Skip to content

GitLab

Unverified Commit 4de8a74e authored by Stella Biderman's avatar Stella Biderman Committed by GitHub
Browse files

Merge branch 'master' into json-task

parents 3226ed64 bda68845
Hide whitespace changes
Inline Side-by-side
Showing with 1097 additions and 0 deletions
results/mpt/mpt-7b/mpt-7b_lambada_0-shot.json 0 → 100644
View file @ 4de8a74e
{
"results": {
"lambada_openai": {
"ppl": 3.8685393479651173,
"ppl_stderr": 0.08079962928213236,
"acc": 0.6834853483407723,
"acc_stderr": 0.006479978824925181
},
"lambada_openai_cloze": {
"ppl": 26.557641771948866,
"ppl_stderr": 0.7040059319391023,
"acc": 0.3964680768484378,
"acc_stderr": 0.006815007030417622
},
"lambada_openai_mt_de": {
"ppl": 70.11746381055114,
"ppl_stderr": 4.044349022196945,
"acc": 0.33766737822627596,
"acc_stderr": 0.006588623616680426
},
"lambada_openai_mt_en": {
"ppl": 3.8685393479651173,
"ppl_stderr": 0.08079962928213236,
"acc": 0.6834853483407723,
"acc_stderr": 0.006479978824925181
},
"lambada_openai_mt_es": {
"ppl": 67.22873557270539,
"ppl_stderr": 3.6853291413042055,
"acc": 0.3694934989326606,
"acc_stderr": 0.006724504027913079
},
"lambada_openai_mt_fr": {
"ppl": 42.93424455960906,
"ppl_stderr": 2.3689294613751506,
"acc": 0.4302348146710654,
"acc_stderr": 0.006897835015074962
},
"lambada_openai_mt_it": {
"ppl": 65.76277239773485,
"ppl_stderr": 3.8678074045404967,
"acc": 0.392004657481079,
"acc_stderr": 0.006801548708056975
},
"lambada_standard": {
"ppl": 4.922814417244969,
"ppl_stderr": 0.10844800336124351,
"acc": 0.619056860081506,
"acc_stderr": 0.006765617200231529
},
"lambada_standard_cloze": {
"ppl": 109.09886744922697,
"ppl_stderr": 3.0351063735026287,
"acc": 0.1674752571317679,
"acc_stderr": 0.005202187177767864
}
},
"versions": {
"lambada_openai": 0,
"lambada_openai_cloze": 0,
"lambada_openai_mt_de": 0,
"lambada_openai_mt_en": 0,
"lambada_openai_mt_es": 0,
"lambada_openai_mt_fr": 0,
"lambada_openai_mt_it": 0,
"lambada_standard": 0,
"lambada_standard_cloze": 0
},
"config": {
"model": "hf-causal-experimental",
"model_args": "pretrained=mosaicml/mpt-7b,trust_remote_code=True",
"num_fewshot": 0,
"batch_size": "auto",
"device": "cuda",
"no_cache": true,
"limit": null,
"bootstrap_iters": 100000,
"description_dict": {}
}
}
results/mpt/mpt-7b/mpt-7b_mmlu_5-shot.json 0 → 100644
View file @ 4de8a74e
{
"results": {
"hendrycksTest-abstract_algebra": {
"acc": 0.18,
"acc_stderr": 0.03861229196653695,
"acc_norm": 0.21,
"acc_norm_stderr": 0.040936018074033256
},
"hendrycksTest-anatomy": {
"acc": 0.3851851851851852,
"acc_stderr": 0.042039210401562783,
"acc_norm": 0.37777777777777777,
"acc_norm_stderr": 0.04188307537595853
},
"hendrycksTest-astronomy": {
"acc": 0.39473684210526316,
"acc_stderr": 0.039777499346220734,
"acc_norm": 0.42105263157894735,
"acc_norm_stderr": 0.04017901275981748
},
"hendrycksTest-business_ethics": {
"acc": 0.49,
"acc_stderr": 0.05024183937956911,
"acc_norm": 0.48,
"acc_norm_stderr": 0.050211673156867795
},
"hendrycksTest-clinical_knowledge": {
"acc": 0.3320754716981132,
"acc_stderr": 0.028985455652334388,
"acc_norm": 0.37735849056603776,
"acc_norm_stderr": 0.029832808114796005
},
"hendrycksTest-college_biology": {
"acc": 0.3819444444444444,
"acc_stderr": 0.040629907841466674,
"acc_norm": 0.3541666666666667,
"acc_norm_stderr": 0.039994111357535424
},
"hendrycksTest-college_chemistry": {
"acc": 0.39,
"acc_stderr": 0.04902071300001974,
"acc_norm": 0.41,
"acc_norm_stderr": 0.049431107042371025
},
"hendrycksTest-college_computer_science": {
"acc": 0.34,
"acc_stderr": 0.04760952285695235,
"acc_norm": 0.32,
"acc_norm_stderr": 0.046882617226215034
},
"hendrycksTest-college_mathematics": {
"acc": 0.27,
