遇见数据集

open-llm-leaderboard-old/details_numfa__numfa_3b_1epoch

收藏
Hugging Face2024-04-17 更新2024-06-22 收录
官方服务:

资源简介:

--- pretty_name: Evaluation run of numfa/numfa_3b_1epoch dataset_summary: "Dataset automatically created during the evaluation run of model\ \ [numfa/numfa_3b_1epoch](https://huggingface.co/numfa/numfa_3b_1epoch) on the [Open\ \ LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard).\n\ \nThe dataset is composed of 63 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 aggregated metrics on the [Open LLM\ \ Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)).\n\ \nTo load the details from a run, you can for instance do the following:\n```python\n\ from datasets import load_dataset\ndata = load_dataset(\"open-llm-leaderboard/details_numfa__numfa_3b_1epoch\"\ ,\n\t\"harness_winogrande_5\",\n\tsplit=\"train\")\n```\n\n## Latest results\n\n\ These are the [latest results from run 2024-04-17T10:06:01.259030](https://huggingface.co/datasets/open-llm-leaderboard/details_numfa__numfa_3b_1epoch/blob/main/results_2024-04-17T10-06-01.259030.json)(note\ \ that their might be results for other tasks in the repos if successive evals didn't\ \ cover the same tasks. You find each in the results and the \"latest\" split for\ \ each eval):\n\n```python\n{\n \"all\": {\n \"acc\": 0.24284410435712883,\n\ \ \"acc_stderr\": 0.030301622085671234,\n \"acc_norm\": 0.24402676198164272,\n\ \ \"acc_norm_stderr\": 0.031108594599294343,\n \"mc1\": 0.24112607099143207,\n\ \ \"mc1_stderr\": 0.01497482727975233,\n \"mc2\": 0.4242822290197145,\n\ \ \"mc2_stderr\": 0.014964426554036708\n },\n \"harness|arc:challenge|25\"\ : {\n \"acc\": 0.2098976109215017,\n \"acc_stderr\": 0.011900548748047456,\n\ \ \"acc_norm\": 0.257679180887372,\n \"acc_norm_stderr\": 0.012780770562768405\n\ \ },\n \"harness|hellaswag|10\": {\n \"acc\": 0.3194582752439753,\n\ \ \"acc_stderr\": 0.004653138360948109,\n \"acc_norm\": 0.37273451503684524,\n\ \ \"acc_norm_stderr\": 0.004825441080261187\n },\n \"harness|hendrycksTest-abstract_algebra|5\"\ : {\n \"acc\": 0.22,\n \"acc_stderr\": 0.04163331998932268,\n \ \ \"acc_norm\": 0.22,\n \"acc_norm_stderr\": 0.04163331998932268\n \ \ },\n \"harness|hendrycksTest-anatomy|5\": {\n \"acc\": 0.18518518518518517,\n\ \ \"acc_stderr\": 0.03355677216313142,\n \"acc_norm\": 0.18518518518518517,\n\ \ \"acc_norm_stderr\": 0.03355677216313142\n },\n \"harness|hendrycksTest-astronomy|5\"\ : {\n \"acc\": 0.17763157894736842,\n \"acc_stderr\": 0.031103182383123398,\n\ \ \"acc_norm\": 0.17763157894736842,\n \"acc_norm_stderr\": 0.031103182383123398\n\ \ },\n \"harness|hendrycksTest-business_ethics|5\": {\n \"acc\": 0.3,\n\ \ \"acc_stderr\": 0.046056618647183814,\n \"acc_norm\": 0.3,\n \ \ \"acc_norm_stderr\": 0.046056618647183814\n },\n \"harness|hendrycksTest-clinical_knowledge|5\"\ : {\n \"acc\": 0.21132075471698114,\n \"acc_stderr\": 0.025125766484827845,\n\ \ \"acc_norm\": 0.21132075471698114,\n \"acc_norm_stderr\": 0.025125766484827845\n\ \ },\n \"harness|hendrycksTest-college_biology|5\": {\n \"acc\": 0.2569444444444444,\n\ \ \"acc_stderr\": 0.03653946969442099,\n \"acc_norm\": 0.2569444444444444,\n\ \ \"acc_norm_stderr\": 0.03653946969442099\n },\n \"harness|hendrycksTest-college_chemistry|5\"\ : {\n \"acc\": 0.21,\n \"acc_stderr\": 0.04093601807403326,\n \ \ \"acc_norm\": 0.21,\n \"acc_norm_stderr\": 0.04093601807403326\n \ \ },\n \"harness|hendrycksTest-college_computer_science|5\": {\n \"acc\"\ : 0.36,\n \"acc_stderr\": 0.04824181513244218,\n \"acc_norm\": 0.36,\n\ \ \"acc_norm_stderr\": 0.04824181513244218\n },\n \"harness|hendrycksTest-college_mathematics|5\"\ : {\n \"acc\": 0.22,\n \"acc_stderr\": 0.04163331998932269,\n \ \ \"acc_norm\": 0.22,\n \"acc_norm_stderr\": 0.04163331998932269\n \ \ },\n \"harness|hendrycksTest-college_medicine|5\": {\n \"acc\": 0.20809248554913296,\n\ \ \"acc_stderr\": 0.030952890217749874,\n \"acc_norm\": 0.20809248554913296,\n\ \ \"acc_norm_stderr\": 0.030952890217749874\n },\n \"harness|hendrycksTest-college_physics|5\"\ : {\n \"acc\": 0.21568627450980393,\n \"acc_stderr\": 0.04092563958237654,\n\ \ \"acc_norm\": 0.21568627450980393,\n \"acc_norm_stderr\": 0.04092563958237654\n\ \ },\n \"harness|hendrycksTest-computer_security|5\": {\n \"acc\":\ \ 0.28,\n \"acc_stderr\": 0.045126085985421276,\n \"acc_norm\": 0.28,\n\ \ \"acc_norm_stderr\": 0.045126085985421276\n },\n \"harness|hendrycksTest-conceptual_physics|5\"\ : {\n \"acc\": 0.26382978723404255,\n \"acc_stderr\": 0.028809989854102973,\n\ \ \"acc_norm\": 0.26382978723404255,\n \"acc_norm_stderr\": 0.028809989854102973\n\ \ },\n \"harness|hendrycksTest-econometrics|5\": {\n \"acc\": 0.2543859649122807,\n\ \ \"acc_stderr\": 0.040969851398436695,\n \"acc_norm\": 0.2543859649122807,\n\ \ \"acc_norm_stderr\": 0.040969851398436695\n },\n \"harness|hendrycksTest-electrical_engineering|5\"\ : {\n \"acc\": 0.2413793103448276,\n \"acc_stderr\": 0.03565998174135302,\n\ \ \"acc_norm\": 0.2413793103448276,\n \"acc_norm_stderr\": 0.03565998174135302\n\ \ },\n \"harness|hendrycksTest-elementary_mathematics|5\": {\n \"acc\"\ : 0.22486772486772486,\n \"acc_stderr\": 0.021502096078229147,\n \"\ acc_norm\": 0.22486772486772486,\n \"acc_norm_stderr\": 0.021502096078229147\n\ \ },\n \"harness|hendrycksTest-formal_logic|5\": {\n \"acc\": 0.29365079365079366,\n\ \ \"acc_stderr\": 0.04073524322147127,\n \"acc_norm\": 0.29365079365079366,\n\ \ \"acc_norm_stderr\": 0.04073524322147127\n },\n \"harness|hendrycksTest-global_facts|5\"\ : {\n \"acc\": 0.18,\n \"acc_stderr\": 0.038612291966536934,\n \ \ \"acc_norm\": 0.18,\n \"acc_norm_stderr\": 0.038612291966536934\n \ \ },\n \"harness|hendrycksTest-high_school_biology|5\": {\n \"acc\"\ : 0.19032258064516128,\n \"acc_stderr\": 0.022331707611823078,\n \"\ acc_norm\": 0.19032258064516128,\n \"acc_norm_stderr\": 0.022331707611823078\n\ \ },\n \"harness|hendrycksTest-high_school_chemistry|5\": {\n \"acc\"\ : 0.17733990147783252,\n \"acc_stderr\": 0.026874337276808356,\n \"\ acc_norm\": 0.17733990147783252,\n \"acc_norm_stderr\": 0.026874337276808356\n\ \ },\n \"harness|hendrycksTest-high_school_computer_science|5\": {\n \ \ \"acc\": 0.22,\n \"acc_stderr\": 0.041633319989322695,\n \"acc_norm\"\ : 0.22,\n \"acc_norm_stderr\": 0.041633319989322695\n },\n \"harness|hendrycksTest-high_school_european_history|5\"\ : {\n \"acc\": 0.22424242424242424,\n \"acc_stderr\": 0.032568666616811015,\n\ \ \"acc_norm\": 0.22424242424242424,\n \"acc_norm_stderr\": 0.032568666616811015\n\ \ },\n \"harness|hendrycksTest-high_school_geography|5\": {\n \"acc\"\ : 0.17676767676767677,\n \"acc_stderr\": 0.027178752639044915,\n \"\ acc_norm\": 0.17676767676767677,\n \"acc_norm_stderr\": 0.027178752639044915\n\ \ },\n \"harness|hendrycksTest-high_school_government_and_politics|5\": {\n\ \ \"acc\": 0.21761658031088082,\n \"acc_stderr\": 0.02977866303775295,\n\ \ \"acc_norm\": 0.21761658031088082,\n \"acc_norm_stderr\": 0.02977866303775295\n\ \ },\n \"harness|hendrycksTest-high_school_macroeconomics|5\": {\n \ \ \"acc\": 0.3282051282051282,\n \"acc_stderr\": 0.023807633198657262,\n\ \ \"acc_norm\": 0.3282051282051282,\n \"acc_norm_stderr\": 0.023807633198657262\n\ \ },\n \"harness|hendrycksTest-high_school_mathematics|5\": {\n \"\ acc\": 0.27037037037037037,\n \"acc_stderr\": 0.027080372815145647,\n \ \ \"acc_norm\": 0.27037037037037037,\n \"acc_norm_stderr\": 0.027080372815145647\n\ \ },\n \"harness|hendrycksTest-high_school_microeconomics|5\": {\n \ \ \"acc\": 0.23529411764705882,\n \"acc_stderr\": 0.027553614467863825,\n\ \ \"acc_norm\": 0.23529411764705882,\n \"acc_norm_stderr\": 0.027553614467863825\n\ \ },\n \"harness|hendrycksTest-high_school_physics|5\": {\n \"acc\"\ : 0.2119205298013245,\n \"acc_stderr\": 0.033367670865679766,\n \"\ acc_norm\": 0.2119205298013245,\n \"acc_norm_stderr\": 0.033367670865679766\n\ \ },\n \"harness|hendrycksTest-high_school_psychology|5\": {\n \"acc\"\ : 0.1963302752293578,\n \"acc_stderr\": 0.017030719339154357,\n \"\ acc_norm\": 0.1963302752293578,\n \"acc_norm_stderr\": 0.017030719339154357\n\ \ },\n \"harness|hendrycksTest-high_school_statistics|5\": {\n \"acc\"\ : 0.33796296296296297,\n \"acc_stderr\": 0.03225941352631295,\n \"\ acc_norm\": 0.33796296296296297,\n \"acc_norm_stderr\": 0.03225941352631295\n\ \ },\n \"harness|hendrycksTest-high_school_us_history|5\": {\n \"acc\"\ : 0.25,\n \"acc_stderr\": 0.03039153369274154,\n \"acc_norm\": 0.25,\n\ \ \"acc_norm_stderr\": 0.03039153369274154\n },\n \"harness|hendrycksTest-high_school_world_history|5\"\ : {\n \"acc\": 0.270042194092827,\n \"acc_stderr\": 0.028900721906293426,\n\ \ \"acc_norm\": 0.270042194092827,\n \"acc_norm_stderr\": 0.028900721906293426\n\ \ },\n \"harness|hendrycksTest-human_aging|5\": {\n \"acc\": 0.31390134529147984,\n\ \ \"acc_stderr\": 0.031146796482972465,\n \"acc_norm\": 0.31390134529147984,\n\ \ \"acc_norm_stderr\": 0.031146796482972465\n },\n \"harness|hendrycksTest-human_sexuality|5\"\ : {\n \"acc\": 0.2595419847328244,\n \"acc_stderr\": 0.03844876139785271,\n\ \ \"acc_norm\": 0.2595419847328244,\n \"acc_norm_stderr\": 0.03844876139785271\n\ \ },\n \"harness|hendrycksTest-international_law|5\": {\n \"acc\":\ \ 0.2396694214876033,\n \"acc_stderr\": 0.03896878985070417,\n \"\ acc_norm\": 0.2396694214876033,\n \"acc_norm_stderr\": 0.03896878985070417\n\ \ },\n \"harness|hendrycksTest-jurisprudence|5\": {\n \"acc\": 0.24074074074074073,\n\ \ \"acc_stderr\": 0.0413311944024384,\n \"acc_norm\": 0.24074074074074073,\n\ \ \"acc_norm_stderr\": 0.0413311944024384\n },\n \"harness|hendrycksTest-logical_fallacies|5\"\ : {\n \"acc\": 0.2147239263803681,\n \"acc_stderr\": 0.03226219377286774,\n\ \ \"acc_norm\": 0.2147239263803681,\n \"acc_norm_stderr\": 0.03226219377286774\n\ \ },\n \"harness|hendrycksTest-machine_learning|5\": {\n \"acc\": 0.32142857142857145,\n\ \ \"acc_stderr\": 0.04432804055291519,\n \"acc_norm\": 0.32142857142857145,\n\ \ \"acc_norm_stderr\": 0.04432804055291519\n },\n \"harness|hendrycksTest-management|5\"\ : {\n \"acc\": 0.17475728155339806,\n \"acc_stderr\": 0.037601780060266224,\n\ \ \"acc_norm\": 0.17475728155339806,\n \"acc_norm_stderr\": 0.037601780060266224\n\ \ },\n \"harness|hendrycksTest-marketing|5\": {\n \"acc\": 0.25213675213675213,\n\ \ \"acc_stderr\": 0.02844796547623102,\n \"acc_norm\": 0.25213675213675213,\n\ \ \"acc_norm_stderr\": 0.02844796547623102\n },\n \"harness|hendrycksTest-medical_genetics|5\"\ : {\n \"acc\": 0.3,\n \"acc_stderr\": 0.046056618647183814,\n \ \ \"acc_norm\": 0.3,\n \"acc_norm_stderr\": 0.046056618647183814\n \ \ },\n \"harness|hendrycksTest-miscellaneous|5\": {\n \"acc\": 0.24010217113665389,\n\ \ \"acc_stderr\": 0.015274685213734195,\n \"acc_norm\": 0.24010217113665389,\n\ \ \"acc_norm_stderr\": 0.015274685213734195\n },\n \"harness|hendrycksTest-moral_disputes|5\"\ : {\n \"acc\": 0.24855491329479767,\n \"acc_stderr\": 0.023267528432100174,\n\ \ \"acc_norm\": 0.24855491329479767,\n \"acc_norm_stderr\": 0.023267528432100174\n\ \ },\n \"harness|hendrycksTest-moral_scenarios|5\": {\n \"acc\": 0.23798882681564246,\n\ \ \"acc_stderr\": 0.014242630070574889,\n \"acc_norm\": 0.23798882681564246,\n\ \ \"acc_norm_stderr\": 0.014242630070574889\n },\n \"harness|hendrycksTest-nutrition|5\"\ : {\n \"acc\": 0.22549019607843138,\n \"acc_stderr\": 0.023929155517351284,\n\ \ \"acc_norm\": 0.22549019607843138,\n \"acc_norm_stderr\": 0.023929155517351284\n\ \ },\n \"harness|hendrycksTest-philosophy|5\": {\n \"acc\": 0.1864951768488746,\n\ \ \"acc_stderr\": 0.02212243977248077,\n \"acc_norm\": 0.1864951768488746,\n\ \ \"acc_norm_stderr\": 0.02212243977248077\n },\n \"harness|hendrycksTest-prehistory|5\"\ : {\n \"acc\": 0.2191358024691358,\n \"acc_stderr\": 0.0230167056402622,\n\ \ \"acc_norm\": 0.2191358024691358,\n \"acc_norm_stderr\": 0.0230167056402622\n\ \ },\n \"harness|hendrycksTest-professional_accounting|5\": {\n \"\ acc\": 0.23404255319148937,\n \"acc_stderr\": 0.025257861359432417,\n \ \ \"acc_norm\": 0.23404255319148937,\n \"acc_norm_stderr\": 0.025257861359432417\n\ \ },\n \"harness|hendrycksTest-professional_law|5\": {\n \"acc\": 0.2457627118644068,\n\ \ \"acc_stderr\": 0.010996156635142692,\n \"acc_norm\": 0.2457627118644068,\n\ \ \"acc_norm_stderr\": 0.010996156635142692\n },\n \"harness|hendrycksTest-professional_medicine|5\"\ : {\n \"acc\": 0.27205882352941174,\n \"acc_stderr\": 0.027033041151681456,\n\ \ \"acc_norm\": 0.27205882352941174,\n \"acc_norm_stderr\": 0.027033041151681456\n\ \ },\n \"harness|hendrycksTest-professional_psychology|5\": {\n \"\ acc\": 0.25,\n \"acc_stderr\": 0.01751781884501444,\n \"acc_norm\"\ : 0.25,\n \"acc_norm_stderr\": 0.01751781884501444\n },\n \"harness|hendrycksTest-public_relations|5\"\ : {\n \"acc\": 0.20909090909090908,\n \"acc_stderr\": 0.03895091015724136,\n\ \ \"acc_norm\": 0.20909090909090908,\n \"acc_norm_stderr\": 0.03895091015724136\n\ \ },\n \"harness|hendrycksTest-security_studies|5\": {\n \"acc\": 0.18775510204081633,\n\ \ \"acc_stderr\": 0.02500025603954621,\n \"acc_norm\": 0.18775510204081633,\n\ \ \"acc_norm_stderr\": 0.02500025603954621\n },\n \"harness|hendrycksTest-sociology|5\"\ : {\n \"acc\": 0.24378109452736318,\n \"acc_stderr\": 0.03036049015401465,\n\ \ \"acc_norm\": 0.24378109452736318,\n \"acc_norm_stderr\": 0.03036049015401465\n\ \ },\n \"harness|hendrycksTest-us_foreign_policy|5\": {\n \"acc\":\ \ 0.23,\n \"acc_stderr\": 0.04229525846816505,\n \"acc_norm\": 0.23,\n\ \ \"acc_norm_stderr\": 0.04229525846816505\n },\n \"harness|hendrycksTest-virology|5\"\ : {\n \"acc\": 0.28313253012048195,\n \"acc_stderr\": 0.03507295431370518,\n\ \ \"acc_norm\": 0.28313253012048195,\n \"acc_norm_stderr\": 0.03507295431370518\n\ \ },\n \"harness|hendrycksTest-world_religions|5\": {\n \"acc\": 0.32748538011695905,\n\ \ \"acc_stderr\": 0.035993357714560276,\n \"acc_norm\": 0.32748538011695905,\n\ \ \"acc_norm_stderr\": 0.035993357714560276\n },\n \"harness|truthfulqa:mc|0\"\ : {\n \"mc1\": 0.24112607099143207,\n \"mc1_stderr\": 0.01497482727975233,\n\ \ \"mc2\": 0.4242822290197145,\n \"mc2_stderr\": 0.014964426554036708\n\ \ },\n \"harness|winogrande|5\": {\n \"acc\": 0.5169692186266772,\n\ \ \"acc_stderr\": 0.014044390401612981\n },\n \"harness|gsm8k|5\":\ \ {\n \"acc\": 0.0,\n \"acc_stderr\": 0.0\n }\n}\n```" repo_url: https://huggingface.co/numfa/numfa_3b_1epoch 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: 2024_04_17T09_14_53.327068 path: - '**/details_harness|arc:challenge|25_2024-04-17T09-14-53.327068.parquet' - split: 2024_04_17T10_06_01.259030 path: - '**/details_harness|arc:challenge|25_2024-04-17T10-06-01.259030.parquet' - split: latest path: - '**/details_harness|arc:challenge|25_2024-04-17T10-06-01.259030.parquet' - config_name: harness_gsm8k_5 data_files: - split: 2024_04_17T09_14_53.327068 path: - '**/details_harness|gsm8k|5_2024-04-17T09-14-53.327068.parquet' - split: 2024_04_17T10_06_01.259030 path: - '**/details_harness|gsm8k|5_2024-04-17T10-06-01.259030.parquet' - split: latest path: - '**/details_harness|gsm8k|5_2024-04-17T10-06-01.259030.parquet' - config_name: harness_hellaswag_10 data_files: - split: 2024_04_17T09_14_53.327068 path: - '**/details_harness|hellaswag|10_2024-04-17T09-14-53.327068.parquet' - split: 2024_04_17T10_06_01.259030 path: - '**/details_harness|hellaswag|10_2024-04-17T10-06-01.259030.parquet' - split: latest path: - '**/details_harness|hellaswag|10_2024-04-17T10-06-01.259030.parquet' - config_name: harness_hendrycksTest_5 data_files: - split: 2024_04_17T09_14_53.327068 path: - '**/details_harness|hendrycksTest-abstract_algebra|5_2024-04-17T09-14-53.327068.parquet' - '**/details_harness|hendrycksTest-anatomy|5_2024-04-17T09-14-53.327068.parquet' - '**/details_harness|hendrycksTest-astronomy|5_2024-04-17T09-14-53.327068.parquet' - '**/details_harness|hendrycksTest-business_ethics|5_2024-04-17T09-14-53.327068.parquet' - '**/details_harness|hendrycksTest-clinical_knowledge|5_2024-04-17T09-14-53.327068.parquet' - '**/details_harness|hendrycksTest-college_biology|5_2024-04-17T09-14-53.327068.parquet' - '**/details_harness|hendrycksTest-college_chemistry|5_2024-04-17T09-14-53.327068.parquet' - '**/details_harness|hendrycksTest-college_computer_science|5_2024-04-17T09-14-53.327068.parquet' - '**/details_harness|hendrycksTest-college_mathematics|5_2024-04-17T09-14-53.327068.parquet' - '**/details_harness|hendrycksTest-college_medicine|5_2024-04-17T09-14-53.327068.parquet' - '**/details_harness|hendrycksTest-college_physics|5_2024-04-17T09-14-53.327068.parquet' - '**/details_harness|hendrycksTest-computer_security|5_2024-04-17T09-14-53.327068.parquet' - '**/details_harness|hendrycksTest-conceptual_physics|5_2024-04-17T09-14-53.327068.parquet' - '**/details_harness|hendrycksTest-econometrics|5_2024-04-17T09-14-53.327068.parquet' - '**/details_harness|hendrycksTest-electrical_engineering|5_2024-04-17T09-14-53.327068.parquet' - '**/details_harness|hendrycksTest-elementary_mathematics|5_2024-04-17T09-14-53.327068.parquet' - '**/details_harness|hendrycksTest-formal_logic|5_2024-04-17T09-14-53.327068.parquet' - '**/details_harness|hendrycksTest-global_facts|5_2024-04-17T09-14-53.327068.parquet' - '**/details_harness|hendrycksTest-high_school_biology|5_2024-04-17T09-14-53.327068.parquet' - '**/details_harness|hendrycksTest-high_school_chemistry|5_2024-04-17T09-14-53.327068.parquet' - '**/details_harness|hendrycksTest-high_school_computer_science|5_2024-04-17T09-14-53.327068.parquet' - '**/details_harness|hendrycksTest-high_school_european_history|5_2024-04-17T09-14-53.327068.parquet' - '**/details_harness|hendrycksTest-high_school_geography|5_2024-04-17T09-14-53.327068.parquet' - '**/details_harness|hendrycksTest-high_school_government_and_politics|5_2024-04-17T09-14-53.327068.parquet' - '**/details_harness|hendrycksTest-high_school_macroeconomics|5_2024-04-17T09-14-53.327068.parquet' - '**/details_harness|hendrycksTest-high_school_mathematics|5_2024-04-17T09-14-53.327068.parquet' - '**/details_harness|hendrycksTest-high_school_microeconomics|5_2024-04-17T09-14-53.327068.parquet' - '**/details_harness|hendrycksTest-high_school_physics|5_2024-04-17T09-14-53.327068.parquet' - '**/details_harness|hendrycksTest-high_school_psychology|5_2024-04-17T09-14-53.327068.parquet' - '**/details_harness|hendrycksTest-high_school_statistics|5_2024-04-17T09-14-53.327068.parquet' - '**/details_harness|hendrycksTest-high_school_us_history|5_2024-04-17T09-14-53.327068.parquet' - '**/details_harness|hendrycksTest-high_school_world_history|5_2024-04-17T09-14-53.327068.parquet' - '**/details_harness|hendrycksTest-human_aging|5_2024-04-17T09-14-53.327068.parquet' - '**/details_harness|hendrycksTest-human_sexuality|5_2024-04-17T09-14-53.327068.parquet' - '**/details_harness|hendrycksTest-international_law|5_2024-04-17T09-14-53.327068.parquet' - '**/details_harness|hendrycksTest-jurisprudence|5_2024-04-17T09-14-53.327068.parquet' - '**/details_harness|hendrycksTest-logical_fallacies|5_2024-04-17T09-14-53.327068.parquet' - '**/details_harness|hendrycksTest-machine_learning|5_2024-04-17T09-14-53.327068.parquet' - '**/details_harness|hendrycksTest-management|5_2024-04-17T09-14-53.327068.parquet' - '**/details_harness|hendrycksTest-marketing|5_2024-04-17T09-14-53.327068.parquet' - '**/details_harness|hendrycksTest-medical_genetics|5_2024-04-17T09-14-53.327068.parquet' - '**/details_harness|hendrycksTest-miscellaneous|5_2024-04-17T09-14-53.327068.parquet' - '**/details_harness|hendrycksTest-moral_disputes|5_2024-04-17T09-14-53.327068.parquet' - '**/details_harness|hendrycksTest-moral_scenarios|5_2024-04-17T09-14-53.327068.parquet' - '**/details_harness|hendrycksTest-nutrition|5_2024-04-17T09-14-53.327068.parquet' - '**/details_harness|hendrycksTest-philosophy|5_2024-04-17T09-14-53.327068.parquet' - '**/details_harness|hendrycksTest-prehistory|5_2024-04-17T09-14-53.327068.parquet' - '**/details_harness|hendrycksTest-professional_accounting|5_2024-04-17T09-14-53.327068.parquet' - '**/details_harness|hendrycksTest-professional_law|5_2024-04-17T09-14-53.327068.parquet' - '**/details_harness|hendrycksTest-professional_medicine|5_2024-04-17T09-14-53.327068.parquet' - '**/details_harness|hendrycksTest-professional_psychology|5_2024-04-17T09-14-53.327068.parquet' - '**/details_harness|hendrycksTest-public_relations|5_2024-04-17T09-14-53.327068.parquet' - '**/details_harness|hendrycksTest-security_studies|5_2024-04-17T09-14-53.327068.parquet' - '**/details_harness|hendrycksTest-sociology|5_2024-04-17T09-14-53.327068.parquet' - '**/details_harness|hendrycksTest-us_foreign_policy|5_2024-04-17T09-14-53.327068.parquet' - '**/details_harness|hendrycksTest-virology|5_2024-04-17T09-14-53.327068.parquet' - '**/details_harness|hendrycksTest-world_religions|5_2024-04-17T09-14-53.327068.parquet' - split: 