open-llm-leaderboard-old/details_TheTravellingEngineer__bloom-1b1-RLHF-v2
收藏Hugging Face2023-12-02 更新2024-06-22 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard-old/details_TheTravellingEngineer__bloom-1b1-RLHF-v2
下载链接
链接失效反馈官方服务:
资源简介:
该数据集是在模型TheTravellingEngineer/bloom-1b1-RLHF-v2的评估运行中自动创建的。数据集由64个配置组成,每个配置对应一个评估任务。数据集是从4次运行中创建的,每次运行都作为特定配置中的一个分割,分割名称使用运行的时间戳。train分割始终指向最新的结果。此外,还有一个名为results的配置,存储了所有运行的聚合结果,并用于计算和显示在Open LLM Leaderboard上的聚合指标。
该数据集是在模型TheTravellingEngineer/bloom-1b1-RLHF-v2的评估运行中自动创建的。数据集由64个配置组成,每个配置对应一个评估任务。数据集是从4次运行中创建的,每次运行都作为特定配置中的一个分割,分割名称使用运行的时间戳。train分割始终指向最新的结果。此外,还有一个名为results的配置,存储了所有运行的聚合结果,并用于计算和显示在Open LLM Leaderboard上的聚合指标。
提供机构:
open-llm-leaderboard-old
原始信息汇总
数据集概述
该数据集是在模型TheTravellingEngineer/bloom-1b1-RLHF-v2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64个配置,每个配置对应一个评估任务。
- 数据集从4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,用于计算和显示在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_TheTravellingEngineer__bloom-1b1-RLHF-v2", "harness_gsm8k_5", split="train")
最新结果
以下是2023-12-02T13:43:58.509097运行的最新结果: python { "all": { "acc": 0.0, "acc_stderr": 0.0 }, "harness|gsm8k|5": { "acc": 0.0, "acc_stderr": 0.0 } }
配置详情
-
harness_arc_challenge_25
- 分割: 2023_08_16T12_59_32.515550
- 路径: **/details_harness|arc:challenge|25_2023-08-16T12:59:32.515550.parquet
- 分割: latest
- 路径: **/details_harness|arc:challenge|25_2023-08-16T12:59:32.515550.parquet
- 分割: 2023_08_16T12_59_32.515550
-
harness_drop_3
- 分割: 2023_10_18T08_04_05.021795
- 路径: **/details_harness|drop|3_2023-10-18T08-04-05.021795.parquet
- 分割: latest
- 路径: **/details_harness|drop|3_2023-10-18T08-04-05.021795.parquet
- 分割: 2023_10_18T08_04_05.021795
-
harness_gsm8k_5
- 分割: 2023_10_18T08_04_05.021795
- 路径: **/details_harness|gsm8k|5_2023-10-18T08-04-05.021795.parquet
- 分割: 2023_12_02T13_43_40.813288
- 路径: **/details_harness|gsm8k|5_2023-12-02T13-43-40.813288.parquet
- 分割: 2023_12_02T13_43_58.509097
- 路径: **/details_harness|gsm8k|5_2023-12-02T13-43-58.509097.parquet
- 分割: latest
- 路径: **/details_harness|gsm8k|5_2023-12-02T13-43-58.509097.parquet
- 分割: 2023_10_18T08_04_05.021795
-
harness_hellaswag_10
- 分割: 2023_08_16T12_59_32.515550
- 路径: **/details_harness|hellaswag|10_2023-08-16T12:59:32.515550.parquet
- 分割: latest
- 路径: **/details_harness|hellaswag|10_2023-08-16T12:59:32.515550.parquet
- 分割: 2023_08_16T12_59_32.515550
-
harness_hendrycksTest_5
- 分割: 2023_08_16T12_59_32.515550
- 路径:
- **/details_harness|hendrycksTest-abstract_algebra|5_2023-08-16T12:59:32.515550.parquet
- **/details_harness|hendrycksTest-anatomy|5_2023-08-16T12:59:32.515550.parquet
- **/details_harness|hendrycksTest-astronomy|5_2023-08-16T12:59:32.515550.parquet
- **/details_harness|hendrycksTest-business_ethics|5_2023-08-16T12:59:32.515550.parquet
- **/details_harness|hendrycksTest-clinical_knowledge|5_2023-08-16T12:59:32.515550.parquet
- **/details_harness|hendrycksTest-college_biology|5_2023-08-16T12:59:32.515550.parquet
- **/details_harness|hendrycksTest-college_chemistry|5_2023-08-16T12:59:32.515550.parquet
- **/details_harness|hendrycksTest-college_computer_science|5_2023-08-16T12:59:32.515550.parquet
- **/details_harness|hendrycksTest-college_mathematics|5_2023-08-16T12:59:32.515550.parquet
- **/details_harness|hendrycksTest-college_medicine|5_2023-08-16T12:59:32.515550.parquet
- **/details_harness|hendrycksTest-college_physics|5_2023-08-16T12:59:32.515550.parquet
- **/details_harness|hendrycksTest-computer_security|5_2023-08-16T12:59:32.515550.parquet
- **/details_harness|hendrycksTest-conceptual_physics|5_2023-08-16T12:59:32.515550.parquet
- **/details_harness|hendrycksTest-econometrics|5_2023-08-16T12:59:32.515550.parquet
- **/details_harness|hendrycksTest-electrical_engineering|5_2023-08-16T12:59:32.515550.parquet
- **/details_harness|hendrycksTest-elementary_mathematics|5_2023-08-16T12:59:32.515550.parquet
- **/details_harness|hendrycksTest-formal_logic|5_2023-08-16T12:59:32.515550.parquet
- **/details_harness|hendrycksTest-global_facts|5_2023-08-16T12:59:32.515550.parquet
- **/details_harness|hendrycksTest-high_school_biology|5_2023-08-16T12:59:32.515550.parquet
- **/details_harness|hendrycksTest-high_school_chemistry|5_2023-08-16T12:59:32.515550.parquet
- **/details_harness|hendrycksTest-high_school_computer_science|5_2023-08-16T12:59:32.515550.parquet
- **/details_harness|hendrycksTest-high_school_european_history|5_2023-08-16T12:59:32.515550.parquet
- **/details_harness|hendrycksTest-high_school_geography|5_2023-08-16T12:59:32.515550.parquet
- **/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-08-16T12:59:32.515550.parquet
- **/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-08-16T12:59:32.515550.parquet
- **/details_harness|hendrycksTest-high_school_mathematics|5_2023-08-16T12:59:32.515550.parquet
- **/details_harness|hendrycksTest-high_school_microeconomics|5_2023-08-16T12:59:32.515550.parquet
- **/details_harness|hendrycksTest-high_school_physics|5_2023-08-16T12:59:32.515550.parquet
- **/details_harness|hendrycksTest-high_school_psychology|5_2023-08-16T12:59:32.515550.parquet
- **/details_harness|hendrycksTest-high_school_statistics|5_2023-08-16T12:59:32.515550.parquet
- **/details_harness|hendrycksTest-high_school_us_history|5_2023-08-16T12:59:32.515550.parquet
- **/details_harness|hendrycksTest-high_school_world_history|5_2023-08-16T12:59:32.515550.parquet
- **/details_harness|hendrycksTest-human_aging|5_2023-08-16T12:59:32.515550.parquet
- **/details_harness|hendrycksTest-human_sexuality|5_2023-08-16T12:59:32.515550.parquet
- **/details_harness|hendrycksTest-international_law|5_2023-08-16T12:59:32.515550.parquet
- **/details_harness|hendrycksTest-jurisprudence|5_2023-08-16T12:59:32.515550.parquet
- **/details_harness|hendrycksTest-logical_fallacies|5_2023-08-16T12:59:32.515550.parquet
- **/details_harness|hendrycksTest-machine_learning|5_2023-08-16T12:59:32.515550.parquet
- **/details_harness|hendrycksTest-management|5_2023-08-16T12:59:32.515550.parquet
- **/details_harness|hendrycksTest-marketing|5_2023-08-16T12:59:32.515550.parquet
- **/details_harness|hendrycksTest-medical_genetics|5_2023-08-16T12:59:32.515550.parquet
- **/details_harness|hendrycksTest-miscellaneous|5_2023-08-16T12:59:32.515550.parquet
- **/details_harness|hendrycksTest-moral_disputes|5_2023-08-16T12:59:32.515550.parquet
- **/details_harness|hendrycksTest-moral_scenarios|5_2023-08-16T12:59:32.515550.parquet
- **/details_harness|hendrycksTest-nutrition|5_2023-08-16T12:59:32.515550.parquet
- **/details_harness|hendrycksTest-philosophy|5_2023-08-16T12:59:32.515550.parquet
- **/details_harness|hendrycksTest-prehistory|5_2023-08-16T12:59:32.515550.parquet
- **/details_harness|hendrycksTest-professional_accounting|5_2023-08-16T12:59:32.515550.parquet
- **/details_harness|hendrycksTest-professional_law|5_2023-08-16T12:59:32.515550.parquet
- **/details_harness|hendrycksTest-professional_medicine|5_2023-08-16T12:59:32.515550.parquet
- **/details_harness|hendrycksTest-professional_psychology|5_2023-08-16T12:59:32.515550.parquet
- **/details_harness|hendrycksTest-public_relations|5_2023-08-16T12:59:32.515550.parquet
- **/details_harness|hendrycksTest-security_studies|5_2023-08-16T12:59:32.515550.parquet
- **/details_harness|hendrycks
- 路径:
- 分割: 2023_08_16T12_59_32.515550