"acc_stderr": 0.044619604333847394,
"acc_norm": 0.33,
"acc_norm_stderr": 0.047258156262526045
},
"hendrycksTest-college_medicine": {
"acc": 0.36416184971098264,
"acc_stderr": 0.03669072477416907,
"acc_norm": 0.3468208092485549,
"acc_norm_stderr": 0.036291466701596636
},
"hendrycksTest-college_physics": {
"acc": 0.30392156862745096,
"acc_stderr": 0.045766654032077615,
"acc_norm": 0.3333333333333333,
"acc_norm_stderr": 0.04690650298201943
},
"hendrycksTest-computer_security": {
"acc": 0.41,
"acc_stderr": 0.04943110704237102,
"acc_norm": 0.41,
"acc_norm_stderr": 0.049431107042371025
},
"hendrycksTest-conceptual_physics": {
"acc": 0.3276595744680851,
"acc_stderr": 0.030683020843231015,
"acc_norm": 0.2553191489361702,
"acc_norm_stderr": 0.02850485647051418
},
"hendrycksTest-econometrics": {
"acc": 0.2719298245614035,
"acc_stderr": 0.04185774424022056,
"acc_norm": 0.23684210526315788,
"acc_norm_stderr": 0.039994238792813365
},
"hendrycksTest-electrical_engineering": {
"acc": 0.36551724137931035,
"acc_stderr": 0.040131241954243856,
"acc_norm": 0.33793103448275863,
"acc_norm_stderr": 0.03941707632064889
},
"hendrycksTest-elementary_mathematics": {
"acc": 0.29894179894179895,
"acc_stderr": 0.023577604791655802,
"acc_norm": 0.28835978835978837,
"acc_norm_stderr": 0.023330654054535892
},
"hendrycksTest-formal_logic": {
"acc": 0.30952380952380953,
"acc_stderr": 0.04134913018303316,
"acc_norm": 0.2857142857142857,
"acc_norm_stderr": 0.040406101782088394
},
"hendrycksTest-global_facts": {
"acc": 0.35,
"acc_stderr": 0.047937248544110196,
"acc_norm": 0.33,
"acc_norm_stderr": 0.047258156262526045
},
"hendrycksTest-high_school_biology": {
"acc": 0.36451612903225805,
"acc_stderr": 0.02737987122994325,
"acc_norm": 0.3903225806451613,
"acc_norm_stderr": 0.027751256636969583
},
"hendrycksTest-high_school_chemistry": {
"acc": 0.21182266009852216,
"acc_stderr": 0.02874898368994106,
"acc_norm": 0.21674876847290642,
"acc_norm_stderr": 0.028990331252516235
},
"hendrycksTest-high_school_computer_science": {
"acc": 0.43,
"acc_stderr": 0.04975698519562428,
"acc_norm": 0.41,
"acc_norm_stderr": 0.049431107042371025
},
"hendrycksTest-high_school_european_history": {
"acc": 0.38181818181818183,
"acc_stderr": 0.03793713171165635,
"acc_norm": 0.37575757575757573,
"acc_norm_stderr": 0.03781887353205983
},
"hendrycksTest-high_school_geography": {
"acc": 0.3838383838383838,
"acc_stderr": 0.03464881675016339,
"acc_norm": 0.40404040404040403,
"acc_norm_stderr": 0.03496130972056128
},
"hendrycksTest-high_school_government_and_politics": {
"acc": 0.41450777202072536,
"acc_stderr": 0.03555300319557673,
"acc_norm": 0.41450777202072536,
"acc_norm_stderr": 0.03555300319557672
},
"hendrycksTest-high_school_macroeconomics": {
"acc": 0.3487179487179487,
"acc_stderr": 0.024162780284017717,
"acc_norm": 0.29743589743589743,
"acc_norm_stderr": 0.02317740813146594
},
"hendrycksTest-high_school_mathematics": {
"acc": 0.29259259259259257,
"acc_stderr": 0.027738969632176088,
"acc_norm": 0.3037037037037037,
"acc_norm_stderr": 0.02803792996911499
},
"hendrycksTest-high_school_microeconomics": {
"acc": 0.33613445378151263,
"acc_stderr": 0.030684737115135353,
"acc_norm": 0.3697478991596639,
"acc_norm_stderr": 0.03135709599613591
},
"hendrycksTest-high_school_physics": {
"acc": 0.2781456953642384,
"acc_stderr": 0.03658603262763743,
"acc_norm": 0.2781456953642384,
"acc_norm_stderr": 0.03658603262763743
},
"hendrycksTest-high_school_psychology": {
"acc": 0.46972477064220186,
"acc_stderr": 0.021397988604936965,
"acc_norm": 0.44587155963302755,
"acc_norm_stderr": 0.02131133500970858
},
"hendrycksTest-high_school_statistics": {
"acc": 0.3287037037037037,
"acc_stderr": 0.03203614084670058,
