Add files using upload-large-folder tool
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/answer_only/_answer_only.yaml +44 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/answer_only/_mmlusr_a_yml +16 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/answer_only/answer_only_abstract_algebra.yaml +7 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/answer_only/answer_only_astronomy.yaml +7 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/answer_only/answer_only_college_computer_science.yaml +7 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/answer_only/answer_only_college_mathematics.yaml +7 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/answer_only/answer_only_college_physics.yaml +7 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/answer_only/answer_only_econometrics.yaml +7 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/answer_only/answer_only_global_facts.yaml +7 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/answer_only/answer_only_high_school_european_history.yaml +7 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/answer_only/answer_only_high_school_government_and_politics.yaml +7 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/answer_only/answer_only_high_school_mathematics.yaml +7 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/answer_only/answer_only_high_school_physics.yaml +7 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/answer_only/answer_only_high_school_world_history.yaml +7 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/answer_only/answer_only_human_aging.yaml +7 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/answer_only/answer_only_human_sexuality.yaml +7 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/answer_only/answer_only_marketing.yaml +7 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/answer_only/answer_only_medical_genetics.yaml +7 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/answer_only/answer_only_moral_disputes.yaml +7 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/answer_only/answer_only_nutrition.yaml +7 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/answer_only/answer_only_prehistory.yaml +7 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/answer_only/answer_only_professional_medicine.yaml +7 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/answer_only/answer_only_public_relations.yaml +7 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/answer_only/answer_only_sociology.yaml +7 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/answer_only/answer_only_us_foreign_policy.yaml +7 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/answer_only/answer_only_virology.yaml +7 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/question_only/_mmlusr_q_yml +16 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/question_only/question_only_abstract_algebra.yaml +7 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/question_only/question_only_anatomy.yaml +7 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/question_only/question_only_astronomy.yaml +7 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/question_only/question_only_business_ethics.yaml +7 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/question_only/question_only_clinical_knowledge.yaml +7 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/question_only/question_only_college_biology.yaml +7 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/question_only/question_only_college_computer_science.yaml +7 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/question_only/question_only_college_mathematics.yaml +7 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/question_only/question_only_college_medicine.yaml +7 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/question_only/question_only_college_physics.yaml +7 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/question_only/question_only_conceptual_physics.yaml +7 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/question_only/question_only_econometrics.yaml +7 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/question_only/question_only_electrical_engineering.yaml +7 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/question_only/question_only_elementary_mathematics.yaml +7 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/question_only/question_only_formal_logic.yaml +7 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/question_only/question_only_global_facts.yaml +7 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/question_only/question_only_high_school_chemistry.yaml +7 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/question_only/question_only_high_school_european_history.yaml +7 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/question_only/question_only_high_school_geography.yaml +7 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/question_only/question_only_high_school_government_and_politics.yaml +7 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/question_only/question_only_high_school_mathematics.yaml +7 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/question_only/question_only_high_school_microeconomics.yaml +7 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/question_only/question_only_high_school_physics.yaml +7 -0
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/answer_only/_answer_only.yaml
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
group: mmlusr_answer_only
|
| 2 |
+
group_alias: MMLU-SR (Answer Only)
|
| 3 |
+
task:
|
| 4 |
+
- group: mmlusr_ao_stem
|
| 5 |
+
group_alias: STEM (Answer Only)
|
| 6 |
+
task:
|
| 7 |
+
- mmlusr_answer_only_stem_tasks
|
| 8 |
+
aggregate_metric_list:
|
| 9 |
+
- metric: acc
|
| 10 |
+
weight_by_size: True
|
| 11 |
+
metadata:
|
| 12 |
+
version: 2
|
| 13 |
+
- group: mmlusr_ao_other
|
| 14 |
+
group_alias: Other (Answer Only)
|
| 15 |
+
task:
|
| 16 |
+
- mmlusr_answer_only_other_tasks
|
| 17 |
+
aggregate_metric_list:
|
| 18 |
+
- metric: acc
|
| 19 |
+
weight_by_size: True
|
| 20 |
+
metadata:
|
| 21 |
+
version: 2
|
| 22 |
+
- group: mmlusr_ao_social_sciences
|
| 23 |
+
group_alias: Social Sciences (Answer Only)
|
| 24 |
+
task:
|
| 25 |
+
- mmlusr_answer_only_social_sciences_tasks
|
| 26 |
+
aggregate_metric_list:
|
| 27 |
+
- metric: acc
|
| 28 |
+
weight_by_size: True
|
| 29 |
+
metadata:
|
| 30 |
+
version: 2
|
| 31 |
+
- group: mmlusr_ao_humanities
|
| 32 |
+
group_alias: Humanities (Answer Only)
|
| 33 |
+
task:
|
| 34 |
+
- mmlusr_answer_only_humanities_tasks
|
| 35 |
+
aggregate_metric_list:
|
| 36 |
+
- metric: acc
|
| 37 |
+
weight_by_size: True
|
| 38 |
+
metadata:
|
| 39 |
+
version: 2
|
| 40 |
+
aggregate_metric_list:
|
| 41 |
+
- metric: acc
|
| 42 |
+
weight_by_size: True
|
| 43 |
+
metadata:
|
| 44 |
+
version: 2
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/answer_only/_mmlusr_a_yml
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
dataset_path: NiniCat/MMLU-SR
|
| 2 |
+
test_split: test
|
| 3 |
+
fewshot_split: train
|
| 4 |
+
fewshot_config:
|
| 5 |
+
sampler: first_n
|
| 6 |
+
output_type: multiple_choice
|
| 7 |
+
process_docs: !function utils.process_docs
|
| 8 |
+
doc_to_text: "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:"
|
| 9 |
+
doc_to_choice: ["A", "B", "C", "D"]
|
| 10 |
+
doc_to_target: answer
|
| 11 |
+
metric_list:
|
| 12 |
+
- metric: acc
|
| 13 |
+
aggregation: mean
|
| 14 |
+
higher_is_better: true
|
| 15 |
+
metadata:
|
| 16 |
+
version: 1.0
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/answer_only/answer_only_abstract_algebra.yaml
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "answer_only_abstract_algebra"
|
| 2 |
+
"description": "The following are multiple choice questions (with answers) about abstract\
|
| 3 |
+
\ algebra.\n\n"
|
| 4 |
+
"tag": "mmlusr_answer_only_stem_tasks"
|
| 5 |
+
"include": "_mmlusr_a_yml"
|
| 6 |
+
"task": "mmlusr_answer_only_abstract_algebra"
|
| 7 |
+
"task_alias": "abstract algebra"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/answer_only/answer_only_astronomy.yaml
