423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-09-18 19:12:49 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix eval scripts

Browse Source 
Former-commit-id: 177604fb6bf09fdfc05216b5f1e5e1c95fcc8d43
This commit is contained in:
hiyouga 2024-05-05 00:53:07 +08:00
parent 9bbb5c846d
commit a510ea9390
3 changed files with 74 additions and 86 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
evaluation/ceval/ceval.py
View File

@ -133,25 +133,19 @@ class Ceval(datasets.GeneratorBasedBuilder):
datasets.SplitGenerator( datasets.SplitGenerator(
name=datasets.Split.TEST, name=datasets.Split.TEST,
gen_kwargs={ gen_kwargs={
"filepath": os.path.join( "filepath": os.path.join(data_dir, "test", f"{task_name}_test.csv"),
data_dir, "test", f"{task_name}_test.csv"
),
}, },
), ),
datasets.SplitGenerator( datasets.SplitGenerator(
name=datasets.Split.VALIDATION, name=datasets.Split.VALIDATION,
gen_kwargs={ gen_kwargs={
"filepath": os.path.join( "filepath": os.path.join(data_dir, "val", f"{task_name}_val.csv"),
data_dir, "val", f"{task_name}_val.csv"
),
}, },
), ),
datasets.SplitGenerator( datasets.SplitGenerator(
name=datasets.Split.TRAIN, name=datasets.Split.TRAIN,
gen_kwargs={ gen_kwargs={
"filepath": os.path.join( "filepath": os.path.join(data_dir, "dev", f"{task_name}_dev.csv"),
data_dir, "dev", f"{task_name}_dev.csv"
),
}, },
), ),
] ]

134
evaluation/cmmlu/cmmlu.py
View File

@ -37,73 +37,73 @@ _LICENSE = "Creative Commons Attribution-NonCommercial-ShareAlike 4.0 Internatio
_URL = "cmmlu.zip" _URL = "cmmlu.zip"
task_list = [ task_list = [
'agronomy', "agronomy",
'anatomy', "anatomy",
'ancient_chinese', "ancient_chinese",
'arts', "arts",
'astronomy', "astronomy",
'business_ethics', "business_ethics",
'chinese_civil_service_exam', "chinese_civil_service_exam",
'chinese_driving_rule', "chinese_driving_rule",
'chinese_food_culture', "chinese_food_culture",
'chinese_foreign_policy', "chinese_foreign_policy",
'chinese_history', "chinese_history",
'chinese_literature', "chinese_literature",
'chinese_teacher_qualification', "chinese_teacher_qualification",
'clinical_knowledge', "clinical_knowledge",
'college_actuarial_science', "college_actuarial_science",
'college_education', "college_education",
'college_engineering_hydrology', "college_engineering_hydrology",
'college_law', "college_law",
'college_mathematics', "college_mathematics",
'college_medical_statistics', "college_medical_statistics",
'college_medicine', "college_medicine",
'computer_science', "computer_science",
'computer_security', "computer_security",
'conceptual_physics', "conceptual_physics",
'construction_project_management', "construction_project_management",
'economics', "economics",
'education', "education",
'electrical_engineering', "electrical_engineering",
'elementary_chinese', "elementary_chinese",
'elementary_commonsense', "elementary_commonsense",
'elementary_information_and_technology', "elementary_information_and_technology",
'elementary_mathematics', "elementary_mathematics",
'ethnology', "ethnology",
'food_science', "food_science",
'genetics', "genetics",
'global_facts', "global_facts",
'high_school_biology', "high_school_biology",
'high_school_chemistry', "high_school_chemistry",
'high_school_geography', "high_school_geography",
'high_school_mathematics', "high_school_mathematics",
'high_school_physics', "high_school_physics",
'high_school_politics', "high_school_politics",
'human_sexuality', "human_sexuality",
'international_law', "international_law",
'journalism', "journalism",
'jurisprudence', "jurisprudence",
'legal_and_moral_basis', "legal_and_moral_basis",
'logical', "logical",
'machine_learning', "machine_learning",
'management', "management",
'marketing', "marketing",
'marxist_theory', "marxist_theory",
'modern_chinese', "modern_chinese",
'nutrition', "nutrition",
'philosophy', "philosophy",
'professional_accounting', "professional_accounting",
'professional_law', "professional_law",
'professional_medicine', "professional_medicine",
'professional_psychology', "professional_psychology",
'public_relations', "public_relations",
'security_study', "security_study",
'sociology', "sociology",
'sports_science', "sports_science",
'traditional_chinese_medicine', "traditional_chinese_medicine",
'virology', "virology",
'world_history', "world_history",
'world_religions', "world_religions",
] ]

12
evaluation/mmlu/mmlu.py
View File

@ -136,25 +136,19 @@ class MMLU(datasets.GeneratorBasedBuilder):
datasets.SplitGenerator( datasets.SplitGenerator(
name=datasets.Split.TEST, name=datasets.Split.TEST,
gen_kwargs={ gen_kwargs={
"filepath": os.path.join( "filepath": os.path.join(data_dir, "data", "test", f"{task_name}_test.csv"),
data_dir, "data", "test", f"{task_name}_test.csv"
),
}, },
), ),
datasets.SplitGenerator( datasets.SplitGenerator(
name=datasets.Split.VALIDATION, name=datasets.Split.VALIDATION,
gen_kwargs={ gen_kwargs={
"filepath": os.path.join( "filepath": os.path.join(data_dir, "data", "val", f"{task_name}_val.csv"),
data_dir, "data", "val", f"{task_name}_val.csv"
),
}, },
), ),
datasets.SplitGenerator( datasets.SplitGenerator(
name=datasets.Split.TRAIN, name=datasets.Split.TRAIN,
gen_kwargs={ gen_kwargs={
"filepath": os.path.join( "filepath": os.path.join(data_dir, "data", "dev", f"{task_name}_dev.csv"),
data_dir, "data", "dev", f"{task_name}_dev.csv"
),
}, },
), ),
] ]