koichi12 commited on
Commit
8a96407
·
verified ·
1 Parent(s): 6dd8cad

Add files using upload-large-folder tool

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/_default_template_yaml +17 -0
  2. scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/_mmlu.yaml +11 -0
  3. scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/_mmlu_humanities.yaml +9 -0
  4. scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/_mmlu_other.yaml +9 -0
  5. scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/_mmlu_social_sciences.yaml +9 -0
  6. scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/_mmlu_stem.yaml +9 -0
  7. scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_abstract_algebra.yaml +7 -0
  8. scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_anatomy.yaml +7 -0
  9. scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_astronomy.yaml +7 -0
  10. scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_business_ethics.yaml +7 -0
  11. scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_clinical_knowledge.yaml +7 -0
  12. scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_college_biology.yaml +7 -0
  13. scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_college_chemistry.yaml +7 -0
  14. scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_college_computer_science.yaml +7 -0
  15. scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_college_mathematics.yaml +7 -0
  16. scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_college_medicine.yaml +7 -0
  17. scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_college_physics.yaml +7 -0
  18. scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_computer_security.yaml +7 -0
  19. scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_conceptual_physics.yaml +7 -0
  20. scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_electrical_engineering.yaml +7 -0
  21. scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_elementary_mathematics.yaml +7 -0
  22. scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_formal_logic.yaml +7 -0
  23. scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_global_facts.yaml +7 -0
  24. scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_high_school_biology.yaml +7 -0
  25. scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_high_school_chemistry.yaml +7 -0
  26. scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_high_school_computer_science.yaml +7 -0
  27. scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_high_school_european_history.yaml +7 -0
  28. scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_high_school_geography.yaml +7 -0
  29. scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_high_school_government_and_politics.yaml +7 -0
  30. scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_high_school_macroeconomics.yaml +7 -0
  31. scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_high_school_mathematics.yaml +7 -0
  32. scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_high_school_microeconomics.yaml +7 -0
  33. scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_high_school_physics.yaml +7 -0
  34. scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_high_school_psychology.yaml +7 -0
  35. scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_high_school_statistics.yaml +7 -0
  36. scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_high_school_us_history.yaml +7 -0
  37. scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_high_school_world_history.yaml +7 -0
  38. scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_human_aging.yaml +7 -0
  39. scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_human_sexuality.yaml +7 -0
  40. scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_international_law.yaml +7 -0
  41. scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_jurisprudence.yaml +7 -0
  42. scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_logical_fallacies.yaml +7 -0
  43. scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_machine_learning.yaml +7 -0
  44. scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_management.yaml +7 -0
  45. scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_marketing.yaml +7 -0
  46. scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_medical_genetics.yaml +7 -0
  47. scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_miscellaneous.yaml +7 -0
  48. scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_moral_disputes.yaml +7 -0
  49. scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_moral_scenarios.yaml +7 -0
  50. scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_nutrition.yaml +7 -0
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/_default_template_yaml ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ dataset_path: hails/mmlu_no_train # a copy of `cais/mmlu` with no auxiliary_train split
2
+ test_split: test
3
+ fewshot_split: dev
4
+ fewshot_config:
5
+ sampler: first_n
6
+ output_type: multiple_choice
7
+ doc_to_text: "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:"
8
+ doc_to_choice: ["A", "B", "C", "D"]
9
+ doc_to_target: answer
10
+ metric_list:
11
+ - metric: acc
