AR-Diff / SDAR-100M-midtrain-ar_diff /composition /autoregressive /checkpoint-38796_metrics.json
DatPySci's picture
Add files using upload-large-folder tool
2616764 verified
Raw History Blame Contribute Delete
60.9 kB
{
"checkpoint": "checkpoint-38796",
"id": {
"answer_accuracy": 0.9916449652777778,
"avg_response_len": 200.28180034722223,
"avg_loss": 0.0,
"count": 1152000,
"validation_metrics": {},
"pass_at_k": {
"pass@1": 0.9916449652777778,
"pass@2": 0.9942652148950116,
"pass@4": 0.9960372402824641,
"pass@8": 0.9973541288508918,
"pass@16": 0.9983286171835405,
"pass@32": 0.9990140951617359,
"pass@64": 0.9995384212572507,
"pass@128": 0.9998888888888889
},
"per_op_pass_at_k": {
"10": {
"pass@1": 0.9466015625,
"pass@2": 0.9610051673228348,
"pass@4": 0.9726838771091111,
"pass@8": 0.9821482544180546,
"pass@16": 0.9891967479504874,
"pass@32": 0.9936529337175701,
"pass@64": 0.9968173920169906,
"pass@128": 0.999
},
"2": {
"pass@1": 1.0,
"pass@2": 1.0,
"pass@4": 1.0,
"pass@8": 1.0,
"pass@16": 1.0,
"pass@32": 1.0,
"pass@64": 1.0,
"pass@128": 1.0
},
"3": {
"pass@1": 0.9997734375,
"pass@2": 0.9999870816929133,
"pass@4": 0.9999999652230971,
"pass@8": 0.9999999999999623,
"pass@16": 1.0,
"pass@32": 1.0,
"pass@64": 1.0,
"pass@128": 1.0
},
"4": {
"pass@1": 0.999140625,
"pass@2": 0.9997561515748032,
"pass@4": 0.999979291807274,
"pass@8": 0.9999998345181814,
"pass@16": 0.9999999999930597,
"pass@32": 1.0,
"pass@64": 1.0,
"pass@128": 1.0
},
"5": {
"pass@1": 0.99578125,
"pass@2": 0.9977439714566931,
"pass@4": 0.9987070024371953,
"pass@8": 0.9991198166176619,
"pass@16": 0.9993307064026963,
"pass@32": 0.9995814578957427,
"pass@64": 0.9998779527559055,
"pass@128": 1.0
},
"6": {
"pass@1": 0.99965625,
"pass@2": 0.9999856053149606,
"pass@4": 0.9999999461004874,
"pass@8": 0.9999999999996532,
"pass@16": 1.0,
"pass@32": 1.0,
"pass@64": 1.0,
"pass@128": 1.0
},
"7": {
"pass@1": 0.996609375,
"pass@2": 0.9978914862204724,
"pass@4": 0.9985337887139109,
"pass@8": 0.9990995140827746,
"pass@16": 0.9995617639865387,
"pass@32": 0.9998720986680215,
"pass@64": 0.9999934279136211,
"pass@128": 1.0
},
"8": {
"pass@1": 0.9941640625,
"pass@2": 0.9970008612204726,
"pass@4": 0.9984830455568053,
"pass@8": 0.9991411297284428,
"pass@16": 0.9994807385991464,
"pass@32": 0.9997688993231002,
"pass@64": 0.9999711811023325,
"pass@128": 1.0
},
"9": {
"pass@1": 0.993078125,
"pass@2": 0.9950166092519686,
"pass@4": 0.9959482455943007,
"pass@8": 0.9966786102933006,
"pass@16": 0.9973875977199353,
"pass@32": 0.9982514668511898,
"pass@64": 0.9991858375264056,
"pass@128": 1.0
}
},
"per_op_accuracy": {
"10": 0.9466015625,
"2": 1.0,
"3": 0.9997734375,
"4": 0.999140625,
"5": 0.99578125,
"6": 0.99965625,
"7": 0.996609375,
"8": 0.9941640625,
"9": 0.993078125
},
"per_op_avg_response_len": {
"10": 281.451125,
"2": 115.6058828125,
"3": 144.85159375,
"4": 159.9671640625,
"5": 173.505046875,
"6": 199.2678984375,
"7": 224.5584296875,
"8": 243.6461640625,
"9": 259.6828984375
},
"per_op_avg_loss": {},
"per_op_length": {
"10": 281.451125,
"2": 115.6058828125,
"3": 144.85159375,
"4": 159.9671640625,
"5": 173.505046875,
"6": 199.2678984375,
"7": 224.5584296875,
"8": 243.6461640625,
"9": 259.6828984375
},
"per_op_loss": {},
"per_template": {
"crazy_zootopia": {
"count": 379008,
"correct": 375891,
"answer_accuracy": 0.9917758991894631,
"avg_response_len": 190.7352694402229,
"resp_tokens_sum": 72290193,
"pass_at_k": {
"pass@1": 0.9917758991894631,
"pass@2": 0.9941626312668362,
"pass@4": 0.995686200160897,
"pass@8": 0.9969115368390852,
"pass@16": 0.9979796890499223,
"pass@32": 0.998873696427674,
"pass@64": 0.9995997924414013,
"pass@128": 1.0
},
"per_op_pass_at_k": {
"10": {
"pass@1": 0.9496450958702065,
"pass@2": 0.9618148706245786,
"pass@4": 0.9709195504323019,
"pass@8": 0.9791190874933853,
"pass@16": 0.9868342218489051,
"pass@32": 0.993298633445245,
"pass@64": 0.9981549989323758,
"pass@128": 1.0
},
"2": {
"pass@1": 1.0,
"pass@2": 1.0,
"pass@4": 1.0,
"pass@8": 1.0,
"pass@16": 1.0,
"pass@32": 1.0,
"pass@64": 1.0,
"pass@128": 1.0
},
"3": {
"pass@1": 0.9997849770642202,
"pass@2": 0.9999864552481399,
"pass@4": 0.9999999638806617,
"pass@8": 0.9999999999999809,
"pass@16": 1.0,
"pass@32": 1.0,
"pass@64": 1.0,
"pass@128": 1.0
},
"4": {
"pass@1": 0.9999755859375,
"pass@2": 1.0,
"pass@4": 1.0,
"pass@8": 1.0,
"pass@16": 1.0,
"pass@32": 1.0,
"pass@64": 1.0,
"pass@128": 1.0
},
"5": {
"pass@1": 0.9954117063492064,
"pass@2": 0.9981478877640296,
"pass@4": 0.9995556263800359,
"pass@8": 0.9999615639259287,
"pass@16": 0.9999997091342684,
"pass@32": 0.9999999999966475,
"pass@64": 1.0,
"pass@128": 1.0
},
"6": {
"pass@1": 0.9997427020958084,
"pass@2": 0.999995948064501,
"pass@4": 0.9999999985967324,
"pass@8": 1.0,
"pass@16": 1.0,
"pass@32": 1.0,
"pass@64": 1.0,
"pass@128": 1.0
},
"7": {
"pass@1": 0.9956083579881657,
"pass@2": 0.9976401976657503,
"pass@4": 0.9985032811172272,
"pass@8": 0.9992715079029393,
"pass@16": 0.9998386699365346,
"pass@32": 0.9999946547625592,
"pass@64": 0.9999999995148912,
"pass@128": 1.0
},
"8": {
"pass@1": 0.9960186298076923,
"pass@2": 0.9985326916767614,
"pass@4": 0.9996494007960544,
"pass@8": 0.9999753031040152,
"pass@16": 0.9999998899899415,
"pass@32": 0.9999999999996564,
"pass@64": 1.0,
"pass@128": 1.0
},
"9": {
"pass@1": 0.9917033450704226,
"pass@2": 0.9929716091826549,
"pass@4": 0.9939165605179635,
"pass@8": 0.9949288254759624,
"pass@16": 0.9958752495136213,
"pass@32": 0.9970100988051338,
"pass@64": 0.9984237773095228,
"pass@128": 1.0
}
}
},
"teachers_in_school": {
"count": 390656,
"correct": 387076,
"answer_accuracy": 0.9908359272608126,
"avg_response_len": 198.307644065367,
"resp_tokens_sum": 77470071,
"pass_at_k": {
"pass@1": 0.9908359272608126,
"pass@2": 0.9934299891125998,
"pass@4": 0.9953776159799322,
"pass@8": 0.9968998465378482,
"pass@16": 0.9979383162737498,
"pass@32": 0.9986008798739462,
"pass@64": 0.9991527101183229,
"pass@128": 0.9996723460026212
},
"per_op_pass_at_k": {
"10": {
"pass@1": 0.9329706671779141,
"pass@2": 0.9490174085792956,
"pass@4": 0.9641241520423445,
"pass@8": 0.976390759682789,
"pass@16": 0.9846418367918528,
"pass@32": 0.9893313200761069,
"pass@64": 0.9929169376529189,
"pass@128": 0.9969325153374233
},
"2": {
"pass@1": 1.0,
"pass@2": 1.0,
"pass@4": 1.0,
"pass@8": 1.0,
"pass@16": 1.0,
"pass@32": 1.0,
"pass@64": 1.0,
"pass@128": 1.0
},
"3": {
"pass@1": 0.9995265151515151,
"pass@2": 0.9999742752326415,
"pass@4": 0.9999999304064264,
"pass@8": 0.9999999999999045,
"pass@16": 1.0,
"pass@32": 1.0,
"pass@64": 1.0,
"pass@128": 1.0
},
"4": {
"pass@1": 0.9985207100591716,
"pass@2": 0.9996389134790105,
"pass@4": 0.9999800542683642,
"pass@8": 0.9999999564675484,
"pass@16": 0.999999999999962,
"pass@32": 1.0,
"pass@64": 1.0,
"pass@128": 1.0
},
"5": {
"pass@1": 0.9973505434782609,
"pass@2": 0.9985510812507132,
"pass@4": 0.9993644259141521,
"pass@8": 0.9998696856114555,
"pass@16": 0.9999955044084027,
"pass@32": 0.9999999980554193,
"pass@64": 1.0,
"pass@128": 1.0
},
"6": {
"pass@1": 0.9993508237822349,
"pass@2": 0.999962984793448,
"pass@4": 0.9999998469030911,
"pass@8": 0.9999999999990058,
"pass@16": 1.0,
"pass@32": 1.0,
"pass@64": 1.0,
"pass@128": 1.0
},
"7": {
"pass@1": 0.9994806719653179,
"pass@2": 0.9999896881116016,
"pass@4": 0.9999999953943619,
"pass@8": 1.0,
"pass@16": 1.0,
"pass@32": 1.0,
"pass@64": 1.0,
"pass@128": 1.0
},
"8": {
"pass@1": 0.993155809859155,
"pass@2": 0.9950745813463459,
"pass@4": 0.9964881184746273,
"pass@8": 0.9976291893269761,
"pass@16": 0.9985375133295249,
"pass@32": 0.9993490121785924,
"pass@64": 0.9999188200065704,
"pass@128": 1.0
},
"9": {
"pass@1": 0.9948774326347305,
"pass@2": 0.9968984275543402,
"pass@4": 0.9971880869868812,
"pass@8": 0.9973699249827601,
"pass@16": 0.9977102880852468,
"pass@32": 0.9983202885567448,
"pass@64": 0.9992573907303504,
"pass@128": 1.0
}
}
},
"movie_festival_awards": {
"count": 382336,
"correct": 379408,
"answer_accuracy": 0.9923418145296284,
"avg_response_len": 211.76235039337126,
"resp_tokens_sum": 80964370,
"pass_at_k": {
"pass@1": 0.9923418145296284,
"pass@2": 0.9952203066964725,
"pass@4": 0.9970592031787792,
"pass@8": 0.9982570363053186,
"pass@16": 0.99907330234602,
"pass@32": 0.9995754790619344,
"pass@64": 0.999871688856761,
"pass@128": 1.0
},
"per_op_pass_at_k": {
"10": {
"pass@1": 0.9567863805970149,
"pass@2": 0.971851495475379,
"pass@4": 0.9827990326768856,
"pass@8": 0.9908164062722622,
"pass@16": 0.9960200237300442,
"pass@32": 0.9982169750293176,
"pass@64": 0.9992594797136242,
"pass@128": 1.0
},
"2": {
"pass@1": 1.0,
"pass@2": 1.0,
"pass@4": 1.0,
"pass@8": 1.0,
"pass@16": 1.0,
"pass@32": 1.0,
"pass@64": 1.0,
"pass@128": 1.0
},
"3": {
"pass@1": 1.0,
"pass@2": 1.0,
"pass@4": 1.0,
"pass@8": 1.0,
"pass@16": 1.0,
"pass@32": 1.0,
"pass@64": 1.0,
"pass@128": 1.0
},
"4": {
"pass@1": 0.9989720394736842,
"pass@2": 0.9996438561956071,
"pass@4": 0.9999591621770964,
"pass@8": 0.9999995591583335,
"pass@16": 0.9999999999797444,
"pass@32": 1.0,
"pass@64": 1.0,
"pass@128": 1.0
},
"5": {
"pass@1": 0.99453125,
"pass@2": 0.9965507758221399,
"pass@4": 0.9972536858444163,
"pass@8": 0.9975790660148303,
"pass@16": 0.9980363206014791,
"pass@32": 0.9987689957872913,
"pass@64": 0.9996410375173692,
"pass@128": 1.0
},
"6": {
"pass@1": 0.9999014195583596,
"pass@2": 0.999999611888025,
"pass@4": 1.0,
"pass@8": 1.0,
"pass@16": 1.0,
"pass@32": 1.0,
"pass@64": 1.0,
"pass@128": 1.0
},
"7": {
"pass@1": 0.9945361946202531,
"pass@2": 0.9958628712747932,
"pass@4": 0.9969610167399962,
"pass@8": 0.997929570922725,
"pass@16": 0.9987857390759178,
"pass@32": 0.9996009663236596,
"pass@64": 0.9999792027771768,
"pass@128": 1.0
},
"8": {
"pass@1": 0.9935013138138138,
"pass@2": 0.9976191742924027,
"pass@4": 0.9995169683181494,
"pass@8": 0.9999713902369773,
"pass@16": 0.9999998669378484,
"pass@32": 0.9999999999994204,
"pass@64": 1.0,
"pass@128": 1.0
},
"9": {
"pass@1": 0.9927150321543409,
"pass@2": 0.9953299459452619,
"pass@4": 0.9969358378032327,
"pass@8": 0.997933512235023,
"pass@16": 0.9987673566627887,
"pass@32": 0.9995945511170884,
"pass@64": 0.9999788684166812,
"pass@128": 1.0
}
}
}
}
},
"ood": {
"answer_accuracy": 0.88128359375,
"avg_response_len": 381.877265625,
"avg_loss": 0.0,
"count": 1280000,
"validation_metrics": {},
"pass_at_k": {
"pass@1": 0.88128359375,
"pass@2": 0.9169421874999801,
"pass@4": 0.9403016251687241,
"pass@8": 0.9566609083280344,
"pass@16": 0.968339831127487,
"pass@32": 0.9765863281317172,
"pass@64": 0.9824299016731352,
"pass@128": 0.9866
},
"per_op_pass_at_k": {
"11": {
"pass@1": 0.96628125,
"pass@2": 0.9785717273622044,
"pass@4": 0.9873329736595432,
"pass@8": 0.9931112776863448,
"pass@16": 0.9965805325156889,
"pass@32": 0.9983545476738703,
"pass@64": 0.9989335858094942,
"pass@128": 0.999
},
"12": {
"pass@1": 0.9478046875,
"pass@2": 0.9690962106299207,
"pass@4": 0.9831062861829775,
"pass@8": 0.9913355415158315,
"pass@16": 0.996070057574652,
"pass@32": 0.9987139354985618,
"pass@64": 0.9997237180814249,
"pass@128": 1.0
},
"13": {
"pass@1": 0.924203125,
"pass@2": 0.9514560777559056,
"pass@4": 0.9705920066554181,
"pass@8": 0.983524048574781,
"pass@16": 0.9914554111118253,
"pass@32": 0.995615897875724,
"pass@64": 0.9977893333892781,
"pass@128": 0.999
},
"14": {
"pass@1": 0.94225,
"pass@2": 0.9635307578740164,
"pass@4": 0.9773012244094489,
"pass@8": 0.9867741013499881,
"pass@16": 0.9931041553200217,
"pass@32": 0.9969675206156218,
"pass@64": 0.9990483415511645,
"pass@128": 1.0
},
"15": {
"pass@1": 0.952296875,
"pass@2": 0.9725359251968507,
"pass@4": 0.983482671259842,
"pass@8": 0.9906915517961334,
"pass@16": 0.9953419881536004,
"pass@32": 0.997607897381467,
"pass@64": 0.998434589414787,
"pass@128": 0.999
},
"16": {
"pass@1": 0.8923984375,
"pass@2": 0.9232349901574809,
"pass@4": 0.944543639295088,
"pass@8": 0.9600311462677881,
"pass@16": 0.9714450156787062,
"pass@32": 0.9800956769939823,
"pass@64": 0.986847916902909,
"pass@128": 0.992
},
"17": {
"pass@1": 0.87903125,
"pass@2": 0.9084288877952762,
"pass@4": 0.9289755383389573,
"pass@8": 0.9456187949405052,
"pass@16": 0.9588866468354461,
"pass@32": 0.9690113051788568,
"pass@64": 0.976362763314076,
"pass@128": 0.983
},
"18": {
"pass@1": 0.8645078125,
"pass@2": 0.9091412401574817,
"pass@4": 0.9346570592425941,
"pass@8": 0.9512213333892252,
"pass@16": 0.9633840273152701,
"pass@32": 0.9726363613074998,
"pass@64": 0.979410245686971,
"pass@128": 0.983
},
"19": {
"pass@1": 0.750859375,
"pass@2": 0.8167075541338586,
"pass@4": 0.860467028308961,
"pass@8": 0.8921891852379328,
"pass@16": 0.9155518651584171,
"pass@32": 0.9329156898194609,
"pass@64": 0.946665061674124,
"pass@128": 0.957
},
"20": {
"pass@1": 0.693203125,
"pass@2": 0.7767185039370087,
"pass@4": 0.8325578243344577,
"pass@8": 0.8721121025217957,
"pass@16": 0.9015786116111969,
"pass@32": 0.9239444489720972,
"pass@64": 0.9410834609070993,
"pass@128": 0.954
}
},
"per_op_accuracy": {
"11": 0.96628125,
"12": 0.9478046875,
"13": 0.924203125,
"14": 0.94225,
"15": 0.952296875,
"16": 0.8923984375,
"17": 0.87903125,
"18": 0.8645078125,
"19": 0.750859375,
"20": 0.693203125
},
"per_op_avg_response_len": {
"11": 300.90371875,
"12": 313.225015625,
"13": 334.0887734375,
"14": 361.206921875,
"15": 381.5723984375,
"16": 391.865984375,
"17": 413.0096484375,
"18": 431.9963671875,
"19": 435.01728125,
"20": 455.886546875
},
"per_op_avg_loss": {},
"per_op_length": {
"11": 300.90371875,
"12": 313.225015625,
"13": 334.0887734375,
"14": 361.206921875,
"15": 381.5723984375,
"16": 391.865984375,
"17": 413.0096484375,
"18": 431.9963671875,
"19": 435.01728125,
"20": 455.886546875
},
"per_op_loss": {},
"per_template": {
"crazy_zootopia": {
"count": 430720,
"correct": 378677,
"answer_accuracy": 0.8791720839524517,
"avg_response_len": 363.8872585438336,
"resp_tokens_sum": 156733520,
"pass_at_k": {
"pass@1": 0.8791720839524517,
"pass@2": 0.9144079570848619,
"pass@4": 0.9376800844730981,
"pass@8": 0.9540837108661213,
"pass@16": 0.9657676862206042,
"pass@32": 0.9739935535366472,
"pass@64": 0.9799957539858889,
"pass@128": 0.9842496285289747
},
"per_op_pass_at_k": {
"11": {
"pass@1": 0.9635047804532578,
"pass@2": 0.977436093328277,
"pass@4": 0.9865923250386901,
"pass@8": 0.9927103321039095,
"pass@16": 0.9970124444229089,
"pass@32": 0.9993847243796702,
"pass@64": 0.9999852421618102,
"pass@128": 1.0
},
"12": {
"pass@1": 0.9450918079096046,
"pass@2": 0.9655720338983056,
"pass@4": 0.9781990243804268,
"pass@8": 0.9861440250122284,
"pass@16": 0.9923112374071664,
"pass@32": 0.9969355017981401,
"pass@64": 0.9992276493263522,
"pass@128": 1.0
},
"13": {
"pass@1": 0.9179075235109718,
"pass@2": 0.9502324099671706,
"pass@4": 0.9729623692218725,
"pass@8": 0.9865352063542692,
"pass@16": 0.9929416594162586,
"pass@32": 0.9950239922483407,
"pass@64": 0.9960875780112477,
"pass@128": 0.9968652037617555
},
"14": {
"pass@1": 0.9201956775700935,
"pass@2": 0.9446224121225502,
"pass@4": 0.9626010729383125,
"pass@8": 0.9762203698107813,
"pass@16": 0.986550455857625,
"pass@32": 0.9938274615772782,
"pass@64": 0.9980046339203555,
"pass@128": 1.0
},
"15": {
"pass@1": 0.9622696893063584,
"pass@2": 0.9790736226161763,
"pass@4": 0.9878219928975642,
"pass@8": 0.9938863424829786,
"pass@16": 0.9974854612936562,
"pass@32": 0.9990553826707531,
"pass@64": 0.9998278336678724,
"pass@128": 1.0
},
"16": {
"pass@1": 0.8738155241935484,
"pass@2": 0.9108982092964184,
"pass@4": 0.9368475640141757,
"pass@8": 0.9526611840974472,
"pass@16": 0.9624771254488251,
"pass@32": 0.9706463781509711,
"pass@64": 0.97815086262173,
"pass@128": 0.9838709677419355
},
"17": {
"pass@1": 0.8999954841040463,
"pass@2": 0.9269427597742481,
"pass@4": 0.9442069857777889,
"pass@8": 0.9584880211486807,
"pass@16": 0.9699099356325508,
"pass@32": 0.977956592718777,
"pass@64": 0.9832164176739884,
"pass@128": 0.9884393063583815
},
"18": {
"pass@1": 0.8340625,
"pass@2": 0.875173298650169,
"pass@4": 0.9003785883014621,
"pass@8": 0.9191113837595276,
"pass@16": 0.9347451165816725,
"pass@32": 0.9484697556158473,
"pass@64": 0.9606376972907202,
"pass@128": 0.9685714285714285
},
"19": {
"pass@1": 0.7546218093093093,
"pass@2": 0.8168980988862881,
"pass@4": 0.8594574675913256,
"pass@8": 0.8903657440259747,
"pass@16": 0.9127998493831533,
"pass@32": 0.9301485120186141,
"pass@64": 0.9444138248825593,
"pass@128": 0.954954954954955
},
"20": {
"pass@1": 0.7120167042042042,
"pass@2": 0.7915602610484499,
"pass@4": 0.8442564102347557,
"pass@8": 0.8824961305644767,
"pass@16": 0.9097409929460565,
"pass@32": 0.927053074881089,
"pass@64": 0.9392787772648254,
"pass@128": 0.948948948948949
}
}
},
"teachers_in_school": {
"count": 430464,
"correct": 382426,
"answer_accuracy": 0.8884041406482307,
"avg_response_len": 377.3070268361582,
"resp_tokens_sum": 162417092,
"pass_at_k": {
"pass@1": 0.8884041406482307,
"pass@2": 0.9226806496004516,
"pass@4": 0.9454679196824326,
"pass@8": 0.961442993074218,
"pass@16": 0.972427449762373,
"pass@32": 0.9796245471643623,
"pass@64": 0.9842425816177335,
"pass@128": 0.9878085043116265
},
"per_op_pass_at_k": {
"11": {
"pass@1": 0.9722797439759037,
"pass@2": 0.9806206864861019,
"pass@4": 0.987148461675724,
"pass@8": 0.992097089748973,
"pass@16": 0.9952356342084575,
"pass@32": 0.996694117094797,
"pass@64": 0.9969831820276938,
"pass@128": 0.9969879518072289
},
"12": {
"pass@1": 0.9480309561128527,
"pass@2": 0.9714501363759779,
"pass@4": 0.9865298393343465,
"pass@8": 0.9942286337372813,
"pass@16": 0.9978628049514008,
"pass@32": 0.9996281644114471,
"pass@64": 0.9999956190522251,
"pass@128": 1.0
},
"13": {
"pass@1": 0.9407169117647058,
"pass@2": 0.9625553469419262,
"pass@4": 0.9774801687079033,
"pass@8": 0.9874219685475781,
"pass@16": 0.9934829131966962,
"pass@32": 0.9968338780653557,
"pass@64": 0.9985126025262858,
"pass@128": 1.0
},
"14": {
"pass@1": 0.9497669956140351,
"pass@2": 0.9702634312980611,
"pass@4": 0.9843248648195289,
"pass@8": 0.9936793355130432,
"pass@16": 0.9984837564707297,
"pass@32": 0.999880078009628,
"pass@64": 0.999999559195243,
"pass@128": 1.0
},
"15": {
"pass@1": 0.9554214015151515,
"pass@2": 0.9778524665950848,
"pass@4": 0.990172612230289,
"pass@8": 0.9965689152787764,
"pass@16": 0.9990389896488282,
"pass@32": 0.9998467083150427,
"pass@64": 0.9999979765261304,
"pass@128": 1.0
},
"16": {
"pass@1": 0.8984820156695157,
"pass@2": 0.9263237628149055,
"pass@4": 0.9466511985147156,
"pass@8": 0.9628916229912796,
"pass@16": 0.9756373410907596,
"pass@32": 0.9843113854696494,
"pass@64": 0.9896611343512275,
"pass@128": 0.9943019943019943
},
"17": {
"pass@1": 0.8989955357142857,
"pass@2": 0.9258540372670809,
"pass@4": 0.9430381279009376,
"pass@8": 0.9567724437885808,
"pass@16": 0.9678264048731167,
"pass@32": 0.975789443612367,
"pass@64": 0.9804645618033802,
"pass@128": 0.984472049689441
},
"18": {
"pass@1": 0.8785386029411765,
"pass@2": 0.9263135421491432,
"pass@4": 0.9540938742032239,
"pass@8": 0.970755896754488,
"pass@16": 0.9808158406179858,
"pass@32": 0.9865832611536812,
"pass@64": 0.989914086501943,
"pass@128": 0.9911764705882353
},
"19": {
"pass@1": 0.7576497395833334,
"pass@2": 0.8213040752718409,
"pass@4": 0.8629211197930617,
"pass@8": 0.8939620372022703,
"pass@16": 0.9169075579630253,
"pass@32": 0.9325509025737705,
"pass@64": 0.94412425958293,
"pass@128": 0.9553571428571429
},
"20": {
"pass@1": 0.6838978293413174,
"pass@2": 0.7640517439530387,
"pass@4": 0.8220046661457729,
"pass@8": 0.8655627671390692,
"pass@16": 0.8983598878087751,
"pass@32": 0.9234805889172719,
"pass@64": 0.9421120203018302,
"pass@128": 0.9550898203592815
}
}
},
"movie_festival_awards": {
"count": 418816,
"correct": 366940,
"answer_accuracy": 0.8761365372860636,
"avg_response_len": 405.07594743276286,
"resp_tokens_sum": 169652288,
"pass_at_k": {
"pass@1": 0.8761365372860636,
"pass@2": 0.9136503896097687,
"pass@4": 0.9376876997381768,
"pass@8": 0.9543962746048996,
"pass@16": 0.9667837816600432,
"pass@32": 0.9761300799366067,
"pass@64": 0.9830701413778614,
"pass@128": 0.9877750611246944
},
"per_op_pass_at_k": {
"11": {
"pass@1": 0.9630704365079366,
"pass@2": 0.9776848206474192,
"pass@4": 0.9883574401414106,
"pass@8": 0.9946295131968437,
"pass@16": 0.997513997070458,
"pass@32": 0.9989501368011887,
"pass@64": 0.9998107266450182,
"pass@128": 1.0
},
"12": {
"pass@1": 0.9505208333333334,
"pass@2": 0.9706150370825212,
"pass@4": 0.9850789382405178,
"pass@8": 0.994133402138561,
"pass@16": 0.9983903509266632,
"pass@32": 0.9997473498922584,
"pass@64": 0.9999954976826797,
"pass@128": 1.0
},
"13": {
"pass@1": 0.9122058256172839,
"pass@2": 0.9404311114756491,
"pass@4": 0.9606684896448127,
"pass@8": 0.9762644289391496,
"pass@16": 0.9877580918111676,
"pass@32": 0.9948566354295425,
"pass@64": 0.9986678916722411,
"pass@128": 1.0
},
"14": {
"pass@1": 0.955628709198813,
"pass@2": 0.9747088132900301,
"pass@4": 0.9841755971156422,
"pass@8": 0.9898190798079135,
"pass@16": 0.9938872827202818,
"pass@32": 0.9970027263205429,
"pass@64": 0.99907716563192,
"pass@128": 1.0
},
"15": {
"pass@1": 0.9384645061728395,
"pass@2": 0.9601393141829493,
"pass@4": 0.9720348755595365,
"pass@8": 0.981293627330329,
"pass@16": 0.9892875060551926,
"pass@32": 0.9937818556587116,
"pass@64": 0.995354403432346,
"pass@128": 0.9969135802469136
},
"16": {
"pass@1": 0.9030927359882006,
"pass@2": 0.9313183024411773,
"pass@4": 0.949399185168225,
"pass@8": 0.9638089071611805,
"pass@16": 0.9753050149460608,
"pass@32": 0.9843716916440536,
"pass@64": 0.9918881750232778,
"pass@128": 0.9970501474926253
},
"17": {
"pass@1": 0.8378200301204819,
"pass@2": 0.8722340147993546,
"pass@4": 0.8994627833606642,
"pass@8": 0.921389194949213,
"pass@16": 0.9387280323416873,
"pass@32": 0.953114829081259,
"pass@64": 0.9652418490909267,
"pass@128": 0.9759036144578314
},
"18": {
"pass@1": 0.8834929435483871,
"pass@2": 0.9286580041910086,
"pass@4": 0.9520407616386656,
"pass@8": 0.966049497344724,
"pass@16": 0.9765995183921604,
"pass@32": 0.9846246388700052,
"pass@64": 0.989084716853413,
"pass@128": 0.9903225806451613
},
"19": {
"pass@1": 0.7401812688821753,
"pass@2": 0.8118499030615883,
"pass@4": 0.8589915267389155,
"pass@8": 0.8922240120160714,
"pass@16": 0.9169443378799137,
"pass@32": 0.9360698853549126,
"pass@64": 0.9515090838923458,
"pass@128": 0.9607250755287009
},
"20": {
"pass@1": 0.6837227852852853,
"pass@2": 0.7745815451278046,
"pass@4": 0.8314440877885758,
"pass@8": 0.8682970775356633,
"pass@16": 0.8966446199160057,
"pass@32": 0.92130107609107,
"pass@64": 0.9418564963876911,
"pass@128": 0.9579579579579579
}
}
}
}
},
"total": {
"answer_accuracy": 0.9335600328947369,
"avg_loss": 0.0,
"count": 2432000,
"validation_metrics": {
"id": {},
"ood": {}
},
"pass_at_k": {
"pass@1": 0.9335600328947369,
"pass@2": 0.9535688846871059,
"pass@4": 0.9667027060120662,
"pass@8": 0.9759366443651816,
"pass@16": 0.9825450455750843,
"pass@32": 0.9872100072512014,
"pass@64": 0.9905339372656115,
"pass@128": 0.9928947368421053
},
"per_op_pass_at_k": {
"10": {
"pass@1": 0.9466015625,
"pass@2": 0.9610051673228348,
"pass@4": 0.9726838771091111,
"pass@8": 0.9821482544180546,
"pass@16": 0.9891967479504874,
"pass@32": 0.9936529337175701,
"pass@64": 0.9968173920169906,
"pass@128": 0.999
},
"2": {
"pass@1": 1.0,
"pass@2": 1.0,
"pass@4": 1.0,
"pass@8": 1.0,
"pass@16": 1.0,
"pass@32": 1.0,
"pass@64": 1.0,
"pass@128": 1.0
},
"3": {
"pass@1": 0.9997734375,
"pass@2": 0.9999870816929133,
"pass@4": 0.9999999652230971,
"pass@8": 0.9999999999999623,
"pass@16": 1.0,
"pass@32": 1.0,
"pass@64": 1.0,
"pass@128": 1.0
},
"4": {
"pass@1": 0.999140625,
"pass@2": 0.9997561515748032,
"pass@4": 0.999979291807274,
"pass@8": 0.9999998345181814,
"pass@16": 0.9999999999930597,
"pass@32": 1.0,
"pass@64": 1.0,
"pass@128": 1.0
},
"5": {
"pass@1": 0.99578125,
"pass@2": 0.9977439714566931,
"pass@4": 0.9987070024371953,
"pass@8": 0.9991198166176619,
"pass@16": 0.9993307064026963,
"pass@32": 0.9995814578957427,
"pass@64": 0.9998779527559055,
"pass@128": 1.0
},
"6": {
"pass@1": 0.99965625,
"pass@2": 0.9999856053149606,
"pass@4": 0.9999999461004874,
"pass@8": 0.9999999999996532,
"pass@16": 1.0,
"pass@32": 1.0,
"pass@64": 1.0,
"pass@128": 1.0
},
"7": {
"pass@1": 0.996609375,
"pass@2": 0.9978914862204724,
"pass@4": 0.9985337887139109,
"pass@8": 0.9990995140827746,
"pass@16": 0.9995617639865387,
"pass@32": 0.9998720986680215,
"pass@64": 0.9999934279136211,
"pass@128": 1.0
},
"8": {
"pass@1": 0.9941640625,
"pass@2": 0.9970008612204726,
"pass@4": 0.9984830455568053,
"pass@8": 0.9991411297284428,
"pass@16": 0.9994807385991464,
"pass@32": 0.9997688993231002,
"pass@64": 0.9999711811023325,
"pass@128": 1.0
},
"9": {
"pass@1": 0.993078125,
"pass@2": 0.9950166092519686,
"pass@4": 0.9959482455943007,
"pass@8": 0.9966786102933006,
"pass@16": 0.9973875977199353,
"pass@32": 0.9982514668511898,
"pass@64": 0.9991858375264056,
"pass@128": 1.0
},
"11": {
"pass@1": 0.96628125,
"pass@2": 0.9785717273622044,
"pass@4": 0.9873329736595432,
"pass@8": 0.9931112776863448,
"pass@16": 0.9965805325156889,
"pass@32": 0.9983545476738703,
"pass@64": 0.9989335858094942,
"pass@128": 0.999
},
"12": {
"pass@1": 0.9478046875,
"pass@2": 0.9690962106299207,
"pass@4": 0.9831062861829775,
"pass@8": 0.9913355415158315,
"pass@16": 0.996070057574652,
"pass@32": 0.9987139354985618,
"pass@64": 0.9997237180814249,
"pass@128": 1.0
},
"13": {
"pass@1": 0.924203125,
"pass@2": 0.9514560777559056,
"pass@4": 0.9705920066554181,
"pass@8": 0.983524048574781,
"pass@16": 0.9914554111118253,
"pass@32": 0.995615897875724,
"pass@64": 0.9977893333892781,
"pass@128": 0.999
},
"14": {
"pass@1": 0.94225,
"pass@2": 0.9635307578740164,
"pass@4": 0.9773012244094489,
"pass@8": 0.9867741013499881,
"pass@16": 0.9931041553200217,
"pass@32": 0.9969675206156218,
"pass@64": 0.9990483415511645,
"pass@128": 1.0
},
"15": {
"pass@1": 0.952296875,
"pass@2": 0.9725359251968507,
"pass@4": 0.983482671259842,
"pass@8": 0.9906915517961334,
"pass@16": 0.9953419881536004,
"pass@32": 0.997607897381467,
"pass@64": 0.998434589414787,
"pass@128": 0.999
},
"16": {
"pass@1": 0.8923984375,
"pass@2": 0.9232349901574809,
"pass@4": 0.944543639295088,
"pass@8": 0.9600311462677881,
"pass@16": 0.9714450156787062,
"pass@32": 0.9800956769939823,
"pass@64": 0.986847916902909,
"pass@128": 0.992
},
"17": {
"pass@1": 0.87903125,
"pass@2": 0.9084288877952762,
"pass@4": 0.9289755383389573,
"pass@8": 0.9456187949405052,
"pass@16": 0.9588866468354461,
"pass@32": 0.9690113051788568,
"pass@64": 0.976362763314076,
"pass@128": 0.983
},
"18": {
"pass@1": 0.8645078125,
"pass@2": 0.9091412401574817,
"pass@4": 0.9346570592425941,
"pass@8": 0.9512213333892252,
"pass@16": 0.9633840273152701,
"pass@32": 0.9726363613074998,
"pass@64": 0.979410245686971,
"pass@128": 0.983
},
"19": {
"pass@1": 0.750859375,
"pass@2": 0.8167075541338586,
"pass@4": 0.860467028308961,
