five

open-llm-leaderboard/details_microsoft__DialoGPT-small

收藏
Hugging Face2023-12-03 更新2024-03-04 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard/details_microsoft__DialoGPT-small
下载链接
链接失效反馈
官方服务:
资源简介:
--- pretty_name: Evaluation run of microsoft/DialoGPT-small dataset_summary: "Dataset automatically created during the evaluation run of model\ \ [microsoft/DialoGPT-small](https://huggingface.co/microsoft/DialoGPT-small) 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 3 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_microsoft__DialoGPT-small\"\ ,\n\t\"harness_gsm8k_5\",\n\tsplit=\"train\")\n```\n\n## Latest results\n\nThese\ \ are the [latest results from run 2023-12-03T18:22:26.346357](https://huggingface.co/datasets/open-llm-leaderboard/details_microsoft__DialoGPT-small/blob/main/results_2023-12-03T18-22-26.346357.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\": 0.0,\n \"\ acc_stderr\": 0.0\n },\n \"harness|gsm8k|5\": {\n \"acc\": 0.0,\n \ \ \"acc_stderr\": 0.0\n }\n}\n```" repo_url: https://huggingface.co/microsoft/DialoGPT-small 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_07_19T18_58_31.382707 path: - '**/details_harness|arc:challenge|25_2023-07-19T18:58:31.382707.parquet' - split: latest path: - '**/details_harness|arc:challenge|25_2023-07-19T18:58:31.382707.parquet' - config_name: harness_drop_3 data_files: - split: 2023_10_17T19_54_07.074277 path: - '**/details_harness|drop|3_2023-10-17T19-54-07.074277.parquet' - split: latest path: - '**/details_harness|drop|3_2023-10-17T19-54-07.074277.parquet' - config_name: harness_gsm8k_5 data_files: - split: 2023_10_17T19_54_07.074277 path: - '**/details_harness|gsm8k|5_2023-10-17T19-54-07.074277.parquet' - split: 2023_12_03T18_22_26.346357 path: - '**/details_harness|gsm8k|5_2023-12-03T18-22-26.346357.parquet' - split: latest path: - '**/details_harness|gsm8k|5_2023-12-03T18-22-26.346357.parquet' - config_name: harness_hellaswag_10 data_files: - split: 2023_07_19T18_58_31.382707 path: - '**/details_harness|hellaswag|10_2023-07-19T18:58:31.382707.parquet' - split: latest path: - '**/details_harness|hellaswag|10_2023-07-19T18:58:31.382707.parquet' - config_name: harness_hendrycksTest_5 data_files: - split: 2023_07_19T18_58_31.382707 path: - '**/details_harness|hendrycksTest-abstract_algebra|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-anatomy|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-astronomy|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-business_ethics|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-clinical_knowledge|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-college_biology|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-college_chemistry|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-college_computer_science|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-college_mathematics|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-college_medicine|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-college_physics|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-computer_security|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-conceptual_physics|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-econometrics|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-electrical_engineering|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-elementary_mathematics|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-formal_logic|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-global_facts|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-high_school_biology|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-high_school_chemistry|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-high_school_computer_science|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-high_school_european_history|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-high_school_geography|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-high_school_mathematics|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-high_school_physics|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-high_school_psychology|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-high_school_statistics|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-high_school_us_history|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-high_school_world_history|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-human_aging|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-human_sexuality|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-international_law|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-jurisprudence|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-logical_fallacies|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-machine_learning|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-management|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-marketing|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-medical_genetics|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-miscellaneous|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-moral_disputes|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-moral_scenarios|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-nutrition|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-philosophy|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-prehistory|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-professional_accounting|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-professional_law|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-professional_medicine|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-professional_psychology|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-public_relations|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-security_studies|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-sociology|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-us_foreign_policy|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-virology|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-world_religions|5_2023-07-19T18:58:31.382707.parquet' - split: latest path: - '**/details_harness|hendrycksTest-abstract_algebra|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-anatomy|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-astronomy|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-business_ethics|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-clinical_knowledge|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-college_biology|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-college_chemistry|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-college_computer_science|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-college_mathematics|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-college_medicine|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-college_physics|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-computer_security|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-conceptual_physics|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-econometrics|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-electrical_engineering|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-elementary_mathematics|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-formal_logic|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-global_facts|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-high_school_biology|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-high_school_chemistry|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-high_school_computer_science|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-high_school_european_history|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-high_school_geography|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-high_school_mathematics|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-high_school_physics|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-high_school_psychology|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-high_school_statistics|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-high_school_us_history|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-high_school_world_history|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-human_aging|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-human_sexuality|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-international_law|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-jurisprudence|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-logical_fallacies|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-machine_learning|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-management|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-marketing|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-medical_genetics|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-miscellaneous|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-moral_disputes|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-moral_scenarios|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-nutrition|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-philosophy|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-prehistory|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-professional_accounting|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-professional_law|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-professional_medicine|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-professional_psychology|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-public_relations|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-security_studies|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-sociology|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-us_foreign_policy|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-virology|5_2023-07-19T18:58:31.382707.parquet' - '**/details_harness|hendrycksTest-world_religions|5_2023-07-19T18:58:31.382707.parquet' - config_name: harness_hendrycksTest_abstract_algebra_5 data_files: - split: 2023_07_19T18_58_31.382707 path: - '**/details_harness|hendrycksTest-abstract_algebra|5_2023-07-19T18:58:31.382707.parquet' - split: latest path: - '**/details_harness|hendrycksTest-abstract_algebra|5_2023-07-19T18:58:31.382707.parquet' - config_name: harness_hendrycksTest_anatomy_5 data_files: - split: 2023_07_19T18_58_31.382707 path: - '**/details_harness|hendrycksTest-anatomy|5_2023-07-19T18:58:31.382707.parquet' - split: latest path: - '**/details_harness|hendrycksTest-anatomy|5_2023-07-19T18:58:31.382707.parquet' - config_name: harness_hendrycksTest_astronomy_5 data_files: - split: 2023_07_19T18_58_31.382707 path: - '**/details_harness|hendrycksTest-astronomy|5_2023-07-19T18:58:31.382707.parquet' - split: latest path: - '**/details_harness|hendrycksTest-astronomy|5_2023-07-19T18:58:31.382707.parquet' - config_name: harness_hendrycksTest_business_ethics_5 data_files: - split: 2023_07_19T18_58_31.382707 path: - '**/details_harness|hendrycksTest-business_ethics|5_2023-07-19T18:58:31.382707.parquet' - split: latest path: - '**/details_harness|hendrycksTest-business_ethics|5_2023-07-19T18:58:31.382707.parquet' - config_name: harness_hendrycksTest_clinical_knowledge_5 data_files: - split: 2023_07_19T18_58_31.382707 path: - '**/details_harness|hendrycksTest-clinical_knowledge|5_2023-07-19T18:58:31.382707.parquet' - split: latest path: - '**/details_harness|hendrycksTest-clinical_knowledge|5_2023-07-19T18:58:31.382707.parquet' - config_name: harness_hendrycksTest_college_biology_5 data_files: - split: 2023_07_19T18_58_31.382707 path: - '**/details_harness|hendrycksTest-college_biology|5_2023-07-19T18:58:31.382707.parquet' - split: latest path: - '**/details_harness|hendrycksTest-college_biology|5_2023-07-19T18:58:31.382707.parquet' - config_name: harness_hendrycksTest_college_chemistry_5 data_files: - split: 2023_07_19T18_58_31.382707 path: - '**/details_harness|hendrycksTest-college_chemistry|5_2023-07-19T18:58:31.382707.parquet' - split: latest path: - '**/details_harness|hendrycksTest-college_chemistry|5_2023-07-19T18:58:31.382707.parquet' - config_name: harness_hendrycksTest_college_computer_science_5 data_files: - split: 2023_07_19T18_58_31.382707 path: - '**/details_harness|hendrycksTest-college_computer_science|5_2023-07-19T18:58:31.382707.parquet' - split: latest path: - '**/details_harness|hendrycksTest-college_computer_science|5_2023-07-19T18:58:31.382707.parquet' - config_name: harness_hendrycksTest_college_mathematics_5 data_files: - split: 2023_07_19T18_58_31.382707 path: - '**/details_harness|hendrycksTest-college_mathematics|5_2023-07-19T18:58:31.382707.parquet' - split: latest path: - '**/details_harness|hendrycksTest-college_mathematics|5_2023-07-19T18:58:31.382707.parquet' - config_name: harness_hendrycksTest_college_medicine_5 data_files: - split: 2023_07_19T18_58_31.382707 path: - '**/details_harness|hendrycksTest-college_medicine|5_2023-07-19T18:58:31.382707.parquet' - split: latest path: - '**/details_harness|hendrycksTest-college_medicine|5_2023-07-19T18:58:31.382707.parquet' - config_name: harness_hendrycksTest_college_physics_5 data_files: - split: 2023_07_19T18_58_31.382707 path: - '**/details_harness|hendrycksTest-college_physics|5_2023-07-19T18:58:31.382707.parquet' - split: latest path: - '**/details_harness|hendrycksTest-college_physics|5_2023-07-19T18:58:31.382707.parquet' - config_name: harness_hendrycksTest_computer_security_5 data_files: - split: 2023_07_19T18_58_31.382707 path: - '**/details_harness|hendrycksTest-computer_security|5_2023-07-19T18:58:31.382707.parquet' - split: latest path: - '**/details_harness|hendrycksTest-computer_security|5_2023-07-19T18:58:31.382707.parquet' - config_name: harness_hendrycksTest_conceptual_physics_5 data_files: - split: 2023_07_19T18_58_31.382707 path: - '**/details_harness|hendrycksTest-conceptual_physics|5_2023-07-19T18:58:31.382707.parquet' - split: latest path: - '**/details_harness|hendrycksTest-conceptual_physics|5_2023-07-19T18:58:31.382707.parquet' - config_name: harness_hendrycksTest_econometrics_5 data_files: - split: 2023_07_19T18_58_31.382707 path: - '**/details_harness|hendrycksTest-econometrics|5_2023-07-19T18:58:31.382707.parquet' - split: latest path: - '**/details_harness|hendrycksTest-econometrics|5_2023-07-19T18:58:31.382707.parquet' - config_name: harness_hendrycksTest_electrical_engineering_5 data_files: - split: 2023_07_19T18_58_31.382707 path: - '**/details_harness|hendrycksTest-electrical_engineering|5_2023-07-19T18:58:31.382707.parquet' - split: latest path: - '**/details_harness|hendrycksTest-electrical_engineering|5_2023-07-19T18:58:31.382707.parquet' - config_name: harness_hendrycksTest_elementary_mathematics_5 data_files: - split: 2023_07_19T18_58_31.382707 path: - '**/details_harness|hendrycksTest-elementary_mathematics|5_2023-07-19T18:58:31.382707.parquet' - split: latest path: - '**/details_harness|hendrycksTest-elementary_mathematics|5_2023-07-19T18:58:31.382707.parquet' - config_name: harness_hendrycksTest_formal_logic_5 data_files: - split: 2023_07_19T18_58_31.382707 path: - '**/details_harness|hendrycksTest-formal_logic|5_2023-07-19T18:58:31.382707.parquet' - split: latest path: - '**/details_harness|hendrycksTest-formal_logic|5_2023-07-19T18:58:31.382707.parquet' - config_name: harness_hendrycksTest_global_facts_5 data_files: - split: 2023_07_19T18_58_31.382707 path: - '**/details_harness|hendrycksTest-global_facts|5_2023-07-19T18:58:31.382707.parquet' - split: latest path: - '**/details_harness|hendrycksTest-global_facts|5_2023-07-19T18:58:31.382707.parquet' - config_name: harness_hendrycksTest_high_school_biology_5 data_files: - split: 2023_07_19T18_58_31.382707 path: - '**/details_harness|hendrycksTest-high_school_biology|5_2023-07-19T18:58:31.382707.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_biology|5_2023-07-19T18:58:31.382707.parquet' - config_name: harness_hendrycksTest_high_school_chemistry_5 data_files: - split: 2023_07_19T18_58_31.382707 path: - '**/details_harness|hendrycksTest-high_school_chemistry|5_2023-07-19T18:58:31.382707.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_chemistry|5_2023-07-19T18:58:31.382707.parquet' - config_name: harness_hendrycksTest_high_school_computer_science_5 data_files: - split: 2023_07_19T18_58_31.382707 path: - '**/details_harness|hendrycksTest-high_school_computer_science|5_2023-07-19T18:58:31.382707.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_computer_science|5_2023-07-19T18:58:31.382707.parquet' - config_name: harness_hendrycksTest_high_school_european_history_5 data_files: - split: 2023_07_19T18_58_31.382707 path: - '**/details_harness|hendrycksTest-high_school_european_history|5_2023-07-19T18:58:31.382707.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_european_history|5_2023-07-19T18:58:31.382707.parquet' - config_name: harness_hendrycksTest_high_school_geography_5 data_files: - split: 2023_07_19T18_58_31.382707 path: - '**/details_harness|hendrycksTest-high_school_geography|5_2023-07-19T18:58:31.382707.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_geography|5_2023-07-19T18:58:31.382707.parquet' - config_name: harness_hendrycksTest_high_school_government_and_politics_5 data_files: - split: 2023_07_19T18_58_31.382707 path: - '**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-07-19T18:58:31.382707.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-07-19T18:58:31.382707.parquet' - config_name: harness_hendrycksTest_high_school_macroeconomics_5 data_files: - split: 2023_07_19T18_58_31.382707 path: - '**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-07-19T18:58:31.382707.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-07-19T18:58:31.382707.parquet' - config_name: harness_hendrycksTest_high_school_mathematics_5 data_files: - split: 2023_07_19T18_58_31.382707 path: - '**/details_harness|hendrycksTest-high_school_mathematics|5_2023-07-19T18:58:31.382707.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_mathematics|5_2023-07-19T18:58:31.382707.parquet' - config_name: harness_hendrycksTest_high_school_microeconomics_5 data_files: - split: 2023_07_19T18_58_31.382707 path: - '**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-07-19T18:58:31.382707.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-07-19T18:58:31.382707.parquet' - config_name: harness_hendrycksTest_high_school_physics_5 data_files: - split: 2023_07_19T18_58_31.382707 path: - '**/details_harness|hendrycksTest-high_school_physics|5_2023-07-19T18:58:31.382707.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_physics|5_2023-07-19T18:58:31.382707.parquet' - config_name: harness_hendrycksTest_high_school_psychology_5 data_files: - split: 2023_07_19T18_58_31.382707 path: - '**/details_harness|hendrycksTest-high_school_psychology|5_2023-07-19T18:58:31.382707.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_psychology|5_2023-07-19T18:58:31.382707.parquet' - config_name: harness_hendrycksTest_high_school_statistics_5 data_files: - split: 2023_07_19T18_58_31.382707 path: - '**/details_harness|hendrycksTest-high_school_statistics|5_2023-07-19T18:58:31.382707.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_statistics|5_2023-07-19T18:58:31.382707.parquet' - config_name: harness_hendrycksTest_high_school_us_history_5 data_files: - split: 2023_07_19T18_58_31.382707 path: - '**/details_harness|hendrycksTest-high_school_us_history|5_2023-07-19T18:58:31.382707.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_us_history|5_2023-07-19T18:58:31.382707.parquet' - config_name: harness_hendrycksTest_high_school_world_history_5 data_files: - split: 2023_07_19T18_58_31.382707 path: - '**/details_harness|hendrycksTest-high_school_world_history|5_2023-07-19T18:58:31.382707.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_world_history|5_2023-07-19T18:58:31.382707.parquet' - config_name: harness_hendrycksTest_human_aging_5 data_files: - split: 2023_07_19T18_58_31.382707 path: - '**/details_harness|hendrycksTest-human_aging|5_2023-07-19T18:58:31.382707.parquet' - split: latest path: - '**/details_harness|hendrycksTest-human_aging|5_2023-07-19T18:58:31.382707.parquet' - config_name: harness_hendrycksTest_human_sexuality_5 data_files: - split: 2023_07_19T18_58_31.382707 path: - '**/details_harness|hendrycksTest-human_sexuality|5_2023-07-19T18:58:31.382707.parquet' - split: latest path: - '**/details_harness|hendrycksTest-human_sexuality|5_2023-07-19T18:58:31.382707.parquet' - config_name: harness_hendrycksTest_international_law_5 data_files: - split: 2023_07_19T18_58_31.382707 path: - '**/details_harness|hendrycksTest-international_law|5_2023-07-19T18:58:31.382707.parquet' - split: latest path: - '**/details_harness|hendrycksTest-international_law|5_2023-07-19T18:58:31.382707.parquet' - config_name: harness_hendrycksTest_jurisprudence_5 data_files: - split: 2023_07_19T18_58_31.382707 path: - '**/details_harness|hendrycksTest-jurisprudence|5_2023-07-19T18:58:31.382707.parquet' - split: latest path: - '**/details_harness|hendrycksTest-jurisprudence|5_2023-07-19T18:58:31.382707.parquet' - config_name: harness_hendrycksTest_logical_fallacies_5 data_files: - split: 2023_07_19T18_58_31.382707 path: - '**/details_harness|hendrycksTest-logical_fallacies|5_2023-07-19T18:58:31.382707.parquet' - split: latest path: - '**/details_harness|hendrycksTest-logical_fallacies|5_2023-07-19T18:58:31.382707.parquet' - config_name: harness_hendrycksTest_machine_learning_5 data_files: - split: 2023_07_19T18_58_31.382707 path: - '**/details_harness|hendrycksTest-machine_learning|5_2023-07-19T18:58:31.382707.parquet' - split: latest path: - '**/details_harness|hendrycksTest-machine_learning|5_2023-07-19T18:58:31.382707.parquet' - config_name: harness_hendrycksTest_management_5 data_files: - split: 2023_07_19T18_58_31.382707 path: - '**/details_harness|hendrycksTest-management|5_2023-07-19T18:58:31.382707.parquet' - split: latest path: - '**/details_harness|hendrycksTest-management|5_2023-07-19T18:58:31.382707.parquet' - config_name: harness_hendrycksTest_marketing_5 data_files: - split: 2023_07_19T18_58_31.382707 path: - '**/details_harness|hendrycksTest-marketing|5_2023-07-19T18:58:31.382707.parquet' - split: latest path: - '**/details_harness|hendrycksTest-marketing|5_2023-07-19T18:58:31.382707.parquet' - config_name: harness_hendrycksTest_medical_genetics_5 data_files: - split: 2023_07_19T18_58_31.382707 path: - '**/details_harness|hendrycksTest-medical_genetics|5_2023-07-19T18:58:31.382707.parquet' - split: latest path: - '**/details_harness|hendrycksTest-medical_genetics|5_2023-07-19T18:58:31.382707.parquet' - config_name: harness_hendrycksTest_miscellaneous_5 data_files: - split: 2023_07_19T18_58_31.382707 path: - '**/details_harness|hendrycksTest-miscellaneous|5_2023-07-19T18:58:31.382707.parquet' - split: latest path: - '**/details_harness|hendrycksTest-miscellaneous|5_2023-07-19T18:58:31.382707.parquet' - config_name: harness_hendrycksTest_moral_disputes_5 data_files: - split: 2023_07_19T18_58_31.382707 path: - '**/details_harness|hendrycksTest-moral_disputes|5_2023-07-19T18:58:31.382707.parquet' - split: latest path: - '**/details_harness|hendrycksTest-moral_disputes|5_2023-07-19T18:58:31.382707.parquet' - config_name: harness_hendrycksTest_moral_scenarios_5 data_files: - split: 2023_07_19T18_58_31.382707 path: - '**/details_harness|hendrycksTest-moral_scenarios|5_2023-07-19T18:58:31.382707.parquet' - split: latest path: - '**/details_harness|hendrycksTest-moral_scenarios|5_2023-07-19T18:58:31.382707.parquet' - config_name: harness_hendrycksTest_nutrition_5 data_files: - split: 2023_07_19T18_58_31.382707 path: - '**/details_harness|hendrycksTest-nutrition|5_2023-07-19T18:58:31.382707.parquet' - split: latest path: - '**/details_harness|hendrycksTest-nutrition|5_2023-07-19T18:58:31.382707.parquet' - config_name: harness_hendrycksTest_philosophy_5 data_files: - split: 2023_07_19T18_58_31.382707 path: - '**/details_harness|hendrycksTest-philosophy|5_2023-07-19T18:58:31.382707.parquet' - split: latest path: - '**/details_harness|hendrycksTest-philosophy|5_2023-07-19T18:58:31.382707.parquet' - config_name: harness_hendrycksTest_prehistory_5 data_files: - split: 2023_07_19T18_58_31.382707 path: - '**/details_harness|hendrycksTest-prehistory|5_2023-07-19T18:58:31.382707.parquet' - split: latest path: - '**/details_harness|hendrycksTest-prehistory|5_2023-07-19T18:58:31.382707.parquet' - config_name: harness_hendrycksTest_professional_accounting_5 data_files: - split: 2023_07_19T18_58_31.382707 path: - '**/details_harness|hendrycksTest-professional_accounting|5_2023-07-19T18:58:31.382707.parquet' - split: latest path: - '**/details_harness|hendrycksTest-professional_accounting|5_2023-07-19T18:58:31.382707.parquet' - config_name: harness_hendrycksTest_professional_law_5 data_files: - split: 2023_07_19T18_58_31.382707 path: - '**/details_harness|hendrycksTest-professional_law|5_2023-07-19T18:58:31.382707.parquet' - split: latest path: - '**/details_harness|hendrycksTest-professional_law|5_2023-07-19T18:58:31.382707.parquet' - config_name: harness_hendrycksTest_professional_medicine_5 data_files: - split: 2023_07_19T18_58_31.382707 path: - '**/details_harness|hendrycksTest-professional_medicine|5_2023-07-19T18:58:31.382707.parquet' - split: latest path: - '**/details_harness|hendrycksTest-professional_medicine|5_2023-07-19T18:58:31.382707.parquet' - config_name: harness_hendrycksTest_professional_psychology_5 data_files: - split: 2023_07_19T18_58_31.382707 path: - '**/details_harness|hendrycksTest-professional_psychology|5_2023-07-19T18:58:31.382707.parquet' - split: latest path: - '**/details_harness|hendrycksTest-professional_psychology|5_2023-07-19T18:58:31.382707.parquet' - config_name: harness_hendrycksTest_public_relations_5 data_files: - split: 2023_07_19T18_58_31.382707 path: - '**/details_harness|hendrycksTest-public_relations|5_2023-07-19T18:58:31.382707.parquet' - split: latest path: - '**/details_harness|hendrycksTest-public_relations|5_2023-07-19T18:58:31.382707.parquet' - config_name: harness_hendrycksTest_security_studies_5 data_files: - split: 2023_07_19T18_58_31.382707 path: - '**/details_harness|hendrycksTest-security_studies|5_2023-07-19T18:58:31.382707.parquet' - split: latest path: - '**/details_harness|hendrycksTest-security_studies|5_2023-07-19T18:58:31.382707.parquet' - config_name: harness_hendrycksTest_sociology_5 data_files: - split: 2023_07_19T18_58_31.382707 path: - '**/details_harness|hendrycksTest-sociology|5_2023-07-19T18:58:31.382707.parquet' - split: latest path: - '**/details_harness|hendrycksTest-sociology|5_2023-07-19T18:58:31.382707.parquet' - config_name: harness_hendrycksTest_us_foreign_policy_5 data_files: - split: 2023_07_19T18_58_31.382707 path: - '**/details_harness|hendrycksTest-us_foreign_policy|5_2023-07-19T18:58:31.382707.parquet' - split: latest path: - '**/details_harness|hendrycksTest-us_foreign_policy|5_2023-07-19T18:58:31.382707.parquet' - config_name: harness_hendrycksTest_virology_5 data_files: - split: 2023_07_19T18_58_31.382707 path: - '**/details_harness|hendrycksTest-virology|5_2023-07-19T18:58:31.382707.parquet' - split: latest path: - '**/details_harness|hendrycksTest-virology|5_2023-07-19T18:58:31.382707.parquet' - config_name: harness_hendrycksTest_world_religions_5 data_files: - split: 2023_07_19T18_58_31.382707 path: - '**/details_harness|hendrycksTest-world_religions|5_2023-07-19T18:58:31.382707.parquet' - split: latest path: - '**/details_harness|hendrycksTest-world_religions|5_2023-07-19T18:58:31.382707.parquet' - config_name: harness_truthfulqa_mc_0 data_files: - split: 2023_07_19T18_58_31.382707 path: - '**/details_harness|truthfulqa:mc|0_2023-07-19T18:58:31.382707.parquet' - split: latest path: - '**/details_harness|truthfulqa:mc|0_2023-07-19T18:58:31.382707.parquet' - config_name: harness_winogrande_5 data_files: - split: 2023_10_17T19_54_07.074277 path: - '**/details_harness|winogrande|5_2023-10-17T19-54-07.074277.parquet' - split: latest path: - '**/details_harness|winogrande|5_2023-10-17T19-54-07.074277.parquet' - config_name: results data_files: - split: 2023_07_19T18_58_31.382707 path: - results_2023-07-19T18:58:31.382707.parquet - split: 2023_10_17T19_54_07.074277 path: - results_2023-10-17T19-54-07.074277.parquet - split: 2023_12_03T18_22_26.346357 path: - results_2023-12-03T18-22-26.346357.parquet - split: latest path: - results_2023-12-03T18-22-26.346357.parquet --- # Dataset Card for Evaluation run of microsoft/DialoGPT-small ## Dataset Description - **Homepage:** - **Repository:** https://huggingface.co/microsoft/DialoGPT-small - **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 [microsoft/DialoGPT-small](https://huggingface.co/microsoft/DialoGPT-small) 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 3 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_microsoft__DialoGPT-small", "harness_gsm8k_5", split="train") ``` ## Latest results These are the [latest results from run 2023-12-03T18:22:26.346357](https://huggingface.co/datasets/open-llm-leaderboard/details_microsoft__DialoGPT-small/blob/main/results_2023-12-03T18-22-26.346357.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": 0.0, "acc_stderr": 0.0 }, "harness|gsm8k|5": { "acc": 0.0, "acc_stderr": 0.0 } } ``` ### 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]
提供机构:
open-llm-leaderboard
原始信息汇总

数据集概述

数据集简介

该数据集是在评估模型microsoft/DialoGPT-smallOpen LLM Leaderboard上的运行过程中自动创建的。

数据集结构

  • 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3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。
  • 一个额外的配置"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_microsoft__DialoGPT-small", "harness_gsm8k_5", split="train")

最新结果

以下是2023-12-03T18:22:26.346357运行的最新结果: python { "all": { "acc": 0.0, "acc_stderr": 0.0 }, "harness|gsm8k|5": { "acc": 0.0, "acc_stderr": 0.0 } }

配置详情

  • harness_arc_challenge_25

    • 分割: 2023_07_19T18_58_31.382707
      • 路径: **/details_harness|arc:challenge|25_2023-07-19T18:58:31.382707.parquet
    • 分割: latest
      • 路径: **/details_harness|arc:challenge|25_2023-07-19T18:58:31.382707.parquet
  • harness_drop_3

    • 分割: 2023_10_17T19_54_07.074277
      • 路径: **/details_harness|drop|3_2023-10-17T19-54-07.074277.parquet
    • 分割: latest
      • 路径: **/details_harness|drop|3_2023-10-17T19-54-07.074277.parquet
  • harness_gsm8k_5

    • 分割: 2023_10_17T19_54_07.074277
      • 路径: **/details_harness|gsm8k|5_2023-10-17T19-54-07.074277.parquet
    • 分割: 2023_12_03T18_22_26.346357
      • 路径: **/details_harness|gsm8k|5_2023-12-03T18-22-26.346357.parquet
    • 分割: latest
      • 路径: **/details_harness|gsm8k|5_2023-12-03T18-22-26.346357.parquet
  • harness_hellaswag_10

    • 分割: 2023_07_19T18_58_31.382707
      • 路径: **/details_harness|hellaswag|10_2023-07-19T18:58:31.382707.parquet
    • 分割: latest
      • 路径: **/details_harness|hellaswag|10_2023-07-19T18:58:31.382707.parquet
  • harness_hendrycksTest_5

    • 分割: 2023_07_19T18_58_31.382707
      • 路径:
        • **/details_harness|hendrycksTest-abstract_algebra|5_2023-07-19T18:58:31.382707.parquet
        • **/details_harness|hendrycksTest-anatomy|5_2023-07-19T18:58:31.382707.parquet
        • **/details_harness|hendrycksTest-astronomy|5_2023-07-19T18:58:31.382707.parquet
        • **/details_harness|hendrycksTest-business_ethics|5_2023-07-19T18:58:31.382707.parquet
        • **/details_harness|hendrycksTest-clinical_knowledge|5_2023-07-19T18:58:31.382707.parquet
        • **/details_harness|hendrycksTest-college_biology|5_2023-07-19T18:58:31.382707.parquet
        • **/details_harness|hendrycksTest-college_chemistry|5_2023-07-19T18:58:31.382707.parquet
        • **/details_harness|hendrycksTest-college_computer_science|5_2023-07-19T18:58:31.382707.parquet
        • **/details_harness|hendrycksTest-college_mathematics|5_2023-07-19T18:58:31.382707.parquet
        • **/details_harness|hendrycksTest-college_medicine|5_2023-07-19T18:58:31.382707.parquet
        • **/details_harness|hendrycksTest-college_physics|5_2023-07-19T18:58:31.382707.parquet
        • **/details_harness|hendrycksTest-computer_security|5_2023-07-19T18:58:31.382707.parquet
        • **/details_harness|hendrycksTest-conceptual_physics|5_2023-07-19T18:58:31.382707.parquet
        • **/details_harness|hendrycksTest-econometrics|5_2023-07-19T18:58:31.382707.parquet
        • **/details_harness|hendrycksTest-electrical_engineering|5_2023-07-19T18:58:31.382707.parquet
        • **/details_harness|hendrycksTest-elementary_mathematics|5_2023-07-19T18:58:31.382707.parquet
        • **/details_harness|hendrycksTest-formal_logic|5_2023-07-19T18:58:31.382707.parquet
        • **/details_harness|hendrycksTest-global_facts|5_2023-07-19T18:58:31.382707.parquet
        • **/details_harness|hendrycksTest-high_school_biology|5_2023-07-19T18:58:31.382707.parquet
        • **/details_harness|hendrycksTest-high_school_chemistry|5_2023-07-19T18:58:31.382707.parquet
        • **/details_harness|hendrycksTest-high_school_computer_science|5_2023-07-19T18:58:31.382707.parquet
        • **/details_harness|hendrycksTest-high_school_european_history|5_2023-07-19T18:58:31.382707.parquet
        • **/details_harness|hendrycksTest-high_school_geography|5_2023-07-19T18:58:31.382707.parquet
        • **/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-07-19T18:58:31.382707.parquet
        • **/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-07-19T18:58:31.382707.parquet
        • **/details_harness|hendrycksTest-high_school_mathematics|5_2023-07-19T18:58:31.382707.parquet
        • **/details_harness|hendrycksTest-high_school_microeconomics|5_2023-07-19T18:58:31.382707.parquet
        • **/details_harness|hendrycksTest-high_school_physics|5_2023-07-19T18:58:31.382707.parquet
        • **/details_harness|hendrycksTest-high_school_psychology|5_2023-07-19T18:58:31.382707.parquet
        • **/details_harness|hendrycksTest-high_school_statistics|5_2023-07-19T18:58:31.382707.parquet
        • **/details_harness|hendrycksTest-high_school_us_history|5_2023-07-19T18:58:31.382707.parquet
        • **/details_harness|hendrycksTest-high_school_world_history|5_2023-07-19T18:58:31.382707.parquet
        • **/details_harness|hendrycksTest-human_aging|5_2023-07-19T18:58:31.382707.parquet
        • **/details_harness|hendrycksTest-human_sexuality|5_2023-07-19T18:58:31.382707.parquet
        • **/details_harness|hendrycksTest-international_law|5_2023-07-19T18:58:31.382707.parquet
        • **/details_harness|hendrycksTest-jurisprudence|5_2023-07-19T18:58:31.382707.parquet
        • **/details_harness|hendrycksTest-logical_fallacies|5_2023-07-19T18:58:31.382707.parquet
        • **/details_harness|hendrycksTest-machine_learning|5_2023-07-19T18:58:31.382707.parquet
        • **/details_harness|hendrycksTest-management|5_2023-07-19T18:58:31.382707.parquet
        • **/details_harness|hendrycksTest-marketing|5_2023-07-19T18:58:31.382707.parquet
        • **/details_harness|hendrycksTest-medical_genetics|5_2023-07-19T18:58:31.382707.parquet
        • **/details_harness|hendrycksTest-miscellaneous|5_2023-07-19T18:58:31.382707.parquet
        • **/details_harness|hendrycksTest-moral_disputes|5_2023-07-19T18:58:31.382707.parquet
        • **/details_harness|hendrycksTest-moral_scenarios|5_2023-07-19T18:58:31.382707.parquet
        • **/details_harness|hendrycksTest-nutrition|5_2023-07-19T18:58:31.382707.parquet
        • **/details_harness|hendrycksTest-philosophy|5_2023-07-19T18:58:31.382707.parquet
        • **/details_harness|hendrycksTest-prehistory|5_2023-07-19T18:58:31.382707.parquet
        • **/details_harness|hendrycksTest-professional_accounting|5_2023-07-19T18:58:31.382707.parquet
        • **/details_harness|hendrycksTest-professional_law|5_2023-07-19T18:58:31.382707.parquet
        • **/details_harness|hendrycksTest-professional_medicine|5_2023-07-19T18:58:31.382707.parquet
        • **/details_harness|hendrycksTest-professional_psychology|5_2023-07-19T18:58:31.382707.parquet
        • **/details_harness|hendrycksTest-public_relations|5_2023-07-19T18:58:31.382707.parquet
        • **/details_harness|hendrycksTest-security_studies|5_2023-07-19T18:58:31.382707.parquet
        • **/details_harness|hendrycksTest-sociology|5_2023-07-19T18:58:31.382707.parquet
        • **/details_harness|hendrycksTest-us_foreign_policy|5_2023-07-19T18:58:31.382707.parquet
        • **/details_harness|hendrycksTest-virology|5_202
搜集汇总
数据集介绍
main_image_url
构建方式
在大型语言模型评估领域,该数据集作为Open LLM Leaderboard评估流程的自动化产物而诞生。其构建过程依托于对microsoft/DialoGPT-small模型在多个标准化评测任务上的系统性测试,通过三次独立的运行生成详尽的评估细节。数据集以配置为单位进行组织,共计包含64种配置,每一种配置对应一个特定的评估任务,例如ARC挑战、GSM8K数学推理或Hellaswag常识推理等。每次运行的结果被存储为独立的分割,并以时间戳命名,而“train”分割则始终指向最新的评估结果,确保了数据的时效性与可追溯性。此外,一个专门的“results”配置汇总了所有运行的聚合指标,为模型能力的宏观分析提供了数据基础。
特点
该数据集的核心特征在于其作为模型评估元数据的精细结构与全面覆盖。它并非原始的训练或测试语料,而是详细记录了模型在多样化基准测试中每一次预测的输入、输出及评分细节。这种设计使得研究者能够超越单一的汇总分数,深入剖析模型在具体问题上的表现模式与失败案例。数据集覆盖了从常识推理、数学解题到专业学科知识的多维度能力评估,特别是通过HendrycksTest系列配置,实现了对数十个专业领域知识的细粒度考察。其多版本分割的存储方式,不仅保留了历史评估的完整轨迹,也便于进行模型性能的纵向比较与演变分析。
使用方法
为利用此数据集进行深入分析,研究者可通过Hugging Face的`datasets`库便捷加载。典型的使用方式是调用`load_dataset`函数,指定数据集名称、目标配置(如`harness_gsm8k_5`)以及所需的分割(如`train`或特定时间戳)。加载后的数据以结构化的格式呈现,允许用户提取特定任务下模型响应的具体内容与评估指标。例如,通过分析GSM8K数学问题上的详细回答,可以诊断模型在分步推理中的常见错误。同时,聚合的“results”配置为用户提供了快速获取模型整体性能概览的途径。这种灵活的数据访问方式,支撑了从宏观基准比较到微观错误分析的各类研究需求。
背景与挑战
背景概述
在人工智能领域,大型语言模型(LLM)的评估与比较已成为推动技术进步的关键环节。由HuggingFace团队于2023年主导创建的Open LLM Leaderboard,旨在通过标准化基准测试,系统性地评估各类开放语言模型的综合性能。该平台聚焦于解决对话生成、常识推理、数学解题及多学科知识问答等核心研究问题,为研究社区提供了透明、可复现的模型性能对比框架。其影响力不仅体现在促进了模型优化与创新,还推动了评估方法的标准化,成为学术界与工业界衡量语言模型能力的重要参考。
当前挑战
Open LLM Leaderboard在解决语言模型综合评估这一领域问题时,面临多重挑战:其一,评估任务需涵盖多样化的认知能力,如逻辑推理、数学计算与专业知识应用,这对基准设计的全面性与平衡性提出了极高要求;其二,构建过程中,如何整合不同时间点的评估运行结果,并确保数据版本管理与聚合指标计算的准确性与一致性,成为技术实施上的关键难点。此外,随着模型迭代加速,保持评估框架的时效性与扩展性,以适应新兴任务与模型架构,亦是持续面临的挑战。
常用场景
经典使用场景
在大型语言模型评估领域,该数据集作为Open LLM Leaderboard评估框架的组成部分,其经典使用场景在于为DialoGPT-small模型提供多维度性能基准测试。通过涵盖ARC挑战、HellaSwag、MMLU及GSM8K等标准化评测任务,数据集能够系统性地衡量模型在常识推理、语言理解与数学解题等方面的综合能力,为研究者提供了模型横向对比的客观依据。
衍生相关工作
围绕该数据集构建的评估生态催生了系列经典研究工作,包括基于多任务评估的模型诊断框架、针对特定缺陷的微调策略以及评估指标的可视化分析工具。这些工作不仅深化了对生成式模型能力边界的认识,更推动了如HELM、Big-Bench等下一代评估体系的演进,形成了模型评估与能力迭代的良性循环。
数据集最近研究
最新研究方向
在对话生成模型评估领域,该数据集作为Open LLM Leaderboard的评估结果记录,体现了当前研究对模型性能标准化测评的重视。前沿方向聚焦于多维度能力评估,涵盖常识推理、数学解题、专业知识及伦理判断等复杂任务,如ARC挑战、HellaSwag、MMLU及GSM8K等基准测试。这些评估不仅追踪模型在对话流畅性上的进展,更深入探究其逻辑严谨性与知识准确性。随着大语言模型在产业界广泛应用,此类标准化测评数据为模型优化提供了关键参照,推动着对话系统向更可靠、更智能的方向演进。
以上内容由遇见数据集搜集并总结生成
二维码
社区交流群
二维码
科研交流群
商业服务