"acc_norm": 0.32407407407407407,
"acc_norm_stderr": 0.03191923445686185
},
"hendrycksTest-high_school_us_history": {
"acc": 0.3431372549019608,
"acc_stderr": 0.03332139944668085,
"acc_norm": 0.3137254901960784,
"acc_norm_stderr": 0.032566854844603886
},
"hendrycksTest-high_school_world_history": {
"acc": 0.29535864978902954,
"acc_stderr": 0.029696338713422876,
"acc_norm": 0.2869198312236287,
"acc_norm_stderr": 0.02944377302259469
},
"hendrycksTest-human_aging": {
"acc": 0.336322869955157,
"acc_stderr": 0.031708824268455,
"acc_norm": 0.3273542600896861,
"acc_norm_stderr": 0.031493846709941306
},
"hendrycksTest-human_sexuality": {
"acc": 0.2748091603053435,
"acc_stderr": 0.03915345408847836,
"acc_norm": 0.3282442748091603,
"acc_norm_stderr": 0.041184385658062976
},
"hendrycksTest-international_law": {
"acc": 0.371900826446281,
"acc_stderr": 0.04412015806624504,
"acc_norm": 0.49586776859504134,
"acc_norm_stderr": 0.045641987674327526
},
"hendrycksTest-jurisprudence": {
"acc": 0.3425925925925926,
"acc_stderr": 0.045879047413018105,
"acc_norm": 0.39814814814814814,
"acc_norm_stderr": 0.04732332615978814
},
"hendrycksTest-logical_fallacies": {
"acc": 0.3803680981595092,
"acc_stderr": 0.038142698932618374,
"acc_norm": 0.36809815950920244,
"acc_norm_stderr": 0.03789213935838395
},
"hendrycksTest-machine_learning": {
"acc": 0.26785714285714285,
"acc_stderr": 0.04203277291467763,
"acc_norm": 0.24107142857142858,
"acc_norm_stderr": 0.04059867246952686
},
"hendrycksTest-management": {
"acc": 0.42718446601941745,
"acc_stderr": 0.04897957737781169,
"acc_norm": 0.39805825242718446,
"acc_norm_stderr": 0.0484674825397724
},
"hendrycksTest-marketing": {
"acc": 0.5512820512820513,
"acc_stderr": 0.032583346493868806,
"acc_norm": 0.5512820512820513,
"acc_norm_stderr": 0.032583346493868806
},
"hendrycksTest-medical_genetics": {
"acc": 0.39,
"acc_stderr": 0.04902071300001975,
"acc_norm": 0.38,
"acc_norm_stderr": 0.04878317312145633
},
"hendrycksTest-miscellaneous": {
"acc": 0.5555555555555556,
"acc_stderr": 0.017769250583533246,
"acc_norm": 0.5568326947637292,
"acc_norm_stderr": 0.01776408503534841
},
"hendrycksTest-moral_disputes": {
"acc": 0.3208092485549133,
"acc_stderr": 0.025131000233647904,
"acc_norm": 0.30057803468208094,
"acc_norm_stderr": 0.024685316867257796
},
"hendrycksTest-moral_scenarios": {
"acc": 0.26033519553072626,
"acc_stderr": 0.014676252009319483,
"acc_norm": 0.27262569832402234,
"acc_norm_stderr": 0.014893391735249614
},
"hendrycksTest-nutrition": {
"acc": 0.3431372549019608,
"acc_stderr": 0.027184498909941616,
"acc_norm": 0.4019607843137255,
"acc_norm_stderr": 0.02807415894760066
},
"hendrycksTest-philosophy": {
"acc": 0.3762057877813505,
"acc_stderr": 0.027513925683549427,
"acc_norm": 0.36977491961414793,
"acc_norm_stderr": 0.027417996705630998
},
"hendrycksTest-prehistory": {
"acc": 0.33641975308641975,
"acc_stderr": 0.02628973494595293,
"acc_norm": 0.3055555555555556,
"acc_norm_stderr": 0.025630824975621344
},
"hendrycksTest-professional_accounting": {
"acc": 0.3049645390070922,
"acc_stderr": 0.027464708442022135,
"acc_norm": 0.2907801418439716,
"acc_norm_stderr": 0.027090664368353178
},
"hendrycksTest-professional_law": {
"acc": 0.25945241199478486,
"acc_stderr": 0.011195262076350299,
"acc_norm": 0.2842242503259452,
"acc_norm_stderr": 0.011519880596516074
},
"hendrycksTest-professional_medicine": {
"acc": 0.29411764705882354,
"acc_stderr": 0.027678468642144703,
"acc_norm": 0.3161764705882353,
"acc_norm_stderr": 0.02824568739146291
},
"hendrycksTest-professional_psychology": {
"acc": 0.315359477124183,
"acc_stderr": 0.018798086284886883,
"acc_norm": 0.3022875816993464,
"acc_norm_stderr": 0.01857923271111388
