DatPySci's picture
Add files using upload-large-folder tool
2616764 verified
Raw
History Blame Contribute Delete
22.1 kB
[
{
"checkpoint": "checkpoint-38796",
"id_acc": 0.9899713541666667,
"ood_acc": 0.8540453125,
"total_acc": 0.9184313322368421,
"id_avg_loss": 0.0,
"ood_avg_loss": 0.0,
"total_avg_loss": 0.0,
"id_avg_resp_len": 200.3366076388889,
"ood_avg_resp_len": 381.87561171875,
"count_id": 1152000,
"count_ood": 1280000,
"count_total": 2432000,
"template_metrics": {
"crazy_zootopia": {
"count": 809728,
"correct": 742004,
"answer_accuracy": 0.9163620376225102,
"avg_response_len": 282.5668360239488,
"resp_tokens_sum": 228802279,
"pass_at_k": {
"pass@1": 0.9163620376225102,
"pass@2": 0.9432990699238839,
"pass@4": 0.9594926690468993,
"pass@8": 0.9702768212202704,
"pass@16": 0.978067131021929,
"pass@32": 0.9837285212462428,
"pass@64": 0.9878001481817852,
"pass@128": 0.9908314890926335
},
"per_op_pass_at_k": {
"10": {
"pass@1": 0.940058075221239,
"pass@2": 0.952202445241911,
"pass@4": 0.9639851915634436,
"pass@8": 0.9747452943211968,
"pass@16": 0.9837117746740343,
"pass@32": 0.9903082598333327,
"pass@64": 0.9945723951890973,
"pass@128": 0.9970501474926253
},
"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": 0.999641628440367,
"pass@2": 0.9999793066291025,
"pass@4": 0.999999905401733,
"pass@8": 0.9999999999996472,
"pass@16": 1.0,
"pass@32": 1.0,
"pass@64": 1.0,
"pass@128": 1.0
},
"4": {
"pass@1": 0.9995361328125,
"pass@2": 0.9999784694881889,
"pass@4": 0.9999999370195912,
"pass@8": 0.9999999999999016,
"pass@16": 1.0,
"pass@32": 1.0,
"pass@64": 1.0,
"pass@128": 1.0
},
"5": {
"pass@1": 0.991170634920635,
"pass@2": 0.9935695538057743,
"pass@4": 0.9953833833270841,
"pass@8": 0.996783521967192,
"pass@16": 0.9975425302123753,
"pass@32": 0.9982188768739435,
"pass@64": 0.9992125984251853,
"pass@128": 1.0
},
"6": {
"pass@1": 0.9999298278443114,
"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
},
"7": {
"pass@1": 0.9981046597633136,
"pass@2": 0.9996745853328983,
"pass@4": 0.9999718887764769,
"pass@8": 0.9999998022755866,
"pass@16": 0.9999999999967328,
"pass@32": 1.0,
"pass@64": 1.0,
"pass@128": 1.0
},
"8": {
"pass@1": 0.9924879807692307,
"pass@2": 0.995214390268524,
"pass@4": 0.9969837258924363,
"pass@8": 0.9983251613066434,
"pass@16": 0.9993038302603201,
"pass@32": 0.9998838431738969,
"pass@64": 0.9999990205966608,
"pass@128": 1.0
},
"9": {
"pass@1": 0.9905809859154929,
"pass@2": 0.992608059775979,
"pass@4": 0.9937131769620348,
"pass@8": 0.9952330962332059,
"pass@16": 0.9970819743714158,
"pass@32": 0.9986530587245823,
"pass@64": 0.9996542900027615,
"pass@128": 1.0
},
"11": {
"pass@1": 0.9567767351274787,
"pass@2": 0.9729954579420491,
"pass@4": 0.9837077224412106,
"pass@8": 0.9915053244533025,
"pass@16": 0.9967604348473688,
"pass@32": 0.9993037377604537,
"pass@64": 0.999959962274875,
"pass@128": 1.0
},
"12": {
"pass@1": 0.9463497528248588,
"pass@2": 0.9650545370123225,
