open-llm-leaderboard-old/details_bigscience__bloomz-7b1
收藏Hugging Face2023-12-04 更新2024-06-22 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard-old/details_bigscience__bloomz-7b1
下载链接
链接失效反馈官方服务:
资源简介:
---
pretty_name: Evaluation run of bigscience/bloomz-7b1
dataset_summary: "Dataset automatically created during the evaluation run of model\
\ [bigscience/bloomz-7b1](https://huggingface.co/bigscience/bloomz-7b1) on the [Open\
\ LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard).\n\
\nThe dataset is composed of 64 configuration, each one coresponding to one of the\
\ evaluated task.\n\nThe dataset has been created from 10 run(s). Each run can be\
\ found as a specific split in each configuration, the split being named using the\
\ timestamp of the run.The \"train\" split is always pointing to the latest results.\n\
\nAn additional configuration \"results\" store all the aggregated results of the\
\ run (and is used to compute and display the aggregated metrics on the [Open LLM\
\ Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)).\n\
\nTo load the details from a run, you can for instance do the following:\n```python\n\
from datasets import load_dataset\ndata = load_dataset(\"open-llm-leaderboard/details_bigscience__bloomz-7b1\"\
,\n\t\"harness_gsm8k_5\",\n\tsplit=\"train\")\n```\n\n## Latest results\n\nThese\
\ are the [latest results from run 2023-12-04T12:56:49.944014](https://huggingface.co/datasets/open-llm-leaderboard/details_bigscience__bloomz-7b1/blob/main/results_2023-12-04T12-56-49.944014.json)(note\
\ that their might be results for other tasks in the repos if successive evals didn't\
\ cover the same tasks. You find each in the results and the \"latest\" split for\
\ each eval):\n\n```python\n{\n \"all\": {\n \"acc\": 0.000758150113722517,\n\
\ \"acc_stderr\": 0.0007581501137225419\n },\n \"harness|gsm8k|5\"\
: {\n \"acc\": 0.000758150113722517,\n \"acc_stderr\": 0.0007581501137225419\n\
\ }\n}\n```"
repo_url: https://huggingface.co/bigscience/bloomz-7b1
leaderboard_url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard
point_of_contact: clementine@hf.co
configs:
- config_name: harness_arc_challenge_25
data_files:
- split: 2023_08_22T10_10_08.875186
path:
- '**/details_harness|arc:challenge|25_2023-08-22T10:10:08.875186.parquet'
- split: 2023_08_22T11_29_59.333088
path:
- '**/details_harness|arc:challenge|25_2023-08-22T11:29:59.333088.parquet'
- split: latest
path:
- '**/details_harness|arc:challenge|25_2023-08-22T11:29:59.333088.parquet'
- config_name: harness_drop_3
data_files:
- split: 2023_09_22T17_52_30.288263
path:
- '**/details_harness|drop|3_2023-09-22T17-52-30.288263.parquet'
- split: latest
path:
- '**/details_harness|drop|3_2023-09-22T17-52-30.288263.parquet'
- config_name: harness_gsm8k_5
data_files:
- split: 2023_09_22T17_52_30.288263
path:
- '**/details_harness|gsm8k|5_2023-09-22T17-52-30.288263.parquet'
- split: 2023_12_03T14_53_17.113107
path:
- '**/details_harness|gsm8k|5_2023-12-03T14-53-17.113107.parquet'
- split: 2023_12_03T15_55_50.672449
path:
- '**/details_harness|gsm8k|5_2023-12-03T15-55-50.672449.parquet'
- split: 2023_12_03T15_56_16.405841
path:
- '**/details_harness|gsm8k|5_2023-12-03T15-56-16.405841.parquet'
- split: 2023_12_04T09_46_15.159375
path:
- '**/details_harness|gsm8k|5_2023-12-04T09-46-15.159375.parquet'
- split: 2023_12_04T09_46_26.874047
path:
- '**/details_harness|gsm8k|5_2023-12-04T09-46-26.874047.parquet'
- split: 2023_12_04T12_56_20.274289
path:
- '**/details_harness|gsm8k|5_2023-12-04T12-56-20.274289.parquet'
- split: 2023_12_04T12_56_49.944014
path:
- '**/details_harness|gsm8k|5_2023-12-04T12-56-49.944014.parquet'
- split: latest
path:
- '**/details_harness|gsm8k|5_2023-12-04T12-56-49.944014.parquet'
- config_name: harness_hellaswag_10
data_files:
- split: 2023_08_22T10_10_08.875186
path:
- '**/details_harness|hellaswag|10_2023-08-22T10:10:08.875186.parquet'
- split: 2023_08_22T11_29_59.333088
path:
- '**/details_harness|hellaswag|10_2023-08-22T11:29:59.333088.parquet'
- split: latest
path:
- '**/details_harness|hellaswag|10_2023-08-22T11:29:59.333088.parquet'
- config_name: harness_hendrycksTest_5
data_files:
- split: 2023_08_22T10_10_08.875186
path:
- '**/details_harness|hendrycksTest-abstract_algebra|5_2023-08-22T10:10:08.875186.parquet'
- '**/details_harness|hendrycksTest-anatomy|5_2023-08-22T10:10:08.875186.parquet'
- '**/details_harness|hendrycksTest-astronomy|5_2023-08-22T10:10:08.875186.parquet'
- '**/details_harness|hendrycksTest-business_ethics|5_2023-08-22T10:10:08.875186.parquet'
- '**/details_harness|hendrycksTest-clinical_knowledge|5_2023-08-22T10:10:08.875186.parquet'
- '**/details_harness|hendrycksTest-college_biology|5_2023-08-22T10:10:08.875186.parquet'
- '**/details_harness|hendrycksTest-college_chemistry|5_2023-08-22T10:10:08.875186.parquet'
- '**/details_harness|hendrycksTest-college_computer_science|5_2023-08-22T10:10:08.875186.parquet'
- '**/details_harness|hendrycksTest-college_mathematics|5_2023-08-22T10:10:08.875186.parquet'
- '**/details_harness|hendrycksTest-college_medicine|5_2023-08-22T10:10:08.875186.parquet'
- '**/details_harness|hendrycksTest-college_physics|5_2023-08-22T10:10:08.875186.parquet'
- '**/details_harness|hendrycksTest-computer_security|5_2023-08-22T10:10:08.875186.parquet'
- '**/details_harness|hendrycksTest-conceptual_physics|5_2023-08-22T10:10:08.875186.parquet'
- '**/details_harness|hendrycksTest-econometrics|5_2023-08-22T10:10:08.875186.parquet'
- '**/details_harness|hendrycksTest-electrical_engineering|5_2023-08-22T10:10:08.875186.parquet'
- '**/details_harness|hendrycksTest-elementary_mathematics|5_2023-08-22T10:10:08.875186.parquet'
- '**/details_harness|hendrycksTest-formal_logic|5_2023-08-22T10:10:08.875186.parquet'
- '**/details_harness|hendrycksTest-global_facts|5_2023-08-22T10:10:08.875186.parquet'
- '**/details_harness|hendrycksTest-high_school_biology|5_2023-08-22T10:10:08.875186.parquet'
- '**/details_harness|hendrycksTest-high_school_chemistry|5_2023-08-22T10:10:08.875186.parquet'
- '**/details_harness|hendrycksTest-high_school_computer_science|5_2023-08-22T10:10:08.875186.parquet'
- '**/details_harness|hendrycksTest-high_school_european_history|5_2023-08-22T10:10:08.875186.parquet'
- '**/details_harness|hendrycksTest-high_school_geography|5_2023-08-22T10:10:08.875186.parquet'
- '**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-08-22T10:10:08.875186.parquet'
- '**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-08-22T10:10:08.875186.parquet'
- '**/details_harness|hendrycksTest-high_school_mathematics|5_2023-08-22T10:10:08.875186.parquet'
- '**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-08-22T10:10:08.875186.parquet'
- '**/details_harness|hendrycksTest-high_school_physics|5_2023-08-22T10:10:08.875186.parquet'
- '**/details_harness|hendrycksTest-high_school_psychology|5_2023-08-22T10:10:08.875186.parquet'
- '**/details_harness|hendrycksTest-high_school_statistics|5_2023-08-22T10:10:08.875186.parquet'
- '**/details_harness|hendrycksTest-high_school_us_history|5_2023-08-22T10:10:08.875186.parquet'
- '**/details_harness|hendrycksTest-high_school_world_history|5_2023-08-22T10:10:08.875186.parquet'
- '**/details_harness|hendrycksTest-human_aging|5_2023-08-22T10:10:08.875186.parquet'
- '**/details_harness|hendrycksTest-human_sexuality|5_2023-08-22T10:10:08.875186.parquet'
- '**/details_harness|hendrycksTest-international_law|5_2023-08-22T10:10:08.875186.parquet'
- '**/details_harness|hendrycksTest-jurisprudence|5_2023-08-22T10:10:08.875186.parquet'
- '**/details_harness|hendrycksTest-logical_fallacies|5_2023-08-22T10:10:08.875186.parquet'
- '**/details_harness|hendrycksTest-machine_learning|5_2023-08-22T10:10:08.875186.parquet'
- '**/details_harness|hendrycksTest-management|5_2023-08-22T10:10:08.875186.parquet'
- '**/details_harness|hendrycksTest-marketing|5_2023-08-22T10:10:08.875186.parquet'
- '**/details_harness|hendrycksTest-medical_genetics|5_2023-08-22T10:10:08.875186.parquet'
- '**/details_harness|hendrycksTest-miscellaneous|5_2023-08-22T10:10:08.875186.parquet'
- '**/details_harness|hendrycksTest-moral_disputes|5_2023-08-22T10:10:08.875186.parquet'
- '**/details_harness|hendrycksTest-moral_scenarios|5_2023-08-22T10:10:08.875186.parquet'
- '**/details_harness|hendrycksTest-nutrition|5_2023-08-22T10:10:08.875186.parquet'
- '**/details_harness|hendrycksTest-philosophy|5_2023-08-22T10:10:08.875186.parquet'
- '**/details_harness|hendrycksTest-prehistory|5_2023-08-22T10:10:08.875186.parquet'
- '**/details_harness|hendrycksTest-professional_accounting|5_2023-08-22T10:10:08.875186.parquet'
- '**/details_harness|hendrycksTest-professional_law|5_2023-08-22T10:10:08.875186.parquet'
- '**/details_harness|hendrycksTest-professional_medicine|5_2023-08-22T10:10:08.875186.parquet'
- '**/details_harness|hendrycksTest-professional_psychology|5_2023-08-22T10:10:08.875186.parquet'
- '**/details_harness|hendrycksTest-public_relations|5_2023-08-22T10:10:08.875186.parquet'
- '**/details_harness|hendrycksTest-security_studies|5_2023-08-22T10:10:08.875186.parquet'
- '**/details_harness|hendrycksTest-sociology|5_2023-08-22T10:10:08.875186.parquet'
- '**/details_harness|hendrycksTest-us_foreign_policy|5_2023-08-22T10:10:08.875186.parquet'
- '**/details_harness|hendrycksTest-virology|5_2023-08-22T10:10:08.875186.parquet'
- '**/details_harness|hendrycksTest-world_religions|5_2023-08-22T10:10:08.875186.parquet'
- split: 2023_08_22T11_29_59.333088
path:
- '**/details_harness|hendrycksTest-abstract_algebra|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-anatomy|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-astronomy|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-business_ethics|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-clinical_knowledge|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-college_biology|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-college_chemistry|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-college_computer_science|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-college_mathematics|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-college_medicine|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-college_physics|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-computer_security|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-conceptual_physics|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-econometrics|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-electrical_engineering|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-elementary_mathematics|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-formal_logic|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-global_facts|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-high_school_biology|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-high_school_chemistry|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-high_school_computer_science|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-high_school_european_history|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-high_school_geography|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-high_school_mathematics|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-high_school_physics|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-high_school_psychology|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-high_school_statistics|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-high_school_us_history|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-high_school_world_history|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-human_aging|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-human_sexuality|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-international_law|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-jurisprudence|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-logical_fallacies|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-machine_learning|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-management|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-marketing|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-medical_genetics|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-miscellaneous|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-moral_disputes|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-moral_scenarios|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-nutrition|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-philosophy|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-prehistory|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-professional_accounting|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-professional_law|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-professional_medicine|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-professional_psychology|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-public_relations|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-security_studies|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-sociology|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-us_foreign_policy|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-virology|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-world_religions|5_2023-08-22T11:29:59.333088.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-abstract_algebra|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-anatomy|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-astronomy|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-business_ethics|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-clinical_knowledge|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-college_biology|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-college_chemistry|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-college_computer_science|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-college_mathematics|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-college_medicine|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-college_physics|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-computer_security|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-conceptual_physics|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-econometrics|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-electrical_engineering|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-elementary_mathematics|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-formal_logic|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-global_facts|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-high_school_biology|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-high_school_chemistry|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-high_school_computer_science|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-high_school_european_history|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-high_school_geography|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-high_school_mathematics|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-high_school_physics|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-high_school_psychology|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-high_school_statistics|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-high_school_us_history|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-high_school_world_history|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-human_aging|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-human_sexuality|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-international_law|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-jurisprudence|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-logical_fallacies|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-machine_learning|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-management|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-marketing|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-medical_genetics|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-miscellaneous|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-moral_disputes|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-moral_scenarios|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-nutrition|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-philosophy|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-prehistory|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-professional_accounting|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-professional_law|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-professional_medicine|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-professional_psychology|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-public_relations|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-security_studies|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-sociology|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-us_foreign_policy|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-virology|5_2023-08-22T11:29:59.333088.parquet'
- '**/details_harness|hendrycksTest-world_religions|5_2023-08-22T11:29:59.333088.parquet'
- config_name: harness_hendrycksTest_abstract_algebra_5
data_files:
- split: 2023_08_22T10_10_08.875186
path:
- '**/details_harness|hendrycksTest-abstract_algebra|5_2023-08-22T10:10:08.875186.parquet'
- split: 2023_08_22T11_29_59.333088
path:
- '**/details_harness|hendrycksTest-abstract_algebra|5_2023-08-22T11:29:59.333088.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-abstract_algebra|5_2023-08-22T11:29:59.333088.parquet'
- config_name: harness_hendrycksTest_anatomy_5
data_files:
- split: 2023_08_22T10_10_08.875186
path:
- '**/details_harness|hendrycksTest-anatomy|5_2023-08-22T10:10:08.875186.parquet'
- split: 2023_08_22T11_29_59.333088
path:
- '**/details_harness|hendrycksTest-anatomy|5_2023-08-22T11:29:59.333088.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-anatomy|5_2023-08-22T11:29:59.333088.parquet'
- config_name: harness_hendrycksTest_astronomy_5
data_files:
- split: 2023_08_22T10_10_08.875186
path:
- '**/details_harness|hendrycksTest-astronomy|5_2023-08-22T10:10:08.875186.parquet'
- split: 2023_08_22T11_29_59.333088
path:
- '**/details_harness|hendrycksTest-astronomy|5_2023-08-22T11:29:59.333088.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-astronomy|5_2023-08-22T11:29:59.333088.parquet'
- config_name: harness_hendrycksTest_business_ethics_5
data_files:
- split: 2023_08_22T10_10_08.875186
path:
- '**/details_harness|hendrycksTest-business_ethics|5_2023-08-22T10:10:08.875186.parquet'
- split: 2023_08_22T11_29_59.333088
path:
- '**/details_harness|hendrycksTest-business_ethics|5_2023-08-22T11:29:59.333088.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-business_ethics|5_2023-08-22T11:29:59.333088.parquet'
- config_name: harness_hendrycksTest_clinical_knowledge_5
data_files:
- split: 2023_08_22T10_10_08.875186
path:
- '**/details_harness|hendrycksTest-clinical_knowledge|5_2023-08-22T10:10:08.875186.parquet'
- split: 2023_08_22T11_29_59.333088
path:
- '**/details_harness|hendrycksTest-clinical_knowledge|5_2023-08-22T11:29:59.333088.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-clinical_knowledge|5_2023-08-22T11:29:59.333088.parquet'
- config_name: harness_hendrycksTest_college_biology_5
data_files:
- split: 2023_08_22T10_10_08.875186
path:
- '**/details_harness|hendrycksTest-college_biology|5_2023-08-22T10:10:08.875186.parquet'
- split: 2023_08_22T11_29_59.333088
path:
- '**/details_harness|hendrycksTest-college_biology|5_2023-08-22T11:29:59.333088.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-college_biology|5_2023-08-22T11:29:59.333088.parquet'
- config_name: harness_hendrycksTest_college_chemistry_5
data_files:
- split: 2023_08_22T10_10_08.875186
path:
- '**/details_harness|hendrycksTest-college_chemistry|5_2023-08-22T10:10:08.875186.parquet'
- split: 2023_08_22T11_29_59.333088
path:
- '**/details_harness|hendrycksTest-college_chemistry|5_2023-08-22T11:29:59.333088.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-college_chemistry|5_2023-08-22T11:29:59.333088.parquet'
- config_name: harness_hendrycksTest_college_computer_science_5
data_files:
- split: 2023_08_22T10_10_08.875186
path:
- '**/details_harness|hendrycksTest-college_computer_science|5_2023-08-22T10:10:08.875186.parquet'
- split: 2023_08_22T11_29_59.333088
path:
- '**/details_harness|hendrycksTest-college_computer_science|5_2023-08-22T11:29:59.333088.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-college_computer_science|5_2023-08-22T11:29:59.333088.parquet'
- config_name: harness_hendrycksTest_college_mathematics_5
data_files:
- split: 2023_08_22T10_10_08.875186
path:
- '**/details_harness|hendrycksTest-college_mathematics|5_2023-08-22T10:10:08.875186.parquet'
- split: 2023_08_22T11_29_59.333088
path:
- '**/details_harness|hendrycksTest-college_mathematics|5_2023-08-22T11:29:59.333088.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-college_mathematics|5_2023-08-22T11:29:59.333088.parquet'
- config_name: harness_hendrycksTest_college_medicine_5
data_files:
- split: 2023_08_22T10_10_08.875186
path:
- '**/details_harness|hendrycksTest-college_medicine|5_2023-08-22T10:10:08.875186.parquet'
- split: 2023_08_22T11_29_59.333088
path:
- '**/details_harness|hendrycksTest-college_medicine|5_2023-08-22T11:29:59.333088.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-college_medicine|5_2023-08-22T11:29:59.333088.parquet'
- config_name: harness_hendrycksTest_college_physics_5
data_files:
- split: 2023_08_22T10_10_08.875186
path:
- '**/details_harness|hendrycksTest-college_physics|5_2023-08-22T10:10:08.875186.parquet'
- split: 2023_08_22T11_29_59.333088
path:
- '**/details_harness|hendrycksTest-college_physics|5_2023-08-22T11:29:59.333088.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-college_physics|5_2023-08-22T11:29:59.333088.parquet'
- config_name: harness_hendrycksTest_computer_security_5
data_files:
- split: 2023_08_22T10_10_08.875186
path:
- '**/details_harness|hendrycksTest-computer_security|5_2023-08-22T10:10:08.875186.parquet'
- split: 2023_08_22T11_29_59.333088
path:
- '**/details_harness|hendrycksTest-computer_security|5_2023-08-22T11:29:59.333088.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-computer_security|5_2023-08-22T11:29:59.333088.parquet'
- config_name: harness_hendrycksTest_conceptual_physics_5
data_files:
- split: 2023_08_22T10_10_08.875186
path:
- '**/details_harness|hendrycksTest-conceptual_physics|5_2023-08-22T10:10:08.875186.parquet'
- split: 2023_08_22T11_29_59.333088
path:
- '**/details_harness|hendrycksTest-conceptual_physics|5_2023-08-22T11:29:59.333088.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-conceptual_physics|5_2023-08-22T11:29:59.333088.parquet'
- config_name: harness_hendrycksTest_econometrics_5
data_files:
- split: 2023_08_22T10_10_08.875186
path:
- '**/details_harness|hendrycksTest-econometrics|5_2023-08-22T10:10:08.875186.parquet'
- split: 2023_08_22T11_29_59.333088
path:
- '**/details_harness|hendrycksTest-econometrics|5_2023-08-22T11:29:59.333088.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-econometrics|5_2023-08-22T11:29:59.333088.parquet'
- config_name: harness_hendrycksTest_electrical_engineering_5
data_files:
- split: 2023_08_22T10_10_08.875186
path:
- '**/details_harness|hendrycksTest-electrical_engineering|5_2023-08-22T10:10:08.875186.parquet'
- split: 2023_08_22T11_29_59.333088
path:
- '**/details_harness|hendrycksTest-electrical_engineering|5_2023-08-22T11:29:59.333088.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-electrical_engineering|5_2023-08-22T11:29:59.333088.parquet'
- config_name: harness_hendrycksTest_elementary_mathematics_5
data_files:
- split: 2023_08_22T10_10_08.875186
path:
- '**/details_harness|hendrycksTest-elementary_mathematics|5_2023-08-22T10:10:08.875186.parquet'
- split: 2023_08_22T11_29_59.333088
path:
- '**/details_harness|hendrycksTest-elementary_mathematics|5_2023-08-22T11:29:59.333088.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-elementary_mathematics|5_2023-08-22T11:29:59.333088.parquet'
- config_name: harness_hendrycksTest_formal_logic_5
data_files:
- split: 2023_08_22T10_10_08.875186
path:
- '**/details_harness|hendrycksTest-formal_logic|5_2023-08-22T10:10:08.875186.parquet'
- split: 2023_08_22T11_29_59.333088
path:
- '**/details_harness|hendrycksTest-formal_logic|5_2023-08-22T11:29:59.333088.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-formal_logic|5_2023-08-22T11:29:59.333088.parquet'
- config_name: harness_hendrycksTest_global_facts_5
data_files:
- split: 2023_08_22T10_10_08.875186
path:
- '**/details_harness|hendrycksTest-global_facts|5_2023-08-22T10:10:08.875186.parquet'
- split: 2023_08_22T11_29_59.333088
path:
- '**/details_harness|hendrycksTest-global_facts|5_2023-08-22T11:29:59.333088.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-global_facts|5_2023-08-22T11:29:59.333088.parquet'
- config_name: harness_hendrycksTest_high_school_biology_5
data_files:
- split: 2023_08_22T10_10_08.875186
path:
- '**/details_harness|hendrycksTest-high_school_biology|5_2023-08-22T10:10:08.875186.parquet'
- split: 2023_08_22T11_29_59.333088
path:
- '**/details_harness|hendrycksTest-high_school_biology|5_2023-08-22T11:29:59.333088.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-high_school_biology|5_2023-08-22T11:29:59.333088.parquet'
- config_name: harness_hendrycksTest_high_school_chemistry_5
data_files:
- split: 2023_08_22T10_10_08.875186
path:
- '**/details_harness|hendrycksTest-high_school_chemistry|5_2023-08-22T10:10:08.875186.parquet'
- split: 2023_08_22T11_29_59.333088
path:
- '**/details_harness|hendrycksTest-high_school_chemistry|5_2023-08-22T11:29:59.333088.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-high_school_chemistry|5_2023-08-22T11:29:59.333088.parquet'
- config_name: harness_hendrycksTest_high_school_computer_science_5
data_files:
- split: 2023_08_22T10_10_08.875186
path:
- '**/details_harness|hendrycksTest-high_school_computer_science|5_2023-08-22T10:10:08.875186.parquet'
- split: 2023_08_22T11_29_59.333088
path:
- '**/details_harness|hendrycksTest-high_school_computer_science|5_2023-08-22T11:29:59.333088.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-high_school_computer_science|5_2023-08-22T11:29:59.333088.parquet'
- config_name: harness_hendrycksTest_high_school_european_history_5
data_files:
- split: 2023_08_22T10_10_08.875186
path:
- '**/details_harness|hendrycksTest-high_school_european_history|5_2023-08-22T10:10:08.875186.parquet'
- split: 2023_08_22T11_29_59.333088
path:
- '**/details_harness|hendrycksTest-high_school_european_history|5_2023-08-22T11:29:59.333088.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-high_school_european_history|5_2023-08-22T11:29:59.333088.parquet'
- config_name: harness_hendrycksTest_high_school_geography_5
data_files:
- split: 2023_08_22T10_10_08.875186
path:
- '**/details_harness|hendrycksTest-high_school_geography|5_2023-08-22T10:10:08.875186.parquet'
- split: 2023_08_22T11_29_59.333088
path:
- '**/details_harness|hendrycksTest-high_school_geography|5_2023-08-22T11:29:59.333088.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-high_school_geography|5_2023-08-22T11:29:59.333088.parquet'
- config_name: harness_hendrycksTest_high_school_government_and_politics_5
data_files:
- split: 2023_08_22T10_10_08.875186
path:
- '**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-08-22T10:10:08.875186.parquet'
- split: 2023_08_22T11_29_59.333088
path:
- '**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-08-22T11:29:59.333088.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-08-22T11:29:59.333088.parquet'
- config_name: harness_hendrycksTest_high_school_macroeconomics_5
data_files:
- split: 2023_08_22T10_10_08.875186
path:
- '**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-08-22T10:10:08.875186.parquet'
- split: 2023_08_22T11_29_59.333088
path:
- '**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-08-22T11:29:59.333088.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-08-22T11:29:59.333088.parquet'
- config_name: harness_hendrycksTest_high_school_mathematics_5
data_files:
- split: 2023_08_22T10_10_08.875186
path:
- '**/details_harness|hendrycksTest-high_school_mathematics|5_2023-08-22T10:10:08.875186.parquet'
- split: 2023_08_22T11_29_59.333088
path:
- '**/details_harness|hendrycksTest-high_school_mathematics|5_2023-08-22T11:29:59.333088.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-high_school_mathematics|5_2023-08-22T11:29:59.333088.parquet'
- config_name: harness_hendrycksTest_high_school_microeconomics_5
data_files:
- split: 2023_08_22T10_10_08.875186
path:
- '**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-08-22T10:10:08.875186.parquet'
- split: 2023_08_22T11_29_59.333088
path:
- '**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-08-22T11:29:59.333088.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-08-22T11:29:59.333088.parquet'
- config_name: harness_hendrycksTest_high_school_physics_5
data_files:
- split: 2023_08_22T10_10_08.875186
path:
- '**/details_harness|hendrycksTest-high_school_physics|5_2023-08-22T10:10:08.875186.parquet'
- split: 2023_08_22T11_29_59.333088
path:
- '**/details_harness|hendrycksTest-high_school_physics|5_2023-08-22T11:29:59.333088.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-high_school_physics|5_2023-08-22T11:29:59.333088.parquet'
- config_name: harness_hendrycksTest_high_school_psychology_5
data_files:
- split: 2023_08_22T10_10_08.875186
path:
- '**/details_harness|hendrycksTest-high_school_psychology|5_2023-08-22T10:10:08.875186.parquet'
- split: 2023_08_22T11_29_59.333088
path:
- '**/details_harness|hendrycksTest-high_school_psychology|5_2023-08-22T11:29:59.333088.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-high_school_psychology|5_2023-08-22T11:29:59.333088.parquet'
- config_name: harness_hendrycksTest_high_school_statistics_5
data_files:
- split: 2023_08_22T10_10_08.875186
path:
- '**/details_harness|hendrycksTest-high_school_statistics|5_2023-08-22T10:10:08.875186.parquet'
- split: 2023_08_22T11_29_59.333088
path:
- '**/details_harness|hendrycksTest-high_school_statistics|5_2023-08-22T11:29:59.333088.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-high_school_statistics|5_2023-08-22T11:29:59.333088.parquet'