},
"hendrycksTest-public_relations": {
"acc": 0.41818181818181815,
"acc_stderr": 0.04724577405731571,
"acc_norm": 0.42727272727272725,
"acc_norm_stderr": 0.04738198703545483
},
"hendrycksTest-security_studies": {
"acc": 0.2816326530612245,
"acc_stderr": 0.028795185574291282,
"acc_norm": 0.24081632653061225,
"acc_norm_stderr": 0.027372942201788163
},
"hendrycksTest-sociology": {
"acc": 0.34328358208955223,
"acc_stderr": 0.03357379665433431,
"acc_norm": 0.3681592039800995,
"acc_norm_stderr": 0.034104105654953025
},
"hendrycksTest-us_foreign_policy": {
"acc": 0.38,
"acc_stderr": 0.04878317312145632,
"acc_norm": 0.39,
"acc_norm_stderr": 0.04902071300001975
},
"hendrycksTest-virology": {
"acc": 0.3253012048192771,
"acc_stderr": 0.03647168523683229,
"acc_norm": 0.3253012048192771,
"acc_norm_stderr": 0.03647168523683227
},
"hendrycksTest-world_religions": {
"acc": 0.543859649122807,
"acc_stderr": 0.03820042586602966,
"acc_norm": 0.5789473684210527,
"acc_norm_stderr": 0.03786720706234214
}
},
"versions": {
"hendrycksTest-abstract_algebra": 0,
"hendrycksTest-anatomy": 0,
"hendrycksTest-astronomy": 0,
"hendrycksTest-business_ethics": 0,
"hendrycksTest-clinical_knowledge": 0,
"hendrycksTest-college_biology": 0,
"hendrycksTest-college_chemistry": 0,
"hendrycksTest-college_computer_science": 0,
"hendrycksTest-college_mathematics": 0,
"hendrycksTest-college_medicine": 0,
"hendrycksTest-college_physics": 0,
"hendrycksTest-computer_security": 0,
"hendrycksTest-conceptual_physics": 0,
"hendrycksTest-econometrics": 0,
"hendrycksTest-electrical_engineering": 0,
"hendrycksTest-elementary_mathematics": 0,
"hendrycksTest-formal_logic": 0,
"hendrycksTest-global_facts": 0,
"hendrycksTest-high_school_biology": 0,
"hendrycksTest-high_school_chemistry": 0,
"hendrycksTest-high_school_computer_science": 0,
"hendrycksTest-high_school_european_history": 0,
"hendrycksTest-high_school_geography": 0,
"hendrycksTest-high_school_government_and_politics": 0,
"hendrycksTest-high_school_macroeconomics": 0,
"hendrycksTest-high_school_mathematics": 0,
"hendrycksTest-high_school_microeconomics": 0,
"hendrycksTest-high_school_physics": 0,
"hendrycksTest-high_school_psychology": 0,
"hendrycksTest-high_school_statistics": 0,
"hendrycksTest-high_school_us_history": 0,
"hendrycksTest-high_school_world_history": 0,
"hendrycksTest-human_aging": 0,
"hendrycksTest-human_sexuality": 0,
"hendrycksTest-international_law": 0,
"hendrycksTest-jurisprudence": 0,
"hendrycksTest-logical_fallacies": 0,
"hendrycksTest-machine_learning": 0,
"hendrycksTest-management": 0,
"hendrycksTest-marketing": 0,
"hendrycksTest-medical_genetics": 0,
"hendrycksTest-miscellaneous": 0,
"hendrycksTest-moral_disputes": 0,
"hendrycksTest-moral_scenarios": 0,
"hendrycksTest-nutrition": 0,
"hendrycksTest-philosophy": 0,
"hendrycksTest-prehistory": 0,
"hendrycksTest-professional_accounting": 0,
"hendrycksTest-professional_law": 0,
"hendrycksTest-professional_medicine": 0,
"hendrycksTest-professional_psychology": 0,
"hendrycksTest-public_relations": 0,
"hendrycksTest-security_studies": 0,
"hendrycksTest-sociology": 0,
"hendrycksTest-us_foreign_policy": 0,
"hendrycksTest-virology": 0,
"hendrycksTest-world_religions": 0
},
"config": {
"model": "hf-causal-experimental",
"model_args": "pretrained=mosaicml/mpt-7b,trust_remote_code=True,dtype=bfloat16",
"num_fewshot": 5,
"batch_size": "auto",
"device": "cuda",
"no_cache": true,
"limit": null,
"bootstrap_iters": 100000,
"description_dict": {}
}
}
results/mpt/mpt-7b/mpt-7b_pawsx_0-shot.json 0 → 100644
View file @ 4de8a74e
{
"results": {
"pawsx_de": {
"acc": 0.614,
"acc_stderr": 0.010888584877766427
},
"pawsx_en": {
"acc": 0.7035,
