Skip to content

GitLab

Unverified Commit d5017101 authored by Xu Song's avatar Xu Song Committed by GitHub
Browse files

[Fix] Fix AGIEval chinese sets (#972) 

* [Fix] Fix AGIEval chinese sets

* Create agieval_gen_617738.py

* [Fix] Fix AGIEval chinese sets

* Restore agieval_gen_64afd3.py

* Update agieval_gen.py

* Create agieval_mixed_0fa998.py

* Update agieval_mixed.py
parent af10ecc2
Hide whitespace changes
Inline Side-by-side
Showing with 424 additions and 2 deletions
configs/datasets/agieval/agieval_gen.py
View file @ d5017101
from mmengine.config import read_base
with read_base():
from .agieval_gen_64afd3 import agieval_datasets # noqa: F401, F403
from .agieval_gen_617738 import agieval_datasets # noqa: F401, F403
configs/datasets/agieval/agieval_gen_617738.py 0 → 100644
View file @ d5017101
from opencompass.openicl.icl_prompt_template import PromptTemplate
from opencompass.openicl.icl_retriever import ZeroRetriever
from opencompass.openicl.icl_inferencer import GenInferencer
from opencompass.openicl.icl_evaluator import AccEvaluator
from opencompass.datasets import AGIEvalDataset_v2, AGIEvalEvaluator
from opencompass.utils.text_postprocessors import first_option_postprocess, first_capital_postprocess_multi
agieval_reader_cfg = dict(
input_columns=['question', 'options'], output_column='label')
agieval_single_choice_sets = [
'gaokao-chinese',
'gaokao-english',
'gaokao-geography',
'gaokao-history',
'gaokao-biology',
'gaokao-chemistry',
'gaokao-mathqa',
'logiqa-zh',
'lsat-ar',
'lsat-lr',
'lsat-rc',
'logiqa-en',
'sat-math',
'sat-en',
'sat-en-without-passage',
'aqua-rat',
]
agieval_multiple_choices_sets = [
'gaokao-physics',
'jec-qa-kd',
'jec-qa-ca',
]
agieval_cloze_sets = ['gaokao-mathcloze', 'math']
agieval_chinese_sets = [
'gaokao-chinese',
'gaokao-english',
'gaokao-geography',
'gaokao-history',
'gaokao-biology',
'gaokao-chemistry',
'gaokao-physics',
'gaokao-mathqa',
'logiqa-zh',
'gaokao-mathcloze',
'jec-qa-kd',
'jec-qa-ca',
]
agieval_english_sets = [
'lsat-ar',
'lsat-lr',
'lsat-rc',
'logiqa-en',
'sat-math',
'sat-en',
'sat-en-without-passage',
'aqua-rat',
'math',
]
agieval_gaokao_sets = [
'gaokao-chinese',
'gaokao-english',
'gaokao-geography',
'gaokao-history',
'gaokao-biology',
'gaokao-chemistry',
'gaokao-physics',
'gaokao-mathqa',
]
agieval_datasets = []
for _name in agieval_single_choice_sets:
if _name in agieval_chinese_sets:
_hint = '答案是： '
else:
_hint = 'The answer is '
agieval_infer_cfg = dict(
prompt_template=dict(
type=PromptTemplate,
template=dict(round=[
dict(
role='HUMAN', prompt=f'{{question}}\n{{options}}\n{_hint}')
])),
retriever=dict(type=ZeroRetriever),
inferencer=dict(type=GenInferencer, max_out_len=1024))
agieval_eval_cfg = dict(
evaluator=dict(type=AccEvaluator),
pred_postprocessor=dict(
type=first_option_postprocess, options='ABCDE'))
agieval_datasets.append(
dict(
type=AGIEvalDataset_v2,
path='./data/AGIEval/data/v1/',
name=_name,
abbr='agieval-' + _name,
setting_name='zero-shot',
reader_cfg=agieval_reader_cfg,
infer_cfg=agieval_infer_cfg.copy(),
eval_cfg=agieval_eval_cfg.copy()))
for _name in agieval_multiple_choices_sets:
if _name in agieval_chinese_sets:
_hint = '答案是： '
else:
_hint = 'The answer is '
agieval_infer_cfg = dict(
prompt_template=dict(
type=PromptTemplate,
template=dict(round=[
dict(
role='HUMAN', prompt=f'{{question}}\n{{options}}\n{_hint}')
])),
retriever=dict(type=ZeroRetriever),
inferencer=dict(type=GenInferencer, max_out_len=1024))
agieval_eval_cfg = dict(
evaluator=dict(type=AccEvaluator),
pred_postprocessor=dict(type=first_capital_postprocess_multi))
agieval_datasets.append(
dict(
type=AGIEvalDataset_v2,
path='./data/AGIEval/data/v1/',
name=_name,
abbr='agieval-' + _name,
setting_name='zero-shot',
reader_cfg=agieval_reader_cfg,
infer_cfg=agieval_infer_cfg.copy(),
eval_cfg=agieval_eval_cfg.copy()))
for _name in agieval_cloze_sets:
if _name in agieval_chinese_sets:
_hint = '答案是： '
else:
_hint = 'The answer is '
agieval_infer_cfg = dict(
prompt_template=dict(
type=PromptTemplate,
template=dict(
round=[dict(role='HUMAN', prompt=f'{{question}}\n{_hint}')])),
retriever=dict(type=ZeroRetriever),
inferencer=dict(type=GenInferencer, max_out_len=1024))
agieval_eval_cfg = dict(evaluator=dict(type=AGIEvalEvaluator))
agieval_datasets.append(
dict(
type=AGIEvalDataset_v2,
path='./data/AGIEval/data/v1/',
name=_name,
abbr='agieval-' + _name,
setting_name='zero-shot',
reader_cfg=agieval_reader_cfg,
infer_cfg=agieval_infer_cfg.copy(),
eval_cfg=agieval_eval_cfg.copy()))
for _item in agieval_datasets:
_name = _item['name']
_intro = {
'gaokao-chinese':
'以下是一道中国高考语文选择题，请选择正确的答案。',
'gaokao-english':
'以下是一道中国高考英语选择题，请选择正确的答案。',
'gaokao-geography':
'以下是一道中国高考地理选择题，请选择正确的答案。',
'gaokao-history':
'以下是一道中国高考历史选择题，请选择正确的答案。',
'gaokao-biology':
'以下是一道中国高考生物选择题，请选择正确的答案。',
'gaokao-chemistry':
'以下是一道中国高考化学选择题，请选择正确的答案。',
'gaokao-physics':
'以下是一道中国高考物理选择题，请选择正确的答案。',
'gaokao-mathqa':
'以下是一道中国高考数学选择题，请选择正确的答案。',
'logiqa-zh':
'以下是一道中国公务员考试题，请选择正确的答案。',
'lsat-ar':
'The following is a LSAT Analytical Reasoning question. Please select the correct answer.',
'lsat-lr':
'The following is a LSAT Logical Reasoning question. Please select the correct answer.',
'lsat-rc':
'The following is a LSAT Reading Comprehension question. Please select the correct answer.',
'logiqa-en':
'The following is a Logic Reasoning question. Please select the correct answer.',
'sat-math':
'The following is a SAT Math question. Please select the correct answer.',
'sat-en':
'The following is a SAT English question. Please select the correct answer.',
'sat-en-without-passage':
'The following is a SAT English question. Please select the correct answer.',
'aqua-rat':
'The following is a AQUA-RAT question. Please select the correct answer.',
'jec-qa-kd':
'以下是一道中国司法考试基础知识题，请选择正确的答案。',
'jec-qa-ca':
'以下是一道中国司法考试案例分析题，请选择正确的答案。',
'gaokao-mathcloze':
'以下是一道中国高考数学填空题，请填入正确的答案。',
'math':
'The following is a Math question. Please select the correct answer.',
}[_name]
_templates = _item['infer_cfg']['prompt_template']['template']
_templates['round'][0][
'prompt'] = _intro + '\n' + _templates['round'][0]['prompt']
