open-llm-leaderboard-old/details_luffycodes__vicuna-class-shishya-all-hal-7b-ep3
收藏数据集概述
该数据集是在对模型 luffycodes/vicuna-class-shishya-all-hal-7b-ep3 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。
- 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 Open LLM Leaderboard 上的聚合指标。
加载数据示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_luffycodes__vicuna-class-shishya-all-hal-7b-ep3", "harness_winogrande_5", split="train")
最新结果
以下是 2023-12-16T14:43:13.038199 运行的最新结果：
python { "all": { "acc": 0.5101563719470747, "acc_stderr": 0.034174127741758806, "acc_norm": 0.5187563327932377, "acc_norm_stderr": 0.035034297734345236, "mc1": 0.2962056303549572, "mc1_stderr": 0.015983595101811392, "mc2": 0.4483407078884665, "mc2_stderr": 0.015114510843263715 }, "harness|arc:challenge|25": { "acc": 0.42150170648464164, "acc_stderr": 0.014430197069326014, "acc_norm": 0.454778156996587, "acc_norm_stderr": 0.014551507060836355 }, "harness|hellaswag|10": { "acc": 0.5836486755626369, "acc_stderr": 0.004919457850104234, "acc_norm": 0.7720573590918144, "acc_norm_stderr": 0.004186480645315569 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.29, "acc_stderr": 0.04560480215720684, "acc_norm": 0.29, "acc_norm_stderr": 0.04560480215720684 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.4666666666666667, "acc_stderr": 0.043097329010363554, "acc_norm": 0.4666666666666667, "acc_norm_stderr": 0.043097329010363554 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.506578947368421, "acc_stderr": 0.040685900502249704, "acc_norm": 0.506578947368421, "acc_norm_stderr": 0.040685900502249704 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.55, "acc_stderr": 0.05, "acc_norm": 0.55, "acc_norm_stderr": 0.05 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.5547169811320755, "acc_stderr": 0.030588052974270655, "acc_norm": 0.5547169811320755, "acc_norm_stderr": 0.030588052974270655 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.5208333333333334, "acc_stderr": 0.041775789507399935, "acc_norm": 0.5208333333333334, "acc_norm_stderr": 0.041775789507399935 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.34, "acc_stderr": 0.04760952285695235, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695235 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.44, "acc_stderr": 0.04988876515698589, "acc_norm": 0.44, "acc_norm_stderr": 0.04988876515698589 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.37, "acc_stderr": 0.04852365870939099, "acc_norm": 0.37, "acc_norm_stderr": 0.04852365870939099 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.4393063583815029, "acc_stderr": 0.037842719328874674, "acc_norm": 0.4393063583815029, "acc_norm_stderr": 0.037842719328874674 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.20588235294117646, "acc_stderr": 0.040233822736177476, "acc_norm": 0.20588235294117646, "acc_norm_stderr": 0.040233822736177476 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.64, "acc_stderr": 0.04824181513244218, "acc_norm": 0.64, "acc_norm_stderr": 0.04824181513244218 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.451063829787234, "acc_stderr": 0.032529096196131965, "acc_norm": 0.451063829787234, "acc_norm_stderr": 0.032529096196131965 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.3333333333333333, "acc_stderr": 0.044346007015849245, "acc_norm": 0.3333333333333333, "acc_norm_stderr": 0.044346007015849245 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.47586206896551725, "acc_stderr": 0.041618085035015295, "acc_norm": 0.47586206896551725, "acc_norm_stderr": 0.041618085035015295 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.30158730158730157, "acc_stderr": 0.023636975996101803, "acc_norm": 0.30158730158730157, "acc_norm_stderr": 0.023636975996101803 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.3492063492063492, "acc_stderr": 0.04263906892795133, "acc_norm": 0.3492063492063492, "acc_norm_stderr": 0.04263906892795133 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.36, "acc_stderr": 0.048241815132442176, "acc_norm": 0.36, "acc_norm_stderr": 0.048241815132442176 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.5612903225806452, "acc_stderr": 0.02822949732031722, "acc_norm": 0.5612903225806452, "acc_norm_stderr": 0.02822949732031722 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.4039408866995074, "acc_stderr": 0.034524539038220406, "acc_norm": 0.4039408866995074, "acc_norm_stderr": 0.034524539038220406 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.42, "acc_stderr": 0.049604496374885836, "acc_norm": 0.42, "acc_norm_stderr": 0.049604496374885836 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.6303030303030303, "acc_stderr": 0.03769430314512568, "acc_norm": 0.6303030303030303, "acc_norm_stderr": 0.03769430314512568 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.5858585858585859, "acc_stderr": 0.03509438348879629, "acc_norm": 0.5858585858585859, "acc_norm_stderr": 0.03509438348879629 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.7564766839378239, "acc_stderr": 0.030975436386845436, "acc_norm": 0.7564766839378239, "acc_norm_stderr": 0.030975436386845436 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.5256410256410257, "acc_stderr": 0.025317649726448663, "acc_norm": 0.5256410256410257, "acc_norm_stderr": 0.025317649726448663 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.2740740740740741, "acc_stderr": 0.027195934804085626, "acc_norm": 0.2740740740740741, "acc_norm_stderr": 0.027195934
