DatPySci's picture
Add files using upload-large-folder tool
2616764 verified
Raw History Blame Contribute Delete
64.5 kB
{
"checkpoint": "checkpoint-38796",
"id": {
"answer_accuracy": 0.7004678819444444,
"avg_response_len": 198.95842534722223,
"avg_loss": 0.0,
"count": 1152000,
"validation_metrics": {},
"pass_at_k": {
"pass@1": 0.7004678819444444,
"pass@2": 0.803145190835523,
"pass@4": 0.8810327584676866,
"pass@8": 0.930000105282735,
"pass@16": 0.9581204489043869,
"pass@32": 0.9742042919530437,
"pass@64": 0.9838618914836799,
"pass@128": 0.9898888888888889
},
"per_op_pass_at_k": {
"10": {
"pass@1": 0.5105703125,
"pass@2": 0.6699938484251962,
"pass@4": 0.7991659679415073,
"pass@8": 0.8847154633623784,
"pass@16": 0.9347854223296508,
"pass@32": 0.9632970265066139,
"pass@64": 0.980442548083157,
"pass@128": 0.992
},
"2": {
"pass@1": 0.935890625,
"pass@2": 0.9592861712598416,
"pass@4": 0.9768458330521185,
"pass@8": 0.9867971535992609,
"pass@16": 0.9919445464167224,
"pass@32": 0.9942186611862515,
"pass@64": 0.9948690786426989,
"pass@128": 0.995
},
"3": {
"pass@1": 0.93975,
"pass@2": 0.9609361466535429,
"pass@4": 0.9775336966629172,
"pass@8": 0.9882813969399472,
"pass@16": 0.9934026899376711,
"pass@32": 0.9952107555410625,
"pass@64": 0.9959019362061534,
"pass@128": 0.996
},
"4": {
"pass@1": 0.806453125,
"pass@2": 0.8676486220472444,
"pass@4": 0.911353344019498,
"pass@8": 0.9400612877585252,
"pass@16": 0.9589647416451935,
"pass@32": 0.9720786045524892,
"pass@64": 0.9811436774483744,
"pass@128": 0.987
},
"5": {
"pass@1": 0.719234375,
"pass@2": 0.8196967273622047,
"pass@4": 0.8851043299587543,
"pass@8": 0.9222199389254376,
"pass@16": 0.9448174036914444,
"pass@32": 0.9598280784653056,
"pass@64": 0.9709283962665971,
"pass@128": 0.98
},
"6": {
"pass@1": 0.698921875,
"pass@2": 0.809659571850394,
"pass@4": 0.8861456253280843,
"pass@8": 0.9296744960557235,
"pass@16": 0.9532426321493441,
"pass@32": 0.9681859214131414,
"pass@64": 0.9788188969365212,
"pass@128": 0.986
},
"7": {
"pass@1": 0.618640625,
"pass@2": 0.7534297490157486,
"pass@4": 0.8522904651293589,
"pass@8": 0.9134351163840331,
"pass@16": 0.9500415651070467,
"pass@32": 0.9713268310837263,
"pass@64": 0.9833246380222623,
"pass@128": 0.99
},
"8": {
"pass@1": 0.57221875,
"pass@2": 0.7231927903543292,
"pass@4": 0.8385967574990625,
"pass@8": 0.909620771341596,
"pass@16": 0.9483642685489777,
"pass@32": 0.9693944224018802,
"pass@64": 0.9815823234229324,
"pass@128": 0.989
},
"9": {
"pass@1": 0.50253125,
"pass@2": 0.6644630905511801,
"pass@4": 0.8022588066179234,
"pass@8": 0.8951953231778146,
"pass@16": 0.9475207703133638,
"pass@32": 0.9742983264269067,
"pass@64": 0.9877455283243902,
"pass@128": 0.994
}
},
"per_op_accuracy": {
"10": 0.5105703125,
"2": 0.935890625,
"3": 0.93975,
"4": 0.806453125,
"5": 0.719234375,
"6": 0.698921875,
"7": 0.618640625,
"8": 0.57221875,
"9": 0.50253125
},
"per_op_avg_response_len": {
"10": 280.0350625,
"2": 116.76371875,
"3": 149.778203125,
"4": 158.538859375,
"5": 173.8068046875,
"6": 193.58321875,
"7": 222.0638046875,
"8": 240.2696328125,
"9": 255.7865234375
},
"per_op_avg_loss": {},
"per_op_length": {
"10": 280.0350625,
"2": 116.76371875,
"3": 149.778203125,
"4": 158.538859375,
"5": 173.8068046875,
"6": 193.58321875,
"7": 222.0638046875,
"8": 240.2696328125,
"9": 255.7865234375
},
"per_op_loss": {},
"per_template": {
"crazy_zootopia": {
"count": 379008,
"correct": 260419,
"answer_accuracy": 0.6871068684566025,
"avg_response_len": 189.2360583417764,
"resp_tokens_sum": 71721980,
"pass_at_k": {
"pass@1": 0.6871068684566025,
"pass@2": 0.792426960592694,
"pass@4": 0.8731736406872669,
"pass@8": 0.9240051211601905,
"pass@16": 0.9530947039397669,
"pass@32": 0.9700868842236148,
"pass@64": 0.9808123981985275,
"pass@128": 0.9878419452887538
},
"per_op_pass_at_k": {
"10": {
"pass@1": 0.5095409292035398,
"pass@2": 0.6676066418135783,
"pass@4": 0.792585876710101,
"pass@8": 0.8760817636863799,
"pass@16": 0.9283330831148673,
"pass@32": 0.9602328298448352,
"pass@64": 0.9791876634794598,
"pass@128": 0.9911504424778761
},
"2": {
"pass@1": 0.9343360591900312,
"pass@2": 0.9592853901439887,
"pass@4": 0.9779000282674944,
"pass@8": 0.9878251114374832,
"pass@16": 0.9922969056587208,
"pass@32": 0.9936688924295337,
"pass@64": 0.9937693490770984,
"pass@128": 0.9937694704049844
},
"3": {
"pass@1": 0.9195575305810397,
"pass@2": 0.9484343771822101,
"pass@4": 0.9708153361563746,
"pass@8": 0.984238780440124,
"pass@16": 0.9897953555580769,
"pass@32": 0.990792748570468,
"pass@64": 0.9908256717392108,
"pass@128": 0.9908256880733946
},
"4": {
"pass@1": 0.7866455078125,
"pass@2": 0.8459907111220479,
"pass@4": 0.8906744697928376,
"pass@8": 0.9215507509441558,
"pass@16": 0.9437763487973065,
"pass@32": 0.9611323349556897,
"pass@64": 0.9735555459387797,
"pass@128": 0.98125
},
"5": {
"pass@1": 0.6709573412698413,
"pass@2": 0.7741130014998127,
"pass@4": 0.8445359746698321,
"pass@8": 0.8894758925880082,
"pass@16": 0.9211739208974751,
"pass@32": 0.9452852732182677,
"pass@64": 0.964295583575878,
"pass@128": 0.9777777777777777
},
"6": {
"pass@1": 0.7365503368263473,
"pass@2": 0.8420378730727522,
"pass@4": 0.9124382115970529,
"pass@8": 0.9505378525143745,
"pass@16": 0.9685954065179547,
"pass@32": 0.97972634565819,
"pass@64": 0.9880378752295537,
"pass@128": 0.9940119760479041
},
"7": {
"pass@1": 0.6175110946745562,
"pass@2": 0.7572351983646276,
"pass@4": 0.8602960354807709,
"pass@8": 0.9199085087926454,
"pass@16": 0.9515635930824008,
"pass@32": 0.9699748728805815,
"pass@64": 0.9825938231042854,
"pass@128": 0.9911242603550295
},
"8": {
"pass@1": 0.5553635817307693,
"pass@2": 0.705602191853422,
"pass@4": 0.821673709956928,
"pass@8": 0.8943235864636814,
"pass@16": 0.9343372725706356,
"pass@32": 0.9560323516975169,
