From 177604fb6bf09fdfc05216b5f1e5e1c95fcc8d43 Mon Sep 17 00:00:00 2001 From: hiyouga Date: Sun, 5 May 2024 00:53:07 +0800 Subject: [PATCH] fix eval scripts --- evaluation/ceval/ceval.py | 14 ++-- evaluation/cmmlu/cmmlu.py | 134 +++++++++++++++++++------------------- evaluation/mmlu/mmlu.py | 12 +--- 3 files changed, 74 insertions(+), 86 deletions(-) diff --git a/evaluation/ceval/ceval.py b/evaluation/ceval/ceval.py index 33005de3..4111d6b4 100644 --- a/evaluation/ceval/ceval.py +++ b/evaluation/ceval/ceval.py @@ -19,7 +19,7 @@ import pandas as pd _CITATION = """\ @article{huang2023ceval, - title={C-Eval: A Multi-Level Multi-Discipline Chinese Evaluation Suite for Foundation Models}, + title={C-Eval: A Multi-Level Multi-Discipline Chinese Evaluation Suite for Foundation Models}, author={Huang, Yuzhen and Bai, Yuzhuo and Zhu, Zhihao and Zhang, Junlei and Zhang, Jinghan and Su, Tangjun and Liu, Junteng and Lv, Chuancheng and Zhang, Yikai and Lei, Jiayi and Fu, Yao and Sun, Maosong and He, Junxian}, journal={arXiv preprint arXiv:2305.08322}, year={2023} @@ -133,25 +133,19 @@ class Ceval(datasets.GeneratorBasedBuilder): datasets.SplitGenerator( name=datasets.Split.TEST, gen_kwargs={ - "filepath": os.path.join( - data_dir, "test", f"{task_name}_test.csv" - ), + "filepath": os.path.join(data_dir, "test", f"{task_name}_test.csv"), }, ), datasets.SplitGenerator( name=datasets.Split.VALIDATION, gen_kwargs={ - "filepath": os.path.join( - data_dir, "val", f"{task_name}_val.csv" - ), + "filepath": os.path.join(data_dir, "val", f"{task_name}_val.csv"), }, ), datasets.SplitGenerator( name=datasets.Split.TRAIN, gen_kwargs={ - "filepath": os.path.join( - data_dir, "dev", f"{task_name}_dev.csv" - ), + "filepath": os.path.join(data_dir, "dev", f"{task_name}_dev.csv"), }, ), ] diff --git a/evaluation/cmmlu/cmmlu.py b/evaluation/cmmlu/cmmlu.py index 62096203..37efb328 100644 --- a/evaluation/cmmlu/cmmlu.py +++ b/evaluation/cmmlu/cmmlu.py @@ -37,73 +37,73 @@ _LICENSE = "Creative Commons Attribution-NonCommercial-ShareAlike 4.0 Internatio _URL = "cmmlu.zip" task_list = [ - 'agronomy', - 'anatomy', - 'ancient_chinese', - 'arts', - 'astronomy', - 'business_ethics', - 'chinese_civil_service_exam', - 'chinese_driving_rule', - 'chinese_food_culture', - 'chinese_foreign_policy', - 'chinese_history', - 'chinese_literature', - 'chinese_teacher_qualification', - 'clinical_knowledge', - 'college_actuarial_science', - 'college_education', - 'college_engineering_hydrology', - 'college_law', - 'college_mathematics', - 'college_medical_statistics', - 'college_medicine', - 'computer_science', - 'computer_security', - 'conceptual_physics', - 'construction_project_management', - 'economics', - 'education', - 'electrical_engineering', - 'elementary_chinese', - 'elementary_commonsense', - 'elementary_information_and_technology', - 'elementary_mathematics', - 'ethnology', - 'food_science', - 'genetics', - 'global_facts', - 'high_school_biology', - 'high_school_chemistry', - 'high_school_geography', - 'high_school_mathematics', - 'high_school_physics', - 'high_school_politics', - 'human_sexuality', - 'international_law', - 'journalism', - 'jurisprudence', - 'legal_and_moral_basis', - 'logical', - 'machine_learning', - 'management', - 'marketing', - 'marxist_theory', - 'modern_chinese', - 'nutrition', - 'philosophy', - 'professional_accounting', - 'professional_law', - 'professional_medicine', - 'professional_psychology', - 'public_relations', - 'security_study', - 'sociology', - 'sports_science', - 'traditional_chinese_medicine', - 'virology', - 'world_history', - 'world_religions', + "agronomy", + "anatomy", + "ancient_chinese", + "arts", + "astronomy", + "business_ethics", + "chinese_civil_service_exam", + "chinese_driving_rule", + "chinese_food_culture", + "chinese_foreign_policy", + "chinese_history", + "chinese_literature", + "chinese_teacher_qualification", + "clinical_knowledge", + "college_actuarial_science", + "college_education", + "college_engineering_hydrology", + "college_law", + "college_mathematics", + "college_medical_statistics", + "college_medicine", + "computer_science", + "computer_security", + "conceptual_physics", + "construction_project_management", + "economics", + "education", + "electrical_engineering", + "elementary_chinese", + "elementary_commonsense", + "elementary_information_and_technology", + "elementary_mathematics", + "ethnology", + "food_science", + "genetics", + "global_facts", + "high_school_biology", + "high_school_chemistry", + "high_school_geography", + "high_school_mathematics", + "high_school_physics", + "high_school_politics", + "human_sexuality", + "international_law", + "journalism", + "jurisprudence", + "legal_and_moral_basis", + "logical", + "machine_learning", + "management", + "marketing", + "marxist_theory", + "modern_chinese", + "nutrition", + "philosophy", + "professional_accounting", + "professional_law", + "professional_medicine", + "professional_psychology", + "public_relations", + "security_study", + "sociology", + "sports_science", + "traditional_chinese_medicine", + "virology", + "world_history", + "world_religions", ] diff --git a/evaluation/mmlu/mmlu.py b/evaluation/mmlu/mmlu.py index 9f1bd101..f3218c38 100644 --- a/evaluation/mmlu/mmlu.py +++ b/evaluation/mmlu/mmlu.py @@ -136,25 +136,19 @@ class MMLU(datasets.GeneratorBasedBuilder): datasets.SplitGenerator( name=datasets.Split.TEST, gen_kwargs={ - "filepath": os.path.join( - data_dir, "data", "test", f"{task_name}_test.csv" - ), + "filepath": os.path.join(data_dir, "data", "test", f"{task_name}_test.csv"), }, ), datasets.SplitGenerator( name=datasets.Split.VALIDATION, gen_kwargs={ - "filepath": os.path.join( - data_dir, "data", "val", f"{task_name}_val.csv" - ), + "filepath": os.path.join(data_dir, "data", "val", f"{task_name}_val.csv"), }, ), datasets.SplitGenerator( name=datasets.Split.TRAIN, gen_kwargs={ - "filepath": os.path.join( - data_dir, "data", "dev", f"{task_name}_dev.csv" - ), + "filepath": os.path.join(data_dir, "data", "dev", f"{task_name}_dev.csv"), }, ), ]