open-llm-leaderboard-old/details_KnutJaegersberg__Walter-SOLAR-11B
收藏数据集概述
该数据集是在对模型 KnutJaegersberg/Walter-SOLAR-11B 进行评估运行期间自动创建的，用于 Open LLM Leaderboard。
数据集组成
- 数据集包含 63 个配置，每个配置对应一个评估任务。
- 数据集从 1 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。
- "train" 分割始终指向最新的结果。
- 额外的配置 "results" 存储所有运行的聚合结果，用于计算和显示 Open LLM Leaderboard 上的聚合指标。
最新结果
以下是 2023-12-16T17:23:07.067772 运行 的最新结果：
python { "all": { "acc": 0.6404707310339822, "acc_stderr": 0.0318661190240921, "acc_norm": 0.6524926684204396, "acc_norm_stderr": 0.03268492668160191, "mc1": 0.29253365973072215, "mc1_stderr": 0.015925597445286165, "mc2": 0.4487960219023809, "mc2_stderr": 0.014224892990272523 }, "harness|arc:challenge|25": { "acc": 0.5639931740614335, "acc_stderr": 0.014491225699230918, "acc_norm": 0.6040955631399317, "acc_norm_stderr": 0.01429122839353659 }, "harness|hellaswag|10": { "acc": 0.6549492133041227, "acc_stderr": 0.004744132825391527, "acc_norm": 0.848635729934276, "acc_norm_stderr": 0.003576711065619589 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6, "acc_stderr": 0.04232073695151589, "acc_norm": 0.6, "acc_norm_stderr": 0.04232073695151589 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.7368421052631579, "acc_stderr": 0.03583496176361074, "acc_norm": 0.7368421052631579, "acc_norm_stderr": 0.03583496176361074 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.66, "acc_stderr": 0.04760952285695237, "acc_norm": 0.66, "acc_norm_stderr": 0.04760952285695237 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6754716981132075, "acc_stderr": 0.028815615713432108, "acc_norm": 0.6754716981132075, "acc_norm_stderr": 0.028815615713432108 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7430555555555556, "acc_stderr": 0.03653946969442099, "acc_norm": 0.7430555555555556, "acc_norm_stderr": 0.03653946969442099 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.45, "acc_stderr": 0.05, "acc_norm": 0.45, "acc_norm_stderr": 0.05 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.54, "acc_stderr": 0.05009082659620332, "acc_norm": 0.54, "acc_norm_stderr": 0.05009082659620332 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.41, "acc_stderr": 0.049431107042371025, "acc_norm": 0.41, "acc_norm_stderr": 0.049431107042371025 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6473988439306358, "acc_stderr": 0.03643037168958548, "acc_norm": 0.6473988439306358, "acc_norm_stderr": 0.03643037168958548 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.3333333333333333, "acc_stderr": 0.04690650298201943, "acc_norm": 0.3333333333333333, "acc_norm_stderr": 0.04690650298201943 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.72, "acc_stderr": 0.04512608598542128, "acc_norm": 0.72, "acc_norm_stderr": 0.04512608598542128 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.574468085106383, "acc_stderr": 0.03232146916224468, "acc_norm": 0.574468085106383, "acc_norm_stderr": 0.03232146916224468 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.43859649122807015, "acc_stderr": 0.04668000738510455, "acc_norm": 0.43859649122807015, "acc_norm_stderr": 0.04668000738510455 }, "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": 0.4312169312169312, "acc_stderr": 0.0255064816981382, "acc_norm": 0.4312169312169312, "acc_norm_stderr": 0.0255064816981382 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.4126984126984127, "acc_stderr": 0.04403438954768176, "acc_norm": 0.4126984126984127, "acc_norm_stderr": 0.04403438954768176 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.35, "acc_stderr": 0.04793724854411019, "acc_norm": 0.35, "acc_norm_stderr": 0.04793724854411019 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7838709677419354, "acc_stderr": 0.02341529343356852, "acc_norm": 0.7838709677419354, "acc_norm_stderr": 0.02341529343356852 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.5221674876847291, "acc_stderr": 0.03514528562175007, "acc_norm": 0.5221674876847291, "acc_norm_stderr": 0.03514528562175007 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.69, "acc_stderr": 0.04648231987117316, "acc_norm": 0.69, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7818181818181819, "acc_stderr": 0.03225078108306289, "acc_norm": 0.7818181818181819, "acc_norm_stderr": 0.03225078108306289 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.8282828282828283, "acc_stderr": 0.02686971618742991, "acc_norm": 0.8282828282828283, "acc_norm_stderr": 0.02686971618742991 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8704663212435233, "acc_stderr": 0.024233532297758723, "acc_norm": 0.8704663212435233, "acc_norm_stderr": 0.024233532297758723 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6461538461538462, "acc_stderr": 0.02424378399406216, "acc_norm": 0.6461538461538462, "acc_norm_stderr": 0.02424378399406216 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.37037037037037035, "acc_stderr": 0.02944316932303154, "acc_norm": 0.37037037037037035, "acc_norm_stderr": 0.02944316932303154 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.6680672268907563, "acc_stderr": 0.03058869701378364, "acc_norm": 0.6680672268907563, "acc_norm_stderr": 0.030
