open-llm-leaderboard-old/details_MTSAIR__MultiVerse_70B
收藏数据集概述
数据集简介
该数据集是在模型 MTSAIR/MultiVerse_70B 在 Open LLM Leaderboard 上的评估运行期间自动创建的。数据集包含 63 个配置，每个配置对应一个评估任务。
数据集结构
数据集由 2 次运行创建，每次运行可以在每个配置中找到特定的分割，分割名称使用运行的时间戳。"train" 分割始终指向最新的结果。此外，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
以下是加载特定运行详细信息的示例代码： python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_MTSAIR__MultiVerse_70B", "harness_winogrande_5", split="train")
最新结果
以下是 2024-03-28T11:20:18.515649 运行 的最新结果： python { "all": { "acc": 0.7830598805961457, "acc_stderr": 0.027571176888417693, "acc_norm": 0.7846693275609173, "acc_norm_stderr": 0.028121251178584224, "mc1": 0.6499388004895961, "mc1_stderr": 0.016697949420151022, "mc2": 0.7508968077654237, "mc2_stderr": 0.014534916537858438 }, "harness|arc:challenge|25": { "acc": 0.7636518771331058, "acc_stderr": 0.012414960524301822, "acc_norm": 0.7858361774744027, "acc_norm_stderr": 0.01198838320596649 }, "harness|hellaswag|10": { "acc": 0.7490539733120892, "acc_stderr": 0.0043267144532667355, "acc_norm": 0.8974307906791475, "acc_norm_stderr": 0.0030277534195929483 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.45, "acc_stderr": 0.049999999999999996, "acc_norm": 0.45, "acc_norm_stderr": 0.049999999999999996 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.7333333333333333, "acc_stderr": 0.038201699145179055, "acc_norm": 0.7333333333333333, "acc_norm_stderr": 0.038201699145179055 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.8881578947368421, "acc_stderr": 0.02564834125169361, "acc_norm": 0.8881578947368421, "acc_norm_stderr": 0.02564834125169361 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.79, "acc_stderr": 0.040936018074033256, "acc_norm": 0.79, "acc_norm_stderr": 0.040936018074033256 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.8528301886792453, "acc_stderr": 0.02180412613479737, "acc_norm": 0.8528301886792453, "acc_norm_stderr": 0.02180412613479737 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.9236111111111112, "acc_stderr": 0.022212203938345918, "acc_norm": 0.9236111111111112, "acc_norm_stderr": 0.022212203938345918 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.54, "acc_stderr": 0.05009082659620332, "acc_norm": 0.54, "acc_norm_stderr": 0.05009082659620332 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.64, "acc_stderr": 0.048241815132442176, "acc_norm": 0.64, "acc_norm_stderr": 0.048241815132442176 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.48, "acc_stderr": 0.050211673156867795, "acc_norm": 0.48, "acc_norm_stderr": 0.050211673156867795 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.7630057803468208, "acc_stderr": 0.032424147574830975, "acc_norm": 0.7630057803468208, "acc_norm_stderr": 0.032424147574830975 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.5294117647058824, "acc_stderr": 0.049665709039785295, "acc_norm": 0.5294117647058824, "acc_norm_stderr": 0.049665709039785295 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.84, "acc_stderr": 0.03684529491774709, "acc_norm": 0.84, "acc_norm_stderr": 0.03684529491774709 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.8468085106382979, "acc_stderr": 0.023545179061675203, "acc_norm": 0.8468085106382979, "acc_norm_stderr": 0.023545179061675203 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.5964912280701754, "acc_stderr": 0.04615186962583706, "acc_norm": 0.5964912280701754, "acc_norm_stderr": 0.04615186962583706 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.8, "acc_stderr": 0.0333333333333333, "acc_norm": 0.8, "acc_norm_stderr": 0.0333333333333333 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.6957671957671958, "acc_stderr": 0.023695415009463087, "acc_norm": 0.6957671957671958, "acc_norm_stderr": 0.023695415009463087 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.5476190476190477, "acc_stderr": 0.044518079590553275, "acc_norm": 0.5476190476190477, "acc_norm_stderr": 0.044518079590553275 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.58, "acc_stderr": 0.049604496374885836, "acc_norm": 0.58, "acc_norm_stderr": 0.049604496374885836 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.8870967741935484, "acc_stderr": 0.018003603325863614, "acc_norm": 0.8870967741935484, "acc_norm_stderr": 0.018003603325863614 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.7142857142857143, "acc_stderr": 0.03178529710642751, "acc_norm": 0.7142857142857143, "acc_norm_stderr": 0.03178529710642751 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.79, "acc_stderr": 0.040936018074033256, "acc_norm": 0.79, "acc_norm_stderr": 0.040936018074033256 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.8666666666666667, "acc_stderr": 0.026544435312706467, "acc_norm": 0.8666666666666667, "acc_norm_stderr": 0.026544435312706467 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.9292929292929293, "acc_stderr": 0.01826310542019948, "acc_norm": 0.9292929292929293, "acc_norm_stderr": 0.01826310542019948 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9844559585492227, "acc_stderr": 0.008927492715084334, "acc_norm": 0.9844559585492227, "acc_norm_stderr": 0.008927492715084334 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.8025641025641026, "acc_stderr": 0.02018264696867485, "acc_norm": 0.8025641025641026, "acc_norm_stderr": 0.02018264696867485 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.5037037037037037, "acc_stderr": 0.03048470166508437, "acc_norm": 0.5037037037037037, "acc_norm_stderr": 0.03048470166508437
