five

open-llm-leaderboard/details_togethercomputer__RedPajama-INCITE-7B-Chat

收藏
Hugging Face2023-10-19 更新2024-03-04 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard/details_togethercomputer__RedPajama-INCITE-7B-Chat
下载链接
链接失效反馈
官方服务:
资源简介:
--- pretty_name: Evaluation run of togethercomputer/RedPajama-INCITE-7B-Chat dataset_summary: "Dataset automatically created during the evaluation run of model\ \ [togethercomputer/RedPajama-INCITE-7B-Chat](https://huggingface.co/togethercomputer/RedPajama-INCITE-7B-Chat)\ \ 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 2 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 agregated 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_togethercomputer__RedPajama-INCITE-7B-Chat\"\ ,\n\t\"harness_winogrande_5\",\n\tsplit=\"train\")\n```\n\n## Latest results\n\n\ These are the [latest results from run 2023-10-19T02:47:12.906889](https://huggingface.co/datasets/open-llm-leaderboard/details_togethercomputer__RedPajama-INCITE-7B-Chat/blob/main/results_2023-10-19T02-47-12.906889.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 \"em\": 0.00985738255033557,\n\ \ \"em_stderr\": 0.001011740962658439,\n \"f1\": 0.06564072986577182,\n\ \ \"f1_stderr\": 0.0016570971110147965,\n \"acc\": 0.3014062577602678,\n\ \ \"acc_stderr\": 0.007815997155326552\n },\n \"harness|drop|3\": {\n\ \ \"em\": 0.00985738255033557,\n \"em_stderr\": 0.001011740962658439,\n\ \ \"f1\": 0.06564072986577182,\n \"f1_stderr\": 0.0016570971110147965\n\ \ },\n \"harness|gsm8k|5\": {\n \"acc\": 0.004548900682335102,\n \ \ \"acc_stderr\": 0.0018535550440036204\n },\n \"harness|winogrande|5\"\ : {\n \"acc\": 0.5982636148382005,\n \"acc_stderr\": 0.013778439266649482\n\ \ }\n}\n```" repo_url: https://huggingface.co/togethercomputer/RedPajama-INCITE-7B-Chat 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_19T17_30_52.522444 path: - '**/details_harness|arc:challenge|25_2023-07-19T17:30:52.522444.parquet' - split: latest path: - '**/details_harness|arc:challenge|25_2023-07-19T17:30:52.522444.parquet' - config_name: harness_drop_3 data_files: - split: 2023_10_19T02_47_12.906889 path: - '**/details_harness|drop|3_2023-10-19T02-47-12.906889.parquet' - split: latest path: - '**/details_harness|drop|3_2023-10-19T02-47-12.906889.parquet' - config_name: harness_gsm8k_5 data_files: - split: 2023_10_19T02_47_12.906889 path: - '**/details_harness|gsm8k|5_2023-10-19T02-47-12.906889.parquet' - split: latest path: - '**/details_harness|gsm8k|5_2023-10-19T02-47-12.906889.parquet' - config_name: harness_hellaswag_10 data_files: - split: 2023_07_19T17_30_52.522444 path: - '**/details_harness|hellaswag|10_2023-07-19T17:30:52.522444.parquet' - split: latest path: - '**/details_harness|hellaswag|10_2023-07-19T17:30:52.522444.parquet' - config_name: harness_hendrycksTest_5 data_files: - split: 2023_07_19T17_30_52.522444 path: - '**/details_harness|hendrycksTest-abstract_algebra|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-anatomy|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-astronomy|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-business_ethics|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-clinical_knowledge|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-college_biology|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-college_chemistry|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-college_computer_science|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-college_mathematics|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-college_medicine|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-college_physics|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-computer_security|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-conceptual_physics|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-econometrics|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-electrical_engineering|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-elementary_mathematics|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-formal_logic|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-global_facts|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-high_school_biology|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-high_school_chemistry|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-high_school_computer_science|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-high_school_european_history|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-high_school_geography|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-high_school_mathematics|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-high_school_physics|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-high_school_psychology|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-high_school_statistics|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-high_school_us_history|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-high_school_world_history|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-human_aging|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-human_sexuality|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-international_law|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-jurisprudence|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-logical_fallacies|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-machine_learning|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-management|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-marketing|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-medical_genetics|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-miscellaneous|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-moral_disputes|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-moral_scenarios|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-nutrition|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-philosophy|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-prehistory|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-professional_accounting|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-professional_law|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-professional_medicine|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-professional_psychology|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-public_relations|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-security_studies|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-sociology|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-us_foreign_policy|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-virology|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-world_religions|5_2023-07-19T17:30:52.522444.parquet' - split: latest path: - '**/details_harness|hendrycksTest-abstract_algebra|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-anatomy|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-astronomy|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-business_ethics|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-clinical_knowledge|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-college_biology|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-college_chemistry|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-college_computer_science|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-college_mathematics|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-college_medicine|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-college_physics|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-computer_security|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-conceptual_physics|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-econometrics|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-electrical_engineering|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-elementary_mathematics|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-formal_logic|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-global_facts|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-high_school_biology|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-high_school_chemistry|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-high_school_computer_science|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-high_school_european_history|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-high_school_geography|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-high_school_mathematics|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-high_school_physics|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-high_school_psychology|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-high_school_statistics|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-high_school_us_history|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-high_school_world_history|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-human_aging|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-human_sexuality|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-international_law|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-jurisprudence|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-logical_fallacies|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-machine_learning|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-management|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-marketing|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-medical_genetics|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-miscellaneous|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-moral_disputes|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-moral_scenarios|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-nutrition|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-philosophy|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-prehistory|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-professional_accounting|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-professional_law|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-professional_medicine|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-professional_psychology|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-public_relations|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-security_studies|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-sociology|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-us_foreign_policy|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-virology|5_2023-07-19T17:30:52.522444.parquet' - '**/details_harness|hendrycksTest-world_religions|5_2023-07-19T17:30:52.522444.parquet' - config_name: harness_hendrycksTest_abstract_algebra_5 data_files: - split: 2023_07_19T17_30_52.522444 path: - '**/details_harness|hendrycksTest-abstract_algebra|5_2023-07-19T17:30:52.522444.parquet' - split: latest path: - '**/details_harness|hendrycksTest-abstract_algebra|5_2023-07-19T17:30:52.522444.parquet' - config_name: harness_hendrycksTest_anatomy_5 data_files: - split: 2023_07_19T17_30_52.522444 path: - '**/details_harness|hendrycksTest-anatomy|5_2023-07-19T17:30:52.522444.parquet' - split: latest path: - '**/details_harness|hendrycksTest-anatomy|5_2023-07-19T17:30:52.522444.parquet' - config_name: harness_hendrycksTest_astronomy_5 data_files: - split: 2023_07_19T17_30_52.522444 path: - '**/details_harness|hendrycksTest-astronomy|5_2023-07-19T17:30:52.522444.parquet' - split: latest path: - '**/details_harness|hendrycksTest-astronomy|5_2023-07-19T17:30:52.522444.parquet' - config_name: harness_hendrycksTest_business_ethics_5 data_files: - split: 2023_07_19T17_30_52.522444 path: - '**/details_harness|hendrycksTest-business_ethics|5_2023-07-19T17:30:52.522444.parquet' - split: latest path: - '**/details_harness|hendrycksTest-business_ethics|5_2023-07-19T17:30:52.522444.parquet' - config_name: harness_hendrycksTest_clinical_knowledge_5 data_files: - split: 2023_07_19T17_30_52.522444 path: - '**/details_harness|hendrycksTest-clinical_knowledge|5_2023-07-19T17:30:52.522444.parquet' - split: latest path: - '**/details_harness|hendrycksTest-clinical_knowledge|5_2023-07-19T17:30:52.522444.parquet' - config_name: harness_hendrycksTest_college_biology_5 data_files: - split: 2023_07_19T17_30_52.522444 path: - '**/details_harness|hendrycksTest-college_biology|5_2023-07-19T17:30:52.522444.parquet' - split: latest path: - '**/details_harness|hendrycksTest-college_biology|5_2023-07-19T17:30:52.522444.parquet' - config_name: harness_hendrycksTest_college_chemistry_5 data_files: - split: 2023_07_19T17_30_52.522444 path: - '**/details_harness|hendrycksTest-college_chemistry|5_2023-07-19T17:30:52.522444.parquet' - split: latest path: - '**/details_harness|hendrycksTest-college_chemistry|5_2023-07-19T17:30:52.522444.parquet' - config_name: harness_hendrycksTest_college_computer_science_5 data_files: - split: 2023_07_19T17_30_52.522444 path: - '**/details_harness|hendrycksTest-college_computer_science|5_2023-07-19T17:30:52.522444.parquet' - split: latest path: - '**/details_harness|hendrycksTest-college_computer_science|5_2023-07-19T17:30:52.522444.parquet' - config_name: harness_hendrycksTest_college_mathematics_5 data_files: - split: 2023_07_19T17_30_52.522444 path: - '**/details_harness|hendrycksTest-college_mathematics|5_2023-07-19T17:30:52.522444.parquet' - split: latest path: - '**/details_harness|hendrycksTest-college_mathematics|5_2023-07-19T17:30:52.522444.parquet' - config_name: harness_hendrycksTest_college_medicine_5 data_files: - split: 2023_07_19T17_30_52.522444 path: - '**/details_harness|hendrycksTest-college_medicine|5_2023-07-19T17:30:52.522444.parquet' - split: latest path: - '**/details_harness|hendrycksTest-college_medicine|5_2023-07-19T17:30:52.522444.parquet' - config_name: harness_hendrycksTest_college_physics_5 data_files: - split: 2023_07_19T17_30_52.522444 path: - '**/details_harness|hendrycksTest-college_physics|5_2023-07-19T17:30:52.522444.parquet' - split: latest path: - '**/details_harness|hendrycksTest-college_physics|5_2023-07-19T17:30:52.522444.parquet' - config_name: harness_hendrycksTest_computer_security_5 data_files: - split: 2023_07_19T17_30_52.522444 path: - '**/details_harness|hendrycksTest-computer_security|5_2023-07-19T17:30:52.522444.parquet' - split: latest path: - '**/details_harness|hendrycksTest-computer_security|5_2023-07-19T17:30:52.522444.parquet' - config_name: harness_hendrycksTest_conceptual_physics_5 data_files: - split: 2023_07_19T17_30_52.522444 path: - '**/details_harness|hendrycksTest-conceptual_physics|5_2023-07-19T17:30:52.522444.parquet' - split: latest path: - '**/details_harness|hendrycksTest-conceptual_physics|5_2023-07-19T17:30:52.522444.parquet' - config_name: harness_hendrycksTest_econometrics_5 data_files: - split: 2023_07_19T17_30_52.522444 path: - '**/details_harness|hendrycksTest-econometrics|5_2023-07-19T17:30:52.522444.parquet' - split: latest path: - '**/details_harness|hendrycksTest-econometrics|5_2023-07-19T17:30:52.522444.parquet' - config_name: harness_hendrycksTest_electrical_engineering_5 data_files: - split: 2023_07_19T17_30_52.522444 path: - '**/details_harness|hendrycksTest-electrical_engineering|5_2023-07-19T17:30:52.522444.parquet' - split: latest path: - '**/details_harness|hendrycksTest-electrical_engineering|5_2023-07-19T17:30:52.522444.parquet' - config_name: harness_hendrycksTest_elementary_mathematics_5 data_files: - split: 2023_07_19T17_30_52.522444 path: - '**/details_harness|hendrycksTest-elementary_mathematics|5_2023-07-19T17:30:52.522444.parquet' - split: latest path: - '**/details_harness|hendrycksTest-elementary_mathematics|5_2023-07-19T17:30:52.522444.parquet' - config_name: harness_hendrycksTest_formal_logic_5 data_files: - split: 2023_07_19T17_30_52.522444 path: - '**/details_harness|hendrycksTest-formal_logic|5_2023-07-19T17:30:52.522444.parquet' - split: latest path: - '**/details_harness|hendrycksTest-formal_logic|5_2023-07-19T17:30:52.522444.parquet' - config_name: harness_hendrycksTest_global_facts_5 data_files: - split: 2023_07_19T17_30_52.522444 path: - '**/details_harness|hendrycksTest-global_facts|5_2023-07-19T17:30:52.522444.parquet' - split: latest path: - '**/details_harness|hendrycksTest-global_facts|5_2023-07-19T17:30:52.522444.parquet' - config_name: harness_hendrycksTest_high_school_biology_5 data_files: - split: 2023_07_19T17_30_52.522444 path: - '**/details_harness|hendrycksTest-high_school_biology|5_2023-07-19T17:30:52.522444.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_biology|5_2023-07-19T17:30:52.522444.parquet' - config_name: harness_hendrycksTest_high_school_chemistry_5 data_files: - split: 2023_07_19T17_30_52.522444 path: - '**/details_harness|hendrycksTest-high_school_chemistry|5_2023-07-19T17:30:52.522444.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_chemistry|5_2023-07-19T17:30:52.522444.parquet' - config_name: harness_hendrycksTest_high_school_computer_science_5 data_files: - split: 2023_07_19T17_30_52.522444 path: - '**/details_harness|hendrycksTest-high_school_computer_science|5_2023-07-19T17:30:52.522444.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_computer_science|5_2023-07-19T17:30:52.522444.parquet' - config_name: harness_hendrycksTest_high_school_european_history_5 data_files: - split: 2023_07_19T17_30_52.522444 path: - '**/details_harness|hendrycksTest-high_school_european_history|5_2023-07-19T17:30:52.522444.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_european_history|5_2023-07-19T17:30:52.522444.parquet' - config_name: harness_hendrycksTest_high_school_geography_5 data_files: - split: 2023_07_19T17_30_52.522444 path: - '**/details_harness|hendrycksTest-high_school_geography|5_2023-07-19T17:30:52.522444.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_geography|5_2023-07-19T17:30:52.522444.parquet' - config_name: harness_hendrycksTest_high_school_government_and_politics_5 data_files: - split: 2023_07_19T17_30_52.522444 path: - '**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-07-19T17:30:52.522444.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-07-19T17:30:52.522444.parquet' - config_name: harness_hendrycksTest_high_school_macroeconomics_5 data_files: - split: 2023_07_19T17_30_52.522444 path: - '**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-07-19T17:30:52.522444.