open-llm-leaderboard-old/details_DatPySci__pythia-1b-sft-50k
收藏数据集概述
数据集简介
该数据集是在评估模型 DatPySci/pythia-1b-sft-50k 在 Open LLM Leaderboard 上的自动创建的。数据集包含 63 个配置，每个配置对应一个评估任务。
数据集结构
数据集由 3 次运行结果组成，每次运行的详细结果可以在每个配置中找到，以运行的时间戳命名的特定分片形式存储。"train" 分片始终指向最新的结果。
附加配置
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_DatPySci__pythia-1b-sft-50k", "harness_winogrande_5", split="train")
最新结果
以下是 2024-02-17T14:41:59.887810 运行 的最新结果：
python { "all": { "acc": 0.24467360878008643, "acc_stderr": 0.03024534477539282, "acc_norm": 0.24555697815658845, "acc_norm_stderr": 0.030978837434188194, "mc1": 0.22031823745410037, "mc1_stderr": 0.01450904517148729, "mc2": 0.37005968856579075, "mc2_stderr": 0.014337009699291485 }, "harness|arc:challenge|25": { "acc": 0.27986348122866894, "acc_stderr": 0.01311904089772592, "acc_norm": 0.3003412969283277, "acc_norm_stderr": 0.013395909309957009 }, "harness|hellaswag|10": { "acc": 0.3906592312288389, "acc_stderr": 0.00486901015228075, "acc_norm": 0.4910376419040032, "acc_norm_stderr": 0.004988979750014438 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.22, "acc_stderr": 0.041633319989322716, "acc_norm": 0.22, "acc_norm_stderr": 0.041633319989322716 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.25925925925925924, "acc_stderr": 0.03785714465066653, "acc_norm": 0.25925925925925924, "acc_norm_stderr": 0.03785714465066653 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.17763157894736842, "acc_stderr": 0.031103182383123394, "acc_norm": 0.17763157894736842, "acc_norm_stderr": 0.031103182383123394 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.23, "acc_stderr": 0.04229525846816507, "acc_norm": 0.23, "acc_norm_stderr": 0.04229525846816507 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.27547169811320754, "acc_stderr": 0.02749566368372407, "acc_norm": 0.27547169811320754, "acc_norm_stderr": 0.02749566368372407 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.2222222222222222, "acc_stderr": 0.03476590104304134, "acc_norm": 0.2222222222222222, "acc_norm_stderr": 0.03476590104304134 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.19, "acc_stderr": 0.039427724440366234, "acc_norm": 0.19, "acc_norm_stderr": 0.039427724440366234 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.23, "acc_stderr": 0.04229525846816508, "acc_norm": 0.23, "acc_norm_stderr": 0.04229525846816508 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.26, "acc_stderr": 0.04408440022768078, "acc_norm": 0.26, "acc_norm_stderr": 0.04408440022768078 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.2543352601156069, "acc_stderr": 0.0332055644308557, "acc_norm": 0.2543352601156069, "acc_norm_stderr": 0.0332055644308557 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.22549019607843138, "acc_stderr": 0.04158307533083286, "acc_norm": 0.22549019607843138, "acc_norm_stderr": 0.04158307533083286 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.22, "acc_stderr": 0.0416333199893227, "acc_norm": 0.22, "acc_norm_stderr": 0.0416333199893227 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.23404255319148937, "acc_stderr": 0.02767845257821238, "acc_norm": 0.23404255319148937, "acc_norm_stderr": 0.02767845257821238 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.21929824561403508, "acc_stderr": 0.038924311065187504, "acc_norm": 0.21929824561403508, "acc_norm_stderr": 0.038924311065187504 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.2, "acc_stderr": 0.0333333333333333, "acc_norm": 0.2, "acc_norm_stderr": 0.0333333333333333 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.2566137566137566, "acc_stderr": 0.022494510767503154, "acc_norm": 0.2566137566137566, "acc_norm_stderr": 0.022494510767503154 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.2619047619047619, "acc_stderr": 0.039325376803928704, "acc_norm": 0.2619047619047619, "acc_norm_stderr": 0.039325376803928704 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.23, "acc_stderr": 0.04229525846816506, "acc_norm": 0.23, "acc_norm_stderr": 0.04229525846816506 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.25161290322580643, "acc_stderr": 0.024685979286239963, "acc_norm": 0.25161290322580643, "acc_norm_stderr": 0.024685979286239963 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.21674876847290642, "acc_stderr": 0.028990331252516235, "acc_norm": 0.21674876847290642, "acc_norm_stderr": 0.028990331252516235 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.24, "acc_stderr": 0.04292346959909282, "acc_norm": 0.24, "acc_norm_stderr": 0.04292346959909282 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.24242424242424243, "acc_stderr": 0.03346409881055952, "acc_norm": 0.24242424242424243, "acc_norm_stderr": 0.03346409881055952 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.1717171717171717, "acc_stderr": 0.026869716187429917, "acc_norm": 0.1717171717171717, "acc_norm_stderr": 0.026869716187429917 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.2694300518134715, "acc_stderr": 0.03201867122877795, "acc_norm": 0.2694300518134715, "acc_norm_stderr": 0.03201867122877795 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.2230769230769231, "acc_stderr": 0.021107730127244, "acc_norm": 0.2230769230769231, "acc_norm_stderr": 0.021107730127244 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.29259259259259257, "acc_stderr": 0.027738969632176088, "acc_norm": 0.29259259259259257, "acc_norm_stderr":