2024_04_17T10_06_01.259030 path: - '**/details_harness|hendrycksTest-abstract_algebra|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-anatomy|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-astronomy|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-business_ethics|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-clinical_knowledge|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-college_biology|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-college_chemistry|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-college_computer_science|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-college_mathematics|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-college_medicine|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-college_physics|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-computer_security|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-conceptual_physics|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-econometrics|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-electrical_engineering|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-elementary_mathematics|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-formal_logic|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-global_facts|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-high_school_biology|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-high_school_chemistry|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-high_school_computer_science|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-high_school_european_history|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-high_school_geography|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-high_school_government_and_politics|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-high_school_macroeconomics|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-high_school_mathematics|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-high_school_microeconomics|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-high_school_physics|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-high_school_psychology|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-high_school_statistics|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-high_school_us_history|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-high_school_world_history|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-human_aging|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-human_sexuality|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-international_law|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-jurisprudence|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-logical_fallacies|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-machine_learning|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-management|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-marketing|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-medical_genetics|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-miscellaneous|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-moral_disputes|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-moral_scenarios|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-nutrition|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-philosophy|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-prehistory|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-professional_accounting|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-professional_law|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-professional_medicine|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-professional_psychology|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-public_relations|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-security_studies|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-sociology|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-us_foreign_policy|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-virology|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-world_religions|5_2024-04-17T10-06-01.259030.parquet' - split: latest path: - '**/details_harness|hendrycksTest-abstract_algebra|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-anatomy|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-astronomy|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-business_ethics|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-clinical_knowledge|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-college_biology|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-college_chemistry|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-college_computer_science|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-college_mathematics|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-college_medicine|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-college_physics|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-computer_security|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-conceptual_physics|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-econometrics|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-electrical_engineering|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-elementary_mathematics|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-formal_logic|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-global_facts|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-high_school_biology|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-high_school_chemistry|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-high_school_computer_science|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-high_school_european_history|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-high_school_geography|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-high_school_government_and_politics|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-high_school_macroeconomics|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-high_school_mathematics|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-high_school_microeconomics|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-high_school_physics|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-high_school_psychology|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-high_school_statistics|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-high_school_us_history|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-high_school_world_history|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-human_aging|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-human_sexuality|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-international_law|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-jurisprudence|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-logical_fallacies|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-machine_learning|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-management|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-marketing|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-medical_genetics|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-miscellaneous|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-moral_disputes|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-moral_scenarios|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-nutrition|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-philosophy|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-prehistory|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-professional_accounting|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-professional_law|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-professional_medicine|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-professional_psychology|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-public_relations|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-security_studies|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-sociology|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-us_foreign_policy|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-virology|5_2024-04-17T10-06-01.259030.parquet' - '**/details_harness|hendrycksTest-world_religions|5_2024-04-17T10-06-01.259030.parquet' - config_name: harness_hendrycksTest_abstract_algebra_5 data_files: - split: 2024_04_17T09_14_53.327068 path: - '**/details_harness|hendrycksTest-abstract_algebra|5_2024-04-17T09-14-53.327068.parquet' - split: 2024_04_17T10_06_01.259030 path: - '**/details_harness|hendrycksTest-abstract_algebra|5_2024-04-17T10-06-01.259030.parquet' - split: latest path: - '**/details_harness|hendrycksTest-abstract_algebra|5_2024-04-17T10-06-01.259030.parquet' - config_name: harness_hendrycksTest_anatomy_5 data_files: - split: 2024_04_17T09_14_53.327068 path: - '**/details_harness|hendrycksTest-anatomy|5_2024-04-17T09-14-53.327068.parquet' - split: 2024_04_17T10_06_01.259030 path: - '**/details_harness|hendrycksTest-anatomy|5_2024-04-17T10-06-01.259030.parquet' - split: latest path: - '**/details_harness|hendrycksTest-anatomy|5_2024-04-17T10-06-01.259030.parquet' - config_name: harness_hendrycksTest_astronomy_5 data_files: - split: 2024_04_17T09_14_53.327068 path: - '**/details_harness|hendrycksTest-astronomy|5_2024-04-17T09-14-53.327068.parquet' - split: 2024_04_17T10_06_01.259030 path: - '**/details_harness|hendrycksTest-astronomy|5_2024-04-17T10-06-01.259030.parquet' - split: latest path: - '**/details_harness|hendrycksTest-astronomy|5_2024-04-17T10-06-01.259030.parquet' - config_name: harness_hendrycksTest_business_ethics_5 data_files: - split: 2024_04_17T09_14_53.327068 path: - '**/details_harness|hendrycksTest-business_ethics|5_2024-04-17T09-14-53.327068.parquet' - split: 2024_04_17T10_06_01.259030 path: - '**/details_harness|hendrycksTest-business_ethics|5_2024-04-17T10-06-01.259030.parquet' - split: latest path: - '**/details_harness|hendrycksTest-business_ethics|5_2024-04-17T10-06-01.259030.parquet' - config_name: harness_hendrycksTest_clinical_knowledge_5 data_files: - split: 2024_04_17T09_14_53.327068 path: - '**/details_harness|hendrycksTest-clinical_knowledge|5_2024-04-17T09-14-53.327068.parquet' - split: 2024_04_17T10_06_01.259030 path: - '**/details_harness|hendrycksTest-clinical_knowledge|5_2024-04-17T10-06-01.259030.parquet' - split: latest path: - '**/details_harness|hendrycksTest-clinical_knowledge|5_2024-04-17T10-06-01.259030.parquet' - config_name: harness_hendrycksTest_college_biology_5 data_files: - split: 2024_04_17T09_14_53.327068 path: - '**/details_harness|hendrycksTest-college_biology|5_2024-04-17T09-14-53.327068.parquet' - split: 2024_04_17T10_06_01.259030 path: - '**/details_harness|hendrycksTest-college_biology|5_2024-04-17T10-06-01.259030.parquet' - split: latest path: - '**/details_harness|hendrycksTest-college_biology|5_2024-04-17T10-06-01.259030.parquet' - config_name: harness_hendrycksTest_college_chemistry_5 data_files: - split: 2024_04_17T09_14_53.327068 path: - '**/details_harness|hendrycksTest-college_chemistry|5_2024-04-17T09-14-53.327068.parquet' - split: 2024_04_17T10_06_01.259030 path: - '**/details_harness|hendrycksTest-college_chemistry|5_2024-04-17T10-06-01.259030.parquet' - split: latest path: - '**/details_harness|hendrycksTest-college_chemistry|5_2024-04-17T10-06-01.259030.parquet' - config_name: harness_hendrycksTest_college_computer_science_5 data_files: - split: 2024_04_17T09_14_53.327068 path: - '**/details_harness|hendrycksTest-college_computer_science|5_2024-04-17T09-14-53.327068.parquet' - split: 2024_04_17T10_06_01.259030 path: - '**/details_harness|hendrycksTest-college_computer_science|5_2024-04-17T10-06-01.259030.parquet' - split: latest path: - '**/details_harness|hendrycksTest-college_computer_science|5_2024-04-17T10-06-01.259030.parquet' - config_name: harness_hendrycksTest_college_mathematics_5 data_files: - split: 2024_04_17T09_14_53.327068 path: - '**/details_harness|hendrycksTest-college_mathematics|5_2024-04-17T09-14-53.327068.parquet' - split: 2024_04_17T10_06_01.259030 path: - '**/details_harness|hendrycksTest-college_mathematics|5_2024-04-17T10-06-01.259030.parquet' - split: latest path: - '**/details_harness|hendrycksTest-college_mathematics|5_2024-04-17T10-06-01.259030.parquet' - config_name: harness_hendrycksTest_college_medicine_5 data_files: - split: 2024_04_17T09_14_53.327068 path: - '**/details_harness|hendrycksTest-college_medicine|5_2024-04-17T09-14-53.327068.parquet' - split: 2024_04_17T10_06_01.259030 path: - '**/details_harness|hendrycksTest-college_medicine|5_2024-04-17T10-06-01.259030.parquet' - split: latest path: - '**/details_harness|hendrycksTest-college_medicine|5_2024-04-17T10-06-01.259030.parquet' - config_name: harness_hendrycksTest_college_physics_5 data_files: - split: 2024_04_17T09_14_53.327068 path: - '**/details_harness|hendrycksTest-college_physics|5_2024-04-17T09-14-53.327068.parquet' - split: 2024_04_17T10_06_01.259030 path: - '**/details_harness|hendrycksTest-college_physics|5_2024-04-17T10-06-01.259030.parquet' - split: latest path: - '**/details_harness|hendrycksTest-college_physics|5_2024-04-17T10-06-01.259030.parquet' - config_name: harness_hendrycksTest_computer_security_5 data_files: - split: 2024_04_17T09_14_53.327068 path: - '**/details_harness|hendrycksTest-computer_security|5_2024-04-17T09-14-53.327068.parquet' - split: 2024_04_17T10_06_01.259030 path: - '**/details_harness|hendrycksTest-computer_security|5_2024-04-17T10-06-01.259030.parquet' - split: latest path: - '**/details_harness|hendrycksTest-computer_security|5_2024-04-17T10-06-01.259030.parquet' - config_name: harness_hendrycksTest_conceptual_physics_5 data_files: - split: 2024_04_17T09_14_53.327068 path: - '**/details_harness|hendrycksTest-conceptual_physics|5_2024-04-17T09-14-53.327068.parquet' - split: 2024_04_17T10_06_01.259030 path: - '**/details_harness|hendrycksTest-conceptual_physics|5_2024-04-17T10-06-01.259030.parquet' - split: latest path: - '**/details_harness|hendrycksTest-conceptual_physics|5_2024-04-17T10-06-01.259030.parquet' - config_name: harness_hendrycksTest_econometrics_5 data_files: - split: 2024_04_17T09_14_53.327068 path: - '**/details_harness|hendrycksTest-econometrics|5_2024-04-17T09-14-53.327068.parquet' - split: 2024_04_17T10_06_01.259030 path: - '**/details_harness|hendrycksTest-econometrics|5_2024-04-17T10-06-01.259030.parquet' - split: latest path: - '**/details_harness|hendrycksTest-econometrics|5_2024-04-17T10-06-01.259030.parquet' - config_name: harness_hendrycksTest_electrical_engineering_5 data_files: - split: 2024_04_17T09_14_53.327068 path: - '**/details_harness|hendrycksTest-electrical_engineering|5_2024-04-17T09-14-53.327068.parquet' - split: 2024_04_17T10_06_01.259030 path: - '**/details_harness|hendrycksTest-electrical_engineering|5_2024-04-17T10-06-01.259030.parquet' - split: latest path: - '**/details_harness|hendrycksTest-electrical_engineering|5_2024-04-17T10-06-01.259030.parquet' - config_name: harness_hendrycksTest_elementary_mathematics_5 data_files: - split: 2024_04_17T09_14_53.327068 path: - '**/details_harness|hendrycksTest-elementary_mathematics|5_2024-04-17T09-14-53.327068.parquet' - split: 2024_04_17T10_06_01.259030 path: - '**/details_harness|hendrycksTest-elementary_mathematics|5_2024-04-17T10-06-01.259030.parquet' - split: latest path: - '**/details_harness|hendrycksTest-elementary_mathematics|5_2024-04-17T10-06-01.259030.parquet' - config_name: harness_hendrycksTest_formal_logic_5 data_files: - split: 2024_04_17T09_14_53.327068 path: - '**/details_harness|hendrycksTest-formal_logic|5_2024-04-17T09-14-53.327068.parquet' - split: 2024_04_17T10_06_01.259030 path: - '**/details_harness|hendrycksTest-formal_logic|5_2024-04-17T10-06-01.259030.parquet' - split: latest path: - '**/details_harness|hendrycksTest-formal_logic|5_2024-04-17T10-06-01.259030.parquet' - config_name: harness_hendrycksTest_global_facts_5 data_files: - split: 2024_04_17T09_14_53.327068 path: - '**/details_harness|hendrycksTest-global_facts|5_2024-04-17T09-14-53.327068.parquet' - split: 2024_04_17T10_06_01.259030 path: - '**/details_harness|hendrycksTest-global_facts|5_2024-04-17T10-06-01.259030.parquet' - split: latest path: - '**/details_harness|hendrycksTest-global_facts|5_2024-04-17T10-06-01.259030.parquet' - config_name: harness_hendrycksTest_high_school_biology_5 data_files: - split: 2024_04_17T09_14_53.327068 path: - '**/details_harness|hendrycksTest-high_school_biology|5_2024-04-17T09-14-53.327068.parquet' - split: 2024_04_17T10_06_01.259030 path: - '**/details_harness|hendrycksTest-high_school_biology|5_2024-04-17T10-06-01.259030.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_biology|5_2024-04-17T10-06-01.259030.parquet' - config_name: harness_hendrycksTest_high_school_chemistry_5 data_files: - split: 2024_04_17T09_14_53.327068 path: - '**/details_harness|hendrycksTest-high_school_chemistry|5_2024-04-17T09-14-53.327068.parquet' - split: 2024_04_17T10_06_01.259030 path: - '**/details_harness|hendrycksTest-high_school_chemistry|5_2024-04-17T10-06-01.259030.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_chemistry|5_2024-04-17T10-06-01.259030.parquet' - config_name: harness_hendrycksTest_high_school_computer_science_5 data_files: - split: 2024_04_17T09_14_53.327068 path: - '**/details_harness|hendrycksTest-high_school_computer_science|5_2024-04-17T09-14-53.327068.parquet' - split: 2024_04_17T10_06_01.259030 path: - '**/details_harness|hendrycksTest-high_school_computer_science|5_2024-04-17T10-06-01.259030.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_computer_science|5_2024-04-17T10-06-01.259030.parquet' - config_name: harness_hendrycksTest_high_school_european_history_5 data_files: - split: 2024_04_17T09_14_53.327068 path: - '**/details_harness|hendrycksTest-high_school_european_history|5_2024-04-17T09-14-53.327068.parquet' - split: 2024_04_17T10_06_01.259030 path: - '**/details_harness|hendrycksTest-high_school_european_history|5_2024-04-17T10-06-01.259030.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_european_history|5_2024-04-17T10-06-01.259030.parquet' - config_name: harness_hendrycksTest_high_school_geography_5 data_files: - split: 2024_04_17T09_14_53.327068 path: - '**/details_harness|hendrycksTest-high_school_geography|5_2024-04-17T09-14-53.327068.parquet' - split: 2024_04_17T10_06_01.259030 path: - '**/details_harness|hendrycksTest-high_school_geography|5_2024-04-17T10-06-01.259030.