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "answer_only_astronomy"
|
| 2 |
+
"description": "The following are multiple choice questions (with answers) about astronomy.\n\
|
| 3 |
+
\n"
|
| 4 |
+
"tag": "mmlusr_answer_only_stem_tasks"
|
| 5 |
+
"include": "_mmlusr_a_yml"
|
| 6 |
+
"task": "mmlusr_answer_only_astronomy"
|
| 7 |
+
"task_alias": "astronomy"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/answer_only/answer_only_college_computer_science.yaml
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "answer_only_college_computer_science"
|
| 2 |
+
"description": "The following are multiple choice questions (with answers) about college\
|
| 3 |
+
\ computer science.\n\n"
|
| 4 |
+
"tag": "mmlusr_answer_only_stem_tasks"
|
| 5 |
+
"include": "_mmlusr_a_yml"
|
| 6 |
+
"task": "mmlusr_answer_only_college_computer_science"
|
| 7 |
+
"task_alias": "college computer science"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/answer_only/answer_only_college_mathematics.yaml
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "answer_only_college_mathematics"
|
| 2 |
+
"description": "The following are multiple choice questions (with answers) about college\
|
| 3 |
+
\ mathematics.\n\n"
|
| 4 |
+
"tag": "mmlusr_answer_only_stem_tasks"
|
| 5 |
+
"include": "_mmlusr_a_yml"
|
| 6 |
+
"task": "mmlusr_answer_only_college_mathematics"
|
| 7 |
+
"task_alias": "college mathematics"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/answer_only/answer_only_college_physics.yaml
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "answer_only_college_physics"
|
| 2 |
+
"description": "The following are multiple choice questions (with answers) about college\
|
| 3 |
+
\ physics.\n\n"
|
| 4 |
+
"tag": "mmlusr_answer_only_stem_tasks"
|
| 5 |
+
"include": "_mmlusr_a_yml"
|
| 6 |
+
"task": "mmlusr_answer_only_college_physics"
|
| 7 |
+
"task_alias": "college physics"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/answer_only/answer_only_econometrics.yaml
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "answer_only_econometrics"
|
| 2 |
+
"description": "The following are multiple choice questions (with answers) about econometrics.\n\
|
| 3 |
+
\n"
|
| 4 |
+
"tag": "mmlusr_answer_only_social_sciences_tasks"
|
| 5 |
+
"include": "_mmlusr_a_yml"
|
| 6 |
+
"task": "mmlusr_answer_only_econometrics"
|
| 7 |
+
"task_alias": "econometrics"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/answer_only/answer_only_global_facts.yaml
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "answer_only_global_facts"
|
| 2 |
+
"description": "The following are multiple choice questions (with answers) about global\
|
| 3 |
+
\ facts.\n\n"
|
| 4 |
+
"tag": "mmlusr_answer_only_other_tasks"
|
| 5 |
+
"include": "_mmlusr_a_yml"
|
| 6 |
+
"task": "mmlusr_answer_only_global_facts"
|
| 7 |
+
"task_alias": "global facts"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/answer_only/answer_only_high_school_european_history.yaml
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "answer_only_high_school_european_history"
|
| 2 |
+
"description": "The following are multiple choice questions (with answers) about high\
|
| 3 |
+
\ school european history.\n\n"
|
| 4 |
+
"tag": "mmlusr_answer_only_humanities_tasks"
|
| 5 |
+
"include": "_mmlusr_a_yml"
|
| 6 |
+
"task": "mmlusr_answer_only_high_school_european_history"
|
| 7 |
+
"task_alias": "high school european history"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/answer_only/answer_only_high_school_government_and_politics.yaml
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "answer_only_high_school_government_and_politics"
|
| 2 |
+
"description": "The following are multiple choice questions (with answers) about high\
|
| 3 |
+
\ school government and politics.\n\n"
|
| 4 |
+
"tag": "mmlusr_answer_only_social_sciences_tasks"
|
| 5 |
+
"include": "_mmlusr_a_yml"
|
| 6 |
+
"task": "mmlusr_answer_only_high_school_government_and_politics"
|
| 7 |
+