"pass@4": 0.9766829093397222,
"pass@8": 0.9848453467690281,
"pass@16": 0.9914138441913528,
"pass@32": 0.9958525342115812,
"pass@64": 0.9982239261012225,
"pass@128": 1.0
},
"13": {
"pass@1": 0.9212627351097179,
"pass@2": 0.953259601856194,
"pass@4": 0.974031526035734,
"pass@8": 0.9872172251386195,
"pass@16": 0.9946975877158775,
"pass@32": 0.9979212628228779,
"pass@64": 0.9992200434190286,
"pass@128": 1.0
},
"14": {
"pass@1": 0.9226781542056075,
"pass@2": 0.9488315457355219,
"pass@4": 0.966660107907072,
"pass@8": 0.9807327520370567,
"pass@16": 0.9900033030501925,
"pass@32": 0.994705328348,
"pass@64": 0.997677205060592,
"pass@128": 1.0
},
"15": {
"pass@1": 0.9338872832369942,
"pass@2": 0.9658665826544082,
"pass@4": 0.9800264382595235,
"pass@8": 0.9852710411507393,
"pass@16": 0.9867086223947849,
"pass@32": 0.9875391269726735,
"pass@64": 0.9882671703608444,
"pass@128": 0.9884393063583815
},
"16": {
"pass@1": 0.8443296370967742,
"pass@2": 0.8949314992379985,
"pass@4": 0.9236545057875828,
"pass@8": 0.9436194889710628,
"pass@16": 0.9597137566119098,
"pass@32": 0.9731177144426382,
"pass@64": 0.9836290640887158,
"pass@128": 0.9935483870967742
},
"17": {
"pass@1": 0.8775063222543352,
"pass@2": 0.9258678343043105,
"pass@4": 0.9494584514544068,
"pass@8": 0.9630582535369274,
"pass@16": 0.9726016060789089,
"pass@32": 0.9786961371782323,
"pass@64": 0.9822631761264358,
"pass@128": 0.9855491329479769
},
"18": {
"pass@1": 0.8074330357142857,
"pass@2": 0.8726863048368955,
"pass@4": 0.9079920633135147,
"pass@8": 0.9290310338171512,
"pass@16": 0.9431022516433624,
"pass@32": 0.9531360758782476,
"pass@64": 0.9606210100169015,
"pass@128": 0.9657142857142857
},
"19": {
"pass@1": 0.6631240615615616,
"pass@2": 0.7647959228913951,
"pass@4": 0.8269798164306035,
"pass@8": 0.8654212985928951,
"pass@16": 0.8938579593227545,
"pass@32": 0.9182400396910518,
"pass@64": 0.9393446013378842,
"pass@128": 0.9579579579579579
},
"20": {
"pass@1": 0.6333521021021021,
"pass@2": 0.7295261550920993,
"pass@4": 0.7942091112484806,
"pass@8": 0.8420309365275893,
"pass@16": 0.8790149220263148,
"pass@32": 0.9073538190959931,
"pass@64": 0.9277009935323411,
"pass@128": 0.93993993993994
}
}
},
"teachers_in_school": {
"count": 821120,
"correct": 757653,
"answer_accuracy": 0.9227067907248636,
"avg_response_len": 292.3765210931411,
"resp_tokens_sum": 240076209,
"pass_at_k": {
"pass@1": 0.9227067907248636,
"pass@2": 0.9491983678141017,
"pass@4": 0.9648446673072715,
"pass@8": 0.974732532480983,
"pass@16": 0.9813596376382586,
"pass@32": 0.9859942113928409,
"pass@64": 0.9894281143827801,
"pass@128": 0.9918939984411536
},
"per_op_pass_at_k": {
"10": {
"pass@1": 0.9300469708588958,
"pass@2": 0.9466099916670692,
"pass@4": 0.9608256378803874,
"pass@8": 0.9735479075977559,
"pass@16": 0.9852696934862603,
"pass@32": 0.9940972426092773,
"pass@64": 0.9987733649475956,
"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": 0.9961647727272728,
"pass@2": 0.9972918157957528,