"pass@64": 0.9697434965886538,
"pass@128": 0.9807692307692307
},
"9": {
"pass@1": 0.479137323943662,
"pass@2": 0.6481472496395699,
"pass@4": 0.7957091023833289,
"pass@8": 0.8944526189705332,
"pass@16": 0.9475698851465509,
"pass@32": 0.9725689666299432,
"pass@64": 0.9838555505224045,
"pass@128": 0.9887323943661972
}
}
},
"teachers_in_school": {
"count": 390656,
"correct": 276029,
"answer_accuracy": 0.7065781659567497,
"avg_response_len": 197.2905318233945,
"resp_tokens_sum": 77072730,
"pass_at_k": {
"pass@1": 0.7065781659567497,
"pass@2": 0.80870363986182,
"pass@4": 0.8869682795425502,
"pass@8": 0.9368394808127022,
"pass@16": 0.9653128692761188,
"pass@32": 0.9804199727921247,
"pass@64": 0.9885924403583403,
"pass@128": 0.9934469200524246
},
"per_op_pass_at_k": {
"10": {
"pass@1": 0.4727521088957055,
"pass@2": 0.6345907957345057,
"pass@4": 0.77542852455943,
"pass@8": 0.8752167459860357,
"pass@16": 0.9336091179643451,
"pass@32": 0.9627348671897347,
"pass@64": 0.9780142800175672,
"pass@128": 0.9877300613496932
},
"2": {
"pass@1": 0.9381648936170213,
"pass@2": 0.9569980614125363,
"pass@4": 0.971669399322805,
"pass@8": 0.9823670230919718,
"pass@16": 0.9902618175090221,
"pass@32": 0.9948116541729152,
"pass@64": 0.9965635996372417,
"pass@128": 0.9969604863221885
},
"3": {
"pass@1": 0.950686553030303,
"pass@2": 0.9672959914101645,
"pass@4": 0.9803795730079196,
"pass@8": 0.9893317365210512,
"pass@16": 0.9939045470160155,
"pass@32": 0.9959745105782435,
"pass@64": 0.9968729838687728,
"pass@128": 0.996969696969697
},
"4": {
"pass@1": 0.8468703772189349,
"pass@2": 0.9065033429623076,
"pass@4": 0.9489256611044922,
"pass@8": 0.9743967832425964,
"pass@16": 0.9872230174014897,
"pass@32": 0.9930567852310904,
"pass@64": 0.9965815370797454,
"pass@128": 1.0
},
"5": {
"pass@1": 0.7758605072463768,
"pass@2": 0.8736209774049982,
"pass@4": 0.9324389600756424,
"pass@8": 0.9618868319100985,
"pass@16": 0.9760629639219559,
"pass@32": 0.9825935008857577,
"pass@64": 0.9869077034509552,
"pass@128": 0.991304347826087
},
"6": {
"pass@1": 0.6769340974212035,
"pass@2": 0.7943660740473344,
"pass@4": 0.8786454614018506,
"pass@8": 0.9272978475082277,
"pass@16": 0.9543528148099992,
"pass@32": 0.9711407927719327,
"pass@64": 0.9821259539329217,
"pass@128": 0.9885386819484241
},
"7": {
"pass@1": 0.6066428829479769,
"pass@2": 0.7398836818988667,
"pass@4": 0.8397892167380809,
"pass@8": 0.9042434643738783,
"pass@16": 0.9441212894901903,
"pass@32": 0.96651931919803,
"pass@64": 0.9778479793557311,
"pass@128": 0.9826589595375722
},
"8": {
"pass@1": 0.5825044014084507,
"pass@2": 0.7344803565487412,
"pass@4": 0.8506169114424071,
"pass@8": 0.9214648743029239,
"pass@16": 0.9596192806093881,
"pass@32": 0.9801233610769453,
"pass@64": 0.9908749402461413,
"pass@128": 0.9971830985915493
},
"9": {
"pass@1": 0.5183383233532934,
"pass@2": 0.6750163550851055,
"pass@4": 0.8066507348071007,
"pass@8": 0.8964758234235036,
"pass@16": 0.9496126362729699,
"pass@32": 0.9775149761319307,
"pass@64": 0.9920008501197732,
"pass@128": 1.0
}
}
},
"movie_festival_awards": {
"count": 382336,
"correct": 270491,
"answer_accuracy": 0.7074693463341145,
"avg_response_len": 210.3003536156679,
"resp_tokens_sum": 80405396,
"pass_at_k": {
"pass@1": 0.7074693463341145,
"pass@2": 0.8080907192321637,
"pass@4": 0.8827587837195806,
"pass@8": 0.928954699815554,
"pass@16": 0.9557535134727481,
"pass@32": 0.9719349201304631,
"pass@64": 0.9820513506238909,
"pass@128": 0.9882825577502511
},
"per_op_pass_at_k": {
"10": {
"pass@1": 0.5484141791044777,
"pass@2": 0.7068614848983433,
"pass@4": 0.8289243484489802,
"pass@8": 0.9026957799440277,
"pass@16": 0.9424595065592135,
"pass@32": 0.9669448671204803,
"pass@64": 0.9840754473966935,
"pass@128": 0.9970149253731343
},
"2": {
"pass@1": 0.9351785714285714,
"pass@2": 0.9614377109111365,
"pass@4": 0.9807448331458566,
"pass@8": 0.9900186920873438,
"pass@16": 0.9932031478280128,
"pass@32": 0.994165464267091,
"pass@64": 0.994284838023708,
"pass@128": 0.9942857142857143
},
"3": {
"pass@1": 0.9484784985422741,
"pass@2": 0.9667359421271322,
"pass@4": 0.9812006491171111,
"pass@8": 0.9911249057844892,
"pass@16": 0.9963589159034837,
"pass@32": 0.9986878666696775,
"pass@64": 0.9998071628884445,
"pass@128": 1.0
},
"4": {
"pass@1": 0.7850420321637427,
"pass@2": 0.8495130542892672,
"pass@4": 0.8935691234867573,
"pass@8": 0.9234471775450245,
"pass@16": 0.9452483337671119,
"pass@32": 0.961587906311577,
"pass@64": 0.9729863836696224,
"pass@128": 0.97953216374269
},
"5": {
"pass@1": 0.7065027573529412,
"pass@2": 0.8072114549559978,
"pass@4": 0.8746589903284145,
"pass@8": 0.9123061051506803,
"pass@16": 0.9350173413401953,
"pass@32": 0.9502013517528385,
"pass@64": 0.9608592051459295,
"pass@128": 0.9705882352941176
},
"6": {
"pass@1": 0.6834828470031545,
"pass@2": 0.7923822157778388,
"pass@4": 0.8667003048120562,
"pass@8": 0.9103088471153025,
"pass@16": 0.9358442713049175,
"pass@32": 0.9527734551605721,
"pass@64": 0.9654646330828386,
"pass@128": 0.9747634069400631
},
"7": {
"pass@1": 0.6329855617088608,
"pass@2": 0.7641914494667598,
"pass@4": 0.8574156207135493,
"pass@8": 0.9165753219580909,
"pass@16": 0.9548959002581976,
"pass@32": 0.9780368342011752,
"pass@64": 0.990102927075729,
"pass@128": 0.9968354430379747
},
"8": {
"pass@1": 0.5770457957957958,
"pass@2": 0.7276407805443237,
"pass@4": 0.8416383075989373,
"pass@8": 0.911326672634802,
"pass@16": 0.949508092764589,
"pass@32": 0.9704760825523712,
"pass@64": 0.98276801411379,
"pass@128": 0.987987987987988
},
"9": {
"pass@1": 0.5122588424437299,
"pass@2": 0.6717535509026002,
"pass@4": 0.8050184239429874,
"pass@8": 0.8946679048869003,
"pass@16": 0.9452181368847813,
"pass@32": 0.9728178175087213,
"pass@64": 0.9876158326332224,
"pass@128": 0.9935691318327974
}
}
}
}
},
