open-llm-leaderboard-old/details_cloudyu__mistral_28B_instruct_v0.1
收藏数据集概述
数据集摘要
该数据集是在对模型 cloudyu/mistral_28B_instruct_v0.1 进行评估运行期间自动创建的。数据集包含 63 个配置,每个配置对应一个评估任务。数据集从 1 次运行中创建,每次运行的详细信息可以在每个配置中找到,使用运行的时间戳作为分割名称。"train" 分割始终指向最新的结果。此外,还有一个名为 "results" 的配置,存储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。
最新结果
以下是 2024-03-05T07:24:18.194696 运行的最新结果:
python { "all": { "acc": 0.6048165720098292, "acc_stderr": 0.03318918937904906, "acc_norm": 0.6103008292910913, "acc_norm_stderr": 0.03386256440684409, "mc1": 0.44920440636474906, "mc1_stderr": 0.01741294198611531, "mc2": 0.6416534233937677, "mc2_stderr": 0.015338593594048558 }, "harness|arc:challenge|25": { "acc": 0.53839590443686, "acc_stderr": 0.014568245550296358, "acc_norm": 0.5836177474402731, "acc_norm_stderr": 0.01440561827943618 }, "harness|hellaswag|10": { "acc": 0.6085441147181836, "acc_stderr": 0.004870785036708288, "acc_norm": 0.8053176658036247, "acc_norm_stderr": 0.0039514673865977306 }, "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": 0.6, "acc_stderr": 0.042320736951515885, "acc_norm": 0.6, "acc_norm_stderr": 0.042320736951515885 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6381578947368421, "acc_stderr": 0.03910525752849724, "acc_norm": 0.6381578947368421, "acc_norm_stderr": 0.03910525752849724 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.55, "acc_stderr": 0.049999999999999996, "acc_norm": 0.55, "acc_norm_stderr": 0.049999999999999996 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.690566037735849, "acc_stderr": 0.028450154794118637, "acc_norm": 0.690566037735849, "acc_norm_stderr": 0.028450154794118637 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.6944444444444444, "acc_stderr": 0.03852084696008534, "acc_norm": 0.6944444444444444, "acc_norm_stderr": 0.03852084696008534 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.44, "acc_stderr": 0.049888765156985884, "acc_norm": 0.44, "acc_norm_stderr": 0.049888765156985884 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.52, "acc_stderr": 0.050211673156867795, "acc_norm": 0.52, "acc_norm_stderr": 0.050211673156867795 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.38, "acc_stderr": 0.048783173121456316, "acc_norm": 0.38, "acc_norm_stderr": 0.048783173121456316 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.5722543352601156, "acc_stderr": 0.03772446857518025, "acc_norm": 0.5722543352601156, "acc_norm_stderr": 0.03772446857518025 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.4117647058823529, "acc_stderr": 0.04897104952726366, "acc_norm": 0.4117647058823529, "acc_norm_stderr": 0.04897104952726366 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.73, "acc_stderr": 0.044619604333847394, "acc_norm": 0.73, "acc_norm_stderr": 0.044619604333847394 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5063829787234042, "acc_stderr": 0.032683358999363366, "acc_norm": 0.5063829787234042, "acc_norm_stderr": 0.032683358999363366 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.40350877192982454, "acc_stderr": 0.046151869625837026, "acc_norm": 0.40350877192982454, "acc_norm_stderr": 0.046151869625837026 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5724137931034483, "acc_stderr": 0.041227371113703316, "acc_norm": 0.5724137931034483, "acc_norm_stderr": 0.041227371113703316 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.3835978835978836, "acc_stderr": 0.025043757318520196, "acc_norm": 0.3835978835978836, "acc_norm_stderr": 0.025043757318520196 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.4365079365079365, "acc_stderr": 0.04435932892851466, "acc_norm": 0.4365079365079365, "acc_norm_stderr": 0.04435932892851466 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.37, "acc_stderr": 0.048523658709391, "acc_norm": 0.37, "acc_norm_stderr": 0.048523658709391 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.6516129032258065, "acc_stderr": 0.027104826328100944, "acc_norm": 0.6516129032258065, "acc_norm_stderr": 0.027104826328100944 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.5024630541871922, "acc_stderr": 0.03517945038691063, "acc_norm": 0.5024630541871922, "acc_norm_stderr": 0.03517945038691063 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.64, "acc_stderr": 0.048241815132442176, "acc_norm": 0.64, "acc_norm_stderr": 0.048241815132442176 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7212121212121212, "acc_stderr": 0.03501438706296781, "acc_norm": 0.7212121212121212, "acc_norm_stderr": 0.03501438706296781 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7525252525252525, "acc_stderr": 0.030746300742124488, "acc_norm": 0.7525252525252525, "acc_norm_stderr": 0.030746300742124488 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8341968911917098, "acc_stderr": 0.026839845022314415, "acc_norm": 0.8341968911917098, "acc_norm_stderr": 0.026839845022314415 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.5615384615384615, "acc_stderr": 0.02515826601686859, "acc_norm": 0.5615384615384615, "acc_norm_stderr": 0.02515826601686859 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.28888888888888886, "acc_stderr": 0.027634907264178544, "acc_norm": 0.28888888888888886, "acc_norm_stderr": 0.027634907264178544 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.6470588235294118, "acc_stderr": 0.031041941304059288, "acc_norm": 0.6470588235294118, "acc_norm_stderr": 0.0310419413040