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-07-19T17:30:52.522444.parquet' - config_name: harness_hendrycksTest_high_school_mathematics_5 data_files: - split: 2023_07_19T17_30_52.522444 path: - '**/details_harness|hendrycksTest-high_school_mathematics|5_2023-07-19T17:30:52.522444.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_mathematics|5_2023-07-19T17:30:52.522444.parquet' - config_name: harness_hendrycksTest_high_school_microeconomics_5 data_files: - split: 2023_07_19T17_30_52.522444 path: - '**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-07-19T17:30:52.522444.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-07-19T17:30:52.522444.parquet' - config_name: harness_hendrycksTest_high_school_physics_5 data_files: - split: 2023_07_19T17_30_52.522444 path: - '**/details_harness|hendrycksTest-high_school_physics|5_2023-07-19T17:30:52.522444.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_physics|5_2023-07-19T17:30:52.522444.parquet' - config_name: harness_hendrycksTest_high_school_psychology_5 data_files: - split: 2023_07_19T17_30_52.522444 path: - '**/details_harness|hendrycksTest-high_school_psychology|5_2023-07-19T17:30:52.522444.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_psychology|5_2023-07-19T17:30:52.522444.parquet' - config_name: harness_hendrycksTest_high_school_statistics_5 data_files: - split: 2023_07_19T17_30_52.522444 path: - '**/details_harness|hendrycksTest-high_school_statistics|5_2023-07-19T17:30:52.522444.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_statistics|5_2023-07-19T17:30:52.522444.parquet' - config_name: harness_hendrycksTest_high_school_us_history_5 data_files: - split: 2023_07_19T17_30_52.522444 path: - '**/details_harness|hendrycksTest-high_school_us_history|5_2023-07-19T17:30:52.522444.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_us_history|5_2023-07-19T17:30:52.522444.parquet' - config_name: harness_hendrycksTest_high_school_world_history_5 data_files: - split: 2023_07_19T17_30_52.522444 path: - '**/details_harness|hendrycksTest-high_school_world_history|5_2023-07-19T17:30:52.522444.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_world_history|5_2023-07-19T17:30:52.522444.parquet' - config_name: harness_hendrycksTest_human_aging_5 data_files: - split: 2023_07_19T17_30_52.522444 path: - '**/details_harness|hendrycksTest-human_aging|5_2023-07-19T17:30:52.522444.parquet' - split: latest path: - '**/details_harness|hendrycksTest-human_aging|5_2023-07-19T17:30:52.522444.parquet' - config_name: harness_hendrycksTest_human_sexuality_5 data_files: - split: 2023_07_19T17_30_52.522444 path: - '**/details_harness|hendrycksTest-human_sexuality|5_2023-07-19T17:30:52.522444.parquet' - split: latest path: - '**/details_harness|hendrycksTest-human_sexuality|5_2023-07-19T17:30:52.522444.parquet' - config_name: harness_hendrycksTest_international_law_5 data_files: - split: 2023_07_19T17_30_52.522444 path: - '**/details_harness|hendrycksTest-international_law|5_2023-07-19T17:30:52.522444.parquet' - split: latest path: - '**/details_harness|hendrycksTest-international_law|5_2023-07-19T17:30:52.522444.parquet' - config_name: harness_hendrycksTest_jurisprudence_5 data_files: - split: 2023_07_19T17_30_52.522444 path: - '**/details_harness|hendrycksTest-jurisprudence|5_2023-07-19T17:30:52.522444.parquet' - split: latest path: - '**/details_harness|hendrycksTest-jurisprudence|5_2023-07-19T17:30:52.522444.parquet' - config_name: harness_hendrycksTest_logical_fallacies_5 data_files: - split: 2023_07_19T17_30_52.522444 path: - '**/details_harness|hendrycksTest-logical_fallacies|5_2023-07-19T17:30:52.522444.parquet' - split: latest path: - '**/details_harness|hendrycksTest-logical_fallacies|5_2023-07-19T17:30:52.522444.parquet' - config_name: harness_hendrycksTest_machine_learning_5 data_files: - split: 2023_07_19T17_30_52.522444 path: - '**/details_harness|hendrycksTest-machine_learning|5_2023-07-19T17:30:52.522444.parquet' - split: latest path: - '**/details_harness|hendrycksTest-machine_learning|5_2023-07-19T17:30:52.522444.parquet' - config_name: harness_hendrycksTest_management_5 data_files: - split: 2023_07_19T17_30_52.522444 path: - '**/details_harness|hendrycksTest-management|5_2023-07-19T17:30:52.522444.parquet' - split: latest path: - '**/details_harness|hendrycksTest-management|5_2023-07-19T17:30:52.522444.parquet' - config_name: harness_hendrycksTest_marketing_5 data_files: - split: 2023_07_19T17_30_52.522444 path: - '**/details_harness|hendrycksTest-marketing|5_2023-07-19T17:30:52.522444.parquet' - split: latest path: - '**/details_harness|hendrycksTest-marketing|5_2023-07-19T17:30:52.522444.parquet' - config_name: harness_hendrycksTest_medical_genetics_5 data_files: - split: 2023_07_19T17_30_52.522444 path: - '**/details_harness|hendrycksTest-medical_genetics|5_2023-07-19T17:30:52.522444.parquet' - split: latest path: - '**/details_harness|hendrycksTest-medical_genetics|5_2023-07-19T17:30:52.522444.parquet' - config_name: harness_hendrycksTest_miscellaneous_5 data_files: - split: 2023_07_19T17_30_52.522444 path: - '**/details_harness|hendrycksTest-miscellaneous|5_2023-07-19T17:30:52.522444.parquet' - split: latest path: - '**/details_harness|hendrycksTest-miscellaneous|5_2023-07-19T17:30:52.522444.parquet' - config_name: harness_hendrycksTest_moral_disputes_5 data_files: - split: 2023_07_19T17_30_52.522444 path: - '**/details_harness|hendrycksTest-moral_disputes|5_2023-07-19T17:30:52.522444.parquet' - split: latest path: - '**/details_harness|hendrycksTest-moral_disputes|5_2023-07-19T17:30:52.522444.parquet' - config_name: harness_hendrycksTest_moral_scenarios_5 data_files: - split: 2023_07_19T17_30_52.522444 path: - '**/details_harness|hendrycksTest-moral_scenarios|5_2023-07-19T17:30:52.522444.parquet' - split: latest path: - '**/details_harness|hendrycksTest-moral_scenarios|5_2023-07-19T17:30:52.522444.parquet' - config_name: harness_hendrycksTest_nutrition_5 data_files: - split: 2023_07_19T17_30_52.522444 path: - '**/details_harness|hendrycksTest-nutrition|5_2023-07-19T17:30:52.522444.parquet' - split: latest path: - '**/details_harness|hendrycksTest-nutrition|5_2023-07-19T17:30:52.522444.parquet' - config_name: harness_hendrycksTest_philosophy_5 data_files: - split: 2023_07_19T17_30_52.522444 path: - '**/details_harness|hendrycksTest-philosophy|5_2023-07-19T17:30:52.522444.parquet' - split: latest path: - '**/details_harness|hendrycksTest-philosophy|5_2023-07-19T17:30:52.522444.parquet' - config_name: harness_hendrycksTest_prehistory_5 data_files: - split: 2023_07_19T17_30_52.522444 path: - '**/details_harness|hendrycksTest-prehistory|5_2023-07-19T17:30:52.522444.parquet' - split: latest path: - '**/details_harness|hendrycksTest-prehistory|5_2023-07-19T17:30:52.522444.parquet' - config_name: harness_hendrycksTest_professional_accounting_5 data_files: - split: 2023_07_19T17_30_52.522444 path: - '**/details_harness|hendrycksTest-professional_accounting|5_2023-07-19T17:30:52.522444.parquet' - split: latest path: - '**/details_harness|hendrycksTest-professional_accounting|5_2023-07-19T17:30:52.522444.parquet' - config_name: harness_hendrycksTest_professional_law_5 data_files: - split: 2023_07_19T17_30_52.522444 path: - '**/details_harness|hendrycksTest-professional_law|5_2023-07-19T17:30:52.522444.parquet' - split: latest path: - '**/details_harness|hendrycksTest-professional_law|5_2023-07-19T17:30:52.522444.parquet' - config_name: harness_hendrycksTest_professional_medicine_5 data_files: - split: 2023_07_19T17_30_52.522444 path: - '**/details_harness|hendrycksTest-professional_medicine|5_2023-07-19T17:30:52.522444.parquet' - split: latest path: - '**/details_harness|hendrycksTest-professional_medicine|5_2023-07-19T17:30:52.522444.parquet' - config_name: harness_hendrycksTest_professional_psychology_5 data_files: - split: 2023_07_19T17_30_52.522444 path: - '**/details_harness|hendrycksTest-professional_psychology|5_2023-07-19T17:30:52.522444.parquet' - split: latest path: - '**/details_harness|hendrycksTest-professional_psychology|5_2023-07-19T17:30:52.522444.parquet' - config_name: harness_hendrycksTest_public_relations_5 data_files: - split: 2023_07_19T17_30_52.522444 path: - '**/details_harness|hendrycksTest-public_relations|5_2023-07-19T17:30:52.522444.parquet' - split: latest path: - '**/details_harness|hendrycksTest-public_relations|5_2023-07-19T17:30:52.522444.parquet' - config_name: harness_hendrycksTest_security_studies_5 data_files: - split: 2023_07_19T17_30_52.522444 path: - '**/details_harness|hendrycksTest-security_studies|5_2023-07-19T17:30:52.522444.parquet' - split: latest path: - '**/details_harness|hendrycksTest-security_studies|5_2023-07-19T17:30:52.522444.parquet' - config_name: harness_hendrycksTest_sociology_5 data_files: - split: 2023_07_19T17_30_52.522444 path: - '**/details_harness|hendrycksTest-sociology|5_2023-07-19T17:30:52.522444.parquet' - split: latest path: - '**/details_harness|hendrycksTest-sociology|5_2023-07-19T17:30:52.522444.parquet' - config_name: harness_hendrycksTest_us_foreign_policy_5 data_files: - split: 2023_07_19T17_30_52.522444 path: - '**/details_harness|hendrycksTest-us_foreign_policy|5_2023-07-19T17:30:52.522444.parquet' - split: latest path: - '**/details_harness|hendrycksTest-us_foreign_policy|5_2023-07-19T17:30:52.522444.parquet' - config_name: harness_hendrycksTest_virology_5 data_files: - split: 2023_07_19T17_30_52.522444 path: - '**/details_harness|hendrycksTest-virology|5_2023-07-19T17:30:52.522444.parquet' - split: latest path: - '**/details_harness|hendrycksTest-virology|5_2023-07-19T17:30:52.522444.parquet' - config_name: harness_hendrycksTest_world_religions_5 data_files: - split: 2023_07_19T17_30_52.522444 path: - '**/details_harness|hendrycksTest-world_religions|5_2023-07-19T17:30:52.522444.parquet' - split: latest path: - '**/details_harness|hendrycksTest-world_religions|5_2023-07-19T17:30:52.522444.parquet' - config_name: harness_truthfulqa_mc_0 data_files: - split: 2023_07_19T17_30_52.522444 path: - '**/details_harness|truthfulqa:mc|0_2023-07-19T17:30:52.522444.parquet' - split: latest path: - '**/details_harness|truthfulqa:mc|0_2023-07-19T17:30:52.522444.parquet' - config_name: harness_winogrande_5 data_files: - split: 2023_10_19T02_47_12.906889 path: - '**/details_harness|winogrande|5_2023-10-19T02-47-12.906889.parquet' - split: latest path: - '**/details_harness|winogrande|5_2023-10-19T02-47-12.906889.parquet' - config_name: results data_files: - split: 2023_07_19T17_30_52.522444 path: - results_2023-07-19T17:30:52.522444.parquet - split: 2023_10_19T02_47_12.906889 path: - results_2023-10-19T02-47-12.906889.parquet - split: latest path: - results_2023-10-19T02-47-12.906889.parquet --- # Dataset Card for Evaluation run of togethercomputer/RedPajama-INCITE-7B-Chat ## Dataset Description - **Homepage:** - **Repository:** https://huggingface.co/togethercomputer/RedPajama-INCITE-7B-Chat - **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 [togethercomputer/RedPajama-INCITE-7B-Chat](https://huggingface.co/togethercomputer/RedPajama-INCITE-7B-Chat) 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 2 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 agregated 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_togethercomputer__RedPajama-INCITE-7B-Chat", "harness_winogrande_5", split="train") ``` ## Latest results These are the [latest results from run 2023-10-19T02:47:12.906889](https://huggingface.co/datasets/open-llm-leaderboard/details_togethercomputer__RedPajama-INCITE-7B-Chat/blob/main/results_2023-10-19T02-47-12.906889.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": { "em": 0.00985738255033557, "em_stderr": 0.001011740962658439, "f1": 0.06564072986577182, "f1_stderr": 0.0016570971110147965, "acc": 0.3014062577602678, "acc_stderr": 0.007815997155326552 }, "harness|drop|3": { "em": 0.00985738255033557, "em_stderr": 0.001011740962658439, "f1": 0.06564072986577182, "f1_stderr": 0.0016570971110147965 }, "harness|gsm8k|5": { "acc": 0.004548900682335102, "acc_stderr": 0.0018535550440036204 }, "harness|winogrande|5": { "acc": 0.5982636148382005, "acc_stderr": 0.013778439266649482 } } ``` ### 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