"ood": {
"answer_accuracy": 0.331778125,
"avg_response_len": 371.70684140625,
"avg_loss": 0.0,
"count": 1280000,
"validation_metrics": {},
"pass_at_k": {
"pass@1": 0.331778125,
"pass@2": 0.4780030634842523,
"pass@4": 0.6261648663948085,
"pass@8": 0.7526011526766907,
"pass@16": 0.8449462991420205,
"pass@32": 0.9051796623764043,
"pass@64": 0.9428432153839094,
"pass@128": 0.9652
},
"per_op_pass_at_k": {
"11": {
"pass@1": 0.4547109375,
"pass@2": 0.6138021653543304,
"pass@4": 0.7549666171728527,
"pass@8": 0.8583315153211275,
"pass@16": 0.9221412824985413,
"pass@32": 0.9570664977233017,
"pass@64": 0.974931983836227,
"pass@128": 0.983
},
"12": {
"pass@1": 0.4180625,
"pass@2": 0.5797405265748027,
"pass@4": 0.7296782709973749,
"pass@8": 0.8443357826368147,
"pass@16": 0.916390867717859,
"pass@32": 0.9551260363971661,
"pass@64": 0.975269380378476,
"pass@128": 0.986
},
"13": {
"pass@1": 0.396984375,
"pass@2": 0.5582675935039371,
"pass@4": 0.7075908911698547,
"pass@8": 0.8218632521719159,
"pass@16": 0.8957610496843468,
"pass@32": 0.9375014501187352,
"pass@64": 0.9603788119235547,
"pass@128": 0.975
},
"14": {
"pass@1": 0.3836953125,
"pass@2": 0.5430013533464566,
"pass@4": 0.6984549793775782,
"pass@8": 0.8231021884341475,
"pass@16": 0.9053910203817964,
"pass@32": 0.9510216257343269,
"pass@64": 0.9741567124841395,
"pass@128": 0.985
},
"15": {
"pass@1": 0.33775,
"pass@2": 0.4967496309055121,
"pass@4": 0.6602598811398573,
"pass@8": 0.7980327584444624,
"pass@16": 0.8912756658908414,
"pass@32": 0.9429084818635887,
"pass@64": 0.9696608164732217,
"pass@128": 0.983
},
"16": {
"pass@1": 0.3182265625,
"pass@2": 0.4695752952755903,
"pass@4": 0.6255005896137982,
"pass@8": 0.7595363695753027,
"pass@16": 0.8578304309643211,
"pass@32": 0.9197597659036819,
"pass@64": 0.9536475067446567,
"pass@128": 0.972
},
"17": {
"pass@1": 0.299875,
"pass@2": 0.4421136811023624,
"pass@4": 0.5927719518185219,
"pass@8": 0.7277104389245667,
"pass@16": 0.8309745449337134,
"pass@32": 0.9007491803788847,
"pass@64": 0.9454100163755238,
"pass@128": 0.972
},
"18": {
"pass@1": 0.272328125,
"pass@2": 0.40941916830708663,
"pass@4": 0.5598332344394451,
"pass@8": 0.6993310814147358,
"pass@16": 0.808673856643445,
"pass@32": 0.8838542581208818,
"pass@64": 0.9322295342493997,
"pass@128": 0.957
},
"19": {
"pass@1": 0.2403671875,
"pass@2": 0.3612985974409448,
"pass@4": 0.49474866122984607,
"pass@8": 0.6234513899075376,
"pass@16": 0.7351839126274962,
"pass@32": 0.8242222274517007,
"pass@64": 0.8913528812708557,
"pass@128": 0.937
},
"20": {
"pass@1": 0.19578125,
"pass@2": 0.3060626230314962,
"pass@4": 0.43784358698912595,
"pass@8": 0.5703167499362239,
"pass@16": 0.6858403600775729,
"pass@32": 0.7795871000716412,
"pass@64": 0.8513945101029146,
"pass@128": 0.902
}
},
"per_op_accuracy": {
"11": 0.4547109375,
"12": 0.4180625,
"13": 0.396984375,
"14": 0.3836953125,
"15": 0.33775,
"16": 0.3182265625,
"17": 0.299875,
"18": 0.272328125,
"19": 0.2403671875,
"20": 0.19578125
},
"per_op_avg_response_len": {
"11": 296.70078125,
"12": 310.4506328125,
"13": 328.7139609375,
"14": 352.013390625,
"15": 373.0260234375,
"16": 381.777359375,
"17": 401.5364765625,
"18": 417.4558203125,
"19": 421.0910859375,
"20": 434.3028828125
},
"per_op_avg_loss": {},
"per_op_length": {
"11": 296.70078125,
"12": 310.4506328125,
"13": 328.7139609375,
"14": 352.013390625,
"15": 373.0260234375,
"16": 381.777359375,
"17": 401.5364765625,
"18": 417.4558203125,
"19": 421.0910859375,
"20": 434.3028828125
},
"per_op_loss": {},
"per_template": {
"crazy_zootopia": {
"count": 430720,
"correct": 141383,
"answer_accuracy": 0.3282480497771174,
"avg_response_len": 353.0143457466568,
"resp_tokens_sum": 152050339,
"pass_at_k": {
"pass@1": 0.3282480497771174,
"pass@2": 0.4742019588515418,
"pass@4": 0.6229426643456395,
"pass@8": 0.7505481103707128,
"pass@16": 0.8438042986957948,
"pass@32": 0.9042307574553091,
"pass@64": 0.9417688787017761,
"pass@128": 0.9643387815750372
},
"per_op_pass_at_k": {
"11": {
"pass@1": 0.4631506728045326,
"pass@2": 0.6252648836742432,
"pass@4": 0.767624272798053,
"pass@8": 0.871077584229325,
"pass@16": 0.9329364153366072,
"pass@32": 0.9639094963103593,
"pass@64": 0.9780315644820233,
"pass@128": 0.9858356940509915
},
"12": {
"pass@1": 0.4075962217514124,
"pass@2": 0.5693932392455183,
"pass@4": 0.7213146841814255,
"pass@8": 0.8371093473559977,
"pass@16": 0.9086267449422752,
"pass@32": 0.9469433243538209,
"pass@64": 0.9686512377816593,
"pass@128": 0.9830508474576272
},
"13": {
"pass@1": 0.39882934952978055,
"pass@2": 0.5654986516673662,
"pass@4": 0.7186619650600091,
"pass@8": 0.8329572629488781,
"pass@16": 0.9032880963070734,
"pass@32": 0.9407221789825072,
"pass@64": 0.9613466943723601,
"pass@128": 0.9749216300940439
},
"14": {
"pass@1": 0.35604069314641745,
"pass@2": 0.5193354919420117,
"pass@4": 0.684745257018106,
"pass@8": 0.8188914601096546,
"pass@16": 0.9064022768205324,
"pass@32": 0.9520687996104888,
"pass@64": 0.9726630069903832,
"pass@128": 0.9813084112149533
},
"15": {
"pass@1": 0.33921152456647397,
"pass@2": 0.4931290820854757,
"pass@4": 0.650143435556827,
"pass@8": 0.7837146243177703,
"pass@16": 0.8784636507395034,
"pass@32": 0.9341449136359978,
"pass@64": 0.9638817286290657,
"pass@128": 0.9797687861271677
},
"16": {
"pass@1": 0.3211945564516129,
"pass@2": 0.47427451104902224,
"pass@4": 0.6338670295245349,
"pass@8": 0.7704789743204787,
"pass@16": 0.8674678402262296,
"pass@32": 0.9269334345131763,
"pass@64": 0.95867323469044,
"pass@128": 0.9774193548387097
},
"17": {
"pass@1": 0.2943686777456647,
"pass@2": 0.43410561080515186,
"pass@4": 0.5843995006404546,
"pass@8": 0.7225977142959461,
"pass@16": 0.8319339455322081,
"pass@32": 0.9085076669393349,
"pass@64": 0.9564128585594077,
"pass@128": 0.976878612716763
},
"18": {
"pass@1": 0.2702678571428571,
"pass@2": 0.40575260123734536,
"pass@4": 0.5552940701162348,
"pass@8": 0.6981102462106233,
"pass@16": 0.8141778003682741,
"pass@32": 0.894818854884761,
"pass@64": 0.9449149724164841,
"pass@128": 0.9685714285714285
},
"19": {
"pass@1": 0.23252158408408408,
"pass@2": 0.34998618204819004,
"pass@4": 0.48075028543729326,
"pass@8": 0.6082667201968596,
"pass@16": 0.7195758859617793,
"pass@32": 0.8085267342570868,
"pass@64": 0.8769663601857598,
"pass@128": 0.9279279279279279
},
"20": {
"pass@1": 0.19352946696696696,
"pass@2": 0.29999401468397513,
"pass@4": 0.42863513513513496,
"pass@8": 0.5593568000768633,
"pass@16": 0.6727429737905991,
"pass@32": 0.763426098355866,
"pass@64": 0.8337823046158129,
"pass@128": 0.8858858858858859
}
}
},
"teachers_in_school": {
"count": 430464,
"correct": 144421,
"answer_accuracy": 0.3355007619684805,
"avg_response_len": 368.40574124665477,
"resp_tokens_sum": 158585409,
"pass_at_k": {
"pass@1": 0.3355007619684805,
"pass@2": 0.4832102067192541,
"pass@4": 0.6323251844300062,
"pass@8": 0.7584816977922026,
"pass@16": 0.8501143874517795,
"pass@32": 0.9098559724700692,
"pass@64": 0.9465408118527427,
"pass@128": 0.967885816235504
},
"per_op_pass_at_k": {
"11": {
"pass@1": 0.4303934487951807,
"pass@2": 0.5927442545773641,
"pass@4": 0.7420111311387282,
"pass@8": 0.851233626656646,
"pass@16": 0.9172232851276387,
"pass@32": 0.9531123039455416,
"pass@64": 0.9715619962195704,
"pass@128": 0.9789156626506024
},
"12": {
"pass@1": 0.41724627742946707,
"pass@2": 0.577324331078913,
"pass@4": 0.7282632558861173,
"pass@8": 0.8475615268998387,
"pass@16": 0.9247642940425248,
"pass@32": 0.9665189848115742,
"pass@64": 0.9858146148658699,
"pass@128": 0.9937304075235109
},
"13": {
"pass@1": 0.3948266806722689,
"pass@2": 0.5571427882176495,
"pass@4": 0.7088043327567247,
"pass@8": 0.8258372669093875,
"pass@16": 0.9026431000892041,
"pass@32": 0.9463133172020857,
"pass@64": 0.9691138082317794,
"pass@128": 0.9831932773109243
},
"14": {
"pass@1": 0.41015625,
"pass@2": 0.5688616636736198,
"pass@4": 0.7169494355968666,
"pass@8": 0.831644961695096,
"pass@16": 0.9084661438307753,
"pass@32": 0.9549772171257439,
"pass@64": 0.9812690835166658,
"pass@128": 0.9941520467836257
},
"15": {
"pass@1": 0.33780776515151517,
"pass@2": 0.4990828561202573,
"pass@4": 0.6665392868505067,
"pass@8": 0.807065398160388,
"pass@16": 0.8994904127312967,
"pass@32": 0.9489088718389327,
"pass@64": 0.9717879055264091,
"pass@128": 0.9787878787878788
},
"16": {
"pass@1": 0.32298344017094016,
"pass@2": 0.4738822711263657,
"pass@4": 0.6295656763524213,
"pass@8": 0.7637132042842444,
"pass@16": 0.8619682864031663,
"pass@32": 0.9226160339647616,
"pass@64": 0.9550762847040853,
"pass@128": 0.9743589743589743
},
"17": {
"pass@1": 0.32038528726708076,
"pass@2": 0.4652963301462315,
"pass@4": 0.6150197741198496,
"pass@8": 0.7468171297086604,
"pass@16": 0.8433732629472633,
"pass@32": 0.9032106328795099,
"pass@64": 0.9403173018208404,
"pass@128": 0.968944099378882
},
"18": {
"pass@1": 0.2850873161764706,
"pass@2": 0.4292677454840204,
"pass@4": 0.5829545498908223,
"pass@8": 0.7183212578697612,
"pass@16": 0.8203104066913215,
"pass@32": 0.8889514779071954,
"pass@64": 0.932731144763619,
"pass@128": 0.9558823529411765
},
"19": {
"pass@1": 0.24262927827380953,
"pass@2": 0.3626660925196849,
"pass@4": 0.4944864068330747,
"pass@8": 0.621680543117198,
"pass@16": 0.7348198506994026,
"pass@32": 0.8285702067226429,
"pass@64": 0.8994453819696483,
"pass@128": 0.9434523809523809
},
"20": {
"pass@1": 0.19344124251497005,
"pass@2": 0.3052857130227736,
"pass@4": 0.43797066861777034,
"pass@8": 0.5705444770411404,
"pass@16": 0.6877959075104455,
"pass@32": 0.7850349116495576,
"pass@64": 0.8579923825438611,
"pass@128": 0.907185628742515
}
}
},
"movie_festival_awards": {
"count": 418816,
"correct": 138872,
"answer_accuracy": 0.3315823655256724,
"avg_response_len": 394.32354303560516,
"resp_tokens_sum": 165149009,
"pass_at_k": {
"pass@1": 0.3315823655256724,
"pass@2": 0.4765602439212221,
"pass@4": 0.6231470058640338,
"pass@8": 0.7486684552855316,
"pass@16": 0.8408089368301784,
"pass@32": 0.9013491716106101,
"pass@64": 0.940147654873669,
"pass@128": 0.9633251833740831
},
"per_op_pass_at_k": {
"11": {
"pass@1": 0.4708829365079365,
"pass@2": 0.6231510123734529,
"pass@4": 0.7544366772605811,
"pass@8": 0.851528774724346,
"pass@16": 0.9152272927693456,
"pass@32": 0.9535655892565871,
"pass@64": 0.9750103454894454,
"pass@128": 0.9841269841269841
},
"12": {
"pass@1": 0.43018922018348627,
"pass@2": 0.593299260757543,
"pass@4": 0.7401128262063567,
"pass@8": 0.849012069087901,
"pass@16": 0.916627492993055,
"pass@32": 0.9528701633670399,
"pass@64": 0.9721467280169921,
"pass@128": 0.981651376146789
},
"13": {
"pass@1": 0.39754533179012347,
"pass@2": 0.5523874945319335,
"pass@4": 0.6953536343258018,
"pass@8": 0.8065616697672022,
"pass@16": 0.8807671612053861,
"pass@32": 0.9246210517968243,
"pass@64": 0.9498011940741536,
"pass@128": 0.9660493827160493
},
"14": {
"pass@1": 0.38318341988130566,
"pass@2": 0.5392996185658544,
"pass@4": 0.6927449403579738,
"pass@8": 0.8184434802350886,
"pass@16": 0.9013070276922327,
"pass@32": 0.9460098896212308,
"pass@64": 0.9683616043843487,
"pass@128": 0.9792284866468842
},
"15": {
"pass@1": 0.3361304012345679,
"pass@2": 0.4982395863711481,
"pass@4": 0.6646675548658267,
"pass@8": 0.8041232007332922,
"pass@16": 0.8965907609063177,
"pass@32": 0.9461555988848293,
"pass@64": 0.9736658319254623,
"pass@128": 0.9907407407407407
},
"16": {
"pass@1": 0.3105872050147493,
"pass@2": 0.4608186421387594,
"pass@4": 0.6136408792374404,
"pass@8": 0.7452051705964161,
"pass@16": 0.844733132645075,
"pass@32": 0.9102423990647945,
"pass@64": 0.9475723541577755,
"pass@128": 0.9646017699115044