"acc_stderr": 0.010214991337441791
},
"pawsx_es": {
"acc": 0.6495,
"acc_stderr": 0.01067154233969731
},
"pawsx_fr": {
"acc": 0.6285,
"acc_stderr": 0.01080751017293364
},
"pawsx_ja": {
"acc": 0.493,
"acc_stderr": 0.011182040020027768
},
"pawsx_ko": {
"acc": 0.5365,
"acc_stderr": 0.011153298751334327
},
"pawsx_zh": {
"acc": 0.5625,
"acc_stderr": 0.011095423796079503
}
},
"versions": {
"pawsx_de": 0,
"pawsx_en": 0,
"pawsx_es": 0,
"pawsx_fr": 0,
"pawsx_ja": 0,
"pawsx_ko": 0,
"pawsx_zh": 0
},
"config": {
"model": "hf-causal-experimental",
"model_args": "pretrained=mosaicml/mpt-7b,trust_remote_code=True,dtype=bfloat16",
"num_fewshot": 0,
"batch_size": "auto",
"device": "cuda",
"no_cache": true,
"limit": null,
"bootstrap_iters": 100000,
"description_dict": {}
}
}
results/mpt/mpt-7b/mpt-7b_reading_comprehension_0-shot.json 0 → 100644
View file @ 4de8a74e
{
"results": {
"coqa": {
"f1": 0.7650867255895625,
"f1_stderr": 0.01481717694356494,
"em": 0.6301666666666667,
"em_stderr": 0.018680205213012713
},
"drop": {
"em": 0.03429110738255033,
"em_stderr": 0.0018636035184959787,
"f1": 0.1338569630872482,
"f1_stderr": 0.0025165760673094154
},
"race": {
"acc": 0.3866028708133971,
"acc_stderr": 0.01507138477304713
}
},
"versions": {
"coqa": 1,
"drop": 1,
"race": 1
},
"config": {
"model": "hf-causal-experimental",
"model_args": "pretrained=mosaicml/mpt-7b,trust_remote_code=True",
"num_fewshot": 0,
"batch_size": "auto",
"device": "cuda",
"no_cache": true,
"limit": null,
"bootstrap_iters": 100000,
"description_dict": {}
}
}
results/mpt/mpt-7b/mpt-7b_superglue_0-shot.json 0 → 100644
View file @ 4de8a74e
{
"results": {
"boolq": {
"acc": 0.7382262996941896,
"acc_stderr": 0.007688653730439849
},
"cb": {
"acc": 0.4107142857142857,
"acc_stderr": 0.0663363415035954,
"f1": 0.2126984126984127
},
"copa": {
"acc": 0.84,
"acc_stderr": 0.036845294917747115
},
"multirc": {
"acc": 0.008394543546694649,
"acc_stderr": 0.002956987733350658
},
"record": {
"f1": 0.900992857142857,
"f1_stderr": 0.0029401923751195343,
"em": 0.893,
"em_stderr": 0.0030912870467751773
},
"wic": {
"acc": 0.4843260188087774,
"acc_stderr": 0.01980098495534785
},
"wsc": {
"acc": 0.6346153846153846,
"acc_stderr": 0.0474473339327792
}
},
"versions": {
"boolq": 1,
"cb": 1,
"copa": 0,
"multirc": 1,
"record": 0,
"wic": 0,
"wsc": 0
},
"config": {
"model": "hf-causal-experimental",
"model_args": "pretrained=mosaicml/mpt-7b,trust_remote_code=True",
"num_fewshot": 0,
"batch_size": "auto",
"device": "cuda",
"no_cache": true,
"limit": null,
"bootstrap_iters": 100000,
"description_dict": {}
}
}
results/mpt/mpt-7b/mpt-7b_unscramble_0-shot.json 0 → 100644
View file @ 4de8a74e
{
"results": {
"anagrams1": {
"acc": 0.0,
"acc_stderr": 0.0
},
"anagrams2": {
"acc": 0.0001,
"acc_stderr": 0.0001000000000000119
},
"cycle_letters": {
"acc": 0.0,
"acc_stderr": 0.0
},
"random_insertion": {
"acc": 0.0004,
"acc_stderr": 0.00019996999474889126
},
"reversed_words": {
"acc": 0.0,
"acc_stderr": 0.0
}
},
"versions": {
"anagrams1": 0,
"anagrams2": 0,
"cycle_letters": 0,
"random_insertion": 0,
"reversed_words": 0
},
"config": {
"model": "hf-causal-experimental",
"model_args": "pretrained=mosaicml/mpt-7b,trust_remote_code=True",
"num_fewshot": 0,
"batch_size": "auto",
"device": "cuda",
"no_cache": true,
"limit": null,
"bootstrap_iters": 100000,
"description_dict": {}
}
}
results/mpt/mpt-7b/mpt-7b_xcopa_0-shot.json 0 → 100644
View file @ 4de8a74e
{
"results": {
"xcopa_et": {
"acc": 0.474,
"acc_stderr": 0.02235279165091416
},
"xcopa_ht": {
"acc": 0.498,
"acc_stderr": 0.02238289498648353
},
"xcopa_id": {
"acc": 0.568,
"acc_stderr": 0.02217510926561316
},
"xcopa_it": {
"acc": 0.594,
"acc_stderr": 0.02198396209008634