12
+ aggregation: mean
13
+ higher_is_better: true
14
+ metadata:
15
+ version: 1.0
16
+ dataset_kwargs:
17
+ trust_remote_code: true
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/_mmlu.yaml ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ group: mmlu
2
+ task:
3
+ - mmlu_stem
4
+ - mmlu_other
5
+ - mmlu_social_sciences
6
+ - mmlu_humanities
7
+ aggregate_metric_list:
8
+ - metric: acc
9
+ weight_by_size: True
10
+ metadata:
11
+ version: 2
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/_mmlu_humanities.yaml ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ group: mmlu_humanities
2
+ group_alias: humanities
3
+ task:
4
+ - mmlu_humanities_tasks
5
+ aggregate_metric_list:
6
+ - metric: acc
7
+ weight_by_size: True
8
+ metadata:
9
+ version: 2
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/_mmlu_other.yaml ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ group: mmlu_other
2
+ group_alias: other
3
+ task:
4
+ - mmlu_other_tasks
5
+ aggregate_metric_list:
6
+ - metric: acc
7
+ weight_by_size: True
8
+ metadata:
9
+ version: 2
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/_mmlu_social_sciences.yaml ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ group: mmlu_social_sciences
2
+ group_alias: social sciences
3
+ task:
4
+ - mmlu_social_sciences_tasks
5
+ aggregate_metric_list:
6
+ - metric: acc
7
+ weight_by_size: True
8
+ metadata:
9
+ version: 2
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/_mmlu_stem.yaml ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ group: mmlu_stem
2
+ group_alias: stem
3
+ task:
4
+ - mmlu_stem_tasks
5
+ aggregate_metric_list:
6
+ - metric: acc
7
+ weight_by_size: True
8
+ metadata:
9
+ version: 2
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_abstract_algebra.yaml ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ "dataset_name": "abstract_algebra"
2
+ "description": "The following are multiple choice questions (with answers) about abstract\
3
+ \ algebra.\n\n"
4
+ "tag": "mmlu_stem_tasks"
5
+ "include": "_default_template_yaml"
6
+ "task": "mmlu_abstract_algebra"
7
+ "task_alias": "abstract_algebra"
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_anatomy.yaml ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ "dataset_name": "anatomy"
2
+ "description": "The following are multiple choice questions (with answers) about anatomy.\n\
3
+ \n"
4
+ "tag": "mmlu_stem_tasks"
5
+ "include": "_default_template_yaml"
6
+ "task": "mmlu_anatomy"
7
+ "task_alias": "anatomy"
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_astronomy.yaml ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ "dataset_name": "astronomy"
2
+ "description": "The following are multiple choice questions (with answers) about astronomy.\n\
3
+ \n"
4
+ "tag": "mmlu_stem_tasks"
5
+ "include": "_default_template_yaml"
6
+ "task": "mmlu_astronomy"
7
+ "task_alias": "astronomy"
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_business_ethics.yaml ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ "dataset_name": "business_ethics"
2
+ "description": "The following are multiple choice questions (with answers) about business\
3
+ \ ethics.\n\n"
4
+ "tag": "mmlu_other_tasks"
5
+ "include": "_default_template_yaml"
6
+ "task": "mmlu_business_ethics"
7
+ "task_alias": "business_ethics"
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_clinical_knowledge.yaml ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ "dataset_name": "clinical_knowledge"
2
+ "description": "The following are multiple choice questions (with answers) about clinical\
3
+ \ knowledge.\n\n"
4
+ "tag": "mmlu_other_tasks"
5
+ "include": "_default_template_yaml"
6
+ "task": "mmlu_clinical_knowledge"
7
+ "task_alias": "clinical_knowledge"
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_college_biology.yaml ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ "dataset_name": "college_biology"
2
+ "description": "The following are multiple choice questions (with answers) about college\
3
+ \ biology.\n\n"
4
+ "tag": "mmlu_stem_tasks"
5
+ "include": "_default_template_yaml"
6
+ "task": "mmlu_college_biology"
7
+ "task_alias": "college_biology"
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_college_chemistry.yaml ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ "dataset_name": "college_chemistry"
2
+ "description": "The following are multiple choice questions (with answers) about college\
3
+ \ chemistry.\n\n"
4
+ "tag": "mmlu_stem_tasks"
5
+ "include": "_default_template_yaml"
6
+ "task": "mmlu_college_chemistry"
7
+ "task_alias": "college_chemistry"
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_college_computer_science.yaml ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ "dataset_name": "college_computer_science"
2
+ "description": "The following are multiple choice questions (with answers) about college\
3
+ \ computer science.\n\n"
4
+ "tag": "mmlu_stem_tasks"
5
+ "include": "_default_template_yaml"
6
+ "task": "mmlu_college_computer_science"
7
+ "task_alias": "college_computer_science"
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_college_mathematics.yaml ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ "dataset_name": "college_mathematics"