"pass@8": 0.8921891852379328,
"pass@16": 0.9155518651584171,
"pass@32": 0.9329156898194609,
"pass@64": 0.946665061674124,
"pass@128": 0.957
},
"20": {
"pass@1": 0.693203125,
"pass@2": 0.7767185039370087,
"pass@4": 0.8325578243344577,
"pass@8": 0.8721121025217957,
"pass@16": 0.9015786116111969,
"pass@32": 0.9239444489720972,
"pass@64": 0.9410834609070993,
"pass@128": 0.954
}
},
"per_op_accuracy": {
"10": 0.9466015625,
"2": 1.0,
"3": 0.9997734375,
"4": 0.999140625,
"5": 0.99578125,
"6": 0.99965625,
"7": 0.996609375,
"8": 0.9941640625,
"9": 0.993078125,
"11": 0.96628125,
"12": 0.9478046875,
"13": 0.924203125,
"14": 0.94225,
"15": 0.952296875,
"16": 0.8923984375,
"17": 0.87903125,
"18": 0.8645078125,
"19": 0.750859375,
"20": 0.693203125
},
"per_op_avg_response_len": {
"10": 281.451125,
"2": 115.6058828125,
"3": 144.85159375,
"4": 159.9671640625,
"5": 173.505046875,
"6": 199.2678984375,
"7": 224.5584296875,
"8": 243.6461640625,
"9": 259.6828984375,
"11": 300.90371875,
"12": 313.225015625,
"13": 334.0887734375,
"14": 361.206921875,
"15": 381.5723984375,
"16": 391.865984375,
"17": 413.0096484375,
"18": 431.9963671875,
"19": 435.01728125,
"20": 455.886546875
},
"per_op_avg_loss": {},
"per_op_length": {
"10": 281.451125,
"2": 115.6058828125,
"3": 144.85159375,
"4": 159.9671640625,
"5": 173.505046875,
"6": 199.2678984375,
"7": 224.5584296875,
"8": 243.6461640625,
"9": 259.6828984375,
"11": 300.90371875,
"12": 313.225015625,
"13": 334.0887734375,
"14": 361.206921875,
"15": 381.5723984375,
"16": 391.865984375,
"17": 413.0096484375,
"18": 431.9963671875,
"19": 435.01728125,
"20": 455.886546875
},
"per_op_loss": {},
"per_template": {
"crazy_zootopia": {
"count": 809728,
"correct": 754568,
"answer_accuracy": 0.9318783591527031,
"avg_response_len": 282.8403031635315,
"resp_tokens_sum": 229023713,
"pass_at_k": {
"pass@1": 0.9318783591527031,
"pass@2": 0.9517385910166891,
"pass@4": 0.964830907829337,
"pass@8": 0.9741300581165051,
"pass@16": 0.9808451032894651,
"pass@32": 0.9856391594646161,
"pass@64": 0.9891717827349858,
"pass@128": 0.9916218779639583
},
"per_op_pass_at_k": {
"10": {
"pass@1": 0.9496450958702065,
"pass@2": 0.9618148706245786,
"pass@4": 0.9709195504323019,
"pass@8": 0.9791190874933853,
"pass@16": 0.9868342218489051,
"pass@32": 0.993298633445245,
"pass@64": 0.9981549989323758,
"pass@128": 1.0
},
"2": {
"pass@1": 1.0,
"pass@2": 1.0,
"pass@4": 1.0,
"pass@8": 1.0,
"pass@16": 1.0,
"pass@32": 1.0,
"pass@64": 1.0,
"pass@128": 1.0
},
"3": {
"pass@1": 0.9997849770642202,
"pass@2": 0.9999864552481399,
"pass@4": 0.9999999638806617,
"pass@8": 0.9999999999999809,
"pass@16": 1.0,
"pass@32": 1.0,
"pass@64": 1.0,
"pass@128": 1.0
},
"4": {
"pass@1": 0.9999755859375,
"pass@2": 1.0,
"pass@4": 1.0,
"pass@8": 1.0,
"pass@16": 1.0,
"pass@32": 1.0,
"pass@64": 1.0,
"pass@128": 1.0
},
"5": {
"pass@1": 0.9954117063492064,
"pass@2": 0.9981478877640296,
"pass@4": 0.9995556263800359,
"pass@8": 0.9999615639259287,
"pass@16": 0.9999997091342684,
"pass@32": 0.9999999999966475,
"pass@64": 1.0,
"pass@128": 1.0
},
"6": {
"pass@1": 0.9997427020958084,
"pass@2": 0.999995948064501,
"pass@4": 0.9999999985967324,
"pass@8": 1.0,
"pass@16": 1.0,
"pass@32": 1.0,
"pass@64": 1.0,
"pass@128": 1.0
},
"7": {
"pass@1": 0.9956083579881657,
"pass@2": 0.9976401976657503,
"pass@4": 0.9985032811172272,
"pass@8": 0.9992715079029393,
"pass@16": 0.9998386699365346,
"pass@32": 0.9999946547625592,
"pass@64": 0.9999999995148912,
"pass@128": 1.0
},
"8": {
"pass@1": 0.9960186298076923,
"pass@2": 0.9985326916767614,
"pass@4": 0.9996494007960544,
"pass@8": 0.9999753031040152,
"pass@16": 0.9999998899899415,
"pass@32": 0.9999999999996564,
"pass@64": 1.0,
"pass@128": 1.0
},
"9": {
"pass@1": 0.9917033450704226,
"pass@2": 0.9929716091826549,
"pass@4": 0.9939165605179635,
"pass@8": 0.9949288254759624,
"pass@16": 0.9958752495136213,
"pass@32": 0.9970100988051338,
"pass@64": 0.9984237773095228,
"pass@128": 1.0
},
"11": {
"pass@1": 0.9635047804532578,
"pass@2": 0.977436093328277,
"pass@4": 0.9865923250386901,
"pass@8": 0.9927103321039095,
"pass@16": 0.9970124444229089,
"pass@32": 0.9993847243796702,
"pass@64": 0.9999852421618102,
"pass@128": 1.0
},
"12": {
"pass@1": 0.9450918079096046,
"pass@2": 0.9655720338983056,
"pass@4": 0.9781990243804268,
"pass@8": 0.9861440250122284,
"pass@16": 0.9923112374071664,
"pass@32": 0.9969355017981401,
"pass@64": 0.9992276493263522,
"pass@128": 1.0
},
"13": {
"pass@1": 0.9179075235109718,
"pass@2": 0.9502324099671706,
"pass@4": 0.9729623692218725,
"pass@8": 0.9865352063542692,
"pass@16": 0.9929416594162586,
"pass@32": 0.9950239922483407,
"pass@64": 0.9960875780112477,
"pass@128": 0.9968652037617555
},
"14": {
"pass@1": 0.9201956775700935,
"pass@2": 0.9446224121225502,
"pass@4": 0.9626010729383125,
"pass@8": 0.9762203698107813,
"pass@16": 0.986550455857625,
"pass@32": 0.9938274615772782,
"pass@64": 0.9980046339203555,
"pass@128": 1.0
},
"15": {
"pass@1": 0.9622696893063584,
"pass@2": 0.9790736226161763,
"pass@4": 0.9878219928975642,
"pass@8": 0.9938863424829786,
"pass@16": 0.9974854612936562,
"pass@32": 0.9990553826707531,
"pass@64": 0.9998278336678724,
"pass@128": 1.0
},
"16": {
"pass@1": 0.8738155241935484,
"pass@2": 0.9108982092964184,
"pass@4": 0.9368475640141757,
"pass@8": 0.9526611840974472,
"pass@16": 0.9624771254488251,
"pass@32": 0.9706463781509711,