},
"xcopa_qu": {
"acc": 0.484,
"acc_stderr": 0.0223716109825804
},
"xcopa_sw": {
"acc": 0.516,
"acc_stderr": 0.0223716109825804
},
"xcopa_ta": {
"acc": 0.54,
"acc_stderr": 0.022311333245289663
},
"xcopa_th": {
"acc": 0.542,
"acc_stderr": 0.02230396677426995
},
"xcopa_tr": {
"acc": 0.516,
"acc_stderr": 0.022371610982580396
},
"xcopa_vi": {
"acc": 0.536,
"acc_stderr": 0.022324981738385246
},
"xcopa_zh": {
"acc": 0.632,
"acc_stderr": 0.02158898256835354
}
},
"versions": {
"xcopa_et": 0,
"xcopa_ht": 0,
"xcopa_id": 0,
"xcopa_it": 0,
"xcopa_qu": 0,
"xcopa_sw": 0,
"xcopa_ta": 0,
"xcopa_th": 0,
"xcopa_tr": 0,
"xcopa_vi": 0,
"xcopa_zh": 0
},
"config": {
"model": "hf-causal-experimental",
"model_args": "pretrained=mosaicml/mpt-7b,trust_remote_code=True,dtype=bfloat16",
"num_fewshot": 0,
"batch_size": "auto",
"device": "cuda",
"no_cache": true,
"limit": null,
"bootstrap_iters": 100000,
"description_dict": {}
}
}
results/mpt/mpt-7b/mpt-7b_xnli_0-shot.json 0 → 100644
View file @ 4de8a74e
{
"results": {
"xnli_ar": {
"acc": 0.3331337325349301,
"acc_stderr": 0.006659676975732312
},
"xnli_bg": {
"acc": 0.36826347305389223,
"acc_stderr": 0.00681509322031267
},
"xnli_de": {
"acc": 0.46447105788423154,
"acc_stderr": 0.007046854204317796
},
"xnli_el": {
"acc": 0.36187624750499003,
"acc_stderr": 0.006789799946197319
},
"xnli_en": {
"acc": 0.543313373253493,
"acc_stderr": 0.007038155029004149
},
"xnli_es": {
"acc": 0.4564870259481038,
"acc_stderr": 0.007037909229199955
},
"xnli_fr": {
"acc": 0.4880239520958084,
"acc_stderr": 0.007062685615595022
},
"xnli_hi": {
"acc": 0.3473053892215569,
"acc_stderr": 0.006727214239733754
},
"xnli_ru": {
"acc": 0.444311377245509,
"acc_stderr": 0.007020757195791274
},
"xnli_sw": {
"acc": 0.3341317365269461,
"acc_stderr": 0.006664652441694265
},
"xnli_th": {
"acc": 0.36127744510978044,
"acc_stderr": 0.006787362347422093
},
"xnli_tr": {
"acc": 0.37684630738522956,
"acc_stderr": 0.006847061089041557
},
"xnli_ur": {
"acc": 0.33632734530938124,
"acc_stderr": 0.006675480563072364
},
"xnli_vi": {
"acc": 0.37325349301397204,
"acc_stderr": 0.0068339592620100505
},
"xnli_zh": {
"acc": 0.3534930139720559,
"acc_stderr": 0.006754629196407293
}
},
"versions": {
"xnli_ar": 0,
"xnli_bg": 0,
"xnli_de": 0,
"xnli_el": 0,
"xnli_en": 0,
"xnli_es": 0,
"xnli_fr": 0,
"xnli_hi": 0,
"xnli_ru": 0,
"xnli_sw": 0,
"xnli_th": 0,
"xnli_tr": 0,
"xnli_ur": 0,
"xnli_vi": 0,
"xnli_zh": 0
},
"config": {
"model": "hf-causal-experimental",
"model_args": "pretrained=mosaicml/mpt-7b,trust_remote_code=True,dtype=bfloat16",
"num_fewshot": 0,
"batch_size": "auto",
"device": "cuda",
"no_cache": true,
"limit": null,
"bootstrap_iters": 100000,
"description_dict": {}
}
}
results/mpt/mpt-7b/mpt-7b_xstory_cloze_0-shot.json 0 → 100644
View file @ 4de8a74e
{
"results": {
"xstory_cloze_ar": {
"acc": 0.48510919920582396,
"acc_stderr": 0.012861417842074004
},
"xstory_cloze_en": {
"acc": 0.7789543348775645,
"acc_stderr": 0.010678457581809239
},
"xstory_cloze_es": {
"acc": 0.6604897418927862,
"acc_stderr": 0.01218627614665943
},
"xstory_cloze_eu": {
"acc": 0.5109199205823958,
"acc_stderr": 0.012864056278255038
},
"xstory_cloze_hi": {
"acc": 0.5168762409000662,
"acc_stderr": 0.012859793919977606
},
"xstory_cloze_id": {
"acc": 0.5519523494374586,
"acc_stderr": 0.012797478885304742
},
"xstory_cloze_my": {
"acc": 0.48378557246856385,
"acc_stderr": 0.01286035780505586
},
"xstory_cloze_ru": {
"acc": 0.5724685638649901,
"acc_stderr": 0.012731259626982528
},
"xstory_cloze_sw": {
"acc": 0.4990072799470549,
"acc_stderr": 0.012867099955422935
},
"xstory_cloze_te": {
"acc": 0.5294506949040371,
"acc_stderr": 0.012844785490017004
},
"xstory_cloze_zh": {
"acc": 0.5956320317670417,
"acc_stderr": 0.012629580396570932
}
},
"versions": {
"xstory_cloze_ar": 0,
"xstory_cloze_en": 0,
"xstory_cloze_es": 0,
"xstory_cloze_eu": 0,
"xstory_cloze_hi": 0,
"xstory_cloze_id": 0,
"xstory_cloze_my": 0,
"xstory_cloze_ru": 0,
"xstory_cloze_sw": 0,
"xstory_cloze_te": 0,
"xstory_cloze_zh": 0
},
"config": {
"model": "hf-causal-experimental",
"model_args": "pretrained=mosaicml/mpt-7b,trust_remote_code=True,dtype=bfloat16",
"num_fewshot": 0,
"batch_size": "auto",
"device": "cuda",
"no_cache": true,
"limit": null,
"bootstrap_iters": 100000,
"description_dict": {}
}
}
results/mpt/mpt-7b/mpt-7b_xwinograd_0-shot.json 0 → 100644
View file @ 4de8a74e
{
"results": {
"xwinograd_en": {
"acc": 0.8666666666666667,
"acc_stderr": 0.0070514325016347275
},
"xwinograd_fr": {
"acc": 0.6626506024096386,
"acc_stderr": 0.05221260262032129
},
"xwinograd_jp": {
"acc": 0.602711157455683,
"acc_stderr": 0.015809751560314552
},
"xwinograd_pt": {
"acc": 0.6692015209125475,
"acc_stderr": 0.02906762615931534
},
"xwinograd_ru": {
"acc": 0.6952380952380952,
"acc_stderr": 0.025976599352305375
},
"xwinograd_zh": {
"acc": 0.7162698412698413,
"acc_stderr": 0.02010051064884106
}
},
"versions": {
"xwinograd_en": 0,
"xwinograd_fr": 0,
"xwinograd_jp": 0,
"xwinograd_pt": 0,
"xwinograd_ru": 0,
"xwinograd_zh": 0
},
"config": {
"model": "hf-causal-experimental",
"model_args": "pretrained=mosaicml/mpt-7b,trust_remote_code=True,dtype=bfloat16",
"num_fewshot": 0,
"batch_size": "auto",
"device": "cuda",
"no_cache": true,
"limit": null,
"bootstrap_iters": 100000,
"description_dict": {}
}
}
results/opt/opt-1.3b/README.md 0 → 100644
View file @ 4de8a74e
# opt-1.3b
## opt-1.3b.json
| Task |Version| Metric |Value| |Stderr|
|-------------------------------------------------|------:|--------|----:|---|-----:|
|arc_challenge | 0|acc |23.12|± | 1.23|
| | |acc_norm|29.44|± | 1.33|
|arc_easy | 0|acc |57.03|± | 1.02|
| | |acc_norm|50.93|± | 1.03|
|hendrycksTest-abstract_algebra | 0|acc |26.00|± | 4.41|
| | |acc_norm|25.00|± | 4.35|
|hendrycksTest-anatomy | 0|acc |22.96|± | 3.63|
| | |acc_norm|21.48|± | 3.55|
|hendrycksTest-astronomy | 0|acc |23.68|± | 3.46|
| | |acc_norm|34.21|± | 3.86|
|hendrycksTest-business_ethics | 0|acc |34.00|± | 4.76|
| | |acc_norm|33.00|± | 4.73|
|hendrycksTest-clinical_knowledge | 0|acc |19.25|± | 2.43|
| | |acc_norm|25.28|± | 2.67|
|hendrycksTest-college_biology | 0|acc |26.39|± | 3.69|
| | |acc_norm|27.78|± | 3.75|
|hendrycksTest-college_chemistry | 0|acc |28.00|± | 4.51|
| | |acc_norm|34.00|± | 4.76|
|hendrycksTest-college_computer_science | 0|acc |33.00|± | 4.73|
| | |acc_norm|30.00|± | 4.61|
|hendrycksTest-college_mathematics | 0|acc |19.00|± | 3.94|
| | |acc_norm|30.00|± | 4.61|
|hendrycksTest-college_medicine | 0|acc |17.92|± | 2.92|
| | |acc_norm|23.70|± | 3.24|
|hendrycksTest-college_physics | 0|acc |27.45|± | 4.44|
| | |acc_norm|30.39|± | 4.58|
|hendrycksTest-computer_security | 0|acc |29.00|± | 4.56|
| | |acc_norm|38.00|± | 4.88|
|hendrycksTest-conceptual_physics | 0|acc |21.70|± | 2.69|
| | |acc_norm|20.43|± | 2.64|
|hendrycksTest-econometrics | 0|acc |24.56|± | 4.05|
| | |acc_norm|23.68|± | 4.00|
|hendrycksTest-electrical_engineering | 0|acc |25.52|± | 3.63|
| | |acc_norm|28.97|± | 3.78|
|hendrycksTest-elementary_mathematics | 0|acc |19.58|± | 2.04|
| | |acc_norm|24.87|± | 2.23|
|hendrycksTest-formal_logic | 0|acc |29.37|± | 4.07|
| | |acc_norm|26.98|± | 3.97|
|hendrycksTest-global_facts | 0|acc |16.00|± | 3.68|
| | |acc_norm|18.00|± | 3.86|
|hendrycksTest-high_school_biology | 0|acc |20.97|± | 2.32|
| | |acc_norm|26.77|± | 2.52|
|hendrycksTest-high_school_chemistry | 0|acc |24.63|± | 3.03|
| | |acc_norm|30.54|± | 3.24|