2
+ "description": "The following are multiple choice questions (with answers) about college\
3
+ \ mathematics.\n\n"
4
+ "tag": "mmlu_stem_tasks"
5
+ "include": "_default_template_yaml"
6
+ "task": "mmlu_college_mathematics"
7
+ "task_alias": "college_mathematics"
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_college_medicine.yaml ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ "dataset_name": "college_medicine"
2
+ "description": "The following are multiple choice questions (with answers) about college\
3
+ \ medicine.\n\n"
4
+ "tag": "mmlu_other_tasks"
5
+ "include": "_default_template_yaml"
6
+ "task": "mmlu_college_medicine"
7
+ "task_alias": "college_medicine"
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_college_physics.yaml ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ "dataset_name": "college_physics"
2
+ "description": "The following are multiple choice questions (with answers) about college\
3
+ \ physics.\n\n"
4
+ "tag": "mmlu_stem_tasks"
5
+ "include": "_default_template_yaml"
6
+ "task": "mmlu_college_physics"
7
+ "task_alias": "college_physics"
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_computer_security.yaml ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ "dataset_name": "computer_security"
2
+ "description": "The following are multiple choice questions (with answers) about computer\
3
+ \ security.\n\n"
4
+ "tag": "mmlu_stem_tasks"
5
+ "include": "_default_template_yaml"
6
+ "task": "mmlu_computer_security"
7
+ "task_alias": "computer_security"
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_conceptual_physics.yaml ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ "dataset_name": "conceptual_physics"
2
+ "description": "The following are multiple choice questions (with answers) about conceptual\
3
+ \ physics.\n\n"
4
+ "tag": "mmlu_stem_tasks"
5
+ "include": "_default_template_yaml"
6
+ "task": "mmlu_conceptual_physics"
7
+ "task_alias": "conceptual_physics"
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_electrical_engineering.yaml ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ "dataset_name": "electrical_engineering"
2
+ "description": "The following are multiple choice questions (with answers) about electrical\
3
+ \ engineering.\n\n"
4
+ "tag": "mmlu_stem_tasks"
5
+ "include": "_default_template_yaml"
6
+ "task": "mmlu_electrical_engineering"
7
+ "task_alias": "electrical_engineering"
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_elementary_mathematics.yaml ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ "dataset_name": "elementary_mathematics"
2
+ "description": "The following are multiple choice questions (with answers) about elementary\
3
+ \ mathematics.\n\n"
4
+ "tag": "mmlu_stem_tasks"
5
+ "include": "_default_template_yaml"
6
+ "task": "mmlu_elementary_mathematics"
7
+ "task_alias": "elementary_mathematics"
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_formal_logic.yaml ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ "dataset_name": "formal_logic"
2
+ "description": "The following are multiple choice questions (with answers) about formal\
3
+ \ logic.\n\n"
4
+ "tag": "mmlu_humanities_tasks"
5
+ "include": "_default_template_yaml"
6
+ "task": "mmlu_formal_logic"
7
+ "task_alias": "formal_logic"
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_global_facts.yaml ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ "dataset_name": "global_facts"
2
+ "description": "The following are multiple choice questions (with answers) about global\
3
+ \ facts.\n\n"
4
+ "tag": "mmlu_other_tasks"
5
+ "include": "_default_template_yaml"
6
+ "task": "mmlu_global_facts"
7
+ "task_alias": "global_facts"
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_high_school_biology.yaml ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ "dataset_name": "high_school_biology"
2
+ "description": "The following are multiple choice questions (with answers) about high\
3
+ \ school biology.\n\n"
4
+ "tag": "mmlu_stem_tasks"
5
+ "include": "_default_template_yaml"
6
+ "task": "mmlu_high_school_biology"
7
+ "task_alias": "high_school_biology"
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_high_school_chemistry.yaml ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ "dataset_name": "high_school_chemistry"
2
+ "description": "The following are multiple choice questions (with answers) about high\
3
+ \ school chemistry.\n\n"
4
+ "tag": "mmlu_stem_tasks"
5
+ "include": "_default_template_yaml"
6
+ "task": "mmlu_high_school_chemistry"
7
+ "task_alias": "high_school_chemistry"
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_high_school_computer_science.yaml ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ "dataset_name": "high_school_computer_science"
2
+ "description": "The following are multiple choice questions (with answers) about high\
3
+ \ school computer science.\n\n"
4
+ "tag": "mmlu_stem_tasks"
5
+ "include": "_default_template_yaml"
6
+ "task": "mmlu_high_school_computer_science"
7
+ "task_alias": "high_school_computer_science"
