[Feat] Support dataset_suffix check for mixed configs (#973)

* [Feat] Support dataset_suffix check for mixed configs * update mixed suffix * update suffix --------- Co-authored-by: Leymore <zfz-960727@163.com>
2025-05-30 16:03:24 +08:00 · 2024-05-14 15:03:28 +08:00 · 2024-05-14 15:03:28 +08:00 · 3dbba11945
commit 3dbba11945
parent 7505b3cadf
12 changed files with 18 additions and 229 deletions
--- a/configs/datasets/GaokaoBench/GaokaoBench_mixed.py
+++ b/configs/datasets/GaokaoBench/GaokaoBench_mixed.py
@ -1,4 +1,4 @@
 from mmengine.config import read_base

 with read_base():
-    from .GaokaoBench_mixed_f2038e import GaokaoBench_datasets  # noqa: F401, F403
+    from .GaokaoBench_mixed_9af5ee import GaokaoBench_datasets  # noqa: F401, F403
--- a/configs/datasets/GaokaoBench/GaokaoBench_mixed_9af5ee.py
+++ b/configs/datasets/GaokaoBench/GaokaoBench_mixed_9af5ee.py
--- a/configs/datasets/MathBench/mathbench_2024_wocircular_mixed_dc0207.py
+++ b/configs/datasets/MathBench/mathbench_2024_wocircular_mixed_dc0207.py
--- a/configs/datasets/agieval/agieval_mixed_0fa998.py
+++ b/configs/datasets/agieval/agieval_mixed_0fa998.py
@ -75,6 +75,13 @@ for _name in agieval_single_choice_sets:
        _hint = '答案是：'
    else:
        _hint = 'The answer is '
+    agieval_infer_cfg = dict(
+        prompt_template=dict(
+            type=PromptTemplate,
+            template={
+                label: dict(round=[
+                    dict(role='HUMAN', prompt='{question}\n{options}'),
+                    dict(role='BOT', prompt=f'{_hint}{label}')
                ])
                for label in _options
            }),
--- a/configs/datasets/agieval/agieval_mixed_2f14ad.py
+++ b/configs/datasets/agieval/agieval_mixed_2f14ad.py
@ -1,218 +0,0 @@
-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',
-]
-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 '
-    agieval_infer_cfg = dict(
-        prompt_template=dict(
-            type=PromptTemplate,
-            template={
-                label: dict(round=[
-                    dict(role='HUMAN', prompt='{question}\n{options}'),
-                    dict(role='BOT', prompt=f'{_hint}{label}')
-                ])
-                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
--- a/configs/datasets/collections/base_medium.py
+++ b/configs/datasets/collections/base_medium.py
@ -3,8 +3,8 @@ from mmengine.config import read_base
 with read_base():
    from ..mmlu.mmlu_ppl_ac766d import mmlu_datasets
    from ..ceval.ceval_ppl_578f8d import ceval_datasets
-    from ..agieval.agieval_mixed_2f14ad import agieval_datasets
-    from ..GaokaoBench.GaokaoBench_mixed_f2038e import GaokaoBench_datasets
+    from ..agieval.agieval_mixed_713d14 import agieval_datasets
+    from ..GaokaoBench.GaokaoBench_mixed_9af5ee import GaokaoBench_datasets
    from ..bbh.bbh_gen_5b92b0 import bbh_datasets
    from ..humaneval.humaneval_gen_8e312c import humaneval_datasets
    from ..mbpp.deprecated_mbpp_gen_1e1056 import mbpp_datasets
--- a/configs/datasets/collections/base_medium_llama.py
+++ b/configs/datasets/collections/base_medium_llama.py
@ -3,8 +3,8 @@ from mmengine.config import read_base
 with read_base():
    from ..mmlu.mmlu_ppl_ac766d import mmlu_datasets
    from ..ceval.ceval_ppl_578f8d import ceval_datasets
-    from ..agieval.agieval_mixed_2f14ad import agieval_datasets
-    from ..GaokaoBench.GaokaoBench_mixed_f2038e import GaokaoBench_datasets
+    from ..agieval.agieval_mixed_713d14 import agieval_datasets
+    from ..GaokaoBench.GaokaoBench_mixed_9af5ee import GaokaoBench_datasets
    from ..bbh.bbh_gen_5b92b0 import bbh_datasets
    from ..humaneval.humaneval_gen_a82cae import humaneval_datasets
    from ..mbpp.deprecated_mbpp_gen_1e1056 import mbpp_datasets
--- a/configs/datasets/collections/leaderboard/qwen.py
+++ b/configs/datasets/collections/leaderboard/qwen.py
@ -2,10 +2,10 @@ from mmengine.config import read_base

 with read_base():
    from ...ceval.ceval_ppl_578f8d import ceval_datasets
-    from ...agieval.agieval_mixed_2f14ad import agieval_datasets
+    from ...agieval.agieval_mixed_713d14 import agieval_datasets
    from ...mmlu.mmlu_ppl_ac766d import mmlu_datasets
    from ...cmmlu.cmmlu_ppl_8b9c76 import cmmlu_datasets
-    from ...GaokaoBench.GaokaoBench_mixed_f2038e import GaokaoBench_datasets
+    from ...GaokaoBench.GaokaoBench_mixed_9af5ee import GaokaoBench_datasets
    from ...ARC_c.ARC_c_gen_1e0de5 import ARC_c_datasets
    from ...ARC_e.ARC_e_gen_1e0de5 import ARC_e_datasets

--- a/configs/datasets/collections/leaderboard/qwen_chat.py
+++ b/configs/datasets/collections/leaderboard/qwen_chat.py
@ -2,7 +2,7 @@ from mmengine.config import read_base

 with read_base():
    from ...ceval.ceval_gen_5f30c7 import ceval_datasets
-    from ...agieval.agieval_mixed_2f14ad import agieval_datasets
+    from ...agieval.agieval_mixed_713d14 import agieval_datasets
    from ...mmlu.mmlu_gen_4d595a import mmlu_datasets
    from ...cmmlu.cmmlu_gen_c13365 import cmmlu_datasets
    from ...GaokaoBench.GaokaoBench_gen_5cfe9e import GaokaoBench_datasets
--- a/configs/eval_hf_llama2.py
+++ b/configs/eval_hf_llama2.py
@ -6,7 +6,7 @@ with read_base():
    from .datasets.nq.nq_open_gen_e93f8a import nq_datasets
    from .datasets.gsm8k.gsm8k_gen_3309bd import gsm8k_datasets
    from .datasets.humaneval.humaneval_gen_a82cae import humaneval_datasets
-    from .datasets.agieval.agieval_mixed_2f14ad import agieval_datasets
+    from .datasets.agieval.agieval_mixed_713d14 import agieval_datasets
    from .datasets.SuperGLUE_BoolQ.SuperGLUE_BoolQ_ppl_314797 import BoolQ_datasets
    from .datasets.hellaswag.hellaswag_ppl_a6e128 import hellaswag_datasets
    from .datasets.obqa.obqa_ppl_6aac9e import obqa_datasets
--- a/configs/eval_internlm2_keyset.py
+++ b/configs/eval_internlm2_keyset.py
@ -2,7 +2,7 @@ from mmengine.config import read_base

 with read_base():
    from .datasets.mmlu.mmlu_ppl_ac766d import mmlu_datasets
-    from .datasets.agieval.agieval_mixed_2f14ad import agieval_datasets
+    from .datasets.agieval.agieval_mixed_713d14 import agieval_datasets
    from .datasets.bbh.bbh_gen_5b92b0 import bbh_datasets
    from .datasets.gsm8k.gsm8k_gen_1d7fe4 import gsm8k_datasets
    from .datasets.math.math_gen_265cce import math_datasets
--- a/tools/update_dataset_suffix.py
+++ b/tools/update_dataset_suffix.py
@ -75,7 +75,7 @@ def get_hash(path):

 def check_and_rename(filepath):
    base_name = os.path.basename(filepath)
-    match = re.match(r'(.*)_(gen|ppl|ll)_(.*).py', base_name)
+    match = re.match(r'(.*)_(gen|ppl|ll|mixed)_(.*).py', base_name)
    if match:
        dataset, mode, old_hash = match.groups()
        new_hash = get_hash(filepath)