_generate_configs.py 3.87 KB
Newer Older
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
"""
Take in a YAML, and output all "other" splits with this YAML
"""

import argparse
import logging
import os

import yaml
from tqdm import tqdm


eval_logger = logging.getLogger("lm-eval")


MMLU_SUBJECTS = {
    "global_facts": "other",
    "high_school_european_history": "humanities",
    "high_school_geography": "social_sciences",
    "high_school_government_and_politics": "social_sciences",
    "high_school_psychology": "social_sciences",
    "high_school_statistics": "stem",
    "high_school_world_history": "humanities",
    "human_aging": "other",
    "international_law": "humanities",
    "jurisprudence": "humanities",
    "logical_fallacies": "humanities",
    "management": "other",
    "marketing": "other",
    "moral_disputes": "humanities",
    "moral_scenarios": "humanities",
    "nutrition": "other",
    "philosophy": "humanities",
    "professional_law": "humanities",
    "professional_psychology": "social_sciences",
    "public_relations": "social_sciences",
    "security_studies": "social_sciences",
    "sociology": "social_sciences",
    "world_religions": "humanities",
}


ARABIC_MMLU_SUBJECTS = {
    "islamic_studies": "humanities",
    "driving_test": "other",
    "natural_science": "stem",
    "history": "humanities",
    "general_knowledge": "other",
    "law": "humanities",
    "physics": "stem",
    "social_science": "social_sciences",
    "management_ar": "other",
    "arabic_language": "language",
    "political_science": "social_sciences",
    "philosophy_ar": "humanities",
    "accounting": "social_sciences",
    "computer_science": "stem",
    "geography": "social_sciences",
    "math": "stem",
    "biology": "stem",
    "economics": "social_sciences",
    "arabic_language_(general)": "language",
    "arabic_language_(grammar)": "language",
    "civics": "social_sciences"
}

DATASETS = {
    "mmlu": MMLU_SUBJECTS,
    "ar_mmlu": ARABIC_MMLU_SUBJECTS,
}


def parse_args():
    parser = argparse.ArgumentParser()
    parser.add_argument("--base_yaml_path", default="_default_darijammlu_template_yaml")
    parser.add_argument("--save_prefix_path", default="darijammlu")
    return parser.parse_args()


if __name__ == "__main__":
    args = parse_args()

    # get filename of base_yaml so we can `"include": ` it in our "other" YAMLs.
    base_yaml_name = os.path.split(args.base_yaml_path)[-1]
    with open(args.base_yaml_path, encoding="utf-8") as f:
        base_yaml = yaml.full_load(f)

    ALL_CATEGORIES = []
    for dataset, SUBJECTS in DATASETS.items():
        for subject, category in tqdm(SUBJECTS.items()):
            if category not in ALL_CATEGORIES:
                ALL_CATEGORIES.append(category)

            yaml_dict = {
                "include": base_yaml_name,
                "tag": [f"darijammlu_{category}_tasks", "darijammlu_"+dataset+"_tasks"],
                "task": f"darijammlu_{subject}",
                "task_alias": subject.replace("_", " "),
                "dataset_name": subject,
            }

            file_save_path = (
                args.save_prefix_path + f"_{subject}.yaml"
            )
            eval_logger.info(f"Saving yaml for subset {subject} to {file_save_path}")
            with open(file_save_path, "w", encoding="utf-8") as yaml_file:
                yaml.dump(
                    yaml_dict,
                    yaml_file,
                    allow_unicode=True,
                    default_style='"',
                )

    darijammlu_subcategories = [f"darijammlu_{category}" for category in ALL_CATEGORIES]

    file_save_path = args.save_prefix_path + ".yaml"

    eval_logger.info(f"Saving benchmark config to {file_save_path}")
    with open(file_save_path, "w", encoding="utf-8") as yaml_file:
        yaml.dump(
            {
                "group": "darijammlu",
                "task": darijammlu_subcategories,
            },
            yaml_file,
            indent=4,
            default_flow_style=False,
        )