"task_alias": "high school government and politics"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/answer_only/answer_only_high_school_mathematics.yaml
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "answer_only_high_school_mathematics"
|
| 2 |
+
"description": "The following are multiple choice questions (with answers) about high\
|
| 3 |
+
\ school mathematics.\n\n"
|
| 4 |
+
"tag": "mmlusr_answer_only_stem_tasks"
|
| 5 |
+
"include": "_mmlusr_a_yml"
|
| 6 |
+
"task": "mmlusr_answer_only_high_school_mathematics"
|
| 7 |
+
"task_alias": "high school mathematics"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/answer_only/answer_only_high_school_physics.yaml
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "answer_only_high_school_physics"
|
| 2 |
+
"description": "The following are multiple choice questions (with answers) about high\
|
| 3 |
+
\ school physics.\n\n"
|
| 4 |
+
"tag": "mmlusr_answer_only_stem_tasks"
|
| 5 |
+
"include": "_mmlusr_a_yml"
|
| 6 |
+
"task": "mmlusr_answer_only_high_school_physics"
|
| 7 |
+
"task_alias": "high school physics"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/answer_only/answer_only_high_school_world_history.yaml
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "answer_only_high_school_world_history"
|
| 2 |
+
"description": "The following are multiple choice questions (with answers) about high\
|
| 3 |
+
\ school world history.\n\n"
|
| 4 |
+
"tag": "mmlusr_answer_only_humanities_tasks"
|
| 5 |
+
"include": "_mmlusr_a_yml"
|
| 6 |
+
"task": "mmlusr_answer_only_high_school_world_history"
|
| 7 |
+
"task_alias": "high school world history"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/answer_only/answer_only_human_aging.yaml
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "answer_only_human_aging"
|
| 2 |
+
"description": "The following are multiple choice questions (with answers) about human\
|
| 3 |
+
\ aging.\n\n"
|
| 4 |
+
"tag": "mmlusr_answer_only_other_tasks"
|
| 5 |
+
"include": "_mmlusr_a_yml"
|
| 6 |
+
"task": "mmlusr_answer_only_human_aging"
|
| 7 |
+
"task_alias": "human aging"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/answer_only/answer_only_human_sexuality.yaml
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "answer_only_human_sexuality"
|
| 2 |
+
"description": "The following are multiple choice questions (with answers) about human\
|
| 3 |
+
\ sexuality.\n\n"
|
| 4 |
+
"tag": "mmlusr_answer_only_social_sciences_tasks"
|
| 5 |
+
"include": "_mmlusr_a_yml"
|
| 6 |
+
"task": "mmlusr_answer_only_human_sexuality"
|
| 7 |
+
"task_alias": "human sexuality"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/answer_only/answer_only_marketing.yaml
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "answer_only_marketing"
|
| 2 |
+
"description": "The following are multiple choice questions (with answers) about marketing.\n\
|
| 3 |
+
\n"
|
| 4 |
+
"tag": "mmlusr_answer_only_other_tasks"
|
| 5 |
+
"include": "_mmlusr_a_yml"
|
| 6 |
+
"task": "mmlusr_answer_only_marketing"
|
| 7 |
+
"task_alias": "marketing"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/answer_only/answer_only_medical_genetics.yaml
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "answer_only_medical_genetics"
|
| 2 |
+
"description": "The following are multiple choice questions (with answers) about medical\
|
| 3 |
+
\ genetics.\n\n"
|
| 4 |
+
"tag": "mmlusr_answer_only_other_tasks"
|
| 5 |
+
"include": "_mmlusr_a_yml"
|
| 6 |
+
"task": "mmlusr_answer_only_medical_genetics"
|
| 7 |
+
"task_alias": "medical genetics"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/answer_only/answer_only_moral_disputes.yaml
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "answer_only_moral_disputes"
|
| 2 |
+
"description": "The following are multiple choice questions (with answers) about moral\
|
| 3 |
+
\ disputes.\n\n"
|
| 4 |
+
"tag": "mmlusr_answer_only_humanities_tasks"
|
| 5 |
+
"include": "_mmlusr_a_yml"
|
| 6 |
+
"task": "mmlusr_answer_only_moral_disputes"
|
| 7 |
+
"task_alias": "moral disputes"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/answer_only/answer_only_nutrition.yaml
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "answer_only_nutrition"
|
| 2 |
+
"description": "The following are multiple choice questions (with answers) about nutrition.\n\
|
| 3 |
+
\n"
|
| 4 |
+
"tag": "mmlusr_answer_only_other_tasks"
|
| 5 |
+
"include": "_mmlusr_a_yml"
|
| 6 |
+
"task": "mmlusr_answer_only_nutrition"
|
| 7 |
+
"task_alias": "nutrition"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/answer_only/answer_only_prehistory.yaml
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "answer_only_prehistory"
|
| 2 |
+
"description": "The following are multiple choice questions (with answers) about prehistory.\n\
|
| 3 |
+
\n"
|
| 4 |
+
"tag": "mmlusr_answer_only_humanities_tasks"
|
| 5 |
+
"include": "_mmlusr_a_yml"
|
| 6 |
+
"task": "mmlusr_answer_only_prehistory"
|
| 7 |
+
"task_alias": "prehistory"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/answer_only/answer_only_professional_medicine.yaml
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "answer_only_professional_medicine"
|
| 2 |
+
"description": "The following are multiple choice questions (with answers) about professional\
|
| 3 |
+
\ medicine.\n\n"
|
| 4 |
+
"tag": "mmlusr_answer_only_other_tasks"
|
| 5 |
+
"include": "_mmlusr_a_yml"
|
| 6 |
+
"task": "mmlusr_answer_only_professional_medicine"
|
| 7 |
+
"task_alias": "professional medicine"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/answer_only/answer_only_public_relations.yaml
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "answer_only_public_relations"
|
| 2 |
+
"description": "The following are multiple choice questions (with answers) about public\
|
| 3 |
+
\ relations.\n\n"
|
| 4 |
+
"tag": "mmlusr_answer_only_social_sciences_tasks"
|
| 5 |
+
"include": "_mmlusr_a_yml"
|
| 6 |
+
"task": "mmlusr_answer_only_public_relations"
|
| 7 |
+
"task_alias": "public relations"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/answer_only/answer_only_sociology.yaml
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "answer_only_sociology"
|
| 2 |
+
"description": "The following are multiple choice questions (with answers) about sociology.\n\
|
| 3 |
+
\n"
|
| 4 |
+
"tag": "mmlusr_answer_only_social_sciences_tasks"
|
| 5 |
+
"include": "_mmlusr_a_yml"
|
| 6 |
+
"task": "mmlusr_answer_only_sociology"
|
| 7 |
+
"task_alias": "sociology"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/answer_only/answer_only_us_foreign_policy.yaml
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "answer_only_us_foreign_policy"
|
| 2 |
+
"description": "The following are multiple choice questions (with answers) about us\
|
| 3 |
+
\ foreign policy.\n\n"
|
| 4 |
+
"tag": "mmlusr_answer_only_social_sciences_tasks"
|
| 5 |
+
"include": "_mmlusr_a_yml"
|
| 6 |
+
"task": "mmlusr_answer_only_us_foreign_policy"
|
| 7 |
+
"task_alias": "us foreign policy"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/answer_only/answer_only_virology.yaml
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "answer_only_virology"
|
| 2 |
+
"description": "The following are multiple choice questions (with answers) about virology.\n\
|
| 3 |
+
\n"
|
| 4 |
+
"tag": "mmlusr_answer_only_other_tasks"
|
| 5 |
+
"include": "_mmlusr_a_yml"
|
| 6 |
+
"task": "mmlusr_answer_only_virology"
|
| 7 |
+
"task_alias": "virology"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/question_only/_mmlusr_q_yml
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
dataset_path: NiniCat/MMLU-SR
|
| 2 |
+
test_split: test
|
| 3 |
+
fewshot_split: train
|
| 4 |
+
fewshot_config:
|
| 5 |
+
sampler: first_n
|
| 6 |
+
output_type: multiple_choice
|
| 7 |
+
process_docs: !function utils.process_docs
|
| 8 |
+
doc_to_text: "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:"
|
| 9 |
+
doc_to_choice: ["A", "B", "C", "D"]
|
| 10 |
+
doc_to_target: answer
|
| 11 |
+
metric_list:
|
| 12 |
+
- metric: acc
|
| 13 |
+
