open-llm-leaderboard-old/details_chargoddard__internlm2-7b-llama
收藏数据集概述
数据集简介
该数据集是在评估模型 chargoddard/internlm2-7b-llama 在 Open LLM Leaderboard 上的运行过程中自动创建的。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1次运行创建，每个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。
数据加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_chargoddard__internlm2-7b-llama", "harness_winogrande_5", split="train")
最新结果
以下是 2024-01-18T12:13:04.932540 运行 的最新结果：
python { "all": { "acc": 0.6329686690164976, "acc_stderr": 0.03232315628356604, "acc_norm": 0.634123920290497, "acc_norm_stderr": 0.032983274678832275, "mc1": 0.37576499388004897, "mc1_stderr": 0.016954584060214297, "mc2": 0.5425133114047686, "mc2_stderr": 0.015593910488675748 }, "harness|arc:challenge|25": { "acc": 0.5699658703071673, "acc_stderr": 0.014467631559137994, "acc_norm": 0.6049488054607508, "acc_norm_stderr": 0.014285898292938169 }, "harness|hellaswag|10": { "acc": 0.6154152559251145, "acc_stderr": 0.004855027248398157, "acc_norm": 0.8098984266082454, "acc_norm_stderr": 0.003915792315457799 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.32, "acc_stderr": 0.04688261722621503, "acc_norm": 0.32, "acc_norm_stderr": 0.04688261722621503 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.5925925925925926, "acc_stderr": 0.04244633238353228, "acc_norm": 0.5925925925925926, "acc_norm_stderr": 0.04244633238353228 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.7039473684210527, "acc_stderr": 0.03715062154998905, "acc_norm": 0.7039473684210527, "acc_norm_stderr": 0.03715062154998905 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.72, "acc_stderr": 0.04512608598542127, "acc_norm": 0.72, "acc_norm_stderr": 0.04512608598542127 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6830188679245283, "acc_stderr": 0.028637235639800897, "acc_norm": 0.6830188679245283, "acc_norm_stderr": 0.028637235639800897 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7222222222222222, "acc_stderr": 0.03745554791462457, "acc_norm": 0.7222222222222222, "acc_norm_stderr": 0.03745554791462457 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.42, "acc_stderr": 0.049604496374885836, "acc_norm": 0.42, "acc_norm_stderr": 0.049604496374885836 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.59, "acc_stderr": 0.04943110704237102, "acc_norm": 0.59, "acc_norm_stderr": 0.04943110704237102 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.37, "acc_stderr": 0.048523658709391, "acc_norm": 0.37, "acc_norm_stderr": 0.048523658709391 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6242774566473989, "acc_stderr": 0.036928207672648664, "acc_norm": 0.6242774566473989, "acc_norm_stderr": 0.036928207672648664 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.30392156862745096, "acc_stderr": 0.04576665403207763, "acc_norm": 0.30392156862745096, "acc_norm_stderr": 0.04576665403207763 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.79, "acc_stderr": 0.040936018074033256, "acc_norm": 0.79, "acc_norm_stderr": 0.040936018074033256 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.548936170212766, "acc_stderr": 0.032529096196131965, "acc_norm": 0.548936170212766, "acc_norm_stderr": 0.032529096196131965 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.4824561403508772, "acc_stderr": 0.0470070803355104, "acc_norm": 0.4824561403508772, "acc_norm_stderr": 0.0470070803355104 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5862068965517241, "acc_stderr": 0.04104269211806232, "acc_norm": 0.5862068965517241, "acc_norm_stderr": 0.04104269211806232 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.42592592592592593, "acc_stderr": 0.02546714904546955, "acc_norm": 0.42592592592592593, "acc_norm_stderr": 0.02546714904546955 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.4603174603174603, "acc_stderr": 0.04458029125470973, "acc_norm": 0.4603174603174603, "acc_norm_stderr": 0.04458029125470973 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.32, "acc_stderr": 0.04688261722621505, "acc_norm": 0.32, "acc_norm_stderr": 0.04688261722621505 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7741935483870968, "acc_stderr": 0.023785577884181012, "acc_norm": 0.7741935483870968, "acc_norm_stderr": 0.023785577884181012 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.4827586206896552, "acc_stderr": 0.035158955511657, "acc_norm": 0.4827586206896552, "acc_norm_stderr": 0.035158955511657 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.7, "acc_stderr": 0.046056618647183814, "acc_norm": 0.7, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7272727272727273, "acc_stderr": 0.0347769116216366, "acc_norm": 0.7272727272727273, "acc_norm_stderr": 0.0347769116216366 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7828282828282829, "acc_stderr": 0.02937661648494562, "acc_norm": 0.7828282828282829, "acc_norm_stderr": 0.02937661648494562 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8911917098445595, "acc_stderr": 0.022473253332768763, "acc_norm": 0.8911917098445595, "acc_norm_stderr": 0.022473253332768763 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.5948717948717949, "acc_stderr": 0.024890471769938145, "acc_norm": 0.5948717948717949, "acc_norm_stderr": 0.024890471769938145 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.29259259259259257, "acc_stderr": 0.027738969632176095, "acc_norm": 0.29259259259259257, "acc_norm_stderr": 0.027738969632176095 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.7016806722689075, "acc_stderr": 0.029719142876342856,
