open-llm-leaderboard/details_abacusai__Smaug-2-72B
收藏Hugging Face2024-03-30 更新2024-06-11 收录
下载链接：
https://hf-mirror.com/datasets/open-llm-leaderboard/details_abacusai__Smaug-2-72B
下载链接
链接失效反馈官方服务：
资源简介：
---
pretty_name: Evaluation run of abacusai/Smaug-2-72B
dataset_summary: "Dataset automatically created during the evaluation run of model\
\ [abacusai/Smaug-2-72B](https://huggingface.co/abacusai/Smaug-2-72B) on the [Open\
\ LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard).\n\
\nThe dataset is composed of 63 configuration, each one coresponding to one of the\
\ evaluated task.\n\nThe dataset has been created from 1 run(s). Each run can be\
\ found as a specific split in each configuration, the split being named using the\
\ timestamp of the run.The \"train\" split is always pointing to the latest results.\n\
\nAn additional configuration \"results\" store all the aggregated results of the\
\ run (and is used to compute and display the aggregated metrics on the [Open LLM\
\ Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)).\n\
\nTo load the details from a run, you can for instance do the following:\n```python\n\
from datasets import load_dataset\ndata = load_dataset(\"open-llm-leaderboard/details_abacusai__Smaug-2-72B\"\
,\n\t\"harness_winogrande_5\",\n\tsplit=\"train\")\n```\n\n## Latest results\n\n\
These are the [latest results from run 2024-03-30T01:31:21.040468](https://huggingface.co/datasets/open-llm-leaderboard/details_abacusai__Smaug-2-72B/blob/main/results_2024-03-30T01-31-21.040468.json)(note\
\ that their might be results for other tasks in the repos if successive evals didn't\
\ cover the same tasks. You find each in the results and the \"latest\" split for\
\ each eval):\n\n```python\n{\n \"all\": {\n \"acc\": 0.767796907393265,\n\
\ \"acc_stderr\": 0.027982043283656534,\n \"acc_norm\": 0.7771325485017166,\n\
\ \"acc_norm_stderr\": 0.02849243108304867,\n \"mc1\": 0.4749082007343941,\n\
\ \"mc1_stderr\": 0.017481446804104003,\n \"mc2\": 0.6489991000331015,\n\
\ \"mc2_stderr\": 0.015361203699885669\n },\n \"harness|arc:challenge|25\"\
: {\n \"acc\": 0.6467576791808873,\n \"acc_stderr\": 0.013967822714840055,\n\
\ \"acc_norm\": 0.6791808873720137,\n \"acc_norm_stderr\": 0.013640943091946528\n\
\ },\n \"harness|hellaswag|10\": {\n \"acc\": 0.6796454889464251,\n\
\ \"acc_stderr\": 0.004656591678606762,\n \"acc_norm\": 0.8636725751842262,\n\
\ \"acc_norm_stderr\": 0.0034243464481037195\n },\n \"harness|hendrycksTest-abstract_algebra|5\"\
: {\n \"acc\": 0.52,\n \"acc_stderr\": 0.050211673156867795,\n \
\ \"acc_norm\": 0.52,\n \"acc_norm_stderr\": 0.050211673156867795\n \
\ },\n \"harness|hendrycksTest-anatomy|5\": {\n \"acc\": 0.7407407407407407,\n\
\ \"acc_stderr\": 0.03785714465066653,\n \"acc_norm\": 0.7407407407407407,\n\
\ \"acc_norm_stderr\": 0.03785714465066653\n },\n \"harness|hendrycksTest-astronomy|5\"\
: {\n \"acc\": 0.875,\n \"acc_stderr\": 0.026913523521537846,\n \
\ \"acc_norm\": 0.875,\n \"acc_norm_stderr\": 0.026913523521537846\n\
\ },\n \"harness|hendrycksTest-business_ethics|5\": {\n \"acc\": 0.79,\n\
\ \"acc_stderr\": 0.040936018074033256,\n \"acc_norm\": 0.79,\n \
\ \"acc_norm_stderr\": 0.040936018074033256\n },\n \"harness|hendrycksTest-clinical_knowledge|5\"\
: {\n \"acc\": 0.8037735849056604,\n \"acc_stderr\": 0.02444238813110083,\n\
\ \"acc_norm\": 0.8037735849056604,\n \"acc_norm_stderr\": 0.02444238813110083\n\
\ },\n \"harness|hendrycksTest-college_biology|5\": {\n \"acc\": 0.9166666666666666,\n\
\ \"acc_stderr\": 0.023112508176051236,\n \"acc_norm\": 0.9166666666666666,\n\
\ \"acc_norm_stderr\": 0.023112508176051236\n },\n \"harness|hendrycksTest-college_chemistry|5\"\
: {\n \"acc\": 0.59,\n \"acc_stderr\": 0.04943110704237102,\n \
\ \"acc_norm\": 0.59,\n \"acc_norm_stderr\": 0.04943110704237102\n \
\ },\n \"harness|hendrycksTest-college_computer_science|5\": {\n \"acc\"\
: 0.72,\n \"acc_stderr\": 0.04512608598542127,\n \"acc_norm\": 0.72,\n\
\ \"acc_norm_stderr\": 0.04512608598542127\n },\n \"harness|hendrycksTest-college_mathematics|5\"\
: {\n \"acc\": 0.53,\n \"acc_stderr\": 0.05016135580465919,\n \
\ \"acc_norm\": 0.53,\n \"acc_norm_stderr\": 0.05016135580465919\n \
\ },\n \"harness|hendrycksTest-college_medicine|5\": {\n \"acc\": 0.7456647398843931,\n\
\ \"acc_stderr\": 0.0332055644308557,\n \"acc_norm\": 0.7456647398843931,\n\
\ \"acc_norm_stderr\": 0.0332055644308557\n },\n \"harness|hendrycksTest-college_physics|5\"\
: {\n \"acc\": 0.5882352941176471,\n \"acc_stderr\": 0.04897104952726367,\n\
\ \"acc_norm\": 0.5882352941176471,\n \"acc_norm_stderr\": 0.04897104952726367\n\
\ },\n \"harness|hendrycksTest-computer_security|5\": {\n \"acc\":\
\ 0.85,\n \"acc_stderr\": 0.03588702812826371,\n \"acc_norm\": 0.85,\n\
\ \"acc_norm_stderr\": 0.03588702812826371\n },\n \"harness|hendrycksTest-conceptual_physics|5\"\
: {\n \"acc\": 0.774468085106383,\n \"acc_stderr\": 0.027321078417387536,\n\
\ \"acc_norm\": 0.774468085106383,\n \"acc_norm_stderr\": 0.027321078417387536\n\
\ },\n \"harness|hendrycksTest-econometrics|5\": {\n \"acc\": 0.5701754385964912,\n\
\ \"acc_stderr\": 0.04657047260594964,\n \"acc_norm\": 0.5701754385964912,\n\
\ \"acc_norm_stderr\": 0.04657047260594964\n },\n \"harness|hendrycksTest-electrical_engineering|5\"\
: {\n \"acc\": 0.8,\n \"acc_stderr\": 0.0333333333333333,\n \
\ \"acc_norm\": 0.8,\n \"acc_norm_stderr\": 0.0333333333333333\n },\n\
\ \"harness|hendrycksTest-elementary_mathematics|5\": {\n \"acc\": 0.708994708994709,\n\
\ \"acc_stderr\": 0.023393826500484865,\n \"acc_norm\": 0.708994708994709,\n\
\ \"acc_norm_stderr\": 0.023393826500484865\n },\n \"harness|hendrycksTest-formal_logic|5\"\
: {\n \"acc\": 0.5873015873015873,\n \"acc_stderr\": 0.04403438954768177,\n\
\ \"acc_norm\": 0.5873015873015873,\n \"acc_norm_stderr\": 0.04403438954768177\n\
\ },\n \"harness|hendrycksTest-global_facts|5\": {\n \"acc\": 0.59,\n\
\ \"acc_stderr\": 0.04943110704237101,\n \"acc_norm\": 0.59,\n \
\ \"acc_norm_stderr\": 0.04943110704237101\n },\n \"harness|hendrycksTest-high_school_biology|5\"\
: {\n \"acc\": 0.896774193548387,\n \"acc_stderr\": 0.017308381281034516,\n\
\ \"acc_norm\": 0.896774193548387,\n \"acc_norm_stderr\": 0.017308381281034516\n\
\ },\n \"harness|hendrycksTest-high_school_chemistry|5\": {\n \"acc\"\
: 0.6650246305418719,\n \"acc_stderr\": 0.033208527423483104,\n \"\
acc_norm\": 0.6650246305418719,\n \"acc_norm_stderr\": 0.033208527423483104\n\
\ },\n \"harness|hendrycksTest-high_school_computer_science|5\": {\n \
\ \"acc\": 0.81,\n \"acc_stderr\": 0.039427724440366234,\n \"acc_norm\"\
: 0.81,\n \"acc_norm_stderr\": 0.039427724440366234\n },\n \"harness|hendrycksTest-high_school_european_history|5\"\
: {\n \"acc\": 0.8606060606060606,\n \"acc_stderr\": 0.027045948825865387,\n\
\ \"acc_norm\": 0.8606060606060606,\n \"acc_norm_stderr\": 0.027045948825865387\n\
\ },\n \"harness|hendrycksTest-high_school_geography|5\": {\n \"acc\"\
: 0.9292929292929293,\n \"acc_stderr\": 0.01826310542019949,\n \"\
acc_norm\": 0.9292929292929293,\n \"acc_norm_stderr\": 0.01826310542019949\n\
\ },\n \"harness|hendrycksTest-high_school_government_and_politics|5\": {\n\
\ \"acc\": 0.9896373056994818,\n \"acc_stderr\": 0.007308424386792208,\n\
\ \"acc_norm\": 0.9896373056994818,\n \"acc_norm_stderr\": 0.007308424386792208\n\
\ },\n \"harness|hendrycksTest-high_school_macroeconomics|5\": {\n \
\ \"acc\": 0.8179487179487179,\n \"acc_stderr\": 0.0195652367829309,\n \
\ \"acc_norm\": 0.8179487179487179,\n \"acc_norm_stderr\": 0.0195652367829309\n\
\ },\n \"harness|hendrycksTest-high_school_mathematics|5\": {\n \"\
acc\": 0.5111111111111111,\n \"acc_stderr\": 0.030478009819615823,\n \
\ \"acc_norm\": 0.5111111111111111,\n \"acc_norm_stderr\": 0.030478009819615823\n\
\ },\n \"harness|hendrycksTest-high_school_microeconomics|5\": {\n \
\ \"acc\": 0.8697478991596639,\n \"acc_stderr\": 0.02186325849485212,\n \
\ \"acc_norm\": 0.8697478991596639,\n \"acc_norm_stderr\": 0.02186325849485212\n\
\ },\n \"harness|hendrycksTest-high_school_physics|5\": {\n \"acc\"\
: 0.5231788079470199,\n \"acc_stderr\": 0.04078093859163086,\n \"\
acc_norm\": 0.5231788079470199,\n \"acc_norm_stderr\": 0.04078093859163086\n\
\ },\n \"harness|hendrycksTest-high_school_psychology|5\": {\n \"acc\"\
: 0.9247706422018349,\n \"acc_stderr\": 0.011308662537571762,\n \"\
acc_norm\": 0.9247706422018349,\n \"acc_norm_stderr\": 0.011308662537571762\n\
\ },\n \"harness|hendrycksTest-high_school_statistics|5\": {\n \"acc\"\
: 0.7175925925925926,\n \"acc_stderr\": 0.03070137211151092,\n \"\
acc_norm\": 0.7175925925925926,\n \"acc_norm_stderr\": 0.03070137211151092\n\
\ },\n \"harness|hendrycksTest-high_school_us_history|5\": {\n \"acc\"\
: 0.9117647058823529,\n \"acc_stderr\": 0.01990739979131694,\n \"\
acc_norm\": 0.9117647058823529,\n \"acc_norm_stderr\": 0.01990739979131694\n\
\ },\n \"harness|hendrycksTest-high_school_world_history|5\": {\n \"\
acc\": 0.9156118143459916,\n \"acc_stderr\": 0.01809424711647332,\n \
\ \"acc_norm\": 0.9156118143459916,\n \"acc_norm_stderr\": 0.01809424711647332\n\
\ },\n \"harness|hendrycksTest-human_aging|5\": {\n \"acc\": 0.8116591928251121,\n\
\ \"acc_stderr\": 0.02624113299640725,\n \"acc_norm\": 0.8116591928251121,\n\
\ \"acc_norm_stderr\": 0.02624113299640725\n },\n \"harness|hendrycksTest-human_sexuality|5\"\
: {\n \"acc\": 0.8625954198473282,\n \"acc_stderr\": 0.030194823996804475,\n\
\ \"acc_norm\": 0.8625954198473282,\n \"acc_norm_stderr\": 0.030194823996804475\n\
\ },\n \"harness|hendrycksTest-international_law|5\": {\n \"acc\":\
\ 0.8512396694214877,\n \"acc_stderr\": 0.03248470083807194,\n \"\
acc_norm\": 0.8512396694214877,\n \"acc_norm_stderr\": 0.03248470083807194\n\
\ },\n \"harness|hendrycksTest-jurisprudence|5\": {\n \"acc\": 0.8518518518518519,\n\
\ \"acc_stderr\": 0.03434300243630999,\n \"acc_norm\": 0.8518518518518519,\n\
\ \"acc_norm_stderr\": 0.03434300243630999\n },\n \"harness|hendrycksTest-logical_fallacies|5\"\
: {\n \"acc\": 0.852760736196319,\n \"acc_stderr\": 0.027839915278339653,\n\
\ \"acc_norm\": 0.852760736196319,\n \"acc_norm_stderr\": 0.027839915278339653\n\
\ },\n \"harness|hendrycksTest-machine_learning|5\": {\n \"acc\": 0.5892857142857143,\n\
\ \"acc_stderr\": 0.04669510663875191,\n \"acc_norm\": 0.5892857142857143,\n\
\ \"acc_norm_stderr\": 0.04669510663875191\n },\n \"harness|hendrycksTest-management|5\"\
: {\n \"acc\": 0.8737864077669902,\n \"acc_stderr\": 0.03288180278808628,\n\
\ \"acc_norm\": 0.8737864077669902,\n \"acc_norm_stderr\": 0.03288180278808628\n\
\ },\n \"harness|hendrycksTest-marketing|5\": {\n \"acc\": 0.9487179487179487,\n\
\ \"acc_stderr\": 0.014450181176872735,\n \"acc_norm\": 0.9487179487179487,\n\
\ \"acc_norm_stderr\": 0.014450181176872735\n },\n \"harness|hendrycksTest-medical_genetics|5\"\
: {\n \"acc\": 0.85,\n \"acc_stderr\": 0.03588702812826372,\n \
\ \"acc_norm\": 0.85,\n \"acc_norm_stderr\": 0.03588702812826372\n \
\ },\n \"harness|hendrycksTest-miscellaneous|5\": {\n \"acc\": 0.9169859514687101,\n\
\ \"acc_stderr\": 0.009866287394639541,\n \"acc_norm\": 0.9169859514687101,\n\
\ \"acc_norm_stderr\": 0.009866287394639541\n },\n \"harness|hendrycksTest-moral_disputes|5\"\
: {\n \"acc\": 0.8352601156069365,\n \"acc_stderr\": 0.019971040982442272,\n\
\ \"acc_norm\": 0.8352601156069365,\n \"acc_norm_stderr\": 0.019971040982442272\n\
\ },\n \"harness|hendrycksTest-moral_scenarios|5\": {\n \"acc\": 0.7262569832402235,\n\
\ \"acc_stderr\": 0.01491241309637243,\n \"acc_norm\": 0.7262569832402235,\n\
\ \"acc_norm_stderr\": 0.01491241309637243\n },\n \"harness|hendrycksTest-nutrition|5\"\
: {\n \"acc\": 0.8431372549019608,\n \"acc_stderr\": 0.02082375883758091,\n\
\ \"acc_norm\": 0.8431372549019608,\n \"acc_norm_stderr\": 0.02082375883758091\n\
\ },\n \"harness|hendrycksTest-philosophy|5\": {\n \"acc\": 0.8231511254019293,\n\
\ \"acc_stderr\": 0.021670058885510792,\n \"acc_norm\": 0.8231511254019293,\n\
\ \"acc_norm_stderr\": 0.021670058885510792\n },\n \"harness|hendrycksTest-prehistory|5\"\
: {\n \"acc\": 0.8580246913580247,\n \"acc_stderr\": 0.019420260109438287,\n\
\ \"acc_norm\": 0.8580246913580247,\n \"acc_norm_stderr\": 0.019420260109438287\n\
\ },\n \"harness|hendrycksTest-professional_accounting|5\": {\n \"\
acc\": 0.6134751773049646,\n \"acc_stderr\": 0.029049190342543465,\n \
\ \"acc_norm\": 0.6134751773049646,\n \"acc_norm_stderr\": 0.029049190342543465\n\
\ },\n \"harness|hendrycksTest-professional_law|5\": {\n \"acc\": 0.6023468057366362,\n\
\ \"acc_stderr\": 0.012499840347460643,\n \"acc_norm\": 0.6023468057366362,\n\
\ \"acc_norm_stderr\": 0.012499840347460643\n },\n \"harness|hendrycksTest-professional_medicine|5\"\
: {\n \"acc\": 0.8161764705882353,\n \"acc_stderr\": 0.023529242185193106,\n\
\ \"acc_norm\": 0.8161764705882353,\n \"acc_norm_stderr\": 0.023529242185193106\n\
\ },\n \"harness|hendrycksTest-professional_psychology|5\": {\n \"\
acc\": 0.815359477124183,\n \"acc_stderr\": 0.01569702924075778,\n \
\ \"acc_norm\": 0.815359477124183,\n \"acc_norm_stderr\": 0.01569702924075778\n\
\ },\n \"harness|hendrycksTest-public_relations|5\": {\n \"acc\": 0.7727272727272727,\n\
\ \"acc_stderr\": 0.04013964554072775,\n \"acc_norm\": 0.7727272727272727,\n\
\ \"acc_norm_stderr\": 0.04013964554072775\n },\n \"harness|hendrycksTest-security_studies|5\"\
: {\n \"acc\": 0.8244897959183674,\n \"acc_stderr\": 0.02435280072297001,\n\
\ \"acc_norm\": 0.8244897959183674,\n \"acc_norm_stderr\": 0.02435280072297001\n\
\ },\n \"harness|hendrycksTest-sociology|5\": {\n \"acc\": 0.8955223880597015,\n\
\ \"acc_stderr\": 0.021628920516700643,\n \"acc_norm\": 0.8955223880597015,\n\
\ \"acc_norm_stderr\": 0.021628920516700643\n },\n \"harness|hendrycksTest-us_foreign_policy|5\"\
: {\n \"acc\": 0.95,\n \"acc_stderr\": 0.021904291355759026,\n \
\ \"acc_norm\": 0.95,\n \"acc_norm_stderr\": 0.021904291355759026\n \
\ },\n \"harness|hendrycksTest-virology|5\": {\n \"acc\": 0.5843373493975904,\n\
\ \"acc_stderr\": 0.03836722176598053,\n \"acc_norm\": 0.5843373493975904,\n\
\ \"acc_norm_stderr\": 0.03836722176598053\n },\n \"harness|hendrycksTest-world_religions|5\"\
: {\n \"acc\": 0.8947368421052632,\n \"acc_stderr\": 0.02353755765789256,\n\
\ \"acc_norm\": 0.8947368421052632,\n \"acc_norm_stderr\": 0.02353755765789256\n\
\ },\n \"harness|truthfulqa:mc|0\": {\n \"mc1\": 0.4749082007343941,\n\
\ \"mc1_stderr\": 0.017481446804104003,\n \"mc2\": 0.6489991000331015,\n\
\ \"mc2_stderr\": 0.015361203699885669\n },\n \"harness|winogrande|5\"\
: {\n \"acc\": 0.8161010260457774,\n \"acc_stderr\": 0.010887916013305894\n\
\ },\n \"harness|gsm8k|5\": {\n \"acc\": 0.38514025777103866,\n \
\ \"acc_stderr\": 0.013404165536474305\n }\n}\n```"
repo_url: https://huggingface.co/abacusai/Smaug-2-72B
leaderboard_url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard
point_of_contact: clementine@hf.co
configs:
- config_name: harness_arc_challenge_25
data_files:
- split: 2024_03_30T01_31_21.040468
path:
- '**/details_harness|arc:challenge|25_2024-03-30T01-31-21.040468.parquet'
- split: latest
path:
- '**/details_harness|arc:challenge|25_2024-03-30T01-31-21.040468.parquet'
- config_name: harness_gsm8k_5
data_files:
- split: 2024_03_30T01_31_21.040468
path:
- '**/details_harness|gsm8k|5_2024-03-30T01-31-21.040468.parquet'
- split: latest
path:
- '**/details_harness|gsm8k|5_2024-03-30T01-31-21.040468.parquet'
- config_name: harness_hellaswag_10
data_files:
- split: 2024_03_30T01_31_21.040468
path:
- '**/details_harness|hellaswag|10_2024-03-30T01-31-21.040468.parquet'
- split: latest
path:
- '**/details_harness|hellaswag|10_2024-03-30T01-31-21.040468.parquet'
- config_name: harness_hendrycksTest_5
data_files:
- split: 2024_03_30T01_31_21.040468
path:
- '**/details_harness|hendrycksTest-abstract_algebra|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-anatomy|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-astronomy|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-business_ethics|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-clinical_knowledge|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-college_biology|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-college_chemistry|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-college_computer_science|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-college_mathematics|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-college_medicine|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-college_physics|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-computer_security|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-conceptual_physics|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-econometrics|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-electrical_engineering|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-elementary_mathematics|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-formal_logic|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-global_facts|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-high_school_biology|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-high_school_chemistry|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-high_school_computer_science|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-high_school_european_history|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-high_school_geography|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-high_school_government_and_politics|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-high_school_macroeconomics|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-high_school_mathematics|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-high_school_microeconomics|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-high_school_physics|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-high_school_psychology|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-high_school_statistics|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-high_school_us_history|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-high_school_world_history|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-human_aging|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-human_sexuality|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-international_law|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-jurisprudence|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-logical_fallacies|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-machine_learning|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-management|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-marketing|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-medical_genetics|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-miscellaneous|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-moral_disputes|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-moral_scenarios|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-nutrition|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-philosophy|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-prehistory|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-professional_accounting|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-professional_law|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-professional_medicine|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-professional_psychology|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-public_relations|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-security_studies|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-sociology|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-us_foreign_policy|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-virology|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-world_religions|5_2024-03-30T01-31-21.040468.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-abstract_algebra|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-anatomy|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-astronomy|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-business_ethics|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-clinical_knowledge|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-college_biology|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-college_chemistry|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-college_computer_science|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-college_mathematics|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-college_medicine|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-college_physics|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-computer_security|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-conceptual_physics|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-econometrics|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-electrical_engineering|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-elementary_mathematics|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-formal_logic|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-global_facts|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-high_school_biology|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-high_school_chemistry|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-high_school_computer_science|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-high_school_european_history|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-high_school_geography|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-high_school_government_and_politics|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-high_school_macroeconomics|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-high_school_mathematics|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-high_school_microeconomics|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-high_school_physics|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-high_school_psychology|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-high_school_statistics|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-high_school_us_history|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-high_school_world_history|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-human_aging|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-human_sexuality|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-international_law|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-jurisprudence|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-logical_fallacies|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-machine_learning|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-management|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-marketing|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-medical_genetics|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-miscellaneous|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-moral_disputes|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-moral_scenarios|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-nutrition|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-philosophy|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-prehistory|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-professional_accounting|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-professional_law|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-professional_medicine|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-professional_psychology|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-public_relations|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-security_studies|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-sociology|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-us_foreign_policy|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-virology|5_2024-03-30T01-31-21.040468.parquet'
- '**/details_harness|hendrycksTest-world_religions|5_2024-03-30T01-31-21.040468.parquet'
- config_name: harness_hendrycksTest_abstract_algebra_5
data_files:
- split: 2024_03_30T01_31_21.040468
path:
- '**/details_harness|hendrycksTest-abstract_algebra|5_2024-03-30T01-31-21.040468.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-abstract_algebra|5_2024-03-30T01-31-21.040468.parquet'
- config_name: harness_hendrycksTest_anatomy_5
data_files:
- split: 2024_03_30T01_31_21.040468
path:
- '**/details_harness|hendrycksTest-anatomy|5_2024-03-30T01-31-21.040468.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-anatomy|5_2024-03-30T01-31-21.040468.parquet'
- config_name: harness_hendrycksTest_astronomy_5
data_files:
- split: 2024_03_30T01_31_21.040468
path:
- '**/details_harness|hendrycksTest-astronomy|5_2024-03-30T01-31-21.040468.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-astronomy|5_2024-03-30T01-31-21.040468.parquet'
- config_name: harness_hendrycksTest_business_ethics_5
data_files:
- split: 2024_03_30T01_31_21.040468
path:
- '**/details_harness|hendrycksTest-business_ethics|5_2024-03-30T01-31-21.040468.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-business_ethics|5_2024-03-30T01-31-21.040468.parquet'
- config_name: harness_hendrycksTest_clinical_knowledge_5
data_files:
- split: 2024_03_30T01_31_21.040468
path:
- '**/details_harness|hendrycksTest-clinical_knowledge|5_2024-03-30T01-31-21.040468.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-clinical_knowledge|5_2024-03-30T01-31-21.040468.parquet'
- config_name: harness_hendrycksTest_college_biology_5
data_files:
- split: 2024_03_30T01_31_21.040468
path:
- '**/details_harness|hendrycksTest-college_biology|5_2024-03-30T01-31-21.040468.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-college_biology|5_2024-03-30T01-31-21.040468.parquet'
- config_name: harness_hendrycksTest_college_chemistry_5
data_files:
- split: 2024_03_30T01_31_21.040468
path:
- '**/details_harness|hendrycksTest-college_chemistry|5_2024-03-30T01-31-21.040468.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-college_chemistry|5_2024-03-30T01-31-21.040468.parquet'
- config_name: harness_hendrycksTest_college_computer_science_5
data_files:
- split: 2024_03_30T01_31_21.040468
path:
- '**/details_harness|hendrycksTest-college_computer_science|5_2024-03-30T01-31-21.040468.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-college_computer_science|5_2024-03-30T01-31-21.040468.parquet'
- config_name: harness_hendrycksTest_college_mathematics_5
data_files:
- split: 2024_03_30T01_31_21.040468
path:
- '**/details_harness|hendrycksTest-college_mathematics|5_2024-03-30T01-31-21.040468.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-college_mathematics|5_2024-03-30T01-31-21.040468.parquet'
- config_name: harness_hendrycksTest_college_medicine_5
data_files:
- split: 2024_03_30T01_31_21.040468
path:
- '**/details_harness|hendrycksTest-college_medicine|5_2024-03-30T01-31-21.040468.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-college_medicine|5_2024-03-30T01-31-21.040468.parquet'
- config_name: harness_hendrycksTest_college_physics_5
data_files:
- split: 2024_03_30T01_31_21.040468
path:
- '**/details_harness|hendrycksTest-college_physics|5_2024-03-30T01-31-21.040468.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-college_physics|5_2024-03-30T01-31-21.040468.parquet'
- config_name: harness_hendrycksTest_computer_security_5
data_files:
- split: 2024_03_30T01_31_21.040468
path:
- '**/details_harness|hendrycksTest-computer_security|5_2024-03-30T01-31-21.040468.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-computer_security|5_2024-03-30T01-31-21.040468.parquet'
- config_name: harness_hendrycksTest_conceptual_physics_5
data_files:
- split: 2024_03_30T01_31_21.040468
path:
- '**/details_harness|hendrycksTest-conceptual_physics|5_2024-03-30T01-31-21.040468.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-conceptual_physics|5_2024-03-30T01-31-21.040468.parquet'
- config_name: harness_hendrycksTest_econometrics_5
data_files:
- split: 2024_03_30T01_31_21.040468
path:
- '**/details_harness|hendrycksTest-econometrics|5_2024-03-30T01-31-21.040468.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-econometrics|5_2024-03-30T01-31-21.040468.parquet'
- config_name: harness_hendrycksTest_electrical_engineering_5
data_files:
- split: 2024_03_30T01_31_21.040468
path:
- '**/details_harness|hendrycksTest-electrical_engineering|5_2024-03-30T01-31-21.040468.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-electrical_engineering|5_2024-03-30T01-31-21.040468.parquet'
- config_name: harness_hendrycksTest_elementary_mathematics_5
data_files:
- split: 2024_03_30T01_31_21.040468
path:
- '**/details_harness|hendrycksTest-elementary_mathematics|5_2024-03-30T01-31-21.040468.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-elementary_mathematics|5_2024-03-30T01-31-21.040468.parquet'
- config_name: harness_hendrycksTest_formal_logic_5
data_files:
- split: 2024_03_30T01_31_21.040468
path:
- '**/details_harness|hendrycksTest-formal_logic|5_2024-03-30T01-31-21.040468.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-formal_logic|5_2024-03-30T01-31-21.040468.parquet'
- config_name: harness_hendrycksTest_global_facts_5
data_files:
- split: 2024_03_30T01_31_21.040468
path:
- '**/details_harness|hendrycksTest-global_facts|5_2024-03-30T01-31-21.040468.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-global_facts|5_2024-03-30T01-31-21.040468.parquet'
- config_name: harness_hendrycksTest_high_school_biology_5
data_files:
- split: 2024_03_30T01_31_21.040468
path:
- '**/details_harness|hendrycksTest-high_school_biology|5_2024-03-30T01-31-21.040468.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-high_school_biology|5_2024-03-30T01-31-21.040468.parquet'
- config_name: harness_hendrycksTest_high_school_chemistry_5
data_files:
- split: 2024_03_30T01_31_21.040468
path:
- '**/details_harness|hendrycksTest-high_school_chemistry|5_2024-03-30T01-31-21.040468.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-high_school_chemistry|5_2024-03-30T01-31-21.040468.parquet'
- config_name: harness_hendrycksTest_high_school_computer_science_5
data_files:
- split: 2024_03_30T01_31_21.040468
path:
- '**/details_harness|hendrycksTest-high_school_computer_science|5_2024-03-30T01-31-21.040468.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-high_school_computer_science|5_2024-03-30T01-31-21.040468.parquet'
- config_name: harness_hendrycksTest_high_school_european_history_5
data_files:
- split: 2024_03_30T01_31_21.040468
path:
- '**/details_harness|hendrycksTest-high_school_european_history|5_2024-03-30T01-31-21.040468.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-high_school_european_history|5_2024-03-30T01-31-21.040468.parquet'
- config_name: harness_hendrycksTest_high_school_geography_5
data_files:
- split: 2024_03_30T01_31_21.040468
path:
- '**/details_harness|hendrycksTest-high_school_geography|5_2024-03-30T01-31-21.040468.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-high_school_geography|5_2024-03-30T01-31-21.040468.parquet'
- config_name: harness_hendrycksTest_high_school_government_and_politics_5
data_files:
- split: 2024_03_30T01_31_21.040468
path:
- '**/details_harness|hendrycksTest-high_school_government_and_politics|5_2024-03-30T01-31-21.040468.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-high_school_government_and_politics|5_2024-03-30T01-31-21.040468.parquet'
- config_name: harness_hendrycksTest_high_school_macroeconomics_5
data_files:
- split: 2024_03_30T01_31_21.040468
path:
- '**/details_harness|hendrycksTest-high_school_macroeconomics|5_2024-03-30T01-31-21.040468.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-high_school_macroeconomics|5_2024-03-30T01-31-21.040468.parquet'
- config_name: harness_hendrycksTest_high_school_mathematics_5
data_files:
- split: 2024_03_30T01_31_21.040468
path:
- '**/details_harness|hendrycksTest-high_school_mathematics|5_2024-03-30T01-31-21.040468.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-high_school_mathematics|5_2024-03-30T01-31-21.040468.parquet'
- config_name: harness_hendrycksTest_high_school_microeconomics_5
data_files:
- split: 2024_03_30T01_31_21.040468
path:
- '**/details_harness|hendrycksTest-high_school_microeconomics|5_2024-03-30T01-31-21.040468.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-high_school_microeconomics|5_2024-03-30T01-31-21.040468.parquet'
- config_name: harness_hendrycksTest_high_school_physics_5
data_files:
- split: 2024_03_30T01_31_21.040468
path:
- '**/details_harness|hendrycksTest-high_school_physics|5_2024-03-30T01-31-21.040468.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-high_school_physics|5_2024-03-30T01-31-21.040468.parquet'
- config_name: harness_hendrycksTest_high_school_psychology_5
data_files:
- split: 2024_03_30T01_31_21.040468
path:
- '**/details_harness|hendrycksTest-high_school_psychology|5_2024-03-30T01-31-21.040468.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-high_school_psychology|5_2024-03-30T01-31-21.040468.parquet'
- config_name: harness_hendrycksTest_high_school_statistics_5
data_files:
- split: 2024_03_30T01_31_21.040468
path:
- '**/details_harness|hendrycksTest-high_school_statistics|5_2024-03-30T01-31-21.040468.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-high_school_statistics|5_2024-03-30T01-31-21.040468.parquet'
- config_name: harness_hendrycksTest_high_school_us_history_5
data_files:
- split: 2024_03_30T01_31_21.040468
path:
- '**/details_harness|hendrycksTest-high_school_us_history|5_2024-03-30T01-31-21.040468.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-high_school_us_history|5_2024-03-30T01-31-21.040468.parquet'
- config_name: harness_hendrycksTest_high_school_world_history_5
data_files:
- split: 2024_03_30T01_31_21.040468
path:
- '**/details_harness|hendrycksTest-high_school_world_history|5_2024-03-30T01-31-21.040468.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-high_school_world_history|5_2024-03-30T01-31-21.040468.parquet'
- config_name: harness_hendrycksTest_human_aging_5
data_files:
- split: 2024_03_30T01_31_21.040468
path:
- '**/details_harness|hendrycksTest-human_aging|5_2024-03-30T01-31-21.040468.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-human_aging|5_2024-03-30T01-31-21.040468.parquet'