aggregation: mean
|
| 14 |
+
higher_is_better: true
|
| 15 |
+
metadata:
|
| 16 |
+
version: 1.0
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/question_only/question_only_abstract_algebra.yaml
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "question_only_abstract_algebra"
|
| 2 |
+
"description": "The following are multiple choice questions (with answers) about abstract\
|
| 3 |
+
\ algebra.\n\n"
|
| 4 |
+
"tag": "mmlusr_question_only_stem_tasks"
|
| 5 |
+
"include": "_mmlusr_q_yml"
|
| 6 |
+
"task": "mmlusr_question_only_abstract_algebra"
|
| 7 |
+
"task_alias": "abstract algebra"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/question_only/question_only_anatomy.yaml
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "question_only_anatomy"
|
| 2 |
+
"description": "The following are multiple choice questions (with answers) about anatomy.\n\
|
| 3 |
+
\n"
|
| 4 |
+
"tag": "mmlusr_question_only_stem_tasks"
|
| 5 |
+
"include": "_mmlusr_q_yml"
|
| 6 |
+
"task": "mmlusr_question_only_anatomy"
|
| 7 |
+
"task_alias": "anatomy"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/question_only/question_only_astronomy.yaml
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "question_only_astronomy"
|
| 2 |
+
"description": "The following are multiple choice questions (with answers) about astronomy.\n\
|
| 3 |
+
\n"
|
| 4 |
+
"tag": "mmlusr_question_only_stem_tasks"
|
| 5 |
+
"include": "_mmlusr_q_yml"
|
| 6 |
+
"task": "mmlusr_question_only_astronomy"
|
| 7 |
+
"task_alias": "astronomy"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/question_only/question_only_business_ethics.yaml
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "question_only_business_ethics"
|
| 2 |
+
"description": "The following are multiple choice questions (with answers) about business\
|
| 3 |
+
\ ethics.\n\n"
|
| 4 |
+
"tag": "mmlusr_question_only_other_tasks"
|
| 5 |
+
"include": "_mmlusr_q_yml"
|
| 6 |
+
"task": "mmlusr_question_only_business_ethics"
|
| 7 |
+
"task_alias": "business ethics"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/question_only/question_only_clinical_knowledge.yaml
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "question_only_clinical_knowledge"
|
| 2 |
+
"description": "The following are multiple choice questions (with answers) about clinical\
|
| 3 |
+
\ knowledge.\n\n"
|
| 4 |
+
"tag": "mmlusr_question_only_other_tasks"
|
| 5 |
+
"include": "_mmlusr_q_yml"
|
| 6 |
+
"task": "mmlusr_question_only_clinical_knowledge"
|
| 7 |
+
"task_alias": "clinical knowledge"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/question_only/question_only_college_biology.yaml
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "question_only_college_biology"
|
| 2 |
+
"description": "The following are multiple choice questions (with answers) about college\
|
| 3 |
+
\ biology.\n\n"
|
| 4 |
+
"tag": "mmlusr_question_only_stem_tasks"
|
| 5 |
+
"include": "_mmlusr_q_yml"
|
| 6 |
+
"task": "mmlusr_question_only_college_biology"
|
| 7 |
+
"task_alias": "college biology"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/question_only/question_only_college_computer_science.yaml
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "question_only_college_computer_science"
|
| 2 |
+
"description": "The following are multiple choice questions (with answers) about college\
|
| 3 |
+
\ computer science.\n\n"
|
| 4 |
+
"tag": "mmlusr_question_only_stem_tasks"
|
| 5 |
+
"include": "_mmlusr_q_yml"
|
| 6 |
+
"task": "mmlusr_question_only_college_computer_science"
|
| 7 |
+
"task_alias": "college computer science"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/question_only/question_only_college_mathematics.yaml
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "question_only_college_mathematics"
|
| 2 |
+
"description": "The following are multiple choice questions (with answers) about college\
|
| 3 |
+
\ mathematics.\n\n"
|
| 4 |
+
"tag": "mmlusr_question_only_stem_tasks"
|
| 5 |
+
"include": "_mmlusr_q_yml"
|
| 6 |
+
"task": "mmlusr_question_only_college_mathematics"
|
| 7 |
+
"task_alias": "college mathematics"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/question_only/question_only_college_medicine.yaml
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "question_only_college_medicine"
|
| 2 |
+
"description": "The following are multiple choice questions (with answers) about college\
|
| 3 |
+
\ medicine.\n\n"
|
| 4 |
+
"tag": "mmlusr_question_only_other_tasks"
|
| 5 |
+
"include": "_mmlusr_q_yml"
|
| 6 |
+
"task": "mmlusr_question_only_college_medicine"
|
| 7 |
+
"task_alias": "college medicine"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/question_only/question_only_college_physics.yaml
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "question_only_college_physics"
|
| 2 |
+
"description": "The following are multiple choice questions (with answers) about college\
|
| 3 |
+
\ physics.\n\n"
|
| 4 |
+
"tag": "mmlusr_question_only_stem_tasks"
|
| 5 |
+
"include": "_mmlusr_q_yml"
|
| 6 |
+
"task": "mmlusr_question_only_college_physics"
|
| 7 |
+
"task_alias": "college physics"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/question_only/question_only_conceptual_physics.yaml
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "question_only_conceptual_physics"
|
| 2 |
+
"description": "The following are multiple choice questions (with answers) about conceptual\
|
| 3 |
+
\ physics.\n\n"
|
| 4 |
+
"tag": "mmlusr_question_only_stem_tasks"
|
| 5 |
+
"include": "_mmlusr_q_yml"
|
| 6 |
+
"task": "mmlusr_question_only_conceptual_physics"
|
| 7 |
+
"task_alias": "conceptual physics"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/question_only/question_only_econometrics.yaml
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "question_only_econometrics"
|
| 2 |
+
"description": "The following are multiple choice questions (with answers) about econometrics.\n\
|
| 3 |
+
\n"
|
| 4 |
+
"tag": "mmlusr_question_only_social_sciences_tasks"
|
| 5 |
+
"include": "_mmlusr_q_yml"
|
| 6 |
+
"task": "mmlusr_question_only_econometrics"
|
| 7 |
+
"task_alias": "econometrics"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/question_only/question_only_electrical_engineering.yaml
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "question_only_electrical_engineering"
|
| 2 |
+
"description": "The following are multiple choice questions (with answers) about electrical\
|
| 3 |
+
\ engineering.\n\n"
|
| 4 |
+
"tag": "mmlusr_question_only_stem_tasks"
|
| 5 |
+
"include": "_mmlusr_q_yml"
|
| 6 |
+
"task": "mmlusr_question_only_electrical_engineering"
|
| 7 |
+
"task_alias": "electrical engineering"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/question_only/question_only_elementary_mathematics.yaml
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "question_only_elementary_mathematics"
|
| 2 |
+
"description": "The following are multiple choice questions (with answers) about elementary\
|
| 3 |
+
\ mathematics.\n\n"
|
| 4 |
+
"tag": "mmlusr_question_only_stem_tasks"
|
| 5 |
+
"include": "_mmlusr_q_yml"
|
| 6 |
+
"task": "mmlusr_question_only_elementary_mathematics"
|
| 7 |
+
"task_alias": "elementary mathematics"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/question_only/question_only_formal_logic.yaml
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "question_only_formal_logic"
|
| 2 |
+
"description": "The following are multiple choice questions (with answers) about formal\
|
| 3 |
+
\ logic.\n\n"
|
| 4 |
+
"tag": "mmlusr_question_only_humanities_tasks"
|
| 5 |
+
"include": "_mmlusr_q_yml"
|
| 6 |
+
"task": "mmlusr_question_only_formal_logic"
|
| 7 |
+
"task_alias": "formal logic"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/question_only/question_only_global_facts.yaml
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "question_only_global_facts"
|
| 2 |
+
"description": "The following are multiple choice questions (with answers) about global\
|
| 3 |
+
\ facts.\n\n"
|
| 4 |
+
"tag": "mmlusr_question_only_other_tasks"