"pass@4": 0.9983365499767074,
"pass@8": 0.9991928917832018,
"pass@16": 0.9998063298472625,
"pass@32": 0.9999922499316101,
"pass@64": 0.9999999987964725,
"pass@128": 1.0
},
"4": {
"pass@1": 0.997965976331361,
"pass@2": 0.9991187596095608,
"pass@4": 0.9997857705841503,
"pass@8": 0.9999865024173374,
"pass@16": 0.9999999643806659,
"pass@32": 0.9999999999999731,
"pass@64": 1.0,
"pass@128": 1.0
},
"5": {
"pass@1": 0.99375,
"pass@2": 0.9967833504507589,
"pass@4": 0.9986635988436225,
"pass@8": 0.9996831882834758,
"pass@16": 0.9999789012150662,
"pass@32": 0.9999999417280491,
"pass@64": 0.9999999999999963,
"pass@128": 1.0
},
"6": {
"pass@1": 0.9955676934097422,
"pass@2": 0.9973236243034089,
"pass@4": 0.9983310997300121,
"pass@8": 0.9991142096348365,
"pass@16": 0.9997496114237934,
"pass@32": 0.9999854792844564,
"pass@64": 0.999999993573057,
"pass@128": 1.0
},
"7": {
"pass@1": 0.9948067196531792,
"pass@2": 0.9959908089071959,
"pass@4": 0.9969885587820309,
"pass@8": 0.9979235613025731,
"pass@16": 0.9987206336864413,
"pass@32": 0.9995059858135572,
"pass@64": 0.9999600471131015,
"pass@128": 1.0
},
"8": {
"pass@1": 0.9922975352112676,
"pass@2": 0.9943263419097261,
"pass@4": 0.99571091852955,
"pass@8": 0.9969972148105722,
"pass@16": 0.99814919003857,
"pass@32": 0.9991126715814442,
"pass@64": 0.9998322253384277,
"pass@128": 1.0
},
"9": {
"pass@1": 0.995158121257485,
"pass@2": 0.9969157403696542,
"pass@4": 0.997358424601865,
"pass@8": 0.9976945425380946,
"pass@16": 0.9982569113741001,
"pass@32": 0.9990676801627342,
"pass@64": 0.9998216794756942,
"pass@128": 1.0
},
"11": {
"pass@1": 0.97265625,
"pass@2": 0.9817142586092406,
"pass@4": 0.9872070927128084,
"pass@8": 0.9907918466392928,
"pass@16": 0.9932876981463241,
"pass@32": 0.9946033623345881,
"pass@64": 0.9954810039531555,
"pass@128": 0.9969879518072289
},
"12": {
"pass@1": 0.9539086990595611,
"pass@2": 0.9742443783476912,
"pass@4": 0.9873180110910899,
"pass@8": 0.9939946254019711,
"pass@16": 0.9967163926023948,
"pass@32": 0.9983956273931865,
"pass@64": 0.9996077018477316,
"pass@128": 1.0
},
"13": {
"pass@1": 0.9435836834733894,
"pass@2": 0.9670878686120119,
"pass@4": 0.9795068925207874,
"pass@8": 0.9867661154939795,
"pass@16": 0.9912037146425846,
"pass@32": 0.9943074150090554,
"pass@64": 0.9971910964276763,
"pass@128": 1.0
},
"14": {
"pass@1": 0.9339820906432749,
"pass@2": 0.961808433485288,
"pass@4": 0.9791213154276766,
"pass@8": 0.9903633423119838,
"pass@16": 0.9965715597469695,
"pass@32": 0.998978060543375,
"pass@64": 0.9998257129593244,
"pass@128": 1.0
},
"15": {
"pass@1": 0.936032196969697,
"pass@2": 0.9698241022429014,
"pass@4": 0.986383716808126,
"pass@8": 0.993887020431712,
"pass@16": 0.997341288437486,
"pass@32": 0.9992550901802849,
"pass@64": 0.999953724719699,
"pass@128": 1.0
},
"16": {
"pass@1": 0.8875979344729344,
"pass@2": 0.9302362344931245,
"pass@4": 0.9518918415112638,
"pass@8": 0.9653093003879017,
"pass@16": 0.97478416069728,
