\n
"
"
group"
:
"
mmlu_pro_flan_cot_zeroshot_stem"
"
include"
:
"
_mmlu_pro_flan_cot_zeroshot_template_yaml"
"
task"
:
"
mmlu_pro_flan_cot_zeroshot_physics"
lm_eval/tasks/mmlu_pro/flan_cot_zeroshot/mmlu_pro_psychology.yaml
0 → 100644
View file @
1e4e058c
"
dataset_name"
:
"
psychology"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
psychology.
\n\
\n
"
"
group"
:
"
mmlu_pro_flan_cot_zeroshot_social_sciences"
"
include"
:
"
_mmlu_pro_flan_cot_zeroshot_template_yaml"
"
task"
:
"
mmlu_pro_flan_cot_zeroshot_psychology"
Prev
1
2
Next
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
.
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment