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
2106fbeb
Commit
2106fbeb
authored
Jan 15, 2025
by
Baber
Browse files
Merge branch 'main' into mathvista
# Conflicts: # lm_eval/models/openai_completions.py
parents
4354fe46
703fbffd
Changes
574
Hide whitespace changes
Inline
Side-by-side
Showing
20 changed files
with
114 additions
and
0 deletions
+114
-0
lm_eval/tasks/llama3/instruct/mmlu/_mmlu_stem.yaml
lm_eval/tasks/llama3/instruct/mmlu/_mmlu_stem.yaml
+11
-0
lm_eval/tasks/llama3/instruct/mmlu/llama.yaml
lm_eval/tasks/llama3/instruct/mmlu/llama.yaml
+13
-0
lm_eval/tasks/llama3/instruct/mmlu/mmlu_abstract_algebra.yaml
...val/tasks/llama3/instruct/mmlu/mmlu_abstract_algebra.yaml
+5
-0
lm_eval/tasks/llama3/instruct/mmlu/mmlu_anatomy.yaml
lm_eval/tasks/llama3/instruct/mmlu/mmlu_anatomy.yaml
+5
-0
lm_eval/tasks/llama3/instruct/mmlu/mmlu_astronomy.yaml
lm_eval/tasks/llama3/instruct/mmlu/mmlu_astronomy.yaml
+5
-0
lm_eval/tasks/llama3/instruct/mmlu/mmlu_business_ethics.yaml
lm_eval/tasks/llama3/instruct/mmlu/mmlu_business_ethics.yaml
+5
-0
lm_eval/tasks/llama3/instruct/mmlu/mmlu_clinical_knowledge.yaml
...l/tasks/llama3/instruct/mmlu/mmlu_clinical_knowledge.yaml
+5
-0
lm_eval/tasks/llama3/instruct/mmlu/mmlu_college_biology.yaml
lm_eval/tasks/llama3/instruct/mmlu/mmlu_college_biology.yaml
+5
-0
lm_eval/tasks/llama3/instruct/mmlu/mmlu_college_chemistry.yaml
...al/tasks/llama3/instruct/mmlu/mmlu_college_chemistry.yaml
+5
-0
lm_eval/tasks/llama3/instruct/mmlu/mmlu_college_computer_science.yaml
...s/llama3/instruct/mmlu/mmlu_college_computer_science.yaml
+5
-0
lm_eval/tasks/llama3/instruct/mmlu/mmlu_college_mathematics.yaml
.../tasks/llama3/instruct/mmlu/mmlu_college_mathematics.yaml
+5
-0
lm_eval/tasks/llama3/instruct/mmlu/mmlu_college_medicine.yaml
...val/tasks/llama3/instruct/mmlu/mmlu_college_medicine.yaml
+5
-0
lm_eval/tasks/llama3/instruct/mmlu/mmlu_college_physics.yaml
lm_eval/tasks/llama3/instruct/mmlu/mmlu_college_physics.yaml
+5
-0
lm_eval/tasks/llama3/instruct/mmlu/mmlu_computer_security.yaml
...al/tasks/llama3/instruct/mmlu/mmlu_computer_security.yaml
+5
-0
lm_eval/tasks/llama3/instruct/mmlu/mmlu_conceptual_physics.yaml
...l/tasks/llama3/instruct/mmlu/mmlu_conceptual_physics.yaml
+5
-0
lm_eval/tasks/llama3/instruct/mmlu/mmlu_econometrics.yaml
lm_eval/tasks/llama3/instruct/mmlu/mmlu_econometrics.yaml
+5
-0
lm_eval/tasks/llama3/instruct/mmlu/mmlu_electrical_engineering.yaml
...sks/llama3/instruct/mmlu/mmlu_electrical_engineering.yaml
+5
-0
lm_eval/tasks/llama3/instruct/mmlu/mmlu_elementary_mathematics.yaml
...sks/llama3/instruct/mmlu/mmlu_elementary_mathematics.yaml
+5
-0
lm_eval/tasks/llama3/instruct/mmlu/mmlu_formal_logic.yaml
lm_eval/tasks/llama3/instruct/mmlu/mmlu_formal_logic.yaml
+5
-0
lm_eval/tasks/llama3/instruct/mmlu/mmlu_global_facts.yaml
lm_eval/tasks/llama3/instruct/mmlu/mmlu_global_facts.yaml
+5
-0
No files found.
lm_eval/tasks/llama3/instruct/mmlu/_mmlu_stem.yaml
0 → 100644
View file @
2106fbeb
group
:
mmlu_llama_stem
group_alias
:
stem
task
:
-
mmlu_llama_stem_tasks
aggregate_metric_list
:
-
metric
:
exact_match
aggregation
:
mean
weight_by_size
:
True
filter_list
:
[
strict_match
]
metadata
:
version
:
0
lm_eval/tasks/llama3/instruct/mmlu/llama.yaml
0 → 100644
View file @
2106fbeb
group
:
mmlu_llama
task
:
-
mmlu_llama_stem
-
mmlu_llama_other
-
mmlu_llama_social_sciences
-
mmlu_llama_humanities
aggregate_metric_list
:
-
metric
:
exact_match
aggregation
:
mean
weight_by_size
:
True
filter_list
:
[
strict_match
]
metadata
:
version
:
1
lm_eval/tasks/llama3/instruct/mmlu/mmlu_abstract_algebra.yaml
0 → 100644
View file @
2106fbeb
"
dataset_name"
:
"
abstract_algebra"
"
include"
:
"
_continuation_template_yaml"
"
tag"
:
"
mmlu_llama_stem_tasks"
"
task"
:
"
mmlu_llama_abstract_algebra"
"
task_alias"
:
"
abstract
algebra"
lm_eval/tasks/llama3/instruct/mmlu/mmlu_anatomy.yaml
0 → 100644
View file @
2106fbeb
"
dataset_name"
:
"
anatomy"
"
include"
:
"
_continuation_template_yaml"
"
tag"
:
"
mmlu_llama_stem_tasks"
"
task"
:
"
mmlu_llama_anatomy"
"
task_alias"
:
"
anatomy"
lm_eval/tasks/llama3/instruct/mmlu/mmlu_astronomy.yaml
0 → 100644
View file @
2106fbeb
"
dataset_name"
:
"
astronomy"
"
include"
:
"
_continuation_template_yaml"
"
tag"
:
"
mmlu_llama_stem_tasks"
"
task"
:
"
mmlu_llama_astronomy"
"
task_alias"
:
"
astronomy"
lm_eval/tasks/llama3/instruct/mmlu/mmlu_business_ethics.yaml
0 → 100644
View file @
2106fbeb
"
dataset_name"
:
"
business_ethics"
"
include"
:
"
_continuation_template_yaml"
"
tag"
:
"
mmlu_llama_other_tasks"
"
task"
:
"
mmlu_llama_business_ethics"
"
task_alias"
:
"
business
ethics"
lm_eval/tasks/llama3/instruct/mmlu/mmlu_clinical_knowledge.yaml
0 → 100644
View file @
2106fbeb
"
dataset_name"
:
"
clinical_knowledge"
"
include"
:
"
_continuation_template_yaml"
"
tag"
:
"
mmlu_llama_other_tasks"
"
task"
:
"
mmlu_llama_clinical_knowledge"
"
task_alias"
:
"
clinical
knowledge"
lm_eval/tasks/llama3/instruct/mmlu/mmlu_college_biology.yaml
0 → 100644
View file @
2106fbeb
"
dataset_name"
:
"
college_biology"
"
include"
:
"
_continuation_template_yaml"
"
tag"
:
"
mmlu_llama_stem_tasks"
"
task"
:
"
mmlu_llama_college_biology"
"
task_alias"
:
"
college
biology"
lm_eval/tasks/llama3/instruct/mmlu/mmlu_college_chemistry.yaml
0 → 100644
View file @
2106fbeb
"
dataset_name"
:
"
college_chemistry"
"
include"
:
"
_continuation_template_yaml"
"
tag"
:
"
mmlu_llama_stem_tasks"
"
task"
:
"
mmlu_llama_college_chemistry"
"
task_alias"
:
"
college
chemistry"
lm_eval/tasks/llama3/instruct/mmlu/mmlu_college_computer_science.yaml
0 → 100644
View file @
2106fbeb
"
dataset_name"
:
"
college_computer_science"
"
include"
:
"
_continuation_template_yaml"
"
tag"
:
"
mmlu_llama_stem_tasks"
"
task"
:
"
mmlu_llama_college_computer_science"
"
task_alias"
:
"
college
computer
science"
lm_eval/tasks/llama3/instruct/mmlu/mmlu_college_mathematics.yaml
0 → 100644
View file @
2106fbeb
"
dataset_name"
:
"
college_mathematics"
"
include"
:
"
_continuation_template_yaml"
"
tag"
:
"
mmlu_llama_stem_tasks"
"
task"
:
"
mmlu_llama_college_mathematics"
"
task_alias"
:
"
college
mathematics"
lm_eval/tasks/llama3/instruct/mmlu/mmlu_college_medicine.yaml
0 → 100644
View file @
2106fbeb
"
dataset_name"
:
"
college_medicine"
"
include"
:
"
_continuation_template_yaml"
"
tag"
:
"
mmlu_llama_other_tasks"
"
task"
:
"
mmlu_llama_college_medicine"
"
task_alias"
:
"
college
medicine"
lm_eval/tasks/llama3/instruct/mmlu/mmlu_college_physics.yaml
0 → 100644
View file @
2106fbeb
"
dataset_name"
:
"
college_physics"
"
include"
:
"
_continuation_template_yaml"
"
tag"
:
"
mmlu_llama_stem_tasks"
"
task"
:
"
mmlu_llama_college_physics"
"
task_alias"
:
"
college
physics"
lm_eval/tasks/llama3/instruct/mmlu/mmlu_computer_security.yaml
0 → 100644
View file @
2106fbeb
"
dataset_name"
:
"
computer_security"
"
include"
:
"
_continuation_template_yaml"
"
tag"
:
"
mmlu_llama_stem_tasks"
"
task"
:
"
mmlu_llama_computer_security"
"
task_alias"
:
"
computer
security"
lm_eval/tasks/llama3/instruct/mmlu/mmlu_conceptual_physics.yaml
0 → 100644
View file @
2106fbeb
"
dataset_name"
:
"
conceptual_physics"
"
include"
:
"
_continuation_template_yaml"
"
tag"
:
"
mmlu_llama_stem_tasks"
"
task"
:
"
mmlu_llama_conceptual_physics"
"
task_alias"
:
"
conceptual
physics"
lm_eval/tasks/llama3/instruct/mmlu/mmlu_econometrics.yaml
0 → 100644
View file @
2106fbeb
"
dataset_name"
:
"
econometrics"
"
include"
:
"
_continuation_template_yaml"
"
tag"
:
"
mmlu_llama_social_sciences_tasks"
"
task"
:
"
mmlu_llama_econometrics"
"
task_alias"
:
"
econometrics"
lm_eval/tasks/llama3/instruct/mmlu/mmlu_electrical_engineering.yaml
0 → 100644
View file @
2106fbeb
"
dataset_name"
:
"
electrical_engineering"
"
include"
:
"
_continuation_template_yaml"
"
tag"
:
"
mmlu_llama_stem_tasks"
"
task"
:
"
mmlu_llama_electrical_engineering"
"
task_alias"
:
"
electrical
engineering"
lm_eval/tasks/llama3/instruct/mmlu/mmlu_elementary_mathematics.yaml
0 → 100644
View file @
2106fbeb
"
dataset_name"
:
"
elementary_mathematics"
"
include"
:
"
_continuation_template_yaml"
"
tag"
:
"
mmlu_llama_stem_tasks"
"
task"
:
"
mmlu_llama_elementary_mathematics"
"
task_alias"
:
"
elementary
mathematics"
lm_eval/tasks/llama3/instruct/mmlu/mmlu_formal_logic.yaml
0 → 100644
View file @
2106fbeb
"
dataset_name"
:
"
formal_logic"
"
include"
:
"
_continuation_template_yaml"
"
tag"
:
"
mmlu_llama_humanities_tasks"
"
task"
:
"
mmlu_llama_formal_logic"
"
task_alias"
:
"
formal
logic"
lm_eval/tasks/llama3/instruct/mmlu/mmlu_global_facts.yaml
0 → 100644
View file @
2106fbeb
"
dataset_name"
:
"
global_facts"
"
include"
:
"
_continuation_template_yaml"
"
tag"
:
"
mmlu_llama_other_tasks"
"
task"
:
"
mmlu_llama_global_facts"
"
task_alias"
:
"
global
facts"
Prev
1
…
12
13
14
15
16
17
18
19
20
…
29
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