open-llm-leaderboard-old/details_EleutherAI__gpt-neo-2.7B
收藏数据集概述
数据集简介
该数据集是在评估模型 EleutherAI/gpt-neo-2.7B 在 Open LLM Leaderboard 上的自动创建的。数据集包含 64 个配置,每个配置对应一个评估任务。
数据集结构
数据集由 2 次运行创建,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" 分割总是指向最新的结果。
数据集加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_EleutherAI__gpt-neo-2.7B", "harness_winogrande_5", split="train")
最新结果
以下是 2023-09-16T18:17:27.118418 运行的最新结果: python { "all": { "em": 0.001363255033557047, "em_stderr": 0.0003778609196460643, "f1": 0.04774853187919481, "f1_stderr": 0.0012502430800989544, "acc": 0.3067599823596958, "acc_stderr": 0.008435917406608623 }, "harness|drop|3": { "em": 0.001363255033557047, "em_stderr": 0.0003778609196460643, "f1": 0.04774853187919481, "f1_stderr": 0.0012502430800989544 }, "harness|gsm8k|5": { "acc": 0.01288855193328279, "acc_stderr": 0.003106901266499639 }, "harness|winogrande|5": { "acc": 0.6006314127861089, "acc_stderr": 0.013764933546717609 } }
配置详情
-
harness_arc_challenge_25
- 分割:2023_07_19T17_18_37.000373
- 路径:
**/details_harness|arc:challenge|25_2023-07-19T17:18:37.000373.parquet - 分割:latest
- 路径:
**/details_harness|arc:challenge|25_2023-07-19T17:18:37.000373.parquet
-
harness_drop_3
- 分割:2023_09_16T18_17_27.118418
- 路径:
**/details_harness|drop|3_2023-09-16T18-17-27.118418.parquet - 分割:latest
- 路径:
**/details_harness|drop|3_2023-09-16T18-17-27.118418.parquet
-
harness_gsm8k_5
- 分割:2023_09_16T18_17_27.118418
- 路径:
**/details_harness|gsm8k|5_2023-09-16T18-17-27.118418.parquet - 分割:latest
- 路径:
**/details_harness|gsm8k|5_2023-09-16T18-17-27.118418.parquet
-
harness_hellaswag_10
- 分割:2023_07_19T17_18_37.000373
- 路径:
**/details_harness|hellaswag|10_2023-07-19T17:18:37.000373.parquet - 分割:latest
- 路径:
**/details_harness|hellaswag|10_2023-07-19T17:18:37.000373.parquet
-
harness_hendrycksTest_5
- 分割:2023_07_19T17_18_37.000373
- 路径:多个路径,例如
**/details_harness|hendrycksTest-abstract_algebra|5_2023-07-19T17:18:37.000373.parquet - 分割:latest
- 路径:多个路径,例如
**/details_harness|hendrycksTest-abstract_algebra|5_2023-07-19T17:18:37.000373.parquet
-
harness_hendrycksTest_abstract_algebra_5
- 分割:2023_07_19T17_18_37.000373
- 路径:
**/details_harness|hendrycksTest-abstract_algebra|5_2023-07-19T17:18:37.000373.parquet - 分割:latest
- 路径:
**/details_harness|hendrycksTest-abstract_algebra|5_2023-07-19T17:18:37.000373.parquet
-
harness_hendrycksTest_anatomy_5
- 分割:2023_07_19T17_18_37.000373
- 路径:
**/details_harness|hendrycksTest-anatomy|5_2023-07-19T17:18:37.000373.parquet - 分割:latest
- 路径:
**/details_harness|hendrycksTest-anatomy|5_2023-07-19T17:18:37.000373.parquet
-
harness_hendrycksTest_astronomy_5
- 分割:2023_07_19T17_18_37.000373
- 路径:
**/details_harness|hendrycksTest-astronomy|5_2023-07-19T17:18:37.000373.parquet - 分割:latest
- 路径:
**/details_harness|hendrycksTest-astronomy|5_2023-07-19T17:18:37.000373.parquet
-
harness_hendrycksTest_business_ethics_5
- 分割:2023_07_19T17_18_37.000373
- 路径:
**/details_harness|hendrycksTest-business_ethics|5_2023-07-19T17:18:37.000373.parquet - 分割:latest
- 路径:
**/details_harness|hendrycksTest-business_ethics|5_2023-07-19T17:18:37.000373.parquet
-
harness_hendrycksTest_clinical_knowledge_5
- 分割:2023_07_19T17_18_37.000373
- 路径:
**/details_harness|hendrycksTest-clinical_knowledge|5_2023-07-19T17:18:37.000373.parquet - 分割:latest
- 路径:
**/details_harness|hendrycksTest-clinical_knowledge|5_2023-07-19T17:18:37.000373.parquet
-
harness_hendrycksTest_college_biology_5
- 分割:2023_07_19T17_18_37.000373
- 路径:
**/details_harness|hendrycksTest-college_biology|5_2023-07-19T17:18:37.000373.parquet - 分割:latest
- 路径:
**/details_harness|hendrycksTest-college_biology|5_2023-07-19T17:18:37.000373.parquet
-
harness_hendrycksTest_college_chemistry_5
- 分割:2023_07_19T17_18_37.000373
- 路径:
**/details_harness|hendrycksTest-college_chemistry|5_2023-07-19T17:18:37.000373.parquet - 分割:latest
- 路径:
**/details_harness|hendrycksTest-college_chemistry|5_2023-07-19T17:18:37.000373.parquet
-
harness_hendrycksTest_college_computer_science_5
- 分割:2023_07_19T17_18_37.000373
- 路径:
**/details_harness|hendrycksTest-college_computer_science|5_2023-07-19T17:18:37.000373.parquet - 分割:latest
- 路径:
**/details_harness|hendrycksTest-college_computer_science|5_2023-07-19T17:18:37.000373.parquet
-
harness_hendrycksTest_college_mathematics_5
- 分割:2023_07_19T17_18_37.000373
- 路径:
**/details_harness|hendrycksTest-college_mathematics|5_2023-07-19T17:18:37.000373.parquet - 分割:latest
- 路径:
**/details_harness|hendrycksTest-college_mathematics|5_2023-07-19T17:18:37.000373.parquet
-
harness_hendrycksTest_college_medicine_5
- 分割:2023_07_19T17_18_37.000373
- 路径:
**/details_harness|hendrycksTest-college_medicine|5_2023-07-19T17:18:37.000373.parquet - 分割:latest
- 路径:
**/details_harness|hendrycksTest-college_medicine|5_2023-07-19T17:18:37.000373.parquet
-
harness_hendrycksTest_college_physics_5
- 分割:2023_07_19T17_18_37.000373
- 路径:
**/details_harness|hendrycksTest-college_physics|5_2023-07-19T17:18:37.000373.parquet - 分割:latest
- 路径:
**/details_harness|hendrycksTest-college_physics|5_2023-07-19T17:18:37.000373.parquet
-
harness_hendrycksTest_computer_security_5
- 分割:2023_07_19T17_18_37.000373
- 路径:
**/details_harness|hendrycksTest-computer_security|5_2023-07-19T17:18:37.000373.parquet - 分割:latest
- 路径:
**/details_harness|hendrycksTest-computer_security|5_2023-07-19T17:18:37.000373.parquet
-
harness_hendrycksTest_conceptual_physics_5
- 分割:2023_07_19T17_18_37.000373
- 路径:
**/details_harness|hendrycksTest-conceptual_physics|5_2023-07-19T17:18:37.000373.parquet - 分割:latest
- 路径:
**/details_harness|hendrycksTest-conceptual_physics|5_2023-07-19T17:18:37.000373.parquet
-
harness_hendrycksTest_econometrics_5
- 分割:2023_07_19T17_18_37.000373
- 路径:
**/details_harness|hendrycksTest-econometrics|5_2023-07-19T17:18:37.000373.parquet - 分割:latest
- 路径:
**/details_harness|hendrycksTest-econometrics|5_2023-07-19T17:18:37.000373.parquet
-
harness_hendrycksTest_electrical_engineering_5
- 分割:2023_07_19T17_18_37.000373
- 路径:
**/details_harness|hendrycksTest-electrical_engineering|5_2023-07-19T17:18:37.000373.parquet - 分割:latest
- 路径:
**/details_harness|hendrycksTest-electrical_engineering|5_2023-07-19T17:18:37.000373.parquet
-
harness_hendrycksTest_elementary_mathematics_5
- 分割:2023_07_19T



