open-llm-leaderboard-old/details_wang7776__Llama-2-7b-chat-hf-20-attention-sparsity
收藏数据集概述
数据集摘要
该数据集是在评估模型 wang7776/Llama-2-7b-chat-hf-20-attention-sparsity 在 Open LLM Leaderboard 上的运行过程中自动创建的。
数据集组成
- 该数据集包含 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，每次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。
最新结果
这些是最新结果，来自 2024-01-25T19:08:26.254884 的运行。每个任务的详细结果如下：
python { "all": { "acc": 0.4761943213953472, "acc_stderr": 0.03435344147831958, "acc_norm": 0.4811025232857774, "acc_norm_stderr": 0.03510926677242792, "mc1": 0.30599755201958384, "mc1_stderr": 0.016132229728155045, "mc2": 0.45842205614099396, "mc2_stderr": 0.015621084603112444 }, "harness|arc:challenge|25": { "acc": 0.5008532423208191, "acc_stderr": 0.014611369529813272, "acc_norm": 0.5341296928327645, "acc_norm_stderr": 0.014577311315231102 }, "harness|hellaswag|10": { "acc": 0.59061939852619, "acc_stderr": 0.004907146229347549, "acc_norm": 0.7791276638119896, "acc_norm_stderr": 0.0041398679751162995 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.28, "acc_stderr": 0.04512608598542129, "acc_norm": 0.28, "acc_norm_stderr": 0.04512608598542129 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.42962962962962964, "acc_stderr": 0.04276349494376599, "acc_norm": 0.42962962962962964, "acc_norm_stderr": 0.04276349494376599 }, "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": 0.49, "acc_stderr": 0.05024183937956912, "acc_norm": 0.49, "acc_norm_stderr": 0.05024183937956912 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.5169811320754717, "acc_stderr": 0.030755120364119905, "acc_norm": 0.5169811320754717, "acc_norm_stderr": 0.030755120364119905 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.5, "acc_stderr": 0.04181210050035455, "acc_norm": 0.5, "acc_norm_stderr": 0.04181210050035455 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.29, "acc_stderr": 0.04560480215720684, "acc_norm": 0.29, "acc_norm_stderr": 0.04560480215720684 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.39, "acc_stderr": 0.04902071300001975, "acc_norm": 0.39, "acc_norm_stderr": 0.04902071300001975 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.33, "acc_stderr": 0.047258156262526045, "acc_norm": 0.33, "acc_norm_stderr": 0.047258156262526045 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.3930635838150289, "acc_stderr": 0.03724249595817731, "acc_norm": 0.3930635838150289, "acc_norm_stderr": 0.03724249595817731 }, "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": 0.54, "acc_stderr": 0.05009082659620332, "acc_norm": 0.54, "acc_norm_stderr": 0.05009082659620332 }, "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": 0.3684210526315789, "acc_stderr": 0.04537815354939392, "acc_norm": 0.3684210526315789, "acc_norm_stderr": 0.04537815354939392 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.4827586206896552, "acc_stderr": 0.04164188720169377, "acc_norm": 0.4827586206896552, "acc_norm_stderr": 0.04164188720169377 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.28835978835978837, "acc_stderr": 0.02333065405453589, "acc_norm": 0.28835978835978837, "acc_norm_stderr": 0.02333065405453589 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.23809523809523808, "acc_stderr": 0.03809523809523811, "acc_norm": 0.23809523809523808, "acc_norm_stderr": 0.03809523809523811 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.34, "acc_stderr": 0.04760952285695235, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695235 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.5225806451612903, "acc_stderr": 0.02841498501970786, "acc_norm": 0.5225806451612903, "acc_norm_stderr": 0.02841498501970786 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.3645320197044335, "acc_stderr": 0.033864057460620905, "acc_norm": 0.3645320197044335, "acc_norm_stderr": 0.033864057460620905 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.39, "acc_stderr": 0.04902071300001974, "acc_norm": 0.39, "acc_norm_stderr": 0.04902071300001974 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.5757575757575758, "acc_stderr": 0.03859268142070264, "acc_norm": 0.5757575757575758, "acc_norm_stderr": 0.03859268142070264 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.601010101010101, "acc_stderr": 0.03488901616852732, "acc_norm": 0.601010101010101, "acc_norm_stderr": 0.03488901616852732 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.6683937823834197, "acc_stderr": 0.03397636541089118, "acc_norm": 0.6683937823834197, "acc_norm_stderr": 0.03397636541089118 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.41025641025641024, "acc_stderr": 0.024939313906940777, "acc_norm": 0.41025641025641024, "acc_norm_stderr": 0.024939313906940777 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.25555555555555554, "acc_stderr": 0.026593939101844086, "acc_norm": 0.25555555555555554, "acc_norm_stderr": 0.026593939101844086 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.42016806722689076, "acc_stderr": 0.03206183783236152, "acc_norm": 0.42016806722689076, "
