遇见数据集

open-llm-leaderboard/details_PocketDoc__Dans-TotSirocco-7b

收藏
Hugging Face2023-10-29 更新2024-03-04 收录
官方服务:

资源简介:

--- pretty_name: Evaluation run of PocketDoc/Dans-TotSirocco-7b dataset_summary: "Dataset automatically created during the evaluation run of model\ \ [PocketDoc/Dans-TotSirocco-7b](https://huggingface.co/PocketDoc/Dans-TotSirocco-7b)\ \ 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 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_PocketDoc__Dans-TotSirocco-7b\"\ ,\n\t\"harness_winogrande_5\",\n\tsplit=\"train\")\n```\n\n## Latest results\n\n\ These are the [latest results from run 2023-10-23T12:54:48.005243](https://huggingface.co/datasets/open-llm-leaderboard/details_PocketDoc__Dans-TotSirocco-7b/blob/main/results_2023-10-23T12-54-48.005243.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\": 0.44997902684563756,\n\ \ \"em_stderr\": 0.00509477973209699,\n \"f1\": 0.49544777684563845,\n\ \ \"f1_stderr\": 0.00490923385938236,\n \"acc\": 0.45978722729484023,\n\ \ \"acc_stderr\": 0.01042644341108249\n },\n \"harness|drop|3\": {\n\ \ \"em\": 0.44997902684563756,\n \"em_stderr\": 0.00509477973209699,\n\ \ \"f1\": 0.49544777684563845,\n \"f1_stderr\": 0.00490923385938236\n\ \ },\n \"harness|gsm8k|5\": {\n \"acc\": 0.1326762699014405,\n \ \ \"acc_stderr\": 0.009343929131442216\n },\n \"harness|winogrande|5\"\ : {\n \"acc\": 0.7868981846882399,\n \"acc_stderr\": 0.011508957690722764\n\ \ }\n}\n```" repo_url: https://huggingface.co/PocketDoc/Dans-TotSirocco-7b 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_10_09T23_41_30.846721 path: - '**/details_harness|arc:challenge|25_2023-10-09T23-41-30.846721.parquet' - split: 2023_10_10T03_08_42.670420 path: - '**/details_harness|arc:challenge|25_2023-10-10T03-08-42.670420.parquet' - split: latest path: - '**/details_harness|arc:challenge|25_2023-10-10T03-08-42.670420.parquet' - config_name: harness_drop_3 data_files: - split: 2023_10_23T12_54_48.005243 path: - '**/details_harness|drop|3_2023-10-23T12-54-48.005243.parquet' - split: latest path: - '**/details_harness|drop|3_2023-10-23T12-54-48.005243.parquet' - config_name: harness_gsm8k_5 data_files: - split: 2023_10_23T12_54_48.005243 path: - '**/details_harness|gsm8k|5_2023-10-23T12-54-48.005243.parquet' - split: latest path: - '**/details_harness|gsm8k|5_2023-10-23T12-54-48.005243.parquet' - config_name: harness_hellaswag_10 data_files: - split: 2023_10_09T23_41_30.846721 path: - '**/details_harness|hellaswag|10_2023-10-09T23-41-30.846721.parquet' - split: 2023_10_10T03_08_42.670420 path: - '**/details_harness|hellaswag|10_2023-10-10T03-08-42.670420.parquet' - split: latest path: - '**/details_harness|hellaswag|10_2023-10-10T03-08-42.670420.parquet' - config_name: harness_hendrycksTest_5 data_files: - split: 2023_10_09T23_41_30.846721 path: - '**/details_harness|hendrycksTest-abstract_algebra|5_2023-10-09T23-41-30.846721.parquet' - '**/details_harness|hendrycksTest-anatomy|5_2023-10-09T23-41-30.846721.parquet' - '**/details_harness|hendrycksTest-astronomy|5_2023-10-09T23-41-30.846721.parquet' - '**/details_harness|hendrycksTest-business_ethics|5_2023-10-09T23-41-30.846721.parquet' - '**/details_harness|hendrycksTest-clinical_knowledge|5_2023-10-09T23-41-30.846721.parquet' - '**/details_harness|hendrycksTest-college_biology|5_2023-10-09T23-41-30.846721.parquet' - '**/details_harness|hendrycksTest-college_chemistry|5_2023-10-09T23-41-30.846721.parquet' - '**/details_harness|hendrycksTest-college_computer_science|5_2023-10-09T23-41-30.846721.parquet' - '**/details_harness|hendrycksTest-college_mathematics|5_2023-10-09T23-41-30.846721.parquet' - '**/details_harness|hendrycksTest-college_medicine|5_2023-10-09T23-41-30.846721.parquet' - '**/details_harness|hendrycksTest-college_physics|5_2023-10-09T23-41-30.846721.parquet' - '**/details_harness|hendrycksTest-computer_security|5_2023-10-09T23-41-30.846721.parquet' - '**/details_harness|hendrycksTest-conceptual_physics|5_2023-10-09T23-41-30.846721.parquet' - '**/details_harness|hendrycksTest-econometrics|5_2023-10-09T23-41-30.846721.parquet' - '**/details_harness|hendrycksTest-electrical_engineering|5_2023-10-09T23-41-30.846721.parquet' - '**/details_harness|hendrycksTest-elementary_mathematics|5_2023-10-09T23-41-30.846721.parquet' - '**/details_harness|hendrycksTest-formal_logic|5_2023-10-09T23-41-30.846721.parquet' - '**/details_harness|hendrycksTest-global_facts|5_2023-10-09T23-41-30.846721.parquet' - '**/details_harness|hendrycksTest-high_school_biology|5_2023-10-09T23-41-30.846721.parquet' - '**/details_harness|hendrycksTest-high_school_chemistry|5_2023-10-09T23-41-30.846721.parquet' - '**/details_harness|hendrycksTest-high_school_computer_science|5_2023-10-09T23-41-30.846721.parquet' - '**/details_harness|hendrycksTest-high_school_european_history|5_2023-10-09T23-41-30.846721.parquet' - '**/details_harness|hendrycksTest-high_school_geography|5_2023-10-09T23-41-30.846721.parquet' - '**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-10-09T23-41-30.846721.parquet' - '**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-10-09T23-41-30.846721.parquet' - '**/details_harness|hendrycksTest-high_school_mathematics|5_2023-10-09T23-41-30.846721.parquet' - '**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-10-09T23-41-30.846721.parquet' - '**/details_harness|hendrycksTest-high_school_physics|5_2023-10-09T23-41-30.846721.parquet' - '**/details_harness|hendrycksTest-high_school_psychology|5_2023-10-09T23-41-30.846721.parquet' - '**/details_harness|hendrycksTest-high_school_statistics|5_2023-10-09T23-41-30.846721.parquet' - '**/details_harness|hendrycksTest-high_school_us_history|5_2023-10-09T23-41-30.846721.parquet' - '**/details_harness|hendrycksTest-high_school_world_history|5_2023-10-09T23-41-30.846721.parquet' - '**/details_harness|hendrycksTest-human_aging|5_2023-10-09T23-41-30.846721.parquet' - '**/details_harness|hendrycksTest-human_sexuality|5_2023-10-09T23-41-30.846721.parquet' - '**/details_harness|hendrycksTest-international_law|5_2023-10-09T23-41-30.846721.parquet' - '**/details_harness|hendrycksTest-jurisprudence|5_2023-10-09T23-41-30.846721.parquet' - '**/details_harness|hendrycksTest-logical_fallacies|5_2023-10-09T23-41-30.846721.parquet' - '**/details_harness|hendrycksTest-machine_learning|5_2023-10-09T23-41-30.846721.parquet' - '**/details_harness|hendrycksTest-management|5_2023-10-09T23-41-30.846721.parquet' - '**/details_harness|hendrycksTest-marketing|5_2023-10-09T23-41-30.846721.parquet' - '**/details_harness|hendrycksTest-medical_genetics|5_2023-10-09T23-41-30.846721.parquet' - '**/details_harness|hendrycksTest-miscellaneous|5_2023-10-09T23-41-30.846721.parquet' - '**/details_harness|hendrycksTest-moral_disputes|5_2023-10-09T23-41-30.846721.parquet' - '**/details_harness|hendrycksTest-moral_scenarios|5_2023-10-09T23-41-30.846721.parquet' - '**/details_harness|hendrycksTest-nutrition|5_2023-10-09T23-41-30.846721.parquet' - '**/details_harness|hendrycksTest-philosophy|5_2023-10-09T23-41-30.846721.parquet' - '**/details_harness|hendrycksTest-prehistory|5_2023-10-09T23-41-30.846721.parquet' - '**/details_harness|hendrycksTest-professional_accounting|5_2023-10-09T23-41-30.846721.parquet' - '**/details_harness|hendrycksTest-professional_law|5_2023-10-09T23-41-30.846721.parquet' - '**/details_harness|hendrycksTest-professional_medicine|5_2023-10-09T23-41-30.846721.parquet' - '**/details_harness|hendrycksTest-professional_psychology|5_2023-10-09T23-41-30.846721.parquet' - '**/details_harness|hendrycksTest-public_relations|5_2023-10-09T23-41-30.846721.parquet' - '**/details_harness|hendrycksTest-security_studies|5_2023-10-09T23-41-30.846721.parquet' - '**/details_harness|hendrycksTest-sociology|5_2023-10-09T23-41-30.846721.parquet' - '**/details_harness|hendrycksTest-us_foreign_policy|5_2023-10-09T23-41-30.846721.parquet' - '**/details_harness|hendrycksTest-virology|5_2023-10-09T23-41-30.846721.parquet' - '**/details_harness|hendrycksTest-world_religions|5_2023-10-09T23-41-30.846721.parquet' - split: 2023_10_10T03_08_42.670420 path: - '**/details_harness|hendrycksTest-abstract_algebra|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-anatomy|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-astronomy|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-business_ethics|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-clinical_knowledge|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-college_biology|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-college_chemistry|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-college_computer_science|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-college_mathematics|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-college_medicine|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-college_physics|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-computer_security|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-conceptual_physics|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-econometrics|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-electrical_engineering|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-elementary_mathematics|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-formal_logic|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-global_facts|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-high_school_biology|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-high_school_chemistry|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-high_school_computer_science|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-high_school_european_history|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-high_school_geography|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-high_school_mathematics|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-high_school_physics|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-high_school_psychology|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-high_school_statistics|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-high_school_us_history|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-high_school_world_history|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-human_aging|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-human_sexuality|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-international_law|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-jurisprudence|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-logical_fallacies|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-machine_learning|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-management|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-marketing|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-medical_genetics|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-miscellaneous|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-moral_disputes|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-moral_scenarios|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-nutrition|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-philosophy|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-prehistory|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-professional_accounting|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-professional_law|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-professional_medicine|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-professional_psychology|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-public_relations|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-security_studies|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-sociology|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-us_foreign_policy|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-virology|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-world_religions|5_2023-10-10T03-08-42.670420.parquet' - split: latest path: - '**/details_harness|hendrycksTest-abstract_algebra|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-anatomy|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-astronomy|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-business_ethics|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-clinical_knowledge|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-college_biology|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-college_chemistry|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-college_computer_science|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-college_mathematics|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-college_medicine|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-college_physics|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-computer_security|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-conceptual_physics|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-econometrics|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-electrical_engineering|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-elementary_mathematics|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-formal_logic|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-global_facts|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-high_school_biology|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-high_school_chemistry|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-high_school_computer_science|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-high_school_european_history|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-high_school_geography|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-high_school_mathematics|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-high_school_physics|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-high_school_psychology|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-high_school_statistics|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-high_school_us_history|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-high_school_world_history|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-human_aging|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-human_sexuality|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-international_law|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-jurisprudence|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-logical_fallacies|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-machine_learning|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-management|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-marketing|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-medical_genetics|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-miscellaneous|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-moral_disputes|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-moral_scenarios|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-nutrition|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-philosophy|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-prehistory|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-professional_accounting|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-professional_law|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-professional_medicine|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-professional_psychology|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-public_relations|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-security_studies|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-sociology|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-us_foreign_policy|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-virology|5_2023-10-10T03-08-42.670420.parquet' - '**/details_harness|hendrycksTest-world_religions|5_2023-10-10T03-08-42.670420.parquet' - config_name: harness_hendrycksTest_abstract_algebra_5 data_files: - split: 2023_10_09T23_41_30.846721 path: - '**/details_harness|hendrycksTest-abstract_algebra|5_2023-10-09T23-41-30.846721.parquet' - split: 2023_10_10T03_08_42.670420 path: - '**/details_harness|hendrycksTest-abstract_algebra|5_2023-10-10T03-08-42.670420.parquet' - split: latest path: - '**/details_harness|hendrycksTest-abstract_algebra|5_2023-10-10T03-08-42.670420.parquet' - config_name: harness_hendrycksTest_anatomy_5 data_files: - split: 2023_10_09T23_41_30.846721 path: - '**/details_harness|hendrycksTest-anatomy|5_2023-10-09T23-41-30.846721.parquet' - split: 2023_10_10T03_08_42.670420 path: - '**/details_harness|hendrycksTest-anatomy|5_2023-10-10T03-08-42.670420.parquet' - split: latest path: - '**/details_harness|hendrycksTest-anatomy|5_2023-10-10T03-08-42.670420.parquet' - config_name: harness_hendrycksTest_astronomy_5 data_files: - split: 2023_10_09T23_41_30.846721 path: - '**/details_harness|hendrycksTest-astronomy|5_2023-10-09T23-41-30.846721.parquet' - split: 2023_10_10T03_08_42.670420 path: - '**/details_harness|hendrycksTest-astronomy|5_2023-10-10T03-08-42.670420.parquet' - split: latest path: - '**/details_harness|hendrycksTest-astronomy|5_2023-10-10T03-08-42.670420.parquet' - config_name: harness_hendrycksTest_business_ethics_5 data_files: - split: 2023_10_09T23_41_30.846721 path: - '**/details_harness|hendrycksTest-business_ethics|5_2023-10-09T23-41-30.846721.parquet' - split: 2023_10_10T03_08_42.670420 path: - '**/details_harness|hendrycksTest-business_ethics|5_2023-10-10T03-08-42.670420.parquet' - split: latest path: - '**/details_harness|hendrycksTest-business_ethics|5_2023-10-10T03-08-42.670420.parquet' - config_name: harness_hendrycksTest_clinical_knowledge_5 data_files: - split: 2023_10_09T23_41_30.846721 path: - '**/details_harness|hendrycksTest-clinical_knowledge|5_2023-10-09T23-41-30.846721.parquet' - split: 2023_10_10T03_08_42.670420 path: - '**/details_harness|hendrycksTest-clinical_knowledge|5_2023-10-10T03-08-42.670420.parquet' - split: latest path: - '**/details_harness|hendrycksTest-clinical_knowledge|5_2023-10-10T03-08-42.670420.parquet' - config_name: harness_hendrycksTest_college_biology_5 data_files: - split: 2023_10_09T23_41_30.846721 path: - '**/details_harness|hendrycksTest-college_biology|5_2023-10-09T23-41-30.846721.parquet' - split: 2023_10_10T03_08_42.670420 path: - '**/details_harness|hendrycksTest-college_biology|5_2023-10-10T03-08-42.670420.parquet' - split: latest path: - '**/details_harness|hendrycksTest-college_biology|5_2023-10-10T03-08-42.670420.parquet' - config_name: harness_hendrycksTest_college_chemistry_5 data_files: - split: 2023_10_09T23_41_30.846721 path: - '**/details_harness|hendrycksTest-college_chemistry|5_2023-10-09T23-41-30.846721.parquet' - split: 2023_10_10T03_08_42.670420 path: - '**/details_harness|hendrycksTest-college_chemistry|5_2023-10-10T03-08-42.670420.parquet' - split: latest path: - '**/details_harness|hendrycksTest-college_chemistry|5_2023-10-10T03-08-42.670420.parquet' - config_name: harness_hendrycksTest_college_computer_science_5 data_files: - split: 2023_10_09T23_41_30.846721 path: - '**/details_harness|hendrycksTest-college_computer_science|5_2023-10-09T23-41-30.846721.parquet' - split: 2023_10_10T03_08_42.670420 path: - '**/details_harness|hendrycksTest-college_computer_science|5_2023-10-10T03-08-42.670420.parquet' - split: latest path: - '**/details_harness|hendrycksTest-college_computer_science|5_2023-10-10T03-08-42.670420.parquet' - config_name: harness_hendrycksTest_college_mathematics_5 data_files: - split: 2023_10_09T23_41_30.846721 path: - '**/details_harness|hendrycksTest-college_mathematics|5_2023-10-09T23-41-30.846721.parquet' - split: 2023_10_10T03_08_42.670420 path: - '**/details_harness|hendrycksTest-college_mathematics|5_2023-10-10T03-08-42.670420.parquet' - split: latest path: - '**/details_harness|hendrycksTest-college_mathematics|5_2023-10-10T03-08-42.670420.parquet' - config_name: harness_hendrycksTest_college_medicine_5 data_files: - split: 2023_10_09T23_41_30.846721 path: - '**/details_harness|hendrycksTest-college_medicine|5_2023-10-09T23-41-30.846721.parquet' - split: 2023_10_10T03_08_42.670420 path: - '**/details_harness|hendrycksTest-college_medicine|5_2023-10-10T03-08-42.670420.parquet' - split: latest path: - '**/details_harness|hendrycksTest-college_medicine|5_2023-10-10T03-08-42.670420.parquet' - config_name: harness_hendrycksTest_college_physics_5 data_files: - split: 2023_10_09T23_41_30.846721 path: - '**/details_harness|hendrycksTest-college_physics|5_2023-10-09T23-41-30.846721.parquet' - split: 2023_10_10T03_08_42.670420 path: - '**/details_harness|hendrycksTest-college_physics|5_2023-10-10T03-08-42.670420.parquet' - split: latest path: - '**/details_harness|hendrycksTest-college_physics|5_2023-10-10T03-08-42.670420.parquet' - config_name: harness_hendrycksTest_computer_security_5 data_files: - split: 2023_10_09T23_41_30.846721 path: - '**/details_harness|hendrycksTest-computer_security|5_2023-10-09T23-41-30.846721.parquet' - split: 2023_10_10T03_08_42.670420 path: - '**/details_harness|hendrycksTest-computer_security|5_2023-10-10T03-08-42.670420.parquet' - split: latest path: - '**/details_harness|hendrycksTest-computer_security|5_2023-10-10T03-08-42.670420.parquet' - config_name: harness_hendrycksTest_conceptual_physics_5 data_files: - split: 2023_10_09T23_41_30.846721 path: - '**/details_harness|hendrycksTest-conceptual_physics|5_2023-10-09T23-41-30.846721.parquet' - split: 2023_10_10T03_08_42.670420 path: - '**/details_harness|hendrycksTest-conceptual_physics|5_2023-10-10T03-08-42.670420.parquet' - split: latest path: - '**/details_harness|hendrycksTest-conceptual_physics|5_2023-10-10T03-08-42.670420.parquet' - config_name: harness_hendrycksTest_econometrics_5 data_files: - split: 2023_10_09T23_41_30.846721 path: - '**/details_harness|hendrycksTest-econometrics|5_2023-10-09T23-41-30.846721.parquet' - split: 2023_10_10T03_08_42.670420 path: - '**/details_harness|hendrycksTest-econometrics|5_2023-10-10T03-08-42.670420.parquet' - split: latest path: - '**/details_harness|hendrycksTest-econometrics|5_2023-10-10T03-08-42.670420.parquet' - config_name: harness_hendrycksTest_electrical_engineering_5 data_files: - split: 2023_10_09T23_41_30.846721 path: - '**/details_harness|hendrycksTest-electrical_engineering|5_2023-10-09T23-41-30.846721.parquet' - split: 2023_10_10T03_08_42.670420 path: - '**/details_harness|hendrycksTest-electrical_engineering|5_2023-10-10T03-08-42.670420.parquet' - split: latest path: - '**/details_harness|hendrycksTest-electrical_engineering|5_2023-10-10T03-08-42.670420.parquet' - config_name: harness_hendrycksTest_elementary_mathematics_5 data_files: - split: 2023_10_09T23_41_30.846721 path: - '**/details_harness|hendrycksTest-elementary_mathematics|5_2023-10-09T23-41-30.846721.parquet' - split: 2023_10_10T03_08_42.670420 path: - '**/details_harness|hendrycksTest-elementary_mathematics|5_2023-10-10T03-08-42.670420.parquet' - split: latest path: - '**/details_harness|hendrycksTest-elementary_mathematics|5_2023-10-10T03-08-42.670420.parquet' - config_name: harness_hendrycksTest_formal_logic_5 data_files: - split: 2023_10_09T23_41_30.846721 path: - '**/details_harness|hendrycksTest-formal_logic|5_2023-10-09T23-41-30.846721.parquet' - split: 2023_10_10T03_08_42.670420 path: - '**/details_harness|hendrycksTest-formal_logic|5_2023-10-10T03-08-42.670420.parquet' - split: latest path: - '**/details_harness|hendrycksTest-formal_logic|5_2023-10-10T03-08-42.670420.parquet' - config_name: harness_hendrycksTest_global_facts_5 data_files: - split: 2023_10_09T23_41_30.846721 path: - '**/details_harness|hendrycksTest-global_facts|5_2023-10-09T23-41-30.846721.parquet' - split: 2023_10_10T03_08_42.670420 path: - '**/details_harness|hendrycksTest-global_facts|5_2023-10-10T03-08-42.670420.parquet' - split: latest path: - '**/details_harness|hendrycksTest-global_facts|5_2023-10-10T03-08-42.670420.parquet' - config_name: harness_hendrycksTest_high_school_biology_5 data_files: - split: 2023_10_09T23_41_30.846721 path: - '**/details_harness|hendrycksTest-high_school_biology|5_2023-10-09T23-41-30.846721.parquet' - split: 2023_10_10T03_08_42.670420 path: - '**/details_harness|hendrycksTest-high_school_biology|5_2023-10-10T03-08-42.670420.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_biology|5_2023-10-10T03-08-42.670420.parquet' - config_name: harness_hendrycksTest_high_school_chemistry_5 data_files: - split: 2023_10_09T23_41_30.846721 path: - '**/details_harness|hendrycksTest-high_school_chemistry|5_2023-10-09T23-41-30.846721.parquet' - split: 2023_10_10T03_08_42.670420 path: - '**/details_harness|hendrycksTest-high_school_chemistry|5_2023-10-10T03-08-42.670420.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_chemistry|5_2023-10-10T03-08-42.670420.parquet' - config_name: harness_hendrycksTest_high_school_computer_science_5 data_files: - split: 2023_10_09T23_41_30.846721 path: - '**/details_harness|hendrycksTest-high_school_computer_science|5_2023-10-09T23-41-30.846721.parquet' - split: 2023_10_10T03_08_42.670420 path: - '**/details_harness|hendrycksTest-high_school_computer_science|5_2023-10-10T03-08-42.670420.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_computer_science|5_2023-10-10T03-08-42.670420.parquet' - config_name: harness_hendrycksTest_high_school_european_history_5 data_files: - split: 2023_10_09T23_41_30.846721 path: - '**/details_harness|hendrycksTest-high_school_european_history|5_2023-10-09T23-41-30.846721.parquet' - split: 2023_10_10T03_08_42.670420 path: - '**/details_harness|hendrycksTest-high_school_european_history|5_2023-10-10T03-08-42.670420.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_european_history|5_2023-10-10T03-08-42.670420.parquet' - config_name: harness_hendrycksTest_high_school_geography_5 data_files: - split: 2023_10_09T23_41_30.846721 path: - '**/details_harness|hendrycksTest-high_school_geography|5_2023-10-09T23-41-30.846721.parquet' - split: 2023_10_10T03_08_42.670420 path: - '**/details_harness|hendrycksTest-high_school_geography|5_2023-10-10T03-08-42.670420.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_geography|5_2023-10-10T03-08-42.670420.parquet' - config_name: harness_hendrycksTest_high_school_government_and_politics_5 data_files: - split: 2023_10_09T23_41_30.846721 path: - '**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-10-09T23-41-30.846721.parquet' - split: 2023_10_10T03_08_42.670420 path: - '**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-10-10T03-08-42.670420.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-10-10T03-08-42.670420.parquet' - config_name: harness_hendrycksTest_high_school_macroeconomics_5 data_files: - split: 2023_10_09T23_41_30.846721 path: - '**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-10-09T23-41-30.846721.parquet' - split: 2023_10_10T03_08_42.670420 path: - '**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-10-10T03-08-42.670420.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-10-10T03-08-42.670420.parquet' - config_name: harness_hendrycksTest_high_school_mathematics_5 data_files: - split: 2023_10_09T23_41_30.846721 path: - '**/details_harness|hendrycksTest-high_school_mathematics|5_2023-10-09T23-41-30.846721.parquet' - split: 2023_10_10T03_08_42.670420 path: - '**/details_harness|hendrycksTest-high_school_mathematics|5_2023-10-10T03-08-42.670420.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_mathematics|5_2023-10-10T03-08-42.670420.parquet' - config_name: harness_hendrycksTest_high_school_microeconomics_5 data_files: - split: 2023_10_09T23_41_30.846721 path: - '**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-10-09T23-41-30.846721.parquet' - split: 2023_10_10T03_08_42.670420 path: - '**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-10-10T03-08-42.670420.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-10-10T03-08-42.670420.parquet' - config_name: harness_hendrycksTest_high_school_physics_5 data_files: - split: 2023_10_09T23_41_30.846721 path: - '**/details_harness|hendrycksTest-high_school_physics|5_2023-10-09T23-41-30.846721.parquet' - split: 2023_10_10T03_08_42.670420 path: - '**/details_harness|hendrycksTest-high_school_physics|5_2023-10-10T03-08-42.670420.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_physics|5_2023-10-10T03-08-42.670420.parquet' - config_name: harness_hendrycksTest_high_school_psychology_5 data_files: - split: 2023_10_09T23_41_30.846721 path: - '**/details_harness|hendrycksTest-high_school_psychology|5_2023-10-09T23-41-30.846721.parquet' - split: 2023_10_10T03_08_42.670420 path: - '**/details_harness|hendrycksTest-high_school_psychology|5_2023-10-10T03-08-42.670420.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_psychology|5_2023-10-10T03-08-42.670420.parquet' - config_name: harness_hendrycksTest_high_school_statistics_5 data_files: - split: 2023_10_09T23_41_30.846721 path: - '**/details_harness|hendrycksTest-high_school_statistics|5_2023-10-09T23-41-30.846721.parquet' - split: 2023_10_10T03_08_42.670420 path: - '**/details_harness|hendrycksTest-high_school_statistics|5_2023-10-10T03-08-42.670420.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_statistics|5_2023-10-10T03-08-42.670420.parquet' - config_name: harness_hendrycksTest_high_school_us_history_5 data_files: - split: 2023_10_09T23_41_30.846721 path: - '**/details_harness|hendrycksTest-high_school_us_history|5_2023-10-09T23-41-30.846721.parquet' - split: 2023_10_10T03_08_42.670420 path: - '**/details_harness|hendrycksTest-high_school_us_history|5_2023-10-10T03-08-42.670420.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_us_history|5_2023-10-10T03-08-42.670420.parquet' - config_name: harness_hendrycksTest_high_school_world_history_5 data_files: - split: 2023_10_09T23_41_30.846721 path: - '**/details_harness|hendrycksTest-high_school_world_history|5_2023-10-09T23-41-30.846721.parquet' - split: 2023_10_10T03_08_42.670420 path: - '**/details_harness|hendrycksTest-high_school_world_history|5_2023-10-10T03-08-42.670420.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_world_history|5_2023-10-10T03-08-42.670420.parquet' - config_name: harness_hendrycksTest_human_aging_5 data_files: - split: 2023_10_09T23_41_30.846721 path: - '**/details_harness|hendrycksTest-human_aging|5_2023-10-09T23-41-30.846721.parquet' - split: 2023_10_10T03_08_42.670420 path: - '**/details_harness|hendrycksTest-human_aging|5_2023-10-10T03-08-42.670420.parquet' - split: latest path: - '**/details_harness|hendrycksTest-human_aging|5_2023-10-10T03-08-42.670420.parquet' - config_name: harness_hendrycksTest_human_sexuality_5 data_files: - split: 2023_10_09T23_41_30.846721 path: - '**/details_harness|hendrycksTest-human_sexuality|5_2023-10-09T23-41-30.846721.parquet' - split: 2023_10_10T03_08_42.670420 path: - '**/details_harness|hendrycksTest-human_sexuality|5_2023-10-10T03-08-42.670420.parquet' - split: latest path: - '**/details_harness|hendrycksTest-human_sexuality|5_2023-10-10T03-08-42.670420.parquet' - config_name: harness_hendrycksTest_international_law_5 data_files: - split: 2023_10_09T23_41_30.846721 path: - '**/details_harness|hendrycksTest-international_law|5_2023-10-09T23-41-30.846721.parquet' - split: 2023_10_10T03_08_42.670420 path: - '**/details_harness|hendrycksTest-international_law|5_2023-10-10T03-08-42.670420.parquet' - split: latest path: - '**/details_harness|hendrycksTest-international_law|5_2023-10-10T03-08-42.670420.parquet' - config_name: harness_hendrycksTest_jurisprudence_5 data_files: - split: 2023_10_09T23_41_30.846721 path: - '**/details_harness|hendrycksTest-jurisprudence|5_2023-10-09T23-41-30.846721.parquet' - split: 2023_10_10T03_08_42.670420 path: - '**/details_harness|hendrycksTest-jurisprudence|5_2023-10-10T03-08-42.670420.parquet' - split: latest path: - '**/details_harness|hendrycksTest-jurisprudence|5_2023-10-10T03-08-42.670420.parquet' - config_name: harness_hendrycksTest_logical_fallacies_5 data_files: - split: 2023_10_09T23_41_30.846721 path: - '**/details_harness|hendrycksTest-logical_fallacies|5_2023-10-09T23-41-30.846721.parquet' - split: 2023_10_10T03_08_42.670420 path: - '**/details_harness|hendrycksTest-logical_fallacies|5_2023-10-10T03-08-42.670420.parquet' - split: latest path: - '**/details_harness|hendrycksTest-logical_fallacies|5_2023-10-10T03-08-42.670420.parquet' - config_name: harness_hendrycksTest_machine_learning_5 data_files: - split: 2023_10_09T23_41_30.846721 path: - '**/details_harness|hendrycksTest-machine_learning|5_2023-10-09T23-41-30.846721.parquet' - split: 2023_10_10T03_08_42.670420 path: - '**/details_harness|hendrycksTest-machine_learning|5_2023-10-10T03-08-42.670420.parquet' - split: latest path: - '**/details_harness|hendrycksTest-machine_learning|5_2023-10-10T03-08-42.670420.parquet' - config_name: harness_hendrycksTest_management_5 data_files: - split: 2023_10_09T23_41_30.846721 path: - '**/details_harness|hendrycksTest-management|5_2023-10-09T23-41-30.846721.parquet' - split: 2023_10_10T03_08_42.670420 path: - '**/details_harness|hendrycksTest-management|5_2023-10-10T03-08-42.670420.parquet' - split: latest path: - '**/details_harness|hendrycksTest-management|5_2023-10-10T03-08-42.670420.parquet' - config_name: harness_hendrycksTest_marketing_5 data_files: - split: 2023_10_09T23_41_30.846721 path: - '**/details_harness|hendrycksTest-marketing|5_2023-10-09T23-41-30.846721.parquet' - split: 2023_10_10T03_08_42.670420 path: - '**/details_harness|hendrycksTest-marketing|5_2023-10-10T03-08-42.670420.parquet' - split: latest path: - '**/details_harness|hendrycksTest-marketing|5_2023-10-10T03-08-42.670420.parquet' - config_name: harness_hendrycksTest_medical_genetics_5 data_files: - split: 2023_10_09T23_41_30.846721 path: - '**/details_harness|hendrycksTest-medical_genetics|5_2023-10-09T23-41-30.846721.parquet' - split: 2023_10_10T03_08_42.670420 path: - '**/details_harness|hendrycksTest-medical_genetics|5_2023-10-10T03-08-42.670420.parquet' - split: latest path: - '**/details_harness|hendrycksTest-medical_genetics|5_2023-10-10T03-08-42.670420.parquet' - config_name: harness_hendrycksTest_miscellaneous_5 data_files: - split: 2023_10_09T23_41_30.846721 path: - '**/details_harness|hendrycksTest-miscellaneous|5_2023-10-09T23-41-30.846721.parquet' - split: 2023_10_10T03_08_42.670420 path: - '**/details_harness|hendrycksTest-miscellaneous|5_2023-10-10T03-08-42.670420.parquet' - split: latest path: - '**/details_harness|hendrycksTest-miscellaneous|5_2023-10-10T03-08-42.670420.parquet' - config_name: harness_hendrycksTest_moral_disputes_5 data_files: - split: 2023_10_09T23_41_30.846721 path: - '**/details_harness|hendrycksTest-moral_disputes|5_2023-10-09T23-41-30.846721.parquet' - split: 2023_10_10T03_08_42.670420 path: - '**/details_harness|hendrycksTest-moral_disputes|5_2023-10-10T03-08-42.670420.parquet' - split: latest path: - '**/details_harness|hendrycksTest-moral_disputes|5_2023-10-10T03-08-42.670420.parquet' - config_name: harness_hendrycksTest_moral_scenarios_5 data_files: - split: 2023_10_09T23_41_30.846721 path: - '**/details_harness|hendrycksTest-moral_scenarios|5_2023-10-09T23-41-30.846721.parquet' - split: 2023_10_10T03_08_42.670420 path: - '**/details_harness|hendrycksTest-moral_scenarios|5_2023-10-10T03-08-42.670420.parquet' - split: latest path: - '**/details_harness|hendrycksTest-moral_scenarios|5_2023-10-10T03-08-42.670420.parquet' - config_name: harness_hendrycksTest_nutrition_5 data_files: - split: 2023_10_09T23_41_30.846721 path: - '**/details_harness|hendrycksTest-nutrition|5_2023-10-09T23-41-30.846721.parquet' - split: 2023_10_10T03_08_42.670420 path: - '**/details_harness|hendrycksTest-nutrition|5_2023-10-10T03-08-42.670420.parquet' - split: latest path: - '**/details_harness|hendrycksTest-nutrition|5_2023-10-10T03-08-42.670420.parquet' - config_name: harness_hendrycksTest_philosophy_5 data_files: - split: 2023_10_09T23_41_30.846721 path: - '**/details_harness|hendrycksTest-philosophy|5_2023-10-09T23-41-30.846721.parquet' - split: 2023_10_10T03_08_42.670420 path: - '**/details_harness|hendrycksTest-philosophy|5_2023-10-10T03-08-42.670420.parquet' - split: latest path: - '**/details_harness|hendrycksTest-philosophy|5_2023-10-10T03-08-42.670420.parquet' - config_name: harness_hendrycksTest_prehistory_5 data_files: - split: 2023_10_09T23_41_30.846721 path: - '**/details_harness|hendrycksTest-prehistory|5_2023-10-09T23-41-30.846721.parquet' - split: 2023_10_10T03_08_42.670420 path: - '**/details_harness|hendrycksTest-prehistory|5_2023-10-10T03-08-42.670420.parquet' - split: latest path: - '**/details_harness|hendrycksTest-prehistory|5_2023-10-10T03-08-42.670420.parquet' - config_name: harness_hendrycksTest_professional_accounting_5 data_files: - split: 2023_10_09T23_41_30.846721 path: - '**/details_harness|hendrycksTest-professional_accounting|5_2023-10-09T23-41-30.846721.parquet' - split: 2023_10_10T03_08_42.670420 path: - '**/details_harness|hendrycksTest-professional_accounting|5_2023-10-10T03-08-42.670420.parquet' - split: latest path: - '**/details_harness|hendrycksTest-professional_accounting|5_2023-10-10T03-08-42.670420.parquet' - config_name: harness_hendrycksTest_professional_law_5 data_files: - split: 2023_10_09T23_41_30.846721 path: - '**/details_harness|hendrycksTest-professional_law|5_2023-10-09T23-41-30.846721.parquet' - split: 2023_10_10T03_08_42.670420 path: - '**/details_harness|hendrycksTest-professional_law|5_2023-10-10T03-08-42.670420.parquet' - split: latest path: - '**/details_harness|hendrycksTest-professional_law|5_2023-10-10T03-08-42.670420.parquet' - config_name: harness_hendrycksTest_professional_medicine_5 data_files: - split: 2023_10_09T23_41_30.846721 path: - '**/details_harness|hendrycksTest-professional_medicine|5_2023-10-09T23-41-30.846721.parquet' - split: 2023_10_10T03_08_42.670420 path: - '**/details_harness|hendrycksTest-professional_medicine|5_2023-10-10T03-08-42.670420.parquet' - split: latest path: - '**/details_harness|hendrycksTest-professional_medicine|5_2023-10-10T03-08-42.670420.parquet' - config_name: harness_hendrycksTest_professional_psychology_5 data_files: - split: 2023_10_09T23_41_30.846721 path: - '**/details_harness|hendrycksTest-professional_psychology|5_2023-10-09T23-41-30.846721.parquet' - split: 2023_10_10T03_08_42.670420 path: - '**/details_harness|hendrycksTest-professional_psychology|5_2023-10-10T03-08-42.670420.parquet' - split: latest path: - '**/details_harness|hendrycksTest-professional_psychology|5_2023-10-10T03-08-42.670420.parquet' - config_name: harness_hendrycksTest_public_relations_5 data_files: - split: 2023_10_09T23_41_30.846721 path: - '**/details_harness|hendrycksTest-public_relations|5_2023-10-09T23-41-30.846721.parquet' - split: 2023_10_10T03_08_42.670420 path: - '**/details_harness|hendrycksTest-public_relations|5_2023-10-10T03-08-42.670420.parquet' - split: latest path: - '**/details_harness|hendrycksTest-public_relations|5_2023-10-10T03-08-42.670420.parquet' - config_name: harness_hendrycksTest_security_studies_5 data_files: - split: 2023_10_09T23_41_30.846721 path: - '**/details_harness|hendrycksTest-security_studies|5_2023-10-09T23-41-30.846721.parquet' - split: 2023_10_10T03_08_42.670420 path: - '**/details_harness|hendrycksTest-security_studies|5_2023-10-10T03-08-42.670420.parquet' - split: latest path: - '**/details_harness|hendrycksTest-security_studies|5_2023-10-10T03-08-42.670420.parquet' - config_name: harness_hendrycksTest_sociology_5 data_files: - split: 2023_10_09T23_41_30.846721 path: - '**/details_harness|hendrycksTest-sociology|5_2023-10-09T23-41-30.846721.parquet' - split: 2023_10_10T03_08_42.670420 path: - '**/details_harness|hendrycksTest-sociology|5_2023-10-10T03-08-42.670420.parquet' - split: latest path: - '**/details_harness|hendrycksTest-sociology|5_2023-10-10T03-08-42.670420.parquet' - config_name: harness_hendrycksTest_us_foreign_policy_5 data_files: - split: 2023_10_09T23_41_30.846721 path: - '**/details_harness|hendrycksTest-us_foreign_policy|5_2023-10-09T23-41-30.846721.parquet' - split: 2023_10_10T03_08_42.670420 path: - '**/details_harness|hendrycksTest-us_foreign_policy|5_2023-10-10T03-08-42.670420.parquet' - split: latest path: - '**/details_harness|hendrycksTest-us_foreign_policy|5_2023-10-10T03-08-42.670420.parquet' - config_name: harness_hendrycksTest_virology_5 data_files: - split: 2023_10_09T23_41_30.846721 path: - '**/details_harness|hendrycksTest-virology|5_2023-10-09T23-41-30.846721.parquet' - split: 2023_10_10T03_08_42.670420 path: - '**/details_harness|hendrycksTest-virology|5_2023-10-10T03-08-42.670420.parquet' - split: latest path: - '**/details_harness|hendrycksTest-virology|5_2023-10-10T03-08-42.670420.parquet' - config_name: harness_hendrycksTest_world_religions_5 data_files: - split: 2023_10_09T23_41_30.846721 path: - '**/details_harness|hendrycksTest-world_religions|5_2023-10-09T23-41-30.846721.parquet' - split: 2023_10_10T03_08_42.670420 path: - '**/details_harness|hendrycksTest-world_religions|5_2023-10-10T03-08-42.670420.parquet' - split: latest path: - '**/details_harness|hendrycksTest-world_religions|5_2023-10-10T03-08-42.670420.parquet' - config_name: harness_truthfulqa_mc_0 data_files: - split: 2023_10_09T23_41_30.846721 path: - '**/details_harness|truthfulqa:mc|0_2023-10-09T23-41-30.846721.parquet' - split: 2023_10_10T03_08_42.670420 path: - '**/details_harness|truthfulqa:mc|0_2023-10-10T03-08-42.670420.parquet' - split: latest path: - '**/details_harness|truthfulqa:mc|0_2023-10-10T03-08-42.670420.parquet' - config_name: harness_winogrande_5 data_files: - split: 2023_10_23T12_54_48.005243 path: - '**/details_harness|winogrande|5_2023-10-23T12-54-48.005243.parquet' - split: latest path: - '**/details_harness|winogrande|5_2023-10-23T12-54-48.005243.parquet' - config_name: results data_files: - split: 2023_10_09T23_41_30.846721 path: - results_2023-10-09T23-41-30.846721.parquet - split: 2023_10_10T03_08_42.670420 path: - results_2023-10-10T03-08-42.670420.parquet - split: 2023_10_23T12_54_48.005243 path: - results_2023-10-23T12-54-48.005243.parquet - split: latest path: - results_2023-10-23T12-54-48.005243.parquet --- # Dataset Card for Evaluation run of PocketDoc/Dans-TotSirocco-7b ## Dataset Description - **Homepage:** - **Repository:** https://huggingface.co/PocketDoc/Dans-TotSirocco-7b - **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 [PocketDoc/Dans-TotSirocco-7b](https://huggingface.co/PocketDoc/Dans-TotSirocco-7b) 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 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_PocketDoc__Dans-TotSirocco-7b", "harness_winogrande_5", split="train") ``` ## Latest results These are the [latest results from run 2023-10-23T12:54:48.005243](https://huggingface.co/datasets/open-llm-leaderboard/details_PocketDoc__Dans-TotSirocco-7b/blob/main/results_2023-10-23T12-54-48.005243.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": 0.44997902684563756, "em_stderr": 0.00509477973209699, "f1": 0.49544777684563845, "f1_stderr": 0.00490923385938236, "acc": 0.45978722729484023, "acc_stderr": 0.01042644341108249 }, "harness|drop|3": { "em": 0.44997902684563756, "em_stderr": 0.00509477973209699, "f1": 0.49544777684563845, "f1_stderr": 0.00490923385938236 }, "harness|gsm8k|5": { "acc": 0.1326762699014405, "acc_stderr": 0.009343929131442216 }, "harness|winogrande|5": { "acc": 0.7868981846882399, "acc_stderr": 0.011508957690722764 } } ``` ### 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

该数据集是在评估模型 PocketDoc/Dans-TotSirocco-7bOpen LLM Leaderboard 上的自动创建的。数据集包含 64 个配置,每个配置对应一个评估任务。

数据集结构

  • 配置数量:64 个配置
  • 创建来源: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。
  • 最新结果:"train" 分割总是指向最新的结果。
  • 结果汇总:一个额外的配置 "results" 存储所有运行结果的汇总,用于计算和显示在 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_PocketDoc__Dans-TotSirocco-7b", "harness_winogrande_5", split="train")

最新结果

以下是 2023-10-23T12:54:48.005243 运行的最新结果

python { "all": { "em": 0.44997902684563756, "em_stderr": 0.00509477973209699, "f1": 0.49544777684563845, "f1_stderr": 0.00490923385938236, "acc": 0.45978722729484023, "acc_stderr": 0.01042644341108249 }, "harness|drop|3": { "em": 0.44997902684563756, "em_stderr": 0.00509477973209699, "f1": 0.49544777684563845, "f1_stderr": 0.00490923385938236 }, "harness|gsm8k|5": { "acc": 0.1326762699014405, "acc_stderr": 0.009343929131442216 }, "harness|winogrande|5": { "acc": 0.7868981846882399, "acc_stderr": 0.011508957690722764 } }

配置详情

  • harness_arc_challenge_25

    • 分割:2023_10_09T23_41_30.846721
      • 路径:**/details_harness|arc:challenge|25_2023-10-09T23-41-30.846721.parquet
    • 分割:2023_10_10T03_08_42.670420
      • 路径:**/details_harness|arc:challenge|25_2023-10-10T03-08-42.670420.parquet
    • 分割:latest
      • 路径:**/details_harness|arc:challenge|25_2023-10-10T03-08-42.670420.parquet
  • harness_drop_3

    • 分割:2023_10_23T12_54_48.005243
      • 路径:**/details_harness|drop|3_2023-10-23T12-54-48.005243.parquet
    • 分割:latest
      • 路径:**/details_harness|drop|3_2023-10-23T12-54-48.005243.parquet
  • harness_gsm8k_5

    • 分割:2023_10_23T12_54_48.005243
      • 路径:**/details_harness|gsm8k|5_2023-10-23T12-54-48.005243.parquet
    • 分割:latest
      • 路径:**/details_harness|gsm8k|5_2023-10-23T12-54-48.005243.parquet
  • harness_hellaswag_10

    • 分割:2023_10_09T23_41_30.846721
      • 路径:**/details_harness|hellaswag|10_2023-10-09T23-41-30.846721.parquet
    • 分割:2023_10_10T03_08_42.670420
      • 路径:**/details_harness|hellaswag|10_2023-10-10T03-08-42.670420.parquet
    • 分割:latest
      • 路径:**/details_harness|hellaswag|10_2023-10-10T03-08-42.670420.parquet
  • harness_hendrycksTest_5

    • 分割:2023_10_09T23_41_30.846721
      • 路径:**/details_harness|hendrycksTest-abstract_algebra|5_2023-10-09T23-41-30.846721.parquet
      • 路径:**/details_harness|hendrycksTest-anatomy|5_2023-10-09T23-41-30.846721.parquet
      • 路径:**/details_harness|hendrycksTest-astronomy|5_2023-10-09T23-41-30.846721.parquet
      • 路径:**/details_harness|hendrycksTest-business_ethics|5_2023-10-09T23-41-30.846721.parquet
      • 路径:**/details_harness|hendrycksTest-clinical_knowledge|5_2023-10-09T23-41-30.846721.parquet
      • 路径:**/details_harness|hendrycksTest-college_biology|5_2023-10-09T23-41-30.846721.parquet
      • 路径:**/details_harness|hendrycksTest-college_chemistry|5_2023-10-09T23-41-30.846721.parquet
      • 路径:**/details_harness|hendrycksTest-college_computer_science|5_2023-10-09T23-41-30.846721.parquet
      • 路径:**/details_harness|hendrycksTest-college_mathematics|5_2023-10-09T23-41-30.846721.parquet
      • 路径:**/details_harness|hendrycksTest-college_medicine|5_2023-10-09T23-41-30.846721.parquet
      • 路径:**/details_harness|hendrycksTest-college_physics|5_2023-10-09T23-41-30.846721.parquet
      • 路径:**/details_harness|hendrycksTest-computer_security|5_2023-10-09T23-41-30.846721.parquet
      • 路径:**/details_harness|hendrycksTest-conceptual_physics|5_2023-10-09T23-41-30.846721.parquet
      • 路径:**/details_harness|hendrycksTest-econometrics|5_2023-10-09T23-41-30.846721.parquet
      • 路径:**/details_harness|hendrycksTest-electrical_engineering|5_2023-10-09T23-41-30.846721.parquet
      • 路径:**/details_harness|hendrycksTest-elementary_mathematics|5_2023-10-09T23-41-30.846721.parquet
      • 路径:**/details_harness|hendrycksTest-formal_logic|5_2023-10-09T23-41-30.846721.parquet
      • 路径:**/details_harness|hendrycksTest-global_facts|5_2023-10-09T23-41-30.846721.parquet
      • 路径:**/details_harness|hendrycksTest-high_school_biology|5_2023-10-09T23-41-30.846721.parquet
      • 路径:**/details_harness|hendrycksTest-high_school_chemistry|5_2023-10-09T23-41-30.846721.parquet
      • 路径:**/details_harness|hendrycksTest-high_school_computer_science|5_2023-10-09T23-41-30.846721.parquet
      • 路径:**/details_harness|hendrycksTest-high_school_european_history|5_2023-10-09T23-41-30.846721.parquet
      • 路径:**/details_harness|hendrycksTest-high_school_geography|5_2023-10-09T23-41-30.846721.parquet
      • 路径:**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-10-09T23-41-30.846721.parquet
      • 路径:**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-10-09T23-41-30.846721.parquet
      • 路径:**/details_harness|hendrycksTest-high_school_mathematics|5_2023-10-09T23-41-30.846721.parquet
      • 路径:**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-10-09T23-41-30.846721.parquet
      • 路径:**/details_harness|hendrycksTest-high_school_physics|5_2023-10-09T23-41-30.846721.parquet
      • 路径:**/details_harness|hendrycksTest-high_school_psychology|5_2023-10-09T23-41-30.846721.parquet
      • 路径:**/details_harness|hendrycksTest-high_school_statistics|5_2023-10-09T23-41-30.846721.parquet
      • 路径:**/details_harness|hendrycksTest-high_school_us_history|5_2023-10-09T23-41-30.846721.parquet
      • 路径:**/details_harness|hendrycksTest-high_school_world_history|5_2023-10-09T23-41-30.846721.parquet
      • 路径:**/details_harness|hendrycksTest-human_aging|5_2023-10-09T23-41-30.846721.parquet
      • 路径:**/details_harness|hendrycksTest-human_sexuality|5_2023-10-09T23-41-30.846721.parquet
      • 路径:**/details_harness|hendrycksTest-international_law|5_2023-10-09T23-41-30.846721.parquet
      • 路径:**/details_harness|hendrycksTest-jurisprudence|5_2023-10-09T23-41-30.846721.parquet
      • 路径:**/details_harness|hendrycksTest-logical_fallacies|5_2023-10-09T23-41-30.846721.parquet
      • 路径:**/details_harness|hendrycksTest-machine_learning|5_2023-10-09T23-41-30.846721.parquet
      • 路径:**/details_harness|hendrycksTest-management|5_2023-10-09T23-41-30.846721.parquet
      • 路径:**/details_harness|hendrycksTest-marketing|5_2023-10-09T23-41-30.846721.parquet
      • 路径:**/details_harness|hendrycksTest-medical_genetics|5_2023-10-09T23-41-30.846721.parquet
      • 路径:**/details_harness|hendrycksTest-miscellaneous|5_2023-10-09T23-41-30.846721.parquet
      • 路径:**/details_harness|hendrycksTest-moral_disputes|5_2023-10-09T23-41-30.846721.parquet
      • 路径:`**/details_harness|hendrycksTest-moral_sc
搜集汇总
数据集介绍
open-llm-leaderboard/details_PocketDoc__Dans-TotSirocco-7b 数据集图片
构建方式
在大型语言模型评估的语境下,该数据集是为记录模型PocketDoc/Dans-TotSirocco-7b在Open LLM Leaderboard上的评测过程而自动生成的。其构建依托于多次评测运行,数据集共包含64种配置,每一种配置对应一个独立的评估任务,如ARC挑战、DROP、GSM8K等。每次评测运行均被存储为一个独立的数据分片,分片名称采用运行时间戳进行标识,而“train”分片则始终指向最近一次运行的结果。此外,数据集还设有一个名为“results”的额外配置,用于汇总所有运行的综合指标,为Leaderboard上聚合度量的计算与展示提供支撑。
特点
该数据集具备鲜明的结构化与时效性特征。其核心特色在于以任务为中心的多配置设计,每个评估任务均拥有独立的配置项,便于研究者按需聚焦特定能力维度的分析。数据集中同一任务的多轮评测结果以时间戳分片形式共存,不仅保留了历史评测的完整轨迹,还通过“latest”分片机制自动指向最新成果,实现了动态更新。这种设计使得模型性能的纵向对比与趋势分析成为可能,同时,汇总配置“results”为快速获取模型整体表现提供了便捷入口,极大地提升了评测数据的可复用性与分析深度。
使用方法
使用该数据集时,研究者可通过Hugging Face的datasets库灵活加载所需信息。例如,调用load_dataset函数并指定数据集名称、目标任务配置(如“harness_winogrande_5”)以及具体分片(如“train”),即可获取对应任务的最新评测细节。若需追溯历史评测结果,则可依据时间戳分片名称(如“2023_10_23T12_54_48.005243”)进行加载。此外,通过访问“results”配置,能够一键获取模型在所有任务上的聚合指标,为整体性能评估提供一站式数据支持。这种设计充分满足了从微观任务分析到宏观性能概览的多层次研究需求。
背景与挑战
背景概述
在大语言模型迅猛发展的时代,如何系统、公平地评估模型的多维能力成为学术界与工业界共同关注的核心议题。Open LLM Leaderboard由HuggingFace团队于2023年发起,旨在为开源社区提供一个标准化、透明化的模型评测平台,其核心研究问题在于构建一套涵盖常识推理、数学解题、阅读理解等多元任务的评测体系,以客观反映模型的真实性能。该数据集记录了PocketDoc/Dans-TotSirocco-7b模型在Leaderboard上的评估过程,包含ARC、HellaSwag、MMLU、GSM8K、Winogrande等任务的详细结果,其影响力在于不仅为模型开发者提供了可复现的基准,更推动了社区对评测标准化和结果可解释性的深入思考。
当前挑战
该数据集所面临的挑战首先体现在领域问题的复杂性上:大语言模型评测需覆盖从常识推理到专业知识的广泛任务,如GSM8K的数学推理与DROP的阅读理解,模型在单一任务上的优异表现往往难以泛化至其他领域,揭示了评测维度全面性与模型能力均衡性之间的张力。构建过程中,数据集需整合多次独立运行的结果,每次运行的时间戳、任务配置及模型版本均可能影响最终指标,如何确保跨次运行的稳定性和数据一致性成为技术难点;同时,评测任务涉及大量细分子集(如MMLU的57个学科),数据管理与版本控制的复杂性进一步加剧了构建挑战。
常用场景
经典使用场景
在大型语言模型(LLM)的评估与比较研究中,该数据集作为Open LLM Leaderboard的标准化评测记录,被广泛用于衡量模型在多维度任务上的性能表现。其涵盖ARC-Challenge、HellaSwag、GSM8K、Winogrande等多样化基准测试,支持研究者通过加载特定配置(如harness_gsm8k_5)获取模型在数学推理、常识推理等细分领域的详尽指标。这一数据集为模型间的横向对比提供了可复现的细粒度数据基础,尤其适用于追踪同一模型在不同时间点的迭代改进效果。
衍生相关工作
基于该数据集,衍生出多项推动LLM评估体系发展的工作。例如,研究者利用其多任务得分矩阵开发了模型能力雷达图可视化工具,直观呈现不同架构(如编码器-解码器与纯解码器模型)的优劣势。此外,该数据集催生了针对评测结果偏差校正的统计分析框架,以及通过对比不同运行轮次数据来识别评测环境波动的研究。这些工作进一步巩固了其作为LLM社区标准参照基准的地位,并启发了后续如ELO评分系统在模型排行榜中的应用。
数据集最近研究
最新研究方向
在大型语言模型(LLM)的评估基准研究领域,开放LLM排行榜(Open LLM Leaderboard)已成为衡量模型综合能力的重要平台。针对PocketDoc/Dans-TotSirocco-7b模型的评估数据集,当前前沿研究方向聚焦于多任务泛化性能的细粒度分析,涵盖常识推理(如Winogrande)、数学解题(GSM8K)以及阅读理解(DROP)等关键维度。该数据集通过64个配置项和多次运行记录,揭示了模型在零样本与少样本场景下的表现差异,尤其突出了在Winogrande任务中达到78.7%准确率的优势,而在GSM8K数学任务上仅13.3%的短板。这一研究趋势与社区对LLM推理能力、知识迁移及鲁棒性的热点探讨相呼应,为后续模型优化提供了量化依据,同时推动评估标准的标准化与透明化,对构建更可信的AI系统具有深远影响。
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