open-llm-leaderboard-old/details_BFauber__lora_llama2-7b_10e6
收藏数据集概述
数据集简介
该数据集是在评估模型 BFauber/lora_llama2-7b_10e6 在 Open LLM Leaderboard 上的自动创建的。
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一个特定的分割，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。
数据加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_BFauber__lora_llama2-7b_10e6", "harness_winogrande_5", split="train")
最新结果
这些是最新的结果，来自运行 2024-02-10T01:52:27.465366： python { "all": { "acc": 0.4618485317752384, "acc_stderr": 0.034532848374817675, "acc_norm": 0.46739450592990034, "acc_norm_stderr": 0.035336622817688824, "mc1": 0.24724602203182375, "mc1_stderr": 0.01510240479735965, "mc2": 0.38775302614821305, "mc2_stderr": 0.01355621686916311 }, "harness|arc:challenge|25": { "acc": 0.4931740614334471, "acc_stderr": 0.014610029151379813, "acc_norm": 0.5341296928327645, "acc_norm_stderr": 0.014577311315231106 }, "harness|hellaswag|10": { "acc": 0.5853415654252141, "acc_stderr": 0.0049165612135912825, "acc_norm": 0.7803226448914559, "acc_norm_stderr": 0.004131818797713881 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.31, "acc_stderr": 0.046482319871173156, "acc_norm": 0.31, "acc_norm_stderr": 0.046482319871173156 }, "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": 0.46710526315789475, "acc_stderr": 0.04060127035236395, "acc_norm": 0.46710526315789475, "acc_norm_stderr": 0.04060127035236395 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.51, "acc_stderr": 0.05024183937956912, "acc_norm": 0.51, "acc_norm_stderr": 0.05024183937956912 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.5056603773584906, "acc_stderr": 0.030770900763851302, "acc_norm": 0.5056603773584906, "acc_norm_stderr": 0.030770900763851302 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.4791666666666667, "acc_stderr": 0.04177578950739993, "acc_norm": 0.4791666666666667, "acc_norm_stderr": 0.04177578950739993 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.33, "acc_stderr": 0.047258156262526045, "acc_norm": 0.33, "acc_norm_stderr": 0.047258156262526045 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.33, "acc_stderr": 0.047258156262526045, "acc_norm": 0.33, "acc_norm_stderr": 0.047258156262526045 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.36, "acc_stderr": 0.04824181513244218, "acc_norm": 0.36, "acc_norm_stderr": 0.04824181513244218 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.4277456647398844, "acc_stderr": 0.03772446857518027, "acc_norm": 0.4277456647398844, "acc_norm_stderr": 0.03772446857518027 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.22549019607843138, "acc_stderr": 0.041583075330832865, "acc_norm": 0.22549019607843138, "acc_norm_stderr": 0.041583075330832865 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.57, "acc_stderr": 0.049756985195624284, "acc_norm": 0.57, "acc_norm_stderr": 0.049756985195624284 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.40425531914893614, "acc_stderr": 0.03208115750788684, "acc_norm": 0.40425531914893614, "acc_norm_stderr": 0.03208115750788684 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.2543859649122807, "acc_stderr": 0.04096985139843672, "acc_norm": 0.2543859649122807, "acc_norm_stderr": 0.04096985139843672 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5241379310344828, "acc_stderr": 0.041618085035015295, "acc_norm": 0.5241379310344828, "acc_norm_stderr": 0.041618085035015295 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.28835978835978837, "acc_stderr": 0.023330654054535896, "acc_norm": 0.28835978835978837, "acc_norm_stderr": 0.023330654054535896 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.2857142857142857, "acc_stderr": 0.040406101782088394, "acc_norm": 0.2857142857142857, "acc_norm_stderr": 0.040406101782088394 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.38, "acc_stderr": 0.048783173121456316, "acc_norm": 0.38, "acc_norm_stderr": 0.048783173121456316 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.46774193548387094, "acc_stderr": 0.02838474778881333, "acc_norm": 0.46774193548387094, "acc_norm_stderr": 0.02838474778881333 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.3251231527093596, "acc_stderr": 0.032957975663112704, "acc_norm": 0.3251231527093596, "acc_norm_stderr": 0.032957975663112704 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.37, "acc_stderr": 0.048523658709391, "acc_norm": 0.37, "acc_norm_stderr": 0.048523658709391 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.5212121212121212, "acc_stderr": 0.03900828913737301, "acc_norm": 0.5212121212121212, "acc_norm_stderr": 0.03900828913737301 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.4696969696969697, "acc_stderr": 0.03555804051763929, "acc_norm": 0.4696969696969697, "acc_norm_stderr": 0.03555804051763929 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.616580310880829, "acc_stderr": 0.03508984236295342, "acc_norm": 0.616580310880829, "acc_norm_stderr": 0.03508984236295342 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.43333333333333335, "acc_stderr": 0.025124653525885124, "acc_norm": 0.43333333333333335, "acc_norm_stderr": 0.025124653525885124 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3074074074074074, "acc_stderr": 0.028133252578815625, "acc_norm": 0.3074074074074074, "acc_norm_stderr": 0.028133252578815625 }, "harness|hendrycksTest-high_school_
