open-llm-leaderboard-old/details_kenhktsui__nano-phi-115M-v0.1
收藏数据集概述
数据集来源
该数据集是在对模型 kenhktsui/nano-phi-115M-v0.1 进行评估运行期间自动创建的，评估结果展示在 Open LLM Leaderboard 上。
数据集结构
- 配置数量：63个配置，每个配置对应一个评估任务。
- 数据来源：数据集由1次运行创建，每次运行的详细结果存储在特定的分割中，分割名称使用运行的时间戳。
- 最新结果："train" 分割始终指向最新的结果。
- 结果汇总：一个额外的配置 "results" 存储所有运行的汇总结果，用于计算和显示在 Open LLM Leaderboard 上的聚合指标。
数据加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_kenhktsui__nano-phi-115M-v0.1", "harness_winogrande_5", split="train")
最新结果
以下是 2024-02-09T13:21:05.777292 运行的最新结果：
python { "all": { "acc": 0.2525471471328879, "acc_stderr": 0.030613616045154307, "acc_norm": 0.25320771353725297, "acc_norm_stderr": 0.031427270253272646, "mc1": 0.25091799265605874, "mc1_stderr": 0.015176985027707693, "mc2": 0.4600301977928377, "mc2_stderr": 0.015417429651937565 }, "harness|arc:challenge|25": { "acc": 0.1825938566552901, "acc_stderr": 0.011289730684564993, "acc_norm": 0.21928327645051193, "acc_norm_stderr": 0.012091245787615735 }, "harness|hellaswag|10": { "acc": 0.2731527584146584, "acc_stderr": 0.004446680081493753, "acc_norm": 0.2786297550288787, "acc_norm_stderr": 0.0044740864899406865 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.23, "acc_stderr": 0.04229525846816507, "acc_norm": 0.23, "acc_norm_stderr": 0.04229525846816507 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.3111111111111111, "acc_stderr": 0.039992628766177235, "acc_norm": 0.3111111111111111, "acc_norm_stderr": 0.039992628766177235 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.21710526315789475, "acc_stderr": 0.033550453048829205, "acc_norm": 0.21710526315789475, "acc_norm_stderr": 0.033550453048829205 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.25, "acc_stderr": 0.04351941398892446, "acc_norm": 0.25, "acc_norm_stderr": 0.04351941398892446 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.22264150943396227, "acc_stderr": 0.025604233470899098, "acc_norm": 0.22264150943396227, "acc_norm_stderr": 0.025604233470899098 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.22916666666666666, "acc_stderr": 0.03514697467862388, "acc_norm": 0.22916666666666666, "acc_norm_stderr": 0.03514697467862388 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.17, "acc_stderr": 0.03775251680686371, "acc_norm": 0.17, "acc_norm_stderr": 0.03775251680686371 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.26, "acc_stderr": 0.04408440022768078, "acc_norm": 0.26, "acc_norm_stderr": 0.04408440022768078 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.25, "acc_stderr": 0.04351941398892446, "acc_norm": 0.25, "acc_norm_stderr": 0.04351941398892446 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.2023121387283237, "acc_stderr": 0.030631145539198816, "acc_norm": 0.2023121387283237, "acc_norm_stderr": 0.030631145539198816 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.3235294117647059, "acc_stderr": 0.046550104113196177, "acc_norm": 0.3235294117647059, "acc_norm_stderr": 0.046550104113196177 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.26, "acc_stderr": 0.044084400227680794, "acc_norm": 0.26, "acc_norm_stderr": 0.044084400227680794 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.2425531914893617, "acc_stderr": 0.028020226271200217, "acc_norm": 0.2425531914893617, "acc_norm_stderr": 0.028020226271200217 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.22807017543859648, "acc_stderr": 0.03947152782669415, "acc_norm": 0.22807017543859648, "acc_norm_stderr": 0.03947152782669415 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.22758620689655173, "acc_stderr": 0.03493950380131184, "acc_norm": 0.22758620689655173, "acc_norm_stderr": 0.03493950380131184 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.24603174603174602, "acc_stderr": 0.022182037202948368, "acc_norm": 0.24603174603174602, "acc_norm_stderr": 0.022182037202948368 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.15079365079365079, "acc_stderr": 0.03200686497287392, "acc_norm": 0.15079365079365079, "acc_norm_stderr": 0.03200686497287392 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.3387096774193548, "acc_stderr": 0.026923446059302844, "acc_norm": 0.3387096774193548, "acc_norm_stderr": 0.026923446059302844 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.29064039408866993, "acc_stderr": 0.0319474007226554, "acc_norm": 0.29064039408866993, "acc_norm_stderr": 0.0319474007226554 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.31, "acc_stderr": 0.04648231987117317, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117317 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.21818181818181817, "acc_stderr": 0.03225078108306289, "acc_norm": 0.21818181818181817, "acc_norm_stderr": 0.03225078108306289 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.3181818181818182, "acc_stderr": 0.0331847733384533, "acc_norm": 0.3181818181818182, "acc_norm_stderr": 0.0331847733384533 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.20207253886010362, "acc_stderr": 0.02897908979429673, "acc_norm": 0.20207253886010362, "acc_norm_stderr": 0.02897908979429673 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.24871794871794872, "acc_stderr": 0.0219169577092138, "acc_norm": 0.24871794871794872, "acc_norm_stderr": 0.0219169577092138 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.2777777777777778, "acc_stderr": 0