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_geography|5_2024-04-17T10-06-01.259030.parquet' - config_name: harness_hendrycksTest_high_school_government_and_politics_5 data_files: - split: 2024_04_17T09_14_53.327068 path: - '**/details_harness|hendrycksTest-high_school_government_and_politics|5_2024-04-17T09-14-53.327068.parquet' - split: 2024_04_17T10_06_01.259030 path: - '**/details_harness|hendrycksTest-high_school_government_and_politics|5_2024-04-17T10-06-01.259030.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_government_and_politics|5_2024-04-17T10-06-01.259030.parquet' - config_name: harness_hendrycksTest_high_school_macroeconomics_5 data_files: - split: 2024_04_17T09_14_53.327068 path: - '**/details_harness|hendrycksTest-high_school_macroeconomics|5_2024-04-17T09-14-53.327068.parquet' - split: 2024_04_17T10_06_01.259030 path: - '**/details_harness|hendrycksTest-high_school_macroeconomics|5_2024-04-17T10-06-01.259030.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_macroeconomics|5_2024-04-17T10-06-01.259030.parquet' - config_name: harness_hendrycksTest_high_school_mathematics_5 data_files: - split: 2024_04_17T09_14_53.327068 path: - '**/details_harness|hendrycksTest-high_school_mathematics|5_2024-04-17T09-14-53.327068.parquet' - split: 2024_04_17T10_06_01.259030 path: - '**/details_harness|hendrycksTest-high_school_mathematics|5_2024-04-17T10-06-01.259030.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_mathematics|5_2024-04-17T10-06-01.259030.parquet' - config_name: harness_hendrycksTest_high_school_microeconomics_5 data_files: - split: 2024_04_17T09_14_53.327068 path: - '**/details_harness|hendrycksTest-high_school_microeconomics|5_2024-04-17T09-14-53.327068.parquet' - split: 2024_04_17T10_06_01.259030 path: - '**/details_harness|hendrycksTest-high_school_microeconomics|5_2024-04-17T10-06-01.259030.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_microeconomics|5_2024-04-17T10-06-01.259030.parquet' - config_name: harness_hendrycksTest_high_school_physics_5 data_files: - split: 2024_04_17T09_14_53.327068 path: - '**/details_harness|hendrycksTest-high_school_physics|5_2024-04-17T09-14-53.327068.parquet' - split: 2024_04_17T10_06_01.259030 path: - '**/details_harness|hendrycksTest-high_school_physics|5_2024-04-17T10-06-01.259030.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_physics|5_2024-04-17T10-06-01.259030.parquet' - config_name: harness_hendrycksTest_high_school_psychology_5 data_files: - split: 2024_04_17T09_14_53.327068 path: - '**/details_harness|hendrycksTest-high_school_psychology|5_2024-04-17T09-14-53.327068.parquet' - split: 2024_04_17T10_06_01.259030 path: - '**/details_harness|hendrycksTest-high_school_psychology|5_2024-04-17T10-06-01.259030.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_psychology|5_2024-04-17T10-06-01.259030.parquet' - config_name: harness_hendrycksTest_high_school_statistics_5 data_files: - split: 2024_04_17T09_14_53.327068 path: - '**/details_harness|hendrycksTest-high_school_statistics|5_2024-04-17T09-14-53.327068.parquet' - split: 2024_04_17T10_06_01.259030 path: - '**/details_harness|hendrycksTest-high_school_statistics|5_2024-04-17T10-06-01.259030.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_statistics|5_2024-04-17T10-06-01.259030.parquet' - config_name: harness_hendrycksTest_high_school_us_history_5 data_files: - split: 2024_04_17T09_14_53.327068 path: - '**/details_harness|hendrycksTest-high_school_us_history|5_2024-04-17T09-14-53.327068.parquet' - split: 2024_04_17T10_06_01.259030 path: - '**/details_harness|hendrycksTest-high_school_us_history|5_2024-04-17T10-06-01.259030.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_us_history|5_2024-04-17T10-06-01.259030.parquet' - config_name: harness_hendrycksTest_high_school_world_history_5 data_files: - split: 2024_04_17T09_14_53.327068 path: - '**/details_harness|hendrycksTest-high_school_world_history|5_2024-04-17T09-14-53.327068.parquet' - split: 2024_04_17T10_06_01.259030 path: - '**/details_harness|hendrycksTest-high_school_world_history|5_2024-04-17T10-06-01.259030.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_world_history|5_2024-04-17T10-06-01.259030.parquet' - config_name: harness_hendrycksTest_human_aging_5 data_files: - split: 2024_04_17T09_14_53.327068 path: - '**/details_harness|hendrycksTest-human_aging|5_2024-04-17T09-14-53.327068.parquet' - split: 2024_04_17T10_06_01.259030 path: - '**/details_harness|hendrycksTest-human_aging|5_2024-04-17T10-06-01.259030.parquet' - split: latest path: - '**/details_harness|hendrycksTest-human_aging|5_2024-04-17T10-06-01.259030.parquet' - config_name: harness_hendrycksTest_human_sexuality_5 data_files: - split: 2024_04_17T09_14_53.327068 path: - '**/details_harness|hendrycksTest-human_sexuality|5_2024-04-17T09-14-53.327068.parquet' - split: 2024_04_17T10_06_01.259030 path: - '**/details_harness|hendrycksTest-human_sexuality|5_2024-04-17T10-06-01.259030.parquet' - split: latest path: - '**/details_harness|hendrycksTest-human_sexuality|5_2024-04-17T10-06-01.259030.parquet' - config_name: harness_hendrycksTest_international_law_5 data_files: - split: 2024_04_17T09_14_53.327068 path: - '**/details_harness|hendrycksTest-international_law|5_2024-04-17T09-14-53.327068.parquet' - split: 2024_04_17T10_06_01.259030 path: - '**/details_harness|hendrycksTest-international_law|5_2024-04-17T10-06-01.259030.parquet' - split: latest path: - '**/details_harness|hendrycksTest-international_law|5_2024-04-17T10-06-01.259030.parquet' - config_name: harness_hendrycksTest_jurisprudence_5 data_files: - split: 2024_04_17T09_14_53.327068 path: - '**/details_harness|hendrycksTest-jurisprudence|5_2024-04-17T09-14-53.327068.parquet' - split: 2024_04_17T10_06_01.259030 path: - '**/details_harness|hendrycksTest-jurisprudence|5_2024-04-17T10-06-01.259030.parquet' - split: latest path: - '**/details_harness|hendrycksTest-jurisprudence|5_2024-04-17T10-06-01.259030.parquet' - config_name: harness_hendrycksTest_logical_fallacies_5 data_files: - split: 2024_04_17T09_14_53.327068 path: - '**/details_harness|hendrycksTest-logical_fallacies|5_2024-04-17T09-14-53.327068.parquet' - split: 2024_04_17T10_06_01.259030 path: - '**/details_harness|hendrycksTest-logical_fallacies|5_2024-04-17T10-06-01.259030.parquet' - split: latest path: - '**/details_harness|hendrycksTest-logical_fallacies|5_2024-04-17T10-06-01.259030.parquet' - config_name: harness_hendrycksTest_machine_learning_5 data_files: - split: 2024_04_17T09_14_53.327068 path: - '**/details_harness|hendrycksTest-machine_learning|5_2024-04-17T09-14-53.327068.parquet' - split: 2024_04_17T10_06_01.259030 path: - '**/details_harness|hendrycksTest-machine_learning|5_2024-04-17T10-06-01.259030.parquet' - split: latest path: - '**/details_harness|hendrycksTest-machine_learning|5_2024-04-17T10-06-01.259030.parquet' - config_name: harness_hendrycksTest_management_5 data_files: - split: 2024_04_17T09_14_53.327068 path: - '**/details_harness|hendrycksTest-management|5_2024-04-17T09-14-53.327068.parquet' - split: 2024_04_17T10_06_01.259030 path: - '**/details_harness|hendrycksTest-management|5_2024-04-17T10-06-01.259030.parquet' - split: latest path: - '**/details_harness|hendrycksTest-management|5_2024-04-17T10-06-01.259030.parquet' - config_name: harness_hendrycksTest_marketing_5 data_files: - split: 2024_04_17T09_14_53.327068 path: - '**/details_harness|hendrycksTest-marketing|5_2024-04-17T09-14-53.327068.parquet' - split: 2024_04_17T10_06_01.259030 path: - '**/details_harness|hendrycksTest-marketing|5_2024-04-17T10-06-01.259030.parquet' - split: latest path: - '**/details_harness|hendrycksTest-marketing|5_2024-04-17T10-06-01.259030.parquet' - config_name: harness_hendrycksTest_medical_genetics_5 data_files: - split: 2024_04_17T09_14_53.327068 path: - '**/details_harness|hendrycksTest-medical_genetics|5_2024-04-17T09-14-53.327068.parquet' - split: 2024_04_17T10_06_01.259030 path: - '**/details_harness|hendrycksTest-medical_genetics|5_2024-04-17T10-06-01.259030.parquet' - split: latest path: - '**/details_harness|hendrycksTest-medical_genetics|5_2024-04-17T10-06-01.259030.parquet' - config_name: harness_hendrycksTest_miscellaneous_5 data_files: - split: 2024_04_17T09_14_53.327068 path: - '**/details_harness|hendrycksTest-miscellaneous|5_2024-04-17T09-14-53.327068.parquet' - split: 2024_04_17T10_06_01.259030 path: - '**/details_harness|hendrycksTest-miscellaneous|5_2024-04-17T10-06-01.259030.parquet' - split: latest path: - '**/details_harness|hendrycksTest-miscellaneous|5_2024-04-17T10-06-01.259030.parquet' - config_name: harness_hendrycksTest_moral_disputes_5 data_files: - split: 2024_04_17T09_14_53.327068 path: - '**/details_harness|hendrycksTest-moral_disputes|5_2024-04-17T09-14-53.327068.parquet' - split: 2024_04_17T10_06_01.259030 path: - '**/details_harness|hendrycksTest-moral_disputes|5_2024-04-17T10-06-01.259030.parquet' - split: latest path: - '**/details_harness|hendrycksTest-moral_disputes|5_2024-04-17T10-06-01.259030.parquet' - config_name: harness_hendrycksTest_moral_scenarios_5 data_files: - split: 2024_04_17T09_14_53.327068 path: - '**/details_harness|hendrycksTest-moral_scenarios|5_2024-04-17T09-14-53.327068.parquet' - split: 2024_04_17T10_06_01.259030 path: - '**/details_harness|hendrycksTest-moral_scenarios|5_2024-04-17T10-06-01.259030.parquet' - split: latest path: - '**/details_harness|hendrycksTest-moral_scenarios|5_2024-04-17T10-06-01.259030.parquet' - config_name: harness_hendrycksTest_nutrition_5 data_files: - split: 2024_04_17T09_14_53.327068 path: - '**/details_harness|hendrycksTest-nutrition|5_2024-04-17T09-14-53.327068.parquet' - split: 