数据集摘要

该数据集是在评估模型 togethercomputer/RedPajama-INCITE-7B-ChatOpen LLM Leaderboard 上的自动创建的。

数据集组成

  • 数据集由 64 个配置组成,每个配置对应一个评估任务。
  • 数据集从 2 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,用于计算和显示聚合指标在 Open LLM Leaderboard 上。

数据加载示例

python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_togethercomputer__RedPajama-INCITE-7B-Chat", "harness_winogrande_5", split="train")

最新结果

以下是 2023-10-19T02:47:12.906889 运行的最新结果: python { "all": { "em": 0.00985738255033557, "em_stderr": 0.001011740962658439, "f1": 0.06564072986577182, "f1_stderr": 0.0016570971110147965, "acc": 0.3014062577602678, "acc_stderr": 0.007815997155326552 }, "harness|drop|3": { "em": 0.00985738255033557, "em_stderr": 0.001011740962658439, "f1": 0.06564072986577182, "f1_stderr": 0.0016570971110147965 }, "harness|gsm8k|5": { "acc": 0.004548900682335102, "acc_stderr": 0.0018535550440036204 }, "harness|winogrande|5": { "acc": 0.5982636148382005, "acc_stderr": 0.013778439266649482 } }

配置详情

  • harness_arc_challenge_25

    • 分割: 2023_07_19T17_30_52.522444
    • 路径: **/details_harness|arc:challenge|25_2023-07-19T17:30:52.522444.parquet
    • 分割: latest
    • 路径: **/details_harness|arc:challenge|25_2023-07-19T17:30:52.522444.parquet
  • harness_drop_3

    • 分割: 2023_10_19T02_47_12.906889
    • 路径: **/details_harness|drop|3_2023-10-19T02-47-12.906889.parquet
    • 分割: latest
    • 路径: **/details_harness|drop|3_2023-10-19T02-47-12.906889.parquet
  • harness_gsm8k_5

    • 分割: 2023_10_19T02_47_12.906889
    • 路径: **/details_harness|gsm8k|5_2023-10-19T02-47-12.906889.parquet
    • 分割: latest
    • 路径: **/details_harness|gsm8k|5_2023-10-19T02-47-12.906889.parquet
  • harness_hellaswag_10

    • 分割: 2023_07_19T17_30_52.522444
    • 路径: **/details_harness|hellaswag|10_2023-07-19T17:30:52.522444.parquet
    • 分割: latest
    • 路径: **/details_harness|hellaswag|10_2023-07-19T17:30:52.522444.parquet
  • harness_hendrycksTest_5

    • 分割: 2023_07_19T17_30_52.522444
    • 路径:
      • **/details_harness|hendrycksTest-abstract_algebra|5_2023-07-19T17:30:52.522444.parquet
      • **/details_harness|hendrycksTest-anatomy|5_2023-07-19T17:30:52.522444.parquet
      • **/details_harness|hendrycksTest-astronomy|5_2023-07-19T17:30:52.522444.parquet
      • **/details_harness|hendrycksTest-business_ethics|5_2023-07-19T17:30:52.522444.parquet
      • **/details_harness|hendrycksTest-clinical_knowledge|5_2023-07-19T17:30:52.522444.parquet
      • **/details_harness|hendrycksTest-college_biology|5_2023-07-19T17:30:52.522444.parquet
      • **/details_harness|hendrycksTest-college_chemistry|5_2023-07-19T17:30:52.522444.parquet
      • **/details_harness|hendrycksTest-college_computer_science|5_2023-07-19T17:30:52.522444.parquet
      • **/details_harness|hendrycksTest-college_mathematics|5_2023-07-19T17:30:52.522444.parquet
      • **/details_harness|hendrycksTest-college_medicine|5_2023-07-19T17:30:52.522444.parquet
      • **/details_harness|hendrycksTest-college_physics|5_2023-07-19T17:30:52.522444.parquet
      • **/details_harness|hendrycksTest-computer_security|5_2023-07-19T17:30:52.522444.parquet
      • **/details_harness|hendrycksTest-conceptual_physics|5_2023-07-19T17:30:52.522444.parquet
      • **/details_harness|hendrycksTest-econometrics|5_2023-07-19T17:30:52.522444.parquet
      • **/details_harness|hendrycksTest-electrical_engineering|5_2023-07-19T17:30:52.522444.parquet
      • **/details_harness|hendrycksTest-elementary_mathematics|5_2023-07-19T17:30:52.522444.parquet
      • **/details_harness|hendrycksTest-formal_logic|5_2023-07-19T17:30:52.522444.parquet
      • **/details_harness|hendrycksTest-global_facts|5_2023-07-19T17:30:52.522444.parquet
      • **/details_harness|hendrycksTest-high_school_biology|5_2023-07-19T17:30:52.522444.parquet
      • **/details_harness|hendrycksTest-high_school_chemistry|5_2023-07-19T17:30:52.522444.parquet
      • **/details_harness|hendrycksTest-high_school_computer_science|5_2023-07-19T17:30:52.522444.parquet
      • **/details_harness|hendrycksTest-high_school_european_history|5_2023-07-19T17:30:52.522444.parquet
      • **/details_harness|hendrycksTest-high_school_geography|5_2023-07-19T17:30:52.522444.parquet
      • **/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-07-19T17:30:52.522444.parquet
      • **/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-07-19T17:30:52.522444.parquet
      • **/details_harness|hendrycksTest-high_school_mathematics|5_2023-07-19T17:30:52.522444.parquet
      • **/details_harness|hendrycksTest-high_school_microeconomics|5_2023-07-19T17:30:52.522444.parquet
      • **/details_harness|hendrycksTest-high_school_physics|5_2023-07-19T17:30:52.522444.parquet
      • **/details_harness|hendrycksTest-high_school_psychology|5_2023-07-19T17:30:52.522444.parquet
      • **/details_harness|hendrycksTest-high_school_statistics|5_2023-07-19T17:30:52.522444.parquet
      • **/details_harness|hendrycksTest-high_school_us_history|5_2023-07-19T17:30:52.522444.parquet
      • **/details_harness|hendrycksTest-high_school_world_history|5_2023-07-19T17:30:52.522444.parquet
      • **/details_harness|hendrycksTest-human_aging|5_2023-07-19T17:30:52.522444.parquet
      • **/details_harness|hendrycksTest-human_sexuality|5_2023-07-19T17:30:52.522444.parquet
      • **/details_harness|hendrycksTest-international_law|5_2023-07-19T17:30:52.522444.parquet
      • **/details_harness|hendrycksTest-jurisprudence|5_2023-07-19T17:30:52.522444.parquet
      • **/details_harness|hendrycksTest-logical_fallacies|5_2023-07-19T17:30:52.522444.parquet
      • **/details_harness|hendrycksTest-machine_learning|5_2023-07-19T17:30:52.522444.parquet
      • **/details_harness|hendrycksTest-management|5_2023-07-19T17:30:52.522444.parquet
      • **/details_harness|hendrycksTest-marketing|5_2023-07-19T17:30:52.522444.parquet
      • **/details_harness|hendrycksTest-medical_genetics|5_2023-07-19T17:30:52.522444.parquet
      • **/details_harness|hendrycksTest-miscellaneous|5_2023-07-19T17:30:52.522444.parquet
      • **/details_harness|hendrycksTest-moral_disputes|5_2023-07-19T17:30:52.522444.parquet
      • **/details_harness|hendrycksTest-moral_scenarios|5_2023-07-19T17:30:52.522444.parquet
      • **/details_harness|hendrycksTest-nutrition|5_2023-07-19T17:30:52.522444.parquet
      • **/details_harness|hendrycksTest-philosophy|5_2023-07-19T17:30:52.522444.parquet
      • **/details_harness|hendrycksTest-prehistory|5_2023-07-19T17:30:52.522444.parquet
      • **/details_harness|hendrycksTest-professional_accounting|5_2023-07-19T17:30:52.522444.parquet
      • **/details_harness|hendrycksTest-professional_law|5_2023-07-19T17:30:52.522444.parquet
      • `
搜集汇总
数据集介绍
main_image_url
构建方式
该数据集是Open LLM Leaderboard对togethercomputer/RedPajama-INCITE-7B-Chat模型进行自动评估过程中生成的产物。数据集构建过程围绕模型在多个标准化基准任务上的性能评测展开,共包含64个配置项,每个配置对应一项被评估的特定任务,例如ARC挑战、DROP、GSM8K、HellaSwag、Winogrande以及涵盖57个学科的Hendrycks测试集。评估结果以Parquet格式存储,每个运行记录对应一个独立的数据分割,并以运行时间戳命名,而'train'分割则始终指向最新的评估结果。此外,数据集还包含一个名为'results'的额外配置,用于汇总所有运行的综合指标,这些汇总数据被用于在Open LLM Leaderboard上计算和展示聚合度量。
使用方法
用户可通过HuggingFace的datasets库便捷地加载该数据集。具体而言,调用load_dataset函数,并指定数据集名称'open-llm-leaderboard/details_togethercomputer__RedPajama-INCITE-7B-Chat'以及目标任务的配置名称,例如'harness_winogrande_5',即可获取对应任务的评估详情。通过设置split参数为'train',用户能直接访问最新的评估结果。若需回溯特定历史运行,则可将split设置为对应的时间戳字符串,如'2023_10_19T02_47_12.906889',从而加载该次运行的详细数据。这一设计使得研究人员能够灵活地复现历史评估或进行纵向的性能分析。
背景与挑战
背景概述
随着大规模语言模型(LLM)的蓬勃发展,如何系统性地评估其多维度能力成为自然语言处理领域的核心议题。Open LLM Leaderboard应运而生,由Hugging Face团队主导,旨在为社区提供一个标准化、透明化的模型评测平台。该数据集是针对Together公司开发的RedPajama-INCITE-7B-Chat对话模型在排行榜上的自动评估记录,创建于2023年7月至10月期间,涵盖了从常识推理到数学求解的多个任务。作为开源社区推动LLM性能竞赛的关键纽带,该数据集通过对模型在ARC、HellaSwag、MMLU等基准上的表现进行细粒度追踪,不仅为研究者提供了可复现的对比基准,更推动了对话系统在知识理解与逻辑推理方面的进步,对构建更可靠、更可解释的AI系统具有深远影响。
当前挑战
该数据集面临的核心挑战在于如何公正且全面地反映模型能力。在领域问题层面,LLM评估需应对任务多样性带来的复杂性,例如Winogrande测试中的常识推理与GSM8K中的数学逻辑要求截然不同,单一指标难以刻画模型的真实水平。同时,数据集构建过程中遭遇了技术性挑战:评估需在64个配置中协调不同任务的采样策略与评分标准,确保结果的可比性;此外,多次运行产生的时序数据(如2023年7月与10月的两次评估)需妥善管理,以支持历史对比与趋势分析,而数据格式的标准化(如Parquet文件与JSON结果的转换)也增加了工程实现的难度,这对评测系统的鲁棒性与可扩展性提出了严苛要求。
常用场景
经典使用场景
在大型语言模型评估领域,Open LLM Leaderboard上的RedPajama-INCITE-7B-Chat评估数据集为研究者提供了一个标准化的性能测试框架。该数据集整合了ARC挑战、DROP、GSM8K、HellaSwag、Winogrande以及涵盖57个学科的MMLU等多样化任务,使其成为衡量对话式语言模型在常识推理、数学求解、阅读理解与知识掌握等维度综合能力的经典基准。研究者可通过加载各任务配置的详细评估结果,深入分析模型在特定子任务上的表现优劣。
解决学术问题
该数据集有效解决了大语言模型评估中缺乏统一、可复现度量标准的核心学术难题。通过将评估结果以结构化parquet文件形式存储,并支持按时间戳追溯不同运行轮次,它使得研究者能够精准追踪模型迭代过程中的性能演进。数据集提供的准确率、F1分数与精确匹配等细致指标,为客观比较不同模型在零样本或少样本场景下的泛化能力提供了坚实依据,显著推动了评估方法的规范化进程。
实际应用
在实际应用中,该评估数据集为模型选型与部署决策提供了关键参考。开发团队可依据GSM8K上的数学推理得分筛选适用于教育辅导场景的模型,或参考Winogrande上的指代消解表现优化智能客服系统。数据集记录的错误统计与任务细分结果,还能指导工程师针对性地改进模型在特定领域(如医学知识或法律推理)的对话质量,加速从研究到产品的转化周期。
数据集最近研究
最新研究方向
在大型语言模型评估领域,RedPajama-INCITE-7B-Chat作为开源对话模型,其性能评测正成为研究热点。该数据集依托Open LLM Leaderboard平台,通过涵盖ARC挑战、DROP、GSM8K、HellaSwag及MMLU等多样化基准任务,系统性地揭示了模型在常识推理、数学求解与知识理解等方面的能力边界。当前前沿方向聚焦于利用此类细粒度评估数据,推动模型在少样本学习与复杂推理场景下的鲁棒性提升,同时为开源社区提供可复现的标准化评测范式。这一研究方向不仅加速了对话AI的透明化发展,更通过公开排行榜机制激发了全球研究者对模型短板(如低准确率)的针对性优化,具有推动大模型民主化与可信赖AI落地的深远意义。
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