del _item, _intro, _templates, _name, _hint, agieval_infer_cfg, agieval_eval_cfg
configs/datasets/agieval/agieval_mixed.py
View file @ d5017101
from mmengine.config import read_base
with read_base():
from .agieval_mixed_2f14ad import agieval_datasets # noqa: F401, F403
from .agieval_mixed_0fa998 import agieval_datasets # noqa: F401, F403
configs/datasets/agieval/agieval_mixed_0fa998.py 0 → 100644
View file @ d5017101
from opencompass.openicl.icl_prompt_template import PromptTemplate
from opencompass.openicl.icl_retriever import ZeroRetriever
from opencompass.openicl.icl_inferencer import PPLInferencer, GenInferencer
from opencompass.openicl.icl_evaluator import AccEvaluator
from opencompass.datasets import AGIEvalDataset_v2, AGIEvalEvaluator, AGIEvalEvaluator_mcq
from opencompass.utils.text_postprocessors import first_capital_postprocess_multi
agieval_single_choice_sets = [
'gaokao-chinese',
'gaokao-english',
'gaokao-geography',
'gaokao-history',
'gaokao-biology',
'gaokao-chemistry',
'gaokao-mathqa',
'logiqa-zh',
'lsat-ar',
'lsat-lr',
'lsat-rc',
'logiqa-en',
'sat-math',
'sat-en',
'sat-en-without-passage',
'aqua-rat',
]
agieval_multiple_choices_sets = [
'gaokao-physics',
'jec-qa-kd',
'jec-qa-ca',
]
agieval_cloze_sets = ['gaokao-mathcloze', 'math']
agieval_chinese_sets = [
'gaokao-chinese',
'gaokao-english',
'gaokao-geography',
'gaokao-history',
'gaokao-biology',
'gaokao-chemistry',
'gaokao-physics',
'gaokao-mathqa',
'logiqa-zh',
'gaokao-mathcloze',
'jec-qa-kd',
'jec-qa-ca',
]
agieval_english_sets = [
'lsat-ar',
'lsat-lr',
'lsat-rc',
'logiqa-en',
'sat-math',
'sat-en',
'sat-en-without-passage',
'aqua-rat',
'math',
]
agieval_gaokao_sets = [
'gaokao-chinese',
'gaokao-english',
'gaokao-geography',
'gaokao-history',
'gaokao-biology',
'gaokao-chemistry',
'gaokao-physics',
'gaokao-mathqa',
]
agieval_datasets = []
for _name in agieval_single_choice_sets:
if _name in ['lsat-ar', 'lsat-lr', 'lsat-rc', 'aqua-rat']:
_options = ['A', 'B', 'C', 'D', 'E']
else:
_options = ['A', 'B', 'C', 'D']
if _name in agieval_chinese_sets:
_hint = '答案是：'
else:
_hint = 'The answer is '
])
for label in _options
}),
retriever=dict(type=ZeroRetriever),
inferencer=dict(type=PPLInferencer, labels=_options))
agieval_eval_cfg = dict(evaluator=dict(type=AccEvaluator))
agieval_datasets.append(
dict(
type=AGIEvalDataset_v2,
path='./data/AGIEval/data/v1/',
name=_name,
abbr='agieval-' + _name,
setting_name='zero-shot',
reader_cfg=dict(
input_columns=['question', 'options'] + _options,
output_column='label'),
infer_cfg=agieval_infer_cfg.copy(),
eval_cfg=agieval_eval_cfg.copy()))
for _name in agieval_multiple_choices_sets:
if _name in agieval_chinese_sets:
_hint = '答案是： '
else:
_hint = 'The answer is '
agieval_infer_cfg = dict(
prompt_template=dict(
type=PromptTemplate,
template=dict(round=[
dict(role='HUMAN', prompt=f'{{question}}\n{{options}}\n{_hint}')
])),
retriever=dict(type=ZeroRetriever),
inferencer=dict(type=GenInferencer, max_out_len=1024))
agieval_eval_cfg = dict(
evaluator=dict(type=AGIEvalEvaluator_mcq),