- config_name: harness_hendrycksTest_high_school_us_history_5
data_files:
- split: 2023_08_22T10_10_08.875186
path:
- '**/details_harness|hendrycksTest-high_school_us_history|5_2023-08-22T10:10:08.875186.parquet'
- split: 2023_08_22T11_29_59.333088
path:
- '**/details_harness|hendrycksTest-high_school_us_history|5_2023-08-22T11:29:59.333088.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-high_school_us_history|5_2023-08-22T11:29:59.333088.parquet'
- config_name: harness_hendrycksTest_high_school_world_history_5
data_files:
- split: 2023_08_22T10_10_08.875186
path:
- '**/details_harness|hendrycksTest-high_school_world_history|5_2023-08-22T10:10:08.875186.parquet'
- split: 2023_08_22T11_29_59.333088
path:
- '**/details_harness|hendrycksTest-high_school_world_history|5_2023-08-22T11:29:59.333088.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-high_school_world_history|5_2023-08-22T11:29:59.333088.parquet'
- config_name: harness_hendrycksTest_human_aging_5
data_files:
- split: 2023_08_22T10_10_08.875186
path:
- '**/details_harness|hendrycksTest-human_aging|5_2023-08-22T10:10:08.875186.parquet'
- split: 2023_08_22T11_29_59.333088
path:
- '**/details_harness|hendrycksTest-human_aging|5_2023-08-22T11:29:59.333088.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-human_aging|5_2023-08-22T11:29:59.333088.parquet'
- config_name: harness_hendrycksTest_human_sexuality_5
data_files:
- split: 2023_08_22T10_10_08.875186
path:
- '**/details_harness|hendrycksTest-human_sexuality|5_2023-08-22T10:10:08.875186.parquet'
- split: 2023_08_22T11_29_59.333088
path:
- '**/details_harness|hendrycksTest-human_sexuality|5_2023-08-22T11:29:59.333088.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-human_sexuality|5_2023-08-22T11:29:59.333088.parquet'
- config_name: harness_hendrycksTest_international_law_5
data_files:
- split: 2023_08_22T10_10_08.875186
path:
- '**/details_harness|hendrycksTest-international_law|5_2023-08-22T10:10:08.875186.parquet'
- split: 2023_08_22T11_29_59.333088
path:
- '**/details_harness|hendrycksTest-international_law|5_2023-08-22T11:29:59.333088.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-international_law|5_2023-08-22T11:29:59.333088.parquet'
- config_name: harness_hendrycksTest_jurisprudence_5
data_files:
- split: 2023_08_22T10_10_08.875186
path:
- '**/details_harness|hendrycksTest-jurisprudence|5_2023-08-22T10:10:08.875186.parquet'
- split: 2023_08_22T11_29_59.333088
path:
- '**/details_harness|hendrycksTest-jurisprudence|5_2023-08-22T11:29:59.333088.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-jurisprudence|5_2023-08-22T11:29:59.333088.parquet'
- config_name: harness_hendrycksTest_logical_fallacies_5
data_files:
- split: 2023_08_22T10_10_08.875186
path:
- '**/details_harness|hendrycksTest-logical_fallacies|5_2023-08-22T10:10:08.875186.parquet'
- split: 2023_08_22T11_29_59.333088
path:
- '**/details_harness|hendrycksTest-logical_fallacies|5_2023-08-22T11:29:59.333088.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-logical_fallacies|5_2023-08-22T11:29:59.333088.parquet'
- config_name: harness_hendrycksTest_machine_learning_5
data_files:
- split: 2023_08_22T10_10_08.875186
path:
- '**/details_harness|hendrycksTest-machine_learning|5_2023-08-22T10:10:08.875186.parquet'
- split: 2023_08_22T11_29_59.333088
path:
- '**/details_harness|hendrycksTest-machine_learning|5_2023-08-22T11:29:59.333088.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-machine_learning|5_2023-08-22T11:29:59.333088.parquet'
- config_name: harness_hendrycksTest_management_5
data_files:
- split: 2023_08_22T10_10_08.875186
path:
- '**/details_harness|hendrycksTest-management|5_2023-08-22T10:10:08.875186.parquet'
- split: 2023_08_22T11_29_59.333088
path:
- '**/details_harness|hendrycksTest-management|5_2023-08-22T11:29:59.333088.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-management|5_2023-08-22T11:29:59.333088.parquet'
- config_name: harness_hendrycksTest_marketing_5
data_files:
- split: 2023_08_22T10_10_08.875186
path:
- '**/details_harness|hendrycksTest-marketing|5_2023-08-22T10:10:08.875186.parquet'
- split: 2023_08_22T11_29_59.333088
path:
- '**/details_harness|hendrycksTest-marketing|5_2023-08-22T11:29:59.333088.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-marketing|5_2023-08-22T11:29:59.333088.parquet'
- config_name: harness_hendrycksTest_medical_genetics_5
data_files:
- split: 2023_08_22T10_10_08.875186
path:
- '**/details_harness|hendrycksTest-medical_genetics|5_2023-08-22T10:10:08.875186.parquet'
- split: 2023_08_22T11_29_59.333088
path:
- '**/details_harness|hendrycksTest-medical_genetics|5_2023-08-22T11:29:59.333088.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-medical_genetics|5_2023-08-22T11:29:59.333088.parquet'
- config_name: harness_hendrycksTest_miscellaneous_5
data_files:
- split: 2023_08_22T10_10_08.875186
path:
- '**/details_harness|hendrycksTest-miscellaneous|5_2023-08-22T10:10:08.875186.parquet'
- split: 2023_08_22T11_29_59.333088
path:
- '**/details_harness|hendrycksTest-miscellaneous|5_2023-08-22T11:29:59.333088.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-miscellaneous|5_2023-08-22T11:29:59.333088.parquet'
- config_name: harness_hendrycksTest_moral_disputes_5
data_files:
- split: 2023_08_22T10_10_08.875186
path:
- '**/details_harness|hendrycksTest-moral_disputes|5_2023-08-22T10:10:08.875186.parquet'
- split: 2023_08_22T11_29_59.333088
path:
- '**/details_harness|hendrycksTest-moral_disputes|5_2023-08-22T11:29:59.333088.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-moral_disputes|5_2023-08-22T11:29:59.333088.parquet'
- config_name: harness_hendrycksTest_moral_scenarios_5
data_files:
- split: 2023_08_22T10_10_08.875186
path:
- '**/details_harness|hendrycksTest-moral_scenarios|5_2023-08-22T10:10:08.875186.parquet'
- split: 2023_08_22T11_29_59.333088
path:
- '**/details_harness|hendrycksTest-moral_scenarios|5_2023-08-22T11:29:59.333088.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-moral_scenarios|5_2023-08-22T11:29:59.333088.parquet'
- config_name: harness_hendrycksTest_nutrition_5
data_files:
- split: 2023_08_22T10_10_08.875186
path:
- '**/details_harness|hendrycksTest-nutrition|5_2023-08-22T10:10:08.875186.parquet'
- split: 2023_08_22T11_29_59.333088
path:
- '**/details_harness|hendrycksTest-nutrition|5_2023-08-22T11:29:59.333088.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-nutrition|5_2023-08-22T11:29:59.333088.parquet'
- config_name: harness_hendrycksTest_philosophy_5
data_files:
- split: 2023_08_22T10_10_08.875186
path:
- '**/details_harness|hendrycksTest-philosophy|5_2023-08-22T10:10:08.875186.parquet'
- split: 2023_08_22T11_29_59.333088
path:
- '**/details_harness|hendrycksTest-philosophy|5_2023-08-22T11:29:59.333088.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-philosophy|5_2023-08-22T11:29:59.333088.parquet'
- config_name: harness_hendrycksTest_prehistory_5
data_files:
- split: 2023_08_22T10_10_08.875186
path:
- '**/details_harness|hendrycksTest-prehistory|5_2023-08-22T10:10:08.875186.parquet'
- split: 2023_08_22T11_29_59.333088
path:
- '**/details_harness|hendrycksTest-prehistory|5_2023-08-22T11:29:59.333088.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-prehistory|5_2023-08-22T11:29:59.333088.parquet'
- config_name: harness_hendrycksTest_professional_accounting_5
data_files:
- split: 2023_08_22T10_10_08.875186
path:
- '**/details_harness|hendrycksTest-professional_accounting|5_2023-08-22T10:10:08.875186.parquet'
- split: 2023_08_22T11_29_59.333088
path:
- '**/details_harness|hendrycksTest-professional_accounting|5_2023-08-22T11:29:59.333088.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-professional_accounting|5_2023-08-22T11:29:59.333088.parquet'