},
"17": {
"pass@1": 0.28572100903614456,
"pass@2": 0.4279750646285927,
"pass@4": 0.5799197509949807,
"pass@8": 0.7145075723252433,
"pass@16": 0.8179494250317864,
"pass@32": 0.8902762163574444,
"pass@64": 0.9388825184567935,
"pass@128": 0.9698795180722891
},
"18": {
"pass@1": 0.26066028225806454,
"pass@2": 0.39178943357886703,
"pass@4": 0.5395992352770422,
"pass@8": 0.6798815082751558,
"pass@16": 0.7896970588371004,
"pass@32": 0.8658843755573179,
"pass@64": 0.9173571118838663,
"pass@128": 0.9451612903225807
},
"19": {
"pass@1": 0.24596393504531722,
"pass@2": 0.37129121369269935,
"pass@4": 0.5090978352970231,
"pass@8": 0.6405254066302252,
"pass@16": 0.7512558089644261,
"pass@32": 0.8355988987470783,
"pass@64": 0.8976115860640348,
"pass@128": 0.9395770392749244
},
"20": {
"pass@1": 0.20038006756756757,
"pass@2": 0.3129104744508288,
"pass@4": 0.44692457558796145,
"pass@8": 0.5810482888254881,
"pass@16": 0.6969763264168647,
"pass@32": 0.7902839304149739,
"pass@64": 0.8623890297183104,
"pass@128": 0.9129129129129129
}
}
}
}
},
"total": {
"answer_accuracy": 0.5064206414473684,
"avg_loss": 0.0,
"count": 2432000,
"validation_metrics": {
"id": {},
"ood": {}
},
"pass_at_k": {
"pass@1": 0.5064206414473684,
"pass@2": 0.6320177553874659,
"pass@4": 0.7468917626398424,
"pass@8": 0.8366322354900857,
"pass@16": 0.8985551069241822,
"pass@32": 0.9378755395443024,
"pass@64": 0.9622731145890642,
"pass@128": 0.9768947368421053
},
"per_op_pass_at_k": {
"10": {
"pass@1": 0.5105703125,
"pass@2": 0.6699938484251962,
"pass@4": 0.7991659679415073,
"pass@8": 0.8847154633623784,
"pass@16": 0.9347854223296508,
"pass@32": 0.9632970265066139,
"pass@64": 0.980442548083157,
"pass@128": 0.992
},
"2": {
"pass@1": 0.935890625,
"pass@2": 0.9592861712598416,
"pass@4": 0.9768458330521185,
"pass@8": 0.9867971535992609,
"pass@16": 0.9919445464167224,
"pass@32": 0.9942186611862515,
"pass@64": 0.9948690786426989,
"pass@128": 0.995
},
"3": {
"pass@1": 0.93975,
"pass@2": 0.9609361466535429,
"pass@4": 0.9775336966629172,
"pass@8": 0.9882813969399472,
"pass@16": 0.9934026899376711,
"pass@32": 0.9952107555410625,
"pass@64": 0.9959019362061534,
"pass@128": 0.996
},
"4": {
"pass@1": 0.806453125,
"pass@2": 0.8676486220472444,
"pass@4": 0.911353344019498,
"pass@8": 0.9400612877585252,
"pass@16": 0.9589647416451935,
"pass@32": 0.9720786045524892,
"pass@64": 0.9811436774483744,
"pass@128": 0.987
},
"5": {
"pass@1": 0.719234375,
"pass@2": 0.8196967273622047,
"pass@4": 0.8851043299587543,
"pass@8": 0.9222199389254376,
"pass@16": 0.9448174036914444,
"pass@32": 0.9598280784653056,
"pass@64": 0.9709283962665971,
"pass@128": 0.98
},
"6": {
"pass@1": 0.698921875,
"pass@2": 0.809659571850394,
"pass@4": 0.8861456253280843,
"pass@8": 0.9296744960557235,
"pass@16": 0.9532426321493441,
"pass@32": 0.9681859214131414,
"pass@64": 0.9788188969365212,
"pass@128": 0.986
},
"7": {
"pass@1": 0.618640625,
"pass@2": 0.7534297490157486,
"pass@4": 0.8522904651293589,
"pass@8": 0.9134351163840331,
"pass@16": 0.9500415651070467,
"pass@32": 0.9713268310837263,
"pass@64": 0.9833246380222623,
"pass@128": 0.99
},
"8": {
"pass@1": 0.57221875,
"pass@2": 0.7231927903543292,
"pass@4": 0.8385967574990625,
"pass@8": 0.909620771341596,
"pass@16": 0.9483642685489777,
"pass@32": 0.9693944224018802,
"pass@64": 0.9815823234229324,
"pass@128": 0.989
},
"9": {
"pass@1": 0.50253125,
"pass@2": 0.6644630905511801,
"pass@4": 0.8022588066179234,
"pass@8": 0.8951953231778146,
"pass@16": 0.9475207703133638,
"pass@32": 0.9742983264269067,
"pass@64": 0.9877455283243902,
"pass@128": 0.994
},
"11": {
"pass@1": 0.4547109375,
"pass@2": 0.6138021653543304,
"pass@4": 0.7549666171728527,
"pass@8": 0.8583315153211275,
"pass@16": 0.9221412824985413,
"pass@32": 0.9570664977233017,
"pass@64": 0.974931983836227,
"pass@128": 0.983
},
"12": {
"pass@1": 0.4180625,
"pass@2": 0.5797405265748027,
"pass@4": 0.7296782709973749,
"pass@8": 0.8443357826368147,
"pass@16": 0.916390867717859,
"pass@32": 0.9551260363971661,
"pass@64": 0.975269380378476,
"pass@128": 0.986
},
"13": {
"pass@1": 0.396984375,
"pass@2": 0.5582675935039371,
"pass@4": 0.7075908911698547,
"pass@8": 0.8218632521719159,
"pass@16": 0.8957610496843468,
"pass@32": 0.9375014501187352,
"pass@64": 0.9603788119235547,
"pass@128": 0.975
},
"14": {
"pass@1": 0.3836953125,
"pass@2": 0.5430013533464566,
"pass@4": 0.6984549793775782,
"pass@8": 0.8231021884341475,
"pass@16": 0.9053910203817964,
"pass@32": 0.9510216257343269,
"pass@64": 0.9741567124841395,
"pass@128": 0.985
},
"15": {
"pass@1": 0.33775,
"pass@2": 0.4967496309055121,
"pass@4": 0.6602598811398573,
"pass@8": 0.7980327584444624,
"pass@16": 0.8912756658908414,
"pass@32": 0.9429084818635887,
"pass@64": 0.9696608164732217,
"pass@128": 0.983
},
"16": {
"pass@1": 0.3182265625,
"pass@2": 0.4695752952755903,
"pass@4": 0.6255005896137982,
"pass@8": 0.7595363695753027,
"pass@16": 0.8578304309643211,
"pass@32": 0.9197597659036819,
"pass@64": 0.9536475067446567,
"pass@128": 0.972
},
"17": {
"pass@1": 0.299875,
"pass@2": 0.4421136811023624,
"pass@4": 0.5927719518185219,
"pass@8": 0.7277104389245667,
"pass@16": 0.8309745449337134,
"pass@32": 0.9007491803788847,
"pass@64": 0.9454100163755238,
"pass@128": 0.972
},
"18": {
"pass@1": 0.272328125,
"pass@2": 0.40941916830708663,
"pass@4": 0.5598332344394451,
"pass@8": 0.6993310814147358,
"pass@16": 0.808673856643445,
"pass@32": 0.8838542581208818,
"pass@64": 0.9322295342493997,
"pass@128": 0.957
},
"19": {
"pass@1": 0.2403671875,
"pass@2": 0.3612985974409448,
"pass@4": 0.49474866122984607,
"pass@8": 0.6234513899075376,
"pass@16": 0.7351839126274962,
"pass@32": 0.8242222274517007,
"pass@64": 0.8913528812708557,
"pass@128": 0.937
},
"20": {
"pass@1": 0.19578125,
"pass@2": 0.3060626230314962,
"pass@4": 0.43784358698912595,