2024_04_17T10_06_01.259030 path: - '**/details_harness|hendrycksTest-nutrition|5_2024-04-17T10-06-01.259030.parquet' - split: latest path: - '**/details_harness|hendrycksTest-nutrition|5_2024-04-17T10-06-01.259030.parquet' - config_name: harness_hendrycksTest_philosophy_5 data_files: - split: 2024_04_17T09_14_53.327068 path: - '**/details_harness|hendrycksTest-philosophy|5_2024-04-17T09-14-53.327068.parquet' - split: 2024_04_17T10_06_01.259030 path: - '**/details_harness|hendrycksTest-philosophy|5_2024-04-17T10-06-01.259030.parquet' - split: latest path: - '**/details_harness|hendrycksTest-philosophy|5_2024-04-17T10-06-01.259030.parquet' - config_name: harness_hendrycksTest_prehistory_5 data_files: - split: 2024_04_17T09_14_53.327068 path: - '**/details_harness|hendrycksTest-prehistory|5_2024-04-17T09-14-53.327068.parquet' - split: 2024_04_17T10_06_01.259030 path: - '**/details_harness|hendrycksTest-prehistory|5_2024-04-17T10-06-01.259030.parquet' - split: latest path: - '**/details_harness|hendrycksTest-prehistory|5_2024-04-17T10-06-01.259030.parquet' - config_name: harness_hendrycksTest_professional_accounting_5 data_files: - split: 2024_04_17T09_14_53.327068 path: - '**/details_harness|hendrycksTest-professional_accounting|5_2024-04-17T09-14-53.327068.parquet' - split: 2024_04_17T10_06_01.259030 path: - '**/details_harness|hendrycksTest-professional_accounting|5_2024-04-17T10-06-01.259030.parquet' - split: latest path: - '**/details_harness|hendrycksTest-professional_accounting|5_2024-04-17T10-06-01.259030.parquet' - config_name: harness_hendrycksTest_professional_law_5 data_files: - split: 2024_04_17T09_14_53.327068 path: - '**/details_harness|hendrycksTest-professional_law|5_2024-04-17T09-14-53.327068.parquet' - split: 2024_04_17T10_06_01.259030 path: - '**/details_harness|hendrycksTest-professional_law|5_2024-04-17T10-06-01.259030.parquet' - split: latest path: - '**/details_harness|hendrycksTest-professional_law|5_2024-04-17T10-06-01.259030.parquet' - config_name: harness_hendrycksTest_professional_medicine_5 data_files: - split: 2024_04_17T09_14_53.327068 path: - '**/details_harness|hendrycksTest-professional_medicine|5_2024-04-17T09-14-53.327068.parquet' - split: 2024_04_17T10_06_01.259030 path: - '**/details_harness|hendrycksTest-professional_medicine|5_2024-04-17T10-06-01.259030.parquet' - split: latest path: - '**/details_harness|hendrycksTest-professional_medicine|5_2024-04-17T10-06-01.259030.parquet' - config_name: harness_hendrycksTest_professional_psychology_5 data_files: - split: 2024_04_17T09_14_53.327068 path: - '**/details_harness|hendrycksTest-professional_psychology|5_2024-04-17T09-14-53.327068.parquet' - split: 2024_04_17T10_06_01.259030 path: - '**/details_harness|hendrycksTest-professional_psychology|5_2024-04-17T10-06-01.259030.parquet' - split: latest path: - '**/details_harness|hendrycksTest-professional_psychology|5_2024-04-17T10-06-01.259030.parquet' - config_name: harness_hendrycksTest_public_relations_5 data_files: - split: 2024_04_17T09_14_53.327068 path: - '**/details_harness|hendrycksTest-public_relations|5_2024-04-17T09-14-53.327068.parquet' - split: 2024_04_17T10_06_01.259030 path: - '**/details_harness|hendrycksTest-public_relations|5_2024-04-17T10-06-01.259030.parquet' - split: latest path: - '**/details_harness|hendrycksTest-public_relations|5_2024-04-17T10-06-01.259030.parquet' - config_name: harness_hendrycksTest_security_studies_5 data_files: - split: 2024_04_17T09_14_53.327068 path: - '**/details_harness|hendrycksTest-security_studies|5_2024-04-17T09-14-53.327068.parquet' - split: 2024_04_17T10_06_01.259030 path: - '**/details_harness|hendrycksTest-security_studies|5_2024-04-17T10-06-01.259030.parquet' - split: latest path: - '**/details_harness|hendrycksTest-security_studies|5_2024-04-17T10-06-01.259030.parquet' - config_name: harness_hendrycksTest_sociology_5 data_files: - split: 2024_04_17T09_14_53.327068 path: - '**/details_harness|hendrycksTest-sociology|5_2024-04-17T09-14-53.327068.parquet' - split: 2024_04_17T10_06_01.259030 path: - '**/details_harness|hendrycksTest-sociology|5_2024-04-17T10-06-01.259030.parquet' - split: latest path: - '**/details_harness|hendrycksTest-sociology|5_2024-04-17T10-06-01.259030.parquet' - config_name: harness_hendrycksTest_us_foreign_policy_5 data_files: - split: 2024_04_17T09_14_53.327068 path: - '**/details_harness|hendrycksTest-us_foreign_policy|5_2024-04-17T09-14-53.327068.parquet' - split: 2024_04_17T10_06_01.259030 path: - '**/details_harness|hendrycksTest-us_foreign_policy|5_2024-04-17T10-06-01.259030.parquet' - split: latest path: - '**/details_harness|hendrycksTest-us_foreign_policy|5_2024-04-17T10-06-01.259030.parquet' - config_name: harness_hendrycksTest_virology_5 data_files: - split: 2024_04_17T09_14_53.327068 path: - '**/details_harness|hendrycksTest-virology|5_2024-04-17T09-14-53.327068.parquet' - split: 2024_04_17T10_06_01.259030 path: - '**/details_harness|hendrycksTest-virology|5_2024-04-17T10-06-01.259030.parquet' - split: latest path: - '**/details_harness|hendrycksTest-virology|5_2024-04-17T10-06-01.259030.parquet' - config_name: harness_hendrycksTest_world_religions_5 data_files: - split: 2024_04_17T09_14_53.327068 path: - '**/details_harness|hendrycksTest-world_religions|5_2024-04-17T09-14-53.327068.parquet' - split: 2024_04_17T10_06_01.259030 path: - '**/details_harness|hendrycksTest-world_religions|5_2024-04-17T10-06-01.259030.parquet' - split: latest path: - '**/details_harness|hendrycksTest-world_religions|5_2024-04-17T10-06-01.259030.parquet' - config_name: harness_truthfulqa_mc_0 data_files: - split: 2024_04_17T09_14_53.327068 path: - '**/details_harness|truthfulqa:mc|0_2024-04-17T09-14-53.327068.parquet' - split: 2024_04_17T10_06_01.259030 path: - '**/details_harness|truthfulqa:mc|0_2024-04-17T10-06-01.259030.parquet' - split: latest path: - '**/details_harness|truthfulqa:mc|0_2024-04-17T10-06-01.259030.parquet' - config_name: harness_winogrande_5 data_files: - split: 2024_04_17T09_14_53.327068 path: - '**/details_harness|winogrande|5_2024-04-17T09-14-53.327068.parquet' - split: 2024_04_17T10_06_01.259030 path: - '**/details_harness|winogrande|5_2024-04-17T10-06-01.259030.parquet' - split: latest path: - '**/details_harness|winogrande|5_2024-04-17T10-06-01.259030.parquet' - config_name: results data_files: - split: 2024_04_17T09_14_53.327068 path: - results_2024-04-17T09-14-53.327068.parquet - split: 2024_04_17T10_06_01.259030 path: - results_2024-04-17T10-06-01.259030.parquet - split: latest path: - results_2024-04-17T10-06-01.259030.parquet --- # Dataset Card for Evaluation run of numfa/numfa_3b_1epoch <!-- Provide a quick summary of the dataset. --> Dataset automatically created during the evaluation run of model [numfa/numfa_3b_1epoch](https://huggingface.co/numfa/numfa_3b_1epoch) on the [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard). The dataset is composed of 63 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 aggregated metrics on the [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)). To load the details from a run, you can for instance do the following: ```python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_numfa__numfa_3b_1epoch", "harness_winogrande_5", split="train") ``` ## Latest results These are the [latest results from run 2024-04-17T10:06:01.259030](https://huggingface.co/datasets/open-llm-leaderboard/details_numfa__numfa_3b_1epoch/blob/main/results_2024-04-17T10-06-01.259030.json)(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the "latest" split for each eval): ```python { "all": { "acc": 0.24284410435712883, "acc_stderr": 0.030301622085671234, "acc_norm": 0.24402676198164272, "acc_norm_stderr": 0.031108594599294343, "mc1": 0.24112607099143207, "mc1_stderr": 0.01497482727975233, "mc2": 0.4242822290197145, "mc2_stderr": 0.014964426554036708 }, "harness|arc:challenge|25": { "acc": 0.2098976109215017, "acc_stderr": 0.011900548748047456, "acc_norm": 0.257679180887372, "acc_norm_stderr": 0.012780770562768405 }, "harness|hellaswag|10": { "acc": 0.3194582752439753, "acc_stderr": 0.004653138360948109, "acc_norm": 0.37273451503684524, "acc_norm_stderr": 0.004825441080261187 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.22, "acc_stderr": 0.04163331998932268, "acc_norm": 0.22, "acc_norm_stderr": 0.04163331998932268 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.18518518518518517, "acc_stderr": 0.03355677216313142, "acc_norm": 0.18518518518518517, "acc_norm_stderr": 0.03355677216313142 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.17763157894736842, "acc_stderr": 0.031103182383123398, "acc_norm": 0.17763157894736842, "acc_norm_stderr": 0.031103182383123398 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.21132075471698114, "acc_stderr": 0.025125766484827845, "acc_norm": 0.21132075471698114, "acc_norm_stderr": 0.025125766484827845 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.2569444444444444, "acc_stderr": 0.03653946969442099, "acc_norm": 0.2569444444444444, "acc_norm_stderr": 0.03653946969442099 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.21, "acc_stderr": 0.04093601807403326, "acc_norm": 0.21, "acc_norm_stderr": 0.04093601807403326 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.36, "acc_stderr": 0.04824181513244218, "acc_norm": 0.36, "acc_norm_stderr": 0.04824181513244218 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.22, "acc_stderr": 0.04163331998932269, "acc_norm": 0.22, "acc_norm_stderr": 0.04163331998932269 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.20809248554913296, "acc_stderr": 0.030952890217749874, "acc_norm": 0.20809248554913296, "acc_norm_stderr": 0.030952890217749874 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.21568627450980393, "acc_stderr": 0.04092563958237654, "acc_norm": 0.21568627450980393, "acc_norm_stderr": 0.04092563958237654 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.28, "acc_stderr": 0.045126085985421276, "acc_norm": 0.28, "acc_norm_stderr": 0.045126085985421276 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.26382978723404255, "acc_stderr": 0.028809989854102973, "acc_norm": 0.26382978723404255, "acc_norm_stderr": 0.028809989854102973 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.2543859649122807, "acc_stderr": 0.040969851398436695, "acc_norm": 0.2543859649122807, "acc_norm_stderr": 0.040969851398436695 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.2413793103448276, "acc_stderr": 0.03565998174135302, "acc_norm": 0.2413793103448276, "acc_norm_stderr": 0.03565998174135302 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.22486772486772486, "acc_stderr": 0.021502096078229147, "acc_norm": 0.22486772486772486, "acc_norm_stderr": 0.021502096078229147 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.29365079365079366, "acc_stderr": 0.04073524322147127, "acc_norm": 0.29365079365079366, "acc_norm_stderr": 0.04073524322147127 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.18, "acc_stderr": 0.038612291966536934, "acc_norm": 0.18, "acc_norm_stderr": 0.038612291966536934 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.19032258064516128, "acc_stderr": 0.022331707611823078, "acc_norm": 0.19032258064516128, "acc_norm_stderr": 0.022331707611823078 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.17733990147783252, "acc_stderr": 0.026874337276808356, "acc_norm": 0.17733990147783252, "acc_norm_stderr": 0.026874337276808356 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.22, "acc_stderr": 0.041633319989322695, "acc_norm": 0.22, "acc_norm_stderr": 0.041633319989322695 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.22424242424242424, "acc_stderr": 0.032568666616811015, "acc_norm": 0.22424242424242424, "acc_norm_stderr": 0.032568666616811015 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.17676767676767677, "acc_stderr": 0.027178752639044915, "acc_norm": 0.17676767676767677, "acc_norm_stderr": 0.027178752639044915 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.21761658031088082, "acc_stderr": 0.02977866303775295, "acc_norm": 0.21761658031088082, "acc_norm_stderr": 0.02977866303775295 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.3282051282051282, "acc_stderr": 0.023807633198657262, "acc_norm": 0.3282051282051282, "acc_norm_stderr": 0.023807633198657262 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.27037037037037037, "acc_stderr": 0.027080372815145647, "acc_norm": 0.27037037037037037, "acc_norm_stderr": 0.027080372815145647 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.23529411764705882, "acc_stderr": 0.027553614467863825, "acc_norm": 0.23529411764705882, "acc_norm_stderr": 0.027553614467863825 }, "harness|hendrycksTest-high_school_physics|5": { "acc": 0.2119205298013245, "acc_stderr": 0.033367670865679766, "acc_norm": 0.2119205298013245, "acc_norm_stderr": 0.033367670865679766 }, "harness|hendrycksTest-high_school_psychology|5": { "acc": 0.1963302752293578, "acc_stderr": 0.017030719339154357, "acc_norm": 0.1963302752293578, "acc_norm_stderr": 0.017030719339154357 }, "harness|hendrycksTest-high_school_statistics|5": { "acc": 0.33796296296296297, "acc_stderr": 0.03225941352631295, "acc_norm": 0.33796296296296297, "acc_norm_stderr": 0.03225941352631295 }, "harness|hendrycksTest-high_school_us_history|5": { "acc": 0.25, "acc_stderr": 0.03039153369274154, "acc_norm": 0.25, "acc_norm_stderr": 0.03039153369274154 }, "harness|hendrycksTest-high_school_world_history|5": { "acc": 0.270042194092827, "acc_stderr": 0.028900721906293426, "acc_norm": 0.270042194092827, "acc_norm_stderr": 0.028900721906293426 }, "harness|hendrycksTest-human_aging|5": { "acc": 0.31390134529147984, "acc_stderr": 0.031146796482972465, "acc_norm": 0.31390134529147984, "acc_norm_stderr": 0.031146796482972465 }, "harness|hendrycksTest-human_sexuality|5": { "acc": 0.2595419847328244, "acc_stderr": 0.03844876139785271, "acc_norm": 0.2595419847328244, "acc_norm_stderr": 0.03844876139785271 }, "harness|hendrycksTest-international_law|5": { "acc": 0.2396694214876033, "acc_stderr": 0.03896878985070417, "acc_norm": 0.2396694214876033, "acc_norm_stderr": 0.03896878985070417 }, "harness|hendrycksTest-jurisprudence|5": { "acc": 0.24074074074074073, "acc_stderr": 0.0413311944024384, "acc_norm": 0.24074074074074073, "acc_norm_stderr": 0.0413311944024384 }, "harness|hendrycksTest-logical_fallacies|5": { "acc": 0.2147239263803681, "acc_stderr": 0.03226219377286774, "acc_norm": 0.2147239263803681, "acc_norm_stderr": 0.03226219377286774 }, "harness|hendrycksTest-machine_learning|5": { "acc": 0.32142857142857145, "acc_stderr": 0.04432804055291519, "acc_norm": 0.32142857142857145, "acc_norm_stderr": 0.04432804055291519 }, "harness|hendrycksTest-management|5": { "acc": 0.17475728155339806, "acc_stderr": 0.037601780060266224, "acc_norm": 0.17475728155339806, "acc_norm_stderr": 0.037601780060266224 }, "harness|hendrycksTest-marketing|5": { "acc": 0.25213675213675213, "acc_stderr": 0.02844796547623102, "acc_norm": 0.25213675213675213, "acc_norm_stderr": 0.02844796547623102 }, "harness|hendrycksTest-medical_genetics|5": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-miscellaneous|5": { "acc": 0.24010217113665389, "acc_stderr": 0.015274685213734195, "acc_norm": 0.24010217113665389, "acc_norm_stderr": 0.015274685213734195 }, "harness|hendrycksTest-moral_disputes|5": { "acc": 0.24855491329479767, "acc_stderr": 0.023267528432100174, "acc_norm": 0.24855491329479767, "acc_norm_stderr": 0.023267528432100174 }, "harness|hendrycksTest-moral_scenarios|5": { "acc": 0.23798882681564246, "acc_stderr": 0.014242630070574889, "acc_norm": 0.23798882681564246, "acc_norm_stderr": 0.014242630070574889 }, "harness|hendrycksTest-nutrition|5": { "acc": 0.22549019607843138, "acc_stderr": 0.023929155517351284, "acc_norm": 0.22549019607843138, "acc_norm_stderr": 0.023929155517351284 }, "harness|hendrycksTest-philosophy|5": { "acc": 0.1864951768488746, "acc_stderr": 0.02212243977248077, "acc_norm": 0.1864951768488746, "acc_norm_stderr": 0.02212243977248077 }, "harness|hendrycksTest-prehistory|5": { "acc": 0.2191358024691358, "acc_stderr": 0.0230167056402622, "acc_norm": 0.2191358024691358, "acc_norm_stderr": 0.0230167056402622 }, "harness|hendrycksTest-professional_accounting|5": { "acc": 0.23404255319148937, "acc_stderr": 0.025257861359432417, "acc_norm": 0.23404255319148937, "acc_norm_stderr": 0.025257861359432417 }, "harness|hendrycksTest-professional_law|5": { "acc": 0.2457627118644068, "acc_stderr": 0.010996156635142692, "acc_norm": 0.2457627118644068, "acc_norm_stderr": 0.010996156635142692 }, "harness|hendrycksTest-professional_medicine|5": { "acc": 0.27205882352941174, "acc_stderr": 0.027033041151681456, "acc_norm": 0.27205882352941174, "acc_norm_stderr": 0.027033041151681456 }, "harness|hendrycksTest-professional_psychology|5": { "acc": 0.25, "acc_stderr": 0.01751781884501444, "acc_norm": 0.25, "acc_norm_stderr": 0.01751781884501444 }, "harness|hendrycksTest-public_relations|5": { "acc": 0.20909090909090908, "acc_stderr": 0.03895091015724136, "acc_norm": 0.20909090909090908, "acc_norm_stderr": 0.03895091015724136 }, "harness|hendrycksTest-security_studies|5": { "acc": 0.18775510204081633, "acc_stderr": 0.02500025603954621, "acc_norm": 0.18775510204081633, "acc_norm_stderr": 0.02500025603954621 }, "harness|hendrycksTest-sociology|5": { "acc": 0.24378109452736318, "acc_stderr": 0.03036049015401465, "acc_norm": 0.24378109452736318, "acc_norm_stderr": 0.03036049015401465 }, "harness|hendrycksTest-us_foreign_policy|5": { "acc": 0.23, "acc_stderr": 0.04229525846816505, "acc_norm": 0.23, "acc_norm_stderr": 0.04229525846816505 }, "harness|hendrycksTest-virology|5": { "acc": 0.28313253012048195, "acc_stderr": 0.03507295431370518, "acc_norm": 0.28313253012048195, "acc_norm_stderr": 0.03507295431370518 }, "harness|hendrycksTest-world_religions|5": { "acc": 0.32748538011695905, "acc_stderr": 0.035993357714560276, "acc_norm": 0.32748538011695905, "acc_norm_stderr": 0.035993357714560276 }, "harness|truthfulqa:mc|0": { "mc1": 0.24112607099143207, "mc1_stderr": 0.01497482727975233, "mc2": 0.4242822290197145, "mc2_stderr": 0.014964426554036708 }, "harness|winogrande|5": { "acc": 0.5169692186266772, "acc_stderr": 0.014044390401612981 }, "harness|gsm8k|5": { "acc": 0.0, "acc_stderr": 0.0 } } ``` ## Dataset Details ### Dataset Description <!-- Provide a longer summary of what this dataset is. --> - **Curated by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] ### Dataset Sources [optional] <!-- Provide the basic links for the dataset. --> - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses <!-- Address questions around how the dataset is intended to be used. --> ### Direct Use <!-- This section describes suitable use cases for the dataset. --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the dataset will not work well for. --> [More Information Needed] ## Dataset Structure <!-- This section provides a description of the dataset fields, and additional information about the dataset structure such as criteria used to create the splits, relationships between data points, etc. --> [More Information Needed] ## Dataset Creation ### Curation Rationale <!-- Motivation for the creation of this dataset. --> [More Information Needed] ### Source Data <!-- This section describes the source data (e.g. news text and headlines, social media posts, translated sentences, ...). --> #### Data Collection and Processing <!-- This section describes the data collection and processing process such as data selection criteria, filtering and normalization methods, tools and libraries used, etc. --> [More Information Needed] #### Who are the source data producers? <!