open-llm-leaderboard-old/details_BEE-spoke-data__smol_llama-220M-open_instruct
收藏数据集概述
数据集摘要
该数据集是在模型 BEE-spoke-data/smol_llama-220M-open_instruct 在 Open LLM Leaderboard 上的评估运行期间自动创建的。
数据集组成
- 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，每个运行可以在每个配置中作为一个特定的分片找到，分片名称使用运行的时间戳。
- "train" 分片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。
数据加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_BEE-spoke-data__smol_llama-220M-open_instruct", "harness_winogrande_5", split="train")
最新结果
以下是 2024-01-04T13:39:47.179873 运行的最新结果：
python { "all": { "acc": 0.25998788076923746, "acc_stderr": 0.030908234134550842, "acc_norm": 0.2615422501208712, "acc_norm_stderr": 0.03173823021382238, "mc1": 0.2423500611995104, "mc1_stderr": 0.01500067437357034, "mc2": 0.4406371478334913, "mc2_stderr": 0.015537102899912702 }, "harness|arc:challenge|25": { "acc": 0.19283276450511946, "acc_stderr": 0.011529055465663345, "acc_norm": 0.25, "acc_norm_stderr": 0.012653835621466646 }, "harness|hellaswag|10": { "acc": 0.27972515435172274, "acc_stderr": 0.004479467619464786, "acc_norm": 0.29705238000398326, "acc_norm_stderr": 0.00456025908319737 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.19, "acc_stderr": 0.039427724440366234, "acc_norm": 0.19, "acc_norm_stderr": 0.039427724440366234 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.2222222222222222, "acc_stderr": 0.035914440841969694, "acc_norm": 0.2222222222222222, "acc_norm_stderr": 0.035914440841969694 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.19078947368421054, "acc_stderr": 0.03197565821032499, "acc_norm": 0.19078947368421054, "acc_norm_stderr": 0.03197565821032499 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.18, "acc_stderr": 0.03861229196653696, "acc_norm": 0.18, "acc_norm_stderr": 0.03861229196653696 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.33962264150943394, "acc_stderr": 0.02914690474779834, "acc_norm": 0.33962264150943394, "acc_norm_stderr": 0.02914690474779834 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.25, "acc_stderr": 0.03621034121889507, "acc_norm": 0.25, "acc_norm_stderr": 0.03621034121889507 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.26, "acc_stderr": 0.04408440022768081, "acc_norm": 0.26, "acc_norm_stderr": 0.04408440022768081 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.28, "acc_stderr": 0.045126085985421276, "acc_norm": 0.28, "acc_norm_stderr": 0.045126085985421276 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.27, "acc_stderr": 0.0446196043338474, "acc_norm": 0.27, "acc_norm_stderr": 0.0446196043338474 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.26011560693641617, "acc_stderr": 0.03345036916788992, "acc_norm": 0.26011560693641617, "acc_norm_stderr": 0.03345036916788992 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.21568627450980393, "acc_stderr": 0.04092563958237655, "acc_norm": 0.21568627450980393, "acc_norm_stderr": 0.04092563958237655 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.27, "acc_stderr": 0.044619604333847415, "acc_norm": 0.27, "acc_norm_stderr": 0.044619604333847415 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.26382978723404255, "acc_stderr": 0.02880998985410297, "acc_norm": 0.26382978723404255, "acc_norm_stderr": 0.02880998985410297 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.2894736842105263, "acc_stderr": 0.042663394431593935, "acc_norm": 0.2894736842105263, "acc_norm_stderr": 0.042663394431593935 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.25517241379310346, "acc_stderr": 0.03632984052707842, "acc_norm": 0.25517241379310346, "acc_norm_stderr": 0.03632984052707842 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.25925925925925924, "acc_stderr": 0.022569897074918417, "acc_norm": 0.25925925925925924, "acc_norm_stderr": 0.022569897074918417 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.1746031746031746, "acc_stderr": 0.03395490020856113, "acc_norm": 0.1746031746031746, "acc_norm_stderr": 0.03395490020856113 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.267741935483871, "acc_stderr": 0.02518900666021238, "acc_norm": 0.267741935483871, "acc_norm_stderr": 0.02518900666021238 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.2857142857142857, "acc_stderr": 0.031785297106427496, "acc_norm": 0.2857142857142857, "acc_norm_stderr": 0.031785297106427496 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.25, "acc_stderr": 0.04351941398892446, "acc_norm": 0.25, "acc_norm_stderr": 0.04351941398892446 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.21818181818181817, "acc_stderr": 0.03225078108306289, "acc_norm": 0.21818181818181817, "acc_norm_stderr": 0.03225078108306289 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.2474747474747475, "acc_stderr": 0.030746300742124495, "acc_norm": 0.2474747474747475, "acc_norm_stderr": 0.030746300742124495 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.29015544041450775, "acc_stderr": 0.032752644677915145, "acc_norm": 0.29015544041450775, "acc_norm_stderr": 0.032752644677915145 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.3333333333333333, "acc_stderr": 0.023901157979402534, "acc_norm": 0.3333333333333333, "acc_norm_stderr": 0.023901157979402534 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.26296296296296295, "acc_stderr": 0.026842057873833706, "acc_norm": 0.26296296296296