"pass@8": 0.5703167499362239,
"pass@16": 0.6858403600775729,
"pass@32": 0.7795871000716412,
"pass@64": 0.8513945101029146,
"pass@128": 0.902
}
},
"per_op_accuracy": {
"10": 0.5105703125,
"2": 0.935890625,
"3": 0.93975,
"4": 0.806453125,
"5": 0.719234375,
"6": 0.698921875,
"7": 0.618640625,
"8": 0.57221875,
"9": 0.50253125,
"11": 0.4547109375,
"12": 0.4180625,
"13": 0.396984375,
"14": 0.3836953125,
"15": 0.33775,
"16": 0.3182265625,
"17": 0.299875,
"18": 0.272328125,
"19": 0.2403671875,
"20": 0.19578125
},
"per_op_avg_response_len": {
"10": 280.0350625,
"2": 116.76371875,
"3": 149.778203125,
"4": 158.538859375,
"5": 173.8068046875,
"6": 193.58321875,
"7": 222.0638046875,
"8": 240.2696328125,
"9": 255.7865234375,
"11": 296.70078125,
"12": 310.4506328125,
"13": 328.7139609375,
"14": 352.013390625,
"15": 373.0260234375,
"16": 381.777359375,
"17": 401.5364765625,
"18": 417.4558203125,
"19": 421.0910859375,
"20": 434.3028828125
},
"per_op_avg_loss": {},
"per_op_length": {
"10": 280.0350625,
"2": 116.76371875,
"3": 149.778203125,
"4": 158.538859375,
"5": 173.8068046875,
"6": 193.58321875,
"7": 222.0638046875,
"8": 240.2696328125,
"9": 255.7865234375,
"11": 296.70078125,
"12": 310.4506328125,
"13": 328.7139609375,
"14": 352.013390625,
"15": 373.0260234375,
"16": 381.777359375,
"17": 401.5364765625,
"18": 417.4558203125,
"19": 421.0910859375,
"20": 434.3028828125
},
"per_op_loss": {},
"per_template": {
"crazy_zootopia": {
"count": 809728,
"correct": 401802,
"answer_accuracy": 0.49621848324375595,
"avg_response_len": 276.35492288768575,
"resp_tokens_sum": 223772319,
"pass_at_k": {
"pass@1": 0.49621848324375595,
"pass@2": 0.6231529911240028,
"pass@4": 0.740067849446409,
"pass@8": 0.8317378367298127,
"pass@16": 0.8949596717478773,
"pass@32": 0.9350559220713367,
"pass@64": 0.9600439120925355,
"pass@128": 0.9753398672146696
},
"per_op_pass_at_k": {
"10": {
"pass@1": 0.5095409292035398,
"pass@2": 0.6676066418135783,
"pass@4": 0.792585876710101,
"pass@8": 0.8760817636863799,
"pass@16": 0.9283330831148673,
"pass@32": 0.9602328298448352,
"pass@64": 0.9791876634794598,
"pass@128": 0.9911504424778761
},
"2": {
"pass@1": 0.9343360591900312,
"pass@2": 0.9592853901439887,
"pass@4": 0.9779000282674944,
"pass@8": 0.9878251114374832,
"pass@16": 0.9922969056587208,
"pass@32": 0.9936688924295337,
"pass@64": 0.9937693490770984,
"pass@128": 0.9937694704049844
},
"3": {
"pass@1": 0.9195575305810397,
"pass@2": 0.9484343771822101,
"pass@4": 0.9708153361563746,
"pass@8": 0.984238780440124,
"pass@16": 0.9897953555580769,
"pass@32": 0.990792748570468,
"pass@64": 0.9908256717392108,
"pass@128": 0.9908256880733946
},
"4": {
"pass@1": 0.7866455078125,
"pass@2": 0.8459907111220479,
"pass@4": 0.8906744697928376,
"pass@8": 0.9215507509441558,
"pass@16": 0.9437763487973065,
"pass@32": 0.9611323349556897,
"pass@64": 0.9735555459387797,
"pass@128": 0.98125
},
"5": {
"pass@1": 0.6709573412698413,
"pass@2": 0.7741130014998127,
"pass@4": 0.8445359746698321,
"pass@8": 0.8894758925880082,
"pass@16": 0.9211739208974751,
"pass@32": 0.9452852732182677,
"pass@64": 0.964295583575878,
"pass@128": 0.9777777777777777
},
"6": {
"pass@1": 0.7365503368263473,
"pass@2": 0.8420378730727522,
"pass@4": 0.9124382115970529,
"pass@8": 0.9505378525143745,
"pass@16": 0.9685954065179547,
"pass@32": 0.97972634565819,
"pass@64": 0.9880378752295537,
"pass@128": 0.9940119760479041
},
"7": {
"pass@1": 0.6175110946745562,
"pass@2": 0.7572351983646276,
"pass@4": 0.8602960354807709,
"pass@8": 0.9199085087926454,
"pass@16": 0.9515635930824008,
"pass@32": 0.9699748728805815,
"pass@64": 0.9825938231042854,
"pass@128": 0.9911242603550295
},
"8": {
"pass@1": 0.5553635817307693,
"pass@2": 0.705602191853422,
"pass@4": 0.821673709956928,
"pass@8": 0.8943235864636814,
"pass@16": 0.9343372725706356,
"pass@32": 0.9560323516975169,
"pass@64": 0.9697434965886538,
"pass@128": 0.9807692307692307
},
"9": {
"pass@1": 0.479137323943662,
"pass@2": 0.6481472496395699,
"pass@4": 0.7957091023833289,
"pass@8": 0.8944526189705332,
"pass@16": 0.9475698851465509,
"pass@32": 0.9725689666299432,
"pass@64": 0.9838555505224045,
"pass@128": 0.9887323943661972
},
"11": {
"pass@1": 0.4631506728045326,
"pass@2": 0.6252648836742432,
"pass@4": 0.767624272798053,
"pass@8": 0.871077584229325,
"pass@16": 0.9329364153366072,
"pass@32": 0.9639094963103593,
"pass@64": 0.9780315644820233,
"pass@128": 0.9858356940509915
},
"12": {
"pass@1": 0.4075962217514124,
"pass@2": 0.5693932392455183,
"pass@4": 0.7213146841814255,
"pass@8": 0.8371093473559977,
"pass@16": 0.9086267449422752,
"pass@32": 0.9469433243538209,
"pass@64": 0.9686512377816593,
"pass@128": 0.9830508474576272
},
"13": {
"pass@1": 0.39882934952978055,
"pass@2": 0.5654986516673662,
"pass@4": 0.7186619650600091,
"pass@8": 0.8329572629488781,
"pass@16": 0.9032880963070734,
"pass@32": 0.9407221789825072,
"pass@64": 0.9613466943723601,
"pass@128": 0.9749216300940439
},
"14": {
"pass@1": 0.35604069314641745,
"pass@2": 0.5193354919420117,
"pass@4": 0.684745257018106,
"pass@8": 0.8188914601096546,
"pass@16": 0.9064022768205324,
"pass@32": 0.9520687996104888,
"pass@64": 0.9726630069903832,
"pass@128": 0.9813084112149533
},
"15": {
"pass@1": 0.33921152456647397,
"pass@2": 0.4931290820854757,
"pass@4": 0.650143435556827,
"pass@8": 0.7837146243177703,
"pass@16": 0.8784636507395034,
"pass@32": 0.9341449136359978,
"pass@64": 0.9638817286290657,
"pass@128": 0.9797687861271677
},
"16": {
"pass@1": 0.3211945564516129,
"pass@2": 0.47427451104902224,
"pass@4": 0.6338670295245349,
"pass@8": 0.7704789743204787,
"pass@16": 0.8674678402262296,
"pass@32": 0.9269334345131763,
"pass@64": 0.95867323469044,
"pass@128": 0.9774193548387097
},
"17": {
"pass@1": 0.2943686777456647,
"pass@2": 0.43410561080515186,