|
| 5 |
+
"include": "_mmlusr_q_yml"
|
| 6 |
+
"task": "mmlusr_question_only_global_facts"
|
| 7 |
+
"task_alias": "global facts"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/question_only/question_only_high_school_chemistry.yaml
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "question_only_high_school_chemistry"
|
| 2 |
+
"description": "The following are multiple choice questions (with answers) about high\
|
| 3 |
+
\ school chemistry.\n\n"
|
| 4 |
+
"tag": "mmlusr_question_only_stem_tasks"
|
| 5 |
+
"include": "_mmlusr_q_yml"
|
| 6 |
+
"task": "mmlusr_question_only_high_school_chemistry"
|
| 7 |
+
"task_alias": "high school chemistry"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/question_only/question_only_high_school_european_history.yaml
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "question_only_high_school_european_history"
|
| 2 |
+
"description": "The following are multiple choice questions (with answers) about high\
|
| 3 |
+
\ school european history.\n\n"
|
| 4 |
+
"tag": "mmlusr_question_only_humanities_tasks"
|
| 5 |
+
"include": "_mmlusr_q_yml"
|
| 6 |
+
"task": "mmlusr_question_only_high_school_european_history"
|
| 7 |
+
"task_alias": "high school european history"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/question_only/question_only_high_school_geography.yaml
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "question_only_high_school_geography"
|
| 2 |
+
"description": "The following are multiple choice questions (with answers) about high\
|
| 3 |
+
\ school geography.\n\n"
|
| 4 |
+
"tag": "mmlusr_question_only_social_sciences_tasks"
|
| 5 |
+
"include": "_mmlusr_q_yml"
|
| 6 |
+
"task": "mmlusr_question_only_high_school_geography"
|
| 7 |
+
"task_alias": "high school geography"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/question_only/question_only_high_school_government_and_politics.yaml
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "question_only_high_school_government_and_politics"
|
| 2 |
+
"description": "The following are multiple choice questions (with answers) about high\
|
| 3 |
+
\ school government and politics.\n\n"
|
| 4 |
+
"tag": "mmlusr_question_only_social_sciences_tasks"
|
| 5 |
+
"include": "_mmlusr_q_yml"
|
| 6 |
+
"task": "mmlusr_question_only_high_school_government_and_politics"
|
| 7 |
+
"task_alias": "high school government and politics"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/question_only/question_only_high_school_mathematics.yaml
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "question_only_high_school_mathematics"
|
| 2 |
+
"description": "The following are multiple choice questions (with answers) about high\
|
| 3 |
+
\ school mathematics.\n\n"
|
| 4 |
+
"tag": "mmlusr_question_only_stem_tasks"
|
| 5 |
+
"include": "_mmlusr_q_yml"
|
| 6 |
+
"task": "mmlusr_question_only_high_school_mathematics"
|
| 7 |
+
"task_alias": "high school mathematics"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/question_only/question_only_high_school_microeconomics.yaml
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "question_only_high_school_microeconomics"
|
| 2 |
+
"description": "The following are multiple choice questions (with answers) about high\
|
| 3 |
+
\ school microeconomics.\n\n"
|
| 4 |
+
"tag": "mmlusr_question_only_social_sciences_tasks"
|
| 5 |
+
"include": "_mmlusr_q_yml"
|
| 6 |
+
"task": "mmlusr_question_only_high_school_microeconomics"
|
| 7 |
+
"task_alias": "high school microeconomics"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlusr/question_only/question_only_high_school_physics.yaml
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "question_only_high_school_physics"
|
| 2 |
+
"description": "The following are multiple choice questions (with answers) about high\
|
| 3 |
+
\ school physics.\n\n"
|
| 4 |
+
"tag": "mmlusr_question_only_stem_tasks"
|
| 5 |
+
"include": "_mmlusr_q_yml"
|
| 6 |
+
"task": "mmlusr_question_only_high_school_physics"
|
| 7 |
+
"task_alias": "high school physics"
|