- config_name: harness_hendrycksTest_human_sexuality_5
data_files:
- split: 2024_03_30T01_31_21.040468
path:
- '**/details_harness|hendrycksTest-human_sexuality|5_2024-03-30T01-31-21.040468.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-human_sexuality|5_2024-03-30T01-31-21.040468.parquet'
- config_name: harness_hendrycksTest_international_law_5
data_files:
- split: 2024_03_30T01_31_21.040468
path:
- '**/details_harness|hendrycksTest-international_law|5_2024-03-30T01-31-21.040468.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-international_law|5_2024-03-30T01-31-21.040468.parquet'
- config_name: harness_hendrycksTest_jurisprudence_5
data_files:
- split: 2024_03_30T01_31_21.040468
path:
- '**/details_harness|hendrycksTest-jurisprudence|5_2024-03-30T01-31-21.040468.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-jurisprudence|5_2024-03-30T01-31-21.040468.parquet'
- config_name: harness_hendrycksTest_logical_fallacies_5
data_files:
- split: 2024_03_30T01_31_21.040468
path:
- '**/details_harness|hendrycksTest-logical_fallacies|5_2024-03-30T01-31-21.040468.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-logical_fallacies|5_2024-03-30T01-31-21.040468.parquet'
- config_name: harness_hendrycksTest_machine_learning_5
data_files:
- split: 2024_03_30T01_31_21.040468
path:
- '**/details_harness|hendrycksTest-machine_learning|5_2024-03-30T01-31-21.040468.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-machine_learning|5_2024-03-30T01-31-21.040468.parquet'
- config_name: harness_hendrycksTest_management_5
data_files:
- split: 2024_03_30T01_31_21.040468
path:
- '**/details_harness|hendrycksTest-management|5_2024-03-30T01-31-21.040468.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-management|5_2024-03-30T01-31-21.040468.parquet'
- config_name: harness_hendrycksTest_marketing_5
data_files:
- split: 2024_03_30T01_31_21.040468
path:
- '**/details_harness|hendrycksTest-marketing|5_2024-03-30T01-31-21.040468.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-marketing|5_2024-03-30T01-31-21.040468.parquet'
- config_name: harness_hendrycksTest_medical_genetics_5
data_files:
- split: 2024_03_30T01_31_21.040468
path:
- '**/details_harness|hendrycksTest-medical_genetics|5_2024-03-30T01-31-21.040468.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-medical_genetics|5_2024-03-30T01-31-21.040468.parquet'
- config_name: harness_hendrycksTest_miscellaneous_5
data_files:
- split: 2024_03_30T01_31_21.040468
path:
- '**/details_harness|hendrycksTest-miscellaneous|5_2024-03-30T01-31-21.040468.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-miscellaneous|5_2024-03-30T01-31-21.040468.parquet'
- config_name: harness_hendrycksTest_moral_disputes_5
data_files:
- split: 2024_03_30T01_31_21.040468
path:
- '**/details_harness|hendrycksTest-moral_disputes|5_2024-03-30T01-31-21.040468.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-moral_disputes|5_2024-03-30T01-31-21.040468.parquet'
- config_name: harness_hendrycksTest_moral_scenarios_5
data_files:
- split: 2024_03_30T01_31_21.040468
path:
- '**/details_harness|hendrycksTest-moral_scenarios|5_2024-03-30T01-31-21.040468.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-moral_scenarios|5_2024-03-30T01-31-21.040468.parquet'
- config_name: harness_hendrycksTest_nutrition_5
data_files:
- split: 2024_03_30T01_31_21.040468
path:
- '**/details_harness|hendrycksTest-nutrition|5_2024-03-30T01-31-21.040468.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-nutrition|5_2024-03-30T01-31-21.040468.parquet'
- config_name: harness_hendrycksTest_philosophy_5
data_files:
- split: 2024_03_30T01_31_21.040468
path:
- '**/details_harness|hendrycksTest-philosophy|5_2024-03-30T01-31-21.040468.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-philosophy|5_2024-03-30T01-31-21.040468.parquet'
- config_name: harness_hendrycksTest_prehistory_5
data_files:
- split: 2024_03_30T01_31_21.040468
path:
- '**/details_harness|hendrycksTest-prehistory|5_2024-03-30T01-31-21.040468.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-prehistory|5_2024-03-30T01-31-21.040468.parquet'
- config_name: harness_hendrycksTest_professional_accounting_5
data_files:
- split: 2024_03_30T01_31_21.040468
path:
- '**/details_harness|hendrycksTest-professional_accounting|5_2024-03-30T01-31-21.040468.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-professional_accounting|5_2024-03-30T01-31-21.040468.parquet'
- config_name: harness_hendrycksTest_professional_law_5
data_files:
- split: 2024_03_30T01_31_21.040468
path:
- '**/details_harness|hendrycksTest-professional_law|5_2024-03-30T01-31-21.040468.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-professional_law|5_2024-03-30T01-31-21.040468.parquet'
- config_name: harness_hendrycksTest_professional_medicine_5
data_files:
- split: 2024_03_30T01_31_21.040468
path:
- '**/details_harness|hendrycksTest-professional_medicine|5_2024-03-30T01-31-21.040468.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-professional_medicine|5_2024-03-30T01-31-21.040468.parquet'
- config_name: harness_hendrycksTest_professional_psychology_5
data_files:
- split: 2024_03_30T01_31_21.040468
path:
- '**/details_harness|hendrycksTest-professional_psychology|5_2024-03-30T01-31-21.040468.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-professional_psychology|5_2024-03-30T01-31-21.040468.parquet'
- config_name: harness_hendrycksTest_public_relations_5
data_files:
- split: 2024_03_30T01_31_21.040468
path:
- '**/details_harness|hendrycksTest-public_relations|5_2024-03-30T01-31-21.040468.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-public_relations|5_2024-03-30T01-31-21.040468.parquet'
- config_name: harness_hendrycksTest_security_studies_5
data_files:
- split: 2024_03_30T01_31_21.040468
path:
- '**/details_harness|hendrycksTest-security_studies|5_2024-03-30T01-31-21.040468.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-security_studies|5_2024-03-30T01-31-21.040468.parquet'
- config_name: harness_hendrycksTest_sociology_5
data_files:
- split: 2024_03_30T01_31_21.040468
path:
- '**/details_harness|hendrycksTest-sociology|5_2024-03-30T01-31-21.040468.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-sociology|5_2024-03-30T01-31-21.040468.parquet'
- config_name: harness_hendrycksTest_us_foreign_policy_5
data_files:
- split: 2024_03_30T01_31_21.040468
path:
- '**/details_harness|hendrycksTest-us_foreign_policy|5_2024-03-30T01-31-21.040468.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-us_foreign_policy|5_2024-03-30T01-31-21.040468.parquet'
- config_name: harness_hendrycksTest_virology_5
data_files:
- split: 2024_03_30T01_31_21.040468
path:
- '**/details_harness|hendrycksTest-virology|5_2024-03-30T01-31-21.040468.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-virology|5_2024-03-30T01-31-21.040468.parquet'
- config_name: harness_hendrycksTest_world_religions_5
data_files:
- split: 2024_03_30T01_31_21.040468
path:
- '**/details_harness|hendrycksTest-world_religions|5_2024-03-30T01-31-21.040468.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-world_religions|5_2024-03-30T01-31-21.040468.parquet'
- config_name: harness_truthfulqa_mc_0
data_files:
- split: 2024_03_30T01_31_21.040468
path:
- '**/details_harness|truthfulqa:mc|0_2024-03-30T01-31-21.040468.parquet'
- split: latest
path:
- '**/details_harness|truthfulqa:mc|0_2024-03-30T01-31-21.040468.parquet'
- config_name: harness_winogrande_5
data_files:
- split: 2024_03_30T01_31_21.040468
path:
- '**/details_harness|winogrande|5_2024-03-30T01-31-21.040468.parquet'
- split: latest
path:
- '**/details_harness|winogrande|5_2024-03-30T01-31-21.040468.parquet'
- config_name: results
data_files:
- split: 2024_03_30T01_31_21.040468
path:
- results_2024-03-30T01-31-21.040468.parquet
- split: latest
path:
- results_2024-03-30T01-31-21.040468.parquet
---
# Dataset Card for Evaluation run of abacusai/Smaug-2-72B
<!-- Provide a quick summary of the dataset. -->
Dataset automatically created during the evaluation run of model [abacusai/Smaug-2-72B](https://huggingface.co/abacusai/Smaug-2-72B) on the [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard).
The dataset is composed of 63 configuration, each one coresponding to one of the evaluated task.
The dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is always pointing to the latest results.
An additional configuration "results" store all the aggregated results of the run (and is used to compute and display the aggregated metrics on the [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)).