"pass@4": 0.5843995006404546,
"pass@8": 0.7225977142959461,
"pass@16": 0.8319339455322081,
"pass@32": 0.9085076669393349,
"pass@64": 0.9564128585594077,
"pass@128": 0.976878612716763
},
"18": {
"pass@1": 0.2702678571428571,
"pass@2": 0.40575260123734536,
"pass@4": 0.5552940701162348,
"pass@8": 0.6981102462106233,
"pass@16": 0.8141778003682741,
"pass@32": 0.894818854884761,
"pass@64": 0.9449149724164841,
"pass@128": 0.9685714285714285
},
"19": {
"pass@1": 0.23252158408408408,
"pass@2": 0.34998618204819004,
"pass@4": 0.48075028543729326,
"pass@8": 0.6082667201968596,
"pass@16": 0.7195758859617793,
"pass@32": 0.8085267342570868,
"pass@64": 0.8769663601857598,
"pass@128": 0.9279279279279279
},
"20": {
"pass@1": 0.19352946696696696,
"pass@2": 0.29999401468397513,
"pass@4": 0.42863513513513496,
"pass@8": 0.5593568000768633,
"pass@16": 0.6727429737905991,
"pass@32": 0.763426098355866,
"pass@64": 0.8337823046158129,
"pass@128": 0.8858858858858859
}
}
},
"teachers_in_school": {
"count": 821120,
"correct": 420450,
"answer_accuracy": 0.5120445245518317,
"avg_response_len": 286.99597988113794,
"resp_tokens_sum": 235658139,
"pass_at_k": {
"pass@1": 0.5120445245518317,
"pass@2": 0.6380669421753976,
"pass@4": 0.7534741674827613,
"pass@8": 0.8433371855207411,
"pass@16": 0.904921209981468,
"pass@32": 0.9434274968633595,
"pass@64": 0.9665472920084971,
"pass@128": 0.9800467653936087
},
"per_op_pass_at_k": {
"10": {
"pass@1": 0.4727521088957055,
"pass@2": 0.6345907957345057,
"pass@4": 0.77542852455943,
"pass@8": 0.8752167459860357,
"pass@16": 0.9336091179643451,
"pass@32": 0.9627348671897347,
"pass@64": 0.9780142800175672,
"pass@128": 0.9877300613496932
},
"2": {
"pass@1": 0.9381648936170213,
"pass@2": 0.9569980614125363,
"pass@4": 0.971669399322805,
"pass@8": 0.9823670230919718,
"pass@16": 0.9902618175090221,
"pass@32": 0.9948116541729152,
"pass@64": 0.9965635996372417,
"pass@128": 0.9969604863221885
},
"3": {
"pass@1": 0.950686553030303,
"pass@2": 0.9672959914101645,
"pass@4": 0.9803795730079196,
"pass@8": 0.9893317365210512,
"pass@16": 0.9939045470160155,
"pass@32": 0.9959745105782435,
"pass@64": 0.9968729838687728,
"pass@128": 0.996969696969697
},
"4": {
"pass@1": 0.8468703772189349,
"pass@2": 0.9065033429623076,
"pass@4": 0.9489256611044922,
"pass@8": 0.9743967832425964,
"pass@16": 0.9872230174014897,
"pass@32": 0.9930567852310904,
"pass@64": 0.9965815370797454,
"pass@128": 1.0
},
"5": {
"pass@1": 0.7758605072463768,
"pass@2": 0.8736209774049982,
"pass@4": 0.9324389600756424,
"pass@8": 0.9618868319100985,
"pass@16": 0.9760629639219559,
"pass@32": 0.9825935008857577,
"pass@64": 0.9869077034509552,
"pass@128": 0.991304347826087
},
"6": {
"pass@1": 0.6769340974212035,
"pass@2": 0.7943660740473344,
"pass@4": 0.8786454614018506,
"pass@8": 0.9272978475082277,
"pass@16": 0.9543528148099992,
"pass@32": 0.9711407927719327,
"pass@64": 0.9821259539329217,
"pass@128": 0.9885386819484241
},
"7": {
"pass@1": 0.6066428829479769,
"pass@2": 0.7398836818988667,
"pass@4": 0.8397892167380809,
"pass@8": 0.9042434643738783,
"pass@16": 0.9441212894901903,
"pass@32": 0.96651931919803,
"pass@64": 0.9778479793557311,
"pass@128": 0.9826589595375722
},
"8": {
"pass@1": 0.5825044014084507,
"pass@2": 0.7344803565487412,
"pass@4": 0.8506169114424071,
"pass@8": 0.9214648743029239,
"pass@16": 0.9596192806093881,
"pass@32": 0.9801233610769453,
"pass@64": 0.9908749402461413,
"pass@128": 0.9971830985915493
},
"9": {
"pass@1": 0.5183383233532934,
"pass@2": 0.6750163550851055,
"pass@4": 0.8066507348071007,
"pass@8": 0.8964758234235036,
"pass@16": 0.9496126362729699,
"pass@32": 0.9775149761319307,
"pass@64": 0.9920008501197732,
"pass@128": 1.0
},
"11": {
"pass@1": 0.4303934487951807,
"pass@2": 0.5927442545773641,
"pass@4": 0.7420111311387282,
"pass@8": 0.851233626656646,
"pass@16": 0.9172232851276387,
"pass@32": 0.9531123039455416,
"pass@64": 0.9715619962195704,
"pass@128": 0.9789156626506024
},
"12": {
"pass@1": 0.41724627742946707,
"pass@2": 0.577324331078913,
"pass@4": 0.7282632558861173,
"pass@8": 0.8475615268998387,
"pass@16": 0.9247642940425248,
"pass@32": 0.9665189848115742,
"pass@64": 0.9858146148658699,
"pass@128": 0.9937304075235109
},
"13": {
"pass@1": 0.3948266806722689,
"pass@2": 0.5571427882176495,
"pass@4": 0.7088043327567247,
"pass@8": 0.8258372669093875,
"pass@16": 0.9026431000892041,
"pass@32": 0.9463133172020857,
"pass@64": 0.9691138082317794,
"pass@128": 0.9831932773109243
},
"14": {
"pass@1": 0.41015625,
"pass@2": 0.5688616636736198,
"pass@4": 0.7169494355968666,
"pass@8": 0.831644961695096,
"pass@16": 0.9084661438307753,
"pass@32": 0.9549772171257439,
"pass@64": 0.9812690835166658,
"pass@128": 0.9941520467836257
},
"15": {
"pass@1": 0.33780776515151517,
"pass@2": 0.4990828561202573,
"pass@4": 0.6665392868505067,
"pass@8": 0.807065398160388,
"pass@16": 0.8994904127312967,
"pass@32": 0.9489088718389327,
"pass@64": 0.9717879055264091,
"pass@128": 0.9787878787878788
},
"16": {
"pass@1": 0.32298344017094016,
"pass@2": 0.4738822711263657,
"pass@4": 0.6295656763524213,
"pass@8": 0.7637132042842444,
"pass@16": 0.8619682864031663,
"pass@32": 0.9226160339647616,
"pass@64": 0.9550762847040853,
"pass@128": 0.9743589743589743
},
"17": {
"pass@1": 0.32038528726708076,
"pass@2": 0.4652963301462315,
"pass@4": 0.6150197741198496,
"pass@8": 0.7468171297086604,
"pass@16": 0.8433732629472633,
"pass@32": 0.9032106328795099,
"pass@64": 0.9403173018208404,
"pass@128": 0.968944099378882
},
"18": {
"pass@1": 0.2850873161764706,
"pass@2": 0.4292677454840204,
"pass@4": 0.5829545498908223,
"pass@8": 0.7183212578697612,
"pass@16": 0.8203104066913215,
"pass@32": 0.8889514779071954,
"pass@64": 0.932731144763619,
"pass@128": 0.9558823529411765
},
"19": {
"pass@1": 0.24262927827380953,