"pass@32": 0.9809651521660178,
"pass@64": 0.986492391819359,
"pass@128": 0.9914529914529915
},
"17": {
"pass@1": 0.8626746894409938,
"pass@2": 0.9124707322590117,
"pass@4": 0.9368205890024611,
"pass@8": 0.9508498521267209,
"pass@16": 0.960456726487503,
"pass@32": 0.9678057412486193,
"pass@64": 0.9734389189717876,
"pass@128": 0.9782608695652174
},
"18": {
"pass@1": 0.8121553308823529,
"pass@2": 0.8809753502779064,
"pass@4": 0.9216372758552233,
"pass@8": 0.9462221099752758,
"pass@16": 0.9606949776103674,
"pass@32": 0.9685754572068952,
"pass@64": 0.9731564892213497,
"pass@128": 0.9764705882352941
},
"19": {
"pass@1": 0.66943359375,
"pass@2": 0.7666238985751784,
"pass@4": 0.8258763982627161,
"pass@8": 0.8655574931646675,
"pass@16": 0.8941625232220163,
"pass@32": 0.9161714667742615,
"pass@64": 0.9350029611318369,
"pass@128": 0.9523809523809523
},
"20": {
"pass@1": 0.6556652320359282,
"pass@2": 0.7598498868404915,
"pass@4": 0.8262946623625637,
"pass@8": 0.8690020135890967,
"pass@16": 0.8983220264807161,
"pass@32": 0.9212925306509724,
"pass@64": 0.9391524696479382,
"pass@128": 0.9491017964071856
}
}
},
"movie_festival_awards": {
"count": 801152,
"correct": 733968,
"answer_accuracy": 0.9161407573094743,
"avg_response_len": 312.93695453546894,
"resp_tokens_sum": 250710067,
"pass_at_k": {
"pass@1": 0.9161407573094743,
"pass@2": 0.9444789070667229,
"pass@4": 0.9620470564981104,
"pass@8": 0.9734481996656786,
"pass@16": 0.9808410217800196,
"pass@32": 0.985989950434011,
"pass@64": 0.9899999651668862,
"pass@128": 0.993129892954146
},
"per_op_pass_at_k": {
"10": {
"pass@1": 0.9534048507462687,
"pass@2": 0.970000514161476,
"pass@4": 0.9828655804218498,
"pass@8": 0.9913297716090343,
"pass@16": 0.9958306599914305,
"pass@32": 0.9979223480778879,
"pass@64": 0.9992399818731803,
"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": 0.9987928206997084,
"pass@2": 0.99955952572255,
"pass@4": 0.9999370614387487,
"pass@8": 0.9999989051962135,
"pass@16": 0.9999999998462147,
"pass@32": 1.0,
"pass@64": 1.0,
"pass@128": 1.0
},
"4": {
"pass@1": 0.9986979166666666,
"pass@2": 0.9994841310954552,
"pass@4": 0.9999133192232549,
"pass@8": 0.9999978720766682,
"pass@16": 0.9999999993392,
"pass@32": 1.0,
"pass@64": 1.0,
"pass@128": 1.0
},
"5": {
"pass@1": 0.9966681985294118,
"pass@2": 0.9992585543075498,
"pass@4": 0.999930265610181,
"pass@8": 0.9999993599537156,
"pass@16": 0.9999999999763772,
"pass@32": 1.0,
"pass@64": 1.0,
"pass@128": 1.0
},
"6": {
"pass@1": 0.996352523659306,
"pass@2": 0.9972878735189645,
"pass@4": 0.9978065682444268,
"pass@8": 0.9984953578892186,
"pass@16": 0.9993197040358152,
"pass@32": 0.9998856774168334,
"pass@64": 0.999999036044663,
"pass@128": 1.0
},
"7": {
"pass@1": 0.9953273338607594,
"pass@2": 0.9967836607943786,
"pass@4": 0.9975761380302146,
"pass@8": 0.998262935853195,
"pass@16": 0.9990878595282221,
"pass@32": 0.9997847637219769,
"pass@64": 0.9999954280485364,
"pass@128": 1.0
},
"8": {
"pass@1": 0.9900525525525525,
"pass@2": 0.9931176254995152,
"pass@4": 0.9950761472946511,
"pass@8": 0.996932633631575,
"pass@16": 0.9985345359444987,
"pass@32": 0.9996000242336316,
"pass@64": 0.9999802487805222,
"pass@128": 1.0
},
"9": {
"pass@1": 0.9923382234726688,
"pass@2": 0.9954557466389852,
"pass@4": 0.9969244255440737,
"pass@8": 0.9981047741525653,
"pass@16": 0.9990691147291293,
"pass@32": 0.9997813019589095,
"pass@64": 0.9999953545444935,
"pass@128": 1.0
},
"11": {
"pass@1": 0.9581845238095238,
"pass@2": 0.973211942257218,
"pass@4": 0.9851733461888689,
"pass@8": 0.9935984850997558,
"pass@16": 0.9981004697081209,
"pass@32": 0.9997117617660194,
"pass@64": 0.9999952151978636,
"pass@128": 1.0
},
"12": {
"pass@1": 0.9543434633027523,
"pass@2": 0.9737747266970067,
"pass@4": 0.9860677859648275,
"pass@8": 0.994249571393947,
"pass@16": 0.9986259898728691,
"pass@32": 0.9998862026515789,
"pass@64": 0.9999995629648154,
"pass@128": 1.0
},
"13": {
"pass@1": 0.9164496527777778,
"pass@2": 0.9467269824778841,
"pass@4": 0.966515018955963,
"pass@8": 0.9796284799576312,
"pass@16": 0.9873678160183381,
"pass@32": 0.9923304170452849,
"pass@64": 0.9960751154460078,
"pass@128": 1.0
},
"14": {
"pass@1": 0.9455675074183977,
"pass@2": 0.9688518569359099,
"pass@4": 0.9830591241005852,
"pass@8": 0.9918079912361211,
"pass@16": 0.9964965731596999,
"pass@32": 0.9989974984823478,
"pass@64": 0.999910515524606,
"pass@128": 1.0
},
"15": {
"pass@1": 0.9213927469135802,
"pass@2": 0.9536509216729855,
"pass@4": 0.9729866107593029,
"pass@8": 0.9846111586848604,
"pass@16": 0.9907910506066029,
"pass@32": 0.9946077911424446,
"pass@64": 0.9975593713245301,
"pass@128": 1.0
},
"16": {
"pass@1": 0.8636845501474927,
"pass@2": 0.9176269656005392,
"pass@4": 0.9461433612280757,
"pass@8": 0.9632940350686785,
"pass@16": 0.9731921968948374,
"pass@32": 0.9788198865927932,
"pass@64": 0.9817049567519268,
"pass@128": 0.9823008849557522
},
"17": {
"pass@1": 0.816382718373494,
"pass@2": 0.8697396623897163,
"pass@4": 0.8989555943120052,
"pass@8": 0.918514496266187,
"pass@16": 0.9335748802757035,
"pass@32": 0.9474461636352892,
"pass@64": 0.9617706386333493,
"pass@128": 0.9759036144578314
},
"18": {
"pass@1": 0.8135332661290322,
"pass@2": 0.8886441929133857,
"pass@4": 0.9286830575613528,
"pass@8": 0.9493191452530526,
"pass@16": 0.9612486799216202,
"pass@32": 0.9699809772790603,
"pass@64": 0.9777500114141688,
"pass@128": 0.9838709677419355
},
"19": {
"pass@1": 0.6800651435045317,
"pass@2": 0.7825676636058709,
"pass@4": 0.8478114498338757,
"pass@8": 0.890404706092961,
"pass@16": 0.9181360078721577,
"pass@32": 0.9381630090208142,
"pass@64": 0.9558007487757464,
"pass@128": 0.9697885196374623
},
"20": {
"pass@1": 0.6123545420420421,
"pass@2": 0.7181795476578936,
"pass@4": 0.7932386998922434,
"pass@8": 0.8470943217645397,
"pass@16": 0.8868402120185244,
"pass@32": 0.9171541099551569,
"pass@64": 0.9405105380920781,
"pass@128": 0.9579579579579579
}
}
}
}
}
]