-- This section describes the people or systems who originally created the data. It should also include self-reported demographic or identity information for the source data creators if this information is available. --> [More Information Needed] ### Annotations [optional] <!-- If the dataset contains annotations which are not part of the initial data collection, use this section to describe them. --> #### Annotation process <!-- This section describes the annotation process such as annotation tools used in the process, the amount of data annotated, annotation guidelines provided to the annotators, interannotator statistics, annotation validation, etc. --> [More Information Needed] #### Who are the annotators? <!-- This section describes the people or systems who created the annotations. --> [More Information Needed] #### Personal and Sensitive Information <!-- State whether the dataset contains data that might be considered personal, sensitive, or private (e.g., data that reveals addresses, uniquely identifiable names or aliases, racial or ethnic origins, sexual orientations, religious beliefs, political opinions, financial or health data, etc.). If efforts were made to anonymize the data, describe the anonymization process. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users should be made aware of the risks, biases and limitations of the dataset. More information needed for further recommendations. ## Citation [optional] <!-- If there is a paper or blog post introducing the dataset, the APA and Bibtex information for that should go in this section. --> **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the dataset or dataset card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Dataset Card Authors [optional] [More Information Needed] ## Dataset Card Contact [More Information Needed]

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 numfa/numfa_3b_1epoch 在 Open LLM Leaderboard 上的评估运行期间自动创建的。数据集由 63 个配置组成,每个配置对应一个评估任务。

数据集结构

  • 配置数量:63
  • 创建来源:从 2 次运行中创建,每个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" 分割始终指向最新结果。
  • 聚合结果:一个额外的配置 "results" 存储所有运行的聚合结果,用于计算和显示在 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_numfa__numfa_3b_1epoch", "harness_winogrande_5", split="train")

最新结果

这些是最新结果的示例,来自 2024-04-17T10:06:01.259030 的运行: python { "all": { "acc": 0.24284410435712883, "acc_stderr": 0.030301622085671234, "acc_norm": 0.24402676198164272, "acc_norm_stderr": 0.031108594599294343, "mc1": 0.24112607099143207, "mc1_stderr": 0.01497482727975233, "mc2": 0.4242822290197145, "mc2_stderr": 0.014964426554036708 }, "harness|arc:challenge|25": { "acc": 0.2098976109215017, "acc_stderr": 0.011900548748047456, "acc_norm": 0.257679180887372, "acc_norm_stderr": 0.012780770562768405 }, "harness|hellaswag|10": { "acc": 0.3194582752439753, "acc_stderr": 0.004653138360948109, "acc_norm": 0.37273451503684524, "acc_norm_stderr": 0.004825441080261187 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.22, "acc_stderr": 0.04163331998932268, "acc_norm": 0.22, "acc_norm_stderr": 0.04163331998932268 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.18518518518518517, "acc_stderr": 0.03355677216313142, "acc_norm": 0.18518518518518517, "acc_norm_stderr": 0.03355677216313142 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.17763157894736842, "acc_stderr": 0.031103182383123398, "acc_norm": 0.17763157894736842, "acc_norm_stderr": 0.031103182383123398 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.21132075471698114, "acc_stderr": 0.025125766484827845, "acc_norm": 0.21132075471698114, "acc_norm_stderr": 0.025125766484827845 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.2569444444444444, "acc_stderr": 0.03653946969442099, "acc_norm": 0.2569444444444444, "acc_norm_stderr": 0.03653946969442099 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.21, "acc_stderr": 0.04093601807403326, "acc_norm": 0.21, "acc_norm_stderr": 0.04093601807403326 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.36, "acc_stderr": 0.04824181513244218, "acc_norm": 0.36, "acc_norm_stderr": 0.04824181513244218 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.22, "acc_stderr": 0.04163331998932269, "acc_norm": 0.22, "acc_norm_stderr": 0.04163331998932269 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.20809248554913296, "acc_stderr": 0.030952890217749874, "acc_norm": 0.20809248554913296, "acc_norm_stderr": 0.030952890217749874 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.21568627450980393, "acc_stderr": 0.04092563958237654, "acc_norm": 0.21568627450980393, "acc_norm_stderr": 0.04092563958237654 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.28, "acc_stderr": 0.045126085985421276, "acc_norm": 0.28, "acc_norm_stderr": 0.045126085985421276 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.26382978723404255, "acc_stderr": 0.028809989854102973, "acc_norm": 0.26382978723404255, "acc_norm_stderr": 0.028809989854102973 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.2543859649122807, "acc_stderr": 0.040969851398436695, "acc_norm": 0.2543859649122807, "acc_norm_stderr": 0.040969851398436695 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.2413793103448276, "acc_stderr": 0.03565998174135302, "acc_norm": 0.2413793103448276, "acc_norm_stderr": 0.03565998174135302 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.22486772486772486, "acc_stderr": 0.021502096078229147, "acc_norm": 0.22486772486772486, "acc_norm_stderr": 0.021502096078229147 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.29365079365079366, "acc_stderr": 0.04073524322147127, "acc_norm": 0.29365079365079366, "acc_norm_stderr": 0.04073524322147127 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.18, "acc_stderr": 0.038612291966536934, "acc_norm": 0.18, "acc_norm_stderr": 0.038612291966536934 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.19032258064516128, "acc_stderr": 0.022331707611823078, "acc_norm": 0.19032258064516128, "acc_norm_stderr": 0.022331707611823078 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.17733990147783252, "acc_stderr": 0.026874337276808356, "acc_norm": 0.17733990147783252, "acc_norm_stderr": 0.026874337276808356 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.22, "acc_stderr": 0.041633319989322695, "acc_norm": 0.22, "acc_norm_stderr": 0.041633319989322695 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.22424242424242424, "acc_stderr": 0.032568666616811015, "acc_norm": 0.22424242424242424, "acc_norm_stderr": 0.032568666616811015 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.17676767676767677, "acc_stderr": 0.027178752639044915, "acc_norm": 0.17676767676767677, "acc_norm_stderr": 0.027178752639044915 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.21761658031088082, "acc_stderr": 0.02977866303775295, "acc_norm": 0.21761658031088082, "acc_norm_stderr": 0.02977866303775295 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.3282051282051282, "acc_stderr": 0.023807633198657262, "acc_norm": 0.3282051282051282, "acc_norm_stderr": 0.023807633198657262 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.27037037037037037, "acc_stderr": 0.027080372815145647, "acc_norm": 0.27037037037037037, "acc_norm_stderr": 0.027080

搜集汇总
数据集介绍
open-llm-leaderboard-old/details_numfa__numfa_3b_1epoch 数据集图片
构建方式
在大语言模型评测领域,Open LLM Leaderboard为模型性能的横向比较提供了标准化平台。该数据集正是为记录模型numfa/numfa_3b_1epoch在Leaderboard上的评估过程而自动生成,完整保存了模型在63个不同评测任务上的详细表现。数据集由两次独立的评估运行构成,每次运行对应一个独立的分割(split),并以运行时间戳命名。每个评测任务被组织为独立的配置(configuration),共计63个配置,分别对应ARC-Challenge、HellaSwag、MMLU、TruthfulQA、Winogrande和GSM8K等经典基准。此外,数据集额外包含一个名为“results”的配置,用于存储聚合后的评估指标,这些指标直接服务于Leaderboard上最终分数的计算与展示。
特点
该数据集的结构设计体现了高度的系统性与实用性。63个任务配置各自独立,便于研究者针对单一任务进行深入分析。每个配置内部,两次运行的结果以独立分割的形式并存,其中“train”分割始终指向最新一次的评估结果,确保了数据引用的时效性。这种设计不仅保留了评估历史的完整性,也为复现和对比不同时间点的模型表现提供了便利。数据集以Parquet格式存储,兼顾了高效读写与丰富的元数据承载能力。聚合的“results”配置则提供了宏观视角,使得模型在全部任务上的综合能力一目了然。
使用方法
研究者可通过Hugging Face Datasets库便捷地加载和使用该数据集。以Python为例,使用`load_dataset`函数,指定数据集名称“open-llm-leaderboard/details_numfa__numfa_3b_1epoch”、目标任务配置(如“harness_winogrande_5”)以及所需的分割(如“train”),即可获取对应任务的详细评估记录。若需加载聚合结果,则可选用“results”配置。这种模块化的加载方式使得研究者能够灵活地聚焦于特定任务或宏观分析,极大地降低了数据处理的复杂度,为后续的模型性能分析、消融实验和对比研究提供了坚实的数据基础。
背景与挑战
背景概述
该数据集源自HuggingFace社区发起的Open LLM Leaderboard评测平台,由HuggingFace团队于2024年创建,旨在系统评估开源大语言模型在多样化自然语言理解与推理任务上的表现。核心研究问题聚焦于如何通过标准化、可复现的评测框架,客观衡量模型在常识推理、知识问答、数学求解等维度的能力。该数据集记录了模型numfa/numfa_3b_1epoch在63项任务配置上的详细评测结果,涵盖ARC-Challenge、HellaSwag、MMLU、TruthfulQA、Winogrande及GSM8K等基准测试,为社区提供了模型性能的透明化参考,推动了开源大模型评估体系的规范化发展。
当前挑战
当前面临的核心挑战在于领域问题的复杂性:大语言模型在常识推理(如HellaSwag准确率仅31.9%)和数学逻辑(GSM8K准确率为0%)等任务上表现显著不足,暴露出模型在深层语义理解与符号推理方面的局限。构建过程中遇到的挑战则包括:评测任务覆盖57个学科领域,需确保数据格式统一与结果可复现;多轮评测的时间戳管理和结果聚合增加了数据处理的复杂度;且部分任务(如MMLU子集)的样本量有限,导致统计显著性受限,需谨慎解读性能差异。
常用场景
经典使用场景
该数据集为Open LLM Leaderboard上对模型numfa/numfa_3b_1epoch进行自动化评估的产物,涵盖了63个评估任务配置,每个配置对应一项具体评测,如ARC挑战赛、HellaSwag、MMLU各学科子集、TruthfulQA、Winogrande及GSM8K等。研究者可利用此数据集复现模型在主流大语言模型基准上的细粒度表现,深入分析模型在不同能力维度(如常识推理、数学计算、知识理解与事实一致性)上的优劣。通过加载特定任务(如harness_winogrande_5)的latest分割,可获取最新评测结果,为模型对比与性能追踪提供标准化、可复现的数据支撑。
衍生相关工作
该数据集衍生了多项经典工作,最直接的是Open LLM Leaderboard本身,它已成为社区公认的模型能力竞技场,催生了大量关于模型评估方法论的研究。例如,基于此数据集中的MMLU子任务结果,研究者提出了领域特异性能力剖析方法,用于识别模型在抽象代数、临床知识等学科上的偏差;同时,该数据集为TruthfulQA的mc1与mc2指标提供了对比基准,推动了事实一致性增强技术的探索。此外,GSM8K上零精度的记录引发了关于数学推理能力瓶颈的讨论,衍生出针对少样本提示与思维链优化的专项研究,这些工作共同深化了对大语言模型能力边界与提升路径的理解。
数据集最近研究
最新研究方向
该数据集记录了numfa/numfa_3b_1epoch模型在Open LLM Leaderboard上的评估结果,涵盖了ARC挑战赛、HellaSwag、MMLU(涵盖57个学科)以及GSM8K等多项主流基准测试。当前大语言模型领域的前沿研究方向聚焦于模型在复杂推理与多领域知识上的泛化能力,而该数据集通过细致的任务拆分与分次运行结果对比,为研究者提供了分析模型在常识推理、科学知识、数学问题等维度表现的微观视角。特别是其在GSM8K上得分为零的现象,凸显了小型模型在数学推理这一热点挑战中的瓶颈,推动了针对参数规模与推理能力关系的研究,对理解模型能力边界及优化训练策略具有重要参考意义。
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