"pass@2": 0.3626660925196849,
"pass@4": 0.4944864068330747,
"pass@8": 0.621680543117198,
"pass@16": 0.7348198506994026,
"pass@32": 0.8285702067226429,
"pass@64": 0.8994453819696483,
"pass@128": 0.9434523809523809
},
"20": {
"pass@1": 0.19344124251497005,
"pass@2": 0.3052857130227736,
"pass@4": 0.43797066861777034,
"pass@8": 0.5705444770411404,
"pass@16": 0.6877959075104455,
"pass@32": 0.7850349116495576,
"pass@64": 0.8579923825438611,
"pass@128": 0.907185628742515
}
}
},
"movie_festival_awards": {
"count": 801152,
"correct": 409363,
"answer_accuracy": 0.5109679561431538,
"avg_response_len": 306.50164388280876,
"resp_tokens_sum": 245554405,
"pass_at_k": {
"pass@1": 0.5109679561431538,
"pass@2": 0.6347774558965905,
"pass@4": 0.7470422575742857,
"pass@8": 0.8347069618219127,
"pass@16": 0.8956642572378208,
"pass@32": 0.9350350049432259,
"pass@64": 0.9601454722895479,
"pass@128": 0.975235660648666
},
"per_op_pass_at_k": {
"10": {
"pass@1": 0.5484141791044777,
"pass@2": 0.7068614848983433,
"pass@4": 0.8289243484489802,
"pass@8": 0.9026957799440277,
"pass@16": 0.9424595065592135,
"pass@32": 0.9669448671204803,
"pass@64": 0.9840754473966935,
"pass@128": 0.9970149253731343
},
"2": {
"pass@1": 0.9351785714285714,
"pass@2": 0.9614377109111365,
"pass@4": 0.9807448331458566,
"pass@8": 0.9900186920873438,
"pass@16": 0.9932031478280128,
"pass@32": 0.994165464267091,
"pass@64": 0.994284838023708,
"pass@128": 0.9942857142857143
},
"3": {
"pass@1": 0.9484784985422741,
"pass@2": 0.9667359421271322,
"pass@4": 0.9812006491171111,
"pass@8": 0.9911249057844892,
"pass@16": 0.9963589159034837,
"pass@32": 0.9986878666696775,
"pass@64": 0.9998071628884445,
"pass@128": 1.0
},
"4": {
"pass@1": 0.7850420321637427,
"pass@2": 0.8495130542892672,
"pass@4": 0.8935691234867573,
"pass@8": 0.9234471775450245,
"pass@16": 0.9452483337671119,
"pass@32": 0.961587906311577,
"pass@64": 0.9729863836696224,
"pass@128": 0.97953216374269
},
"5": {
"pass@1": 0.7065027573529412,
"pass@2": 0.8072114549559978,
"pass@4": 0.8746589903284145,
"pass@8": 0.9123061051506803,
"pass@16": 0.9350173413401953,
"pass@32": 0.9502013517528385,
"pass@64": 0.9608592051459295,
"pass@128": 0.9705882352941176
},
"6": {
"pass@1": 0.6834828470031545,
"pass@2": 0.7923822157778388,
"pass@4": 0.8667003048120562,
"pass@8": 0.9103088471153025,
"pass@16": 0.9358442713049175,
"pass@32": 0.9527734551605721,
"pass@64": 0.9654646330828386,
"pass@128": 0.9747634069400631
},
"7": {
"pass@1": 0.6329855617088608,
"pass@2": 0.7641914494667598,
"pass@4": 0.8574156207135493,
"pass@8": 0.9165753219580909,
"pass@16": 0.9548959002581976,
"pass@32": 0.9780368342011752,
"pass@64": 0.990102927075729,
"pass@128": 0.9968354430379747
},
"8": {
"pass@1": 0.5770457957957958,
"pass@2": 0.7276407805443237,
"pass@4": 0.8416383075989373,
"pass@8": 0.911326672634802,
"pass@16": 0.949508092764589,
"pass@32": 0.9704760825523712,
"pass@64": 0.98276801411379,
"pass@128": 0.987987987987988
},
"9": {
"pass@1": 0.5122588424437299,
"pass@2": 0.6717535509026002,
"pass@4": 0.8050184239429874,
"pass@8": 0.8946679048869003,
"pass@16": 0.9452181368847813,
"pass@32": 0.9728178175087213,
"pass@64": 0.9876158326332224,
"pass@128": 0.9935691318327974
},
"11": {
"pass@1": 0.4708829365079365,
"pass@2": 0.6231510123734529,
"pass@4": 0.7544366772605811,
"pass@8": 0.851528774724346,
"pass@16": 0.9152272927693456,
"pass@32": 0.9535655892565871,
"pass@64": 0.9750103454894454,
"pass@128": 0.9841269841269841
},
"12": {
"pass@1": 0.43018922018348627,
"pass@2": 0.593299260757543,
"pass@4": 0.7401128262063567,
"pass@8": 0.849012069087901,
"pass@16": 0.916627492993055,
"pass@32": 0.9528701633670399,
"pass@64": 0.9721467280169921,
"pass@128": 0.981651376146789
},
"13": {
"pass@1": 0.39754533179012347,
"pass@2": 0.5523874945319335,
"pass@4": 0.6953536343258018,
"pass@8": 0.8065616697672022,
"pass@16": 0.8807671612053861,
"pass@32": 0.9246210517968243,
"pass@64": 0.9498011940741536,
"pass@128": 0.9660493827160493
},
"14": {
"pass@1": 0.38318341988130566,
"pass@2": 0.5392996185658544,
"pass@4": 0.6927449403579738,
"pass@8": 0.8184434802350886,
"pass@16": 0.9013070276922327,
"pass@32": 0.9460098896212308,
"pass@64": 0.9683616043843487,
"pass@128": 0.9792284866468842
},
"15": {
"pass@1": 0.3361304012345679,
"pass@2": 0.4982395863711481,
"pass@4": 0.6646675548658267,
"pass@8": 0.8041232007332922,
"pass@16": 0.8965907609063177,
"pass@32": 0.9461555988848293,
"pass@64": 0.9736658319254623,
"pass@128": 0.9907407407407407
},
"16": {
"pass@1": 0.3105872050147493,
"pass@2": 0.4608186421387594,
"pass@4": 0.6136408792374404,
"pass@8": 0.7452051705964161,
"pass@16": 0.844733132645075,
"pass@32": 0.9102423990647945,
"pass@64": 0.9475723541577755,
"pass@128": 0.9646017699115044
},
"17": {
"pass@1": 0.28572100903614456,
"pass@2": 0.4279750646285927,
"pass@4": 0.5799197509949807,
"pass@8": 0.7145075723252433,
"pass@16": 0.8179494250317864,
"pass@32": 0.8902762163574444,
"pass@64": 0.9388825184567935,
"pass@128": 0.9698795180722891
},
"18": {
"pass@1": 0.26066028225806454,
"pass@2": 0.39178943357886703,
"pass@4": 0.5395992352770422,
"pass@8": 0.6798815082751558,
"pass@16": 0.7896970588371004,
"pass@32": 0.8658843755573179,
"pass@64": 0.9173571118838663,
"pass@128": 0.9451612903225807
},
"19": {
"pass@1": 0.24596393504531722,
"pass@2": 0.37129121369269935,
"pass@4": 0.5090978352970231,
"pass@8": 0.6405254066302252,
"pass@16": 0.7512558089644261,
"pass@32": 0.8355988987470783,
"pass@64": 0.8976115860640348,
"pass@128": 0.9395770392749244
},
"20": {
"pass@1": 0.20038006756756757,
"pass@2": 0.3129104744508288,
"pass@4": 0.44692457558796145,
"pass@8": 0.5810482888254881,
"pass@16": 0.6969763264168647,
"pass@32": 0.7902839304149739,
"pass@64": 0.8623890297183104,
"pass@128": 0.9129129129129129
}
}
}
}
}
}