- config_name: harness_hendrycksTest_professional_law_5
data_files:
- split: 2023_08_22T10_10_08.875186
path:
- '**/details_harness|hendrycksTest-professional_law|5_2023-08-22T10:10:08.875186.parquet'
- split: 2023_08_22T11_29_59.333088
path:
- '**/details_harness|hendrycksTest-professional_law|5_2023-08-22T11:29:59.333088.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-professional_law|5_2023-08-22T11:29:59.333088.parquet'
- config_name: harness_hendrycksTest_professional_medicine_5
data_files:
- split: 2023_08_22T10_10_08.875186
path:
- '**/details_harness|hendrycksTest-professional_medicine|5_2023-08-22T10:10:08.875186.parquet'
- split: 2023_08_22T11_29_59.333088
path:
- '**/details_harness|hendrycksTest-professional_medicine|5_2023-08-22T11:29:59.333088.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-professional_medicine|5_2023-08-22T11:29:59.333088.parquet'
- config_name: harness_hendrycksTest_professional_psychology_5
data_files:
- split: 2023_08_22T10_10_08.875186
path:
- '**/details_harness|hendrycksTest-professional_psychology|5_2023-08-22T10:10:08.875186.parquet'
- split: 2023_08_22T11_29_59.333088
path:
- '**/details_harness|hendrycksTest-professional_psychology|5_2023-08-22T11:29:59.333088.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-professional_psychology|5_2023-08-22T11:29:59.333088.parquet'
- config_name: harness_hendrycksTest_public_relations_5
data_files:
- split: 2023_08_22T10_10_08.875186
path:
- '**/details_harness|hendrycksTest-public_relations|5_2023-08-22T10:10:08.875186.parquet'
- split: 2023_08_22T11_29_59.333088
path:
- '**/details_harness|hendrycksTest-public_relations|5_2023-08-22T11:29:59.333088.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-public_relations|5_2023-08-22T11:29:59.333088.parquet'
- config_name: harness_hendrycksTest_security_studies_5
data_files:
- split: 2023_08_22T10_10_08.875186
path:
- '**/details_harness|hendrycksTest-security_studies|5_2023-08-22T10:10:08.875186.parquet'
- split: 2023_08_22T11_29_59.333088
path:
- '**/details_harness|hendrycksTest-security_studies|5_2023-08-22T11:29:59.333088.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-security_studies|5_2023-08-22T11:29:59.333088.parquet'
- config_name: harness_hendrycksTest_sociology_5
data_files:
- split: 2023_08_22T10_10_08.875186
path:
- '**/details_harness|hendrycksTest-sociology|5_2023-08-22T10:10:08.875186.parquet'
- split: 2023_08_22T11_29_59.333088
path:
- '**/details_harness|hendrycksTest-sociology|5_2023-08-22T11:29:59.333088.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-sociology|5_2023-08-22T11:29:59.333088.parquet'
- config_name: harness_hendrycksTest_us_foreign_policy_5
data_files:
- split: 2023_08_22T10_10_08.875186
path:
- '**/details_harness|hendrycksTest-us_foreign_policy|5_2023-08-22T10:10:08.875186.parquet'
- split: 2023_08_22T11_29_59.333088
path:
- '**/details_harness|hendrycksTest-us_foreign_policy|5_2023-08-22T11:29:59.333088.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-us_foreign_policy|5_2023-08-22T11:29:59.333088.parquet'
- config_name: harness_hendrycksTest_virology_5
data_files:
- split: 2023_08_22T10_10_08.875186
path:
- '**/details_harness|hendrycksTest-virology|5_2023-08-22T10:10:08.875186.parquet'
- split: 2023_08_22T11_29_59.333088
path:
- '**/details_harness|hendrycksTest-virology|5_2023-08-22T11:29:59.333088.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-virology|5_2023-08-22T11:29:59.333088.parquet'
- config_name: harness_hendrycksTest_world_religions_5
data_files:
- split: 2023_08_22T10_10_08.875186
path:
- '**/details_harness|hendrycksTest-world_religions|5_2023-08-22T10:10:08.875186.parquet'
- split: 2023_08_22T11_29_59.333088
path:
- '**/details_harness|hendrycksTest-world_religions|5_2023-08-22T11:29:59.333088.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-world_religions|5_2023-08-22T11:29:59.333088.parquet'
- config_name: harness_truthfulqa_mc_0
data_files:
- split: 2023_08_22T10_10_08.875186
path:
- '**/details_harness|truthfulqa:mc|0_2023-08-22T10:10:08.875186.parquet'
- split: 2023_08_22T11_29_59.333088
path:
- '**/details_harness|truthfulqa:mc|0_2023-08-22T11:29:59.333088.parquet'
- split: latest
path:
- '**/details_harness|truthfulqa:mc|0_2023-08-22T11:29:59.333088.parquet'
- config_name: harness_winogrande_5
data_files:
- split: 2023_09_22T17_52_30.288263
path:
- '**/details_harness|winogrande|5_2023-09-22T17-52-30.288263.parquet'
- split: latest
path:
- '**/details_harness|winogrande|5_2023-09-22T17-52-30.288263.parquet'
- config_name: results
data_files:
- split: 2023_09_22T17_52_30.288263
path:
- results_2023-09-22T17-52-30.288263.parquet
- split: 2023_12_03T14_53_17.113107
path:
- results_2023-12-03T14-53-17.113107.parquet
- split: 2023_12_03T15_55_50.672449
path:
- results_2023-12-03T15-55-50.672449.parquet
- split: 2023_12_03T15_56_16.405841
path:
- results_2023-12-03T15-56-16.405841.parquet
- split: 2023_12_04T09_46_15.159375
path:
- results_2023-12-04T09-46-15.159375.parquet
- split: 2023_12_04T09_46_26.874047
path:
- results_2023-12-04T09-46-26.874047.parquet
- split: 2023_12_04T12_56_20.274289
path:
- results_2023-12-04T12-56-20.274289.parquet
- split: 2023_12_04T12_56_49.944014
path:
- results_2023-12-04T12-56-49.944014.parquet
- split: latest
path:
- results_2023-12-04T12-56-49.944014.parquet
---
# Dataset Card for Evaluation run of bigscience/bloomz-7b1
## Dataset Description
- **Homepage:**
- **Repository:** https://huggingface.co/bigscience/bloomz-7b1
- **Paper:**
- **Leaderboard:** https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard
- **Point of Contact:** clementine@hf.co
### Dataset Summary
Dataset automatically created during the evaluation run of model [bigscience/bloomz-7b1](https://huggingface.co/bigscience/bloomz-7b1) on the [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard).
The dataset is composed of 64 configuration, each one coresponding to one of the evaluated task.
The dataset has been created from 10 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is always pointing to the latest results.
An additional configuration "results" store all the aggregated results of the run (and is used to compute and display the aggregated metrics on the [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)).
To load the details from a run, you can for instance do the following:
```python
from datasets import load_dataset
data = load_dataset("open-llm-leaderboard/details_bigscience__bloomz-7b1",
"harness_gsm8k_5",
split="train")
```
## Latest results
These are the [latest results from run 2023-12-04T12:56:49.944014](https://huggingface.co/datasets/open-llm-leaderboard/details_bigscience__bloomz-7b1/blob/main/results_2023-12-04T12-56-49.944014.json)(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the "latest" split for each eval):
```python
{
"all": {
"acc": 0.000758150113722517,
"acc_stderr": 0.0007581501137225419
},
"harness|gsm8k|5": {
"acc": 0.000758150113722517,
"acc_stderr": 0.0007581501137225419
}
}
```
### Supported Tasks and Leaderboards
[More Information Needed]
### Languages
[More Information Needed]
## Dataset Structure
### Data Instances
[More Information Needed]
### Data Fields
[More Information Needed]
### Data Splits
[More Information Needed]
## Dataset Creation
### Curation Rationale
[More Information Needed]
### Source Data
#### Initial Data Collection and Normalization
[More Information Needed]
#### Who are the source language producers?
[More Information Needed]
### Annotations
#### Annotation process
[More Information Needed]