To load the details from a run, you can for instance do the following:
```python
from datasets import load_dataset
data = load_dataset("open-llm-leaderboard/details_abacusai__Smaug-2-72B",
"harness_winogrande_5",
split="train")
```
## Latest results
These are the [latest results from run 2024-03-30T01:31:21.040468](https://huggingface.co/datasets/open-llm-leaderboard/details_abacusai__Smaug-2-72B/blob/main/results_2024-03-30T01-31-21.040468.json)(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the "latest" split for each eval):
```python
{
"all": {
"acc": 0.767796907393265,
"acc_stderr": 0.027982043283656534,
"acc_norm": 0.7771325485017166,
"acc_norm_stderr": 0.02849243108304867,
"mc1": 0.4749082007343941,
"mc1_stderr": 0.017481446804104003,
"mc2": 0.6489991000331015,
"mc2_stderr": 0.015361203699885669
},
"harness|arc:challenge|25": {
"acc": 0.6467576791808873,
"acc_stderr": 0.013967822714840055,
"acc_norm": 0.6791808873720137,
"acc_norm_stderr": 0.013640943091946528
},
"harness|hellaswag|10": {
"acc": 0.6796454889464251,
"acc_stderr": 0.004656591678606762,
"acc_norm": 0.8636725751842262,
"acc_norm_stderr": 0.0034243464481037195
},
"harness|hendrycksTest-abstract_algebra|5": {
"acc": 0.52,
"acc_stderr": 0.050211673156867795,
"acc_norm": 0.52,
"acc_norm_stderr": 0.050211673156867795
},
"harness|hendrycksTest-anatomy|5": {
"acc": 0.7407407407407407,
"acc_stderr": 0.03785714465066653,
"acc_norm": 0.7407407407407407,
"acc_norm_stderr": 0.03785714465066653
},
"harness|hendrycksTest-astronomy|5": {
"acc": 0.875,
"acc_stderr": 0.026913523521537846,
"acc_norm": 0.875,
"acc_norm_stderr": 0.026913523521537846
},
"harness|hendrycksTest-business_ethics|5": {
"acc": 0.79,
"acc_stderr": 0.040936018074033256,
"acc_norm": 0.79,
"acc_norm_stderr": 0.040936018074033256
},
"harness|hendrycksTest-clinical_knowledge|5": {
"acc": 0.8037735849056604,
"acc_stderr": 0.02444238813110083,
"acc_norm": 0.8037735849056604,
"acc_norm_stderr": 0.02444238813110083
},
"harness|hendrycksTest-college_biology|5": {
"acc": 0.9166666666666666,
"acc_stderr": 0.023112508176051236,
"acc_norm": 0.9166666666666666,
"acc_norm_stderr": 0.023112508176051236
},
"harness|hendrycksTest-college_chemistry|5": {
"acc": 0.59,
"acc_stderr": 0.04943110704237102,
"acc_norm": 0.59,
"acc_norm_stderr": 0.04943110704237102
},
"harness|hendrycksTest-college_computer_science|5": {
"acc": 0.72,
"acc_stderr": 0.04512608598542127,
"acc_norm": 0.72,
"acc_norm_stderr": 0.04512608598542127
},
"harness|hendrycksTest-college_mathematics|5": {
"acc": 0.53,
"acc_stderr": 0.05016135580465919,
"acc_norm": 0.53,
"acc_norm_stderr": 0.05016135580465919
},
"harness|hendrycksTest-college_medicine|5": {
"acc": 0.7456647398843931,
"acc_stderr": 0.0332055644308557,
"acc_norm": 0.7456647398843931,
"acc_norm_stderr": 0.0332055644308557
},
"harness|hendrycksTest-college_physics|5": {
"acc": 0.5882352941176471,
"acc_stderr": 0.04897104952726367,
"acc_norm": 0.5882352941176471,
"acc_norm_stderr": 0.04897104952726367
},
"harness|hendrycksTest-computer_security|5": {
"acc": 0.85,
"acc_stderr": 0.03588702812826371,
"acc_norm": 0.85,
"acc_norm_stderr": 0.03588702812826371
},
"harness|hendrycksTest-conceptual_physics|5": {
"acc": 0.774468085106383,
"acc_stderr": 0.027321078417387536,
"acc_norm": 0.774468085106383,
"acc_norm_stderr": 0.027321078417387536
},
"harness|hendrycksTest-econometrics|5": {
"acc": 0.5701754385964912,
"acc_stderr": 0.04657047260594964,
"acc_norm": 0.5701754385964912,
"acc_norm_stderr": 0.04657047260594964
},
"harness|hendrycksTest-electrical_engineering|5": {
"acc": 0.8,
"acc_stderr": 0.0333333333333333,
"acc_norm": 0.8,
"acc_norm_stderr": 0.0333333333333333
},
"harness|hendrycksTest-elementary_mathematics|5": {
"acc": 0.708994708994709,
"acc_stderr": 0.023393826500484865,
"acc_norm": 0.708994708994709,
"acc_norm_stderr": 0.023393826500484865
},
"harness|hendrycksTest-formal_logic|5": {
"acc": 0.5873015873015873,
"acc_stderr": 0.04403438954768177,
"acc_norm": 0.5873015873015873,
"acc_norm_stderr": 0.04403438954768177
},
"harness|hendrycksTest-global_facts|5": {
"acc": 0.59,
"acc_stderr": 0.04943110704237101,
"acc_norm": 0.59,
"acc_norm_stderr": 0.04943110704237101
},
"harness|hendrycksTest-high_school_biology|5": {
"acc": 0.896774193548387,
"acc_stderr": 0.017308381281034516,
"acc_norm": 0.896774193548387,
"acc_norm_stderr": 0.017308381281034516
},
"harness|hendrycksTest-high_school_chemistry|5": {
"acc": 0.6650246305418719,
"acc_stderr": 0.033208527423483104,
"acc_norm": 0.6650246305418719,
"acc_norm_stderr": 0.033208527423483104
},
"harness|hendrycksTest-high_school_computer_science|5": {
"acc": 0.81,
"acc_stderr": 0.039427724440366234,
"acc_norm": 0.81,
"acc_norm_stderr": 0.039427724440366234
},
"harness|hendrycksTest-high_school_european_history|5": {
"acc": 0.8606060606060606,
"acc_stderr": 0.027045948825865387,
"acc_norm": 0.8606060606060606,
"acc_norm_stderr": 0.027045948825865387
},
"harness|hendrycksTest-high_school_geography|5": {
"acc": 0.9292929292929293,
"acc_stderr": 0.01826310542019949,
"acc_norm": 0.9292929292929293,
"acc_norm_stderr": 0.01826310542019949
},
"harness|hendrycksTest-high_school_government_and_politics|5": {
"acc": 0.9896373056994818,
"acc_stderr": 0.007308424386792208,
"acc_norm": 0.9896373056994818,
"acc_norm_stderr": 0.007308424386792208
},
"harness|hendrycksTest-high_school_macroeconomics|5": {
"acc": 0.8179487179487179,
"acc_stderr": 0.0195652367829309,
"acc_norm": 0.8179487179487179,
"acc_norm_stderr": 0.0195652367829309
},
"harness|hendrycksTest-high_school_mathematics|5": {
"acc": 0.5111111111111111,
"acc_stderr": 0.030478009819615823,
"acc_norm": 0.5111111111111111,
"acc_norm_stderr": 0.030478009819615823
},
"harness|hendrycksTest-high_school_microeconomics|5": {
"acc": 0.8697478991596639,
"acc_stderr": 0.02186325849485212,
"acc_norm": 0.8697478991596639,
"acc_norm_stderr": 0.02186325849485212
},
"harness|hendrycksTest-high_school_physics|5": {
"acc": 0.5231788079470199,
"acc_stderr": 0.04078093859163086,
"acc_norm": 0.5231788079470199,
"acc_norm_stderr": 0.04078093859163086
},
"harness|hendrycksTest-high_school_psychology|5": {
"acc": 0.9247706422018349,
"acc_stderr": 0.011308662537571762,
"acc_norm": 0.9247706422018349,
"acc_norm_stderr": 0.011308662537571762
},
"harness|hendrycksTest-high_school_statistics|5": {
"acc": 0.7175925925925926,
"acc_stderr": 0.03070137211151092,
"acc_norm": 0.7175925925925926,
"acc_norm_stderr": 0.03070137211151092
},
"harness|hendrycksTest-high_school_us_history|5": {
"acc": 0.9117647058823529,
"acc_stderr": 0.01990739979131694,
"acc_norm": 0.9117647058823529,
"acc_norm_stderr": 0.01990739979131694
},
"harness|hendrycksTest-high_school_world_history|5": {
"acc": 0.9156118143459916,
"acc_stderr": 0.01809424711647332,
"acc_norm": 0.9156118143459916,
"acc_norm_stderr": 0.01809424711647332
},
"harness|hendrycksTest-human_aging|5": {
"acc": 0.8116591928251121,
"acc_stderr": 0.02624113299640725,
"acc_norm": 0.8116591928251121,
"acc_norm_stderr": 0.02624113299640725
},
"harness|hendrycksTest-human_sexuality|5": {
"acc": 0.8625954198473282,
"acc_stderr": 0.030194823996804475,
"acc_norm": 0.8625954198473282,
"acc_norm_stderr": 0.030194823996804475
},
"harness|hendrycksTest-international_law|5": {
"acc": 0.8512396694214877,
"acc_stderr": 0.03248470083807194,
"acc_norm": 0.8512396694214877,
"acc_norm_stderr": 0.03248470083807194
},
"harness|hendrycksTest-jurisprudence|5": {
"acc": 0.8518518518518519,
"acc_stderr": 0.03434300243630999,
"acc_norm": 0.8518518518518519,
"acc_norm_stderr": 0.03434300243630999
},
"harness|hendrycksTest-logical_fallacies|5": {
"acc": 0.852760736196319,
"acc_stderr": 0.027839915278339653,
"acc_norm": 0.852760736196319,
"acc_norm_stderr": 0.027839915278339653
},
"harness|hendrycksTest-machine_learning|5": {
"acc": 0.5892857142857143,
"acc_stderr": 0.04669510663875191,
"acc_norm": 0.5892857142857143,
"acc_norm_stderr": 0.04669510663875191
},
"harness|hendrycksTest-management|5": {
"acc": 0.8737864077669902,
"acc_stderr": 0.03288180278808628,
"acc_norm": 0.8737864077669902,
"acc_norm_stderr": 0.03288180278808628
},
"harness|hendrycksTest-marketing|5": {
"acc": 0.9487179487179487,
"acc_stderr": 0.014450181176872735,
"acc_norm": 0.9487179487179487,
"acc_norm_stderr": 0.014450181176872735
},
"harness|hendrycksTest-medical_genetics|5": {
"acc": 0.85,
"acc_stderr": 0.03588702812826372,
"acc_norm": 0.85,
"acc_norm_stderr": 0.03588702812826372
},
"harness|hendrycksTest-miscellaneous|5": {
"acc": 0.9169859514687101,
"acc_stderr": 0.009866287394639541,
"acc_norm": 0.9169859514687101,
"acc_norm_stderr": 0.009866287394639541
},
"harness|hendrycksTest-moral_disputes|5": {
"acc": 0.8352601156069365,
"acc_stderr": 0.019971040982442272,
"acc_norm": 0.8352601156069365,
"acc_norm_stderr": 0.019971040982442272
},
"harness|hendrycksTest-moral_scenarios|5": {
"acc": 0.7262569832402235,
"acc_stderr": 0.01491241309637243,
"acc_norm": 0.7262569832402235,
"acc_norm_stderr": 0.01491241309637243
},
"harness|hendrycksTest-nutrition|5": {
"acc": 0.8431372549019608,
"acc_stderr": 0.02082375883758091,
"acc_norm": 0.8431372549019608,
"acc_norm_stderr": 0.02082375883758091
},
"harness|hendrycksTest-philosophy|5": {
"acc": 0.8231511254019293,
"acc_stderr": 0.021670058885510792,
"acc_norm": 0.8231511254019293,
"acc_norm_stderr": 0.021670058885510792
},
"harness|hendrycksTest-prehistory|5": {
"acc": 0.8580246913580247,
"acc_stderr": 0.019420260109438287,
"acc_norm": 0.8580246913580247,
"acc_norm_stderr": 0.019420260109438287
},
"harness|hendrycksTest-professional_accounting|5": {
"acc": 0.6134751773049646,
"acc_stderr": 0.029049190342543465,
"acc_norm": 0.6134751773049646,
"acc_norm_stderr": 0.029049190342543465
},
"harness|hendrycksTest-professional_law|5": {
"acc": 0.6023468057366362,
"acc_stderr": 0.012499840347460643,
"acc_norm": 0.6023468057366362,
"acc_norm_stderr": 0.012499840347460643
},
"harness|hendrycksTest-professional_medicine|5": {
"acc": 0.8161764705882353,
"acc_stderr": 0.023529242185193106,
"acc_norm": 0.8161764705882353,
"acc_norm_stderr": 0.023529242185193106
},
"harness|hendrycksTest-professional_psychology|5": {
"acc": 0.815359477124183,
"acc_stderr": 0.01569702924075778,
"acc_norm": 0.815359477124183,
"acc_norm_stderr": 0.01569702924075778
},
"harness|hendrycksTest-public_relations|5": {
"acc": 0.7727272727272727,
"acc_stderr": 0.04013964554072775,
"acc_norm": 0.7727272727272727,
"acc_norm_stderr": 0.04013964554072775
},
"harness|hendrycksTest-security_studies|5": {
"acc": 0.8244897959183674,
"acc_stderr": 0.02435280072297001,
"acc_norm": 0.8244897959183674,
"acc_norm_stderr": 0.02435280072297001
},
"harness|hendrycksTest-sociology|5": {
"acc": 0.8955223880597015,
"acc_stderr": 0.021628920516700643,
"acc_norm": 0.8955223880597015,
"acc_norm_stderr": 0.021628920516700643
},
"harness|hendrycksTest-us_foreign_policy|5": {
"acc": 0.95,
"acc_stderr": 0.021904291355759026,
"acc_norm": 0.95,
"acc_norm_stderr": 0.021904291355759026
},
"harness|hendrycksTest-virology|5": {
"acc": 0.5843373493975904,
"acc_stderr": 0.03836722176598053,
"acc_norm": 0.5843373493975904,
"acc_norm_stderr": 0.03836722176598053
},
"harness|hendrycksTest-world_religions|5": {
"acc": 0.8947368421052632,
"acc_stderr": 0.02353755765789256,
"acc_norm": 0.8947368421052632,
"acc_norm_stderr": 0.02353755765789256
},
"harness|truthfulqa:mc|0": {
"mc1": 0.4749082007343941,
"mc1_stderr": 0.017481446804104003,
"mc2": 0.6489991000331015,
"mc2_stderr": 0.015361203699885669
},
"harness|winogrande|5": {
"acc": 0.8161010260457774,
"acc_stderr": 0.010887916013305894
},
"harness|gsm8k|5": {
"acc": 0.38514025777103866,
"acc_stderr": 0.013404165536474305
}
}
```
## Dataset Details
### Dataset Description
<!-- Provide a longer summary of what this dataset is. -->
- **Curated by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
### Dataset Sources [optional]
<!-- Provide the basic links for the dataset. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the dataset is intended to be used. -->
### Direct Use
<!-- This section describes suitable use cases for the dataset. -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the dataset will not work well for. -->
[More Information Needed]
## Dataset Structure
<!-- This section provides a description of the dataset fields, and additional information about the dataset structure such as criteria used to create the splits, relationships between data points, etc. -->
[More Information Needed]
## Dataset Creation
### Curation Rationale
<!-- Motivation for the creation of this dataset. -->
[More Information Needed]
### Source Data
<!-- This section describes the source data (e.g. news text and headlines, social media posts, translated sentences, ...). -->
#### Data Collection and Processing
<!-- This section describes the data collection and processing process such as data selection criteria, filtering and normalization methods, tools and libraries used, etc. -->
[More Information Needed]
#### Who are the source data producers?
<!-- This section describes the people or systems who originally created the data. It should also include self-reported demographic or identity information for the source data creators if this information is available. -->
[More Information Needed]
### Annotations [optional]
<!-- If the dataset contains annotations which are not part of the initial data collection, use this section to describe them. -->
#### Annotation process
<!-- This section describes the annotation process such as annotation tools used in the process, the amount of data annotated, annotation guidelines provided to the annotators, interannotator statistics, annotation validation, etc. -->
[More Information Needed]
#### Who are the annotators?
<!-- This section describes the people or systems who created the annotations. -->
[More Information Needed]
#### Personal and Sensitive Information
<!-- State whether the dataset contains data that might be considered personal, sensitive, or private (e.g., data that reveals addresses, uniquely identifiable names or aliases, racial or ethnic origins, sexual orientations, religious beliefs, political opinions, financial or health data, etc.). If efforts were made to anonymize the data, describe the anonymization process. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users should be made aware of the risks, biases and limitations of the dataset. More information needed for further recommendations.
## Citation [optional]
<!-- If there is a paper or blog post introducing the dataset, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the dataset or dataset card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Dataset Card Authors [optional]
[More Information Needed]
## Dataset Card Contact
[More Information Needed]
提供机构：
open-llm-leaderboard原始信息汇总
数据集概述
数据集摘要
该数据集是在对模型 abacusai/Smaug-2-72B 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 63 个配置组成，每个配置对应一个评估任务。
- 数据集从 1 次运行中创建，每次运行可以在每个配置中找到特定的拆分，拆分名称使用运行的时间戳。
- "train" 拆分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_abacusai__Smaug-2-72B", "harness_winogrande_5", split="train")
最新结果
以下是 2024-03-30T01:31:21.040468 运行的最新结果：
python { "all": { "acc": 0.767796907393265, "acc_stderr": 0.027982043283656534, "acc_norm": 0.7771325485017166, "acc_norm_stderr": 0.02849243108304867, "mc1": 0.4749082007343941, "mc1_stderr": 0.017481446804104003, "mc2": 0.6489991000331015, "mc2_stderr": 0.015361203699885669 }, "harness|arc:challenge|25": { "acc": 0.6467576791808873, "acc_stderr": 0.013967822714840055, "acc_norm": 0.6791808873720137, "acc_norm_stderr": 0.013640943091946528 }, "harness|hellaswag|10": { "acc": 0.6796454889464251, "acc_stderr": 0.004656591678606762, "acc_norm": 0.8636725751842262, "acc_norm_stderr": 0.0034243464481037195 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.52, "acc_stderr": 0.050211673156867795, "acc_norm": 0.52, "acc_norm_stderr": 0.050211673156867795 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.7407407407407407, "acc_stderr": 0.03785714465066653, "acc_norm": 0.7407407407407407, "acc_norm_stderr": 0.03785714465066653 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.875, "acc_stderr": 0.026913523521537846, "acc_norm": 0.875, "acc_norm_stderr": 0.026913523521537846 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.79, "acc_stderr": 0.040936018074033256, "acc_norm": 0.79, "acc_norm_stderr": 0.040936018074033256 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.8037735849056604, "acc_stderr": 0.02444238813110083, "acc_norm": 0.8037735849056604, "acc_norm_stderr": 0.02444238813110083 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.9166666666666666, "acc_stderr": 0.023112508176051236, "acc_norm": 0.9166666666666666, "acc_norm_stderr": 0.023112508176051236 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.59, "acc_stderr": 0.04943110704237102, "acc_norm": 0.59, "acc_norm_stderr": 0.04943110704237102 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.72, "acc_stderr": 0.04512608598542127, "acc_norm": 0.72, "acc_norm_stderr": 0.04512608598542127 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.53, "acc_stderr": 0.05016135580465919, "acc_norm": 0.53, "acc_norm_stderr": 0.05016135580465919 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.7456647398843931, "acc_stderr": 0.0332055644308557, "acc_norm": 0.7456647398843931, "acc_norm_stderr": 0.0332055644308557 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.5882352941176471, "acc_stderr": 0.04897104952726367, "acc_norm": 0.5882352941176471, "acc_norm_stderr": 0.04897104952726367 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.85, "acc_stderr": 0.03588702812826371, "acc_norm": 0.85, "acc_norm_stderr": 0.03588702812826371 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.774468085106383, "acc_stderr": 0.027321078417387536, "acc_norm": 0.774468085106383, "acc_norm_stderr": 0.027321078417387536 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.5701754385964912, "acc_stderr": 0.04657047260594964, "acc_norm": 0.5701754385964912, "acc_norm_stderr": 0.04657047260594964 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.8, "acc_stderr": 0.0333333333333333, "acc_norm": 0.8, "acc_norm_stderr": 0.0333333333333333 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.708994708994709, "acc_stderr": 0.023393826500484865, "acc_norm": 0.708994708994709, "acc_norm_stderr": 0.023393826500484865 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.5873015873015873, "acc_stderr": 0.04403438954768177, "acc_norm": 0.5873015873015873, "acc_norm_stderr": 0.04403438954768177 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.59, "acc_stderr": 0.04943110704237101, "acc_norm": 0.59, "acc_norm_stderr": 0.04943110704237101 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.896774193548387, "acc_stderr": 0.017308381281034516, "acc_norm": 0.896774193548387, "acc_norm_stderr": 0.017308381281034516 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.6650246305418719, "acc_stderr": 0.033208527423483104, "acc_norm": 0.6650246305418719, "acc_norm_stderr": 0.033208527423483104 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.81, "acc_stderr": 0.039427724440366234, "acc_norm": 0.81, "acc_norm_stderr": 0.039427724440366234 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.8606060606060606, "acc_stderr": 0.027045948825865387, "acc_norm": 0.8606060606060606, "acc_norm_stderr": 0.027045948825865387 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.9292929292929293, "acc_stderr": 0.01826310542019949, "acc_norm": 0.9292929292929293, "acc_norm_stderr": 0.01826310542019949 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9896373056994818, "acc_stderr": 0.007308424386792208, "acc_norm": 0.9896373056994818, "acc_norm_stderr": 0.007308424386792208 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.8179487179487179, "acc_stderr": 0.0195652367829309, "acc_norm": 0.8179487179487179, "acc_norm_stderr": 0.0195652367829309 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.5111111111111111, "acc_stderr": 0.030478009819615823, "acc_norm": 0.5111111111111111, "acc_norm_stderr": 0.030478009819615823 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.86974
搜集汇总
数据集介绍
构建方式
在大型语言模型评估领域，Open LLM Leaderboard扮演着至关重要的角色，为模型性能的横向对比提供了标准化平台。该数据集正是为评估abacusai/Smaug-2-72B模型而生，由一次完整的评估运行自动生成。数据集的构建精巧而系统，共包含63个配置，每个配置对应一项独立的评估任务。运行结果以时间戳命名作为特定分割存储在各自配置中，而'train'分割则始终指向最新一次运行的评估结果。此外，一个名为'results'的独立配置专门用于汇聚所有任务的聚合指标，为Leaderboard上综合得分的计算与展示提供数据支撑。这种设计确保了评估历史可追溯，同时保持了最新结果的便捷访问。
特点
该数据集的核心特点体现在其结构化与可追溯性上。它覆盖了涵盖常识推理、科学知识、数学能力、语言理解等多元维度的评估任务，如ARC-Challenge、HellaSwag、GSM8K以及涵盖57个学科的MMLU基准测试。每个任务配置下均存储了详细的模型响应与评分，包括准确率及其标准误差等精细化指标。通过时间戳分割的机制，研究者可以回溯特定历史时刻的模型表现，而'latest'分割则自动同步最新进展。这种架构不仅支持对Smaug-2-72B模型能力的深度剖析，也为追踪模型迭代过程中的性能演化提供了宝贵的数据资源。
使用方法
研究人员可通过Hugging Face的datasets库便捷地加载该数据集。例如，若要获取Winogrande任务的评估细节，只需调用load_dataset函数，指定数据集名称与配置名'harness_winogrande_5'，并选择'train'分割即可。每个配置对应一个Parquet文件，存储了该任务下所有样本的详细评估结果。对于需要分析所有任务聚合性能的场景，可直接访问'results'配置，其中包含了如整体准确率、标准化准确率等综合性指标。这种模块化的设计使得研究者能够灵活地聚焦于特定能力维度的分析，或进行跨任务的综合性能评估，极大便利了模型能力的系统性研究。
背景与挑战
背景概述
随着大语言模型（LLM）规模的急剧膨胀，如何客观、全面地评估其多维度能力成为自然语言处理领域的关键议题。在此背景下，Hugging Face团队于2023年发起了Open LLM Leaderboard项目，旨在通过标准化基准测试为社区提供透明的模型性能对比平台。该数据集记录了abacusai公司开发的Smaug-2-72B模型（参数量达720亿）在2024年3月30日的评测结果，由Clémentine（clementine@hf.co）等研究人员主导构建。核心研究问题在于：在涵盖常识推理（如ARC、HellaSwag）、数学解题（GSM8K）、知识问答（MMLU的57个学科）及反事实推理（TruthfulQA）等63项任务的严苛测试中，Smaug-2-72B能否展现出与参数规模相匹配的卓越性能。该数据集不仅为72B级别模型的能力边界提供了关键实证，更推动了LLM评估范式的标准化进程，成为社区衡量模型进步的重要标尺。
当前挑战
该数据集所反映的挑战具有双重维度。在领域问题层面，当前LLM评测面临的核心困境在于：尽管Smaug-2-72B在MMLU的政府与政治（98.96%）、市场营销（94.87%）等学科表现优异，但在抽象代数（52%）、大学数学（53%）等需要深层推理的任务上准确率显著下滑，揭示了模型在专业逻辑推理与多步计算方面的结构性短板。构建过程中，挑战集中于评测的标准化与可复现性：需协调63个异构任务（如ARC的25样本设置与GSM8K的5样本链式推理），确保不同任务间评分粒度的一致性；同时，评测日志的版本管理（如2024-03-30T01:31:21.040468时间戳分片）要求严格的数据溯源机制，以应对模型迭代中可能出现的结果漂移问题。
常用场景
经典使用场景
在大型语言模型评估领域，Open LLM Leaderboard的评估数据集已成为衡量模型综合能力的黄金标准。该数据集专为Smaug-2-72B模型设计，覆盖了从常识推理到数学解题的63项任务配置，包括ARC-Challenge、HellaSwag、GSM8K等经典基准测试。研究者可通过加载不同配置下的评估结果，系统性地分析模型在知识理解、逻辑推理和语言生成等多维度上的表现，从而精准定位模型的优势与短板。
衍生相关工作
该数据集催生了一系列关于模型评估方法论的重要工作。研究者基于其多任务评估框架，开发出诸如模型能力图谱构建、任务难度自适应校准等技术。此外，该数据集的时序运行记录（如2024年3月30日的评估快照）推动了模型性能退化追踪研究，而其对57个MMLU子领域的详尽记录，则启发了针对特定学科（如法学、医学）的领域化评估基准构建，进一步丰富了语言模型可靠性验证的学术工具箱。
数据集最近研究
最新研究方向
在大语言模型激烈角逐的当下，Smaug-2-72B 模型在 Open LLM Leaderboard 上的评估数据集，为前沿研究提供了关键基准。该数据集涵盖从常识推理（如 HellaSwag、ARC-Challenge）到数学解题（GSM8K）及多学科知识（MMLU）等63项任务，其评测结果直接映射了模型在推理、知识广度与逻辑一致性上的综合能力。当前研究热点聚焦于如何通过细粒度评估揭示模型的潜在短板，例如 GSM8K 上仅38.5%的准确率凸显了复杂数学推理的瓶颈，而 HellaSwag 归一化准确率达86.4%则展现了在常识推断上的优势。这一数据集不仅助力研究者定位模型优化方向，更推动了开源社区对评估标准化与透明化的追求，成为追踪大模型能力演进的重要里程碑。
以上内容由遇见数据集搜集并总结生成