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_high_school_european_history.yaml ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ "dataset_name": "high_school_european_history"
2
+ "description": "The following are multiple choice questions (with answers) about high\
3
+ \ school european history.\n\n"
4
+ "tag": "mmlu_humanities_tasks"
5
+ "include": "_default_template_yaml"
6
+ "task": "mmlu_high_school_european_history"
7
+ "task_alias": "high_school_european_history"
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_high_school_geography.yaml ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ "dataset_name": "high_school_geography"
2
+ "description": "The following are multiple choice questions (with answers) about high\
3
+ \ school geography.\n\n"
4
+ "tag": "mmlu_social_sciences_tasks"
5
+ "include": "_default_template_yaml"
6
+ "task": "mmlu_high_school_geography"
7
+ "task_alias": "high_school_geography"
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_high_school_government_and_politics.yaml ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ "dataset_name": "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": "mmlu_social_sciences_tasks"
5
+ "include": "_default_template_yaml"
6
+ "task": "mmlu_high_school_government_and_politics"
7
+ "task_alias": "high_school_government_and_politics"
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_high_school_macroeconomics.yaml ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ "dataset_name": "high_school_macroeconomics"
2
+ "description": "The following are multiple choice questions (with answers) about high\
3
+ \ school macroeconomics.\n\n"
4
+ "tag": "mmlu_social_sciences_tasks"
5
+ "include": "_default_template_yaml"
6
+ "task": "mmlu_high_school_macroeconomics"
7
+ "task_alias": "high_school_macroeconomics"
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_high_school_mathematics.yaml ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ "dataset_name": "high_school_mathematics"
2
+ "description": "The following are multiple choice questions (with answers) about high\
3
+ \ school mathematics.\n\n"
4
+ "tag": "mmlu_stem_tasks"
5
+ "include": "_default_template_yaml"
6
+ "task": "mmlu_high_school_mathematics"
7
+ "task_alias": "high_school_mathematics"
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_high_school_microeconomics.yaml ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ "dataset_name": "high_school_microeconomics"
2
+ "description": "The following are multiple choice questions (with answers) about high\
3
+ \ school microeconomics.\n\n"
4
+ "tag": "mmlu_social_sciences_tasks"
5
+ "include": "_default_template_yaml"
6
+ "task": "mmlu_high_school_microeconomics"
7
+ "task_alias": "high_school_microeconomics"
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_high_school_physics.yaml ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ "dataset_name": "high_school_physics"
2
+ "description": "The following are multiple choice questions (with answers) about high\
3
+ \ school physics.\n\n"
4
+ "tag": "mmlu_stem_tasks"
5
+ "include": "_default_template_yaml"
6
+ "task": "mmlu_high_school_physics"
7
+ "task_alias": "high_school_physics"
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_high_school_psychology.yaml ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ "dataset_name": "high_school_psychology"
2
+ "description": "The following are multiple choice questions (with answers) about high\
3
+ \ school psychology.\n\n"
4
+ "tag": "mmlu_social_sciences_tasks"
5
+ "include": "_default_template_yaml"
6
+ "task": "mmlu_high_school_psychology"
7
+ "task_alias": "high_school_psychology"
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_high_school_statistics.yaml ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ "dataset_name": "high_school_statistics"
2
+ "description": "The following are multiple choice questions (with answers) about high\
3
+ \ school statistics.\n\n"
4
+ "tag": "mmlu_stem_tasks"
5
+ "include": "_default_template_yaml"
6
+ "task": "mmlu_high_school_statistics"
7
+ "task_alias": "high_school_statistics"
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_high_school_us_history.yaml ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ "dataset_name": "high_school_us_history"
2
+ "description": "The following are multiple choice questions (with answers) about high\
3
+ \ school us history.\n\n"
4
+ "tag": "mmlu_humanities_tasks"
5
+ "include": "_default_template_yaml"
6
+ "task": "mmlu_high_school_us_history"
7
+ "task_alias": "high_school_us_history"
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_high_school_world_history.yaml ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ "dataset_name": "high_school_world_history"
2
+ "description": "The following are multiple choice questions (with answers) about high\
3
+ \ school world history.\n\n"
4
+ "tag": "mmlu_humanities_tasks"
5
+ "include": "_default_template_yaml"
6
+ "task": "mmlu_high_school_world_history"
7
+ "task_alias": "high_school_world_history"
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_human_aging.yaml ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ "dataset_name": "human_aging"
2
+ "description": "The following are multiple choice questions (with answers) about human\
3
+ \ aging.\n\n"
4
+ "tag": "mmlu_other_tasks"
5
+ "include": "_default_template_yaml"
6
+ "task": "mmlu_human_aging"
7
+ "task_alias": "human_aging"
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_human_sexuality.yaml ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ "dataset_name": "human_sexuality"
2
+ "description": "The following are multiple choice questions (with answers) about human\
3
+ \ sexuality.\n\n"
4
+ "tag": "mmlu_social_sciences_tasks"
5
+ "include": "_default_template_yaml"
6
+ "task": "mmlu_human_sexuality"
7
+ "task_alias": "human_sexuality"
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_international_law.yaml ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ "dataset_name": "international_law"
2
+ "description": "The following are multiple choice questions (with answers) about international\
3
+ \ law.\n\n"
4
+ "tag": "mmlu_humanities_tasks"
5
+ "include": "_default_template_yaml"
6
+ "task": "mmlu_international_law"
7
+ "task_alias": "international_law"
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_jurisprudence.yaml ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ "dataset_name": "jurisprudence"
2
+ "description": "The following are multiple choice questions (with answers) about jurisprudence.\n\
3
+ \n"
4
+ "tag": "mmlu_humanities_tasks"
5
+ "include": "_default_template_yaml"
6
+ "task": "mmlu_jurisprudence"
7
+ "task_alias": "jurisprudence"
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_logical_fallacies.yaml ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ "dataset_name": "logical_fallacies"
2
+ "description": "The following are multiple choice questions (with answers) about logical\
3
+ \ fallacies.\n\n"
4
+ "tag": "mmlu_humanities_tasks"
5
+ "include": "_default_template_yaml"
6
+ "task": "mmlu_logical_fallacies"
7
+ "task_alias": "logical_fallacies"
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_machine_learning.yaml ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ "dataset_name": "machine_learning"
2
+ "description": "The following are multiple choice questions (with answers) about machine\
3
+ \ learning.\n\n"
4
+ "tag": "mmlu_stem_tasks"
5
+ "include": "_default_template_yaml"
6
+ "task": "mmlu_machine_learning"
7
+ "task_alias": "machine_learning"
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_management.yaml ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ "dataset_name": "management"
2
+ "description": "The following are multiple choice questions (with answers) about management.\n\
3
+ \n"
4
+ "tag": "mmlu_other_tasks"
5
+ "include": "_default_template_yaml"
6
+ "task": "mmlu_management"
7
+ "task_alias": "management"
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_marketing.yaml ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ "dataset_name": "marketing"
2
+ "description": "The following are multiple choice questions (with answers) about marketing.\n\
3
+ \n"
4
+ "tag": "mmlu_other_tasks"
5
+ "include": "_default_template_yaml"
6
+ "task": "mmlu_marketing"
7
+ "task_alias": "marketing"
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_medical_genetics.yaml ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ "dataset_name": "medical_genetics"
2
+ "description": "The following are multiple choice questions (with answers) about medical\
3
+ \ genetics.\n\n"
4
+ "tag": "mmlu_other_tasks"
5
+ "include": "_default_template_yaml"
6
+ "task": "mmlu_medical_genetics"
7
+ "task_alias": "medical_genetics"
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_miscellaneous.yaml ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ "dataset_name": "miscellaneous"
2
+ "description": "The following are multiple choice questions (with answers) about miscellaneous.\n\
3
+ \n"
4
+ "tag": "mmlu_other_tasks"
5
+ "include": "_default_template_yaml"
6
+ "task": "mmlu_miscellaneous"
7
+ "task_alias": "miscellaneous"
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_moral_disputes.yaml ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ "dataset_name": "moral_disputes"
2
+ "description": "The following are multiple choice questions (with answers) about moral\
3
+ \ disputes.\n\n"
4
+ "tag": "mmlu_humanities_tasks"
5
+ "include": "_default_template_yaml"
6
+ "task": "mmlu_moral_disputes"
7
+ "task_alias": "moral_disputes"
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_moral_scenarios.yaml ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ "dataset_name": "moral_scenarios"
2
+ "description": "The following are multiple choice questions (with answers) about moral\
3
+ \ scenarios.\n\n"
4
+ "tag": "mmlu_humanities_tasks"
5
+ "include": "_default_template_yaml"
6
+ "task": "mmlu_moral_scenarios"
7
+ "task_alias": "moral_scenarios"
scripts/yans/lm-evaluation-harness/lm_eval/tasks/mmlu/default/mmlu_nutrition.yaml ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ "dataset_name": "nutrition"
2
+ "description": "The following are multiple choice questions (with answers) about nutrition.\n\
3
+ \n"
4
+ "tag": "mmlu_other_tasks"
5
+ "include": "_default_template_yaml"
6
+ "task": "mmlu_nutrition"
7
+ "task_alias": "nutrition"