|hendrycksTest-high_school_computer_science | 0|acc |27.00|± | 4.46|
| | |acc_norm|32.00|± | 4.69|
|hendrycksTest-high_school_european_history | 0|acc |24.24|± | 3.35|
| | |acc_norm|27.27|± | 3.48|
|hendrycksTest-high_school_geography | 0|acc |22.22|± | 2.96|
| | |acc_norm|28.28|± | 3.21|
|hendrycksTest-high_school_government_and_politics| 0|acc |20.73|± | 2.93|
| | |acc_norm|23.83|± | 3.07|
|hendrycksTest-high_school_macroeconomics | 0|acc |29.23|± | 2.31|
| | |acc_norm|29.23|± | 2.31|
|hendrycksTest-high_school_mathematics | 0|acc |21.85|± | 2.52|
| | |acc_norm|28.89|± | 2.76|
|hendrycksTest-high_school_microeconomics | 0|acc |21.43|± | 2.67|
| | |acc_norm|30.25|± | 2.98|
|hendrycksTest-high_school_physics | 0|acc |22.52|± | 3.41|
| | |acc_norm|25.17|± | 3.54|
|hendrycksTest-high_school_psychology | 0|acc |22.57|± | 1.79|
| | |acc_norm|24.22|± | 1.84|
|hendrycksTest-high_school_statistics | 0|acc |25.46|± | 2.97|
| | |acc_norm|27.78|± | 3.05|
|hendrycksTest-high_school_us_history | 0|acc |25.00|± | 3.04|
| | |acc_norm|25.49|± | 3.06|
|hendrycksTest-high_school_world_history | 0|acc |26.58|± | 2.88|
| | |acc_norm|27.85|± | 2.92|
|hendrycksTest-human_aging | 0|acc |35.43|± | 3.21|
| | |acc_norm|29.15|± | 3.05|
|hendrycksTest-human_sexuality | 0|acc |40.46|± | 4.30|
| | |acc_norm|31.30|± | 4.07|
|hendrycksTest-international_law | 0|acc |17.36|± | 3.46|
| | |acc_norm|47.93|± | 4.56|
|hendrycksTest-jurisprudence | 0|acc |28.70|± | 4.37|
| | |acc_norm|39.81|± | 4.73|
|hendrycksTest-logical_fallacies | 0|acc |19.02|± | 3.08|
| | |acc_norm|28.83|± | 3.56|
|hendrycksTest-machine_learning | 0|acc |27.68|± | 4.25|
| | |acc_norm|27.68|± | 4.25|
|hendrycksTest-management | 0|acc |20.39|± | 3.99|
| | |acc_norm|27.18|± | 4.41|
|hendrycksTest-marketing | 0|acc |28.21|± | 2.95|
| | |acc_norm|33.76|± | 3.10|
|hendrycksTest-medical_genetics | 0|acc |27.00|± | 4.46|
| | |acc_norm|36.00|± | 4.82|
|hendrycksTest-miscellaneous | 0|acc |28.35|± | 1.61|
| | |acc_norm|28.74|± | 1.62|
|hendrycksTest-moral_disputes | 0|acc |27.17|± | 2.39|
| | |acc_norm|30.35|± | 2.48|
|hendrycksTest-moral_scenarios | 0|acc |23.80|± | 1.42|
| | |acc_norm|27.26|± | 1.49|
|hendrycksTest-nutrition | 0|acc |29.41|± | 2.61|
| | |acc_norm|39.54|± | 2.80|
|hendrycksTest-philosophy | 0|acc |23.79|± | 2.42|
| | |acc_norm|30.87|± | 2.62|
|hendrycksTest-prehistory | 0|acc |24.07|± | 2.38|
| | |acc_norm|21.60|± | 2.29|
|hendrycksTest-professional_accounting | 0|acc |25.89|± | 2.61|
| | |acc_norm|26.24|± | 2.62|
|hendrycksTest-professional_law | 0|acc |26.01|± | 1.12|
| | |acc_norm|28.03|± | 1.15|
|hendrycksTest-professional_medicine | 0|acc |24.63|± | 2.62|
| | |acc_norm|22.43|± | 2.53|
|hendrycksTest-professional_psychology | 0|acc |23.69|± | 1.72|
| | |acc_norm|25.49|± | 1.76|
|hendrycksTest-public_relations | 0|acc |25.45|± | 4.17|
| | |acc_norm|19.09|± | 3.76|
|hendrycksTest-security_studies | 0|acc |32.24|± | 2.99|
| | |acc_norm|26.53|± | 2.83|
|hendrycksTest-sociology | 0|acc |33.83|± | 3.35|
| | |acc_norm|34.33|± | 3.36|
|hendrycksTest-us_foreign_policy | 0|acc |32.00|± | 4.69|
| | |acc_norm|27.00|± | 4.46|
|hendrycksTest-virology | 0|acc |34.34|± | 3.70|
| | |acc_norm|30.12|± | 3.57|
|hendrycksTest-world_religions | 0|acc |34.50|± | 3.65|
| | |acc_norm|33.92|± | 3.63|
|lambada_openai | 0|ppl | 6.64|± | 0.17|
| | |acc |57.93|± | 0.69|
|logiqa | 0|acc |22.27|± | 1.63|
| | |acc_norm|27.19|± | 1.75|
|piqa | 0|acc |71.71|± | 1.05|
| | |acc_norm|72.47|± | 1.04|
|sciq | 0|acc |84.50|± | 1.15|
| | |acc_norm|76.50|± | 1.34|
|winogrande | 0|acc |59.75|± | 1.38|
|wsc | 0|acc |38.46|± | 4.79|
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment