open-llm-leaderboard-old/details_BFauber__opt1.3b_10e6
收藏数据集概述
数据集简介
该数据集是在对模型 BFauber/opt1.3b_10e6 进行评估运行期间自动创建的,用于 Open LLM Leaderboard。
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割找到,分割名称使用运行的时间戳。"train" 分割始终指向最新的结果。
额外配置
一个额外的配置 "results" 存储了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_BFauber__opt1.3b_10e6", "harness_winogrande_5", split="train")
最新结果
这些是最新结果,来自 2024-02-02T19:21:41.324363 的运行: python { "all": { "acc": 0.2600682096146715, "acc_stderr": 0.03101730232799903, "acc_norm": 0.26160699891348205, "acc_norm_stderr": 0.03184452335795072, "mc1": 0.2386780905752754, "mc1_stderr": 0.014922629695456416, "mc2": 0.4272454038428265, "mc2_stderr": 0.015391374654641474 }, "harness|arc:challenge|25": { "acc": 0.22525597269624573, "acc_stderr": 0.012207839995407312, "acc_norm": 0.257679180887372, "acc_norm_stderr": 0.012780770562768414 }, "harness|hellaswag|10": { "acc": 0.3370842461661024, "acc_stderr": 0.00471747833568962, "acc_norm": 0.41674965146385184, "acc_norm_stderr": 0.004920130733271778 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, # 其他任务的结果... }
配置详情
-
config_name: harness_arc_challenge_25
- data_files:
- split: 2024_02_02T19_21_41.324363
- path:
**/details_harness|arc:challenge|25_2024-02-02T19-21-41.324363.parquet
- path:
- split: latest
- path:
**/details_harness|arc:challenge|25_2024-02-02T19-21-41.324363.parquet
- path:
- split: 2024_02_02T19_21_41.324363
- data_files:
-
config_name: harness_gsm8k_5
- data_files:
- split: 2024_02_02T19_21_41.324363
- path:
**/details_harness|gsm8k|5_2024-02-02T19-21-41.324363.parquet
- path:
- split: latest
- path:
**/details_harness|gsm8k|5_2024-02-02T19-21-41.324363.parquet
- path:
- split: 2024_02_02T19_21_41.324363
- data_files:
-
config_name: harness_hellaswag_10
- data_files:
- split: 2024_02_02T19_21_41.324363
- path:
**/details_harness|hellaswag|10_2024-02-02T19-21-41.324363.parquet
- path:
- split: latest
- path:
**/details_harness|hellaswag|10_2024-02-02T19-21-41.324363.parquet
- path:
- split: 2024_02_02T19_21_41.324363
- data_files:
-
config_name: harness_hendrycksTest_5
- data_files:
- split: 2024_02_02T19_21_41.324363
- path:
**/details_harness|hendrycksTest-abstract_algebra|5_2024-02-02T19-21-41.324363.parquet**/details_harness|hendrycksTest-anatomy|5_2024-02-02T19-21-41.324363.parquet**/details_harness|hendrycksTest-astronomy|5_2024-02-02T19-21-41.324363.parquet**/details_harness|hendrycksTest-business_ethics|5_2024-02-02T19-21-41.324363.parquet**/details_harness|hendrycksTest-clinical_knowledge|5_2024-02-02T19-21-41.324363.parquet**/details_harness|hendrycksTest-college_biology|5_2024-02-02T19-21-41.324363.parquet**/details_harness|hendrycksTest-college_chemistry|5_2024-02-02T19-21-41.324363.parquet**/details_harness|hendrycksTest-college_computer_science|5_2024-02-02T19-21-41.324363.parquet**/details_harness|hendrycksTest-college_mathematics|5_2024-02-02T19-21-41.324363.parquet**/details_harness|hendrycksTest-college_medicine|5_2024-02-02T19-21-41.324363.parquet**/details_harness|hendrycksTest-college_physics|5_2024-02-02T19-21-41.324363.parquet**/details_harness|hendrycksTest-computer_security|5_2024-02-02T19-21-41.324363.parquet**/details_harness|hendrycksTest-conceptual_physics|5_2024-02-02T19-21-41.324363.parquet**/details_harness|hendrycksTest-econometrics|5_2024-02-02T19-21-41.324363.parquet**/details_harness|hendrycksTest-electrical_engineering|5_2024-02-02T19-21-41.324363.parquet**/details_harness|hendrycksTest-elementary_mathematics|5_2024-02-02T19-21-41.324363.parquet**/details_harness|hendrycksTest-formal_logic|5_2024-02-02T19-21-41.324363.parquet**/details_harness|hendrycksTest-global_facts|5_2024-02-02T19-21-41.324363.parquet**/details_harness|hendrycksTest-high_school_biology|5_2024-02-02T19-21-41.324363.parquet**/details_harness|hendrycksTest-high_school_chemistry|5_2024-02-02T19-21-41.324363.parquet**/details_harness|hendrycksTest-high_school_computer_science|5_2024-02-02T19-21-41.324363.parquet**/details_harness|hendrycksTest-high_school_european_history|5_2024-02-02T19-21-41.324363.parquet**/details_harness|hendrycksTest-high_school_geography|5_2024-02-02T19-21-41.324363.parquet**/details_harness|hendrycksTest-high_school_government_and_politics|5_2024-02-02T19-21-41.324363.parquet**/details_harness|hendrycksTest-high_school_macroeconomics|5_2024-02-02T19-21-41.324363.parquet**/details_harness|hendrycksTest-high_school_mathematics|5_2024-02-02T19-21-41.324363.parquet**/details_harness|hendrycksTest-high_school_microeconomics|5_2024-02-02T19-21-41.324363.parquet**/details_harness|hendrycksTest-high_school_physics|5_2024-02-02T19-21-41.324363.parquet**/details_harness|hendrycksTest-high_school_psychology|5_2024-02-02T19-21-41.324363.parquet**/details_harness|hendrycksTest-high_school_statistics|5_2024-02-02T19-21-41.324363.parquet**/details_harness|hendrycksTest-high_school_us_history|5_2024-02-02T19-21-41.324363.parquet**/details_harness|hendrycksTest-high_school_world_history|5_2024-02-02T19-21-41.324363.parquet**/details_harness|hendrycksTest-human_aging|5_2024-02-02T19-21-41.324363.parquet**/details_harness|hendrycksTest-human_sexuality|5_2024-02-02T19-21-41.324363.parquet**/details_harness|hendrycksTest-international_law|5_2024-02-02T19-21-41.324363.parquet**/details_harness|hendrycksTest-jurisprudence|5_2024-02-02T19-21-41.324363.parquet**/details_harness|hendrycksTest-logical_fallacies|5_2024-02-02T19-21-41.324363.parquet**/details_harness|hendrycksTest-machine_learning|5_2024-02-02T19-21-41.324363.parquet**/details_harness|hendrycksTest-management|5_2024-02-02T19-21-41.324363.parquet**/details_harness|hendrycksTest-marketing|5_2024-02-02T19-21-41.324363.parquet**/details_harness|hendrycksTest-medical_genetics|5_2024-02-02T19-21-41.324363.parquet**/details_harness|hendrycksTest-miscellaneous|5_2024-02-02T19-21-41.324363.parquet**/details_harness|hendrycksTest-moral_disputes|5_2024-02-02T19-21-41.324363.parquet**/details_harness|hendrycksTest-moral_scenarios|5_2024-02-02T19-21-41.324363.parquet**/details_harness|hendrycksTest-nutrition|5_2024-02-02T19-21-41.324363.parquet**/details_harness|hendrycksTest-philosophy|5_2024-02-02T19-21-41.324363.parquet**/details_harness|hendrycksTest-prehistory|5_2024-02-02T19-21-41.324363.parquet**/details_harness|hendrycksTest-professional_accounting|5_2024-02-02T19-21-41.324363.parquet**/details_harness|hendrycksTest-professional_law|5_2024-02-02T19-21-41.324363.parquet- `**/details_harness|hendrycksTest-
- path:
- split: 2024_02_02T19_21_41.324363
- data_files:



