open-llm-leaderboard/details_elinas__chronos-70b-v2
收藏数据集概述
该数据集是在对模型 elinas/chronos-70b-v2 进行评估运行期间自动创建的,用于 Open LLM Leaderboard。
数据集组成
- 数据集由 64 个配置组成,每个配置对应一个评估任务。
- 数据集从 2 次运行中创建,每次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_elinas__chronos-70b-v2", "harness_winogrande_5", split="train")
最新结果
以下是 2023-10-29T18:55:58.874073 运行的最新结果: python { "all": { "em": 0.004928691275167785, "em_stderr": 0.0007171872517059785, "f1": 0.07059983221476518, "f1_stderr": 0.0015017323147269025, "acc": 0.5493677195598541, "acc_stderr": 0.011716161385886395 }, "harness|drop|3": { "em": 0.004928691275167785, "em_stderr": 0.0007171872517059785, "f1": 0.07059983221476518, "f1_stderr": 0.0015017323147269025 }, "harness|gsm8k|5": { "acc": 0.28658074298711145, "acc_stderr": 0.0124548416683377 }, "harness|winogrande|5": { "acc": 0.8121546961325967, "acc_stderr": 0.01097748110343509 } }
配置详情
-
harness_arc_challenge_25
- 分片:2023_09_13T13_39_47.778697
- 路径:
**/details_harness|arc:challenge|25_2023-09-13T13-39-47.778697.parquet - 分片:latest
- 路径:
**/details_harness|arc:challenge|25_2023-09-13T13-39-47.778697.parquet
-
harness_drop_3
- 分片:2023_10_29T18_55_58.874073
- 路径:
**/details_harness|drop|3_2023-10-29T18-55-58.874073.parquet - 分片:latest
- 路径:
**/details_harness|drop|3_2023-10-29T18-55-58.874073.parquet
-
harness_gsm8k_5
- 分片:2023_10_29T18_55_58.874073
- 路径:
**/details_harness|gsm8k|5_2023-10-29T18-55-58.874073.parquet - 分片:latest
- 路径:
**/details_harness|gsm8k|5_2023-10-29T18-55-58.874073.parquet
-
harness_hellaswag_10
- 分片:2023_09_13T13_39_47.778697
- 路径:
**/details_harness|hellaswag|10_2023-09-13T13-39-47.778697.parquet - 分片:latest
- 路径:
**/details_harness|hellaswag|10_2023-09-13T13-39-47.778697.parquet
-
harness_hendrycksTest_5
- 分片:2023_09_13T13_39_47.778697
- 路径:
**/details_harness|hendrycksTest-abstract_algebra|5_2023-09-13T13-39-47.778697.parquet等 40 个文件 - 分片:latest
- 路径:
**/details_harness|hendrycksTest-abstract_algebra|5_2023-09-13T13-39-47.778697.parquet等 40 个文件
-
harness_hendrycksTest_abstract_algebra_5
- 分片:2023_09_13T13_39_47.778697
- 路径:
**/details_harness|hendrycksTest-abstract_algebra|5_2023-09-13T13-39-47.778697.parquet - 分片:latest
- 路径:
**/details_harness|hendrycksTest-abstract_algebra|5_2023-09-13T13-39-47.778697.parquet
-
harness_hendrycksTest_anatomy_5
- 分片:2023_09_13T13_39_47.778697
- 路径:
**/details_harness|hendrycksTest-anatomy|5_2023-09-13T13-39-47.778697.parquet - 分片:latest
- 路径:
**/details_harness|hendrycksTest-anatomy|5_2023-09-13T13-39-47.778697.parquet
-
harness_hendrycksTest_astronomy_5
- 分片:2023_09_13T13_39_47.778697
- 路径:
**/details_harness|hendrycksTest-astronomy|5_2023-09-13T13-39-47.778697.parquet - 分片:latest
- 路径:
**/details_harness|hendrycksTest-astronomy|5_2023-09-13T13-39-47.778697.parquet
-
harness_hendrycksTest_business_ethics_5
- 分片:2023_09_13T13_39_47.778697
- 路径:
**/details_harness|hendrycksTest-business_ethics|5_2023-09-13T13-39-47.778697.parquet - 分片:latest
- 路径:
**/details_harness|hendrycksTest-business_ethics|5_2023-09-13T13-39-47.778697.parquet
-
harness_hendrycksTest_clinical_knowledge_5
- 分片:2023_09_13T13_39_47.778697
- 路径:
**/details_harness|hendrycksTest-clinical_knowledge|5_2023-09-13T13-39-47.778697.parquet - 分片:latest
- 路径:
**/details_harness|hendrycksTest-clinical_knowledge|5_2023-09-13T13-39-47.778697.parquet
-
harness_hendrycksTest_college_biology_5
- 分片:2023_09_13T13_39_47.778697
- 路径:
**/details_harness|hendrycksTest-college_biology|5_2023-09-13T13-39-47.778697.parquet - 分片:latest
- 路径:
**/details_harness|hendrycksTest-college_biology|5_2023-09-13T13-39-47.778697.parquet
-
harness_hendrycksTest_college_chemistry_5
- 分片:2023_09_13T13_39_47.778697
- 路径:
**/details_harness|hendrycksTest-college_chemistry|5_2023-09-13T13-39-47.778697.parquet - 分片:latest
- 路径:
**/details_harness|hendrycksTest-college_chemistry|5_2023-09-13T13-39-47.778697.parquet
-
harness_hendrycksTest_college_computer_science_5
- 分片:2023_09_13T13_39_47.778697
- 路径:
**/details_harness|hendrycksTest-college_computer_science|5_2023-09-13T13-39-47.778697.parquet - 分片:latest
- 路径:
**/details_harness|hendrycksTest-college_computer_science|5_2023-09-13T13-39-47.778697.parquet
-
harness_hendrycksTest_college_mathematics_5
- 分片:2023_09_13T13_39_47.778697
- 路径:
**/details_harness|hendrycksTest-college_mathematics|5_2023-09-13T13-39-47.778697.parquet - 分片:latest
- 路径:
**/details_harness|hendrycksTest-college_mathematics|5_2023-09-13T13-39-47.778697.parquet
-
harness_hendrycksTest_college_medicine_5
- 分片:2023_09_13T13_39_47.778697
- 路径:
**/details_harness|hendrycksTest-college_medicine|5_2023-09-13T13-39-47.778697.parquet - 分片:latest
- 路径:
**/details_harness|hendrycksTest-college_medicine|5_2023-09-13T13-39-47.778697.parquet
-
harness_hendrycksTest_college_physics_5
- 分片:2023_09_13T13_39_47.778697
- 路径:
**/details_harness|hendrycksTest-college_physics|5_2023-09-13T13-39-47.778697.parquet - 分片:latest
- 路径:
**/details_harness|hendrycksTest-college_physics|5_2023-09-13T13-39-47.778697.parquet
-
harness_hendrycksTest_computer_security_5
- 分片:2023_09_13T13_39_47.778697
- 路径:
**/details_harness|hendrycksTest-computer_security|5_2023-09-13T13-39-47.778697.parquet - 分片:latest
- 路径:
**/details_harness|hendrycksTest-computer_security|5_2023-09-13T13-39-47.778697.parquet
-
harness_hendrycksTest_conceptual_physics_5
- 分片:2023_09_13T13_39_47.778697
- 路径:
**/details_harness|hendrycksTest-conceptual_physics|5_2023-09-13T13-39-47.778697.parquet - 分片:latest
- 路径:
**/details_harness|hendrycksTest-conceptual_physics|5_2023-09-13T13-39-47.778697.parquet
-
harness_hendrycksTest_econometrics_5
- 分片:2023_09_13T13_39_47.778697
- 路径:
**/details_harness|hendrycksTest-econometrics|5_2023-09-13T13-39-47.778697.parquet - 分片:latest
- 路径:
**/details_harness|hendrycksTest-econometrics|5_2023-09-13T13-39-47.778697.parquet
-
harness_hendrycksTest_electrical_engineering_5
- 分片:2023_09_13T13_39_47.778697
- 路径:`**/details_harness|hendrycksTest-electrical_engineering|5_2023-09-13T13-3