#### Who are the annotators?
[More Information Needed]
### Personal and Sensitive Information
[More Information Needed]
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
[More Information Needed]
### Licensing Information
[More Information Needed]
### Citation Information
[More Information Needed]
### Contributions
[More Information Needed]
原始信息汇总
数据集概述
数据集名称
- Evaluation run of bigscience/bloomz-7b1
数据集摘要
- 该数据集是在对模型 bigscience/bloomz-7b1 进行评估运行期间自动创建的。
- 数据集包含 64 个配置,每个配置对应一个评估任务。
- 数据集从 10 次运行中创建,每次运行可以在每个配置中找到特定的分割,分割名称使用运行的时间戳。
- "train" 分割始终指向最新的结果。
- 额外的配置 "results" 存储所有运行的聚合结果,用于计算和显示 Open LLM Leaderboard 上的聚合指标。
数据加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_bigscience__bloomz-7b1", "harness_gsm8k_5", split="train")
最新结果
- 这些是最新结果,来自 2023-12-04T12:56:49.944014 的运行(注意可能还有其他任务的结果,可以在结果和每个评估的 "latest" 分割中找到): python { "all": { "acc": 0.000758150113722517, "acc_stderr": 0.0007581501137225419 }, "harness|gsm8k|5": { "acc": 0.000758150113722517, "acc_stderr": 0.0007581501137225419 } }
配置详情
-
harness_arc_challenge_25
- 分割:2023_08_22T10_10_08.875186
- 路径:
**/details_harness|arc:challenge|25_2023-08-22T10:10:08.875186.parquet
- 路径:
- 分割:2023_08_22T11_29_59.333088
- 路径:
**/details_harness|arc:challenge|25_2023-08-22T11:29:59.333088.parquet
- 路径:
- 分割:latest
- 路径:
**/details_harness|arc:challenge|25_2023-08-22T11:29:59.333088.parquet
- 路径:
- 分割:2023_08_22T10_10_08.875186
-
harness_drop_3
- 分割:2023_09_22T17_52_30.288263
- 路径:
**/details_harness|drop|3_2023-09-22T17-52-30.288263.parquet
- 路径:
- 分割:latest
- 路径:
**/details_harness|drop|3_2023-09-22T17-52-30.288263.parquet
- 路径:
- 分割:2023_09_22T17_52_30.288263
-
harness_gsm8k_5
- 分割:2023_09_22T17_52_30.288263
- 路径:
**/details_harness|gsm8k|5_2023-09-22T17-52-30.288263.parquet
- 路径:
- 分割:2023_12_03T14_53_17.113107
- 路径:
**/details_harness|gsm8k|5_2023-12-03T14-53-17.113107.parquet
- 路径:
- 分割:2023_12_03T15_55_50.672449
- 路径:
**/details_harness|gsm8k|5_2023-12-03T15-55-50.672449.parquet
- 路径:
- 分割:2023_12_03T15_56_16.405841
- 路径:
**/details_harness|gsm8k|5_2023-12-03T15-56-16.405841.parquet
- 路径:
- 分割:2023_12_04T09_46_15.159375
- 路径:
**/details_harness|gsm8k|5_2023-12-04T09-46-15.159375.parquet
- 路径:
- 分割:2023_12_04T09_46_26.874047
- 路径:
**/details_harness|gsm8k|5_2023-12-04T09-46-26.874047.parquet
- 路径:
- 分割:2023_12_04T12_56_20.274289
- 路径:
**/details_harness|gsm8k|5_2023-12-04T12-56-20.274289.parquet
- 路径:
- 分割:2023_12_04T12_56_49.944014
- 路径:
**/details_harness|gsm8k|5_2023-12-04T12-56-49.944014.parquet
- 路径:
- 分割:latest
- 路径:
**/details_harness|gsm8k|5_2023-12-04T12-56-49.944014.parquet
- 路径:
- 分割:2023_09_22T17_52_30.288263
-
harness_hellaswag_10
- 分割:2023_08_22T10_10_08.875186
- 路径:
**/details_harness|hellaswag|10_2023-08-22T10:10:08.875186.parquet
- 路径:
- 分割:2023_08_22T11_29_59.333088
- 路径:
**/details_harness|hellaswag|10_2023-08-22T11:29:59.333088.parquet
- 路径:
- 分割:latest
- 路径:
**/details_harness|hellaswag|10_2023-08-22T11:29:59.333088.parquet
- 路径:
- 分割:2023_08_22T10_10_08.875186
-
harness_hendrycksTest_5
- 分割:2023_08_22T10_10_08.875186
- 路径:
**/details_harness|hendrycksTest-abstract_algebra|5_2023-08-22T10:10:08.875186.parquet - 路径:
**/details_harness|hendrycksTest-anatomy|5_2023-08-22T10:10:08.875186.parquet - 路径:
**/details_harness|hendrycksTest-astronomy|5_2023-08-22T10:10:08.875186.parquet - 路径:
**/details_harness|hendrycksTest-business_ethics|5_2023-08-22T10:10:08.875186.parquet - 路径:
**/details_harness|hendrycksTest-clinical_knowledge|5_2023-08-22T10:10:08.875186.parquet - 路径:
**/details_harness|hendrycksTest-college_biology|5_2023-08-22T10:10:08.875186.parquet - 路径:
**/details_harness|hendrycksTest-college_chemistry|5_2023-08-22T10:10:08.875186.parquet - 路径:
**/details_harness|hendrycksTest-college_computer_science|5_2023-08-22T10:10:08.875186.parquet - 路径:
**/details_harness|hendrycksTest-college_mathematics|5_2023-08-22T10:10:08.875186.parquet - 路径:
**/details_harness|hendrycksTest-college_medicine|5_2023-08-22T10:10:08.875186.parquet - 路径:
**/details_harness|hendrycksTest-college_physics|5_2023-08-22T10:10:08.875186.parquet - 路径:
**/details_harness|hendrycksTest-computer_security|5_2023-08-22T10:10:08.875186.parquet - 路径:
**/details_harness|hendrycksTest-conceptual_physics|5_2023-08-22T10:10:08.875186.parquet - 路径:
**/details_harness|hendrycksTest-econometrics|5_2023-08-22T10:10:08.875186.parquet - 路径:
**/details_harness|hendrycksTest-electrical_engineering|5_2023-08-22T10:10:08.875186.parquet - 路径:
**/details_harness|hendrycksTest-elementary_mathematics|5_2023-08-22T10:10:08.875186.parquet - 路径:
**/details_harness|hendrycksTest-formal_logic|5_2023-08-22T10:10:08.875186.parquet - 路径:
**/details_harness|hendrycksTest-global_facts|5_2023-08-22T10:10:08.875186.parquet - 路径:
**/details_harness|hendrycksTest-high_school_biology|5_2023-08-22T10:10:08.875186.parquet - 路径:
**/details_harness|hendrycksTest-high_school_chemistry|5_2023-08-22T10:10:08.875186.parquet - 路径:
**/details_harness|hendrycksTest-high_school_computer_science|5_2023-08-22T10:10:08.875186.parquet - 路径:
**/details_harness|hendrycksTest-high_school_european_history|5_2023-08-22T10:10:08.875186.parquet - 路径:
**/details_harness|hendrycksTest-high_school_geography|5_2023-08-22T10:10:08.875186.parquet - 路径:
**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-08-22T10:10:08.875186.parquet - 路径:
**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-08-22T10:10:08.875186.parquet - 路径:
**/details_harness|hendrycksTest-high_school_mathematics|5_2023-08-22T10:10:08.875186.parquet - 路径:
**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-08-22T10:10:08.875186.parquet - 路径:
**/details_harness|hendrycksTest-high_school_physics|5_2023-08-22T10:10:08.875186.parquet - 路径:
**/details_harness|hendrycksTest-high_school_psychology|5_2023-08-22T10:10:08.875186.parquet - 路径:
**/details_harness|hendrycksTest-high_school_statistics|5_2023-08-22T10:10:08.875186.parquet - 路径:
**/details_harness|hendrycksTest-high_school_us_history|5_2023-08-22T10:10:08.875186.parquet - 路径:
**/details_harness|hendrycksTest-high_school_world_history|5_2023-08-22T10:10:08.875186.parquet - 路径:
**/details_harness|hendrycksTest-human_aging|5_2023-08-22T10:10:08.875186.parquet - 路径:
**/details_harness|hendrycksTest-human_sexuality|5_2023-08-22T10:10:08.875186.parquet - 路径:
**/details_harness|hendrycksTest-international_law|5_2023-08-22T10:10:08.875186.parquet - 路径:
**/details_harness|hendrycksTest-jurisprudence|5_2023-08-22T10:10:08.875186.parquet - 路径:
**/details_harness|hendrycksTest-logical_fallacies|5_2023-08-22T10:10:08.875186.parquet - 路径:
**/details_harness|hendrycksTest-machine_learning|5_2023-08-22T10:10:08.875186.parquet - 路径:
**/details_harness|hendrycksTest-management|5_2023-08-22T10:10:08.875186.parquet - 路径:`**/details_harness|hendrycksTest-marketing|5_2023-08-22T10:10:08.875186.parquet
- 路径:
- 分割:2023_08_22T10_10_08.875186
搜集汇总
数据集介绍

构建方式
在大型语言模型评估领域,Open LLM Leaderboard为模型性能的标准化评测提供了重要基准。该数据集是围绕bigscience/bloomz-7b1模型在Leaderboard上的评估过程自动生成的,其构建方式颇具匠心。数据集由64个配置组成,每个配置对应一项被评估的具体任务,覆盖了从ARC挑战到GSM8K数学推理等多样化的评测维度。数据来源于10次独立的评估运行,每次运行的结果均以时间戳作为分割标识,存储于对应配置中。特别地,每个配置下的'train'分割始终指向最新一次的评估结果,而一个名为'results'的附加配置则汇总了所有运行的聚合指标,为计算和展示Leaderboard上的综合得分提供了数据基础。
特点
该数据集的核心特点在于其精细化的结构设计与历史追溯能力。64个配置的划分使得研究者可以针对特定任务深入分析模型表现,而多运行结果的分割存储则完整保留了评估过程的时序信息,支持对模型性能变化趋势的追踪。每个配置下包含多个以时间戳命名的分割,如'2023_12_04T12_56_49.944014',确保了每次评估的独立性与可复现性。此外,'latest'分割的自动指向机制简化了用户获取最新结果的操作,而'results'配置的聚合特性则为宏观性能评估提供了便捷入口。这种设计兼顾了微观任务分析与宏观性能概览的双重需求。
使用方法
使用该数据集时,研究者可通过HuggingFace的datasets库灵活加载所需信息。例如,欲获取GSM8K任务在最新一次运行中的详细评估数据,可执行'load_dataset("open-llm-leaderboard/details_bigscience__bloomz-7b1", "harness_gsm8k_5", split="train")'。通过指定不同的配置名称(如'harness_arc_challenge_25')和分割标识(如特定时间戳),用户可以精准定位到任意任务在任意运行下的评估细节。对于需要整体性能概览的场景,加载'results'配置即可获得所有任务的聚合指标。这种灵活的加载方式使得数据集既适用于细粒度的模型行为分析,也适用于跨任务的性能比较研究。
背景与挑战
背景概述
随着大语言模型(LLMs)的迅猛发展,如何系统、公平地评估其多任务泛化能力成为自然语言处理领域的核心议题。在此背景下,Hugging Face团队于2023年推出了Open LLM Leaderboard,旨在为社区提供一个标准化、透明的模型性能比较平台。该数据集作为评测流程的副产品,专门记录了bigscience/bloomz-7b1模型在多项基准任务上的详细运行结果。bloomz-7b1是由BigScience项目研发的多语言指令微调模型,其参数规模达7.1B,旨在探索跨语言与跨任务的泛化边界。该数据集由Clementine Fourrier等人维护,通过自动化的评测流水线生成,覆盖了从常识推理(如ARC-Challenge)到数学问题求解(如GSM8K)的数十个子任务。其发布不仅为研究人员提供了细粒度的模型行为分析依据,更推动了LLM评测从单一指标向多维性能剖面的范式转变,对理解模型在不同认知难度任务上的表现差异具有重要参考价值。
当前挑战
该数据集所承载的评测体系面临多重挑战。在领域问题层面,尽管涵盖了ARC、HellaSwag、MMLU等经典基准,但现有任务仍难以全面度量模型在长文本理解、多轮对话、事实性校验及鲁棒性等维度的真实能力,存在评测维度碎片化与生态位重叠的问题。在构建过程中,数据集通过多次独立运行(如GSM8K任务记录了8次不同时间戳的评测结果)来捕捉模型性能的波动性,但评测环境(如硬件、库版本)的细微差异可能导致结果不可复现,且不同任务间的难度标定缺乏统一量纲,使得跨任务比较面临统计偏差。此外,数据集的存储格式(Parquet)与分片策略虽便于程序化加载,却对非技术用户构成访问壁垒,限制了评测数据在更广泛社区中的二次利用与深入分析。
常用场景
经典使用场景
该数据集专为评估大语言模型(LLM)在多样化自然语言理解与推理任务上的表现而设计,是Open LLM Leaderboard生态中的核心组件。它汇集了bigscience/bloomz-7b1模型在64个评测配置下的逐次运行细节,涵盖ARC挑战、GSM8K数学推理、HellaSwag常识推理、MMLU多学科知识等经典基准。研究者可通过加载特定任务配置(如harness_gsm8k_5)获取模型在每轮评估中的细粒度得分与误差统计,从而深入剖析模型在不同能力维度上的优劣,为模型迭代与优化提供精准的量化依据。
实际应用
在实际应用层面,该数据集为工业界部署大语言模型前的性能评估与风险控制提供了关键参考。例如,在构建对话系统或教育辅助工具时,开发者可依据bloomz-7b1在GSM8K上的低准确率(约0.076%)判断其在数学推理场景中的局限性,从而避免将该模型直接用于需要精确计算的领域。同时,通过分析HellaSwag或MMLU等配置的结果,企业能够筛选出在常识理解与多学科知识上表现稳健的模型版本,用于客服、知识问答等实际场景,从而降低部署后出现荒谬回答的风险。
衍生相关工作
该数据集作为Open LLM Leaderboard的标准化评测产物,直接衍生并支撑了多项关于大语言模型能力评估与对比的经典工作。例如,基于此数据集提供的细粒度结果,研究者得以构建模型表现的可视化分析工具,并催生了关于模型在零样本与少样本场景下泛化能力的系统性研究。此外,该数据集中的GSM8K与MMLU配置常被用于验证新提出的推理增强方法或知识注入技术的有效性,成为衡量模型是否达到当前最优水平的基准参照。其结构化存储方式也启发了后续类似评测数据集的构建范式,推动了LLM评测领域的规范化与科学化进程。
以上内容由遇见数据集搜集并总结生成



