open-llm-leaderboard-old/details_uukuguy__speechless-coder-ds-1.3b
收藏数据集概述
数据集简介
该数据集是在模型uukuguy/speechless-coder-ds-1.3b的评估运行期间自动创建的,用于Open LLM Leaderboard。
数据集结构
- 数据集由63个配置组成,每个配置对应一个评估任务。
- 数据集从1次运行中创建,每个运行在每个配置中作为一个特定的分割存在,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。
数据加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_uukuguy__speechless-coder-ds-1.3b", "harness_winogrande_5", split="train")
最新结果
以下是2023-12-30T06:48:01.416618运行的最新结果:
python { "all": { "acc": 0.2506488389989993, "acc_stderr": 0.030580639760232627, "acc_norm": 0.25128428880523795, "acc_norm_stderr": 0.03131936078924142, "mc1": 0.25458996328029376, "mc1_stderr": 0.015250117079156507, "mc2": 0.4211587968245106, "mc2_stderr": 0.01485785907132671 }, "harness|arc:challenge|25": { "acc": 0.23890784982935154, "acc_stderr": 0.012461071376316614, "acc_norm": 0.26535836177474403, "acc_norm_stderr": 0.012902554762313967 }, "harness|hellaswag|10": { "acc": 0.3313085042820155, "acc_stderr": 0.004697217912462985, "acc_norm": 0.39494124676359293, "acc_norm_stderr": 0.0048783902265917105 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.24, "acc_stderr": 0.04292346959909283, "acc_norm": 0.24, "acc_norm_stderr": 0.04292346959909283 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.21481481481481482, "acc_stderr": 0.035478541985608236, "acc_norm": 0.21481481481481482, "acc_norm_stderr": 0.035478541985608236 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.16447368421052633, "acc_stderr": 0.0301675334686327, "acc_norm": 0.16447368421052633, "acc_norm_stderr": 0.0301675334686327 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.23, "acc_stderr": 0.042295258468165065, "acc_norm": 0.23, "acc_norm_stderr": 0.042295258468165065 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.26037735849056604, "acc_stderr": 0.027008766090708094, "acc_norm": 0.26037735849056604, "acc_norm_stderr": 0.027008766090708094 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.2361111111111111, "acc_stderr": 0.03551446610810826, "acc_norm": 0.2361111111111111, "acc_norm_stderr": 0.03551446610810826 }, "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": 0.16, "acc_stderr": 0.0368452949177471, "acc_norm": 0.16, "acc_norm_stderr": 0.0368452949177471 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.24, "acc_stderr": 0.042923469599092816, "acc_norm": 0.24, "acc_norm_stderr": 0.042923469599092816 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.21965317919075145, "acc_stderr": 0.031568093627031744, "acc_norm": 0.21965317919075145, "acc_norm_stderr": 0.031568093627031744 }, "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": 0.21, "acc_stderr": 0.040936018074033256, "acc_norm": 0.21, "acc_norm_stderr": 0.040936018074033256 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.3148936170212766, "acc_stderr": 0.03036358219723817, "acc_norm": 0.3148936170212766, "acc_norm_stderr": 0.03036358219723817 }, "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": 0.2413793103448276, "acc_stderr": 0.03565998174135303, "acc_norm": 0.2413793103448276, "acc_norm_stderr": 0.03565998174135303 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.26455026455026454, "acc_stderr": 0.022717467897708614, "acc_norm": 0.26455026455026454, "acc_norm_stderr": 0.022717467897708614 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.1984126984126984, "acc_stderr": 0.03567016675276862, "acc_norm": 0.1984126984126984, "acc_norm_stderr": 0.03567016675276862 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.24, "acc_stderr": 0.04292346959909281, "acc_norm": 0.24, "acc_norm_stderr": 0.04292346959909281 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.21935483870967742, "acc_stderr": 0.02354079935872329, "acc_norm": 0.21935483870967742, "acc_norm_stderr": 0.02354079935872329 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.21182266009852216, "acc_stderr": 0.02874898368994107, "acc_norm": 0.21182266009852216, "acc_norm_stderr": 0.02874898368994107 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.23, "acc_stderr": 0.04229525846816505, "acc_norm": 0.23, "acc_norm_stderr": 0.04229525846816505 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.2787878787878788, "acc_stderr": 0.03501438706296781, "acc_norm": 0.2787878787878788, "acc_norm_stderr": 0.03501438706296781 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.21717171717171718, "acc_stderr": 0.029376616484945633, "acc_norm": 0.21717171717171718, "acc_norm_stderr": 0.029376616484945633 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.24870466321243523, "acc_stderr": 0.031195840877700314, "acc_norm": 0.24870466321243523, "acc_norm_stderr": 0.031195840877700314 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.21794871794871795, "acc_stderr": 0.020932445774463196, "acc_norm": 0.21794871794871795, "acc_norm_stderr": 0.020932445774463196 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.23703703703703705, "acc_stderr": 0.02592887613276612



