open-llm-leaderboard-old/details__fsx_shared-falcon-180B_converted_safetensors
收藏数据集概述
数据集名称
Evaluation run of _fsx_shared-falcon-180B_converted_safetensors
数据集摘要
该数据集是在对模型 _fsx_shared-falcon-180B_converted_safetensors 进行评估运行期间自动创建的，用于 Open LLM Leaderboard。
数据集组成
数据集由61个配置组成，每个配置对应一个评估任务。数据集是从1次运行中创建的，每次运行可以在每个配置中找到特定的分割，分割名称使用运行的时间戳。"train" 分割始终指向最新的结果。
额外配置
一个额外的配置 "results" 存储了所有运行的聚合结果，用于计算和显示 Open LLM Leaderboard 上的聚合指标。
数据加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details__fsx_shared-falcon-180B_converted_safetensors", "harness_truthfulqa_mc_0", split="train")
最新结果
以下是 2023-09-12T12:25:36.361219 运行的最新结果：
python { "all": { "acc": 0.6616129047646827, "acc_stderr": 0.032465318041276114, "acc_norm": 0.6652364807936633, "acc_norm_stderr": 0.032437975492240805, "mc1": 0.43451652386780903, "mc1_stderr": 0.017352738749259564, "mc2": 0.6219407369869773, "mc2_stderr": 0.015400116321762768 }, "harness|arc:challenge|25": { "acc": 0.6791808873720137, "acc_stderr": 0.013640943091946524, "acc_norm": 0.7090443686006825, "acc_norm_stderr": 0.013273077865907588 }, "harness|hellaswag|10": { "acc": 0.681736705835491, "acc_stderr": 0.004648503177353969, "acc_norm": 0.86566421031667, "acc_norm_stderr": 0.0034031580103095565 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.33, "acc_stderr": 0.04725815626252606, "acc_norm": 0.33, "acc_norm_stderr": 0.04725815626252606 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.5333333333333333, "acc_stderr": 0.043097329010363554, "acc_norm": 0.5333333333333333, "acc_norm_stderr": 0.043097329010363554 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.7302631578947368, "acc_stderr": 0.03611780560284898, "acc_norm": 0.7302631578947368, "acc_norm_stderr": 0.03611780560284898 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.67, "acc_stderr": 0.047258156262526094, "acc_norm": 0.67, "acc_norm_stderr": 0.047258156262526094 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.7169811320754716, "acc_stderr": 0.027724236492700914, "acc_norm": 0.7169811320754716, "acc_norm_stderr": 0.027724236492700914 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7777777777777778, "acc_stderr": 0.034765901043041336, "acc_norm": 0.7777777777777778, "acc_norm_stderr": 0.034765901043041336 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.5, "acc_stderr": 0.050251890762960605, "acc_norm": 0.5, "acc_norm_stderr": 0.050251890762960605 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.53, "acc_stderr": 0.050161355804659205, "acc_norm": 0.53, "acc_norm_stderr": 0.050161355804659205 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.42, "acc_stderr": 0.04960449637488584, "acc_norm": 0.42, "acc_norm_stderr": 0.04960449637488584 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6820809248554913, "acc_stderr": 0.0355068398916558, "acc_norm": 0.6820809248554913, "acc_norm_stderr": 0.0355068398916558 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.3627450980392157, "acc_stderr": 0.047840607041056527, "acc_norm": 0.3627450980392157, "acc_norm_stderr": 0.047840607041056527 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.78, "acc_stderr": 0.041633319989322626, "acc_norm": 0.78, "acc_norm_stderr": 0.041633319989322626 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.6212765957446809, "acc_stderr": 0.031709956060406545, "acc_norm": 0.6212765957446809, "acc_norm_stderr": 0.031709956060406545 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.38596491228070173, "acc_stderr": 0.045796394220704334, "acc_norm": 0.38596491228070173, "acc_norm_stderr": 0.045796394220704334 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.6068965517241379, "acc_stderr": 0.040703290137070705, "acc_norm": 0.6068965517241379, "acc_norm_stderr": 0.040703290137070705 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.4894179894179894, "acc_stderr": 0.02574554227604549, "acc_norm": 0.4894179894179894, "acc_norm_stderr": 0.02574554227604549 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.373015873015873, "acc_stderr": 0.04325506042017086, "acc_norm": 0.373015873015873, "acc_norm_stderr": 0.04325506042017086 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.48, "acc_stderr": 0.050211673156867795, "acc_norm": 0.48, "acc_norm_stderr": 0.050211673156867795 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.8096774193548387, "acc_stderr": 0.022331707611823078, "acc_norm": 0.8096774193548387, "acc_norm_stderr": 0.022331707611823078 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.5270935960591133, "acc_stderr": 0.03512819077876106, "acc_norm": 0.5270935960591133, "acc_norm_stderr": 0.03512819077876106 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.67, "acc_stderr": 0.047258156262526066, "acc_norm": 0.67, "acc_norm_stderr": 0.047258156262526066 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7575757575757576, "acc_stderr": 0.03346409881055953, "acc_norm": 0.7575757575757576, "acc_norm_stderr": 0.03346409881055953 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.8232323232323232, "acc_stderr": 0.027178752639044915, "acc_norm": 0.8232323232323232, "acc_norm_stderr": 0.027178752639044915 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.927461139896373, "acc_stderr": 0.01871899852067817, "acc_norm": 0.927461139896373, "acc_norm_stderr": 0.01871899852067817 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6461538461538462, "acc_stderr": 0.024243783994062157, "acc_norm": 0.6461538461538462, "acc_norm_stderr": 0.024243783994062157 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.32222222222222224, "acc_stderr":