"pass@64": 0.97815086262173,
"pass@128": 0.9838709677419355
},
"17": {
"pass@1": 0.8999954841040463,
"pass@2": 0.9269427597742481,
"pass@4": 0.9442069857777889,
"pass@8": 0.9584880211486807,
"pass@16": 0.9699099356325508,
"pass@32": 0.977956592718777,
"pass@64": 0.9832164176739884,
"pass@128": 0.9884393063583815
},
"18": {
"pass@1": 0.8340625,
"pass@2": 0.875173298650169,
"pass@4": 0.9003785883014621,
"pass@8": 0.9191113837595276,
"pass@16": 0.9347451165816725,
"pass@32": 0.9484697556158473,
"pass@64": 0.9606376972907202,
"pass@128": 0.9685714285714285
},
"19": {
"pass@1": 0.7546218093093093,
"pass@2": 0.8168980988862881,
"pass@4": 0.8594574675913256,
"pass@8": 0.8903657440259747,
"pass@16": 0.9127998493831533,
"pass@32": 0.9301485120186141,
"pass@64": 0.9444138248825593,
"pass@128": 0.954954954954955
},
"20": {
"pass@1": 0.7120167042042042,
"pass@2": 0.7915602610484499,
"pass@4": 0.8442564102347557,
"pass@8": 0.8824961305644767,
"pass@16": 0.9097409929460565,
"pass@32": 0.927053074881089,
"pass@64": 0.9392787772648254,
"pass@128": 0.948948948948949
}
}
},
"teachers_in_school": {
"count": 821120,
"correct": 769502,
"answer_accuracy": 0.9371370810600156,
"avg_response_len": 292.1462916504287,
"resp_tokens_sum": 239887163,
"pass_at_k": {
"pass@1": 0.9371370810600156,
"pass@2": 0.9563403509552427,
"pass@4": 0.9692129536808676,
"pass@8": 0.9783119434671995,
"pass@16": 0.984564498023125,
"pass@32": 0.9886527260310264,
"pass@64": 0.9913362234234722,
"pass@128": 0.9934528448947778
},
"per_op_pass_at_k": {
"10": {
"pass@1": 0.9329706671779141,
"pass@2": 0.9490174085792956,
"pass@4": 0.9641241520423445,
"pass@8": 0.976390759682789,
"pass@16": 0.9846418367918528,
"pass@32": 0.9893313200761069,
"pass@64": 0.9929169376529189,
"pass@128": 0.9969325153374233
},
"2": {
"pass@1": 1.0,
"pass@2": 1.0,
"pass@4": 1.0,
"pass@8": 1.0,
"pass@16": 1.0,
"pass@32": 1.0,
"pass@64": 1.0,
"pass@128": 1.0
},
"3": {
"pass@1": 0.9995265151515151,
"pass@2": 0.9999742752326415,
"pass@4": 0.9999999304064264,
"pass@8": 0.9999999999999045,
"pass@16": 1.0,
"pass@32": 1.0,
"pass@64": 1.0,
"pass@128": 1.0
},
"4": {
"pass@1": 0.9985207100591716,
"pass@2": 0.9996389134790105,
"pass@4": 0.9999800542683642,
"pass@8": 0.9999999564675484,
"pass@16": 0.999999999999962,
"pass@32": 1.0,
"pass@64": 1.0,
"pass@128": 1.0
},
"5": {
"pass@1": 0.9973505434782609,
"pass@2": 0.9985510812507132,
"pass@4": 0.9993644259141521,
"pass@8": 0.9998696856114555,
"pass@16": 0.9999955044084027,
"pass@32": 0.9999999980554193,
"pass@64": 1.0,
"pass@128": 1.0
},
"6": {
"pass@1": 0.9993508237822349,
"pass@2": 0.999962984793448,
"pass@4": 0.9999998469030911,
"pass@8": 0.9999999999990058,
"pass@16": 1.0,
"pass@32": 1.0,
"pass@64": 1.0,
"pass@128": 1.0
},
"7": {
"pass@1": 0.9994806719653179,
"pass@2": 0.9999896881116016,
"pass@4": 0.9999999953943619,
"pass@8": 1.0,
"pass@16": 1.0,
"pass@32": 1.0,
"pass@64": 1.0,
"pass@128": 1.0
},
"8": {
"pass@1": 0.993155809859155,
"pass@2": 0.9950745813463459,
"pass@4": 0.9964881184746273,
"pass@8": 0.9976291893269761,
"pass@16": 0.9985375133295249,
"pass@32": 0.9993490121785924,
"pass@64": 0.9999188200065704,
"pass@128": 1.0
},
"9": {
"pass@1": 0.9948774326347305,
"pass@2": 0.9968984275543402,
"pass@4": 0.9971880869868812,
"pass@8": 0.9973699249827601,
"pass@16": 0.9977102880852468,
"pass@32": 0.9983202885567448,
"pass@64": 0.9992573907303504,
"pass@128": 1.0
},
"11": {
"pass@1": 0.9722797439759037,
"pass@2": 0.9806206864861019,
"pass@4": 0.987148461675724,
"pass@8": 0.992097089748973,
"pass@16": 0.9952356342084575,
"pass@32": 0.996694117094797,
"pass@64": 0.9969831820276938,
"pass@128": 0.9969879518072289
},
"12": {
"pass@1": 0.9480309561128527,
"pass@2": 0.9714501363759779,
"pass@4": 0.9865298393343465,
"pass@8": 0.9942286337372813,
"pass@16": 0.9978628049514008,
"pass@32": 0.9996281644114471,
"pass@64": 0.9999956190522251,
"pass@128": 1.0
},
"13": {
"pass@1": 0.9407169117647058,
"pass@2": 0.9625553469419262,
"pass@4": 0.9774801687079033,
"pass@8": 0.9874219685475781,
"pass@16": 0.9934829131966962,
"pass@32": 0.9968338780653557,
"pass@64": 0.9985126025262858,
"pass@128": 1.0
},
"14": {
"pass@1": 0.9497669956140351,
"pass@2": 0.9702634312980611,
"pass@4": 0.9843248648195289,
"pass@8": 0.9936793355130432,
"pass@16": 0.9984837564707297,
"pass@32": 0.999880078009628,
"pass@64": 0.999999559195243,
"pass@128": 1.0
},
"15": {
"pass@1": 0.9554214015151515,
"pass@2": 0.9778524665950848,
"pass@4": 0.990172612230289,
"pass@8": 0.9965689152787764,
"pass@16": 0.9990389896488282,
"pass@32": 0.9998467083150427,
"pass@64": 0.9999979765261304,
"pass@128": 1.0
},
"16": {
"pass@1": 0.8984820156695157,
"pass@2": 0.9263237628149055,
"pass@4": 0.9466511985147156,
"pass@8": 0.9628916229912796,
"pass@16": 0.9756373410907596,
"pass@32": 0.9843113854696494,
"pass@64": 0.9896611343512275,
"pass@128": 0.9943019943019943
},
"17": {
"pass@1": 0.8989955357142857,
"pass@2": 0.9258540372670809,
"pass@4": 0.9430381279009376,
"pass@8": 0.9567724437885808,
"pass@16": 0.9678264048731167,
"pass@32": 0.975789443612367,
"pass@64": 0.9804645618033802,
"pass@128": 0.984472049689441
},
"18": {
"pass@1": 0.8785386029411765,
"pass@2": 0.9263135421491432,
"pass@4": 0.9540938742032239,
"pass@8": 0.970755896754488,
"pass@16": 0.9808158406179858,
"pass@32": 0.9865832611536812,
"pass@64": 0.989914086501943,
"pass@128": 0.9911764705882353
},
"19": {
"pass@1": 0.7576497395833334,
"pass@2": 0.8213040752718409,
"pass@4": 0.8629211197930617,
"pass@8": 0.8939620372022703,
"pass@16": 0.9169075579630253,
"pass@32": 0.9325509025737705,
"pass@64": 0.94412425958293,
"pass@128": 0.9553571428571429
},
"20": {
"pass@1": 0.6838978293413174,
"pass@2": 0.7640517439530387,
"pass@4": 0.8220046661457729,
"pass@8": 0.8655627671390692,
"pass@16": 0.8983598878087751,
"pass@32": 0.9234805889172719,
"pass@64": 0.9421120203018302,
"pass@128": 0.9550898203592815
}
}
},
"movie_festival_awards": {
"count": 801152,
"correct": 746348,
"answer_accuracy": 0.9315935053522927,
"avg_response_len": 312.82036117990094,
"resp_tokens_sum": 250616658,
"pass_at_k": {
"pass@1": 0.9315935053522927,
"pass@2": 0.9525782282961234,
"pass@4": 0.966021727662297,
"pass@8": 0.975328068054194,
"pass@16": 0.9821933995365425,
"pass@32": 0.9873189930516977,
"pass@64": 0.9910883906699982,
"pass@128": 0.9936092027480428
},
"per_op_pass_at_k": {
"10": {
"pass@1": 0.9567863805970149,
"pass@2": 0.971851495475379,
"pass@4": 0.9827990326768856,
"pass@8": 0.9908164062722622,
"pass@16": 0.9960200237300442,
"pass@32": 0.9982169750293176,
"pass@64": 0.9992594797136242,
"pass@128": 1.0
},
"2": {
"pass@1": 1.0,
"pass@2": 1.0,
"pass@4": 1.0,
"pass@8": 1.0,
"pass@16": 1.0,
"pass@32": 1.0,
"pass@64": 1.0,
"pass@128": 1.0
},
"3": {
"pass@1": 1.0,
"pass@2": 1.0,
"pass@4": 1.0,
"pass@8": 1.0,
"pass@16": 1.0,
"pass@32": 1.0,
"pass@64": 1.0,
"pass@128": 1.0
},
"4": {
"pass@1": 0.9989720394736842,
"pass@2": 0.9996438561956071,
"pass@4": 0.9999591621770964,
"pass@8": 0.9999995591583335,
"pass@16": 0.9999999999797444,
"pass@32": 1.0,
"pass@64": 1.0,
"pass@128": 1.0
},
"5": {
"pass@1": 0.99453125,
"pass@2": 0.9965507758221399,
"pass@4": 0.9972536858444163,
"pass@8": 0.9975790660148303,
"pass@16": 0.9980363206014791,
"pass@32": 0.9987689957872913,
"pass@64": 0.9996410375173692,
"pass@128": 1.0
},
"6": {
"pass@1": 0.9999014195583596,
"pass@2": 0.999999611888025,
"pass@4": 1.0,
"pass@8": 1.0,
"pass@16": 1.0,
"pass@32": 1.0,
"pass@64": 1.0,
"pass@128": 1.0
},
"7": {
"pass@1": 0.9945361946202531,
"pass@2": 0.9958628712747932,
"pass@4": 0.9969610167399962,
"pass@8": 0.997929570922725,
"pass@16": 0.9987857390759178,
"pass@32": 0.9996009663236596,
"pass@64": 0.9999792027771768,
"pass@128": 1.0
},
"8": {
"pass@1": 0.9935013138138138,
"pass@2": 0.9976191742924027,
"pass@4": 0.9995169683181494,
"pass@8": 0.9999713902369773,
"pass@16": 0.9999998669378484,
"pass@32": 0.9999999999994204,
"pass@64": 1.0,
"pass@128": 1.0
},
"9": {
"pass@1": 0.9927150321543409,
"pass@2": 0.9953299459452619,
"pass@4": 0.9969358378032327,
"pass@8": 0.997933512235023,
"pass@16": 0.9987673566627887,
"pass@32": 0.9995945511170884,
"pass@64": 0.9999788684166812,
"pass@128": 1.0
},
"11": {
"pass@1": 0.9630704365079366,
"pass@2": 0.9776848206474192,
"pass@4": 0.9883574401414106,
"pass@8": 0.9946295131968437,
"pass@16": 0.997513997070458,
"pass@32": 0.9989501368011887,
"pass@64": 0.9998107266450182,
"pass@128": 1.0
},
"12": {
"pass@1": 0.9505208333333334,
"pass@2": 0.9706150370825212,
"pass@4": 0.9850789382405178,
"pass@8": 0.994133402138561,
"pass@16": 0.9983903509266632,
"pass@32": 0.9997473498922584,
"pass@64": 0.9999954976826797,
"pass@128": 1.0
},
"13": {
"pass@1": 0.9122058256172839,
"pass@2": 0.9404311114756491,
"pass@4": 0.9606684896448127,
"pass@8": 0.9762644289391496,
"pass@16": 0.9877580918111676,
"pass@32": 0.9948566354295425,
"pass@64": 0.9986678916722411,
"pass@128": 1.0
},
"14": {
"pass@1": 0.955628709198813,
"pass@2": 0.9747088132900301,
"pass@4": 0.9841755971156422,
"pass@8": 0.9898190798079135,
"pass@16": 0.9938872827202818,
"pass@32": 0.9970027263205429,
"pass@64": 0.99907716563192,
"pass@128": 1.0
},
"15": {
"pass@1": 0.9384645061728395,
"pass@2": 0.9601393141829493,
"pass@4": 0.9720348755595365,
"pass@8": 0.981293627330329,
"pass@16": 0.9892875060551926,
"pass@32": 0.9937818556587116,
"pass@64": 0.995354403432346,
"pass@128": 0.9969135802469136
},
"16": {
"pass@1": 0.9030927359882006,
"pass@2": 0.9313183024411773,
"pass@4": 0.949399185168225,
"pass@8": 0.9638089071611805,
"pass@16": 0.9753050149460608,
"pass@32": 0.9843716916440536,
"pass@64": 0.9918881750232778,
"pass@128": 0.9970501474926253
},
"17": {
"pass@1": 0.8378200301204819,
"pass@2": 0.8722340147993546,
"pass@4": 0.8994627833606642,
"pass@8": 0.921389194949213,
"pass@16": 0.9387280323416873,
"pass@32": 0.953114829081259,
"pass@64": 0.9652418490909267,
"pass@128": 0.9759036144578314
},
"18": {
"pass@1": 0.8834929435483871,
"pass@2": 0.9286580041910086,
"pass@4": 0.9520407616386656,
"pass@8": 0.966049497344724,
"pass@16": 0.9765995183921604,
"pass@32": 0.9846246388700052,
"pass@64": 0.989084716853413,
"pass@128": 0.9903225806451613
},
"19": {
"pass@1": 0.7401812688821753,
"pass@2": 0.8118499030615883,
"pass@4": 0.8589915267389155,
"pass@8": 0.8922240120160714,
"pass@16": 0.9169443378799137,
"pass@32": 0.9360698853549126,
"pass@64": 0.9515090838923458,
"pass@128": 0.9607250755287009
},
"20": {
"pass@1": 0.6837227852852853,
"pass@2": 0.7745815451278046,
"pass@4": 0.8314440877885758,
"pass@8": 0.8682970775356633,
"pass@16": 0.8966446199160057,
"pass@32": 0.92130107609107,
"pass@64": 0.9418564963876911,
"pass@128": 0.9579579579579579
}
}
}
}
}
}