pred_postprocessor=dict(type=first_capital_postprocess_multi))
agieval_datasets.append(
dict(
type=AGIEvalDataset_v2,
path='./data/AGIEval/data/v1/',
name=_name,
abbr='agieval-' + _name,
setting_name='zero-shot',
reader_cfg=dict(
input_columns=['question', 'options'], output_column='label'),
infer_cfg=agieval_infer_cfg.copy(),
eval_cfg=agieval_eval_cfg.copy()))
for _name in agieval_cloze_sets:
if _name in agieval_chinese_sets:
_hint = '答案是：'
else:
_hint = 'The answer is '
agieval_infer_cfg = dict(
prompt_template=dict(
type=PromptTemplate,
template=dict(
round=[dict(role='HUMAN', prompt=f'{{question}}{_hint}')])),
retriever=dict(type=ZeroRetriever),
inferencer=dict(type=GenInferencer, max_out_len=1024))
agieval_eval_cfg = dict(evaluator=dict(type=AGIEvalEvaluator))
agieval_datasets.append(
dict(
type=AGIEvalDataset_v2,
path='./data/AGIEval/data/v1/',
name=_name,
abbr='agieval-' + _name,
setting_name='zero-shot',
reader_cfg=dict(
input_columns=['question', 'options'], output_column='label'),
infer_cfg=agieval_infer_cfg.copy(),
eval_cfg=agieval_eval_cfg.copy()))
for _item in agieval_datasets:
_name = _item['name']
_intro = {
'gaokao-chinese':
'以下是一道中国高考语文选择题，请选择正确的答案。',
'gaokao-english':
'以下是一道中国高考英语选择题，请选择正确的答案。',
'gaokao-geography':
'以下是一道中国高考地理选择题，请选择正确的答案。',
'gaokao-history':
'以下是一道中国高考历史选择题，请选择正确的答案。',
'gaokao-biology':
'以下是一道中国高考生物选择题，请选择正确的答案。',
'gaokao-chemistry':
'以下是一道中国高考化学选择题，请选择正确的答案。',
'gaokao-physics':
'以下是一道中国高考物理选择题，请选择正确的答案。',
'gaokao-mathqa':
'以下是一道中国高考数学选择题，请选择正确的答案。',
'logiqa-zh':
'以下是一道中国公务员考试题，请选择正确的答案。',
'lsat-ar':
'The following is a LSAT Analytical Reasoning question. Please select the correct answer.',
'lsat-lr':
'The following is a LSAT Logical Reasoning question. Please select the correct answer.',
'lsat-rc':
'The following is a LSAT Reading Comprehension question. Please select the correct answer.',
'logiqa-en':
'The following is a Logic Reasoning question. Please select the correct answer.',
'sat-math':
'The following is a SAT Math question. Please select the correct answer.',
'sat-en':
'The following is a SAT English question. Please select the correct answer.',
'sat-en-without-passage':
'The following is a SAT English question. Please select the correct answer.',
'aqua-rat':
'The following is a AQUA-RAT question. Please select the correct answer.',
'jec-qa-kd':
'以下是一道中国司法考试基础知识题，请选择正确的答案。',
'jec-qa-ca':
'以下是一道中国司法考试案例分析题，请选择正确的答案。',
'gaokao-mathcloze':
'以下是一道中国高考数学填空题，请填入正确的答案。',
'math':
'The following is a Math question. Please select the correct answer.',
}[_name]
_templates = _item['infer_cfg']['prompt_template']['template']
if _item['infer_cfg']['inferencer']['type'] == PPLInferencer:
for _label in _templates:
_templates[_label]['round'][0][
'prompt'] = _intro + '\n' + _templates[_label]['round'][0][
'prompt']
else:
_templates['round'][0][
'prompt'] = _intro + '\n' + _templates['round'][0]['prompt']
del _item, _intro, _templates, _label, _name, _options, _hint, agieval_infer_cfg, agieval_eval_cfg
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment