[ { "flos": 0.0, "train_loss": NaN, "eval_loss": 12.252012922957137, "eval_accuracy": 0.006801228609039052, "eval_loss_by_set": { "aqua_rat": 11.513664245605469, "gsm8k": 11.73579268022017, "math_qa": 12.550142923990885 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.017437452615617893, "math_qa": 0.0023450586264656616 } }, { "flos": 6901852457140224.0, "train_loss": 6.723526611328125, "eval_loss": 6.096965480495143, "eval_accuracy": 0.009433962264150943, "eval_loss_by_set": { "aqua_rat": 6.021732330322266, "gsm8k": 6.673355796120384, "math_qa": 5.839056015014648 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.017437452615617893, "math_qa": 0.006365159128978224 } }, { "flos": 1.3874060773556224e+16, "train_loss": 6.004356689453125, "eval_loss": 6.028810707298485, "eval_accuracy": 0.012066695919262835, "eval_loss_by_set": { "aqua_rat": 5.970498085021973, "gsm8k": 6.573998191139915, "math_qa": 5.783792495727539 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.02122820318423048, "math_qa": 0.007370184254606365 } }, { "flos": 2.0828793941786624e+16, "train_loss": 5.966402587890625, "eval_loss": 5.992318127606366, "eval_accuracy": 0.008556384379113647, "eval_loss_by_set": { "aqua_rat": 5.955427169799805, "gsm8k": 6.558872569691051, "math_qa": 5.735721588134766 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01288855193328279, "math_qa": 0.006700167504187605 } }, { "flos": 2.771003860896973e+16, "train_loss": 5.941476440429687, "eval_loss": 5.976125974912901, "eval_accuracy": 0.009872751206669592, "eval_loss_by_set": { "aqua_rat": 5.954959869384766, "gsm8k": 6.560576005415483, "math_qa": 5.7100168863932295 }, "eval_accuracy_by_set": { "aqua_rat": 0.011811023622047244, "gsm8k": 0.01592115238817286, "math_qa": 0.007035175879396985 } }, { "flos": 3.467559079981875e+16, "train_loss": 5.930506591796875, "eval_loss": 5.973060221285434, "eval_accuracy": 0.008117595436594998, "eval_loss_by_set": { "aqua_rat": 5.938904285430908, "gsm8k": 6.560203552246094, "math_qa": 5.706799189249675 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.01288855193328279, "math_qa": 0.005360134003350084 } }, { "flos": 4.161332234000794e+16, "train_loss": 5.921109619140625, "eval_loss": 5.9498008006327865, "eval_accuracy": 0.009872751206669592, "eval_loss_by_set": { "aqua_rat": 5.9182844161987305, "gsm8k": 6.512225064364347, "math_qa": 5.694649378458659 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.017437452615617893, "math_qa": 0.006030150753768844 } }, { "flos": 4.856879692696781e+16, "train_loss": 5.923148803710937, "eval_loss": 5.948648401208826, "eval_accuracy": 0.011189118034225537, "eval_loss_by_set": { "aqua_rat": 5.918670654296875, "gsm8k": 6.505121404474432, "math_qa": 5.696096420288086 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.021986353297952996, "math_qa": 0.006030150753768844 } }, { "flos": 5.543800655891661e+16, "train_loss": 5.916842041015625, "eval_loss": 5.9311246098698795, "eval_accuracy": 0.006581834137779728, "eval_loss_by_set": { "aqua_rat": 5.904874801635742, "gsm8k": 6.508225874467329, "math_qa": 5.66880734761556 }, "eval_accuracy_by_set": { "aqua_rat": 0.011811023622047244, "gsm8k": 0.01061410159211524, "math_qa": 0.004355108877721943 } }, { "flos": 6.24267633843241e+16, "train_loss": 5.891141967773438, "eval_loss": 5.944457569637814, "eval_accuracy": 0.008117595436594998, "eval_loss_by_set": { "aqua_rat": 5.916316509246826, "gsm8k": 6.529397444291548, "math_qa": 5.678705215454102 }, "eval_accuracy_by_set": { "aqua_rat": 0.011811023622047244, "gsm8k": 0.018953752843062926, "math_qa": 0.003015075376884422 } }, { "flos": 6.947522186575872e+16, "train_loss": 5.904549560546875, "eval_loss": 5.936005360371357, "eval_accuracy": 0.006362439666520404, "eval_loss_by_set": { "aqua_rat": 5.908689498901367, "gsm8k": 6.51549599387429, "math_qa": 5.67268180847168 }, "eval_accuracy_by_set": { "aqua_rat": 0.011811023622047244, "gsm8k": 0.013646702047005308, "math_qa": 0.002680067001675042 } }, { "flos": 7.639718819161702e+16, "train_loss": 5.880328979492187, "eval_loss": 5.950051024153426, "eval_accuracy": 0.00614304519526108, "eval_loss_by_set": { "aqua_rat": 5.90273380279541, "gsm8k": 6.524473710493608, "math_qa": 5.690717061360677 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.011372251705837756, "math_qa": 0.003015075376884422 } }, { "flos": 8.33753729550254e+16, "train_loss": 5.861644287109375, "eval_loss": 5.941544661650786, "eval_accuracy": 0.008117595436594998, "eval_loss_by_set": { "aqua_rat": 5.889927864074707, "gsm8k": 6.52031777121804, "math_qa": 5.680575052897136 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.01288855193328279, "math_qa": 0.0036850921273031824 } }, { "flos": 9.034585039962112e+16, "train_loss": 5.868399658203125, "eval_loss": 5.923372423326647, "eval_accuracy": 0.009653356735410267, "eval_loss_by_set": { "aqua_rat": 5.889942169189453, "gsm8k": 6.509992426091975, "math_qa": 5.657290776570638 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.01288855193328279, "math_qa": 0.005025125628140704 } }, { "flos": 9.730892976304947e+16, "train_loss": 5.86659912109375, "eval_loss": 5.933609163438952, "eval_accuracy": 0.009653356735410267, "eval_loss_by_set": { "aqua_rat": 5.897189140319824, "gsm8k": 6.539751919833097, "math_qa": 5.6588287353515625 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.013646702047005308, "math_qa": 0.006365159128978224 } }, { "flos": 1.0426786716739174e+17, "train_loss": 5.85818115234375, "eval_loss": 5.927620398031698, "eval_accuracy": 0.009214567792891619, "eval_loss_by_set": { "aqua_rat": 5.890748023986816, "gsm8k": 6.505683898925781, "math_qa": 5.665747324625651 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.012130401819560273, "math_qa": 0.005695142378559464 } }, { "flos": 1.1119333657595085e+17, "train_loss": 5.850162353515625, "eval_loss": 5.926401447605443, "eval_accuracy": 0.008775778850372971, "eval_loss_by_set": { "aqua_rat": 5.886374473571777, "gsm8k": 6.520403775301847, "math_qa": 5.6574859619140625 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.013646702047005308, "math_qa": 0.005025125628140704 } }, { "flos": 1.1812863609090867e+17, "train_loss": 5.846917724609375, "eval_loss": 5.919052562198123, "eval_accuracy": 0.008556384379113647, "eval_loss_by_set": { "aqua_rat": 5.8806233406066895, "gsm8k": 6.514776056463068, "math_qa": 5.64921506245931 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.013646702047005308, "math_qa": 0.004355108877721943 } }, { "flos": 1.25094497519403e+17, "train_loss": 5.861988525390625, "eval_loss": 5.900975356230864, "eval_accuracy": 0.009214567792891619, "eval_loss_by_set": { "aqua_rat": 5.866637229919434, "gsm8k": 6.476803866299716, "math_qa": 5.639915466308594 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.01288855193328279, "math_qa": 0.0033500837520938024 } }, { "flos": 1.3205811268000154e+17, "train_loss": 5.846591796875, "eval_loss": 5.9014061592720655, "eval_accuracy": 0.01075032909170689, "eval_loss_by_set": { "aqua_rat": 5.879005432128906, "gsm8k": 6.493282664905895, "math_qa": 5.631996154785156 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.016679302501895376, "math_qa": 0.004355108877721943 } }, { "flos": 1.389348857493586e+17, "train_loss": 5.843411865234375, "eval_loss": 5.901519930040514, "eval_accuracy": 0.009433962264150943, "eval_loss_by_set": { "aqua_rat": 5.877120018005371, "gsm8k": 6.497374794699929, "math_qa": 5.630453109741211 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.01592115238817286, "math_qa": 0.0033500837520938024 } }, { "flos": 1.4585786139253146e+17, "train_loss": 5.835927124023438, "eval_loss": 5.900982934075433, "eval_accuracy": 0.007020623080298377, "eval_loss_by_set": { "aqua_rat": 5.871591567993164, "gsm8k": 6.531632856889204, "math_qa": 5.6143843332926435 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.012130401819560273, "math_qa": 0.0020100502512562816 } }, { "flos": 1.528475249929093e+17, "train_loss": 5.838731689453125, "eval_loss": 5.9073288376266895, "eval_accuracy": 0.008336989907854322, "eval_loss_by_set": { "aqua_rat": 5.871723175048828, "gsm8k": 6.508807789195668, "math_qa": 5.6346181233723955 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.014404852160727824, "math_qa": 0.0023450586264656616 } }, { "flos": 1.5977697207805542e+17, "train_loss": 5.836088256835938, "eval_loss": 5.8947313154065935, "eval_accuracy": 0.007678806494076349, "eval_loss_by_set": { "aqua_rat": 5.87539005279541, "gsm8k": 6.506318525834517, "math_qa": 5.6160322825113935 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.014404852160727824, "math_qa": 0.0023450586264656616 } }, { "flos": 1.6676352397462733e+17, "train_loss": 5.83031494140625, "eval_loss": 5.892293027929358, "eval_accuracy": 0.009214567792891619, "eval_loss_by_set": { "aqua_rat": 5.872518062591553, "gsm8k": 6.509214921431108, "math_qa": 5.611185073852539 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.01592115238817286, "math_qa": 0.003015075376884422 } }, { "flos": 1.7365620613971968e+17, "train_loss": 5.832994384765625, "eval_loss": 5.9050594278284025, "eval_accuracy": 0.009214567792891619, "eval_loss_by_set": { "aqua_rat": 5.870628833770752, "gsm8k": 6.513756491921165, "math_qa": 5.628942489624023 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.017437452615617893, "math_qa": 0.0023450586264656616 } }, { "flos": 1.8061592683872256e+17, "train_loss": 5.8293695068359375, "eval_loss": 5.915147317422403, "eval_accuracy": 0.007898200965335674, "eval_loss_by_set": { "aqua_rat": 5.878253936767578, "gsm8k": 6.5251007080078125, "math_qa": 5.638659795125325 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.016679302501895376, "math_qa": 0.002680067001675042 } }, { "flos": 1.875054146218885e+17, "train_loss": 5.82548095703125, "eval_loss": 5.901854360425794, "eval_accuracy": 0.008556384379113647, "eval_loss_by_set": { "aqua_rat": 5.870489597320557, "gsm8k": 6.517207058993253, "math_qa": 5.6224314371744795 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.016679302501895376, "math_qa": 0.0020100502512562816 } }, { "flos": 1.9448693818549862e+17, "train_loss": 5.823465576171875, "eval_loss": 5.91090980735985, "eval_accuracy": 0.008556384379113647, "eval_loss_by_set": { "aqua_rat": 5.86012077331543, "gsm8k": 6.523292541503906, "math_qa": 5.634466807047526 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.017437452615617893, "math_qa": 0.0023450586264656616 } }, { "flos": 2.01376838285525e+17, "train_loss": 5.819369506835938, "eval_loss": 5.883038675462878, "eval_accuracy": 0.007459412022817025, "eval_loss_by_set": { "aqua_rat": 5.8605570793151855, "gsm8k": 6.496018149636009, "math_qa": 5.603963216145833 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.015163002274450341, "math_qa": 0.001340033500837521 } }, { "flos": 2.0831875312386048e+17, "train_loss": 5.827261962890625, "eval_loss": 5.878104622299607, "eval_accuracy": 0.008336989907854322, "eval_loss_by_set": { "aqua_rat": 5.865487575531006, "gsm8k": 6.509171919389204, "math_qa": 5.589916865030925 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.016679302501895376, "math_qa": 0.0023450586264656616 } }, { "flos": 2.152881793752105e+17, "train_loss": 5.8226904296875, "eval_loss": 5.90924969234982, "eval_accuracy": 0.007459412022817025, "eval_loss_by_set": { "aqua_rat": 5.87165641784668, "gsm8k": 6.5183022238991475, "math_qa": 5.633233388264974 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.014404852160727824, "math_qa": 0.0020100502512562816 } }, { "flos": 2.2221805864144077e+17, "train_loss": 5.817041015625, "eval_loss": 5.891510061315588, "eval_accuracy": 0.008556384379113647, "eval_loss_by_set": { "aqua_rat": 5.861668586730957, "gsm8k": 6.51105360551314, "math_qa": 5.610039393107097 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.017437452615617893, "math_qa": 0.0020100502512562816 } }, { "flos": 2.292110406409257e+17, "train_loss": 5.815646362304688, "eval_loss": 5.88088625830573, "eval_accuracy": 0.008336989907854322, "eval_loss_by_set": { "aqua_rat": 5.859498500823975, "gsm8k": 6.5044638893821025, "math_qa": 5.596862157185872 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.019711902956785442, "math_qa": 0.0016750418760469012 } }, { "flos": 2.361518012068004e+17, "train_loss": 5.821104736328125, "eval_loss": 5.8962664990811735, "eval_accuracy": 0.008775778850372971, "eval_loss_by_set": { "aqua_rat": 5.871507167816162, "gsm8k": 6.529658230868253, "math_qa": 5.608025232950847 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.02047005307050796, "math_qa": 0.001340033500837521 } }, { "flos": 2.4310787386795622e+17, "train_loss": 5.82146484375, "eval_loss": 5.895359116631585, "eval_accuracy": 0.008775778850372971, "eval_loss_by_set": { "aqua_rat": 5.862288951873779, "gsm8k": 6.516623063520952, "math_qa": 5.613368988037109 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.01819560272934041, "math_qa": 0.003015075376884422 } }, { "flos": 2.500220501968814e+17, "train_loss": 5.804987182617188, "eval_loss": 5.887747017112938, "eval_accuracy": 0.007020623080298377, "eval_loss_by_set": { "aqua_rat": 5.856757164001465, "gsm8k": 6.52401386607777, "math_qa": 5.59870719909668 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.015163002274450341, "math_qa": 0.002680067001675042 } }, { "flos": 2.569473757240361e+17, "train_loss": 5.81263671875, "eval_loss": 5.8971303991369295, "eval_accuracy": 0.007459412022817025, "eval_loss_by_set": { "aqua_rat": 5.859378814697266, "gsm8k": 6.5319907448508525, "math_qa": 5.6092987060546875 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.01592115238817286, "math_qa": 0.002680067001675042 } }, { "flos": 2.638491460399268e+17, "train_loss": 5.817820434570312, "eval_loss": 5.898616326821817, "eval_accuracy": 0.006801228609039052, "eval_loss_by_set": { "aqua_rat": 5.855908393859863, "gsm8k": 6.534143621271307, "math_qa": 5.610891977945964 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.015163002274450341, "math_qa": 0.0023450586264656616 } }, { "flos": 2.7077280189854515e+17, "train_loss": 5.804024047851563, "eval_loss": 5.875028146279825, "eval_accuracy": 0.007020623080298377, "eval_loss_by_set": { "aqua_rat": 5.850019454956055, "gsm8k": 6.511281100186435, "math_qa": 5.585496266682942 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.013646702047005308, "math_qa": 0.002680067001675042 } }, { "flos": 2.7776046672851763e+17, "train_loss": 5.803882446289062, "eval_loss": 5.862812274211162, "eval_accuracy": 0.008556384379113647, "eval_loss_by_set": { "aqua_rat": 5.8499321937561035, "gsm8k": 6.516308177601207, "math_qa": 5.5643666585286455 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.016679302501895376, "math_qa": 0.002680067001675042 } }, { "flos": 2.846526748365947e+17, "train_loss": 5.81162841796875, "eval_loss": 5.8810124783902555, "eval_accuracy": 0.008117595436594998, "eval_loss_by_set": { "aqua_rat": 5.847745895385742, "gsm8k": 6.514442443847656, "math_qa": 5.593462626139323 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.01819560272934041, "math_qa": 0.0020100502512562816 } }, { "flos": 2.915772170690888e+17, "train_loss": 5.802713623046875, "eval_loss": 5.888000230531435, "eval_accuracy": 0.007898200965335674, "eval_loss_by_set": { "aqua_rat": 5.856078147888184, "gsm8k": 6.521643205122515, "math_qa": 5.600240707397461 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.01592115238817286, "math_qa": 0.0023450586264656616 } }, { "flos": 2.985348144436347e+17, "train_loss": 5.805223388671875, "eval_loss": 5.861695779336466, "eval_accuracy": 0.007459412022817025, "eval_loss_by_set": { "aqua_rat": 5.8492889404296875, "gsm8k": 6.4930551702326, "math_qa": 5.573356628417969 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.014404852160727824, "math_qa": 0.0020100502512562816 } }, { "flos": 3.0547841935160115e+17, "train_loss": 5.805278930664063, "eval_loss": 5.881267702257311, "eval_accuracy": 0.007898200965335674, "eval_loss_by_set": { "aqua_rat": 5.8513078689575195, "gsm8k": 6.511071638627485, "math_qa": 5.595104217529297 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.013646702047005308, "math_qa": 0.0016750418760469012 } }, { "flos": 3.1241567683477504e+17, "train_loss": 5.810687255859375, "eval_loss": 5.8796187220393, "eval_accuracy": 0.007678806494076349, "eval_loss_by_set": { "aqua_rat": 5.860054969787598, "gsm8k": 6.514535383744673, "math_qa": 5.5902455647786455 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.014404852160727824, "math_qa": 0.002680067001675042 } }, { "flos": 3.194387461539103e+17, "train_loss": 5.799320678710938, "eval_loss": 5.892378832842852, "eval_accuracy": 0.007020623080298377, "eval_loss_by_set": { "aqua_rat": 5.857107162475586, "gsm8k": 6.537782148881392, "math_qa": 5.599508285522461 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.01288855193328279, "math_qa": 0.0023450586264656616 } }, { "flos": 3.263539119359263e+17, "train_loss": 5.804425659179688, "eval_loss": 5.879537118447794, "eval_accuracy": 0.008556384379113647, "eval_loss_by_set": { "aqua_rat": 5.857702255249023, "gsm8k": 6.527476917613637, "math_qa": 5.584384282430013 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.01288855193328279, "math_qa": 0.004355108877721943 } }, { "flos": 3.3326353398890496e+17, "train_loss": 5.8044287109375, "eval_loss": 5.878786989160486, "eval_accuracy": 0.008556384379113647, "eval_loss_by_set": { "aqua_rat": 5.850347995758057, "gsm8k": 6.476502852006392, "math_qa": 5.6072038014729815 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.014404852160727824, "math_qa": 0.004690117252931323 } }, { "flos": 3.402380712513372e+17, "train_loss": 5.806549072265625, "eval_loss": 5.888103845957163, "eval_accuracy": 0.008995173321632294, "eval_loss_by_set": { "aqua_rat": 5.857426643371582, "gsm8k": 6.524151888760653, "math_qa": 5.599138259887695 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.017437452615617893, "math_qa": 0.0036850921273031824 } }, { "flos": 3.47123045560746e+17, "train_loss": 5.796743774414063, "eval_loss": 5.899708335464065, "eval_accuracy": 0.007240017551557701, "eval_loss_by_set": { "aqua_rat": 5.849060535430908, "gsm8k": 6.523561651056463, "math_qa": 5.6179962158203125 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.013646702047005308, "math_qa": 0.0023450586264656616 } }, { "flos": 3.5416043752207155e+17, "train_loss": 5.81188720703125, "eval_loss": 5.903730907955685, "eval_accuracy": 0.007678806494076349, "eval_loss_by_set": { "aqua_rat": 5.861573219299316, "gsm8k": 6.528676119717685, "math_qa": 5.620810826619466 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.016679302501895376, "math_qa": 0.0023450586264656616 } }, { "flos": 3.611227953309942e+17, "train_loss": 5.806396484375, "eval_loss": 5.879614649592219, "eval_accuracy": 0.007240017551557701, "eval_loss_by_set": { "aqua_rat": 5.860212326049805, "gsm8k": 6.534955111416903, "math_qa": 5.5808671315511065 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.015163002274450341, "math_qa": 0.0020100502512562816 } }, { "flos": 3.679914482278072e+17, "train_loss": 5.79713623046875, "eval_loss": 5.869026905781514, "eval_accuracy": 0.008556384379113647, "eval_loss_by_set": { "aqua_rat": 5.850252151489258, "gsm8k": 6.506575150923296, "math_qa": 5.578381856282552 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.01288855193328279, "math_qa": 0.004355108877721943 } }, { "flos": 3.749083448816435e+17, "train_loss": 5.803619384765625, "eval_loss": 5.888947873502164, "eval_accuracy": 0.008556384379113647, "eval_loss_by_set": { "aqua_rat": 5.860044479370117, "gsm8k": 6.542132984508168, "math_qa": 5.59197998046875 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.015163002274450341, "math_qa": 0.004020100502512563 } }, { "flos": 3.8191356753792205e+17, "train_loss": 5.800960083007812, "eval_loss": 5.877061199497533, "eval_accuracy": 0.008336989907854322, "eval_loss_by_set": { "aqua_rat": 5.852245807647705, "gsm8k": 6.507333235307173, "math_qa": 5.590254465738933 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.016679302501895376, "math_qa": 0.003015075376884422 } }, { "flos": 3.888345240095949e+17, "train_loss": 5.79630859375, "eval_loss": 5.8725983645464925, "eval_accuracy": 0.008995173321632294, "eval_loss_by_set": { "aqua_rat": 5.848239421844482, "gsm8k": 6.503728693181818, "math_qa": 5.585360209147136 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.014404852160727824, "math_qa": 0.004355108877721943 } }, { "flos": 3.95792657181311e+17, "train_loss": 5.797000732421875, "eval_loss": 5.8902774501491235, "eval_accuracy": 0.007898200965335674, "eval_loss_by_set": { "aqua_rat": 5.857717514038086, "gsm8k": 6.533754522150213, "math_qa": 5.598063786824544 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.014404852160727824, "math_qa": 0.004020100502512563 } }, { "flos": 4.027418670215987e+17, "train_loss": 5.793497314453125, "eval_loss": 5.878936226303513, "eval_accuracy": 0.007240017551557701, "eval_loss_by_set": { "aqua_rat": 5.859658718109131, "gsm8k": 6.53504042191939, "math_qa": 5.579828262329102 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.015163002274450341, "math_qa": 0.002680067001675042 } }, { "flos": 4.096024416217989e+17, "train_loss": 5.7876611328125, "eval_loss": 5.884104754473712, "eval_accuracy": 0.009653356735410267, "eval_loss_by_set": { "aqua_rat": 5.844249725341797, "gsm8k": 6.513180819424716, "math_qa": 5.599099477132161 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.011372251705837756, "math_qa": 0.007035175879396985 } }, { "flos": 4.165406466821325e+17, "train_loss": 5.799287109375, "eval_loss": 5.879122708294843, "eval_accuracy": 0.010092145677928916, "eval_loss_by_set": { "aqua_rat": 5.848650932312012, "gsm8k": 6.52397363836115, "math_qa": 5.5861053466796875 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.016679302501895376, "math_qa": 0.004690117252931323 } }, { "flos": 4.235043241197568e+17, "train_loss": 5.79865234375, "eval_loss": 5.880870252042203, "eval_accuracy": 0.007898200965335674, "eval_loss_by_set": { "aqua_rat": 5.8447065353393555, "gsm8k": 6.525498823686079, "math_qa": 5.588429133097331 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.019711902956785442, "math_qa": 0.0016750418760469012 } }, { "flos": 4.3053487419817984e+17, "train_loss": 5.802037353515625, "eval_loss": 5.8722396283536344, "eval_accuracy": 0.008995173321632294, "eval_loss_by_set": { "aqua_rat": 5.843002796173096, "gsm8k": 6.504639365456321, "math_qa": 5.584826151529948 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.019711902956785442, "math_qa": 0.0020100502512562816 } }, { "flos": 4.374088646656e+17, "train_loss": 5.792348022460938, "eval_loss": 5.8732720194636165, "eval_accuracy": 0.007898200965335674, "eval_loss_by_set": { "aqua_rat": 5.846644878387451, "gsm8k": 6.51653428511186, "math_qa": 5.5806624094645185 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.015163002274450341, "math_qa": 0.002680067001675042 } }, { "flos": 4.4439020247187456e+17, "train_loss": 5.790540161132813, "eval_loss": 5.877500147432895, "eval_accuracy": 0.008336989907854322, "eval_loss_by_set": { "aqua_rat": 5.844245433807373, "gsm8k": 6.4975717717951, "math_qa": 5.596071879069011 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.017437452615617893, "math_qa": 0.0016750418760469012 } }, { "flos": 4.513475942248612e+17, "train_loss": 5.785357666015625, "eval_loss": 5.881487047350085, "eval_accuracy": 0.007898200965335674, "eval_loss_by_set": { "aqua_rat": 5.850238800048828, "gsm8k": 6.529741460626775, "math_qa": 5.586974461873372 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.015163002274450341, "math_qa": 0.003015075376884422 } }, { "flos": 4.5821923588204134e+17, "train_loss": 5.784525146484375, "eval_loss": 5.8607468733916415, "eval_accuracy": 0.008117595436594998, "eval_loss_by_set": { "aqua_rat": 5.845715045928955, "gsm8k": 6.483592640269887, "math_qa": 5.576528549194336 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.01288855193328279, "math_qa": 0.004355108877721943 } }, { "flos": 4.651828306415452e+17, "train_loss": 5.783294677734375, "eval_loss": 5.879920237773174, "eval_accuracy": 0.008995173321632294, "eval_loss_by_set": { "aqua_rat": 5.84974479675293, "gsm8k": 6.51404502175071, "math_qa": 5.591794331868489 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.018953752843062926, "math_qa": 0.003015075376884422 } }, { "flos": 4.722056530000609e+17, "train_loss": 5.786920166015625, "eval_loss": 5.877286653260927, "eval_accuracy": 0.007678806494076349, "eval_loss_by_set": { "aqua_rat": 5.85243034362793, "gsm8k": 6.52483437278054, "math_qa": 5.5825653076171875 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.017437452615617893, "math_qa": 0.0020100502512562816 } }, { "flos": 4.7913911856398336e+17, "train_loss": 5.79520751953125, "eval_loss": 5.867283331381308, "eval_accuracy": 0.007020623080298377, "eval_loss_by_set": { "aqua_rat": 5.8435773849487305, "gsm8k": 6.49950478293679, "math_qa": 5.579490661621094 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.016679302501895376, "math_qa": 0.0020100502512562816 } }, { "flos": 4.86023166234198e+17, "train_loss": 5.780355224609375, "eval_loss": 5.881899730579273, "eval_accuracy": 0.008117595436594998, "eval_loss_by_set": { "aqua_rat": 5.8420844078063965, "gsm8k": 6.510278875177557, "math_qa": 5.5972105662028 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.01819560272934041, "math_qa": 0.0020100502512562816 } }, { "flos": 4.930143346837422e+17, "train_loss": 5.790676879882812, "eval_loss": 5.881917850391285, "eval_accuracy": 0.008336989907854322, "eval_loss_by_set": { "aqua_rat": 5.844124794006348, "gsm8k": 6.51736796985973, "math_qa": 5.593819300333659 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.017437452615617893, "math_qa": 0.0023450586264656616 } }, { "flos": 4.9991000507233075e+17, "train_loss": 5.785758666992187, "eval_loss": 5.8732425071097705, "eval_accuracy": 0.008556384379113647, "eval_loss_by_set": { "aqua_rat": 5.850787162780762, "gsm8k": 6.523770419034091, "math_qa": 5.576955159505208 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.017437452615617893, "math_qa": 0.004020100502512563 } }, { "flos": 5.0691116791077274e+17, "train_loss": 5.783773803710938, "eval_loss": 5.8577457118678735, "eval_accuracy": 0.009872751206669592, "eval_loss_by_set": { "aqua_rat": 5.847555160522461, "gsm8k": 6.512861078435725, "math_qa": 5.55833371480306 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.019711902956785442, "math_qa": 0.004020100502512563 } }, { "flos": 5.139231916477645e+17, "train_loss": 5.798349609375, "eval_loss": 5.895525287937474, "eval_accuracy": 0.007898200965335674, "eval_loss_by_set": { "aqua_rat": 5.856387138366699, "gsm8k": 6.534131136807528, "math_qa": 5.60609245300293 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.017437452615617893, "math_qa": 0.003015075376884422 } }, { "flos": 5.209290327793336e+17, "train_loss": 5.786275024414063, "eval_loss": 5.877500843357396, "eval_accuracy": 0.008995173321632294, "eval_loss_by_set": { "aqua_rat": 5.848366737365723, "gsm8k": 6.526080044833097, "math_qa": 5.582663218180339 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.02122820318423048, "math_qa": 0.002680067001675042 } }, { "flos": 5.278897627956511e+17, "train_loss": 5.780975341796875, "eval_loss": 5.891213700578019, "eval_accuracy": 0.008556384379113647, "eval_loss_by_set": { "aqua_rat": 5.8579864501953125, "gsm8k": 6.52665224942294, "math_qa": 5.602739969889323 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.01819560272934041, "math_qa": 0.002680067001675042 } }, { "flos": 5.348372621652132e+17, "train_loss": 5.79255126953125, "eval_loss": 5.864604846851246, "eval_accuracy": 0.007678806494076349, "eval_loss_by_set": { "aqua_rat": 5.851146697998047, "gsm8k": 6.5109946511008525, "math_qa": 5.569464365641276 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.01592115238817286, "math_qa": 0.0023450586264656616 } }, { "flos": 5.4171941360736666e+17, "train_loss": 5.783297729492188, "eval_loss": 5.8807536975757495, "eval_accuracy": 0.008336989907854322, "eval_loss_by_set": { "aqua_rat": 5.849065780639648, "gsm8k": 6.537031693892046, "math_qa": 5.582600275675456 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.02122820318423048, "math_qa": 0.0016750418760469012 } }, { "flos": 5.4869776372701594e+17, "train_loss": 5.7877294921875, "eval_loss": 5.889739500509726, "eval_accuracy": 0.008775778850372971, "eval_loss_by_set": { "aqua_rat": 5.851969242095947, "gsm8k": 6.5303823297674, "math_qa": 5.59925905863444 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.016679302501895376, "math_qa": 0.0033500837520938024 } }, { "flos": 5.5563485639081984e+17, "train_loss": 5.78271240234375, "eval_loss": 5.865703917838432, "eval_accuracy": 0.008775778850372971, "eval_loss_by_set": { "aqua_rat": 5.8452229499816895, "gsm8k": 6.500215703790838, "math_qa": 5.576592763264974 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.021986353297952996, "math_qa": 0.0016750418760469012 } }, { "flos": 5.625707534431027e+17, "train_loss": 5.776988525390625, "eval_loss": 5.864734649658203, "eval_accuracy": 0.007459412022817025, "eval_loss_by_set": { "aqua_rat": 5.846281051635742, "gsm8k": 6.494782187721946, "math_qa": 5.577500661214192 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.01819560272934041, "math_qa": 0.0020100502512562816 } }, { "flos": 5.6952736190142874e+17, "train_loss": 5.788980102539062, "eval_loss": 5.879811158051362, "eval_accuracy": 0.008556384379113647, "eval_loss_by_set": { "aqua_rat": 5.849748611450195, "gsm8k": 6.5256736061789775, "math_qa": 5.586296081542969 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.019711902956785442, "math_qa": 0.0020100502512562816 } }, { "flos": 5.765059176426373e+17, "train_loss": 5.787901611328125, "eval_loss": 5.872871914425412, "eval_accuracy": 0.007240017551557701, "eval_loss_by_set": { "aqua_rat": 5.854154586791992, "gsm8k": 6.535795731977983, "math_qa": 5.5705916086832685 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.016679302501895376, "math_qa": 0.0020100502512562816 } }, { "flos": 5.834993323600773e+17, "train_loss": 5.784495849609375, "eval_loss": 5.870893426843591, "eval_accuracy": 0.008556384379113647, "eval_loss_by_set": { "aqua_rat": 5.845548629760742, "gsm8k": 6.50172909823331, "math_qa": 5.583872477213542 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.022744503411675512, "math_qa": 0.001340033500837521 } }, { "flos": 5.904449773775094e+17, "train_loss": 5.7891796875, "eval_loss": 5.869455285974451, "eval_accuracy": 0.010092145677928916, "eval_loss_by_set": { "aqua_rat": 5.8475189208984375, "gsm8k": 6.513465187766335, "math_qa": 5.576112111409505 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.02122820318423048, "math_qa": 0.003015075376884422 } }, { "flos": 5.974104264891433e+17, "train_loss": 5.77447021484375, "eval_loss": 5.881177696021828, "eval_accuracy": 0.008556384379113647, "eval_loss_by_set": { "aqua_rat": 5.848433494567871, "gsm8k": 6.527776544744318, "math_qa": 5.587548573811849 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.019711902956785442, "math_qa": 0.0020100502512562816 } }, { "flos": 6.042413046117171e+17, "train_loss": 5.77696533203125, "eval_loss": 5.865796527347049, "eval_accuracy": 0.009653356735410267, "eval_loss_by_set": { "aqua_rat": 5.837716102600098, "gsm8k": 6.512331875887784, "math_qa": 5.571807861328125 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.024260803639120546, "math_qa": 0.0020100502512562816 } }, { "flos": 6.112527302745129e+17, "train_loss": 5.7767572021484375, "eval_loss": 5.879672385550834, "eval_accuracy": 0.008556384379113647, "eval_loss_by_set": { "aqua_rat": 5.851751327514648, "gsm8k": 6.521863070401278, "math_qa": 5.5876617431640625 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.019711902956785442, "math_qa": 0.002680067001675042 } }, { "flos": 6.18114397407019e+17, "train_loss": 5.7773779296875, "eval_loss": 5.869465879491858, "eval_accuracy": 0.008336989907854322, "eval_loss_by_set": { "aqua_rat": 5.846608638763428, "gsm8k": 6.503850763494318, "math_qa": 5.580610911051433 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.016679302501895376, "math_qa": 0.002680067001675042 } }, { "flos": 6.250829791604244e+17, "train_loss": 5.783368530273438, "eval_loss": 5.880540693128431, "eval_accuracy": 0.007898200965335674, "eval_loss_by_set": { "aqua_rat": 5.850625991821289, "gsm8k": 6.541308316317472, "math_qa": 5.58018175760905 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.018953752843062926, "math_qa": 0.0020100502512562816 } }, { "flos": 6.319794532447683e+17, "train_loss": 5.769285278320313, "eval_loss": 5.871675285133156, "eval_accuracy": 0.008117595436594998, "eval_loss_by_set": { "aqua_rat": 5.853348731994629, "gsm8k": 6.530367764559659, "math_qa": 5.571301778157552 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.019711902956785442, "math_qa": 0.0016750418760469012 } }, { "flos": 6.389167928691917e+17, "train_loss": 5.781659545898438, "eval_loss": 5.8886209951864705, "eval_accuracy": 0.007898200965335674, "eval_loss_by_set": { "aqua_rat": 5.850438117980957, "gsm8k": 6.542402787642046, "math_qa": 5.592152913411458 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.01819560272934041, "math_qa": 0.0016750418760469012 } }, { "flos": 6.458657353477652e+17, "train_loss": 5.766495361328125, "eval_loss": 5.875988857166187, "eval_accuracy": 0.009653356735410267, "eval_loss_by_set": { "aqua_rat": 5.850618839263916, "gsm8k": 6.512834722345525, "math_qa": 5.586215337117513 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.024260803639120546, "math_qa": 0.0016750418760469012 } }, { "flos": 6.527776240697344e+17, "train_loss": 5.7809381103515625, "eval_loss": 5.867966780791411, "eval_accuracy": 0.008336989907854322, "eval_loss_by_set": { "aqua_rat": 5.843289375305176, "gsm8k": 6.504694158380682, "math_qa": 5.578189849853516 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.01819560272934041, "math_qa": 0.003015075376884422 } }, { "flos": 6.597144901740134e+17, "train_loss": 5.775504150390625, "eval_loss": 5.872916969093117, "eval_accuracy": 0.008336989907854322, "eval_loss_by_set": { "aqua_rat": 5.844272613525391, "gsm8k": 6.508434642444957, "math_qa": 5.584025065104167 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.021986353297952996, "math_qa": 0.0016750418760469012 } }, { "flos": 6.666870281291694e+17, "train_loss": 5.78302734375, "eval_loss": 5.877929326650259, "eval_accuracy": 0.009872751206669592, "eval_loss_by_set": { "aqua_rat": 5.8544816970825195, "gsm8k": 6.527477611194957, "math_qa": 5.582173665364583 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.025018953752843062, "math_qa": 0.0023450586264656616 } }, { "flos": 6.735687259154022e+17, "train_loss": 5.776480712890625, "eval_loss": 5.871429933084024, "eval_accuracy": 0.010311540149188241, "eval_loss_by_set": { "aqua_rat": 5.845738887786865, "gsm8k": 6.524127613414418, "math_qa": 5.57441775004069 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.022744503411675512, "math_qa": 0.0023450586264656616 } }, { "flos": 6.805627376332964e+17, "train_loss": 5.770299072265625, "eval_loss": 5.86973796019683, "eval_accuracy": 0.008995173321632294, "eval_loss_by_set": { "aqua_rat": 5.844878673553467, "gsm8k": 6.512245178222656, "math_qa": 5.5773270924886065 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.02122820318423048, "math_qa": 0.0016750418760469012 } }, { "flos": 6.875002630150554e+17, "train_loss": 5.778617553710937, "eval_loss": 5.867100174362595, "eval_accuracy": 0.008995173321632294, "eval_loss_by_set": { "aqua_rat": 5.846540451049805, "gsm8k": 6.516101490367543, "math_qa": 5.5713545481363935 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.021986353297952996, "math_qa": 0.001340033500837521 } }, { "flos": 6.944164177132913e+17, "train_loss": 5.760896606445312, "eval_loss": 5.8688868960818725, "eval_accuracy": 0.01184730144800351, "eval_loss_by_set": { "aqua_rat": 5.843839645385742, "gsm8k": 6.521288785067472, "math_qa": 5.571956634521484 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.025018953752843062, "math_qa": 0.0036850921273031824 } }, { "flos": 7.013471216132424e+17, "train_loss": 5.7834326171875, "eval_loss": 5.877030243744722, "eval_accuracy": 0.009872751206669592, "eval_loss_by_set": { "aqua_rat": 5.844902038574219, "gsm8k": 6.521380337801847, "math_qa": 5.584380467732747 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.02122820318423048, "math_qa": 0.0023450586264656616 } }, { "flos": 7.083563836862628e+17, "train_loss": 5.7779638671875, "eval_loss": 5.851280934101826, "eval_accuracy": 0.007678806494076349, "eval_loss_by_set": { "aqua_rat": 5.840021133422852, "gsm8k": 6.501391324129972, "math_qa": 5.554251988728841 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.01592115238817286, "math_qa": 0.0020100502512562816 } }, { "flos": 7.152487152746496e+17, "train_loss": 5.7700244140625, "eval_loss": 5.8734458201640365, "eval_accuracy": 0.008336989907854322, "eval_loss_by_set": { "aqua_rat": 5.844592094421387, "gsm8k": 6.522924249822443, "math_qa": 5.57817268371582 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.019711902956785442, "math_qa": 0.002680067001675042 } }, { "flos": 7.222614809672417e+17, "train_loss": 5.77278076171875, "eval_loss": 5.874634613861909, "eval_accuracy": 0.008995173321632294, "eval_loss_by_set": { "aqua_rat": 5.840606689453125, "gsm8k": 6.525866421786222, "math_qa": 5.578989028930664 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.017437452615617893, "math_qa": 0.002680067001675042 } }, { "flos": 7.291733283501507e+17, "train_loss": 5.778349609375, "eval_loss": 5.869352701547983, "eval_accuracy": 0.010092145677928916, "eval_loss_by_set": { "aqua_rat": 5.848093032836914, "gsm8k": 6.516834605823863, "math_qa": 5.574361801147461 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.02122820318423048, "math_qa": 0.002680067001675042 } }, { "flos": 7.361492668456632e+17, "train_loss": 5.773963623046875, "eval_loss": 5.875039616146603, "eval_accuracy": 0.007459412022817025, "eval_loss_by_set": { "aqua_rat": 5.846405506134033, "gsm8k": 6.513811978426847, "math_qa": 5.584655125935872 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.016679302501895376, "math_qa": 0.0020100502512562816 } }, { "flos": 7.430836182465905e+17, "train_loss": 5.765999145507813, "eval_loss": 5.866530289521089, "eval_accuracy": 0.008995173321632294, "eval_loss_by_set": { "aqua_rat": 5.849856376647949, "gsm8k": 6.528879339044744, "math_qa": 5.564343134562175 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.02350265352539803, "math_qa": 0.001340033500837521 } }, { "flos": 7.500198862766735e+17, "train_loss": 5.7746923828125, "eval_loss": 5.8752407898774015, "eval_accuracy": 0.009433962264150943, "eval_loss_by_set": { "aqua_rat": 5.846526145935059, "gsm8k": 6.5219643332741475, "math_qa": 5.581218719482422 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.01819560272934041, "math_qa": 0.0016750418760469012 } }, { "flos": 7.569528777835807e+17, "train_loss": 5.76530029296875, "eval_loss": 5.854507858688767, "eval_accuracy": 0.009653356735410267, "eval_loss_by_set": { "aqua_rat": 5.839683532714844, "gsm8k": 6.483600963245738, "math_qa": 5.5674088795979815 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.02122820318423048, "math_qa": 0.0016750418760469012 } }, { "flos": 7.638344724905984e+17, "train_loss": 5.75980712890625, "eval_loss": 5.8620980494731185, "eval_accuracy": 0.009653356735410267, "eval_loss_by_set": { "aqua_rat": 5.842048168182373, "gsm8k": 6.497729214754972, "math_qa": 5.572437922159831 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.02047005307050796, "math_qa": 0.002680067001675042 } }, { "flos": 7.706937489369334e+17, "train_loss": 5.7660693359375, "eval_loss": 5.858937959413271, "eval_accuracy": 0.009433962264150943, "eval_loss_by_set": { "aqua_rat": 5.84669303894043, "gsm8k": 6.498272288929332, "math_qa": 5.5669301350911455 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.019711902956785442, "math_qa": 0.003015075376884422 } }, { "flos": 7.775882446519665e+17, "train_loss": 5.769309692382812, "eval_loss": 5.870453009734282, "eval_accuracy": 0.008556384379113647, "eval_loss_by_set": { "aqua_rat": 5.837660312652588, "gsm8k": 6.499244689941406, "math_qa": 5.584989547729492 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.02047005307050796, "math_qa": 0.0016750418760469012 } }, { "flos": 7.845561053877371e+17, "train_loss": 5.770958251953125, "eval_loss": 5.8419562159357845, "eval_accuracy": 0.009214567792891619, "eval_loss_by_set": { "aqua_rat": 5.8453779220581055, "gsm8k": 6.4928741455078125, "math_qa": 5.543333689371745 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.022744503411675512, "math_qa": 0.001340033500837521 } }, { "flos": 7.914432024847319e+17, "train_loss": 5.770386962890625, "eval_loss": 5.865403897053486, "eval_accuracy": 0.008995173321632294, "eval_loss_by_set": { "aqua_rat": 5.847530841827393, "gsm8k": 6.514447992498225, "math_qa": 5.569414774576823 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.018953752843062926, "math_qa": 0.0023450586264656616 } }, { "flos": 7.983546176865567e+17, "train_loss": 5.759653930664062, "eval_loss": 5.874766994167018, "eval_accuracy": 0.008556384379113647, "eval_loss_by_set": { "aqua_rat": 5.844932556152344, "gsm8k": 6.535267223011363, "math_qa": 5.57452392578125 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.01819560272934041, "math_qa": 0.002680067001675042 } }, { "flos": 8.053061768739553e+17, "train_loss": 5.770899047851563, "eval_loss": 5.867529508229849, "eval_accuracy": 0.009872751206669592, "eval_loss_by_set": { "aqua_rat": 5.84557580947876, "gsm8k": 6.546528209339488, "math_qa": 5.5581512451171875 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.02047005307050796, "math_qa": 0.0033500837520938024 } }, { "flos": 8.123176852148716e+17, "train_loss": 5.777974243164063, "eval_loss": 5.870580776317699, "eval_accuracy": 0.010969723562966213, "eval_loss_by_set": { "aqua_rat": 5.847664833068848, "gsm8k": 6.522981123490767, "math_qa": 5.573473612467448 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.022744503411675512, "math_qa": 0.004355108877721943 } }, { "flos": 8.192044526731264e+17, "train_loss": 5.767827758789062, "eval_loss": 5.866163511533995, "eval_accuracy": 0.011408512505484861, "eval_loss_by_set": { "aqua_rat": 5.843505859375, "gsm8k": 6.539571588689631, "math_qa": 5.559406280517578 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.019711902956785442, "math_qa": 0.005695142378559464 } }, { "flos": 8.261692425072804e+17, "train_loss": 5.76281982421875, "eval_loss": 5.871037715190166, "eval_accuracy": 0.012505484861781484, "eval_loss_by_set": { "aqua_rat": 5.851780891418457, "gsm8k": 6.537877169522372, "math_qa": 5.567007700602214 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.027293404094010616, "math_qa": 0.004020100502512563 } }, { "flos": 8.3313557799279e+17, "train_loss": 5.76470458984375, "eval_loss": 5.866430798092404, "eval_accuracy": 0.011189118034225537, "eval_loss_by_set": { "aqua_rat": 5.85250186920166, "gsm8k": 6.5068886496803975, "math_qa": 5.574048360188802 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.022744503411675512, "math_qa": 0.004355108877721943 } }, { "flos": 8.400888889899745e+17, "train_loss": 5.77309326171875, "eval_loss": 5.861335960594383, "eval_accuracy": 0.013821851689337429, "eval_loss_by_set": { "aqua_rat": 5.8401336669921875, "gsm8k": 6.5083534934303975, "math_qa": 5.566553115844727 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.025018953752843062, "math_qa": 0.006365159128978224 } }, { "flos": 8.469836526035927e+17, "train_loss": 5.772487182617187, "eval_loss": 5.8643086923135295, "eval_accuracy": 0.01228609039052216, "eval_loss_by_set": { "aqua_rat": 5.845404624938965, "gsm8k": 6.533689325506037, "math_qa": 5.559084574381511 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.02122820318423048, "math_qa": 0.006365159128978224 } }, { "flos": 8.539928733375529e+17, "train_loss": 5.765791015625, "eval_loss": 5.8591109095393, "eval_accuracy": 0.010311540149188241, "eval_loss_by_set": { "aqua_rat": 5.847718238830566, "gsm8k": 6.497861688787287, "math_qa": 5.567299524943034 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.02047005307050796, "math_qa": 0.0033500837520938024 } }, { "flos": 8.610134902303621e+17, "train_loss": 5.77170166015625, "eval_loss": 5.85942149806667, "eval_accuracy": 0.01075032909170689, "eval_loss_by_set": { "aqua_rat": 5.845392227172852, "gsm8k": 6.510046525435015, "math_qa": 5.562387466430664 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.022744503411675512, "math_qa": 0.0036850921273031824 } }, { "flos": 8.679062754746696e+17, "train_loss": 5.76474853515625, "eval_loss": 5.868127513576198, "eval_accuracy": 0.009872751206669592, "eval_loss_by_set": { "aqua_rat": 5.849661827087402, "gsm8k": 6.524714383212003, "math_qa": 5.5687306722005205 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.017437452615617893, "math_qa": 0.005025125628140704 } }, { "flos": 8.748499421227909e+17, "train_loss": 5.760775146484375, "eval_loss": 5.870387567056192, "eval_accuracy": 0.009872751206669592, "eval_loss_by_set": { "aqua_rat": 5.842537879943848, "gsm8k": 6.518616416237571, "math_qa": 5.575603485107422 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.01819560272934041, "math_qa": 0.004690117252931323 } }, { "flos": 8.817930729737421e+17, "train_loss": 5.76531005859375, "eval_loss": 5.851269541559993, "eval_accuracy": 0.011408512505484861, "eval_loss_by_set": { "aqua_rat": 5.848160743713379, "gsm8k": 6.504189924760298, "math_qa": 5.552273432413737 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.021986353297952996, "math_qa": 0.004355108877721943 } }, { "flos": 8.887129374499799e+17, "train_loss": 5.76794921875, "eval_loss": 5.852583447018185, "eval_accuracy": 0.010530934620447565, "eval_loss_by_set": { "aqua_rat": 5.844414710998535, "gsm8k": 6.501867814497515, "math_qa": 5.555675506591797 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.02047005307050796, "math_qa": 0.004690117252931323 } }, { "flos": 8.956670725440143e+17, "train_loss": 5.7655126953125, "eval_loss": 5.850078634313635, "eval_accuracy": 0.01075032909170689, "eval_loss_by_set": { "aqua_rat": 5.844351768493652, "gsm8k": 6.497532237659801, "math_qa": 5.553806304931641 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.018953752843062926, "math_qa": 0.004355108877721943 } }, { "flos": 9.026386215829504e+17, "train_loss": 5.7613232421875, "eval_loss": 5.86128755517908, "eval_accuracy": 0.010311540149188241, "eval_loss_by_set": { "aqua_rat": 5.855710029602051, "gsm8k": 6.519012451171875, "math_qa": 5.560295104980469 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.017437452615617893, "math_qa": 0.0033500837520938024 } }, { "flos": 9.09611118735917e+17, "train_loss": 5.761351318359375, "eval_loss": 5.8559586808488175, "eval_accuracy": 0.01075032909170689, "eval_loss_by_set": { "aqua_rat": 5.840892791748047, "gsm8k": 6.507064125754616, "math_qa": 5.558790842692058 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.02122820318423048, "math_qa": 0.0020100502512562816 } }, { "flos": 9.1647907101619e+17, "train_loss": 5.7598583984375, "eval_loss": 5.867191469347155, "eval_accuracy": 0.008995173321632294, "eval_loss_by_set": { "aqua_rat": 5.848477363586426, "gsm8k": 6.5092079856178975, "math_qa": 5.574493408203125 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.01592115238817286, "math_qa": 0.0033500837520938024 } }, { "flos": 9.234675395419177e+17, "train_loss": 5.74739990234375, "eval_loss": 5.892639752980825, "eval_accuracy": 0.011408512505484861, "eval_loss_by_set": { "aqua_rat": 5.8594889640808105, "gsm8k": 6.552439602938565, "math_qa": 5.592994054158528 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.02047005307050796, "math_qa": 0.005360134003350084 } }, { "flos": 9.30320035845505e+17, "train_loss": 5.761470947265625, "eval_loss": 5.860189798715952, "eval_accuracy": 0.007459412022817025, "eval_loss_by_set": { "aqua_rat": 5.848634719848633, "gsm8k": 6.503192554820668, "math_qa": 5.566443125406901 }, "eval_accuracy_by_set": { "aqua_rat": 0.011811023622047244, "gsm8k": 0.014404852160727824, "math_qa": 0.004020100502512563 } }, { "flos": 9.373449809916068e+17, "train_loss": 5.771962890625, "eval_loss": 5.853215088715425, "eval_accuracy": 0.007678806494076349, "eval_loss_by_set": { "aqua_rat": 5.840978622436523, "gsm8k": 6.494890386408025, "math_qa": 5.560133616129558 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.013646702047005308, "math_qa": 0.0020100502512562816 } }, { "flos": 9.442393532263301e+17, "train_loss": 5.756708374023438, "eval_loss": 5.843526298935349, "eval_accuracy": 0.009214567792891619, "eval_loss_by_set": { "aqua_rat": 5.8485188484191895, "gsm8k": 6.5056020563299, "math_qa": 5.539658864339192 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.018953752843062926, "math_qa": 0.0020100502512562816 } }, { "flos": 9.511824013991608e+17, "train_loss": 5.756123046875, "eval_loss": 5.86656261134792, "eval_accuracy": 0.012505484861781484, "eval_loss_by_set": { "aqua_rat": 5.854413986206055, "gsm8k": 6.538769808682528, "math_qa": 5.55948003133138 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.02350265352539803, "math_qa": 0.005360134003350084 } }, { "flos": 9.58139380835287e+17, "train_loss": 5.75560791015625, "eval_loss": 5.855721215944032, "eval_accuracy": 0.009433962264150943, "eval_loss_by_set": { "aqua_rat": 5.845826625823975, "gsm8k": 6.507665460759943, "math_qa": 5.557737986246745 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.015163002274450341, "math_qa": 0.004020100502512563 } }, { "flos": 9.650745982089953e+17, "train_loss": 5.75666748046875, "eval_loss": 5.8559654854439405, "eval_accuracy": 0.011627906976744186, "eval_loss_by_set": { "aqua_rat": 5.847690582275391, "gsm8k": 6.5067970969460225, "math_qa": 5.558357238769531 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.024260803639120546, "math_qa": 0.0033500837520938024 } }, { "flos": 9.720263839559188e+17, "train_loss": 5.7682733154296875, "eval_loss": 5.8839891279065935, "eval_accuracy": 0.010969723562966213, "eval_loss_by_set": { "aqua_rat": 5.8482561111450195, "gsm8k": 6.534018083052202, "math_qa": 5.58903694152832 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.01819560272934041, "math_qa": 0.005695142378559464 } }, { "flos": 9.790089587127747e+17, "train_loss": 5.77046630859375, "eval_loss": 5.87531143910176, "eval_accuracy": 0.010530934620447565, "eval_loss_by_set": { "aqua_rat": 5.862802028656006, "gsm8k": 6.551774458451704, "math_qa": 5.566308339436849 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.02122820318423048, "math_qa": 0.004020100502512563 } }, { "flos": 9.860124912994222e+17, "train_loss": 5.772645874023437, "eval_loss": 5.868331986504632, "eval_accuracy": 0.01075032909170689, "eval_loss_by_set": { "aqua_rat": 5.847978115081787, "gsm8k": 6.507852727716619, "math_qa": 5.576914469401042 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.017437452615617893, "math_qa": 0.006030150753768844 } }, { "flos": 9.929277596237824e+17, "train_loss": 5.75601318359375, "eval_loss": 5.876461441452439, "eval_accuracy": 0.009214567792891619, "eval_loss_by_set": { "aqua_rat": 5.850767135620117, "gsm8k": 6.5273895263671875, "math_qa": 5.580260594685872 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.01819560272934041, "math_qa": 0.004355108877721943 } }, { "flos": 9.999089122095923e+17, "train_loss": 5.763438720703125, "eval_loss": 5.8625873359473974, "eval_accuracy": 0.009433962264150943, "eval_loss_by_set": { "aqua_rat": 5.848578453063965, "gsm8k": 6.500611045143821, "math_qa": 5.571327209472656 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.017437452615617893, "math_qa": 0.0036850921273031824 } }, { "flos": 1.0068650670119977e+18, "train_loss": 5.756180419921875, "eval_loss": 5.85876531858702, "eval_accuracy": 0.011189118034225537, "eval_loss_by_set": { "aqua_rat": 5.847241401672363, "gsm8k": 6.506999622691762, "math_qa": 5.562618255615234 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.02122820318423048, "math_qa": 0.005025125628140704 } }, { "flos": 1.0138547719514358e+18, "train_loss": 5.774779052734375, "eval_loss": 5.850921166909708, "eval_accuracy": 0.012066695919262835, "eval_loss_by_set": { "aqua_rat": 5.844099998474121, "gsm8k": 6.5005409934303975, "math_qa": 5.553747177124023 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.021986353297952996, "math_qa": 0.005360134003350084 } }, { "flos": 1.0208395720382218e+18, "train_loss": 5.766256103515625, "eval_loss": 5.8566643225180135, "eval_accuracy": 0.012066695919262835, "eval_loss_by_set": { "aqua_rat": 5.842743396759033, "gsm8k": 6.499693437056108, "math_qa": 5.563102722167969 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.02350265352539803, "math_qa": 0.004690117252931323 } }, { "flos": 1.0277728110426194e+18, "train_loss": 5.75502685546875, "eval_loss": 5.868702811163825, "eval_accuracy": 0.011189118034225537, "eval_loss_by_set": { "aqua_rat": 5.845389366149902, "gsm8k": 6.51843885941939, "math_qa": 5.5728499094645185 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.02122820318423048, "math_qa": 0.005025125628140704 } }, { "flos": 1.0346928194002616e+18, "train_loss": 5.751099853515625, "eval_loss": 5.866638595993455, "eval_accuracy": 0.01075032909170689, "eval_loss_by_set": { "aqua_rat": 5.849212646484375, "gsm8k": 6.517195268110796, "math_qa": 5.569918950398763 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.018953752843062926, "math_qa": 0.004355108877721943 } }, { "flos": 1.0416080055833723e+18, "train_loss": 5.76313720703125, "eval_loss": 5.86648956505028, "eval_accuracy": 0.009872751206669592, "eval_loss_by_set": { "aqua_rat": 5.849186897277832, "gsm8k": 6.542003284801137, "math_qa": 5.558320999145508 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.016679302501895376, "math_qa": 0.005025125628140704 } }, { "flos": 1.0485105999961129e+18, "train_loss": 5.744801635742188, "eval_loss": 5.8675344828012825, "eval_accuracy": 0.012724879333040808, "eval_loss_by_set": { "aqua_rat": 5.849123954772949, "gsm8k": 6.525913585316051, "math_qa": 5.567311604817708 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.02350265352539803, "math_qa": 0.004690117252931323 } }, { "flos": 1.0553843021638533e+18, "train_loss": 5.763973388671875, "eval_loss": 5.845003282701647, "eval_accuracy": 0.01228609039052216, "eval_loss_by_set": { "aqua_rat": 5.843349456787109, "gsm8k": 6.50588642467152, "math_qa": 5.542236328125 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.018953752843062926, "math_qa": 0.007705192629815745 } }, { "flos": 1.0623618276497818e+18, "train_loss": 5.75072998046875, "eval_loss": 5.855805783658414, "eval_accuracy": 0.01184730144800351, "eval_loss_by_set": { "aqua_rat": 5.842187881469727, "gsm8k": 6.508388172496449, "math_qa": 5.557840347290039 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.02350265352539803, "math_qa": 0.004690117252931323 } }, { "flos": 1.0693344074808689e+18, "train_loss": 5.743892822265625, "eval_loss": 5.858521409936853, "eval_accuracy": 0.010092145677928916, "eval_loss_by_set": { "aqua_rat": 5.846513271331787, "gsm8k": 6.526149402965199, "math_qa": 5.553525924682617 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.01819560272934041, "math_qa": 0.005025125628140704 } }, { "flos": 1.0763022059396137e+18, "train_loss": 5.764432373046875, "eval_loss": 5.85325661221066, "eval_accuracy": 0.01184730144800351, "eval_loss_by_set": { "aqua_rat": 5.843432903289795, "gsm8k": 6.502059242942116, "math_qa": 5.556707382202148 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.022744503411675512, "math_qa": 0.004020100502512563 } }, { "flos": 1.0831477159420232e+18, "train_loss": 5.7615771484375, "eval_loss": 5.838995701557881, "eval_accuracy": 0.01228609039052216, "eval_loss_by_set": { "aqua_rat": 5.8425493240356445, "gsm8k": 6.497110540216619, "math_qa": 5.5370635986328125 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.017437452615617893, "math_qa": 0.005695142378559464 } }, { "flos": 1.090103623783809e+18, "train_loss": 5.761283569335937, "eval_loss": 5.857318852398847, "eval_accuracy": 0.012066695919262835, "eval_loss_by_set": { "aqua_rat": 5.845956325531006, "gsm8k": 6.528585260564631, "math_qa": 5.550601959228516 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.018953752843062926, "math_qa": 0.005695142378559464 } }, { "flos": 1.0970507731135365e+18, "train_loss": 5.747294921875, "eval_loss": 5.853981945965741, "eval_accuracy": 0.01338306274681878, "eval_loss_by_set": { "aqua_rat": 5.844362258911133, "gsm8k": 6.50566309148615, "math_qa": 5.5560963948567705 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.021986353297952996, "math_qa": 0.006700167504187605 } }, { "flos": 1.1040095247605432e+18, "train_loss": 5.756194458007813, "eval_loss": 5.856988288260795, "eval_accuracy": 0.012944273804300131, "eval_loss_by_set": { "aqua_rat": 5.8478593826293945, "gsm8k": 6.5032958984375, "math_qa": 5.561524709065755 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.021986353297952996, "math_qa": 0.006700167504187605 } }, { "flos": 1.110981795353985e+18, "train_loss": 5.75663818359375, "eval_loss": 5.868277137343948, "eval_accuracy": 0.012505484861781484, "eval_loss_by_set": { "aqua_rat": 5.851232051849365, "gsm8k": 6.531675165349787, "math_qa": 5.565640131632487 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.024260803639120546, "math_qa": 0.005360134003350084 } }, { "flos": 1.1179671108368466e+18, "train_loss": 5.756639404296875, "eval_loss": 5.851896801510373, "eval_accuracy": 0.012724879333040808, "eval_loss_by_set": { "aqua_rat": 5.838677406311035, "gsm8k": 6.512791720303622, "math_qa": 5.550088246663411 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.021986353297952996, "math_qa": 0.006030150753768844 } }, { "flos": 1.124888253065855e+18, "train_loss": 5.759428100585938, "eval_loss": 5.858030319213867, "eval_accuracy": 0.011408512505484861, "eval_loss_by_set": { "aqua_rat": 5.840689659118652, "gsm8k": 6.499751004305753, "math_qa": 5.5653533935546875 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.018953752843062926, "math_qa": 0.005360134003350084 } }, { "flos": 1.1318101157756273e+18, "train_loss": 5.7613134765625, "eval_loss": 5.872166298531197, "eval_accuracy": 0.011189118034225537, "eval_loss_by_set": { "aqua_rat": 5.849916458129883, "gsm8k": 6.526071028275923, "math_qa": 5.574314117431641 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.01592115238817286, "math_qa": 0.005695142378559464 } }, { "flos": 1.1388023966217011e+18, "train_loss": 5.7428759765625, "eval_loss": 5.867893064344251, "eval_accuracy": 0.012724879333040808, "eval_loss_by_set": { "aqua_rat": 5.843817710876465, "gsm8k": 6.528926502574574, "math_qa": 5.566925684611003 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.018953752843062926, "math_qa": 0.007705192629815745 } }, { "flos": 1.1457722147888169e+18, "train_loss": 5.750482177734375, "eval_loss": 5.862759409724055, "eval_accuracy": 0.011189118034225537, "eval_loss_by_set": { "aqua_rat": 5.842892646789551, "gsm8k": 6.506267200816762, "math_qa": 5.56947390238444 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.016679302501895376, "math_qa": 0.006700167504187605 } }, { "flos": 1.15262679254093e+18, "train_loss": 5.745711669921875, "eval_loss": 5.85506212389147, "eval_accuracy": 0.011627906976744186, "eval_loss_by_set": { "aqua_rat": 5.838813781738281, "gsm8k": 6.5185935280539775, "math_qa": 5.552297592163086 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.019711902956785442, "math_qa": 0.005360134003350084 } }, { "flos": 1.159575549262168e+18, "train_loss": 5.75828369140625, "eval_loss": 5.828252019108953, "eval_accuracy": 0.010092145677928916, "eval_loss_by_set": { "aqua_rat": 5.841686248779297, "gsm8k": 6.474307667125355, "math_qa": 5.531023661295573 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.016679302501895376, "math_qa": 0.004020100502512563 } }, { "flos": 1.1664624407376036e+18, "train_loss": 5.75079833984375, "eval_loss": 5.847357260214316, "eval_accuracy": 0.011189118034225537, "eval_loss_by_set": { "aqua_rat": 5.846580505371094, "gsm8k": 6.510991876775568, "math_qa": 5.543256123860677 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.021986353297952996, "math_qa": 0.005360134003350084 } }, { "flos": 1.1734081061561303e+18, "train_loss": 5.757974853515625, "eval_loss": 5.857859663061194, "eval_accuracy": 0.010311540149188241, "eval_loss_by_set": { "aqua_rat": 5.841156482696533, "gsm8k": 6.507763255726207, "math_qa": 5.561379114786784 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.01592115238817286, "math_qa": 0.004690117252931323 } }, { "flos": 1.1803185319048643e+18, "train_loss": 5.7526617431640625, "eval_loss": 5.860533430769637, "eval_accuracy": 0.01184730144800351, "eval_loss_by_set": { "aqua_rat": 5.841281890869141, "gsm8k": 6.497152848677202, "math_qa": 5.570353825887044 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.01819560272934041, "math_qa": 0.007370184254606365 } }, { "flos": 1.1873197774214267e+18, "train_loss": 5.753792114257813, "eval_loss": 5.8464251595574455, "eval_accuracy": 0.012724879333040808, "eval_loss_by_set": { "aqua_rat": 5.844034671783447, "gsm8k": 6.501364274458452, "math_qa": 5.546443939208984 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.019711902956785442, "math_qa": 0.006365159128978224 } }, { "flos": 1.1942595490710815e+18, "train_loss": 5.758753662109375, "eval_loss": 5.862439671078244, "eval_accuracy": 0.009653356735410267, "eval_loss_by_set": { "aqua_rat": 5.849073886871338, "gsm8k": 6.526560696688565, "math_qa": 5.559164683024089 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.01592115238817286, "math_qa": 0.004690117252931323 } }, { "flos": 1.2011003813172347e+18, "train_loss": 5.742318115234375, "eval_loss": 5.859696465569574, "eval_accuracy": 0.011408512505484861, "eval_loss_by_set": { "aqua_rat": 5.841426849365234, "gsm8k": 6.509463223544034, "math_qa": 5.563409169514974 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.01819560272934041, "math_qa": 0.005025125628140704 } }, { "flos": 1.2081554964611072e+18, "train_loss": 5.751145629882813, "eval_loss": 5.844332205282675, "eval_accuracy": 0.011627906976744186, "eval_loss_by_set": { "aqua_rat": 5.846517562866211, "gsm8k": 6.481327403675426, "math_qa": 5.552193959554036 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.01819560272934041, "math_qa": 0.005025125628140704 } }, { "flos": 1.2150557211256422e+18, "train_loss": 5.73951171875, "eval_loss": 5.847619185576567, "eval_accuracy": 0.013821851689337429, "eval_loss_by_set": { "aqua_rat": 5.851632118225098, "gsm8k": 6.499560269442472, "math_qa": 5.548478444417317 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.017437452615617893, "math_qa": 0.008710217755443886 } }, { "flos": 1.2220335150470267e+18, "train_loss": 5.76293212890625, "eval_loss": 5.852822277996991, "eval_accuracy": 0.01184730144800351, "eval_loss_by_set": { "aqua_rat": 5.83961296081543, "gsm8k": 6.503688465465199, "math_qa": 5.555609385172526 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.02047005307050796, "math_qa": 0.005025125628140704 } }, { "flos": 1.2289768724575027e+18, "train_loss": 5.749078369140625, "eval_loss": 5.8571054097768425, "eval_accuracy": 0.011189118034225537, "eval_loss_by_set": { "aqua_rat": 5.850663185119629, "gsm8k": 6.512143915349787, "math_qa": 5.557416280110677 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.021986353297952996, "math_qa": 0.004690117252931323 } }, { "flos": 1.23589611845845e+18, "train_loss": 5.747503662109375, "eval_loss": 5.853614394729202, "eval_accuracy": 0.010969723562966213, "eval_loss_by_set": { "aqua_rat": 5.844669342041016, "gsm8k": 6.506976040926847, "math_qa": 5.55490239461263 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.018953752843062926, "math_qa": 0.004355108877721943 } }, { "flos": 1.242857095435387e+18, "train_loss": 5.75292724609375, "eval_loss": 5.850622898823506, "eval_accuracy": 0.013163668275559455, "eval_loss_by_set": { "aqua_rat": 5.844326972961426, "gsm8k": 6.511434381658381, "math_qa": 5.548275629679362 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.02122820318423048, "math_qa": 0.007370184254606365 } }, { "flos": 1.2497813493682012e+18, "train_loss": 5.755369262695313, "eval_loss": 5.854983407097894, "eval_accuracy": 0.01075032909170689, "eval_loss_by_set": { "aqua_rat": 5.8447160720825195, "gsm8k": 6.522486600008878, "math_qa": 5.549900054931641 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.018953752843062926, "math_qa": 0.005025125628140704 } }, { "flos": 1.256733341273555e+18, "train_loss": 5.744315185546875, "eval_loss": 5.845795837608543, "eval_accuracy": 0.012944273804300131, "eval_loss_by_set": { "aqua_rat": 5.846868991851807, "gsm8k": 6.504893909801137, "math_qa": 5.543619791666667 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.022744503411675512, "math_qa": 0.006030150753768844 } }, { "flos": 1.2637164308896154e+18, "train_loss": 5.741552124023437, "eval_loss": 5.861490120758882, "eval_accuracy": 0.013163668275559455, "eval_loss_by_set": { "aqua_rat": 5.846319675445557, "gsm8k": 6.513165560635653, "math_qa": 5.564069747924805 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.021986353297952996, "math_qa": 0.006700167504187605 } }, { "flos": 1.2706252701848044e+18, "train_loss": 5.762222900390625, "eval_loss": 5.85769864675161, "eval_accuracy": 0.010311540149188241, "eval_loss_by_set": { "aqua_rat": 5.843605995178223, "gsm8k": 6.53112099387429, "math_qa": 5.550221125284831 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.01592115238817286, "math_qa": 0.006700167504187605 } }, { "flos": 1.2775325632917668e+18, "train_loss": 5.750601806640625, "eval_loss": 5.854822545438199, "eval_accuracy": 0.014480035103115402, "eval_loss_by_set": { "aqua_rat": 5.850841999053955, "gsm8k": 6.517491427334872, "math_qa": 5.551431020100911 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.019711902956785442, "math_qa": 0.009380234505862646 } }, { "flos": 1.2845578584777032e+18, "train_loss": 5.74994384765625, "eval_loss": 5.857423163749076, "eval_accuracy": 0.014699429574374727, "eval_loss_by_set": { "aqua_rat": 5.8456315994262695, "gsm8k": 6.498950611461293, "math_qa": 5.564372380574544 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.022744503411675512, "math_qa": 0.008710217755443886 } }, { "flos": 1.2914398037614264e+18, "train_loss": 5.758531494140625, "eval_loss": 5.86351389498324, "eval_accuracy": 0.01184730144800351, "eval_loss_by_set": { "aqua_rat": 5.841992378234863, "gsm8k": 6.508635781028054, "math_qa": 5.569626490275065 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.016679302501895376, "math_qa": 0.007035175879396985 } }, { "flos": 1.2983902092132352e+18, "train_loss": 5.733184814453125, "eval_loss": 5.852877101382694, "eval_accuracy": 0.011189118034225537, "eval_loss_by_set": { "aqua_rat": 5.835660457611084, "gsm8k": 6.497976129705256, "math_qa": 5.55864143371582 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.02047005307050796, "math_qa": 0.005695142378559464 } }, { "flos": 1.3052411190632776e+18, "train_loss": 5.745887451171875, "eval_loss": 5.848689569009317, "eval_accuracy": 0.011408512505484861, "eval_loss_by_set": { "aqua_rat": 5.842442512512207, "gsm8k": 6.520007046786222, "math_qa": 5.541522979736328 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.01592115238817286, "math_qa": 0.005695142378559464 } }, { "flos": 1.312171699482919e+18, "train_loss": 5.735472412109375, "eval_loss": 5.857406358461122, "eval_accuracy": 0.012724879333040808, "eval_loss_by_set": { "aqua_rat": 5.841082572937012, "gsm8k": 6.51971435546875, "math_qa": 5.555208841959636 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.021986353297952996, "math_qa": 0.007370184254606365 } }, { "flos": 1.3191212598999122e+18, "train_loss": 5.751494140625, "eval_loss": 5.867092106793378, "eval_accuracy": 0.010969723562966213, "eval_loss_by_set": { "aqua_rat": 5.856034755706787, "gsm8k": 6.546204306862571, "math_qa": 5.556753794352214 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.01819560272934041, "math_qa": 0.005695142378559464 } }, { "flos": 1.326054374887129e+18, "train_loss": 5.748284912109375, "eval_loss": 5.858759313016324, "eval_accuracy": 0.011408512505484861, "eval_loss_by_set": { "aqua_rat": 5.841003894805908, "gsm8k": 6.50501181862571, "math_qa": 5.564039866129558 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.018953752843062926, "math_qa": 0.005025125628140704 } }, { "flos": 1.3329904576967475e+18, "train_loss": 5.743176879882813, "eval_loss": 5.846784333924989, "eval_accuracy": 0.012944273804300131, "eval_loss_by_set": { "aqua_rat": 5.843793869018555, "gsm8k": 6.514279452237216, "math_qa": 5.541098276774089 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.016679302501895376, "math_qa": 0.007370184254606365 } }, { "flos": 1.3398648400799334e+18, "train_loss": 5.750789794921875, "eval_loss": 5.862402323130015, "eval_accuracy": 0.015357612988152698, "eval_loss_by_set": { "aqua_rat": 5.849279403686523, "gsm8k": 6.518108021129262, "math_qa": 5.562964121500651 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.019711902956785442, "math_qa": 0.009715242881072027 } }, { "flos": 1.3468758953018e+18, "train_loss": 5.74836181640625, "eval_loss": 5.878305125880885, "eval_accuracy": 0.012505484861781484, "eval_loss_by_set": { "aqua_rat": 5.8548688888549805, "gsm8k": 6.531589854847301, "math_qa": 5.5808359781901045 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.01819560272934041, "math_qa": 0.006030150753768844 } }, { "flos": 1.3538240131466527e+18, "train_loss": 5.746795654296875, "eval_loss": 5.850853713783058, "eval_accuracy": 0.009214567792891619, "eval_loss_by_set": { "aqua_rat": 5.843912601470947, "gsm8k": 6.506089643998579, "math_qa": 5.55111567179362 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.01592115238817286, "math_qa": 0.005695142378559464 } }, { "flos": 1.3607902868920074e+18, "train_loss": 5.75510009765625, "eval_loss": 5.8494245168325065, "eval_accuracy": 0.010092145677928916, "eval_loss_by_set": { "aqua_rat": 5.841939926147461, "gsm8k": 6.498270208185369, "math_qa": 5.552660624186198 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.01819560272934041, "math_qa": 0.0036850921273031824 } }, { "flos": 1.3676753852185969e+18, "train_loss": 5.752998657226563, "eval_loss": 5.854101490330052, "eval_accuracy": 0.010969723562966213, "eval_loss_by_set": { "aqua_rat": 5.842740058898926, "gsm8k": 6.515028520063921, "math_qa": 5.552123387654622 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.01592115238817286, "math_qa": 0.007370184254606365 } }, { "flos": 1.3746834726180618e+18, "train_loss": 5.746768798828125, "eval_loss": 5.855621131690773, "eval_accuracy": 0.012724879333040808, "eval_loss_by_set": { "aqua_rat": 5.842853546142578, "gsm8k": 6.4982077858664775, "math_qa": 5.562166213989258 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.02047005307050796, "math_qa": 0.007035175879396985 } }, { "flos": 1.3815915495565558e+18, "train_loss": 5.751934204101563, "eval_loss": 5.865959115930505, "eval_accuracy": 0.011627906976744186, "eval_loss_by_set": { "aqua_rat": 5.847708702087402, "gsm8k": 6.51582821932706, "math_qa": 5.569623311360677 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.02047005307050796, "math_qa": 0.007035175879396985 } }, { "flos": 1.3885509610179133e+18, "train_loss": 5.739290161132812, "eval_loss": 5.852544037071434, "eval_accuracy": 0.012724879333040808, "eval_loss_by_set": { "aqua_rat": 5.843708515167236, "gsm8k": 6.524975169788707, "math_qa": 5.545082728068034 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.021986353297952996, "math_qa": 0.007705192629815745 } }, { "flos": 1.395457862745981e+18, "train_loss": 5.744488525390625, "eval_loss": 5.866758552757469, "eval_accuracy": 0.009433962264150943, "eval_loss_by_set": { "aqua_rat": 5.850020408630371, "gsm8k": 6.5262062766335225, "math_qa": 5.565906524658203 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.01592115238817286, "math_qa": 0.005360134003350084 } }, { "flos": 1.402476192568705e+18, "train_loss": 5.73996826171875, "eval_loss": 5.85402014448836, "eval_accuracy": 0.013602457218078104, "eval_loss_by_set": { "aqua_rat": 5.85153865814209, "gsm8k": 6.52617090398615, "math_qa": 5.5461578369140625 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.02122820318423048, "math_qa": 0.007370184254606365 } }, { "flos": 1.409426968998314e+18, "train_loss": 5.750196533203125, "eval_loss": 5.849806862908441, "eval_accuracy": 0.011408512505484861, "eval_loss_by_set": { "aqua_rat": 5.849787712097168, "gsm8k": 6.52948622270064, "math_qa": 5.538288752237956 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.018953752843062926, "math_qa": 0.006030150753768844 } }, { "flos": 1.4163105839505736e+18, "train_loss": 5.752403564453125, "eval_loss": 5.869042448095374, "eval_accuracy": 0.012066695919262835, "eval_loss_by_set": { "aqua_rat": 5.8513102531433105, "gsm8k": 6.544964877041903, "math_qa": 5.560722351074219 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.021986353297952996, "math_qa": 0.007035175879396985 } }, { "flos": 1.4232269652083343e+18, "train_loss": 5.733125610351562, "eval_loss": 5.86407792890394, "eval_accuracy": 0.010092145677928916, "eval_loss_by_set": { "aqua_rat": 5.849310398101807, "gsm8k": 6.532656582919034, "math_qa": 5.558876673380534 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.015163002274450341, "math_qa": 0.004690117252931323 } }, { "flos": 1.430186108234236e+18, "train_loss": 5.75216064453125, "eval_loss": 5.86617273897738, "eval_accuracy": 0.01601579640193067, "eval_loss_by_set": { "aqua_rat": 5.847136497497559, "gsm8k": 6.526012767444957, "math_qa": 5.565332412719727 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.02350265352539803, "math_qa": 0.009715242881072027 } }, { "flos": 1.4370770799286026e+18, "train_loss": 5.74063720703125, "eval_loss": 5.856666977341111, "eval_accuracy": 0.011189118034225537, "eval_loss_by_set": { "aqua_rat": 5.838340759277344, "gsm8k": 6.51572002064098, "math_qa": 5.556128184000651 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.019711902956785442, "math_qa": 0.005360134003350084 } }, { "flos": 1.4440060325556388e+18, "train_loss": 5.742818603515625, "eval_loss": 5.853642412134119, "eval_accuracy": 0.01601579640193067, "eval_loss_by_set": { "aqua_rat": 5.851573467254639, "gsm8k": 6.523953524502841, "math_qa": 5.546588897705078 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.02047005307050796, "math_qa": 0.010720268006700168 } }, { "flos": 1.4509888752110797e+18, "train_loss": 5.744586181640625, "eval_loss": 5.856209574518977, "eval_accuracy": 0.012944273804300131, "eval_loss_by_set": { "aqua_rat": 5.848956108093262, "gsm8k": 6.536113392223012, "math_qa": 5.5451914469401045 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.017437452615617893, "math_qa": 0.007035175879396985 } }, { "flos": 1.4578651736865505e+18, "train_loss": 5.74735595703125, "eval_loss": 5.856170602746912, "eval_accuracy": 0.015796401930671347, "eval_loss_by_set": { "aqua_rat": 5.843657493591309, "gsm8k": 6.520846280184659, "math_qa": 5.552570343017578 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.022744503411675512, "math_qa": 0.010720268006700168 } }, { "flos": 1.4647702205256172e+18, "train_loss": 5.7499658203125, "eval_loss": 5.857941679052405, "eval_accuracy": 0.017990346643264588, "eval_loss_by_set": { "aqua_rat": 5.847415447235107, "gsm8k": 6.532171075994318, "math_qa": 5.549797058105469 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.022744503411675512, "math_qa": 0.012395309882747068 } }, { "flos": 1.4718189469056369e+18, "train_loss": 5.743711547851563, "eval_loss": 5.870216472728832, "eval_accuracy": 0.013602457218078104, "eval_loss_by_set": { "aqua_rat": 5.848489761352539, "gsm8k": 6.525170759721235, "math_qa": 5.571839650472005 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.019711902956785442, "math_qa": 0.008375209380234505 } }, { "flos": 1.4787878996368425e+18, "train_loss": 5.7515234375, "eval_loss": 5.858383771535513, "eval_accuracy": 0.01228609039052216, "eval_loss_by_set": { "aqua_rat": 5.843181133270264, "gsm8k": 6.501147183504972, "math_qa": 5.565050760904948 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.016679302501895376, "math_qa": 0.008040201005025126 } }, { "flos": 1.4857175732815135e+18, "train_loss": 5.74881591796875, "eval_loss": 5.856701258066538, "eval_accuracy": 0.014041246160596753, "eval_loss_by_set": { "aqua_rat": 5.85146427154541, "gsm8k": 6.522655833851207, "math_qa": 5.551908493041992 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.022744503411675512, "math_qa": 0.007705192629815745 } }, { "flos": 1.4926336249005343e+18, "train_loss": 5.7464501953125, "eval_loss": 5.860381100628827, "eval_accuracy": 0.01338306274681878, "eval_loss_by_set": { "aqua_rat": 5.8568620681762695, "gsm8k": 6.542893843217329, "math_qa": 5.5478560129801435 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.02047005307050796, "math_qa": 0.008710217755443886 } }, { "flos": 1.4996254112884982e+18, "train_loss": 5.747437744140625, "eval_loss": 5.855577520422034, "eval_accuracy": 0.012066695919262835, "eval_loss_by_set": { "aqua_rat": 5.845884323120117, "gsm8k": 6.519532637162642, "math_qa": 5.552072525024414 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.019711902956785442, "math_qa": 0.006030150753768844 } }, { "flos": 1.506523678521688e+18, "train_loss": 5.744259033203125, "eval_loss": 5.8482401048814925, "eval_accuracy": 0.014699429574374727, "eval_loss_by_set": { "aqua_rat": 5.839658737182617, "gsm8k": 6.501176313920454, "math_qa": 5.549692789713542 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.02047005307050796, "math_qa": 0.010385259631490788 } }, { "flos": 1.5134802864431432e+18, "train_loss": 5.74901123046875, "eval_loss": 5.850209313469964, "eval_accuracy": 0.015577007459412023, "eval_loss_by_set": { "aqua_rat": 5.837728500366211, "gsm8k": 6.507045399058949, "math_qa": 5.550199508666992 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.022744503411675512, "math_qa": 0.010385259631490788 } }, { "flos": 1.520400212122665e+18, "train_loss": 5.741412353515625, "eval_loss": 5.867995622995737, "eval_accuracy": 0.013821851689337429, "eval_loss_by_set": { "aqua_rat": 5.846622943878174, "gsm8k": 6.532738425514915, "math_qa": 5.565102895100911 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.021986353297952996, "math_qa": 0.007705192629815745 } }, { "flos": 1.527372750077821e+18, "train_loss": 5.7464447021484375, "eval_loss": 5.849714897774361, "eval_accuracy": 0.01733216322948662, "eval_loss_by_set": { "aqua_rat": 5.845450401306152, "gsm8k": 6.506558504971591, "math_qa": 5.549016952514648 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.022744503411675512, "math_qa": 0.009715242881072027 } }, { "flos": 1.534309183464145e+18, "train_loss": 5.737827758789063, "eval_loss": 5.85118969066723, "eval_accuracy": 0.013821851689337429, "eval_loss_by_set": { "aqua_rat": 5.850582122802734, "gsm8k": 6.519669272682884, "math_qa": 5.544853846232097 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.01819560272934041, "math_qa": 0.009380234505862646 } }, { "flos": 1.5412302430150328e+18, "train_loss": 5.74342041015625, "eval_loss": 5.848605104394861, "eval_accuracy": 0.013602457218078104, "eval_loss_by_set": { "aqua_rat": 5.849447727203369, "gsm8k": 6.492589777166193, "math_qa": 5.553375244140625 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.018953752843062926, "math_qa": 0.007705192629815745 } }, { "flos": 1.5481910347715052e+18, "train_loss": 5.735426025390625, "eval_loss": 5.854800662478885, "eval_accuracy": 0.014041246160596753, "eval_loss_by_set": { "aqua_rat": 5.848976135253906, "gsm8k": 6.511930985884233, "math_qa": 5.554101308186849 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.019711902956785442, "math_qa": 0.008710217755443886 } }, { "flos": 1.555144655006335e+18, "train_loss": 5.748978881835938, "eval_loss": 5.8577878024127035, "eval_accuracy": 0.012505484861781484, "eval_loss_by_set": { "aqua_rat": 5.847422122955322, "gsm8k": 6.513390280983665, "math_qa": 5.558167139689128 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.019711902956785442, "math_qa": 0.005695142378559464 } }, { "flos": 1.5620029011973898e+18, "train_loss": 5.7367529296875, "eval_loss": 5.853741439613136, "eval_accuracy": 0.013821851689337429, "eval_loss_by_set": { "aqua_rat": 5.838169574737549, "gsm8k": 6.4991066672585225, "math_qa": 5.5592466990153 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.02350265352539803, "math_qa": 0.006030150753768844 } }, { "flos": 1.5689518436759634e+18, "train_loss": 5.738939208984375, "eval_loss": 5.8738821390512825, "eval_accuracy": 0.01228609039052216, "eval_loss_by_set": { "aqua_rat": 5.849944114685059, "gsm8k": 6.538653980601918, "math_qa": 5.571189880371094 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.01819560272934041, "math_qa": 0.006700167504187605 } }, { "flos": 1.5758453091357164e+18, "train_loss": 5.72845703125, "eval_loss": 5.855063257990657, "eval_accuracy": 0.015138218516893374, "eval_loss_by_set": { "aqua_rat": 5.847753524780273, "gsm8k": 6.5108559348366475, "math_qa": 5.555100758870442 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.019711902956785442, "math_qa": 0.009715242881072027 } }, { "flos": 1.5828711605199176e+18, "train_loss": 5.744739990234375, "eval_loss": 5.86288715053249, "eval_accuracy": 0.013163668275559455, "eval_loss_by_set": { "aqua_rat": 5.847926139831543, "gsm8k": 6.525342074307528, "math_qa": 5.560508728027344 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.016679302501895376, "math_qa": 0.008375209380234505 } }, { "flos": 1.5897965472503562e+18, "train_loss": 5.739881591796875, "eval_loss": 5.856441214277938, "eval_accuracy": 0.012505484861781484, "eval_loss_by_set": { "aqua_rat": 5.8552327156066895, "gsm8k": 6.509710138494318, "math_qa": 5.557126998901367 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.01592115238817286, "math_qa": 0.008040201005025126 } }, { "flos": 1.596718327818879e+18, "train_loss": 5.7387158203125, "eval_loss": 5.861463031253299, "eval_accuracy": 0.015577007459412023, "eval_loss_by_set": { "aqua_rat": 5.842850685119629, "gsm8k": 6.500486894087358, "math_qa": 5.570128122965495 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.021986353297952996, "math_qa": 0.010050251256281407 } }, { "flos": 1.6036545137077125e+18, "train_loss": 5.737879638671875, "eval_loss": 5.866775306495461, "eval_accuracy": 0.012505484861781484, "eval_loss_by_set": { "aqua_rat": 5.8477325439453125, "gsm8k": 6.519759438254616, "math_qa": 5.569077809651692 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.013646702047005308, "math_qa": 0.008710217755443886 } }, { "flos": 1.6105914410152755e+18, "train_loss": 5.74277099609375, "eval_loss": 5.849958136275008, "eval_accuracy": 0.014480035103115402, "eval_loss_by_set": { "aqua_rat": 5.8424201011657715, "gsm8k": 6.520208185369318, "math_qa": 5.543388366699219 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.02047005307050796, "math_qa": 0.009715242881072027 } }, { "flos": 1.6175017427468288e+18, "train_loss": 5.730221557617187, "eval_loss": 5.853021750579009, "eval_accuracy": 0.019306713470820535, "eval_loss_by_set": { "aqua_rat": 5.840884685516357, "gsm8k": 6.503179376775568, "math_qa": 5.556044260660808 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.024260803639120546, "math_qa": 0.01440536013400335 } }, { "flos": 1.624428181207384e+18, "train_loss": 5.746781005859375, "eval_loss": 5.839506664791623, "eval_accuracy": 0.014041246160596753, "eval_loss_by_set": { "aqua_rat": 5.836533546447754, "gsm8k": 6.50940565629439, "math_qa": 5.532717386881511 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.021986353297952996, "math_qa": 0.008375209380234505 } }, { "flos": 1.631403934482432e+18, "train_loss": 5.739112548828125, "eval_loss": 5.853956583383921, "eval_accuracy": 0.014260640631856078, "eval_loss_by_set": { "aqua_rat": 5.846933364868164, "gsm8k": 6.525973233309659, "math_qa": 5.5465342203776045 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.021986353297952996, "math_qa": 0.009045226130653266 } }, { "flos": 1.638271721943335e+18, "train_loss": 5.736617431640625, "eval_loss": 5.85629483815786, "eval_accuracy": 0.012066695919262835, "eval_loss_by_set": { "aqua_rat": 5.8447160720825195, "gsm8k": 6.51728612726385, "math_qa": 5.55430539449056 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.016679302501895376, "math_qa": 0.007370184254606365 } }, { "flos": 1.64522482731896e+18, "train_loss": 5.73739990234375, "eval_loss": 5.857610805614574, "eval_accuracy": 0.015138218516893374, "eval_loss_by_set": { "aqua_rat": 5.846627235412598, "gsm8k": 6.5240700461647725, "math_qa": 5.5530656178792315 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.025018953752843062, "math_qa": 0.009380234505862646 } }, { "flos": 1.6521841561021972e+18, "train_loss": 5.740508422851563, "eval_loss": 5.851018183940166, "eval_accuracy": 0.015577007459412023, "eval_loss_by_set": { "aqua_rat": 5.844433784484863, "gsm8k": 6.514868302778765, "math_qa": 5.54730224609375 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.01819560272934041, "math_qa": 0.011055276381909548 } }, { "flos": 1.6591764788242022e+18, "train_loss": 5.739478759765625, "eval_loss": 5.850620914149928, "eval_accuracy": 0.012505484861781484, "eval_loss_by_set": { "aqua_rat": 5.849066257476807, "gsm8k": 6.5187530517578125, "math_qa": 5.544523239135742 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.017437452615617893, "math_qa": 0.008375209380234505 } }, { "flos": 1.66607132457907e+18, "train_loss": 5.7393310546875, "eval_loss": 5.8687580211742505, "eval_accuracy": 0.014480035103115402, "eval_loss_by_set": { "aqua_rat": 5.847883224487305, "gsm8k": 6.540788823908025, "math_qa": 5.562483469645183 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.016679302501895376, "math_qa": 0.011390284757118929 } }, { "flos": 1.672995701992194e+18, "train_loss": 5.745235595703125, "eval_loss": 5.851200619259396, "eval_accuracy": 0.013602457218078104, "eval_loss_by_set": { "aqua_rat": 5.841987609863281, "gsm8k": 6.499105973677202, "math_qa": 5.555011749267578 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.01592115238817286, "math_qa": 0.010050251256281407 } }, { "flos": 1.6799737836763873e+18, "train_loss": 5.7375830078125, "eval_loss": 5.866684449685587, "eval_accuracy": 0.012066695919262835, "eval_loss_by_set": { "aqua_rat": 5.850244045257568, "gsm8k": 6.527098222212358, "math_qa": 5.565364837646484 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.018953752843062926, "math_qa": 0.007370184254606365 } }, { "flos": 1.6868980988124856e+18, "train_loss": 5.731451416015625, "eval_loss": 5.858550484116013, "eval_accuracy": 0.012944273804300131, "eval_loss_by_set": { "aqua_rat": 5.844491481781006, "gsm8k": 6.530838706276634, "math_qa": 5.5515899658203125 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.01592115238817286, "math_qa": 0.009715242881072027 } }, { "flos": 1.6938514919509197e+18, "train_loss": 5.74089111328125, "eval_loss": 5.853209186244655, "eval_accuracy": 0.014699429574374727, "eval_loss_by_set": { "aqua_rat": 5.846168041229248, "gsm8k": 6.510801835493608, "math_qa": 5.552399317423503 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.01819560272934041, "math_qa": 0.010050251256281407 } }, { "flos": 1.700738012448555e+18, "train_loss": 5.738796997070312, "eval_loss": 5.85601654568234, "eval_accuracy": 0.012944273804300131, "eval_loss_by_set": { "aqua_rat": 5.84475564956665, "gsm8k": 6.506389964710582, "math_qa": 5.55886713663737 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.016679302501895376, "math_qa": 0.009045226130653266 } }, { "flos": 1.7077121169930322e+18, "train_loss": 5.750474853515625, "eval_loss": 5.85402318593618, "eval_accuracy": 0.01338306274681878, "eval_loss_by_set": { "aqua_rat": 5.850263595581055, "gsm8k": 6.503949252041903, "math_qa": 5.556453704833984 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.02350265352539803, "math_qa": 0.007035175879396985 } }, { "flos": 1.7146315278133494e+18, "train_loss": 5.737440185546875, "eval_loss": 5.8655130541002425, "eval_accuracy": 0.013602457218078104, "eval_loss_by_set": { "aqua_rat": 5.850896835327148, "gsm8k": 6.538202459161932, "math_qa": 5.5584150950113935 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.015163002274450341, "math_qa": 0.011055276381909548 } }, { "flos": 1.7216224283643085e+18, "train_loss": 5.736033325195312, "eval_loss": 5.863368627187368, "eval_accuracy": 0.013602457218078104, "eval_loss_by_set": { "aqua_rat": 5.848250389099121, "gsm8k": 6.519439697265625, "math_qa": 5.5639292399088545 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.02047005307050796, "math_qa": 0.009380234505862646 } }, { "flos": 1.7285457749852815e+18, "train_loss": 5.738920288085938, "eval_loss": 5.858420088484481, "eval_accuracy": 0.014699429574374727, "eval_loss_by_set": { "aqua_rat": 5.841075897216797, "gsm8k": 6.511211048473012, "math_qa": 5.560669581095378 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.016679302501895376, "math_qa": 0.011055276381909548 } }, { "flos": 1.7355477624574444e+18, "train_loss": 5.740156860351562, "eval_loss": 5.85304273141397, "eval_accuracy": 0.01228609039052216, "eval_loss_by_set": { "aqua_rat": 5.847235202789307, "gsm8k": 6.511994101784446, "math_qa": 5.551507314046224 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.017437452615617893, "math_qa": 0.008040201005025126 } }, { "flos": 1.742466822701056e+18, "train_loss": 5.74272216796875, "eval_loss": 5.856991613233411, "eval_accuracy": 0.015577007459412023, "eval_loss_by_set": { "aqua_rat": 5.84555196762085, "gsm8k": 6.522951299493963, "math_qa": 5.552713394165039 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.024260803639120546, "math_qa": 0.010720268006700168 } }, { "flos": 1.74939049949764e+18, "train_loss": 5.743765258789063, "eval_loss": 5.851986137596336, "eval_accuracy": 0.01645458534444932, "eval_loss_by_set": { "aqua_rat": 5.849546432495117, "gsm8k": 6.512576710094105, "math_qa": 5.549418767293294 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.018953752843062926, "math_qa": 0.012730318257956449 } }, { "flos": 1.7563421617642537e+18, "train_loss": 5.740069580078125, "eval_loss": 5.868075345013593, "eval_accuracy": 0.021281263712154455, "eval_loss_by_set": { "aqua_rat": 5.8505964279174805, "gsm8k": 6.53035458651456, "math_qa": 5.565987269083659 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.022744503411675512, "math_qa": 0.019095477386934675 } }, { "flos": 1.7632320822653747e+18, "train_loss": 5.7393701171875, "eval_loss": 5.8557233810424805, "eval_accuracy": 0.017990346643264588, "eval_loss_by_set": { "aqua_rat": 5.841601848602295, "gsm8k": 6.525109030983665, "math_qa": 5.550098419189453 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.018953752843062926, "math_qa": 0.01507537688442211 } }, { "flos": 1.7701920703260918e+18, "train_loss": 5.74174072265625, "eval_loss": 5.862106168592298, "eval_accuracy": 0.017551557700745943, "eval_loss_by_set": { "aqua_rat": 5.848332405090332, "gsm8k": 6.516129927201704, "math_qa": 5.563493092854817 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.025018953752843062, "math_qa": 0.011725293132328308 } }, { "flos": 1.777118240351191e+18, "train_loss": 5.731126098632813, "eval_loss": 5.869029637929556, "eval_accuracy": 0.01689337428696797, "eval_loss_by_set": { "aqua_rat": 5.860308647155762, "gsm8k": 6.538240606134588, "math_qa": 5.563034693400065 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.026535253980288095, "math_qa": 0.010050251256281407 } }, { "flos": 1.7840338592522568e+18, "train_loss": 5.745670166015625, "eval_loss": 5.855463852753511, "eval_accuracy": 0.01689337428696797, "eval_loss_by_set": { "aqua_rat": 5.849869728088379, "gsm8k": 6.518998579545454, "math_qa": 5.551809946695964 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.016679302501895376, "math_qa": 0.01407035175879397 } }, { "flos": 1.7910107872008602e+18, "train_loss": 5.739054565429687, "eval_loss": 5.861417357986038, "eval_accuracy": 0.013821851689337429, "eval_loss_by_set": { "aqua_rat": 5.856078147888184, "gsm8k": 6.52531641179865, "math_qa": 5.557575225830078 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.021986353297952996, "math_qa": 0.007705192629815745 } }, { "flos": 1.7979388534540206e+18, "train_loss": 5.737703857421875, "eval_loss": 5.8518812334215315, "eval_accuracy": 0.01689337428696797, "eval_loss_by_set": { "aqua_rat": 5.847830772399902, "gsm8k": 6.506633411754262, "math_qa": 5.5521240234375 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.021986353297952996, "math_qa": 0.012395309882747068 } }, { "flos": 1.8049189757845504e+18, "train_loss": 5.7360772705078125, "eval_loss": 5.846722602844238, "eval_accuracy": 0.017112768758227294, "eval_loss_by_set": { "aqua_rat": 5.8391499519348145, "gsm8k": 6.498444990678267, "math_qa": 5.548647562662761 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.017437452615617893, "math_qa": 0.01373534338358459 } }, { "flos": 1.8118519055513027e+18, "train_loss": 5.74336181640625, "eval_loss": 5.867636525953138, "eval_accuracy": 0.01733216322948662, "eval_loss_by_set": { "aqua_rat": 5.8477349281311035, "gsm8k": 6.536999095569957, "math_qa": 5.562503814697266 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.022744503411675512, "math_qa": 0.01306532663316583 } }, { "flos": 1.818782156332204e+18, "train_loss": 5.742239990234375, "eval_loss": 5.847987948237239, "eval_accuracy": 0.013821851689337429, "eval_loss_by_set": { "aqua_rat": 5.8483757972717285, "gsm8k": 6.516170154918324, "math_qa": 5.5417054494222 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.01819560272934041, "math_qa": 0.010385259631490788 } }, { "flos": 1.82575387019051e+18, "train_loss": 5.73718505859375, "eval_loss": 5.8510015590770825, "eval_accuracy": 0.014699429574374727, "eval_loss_by_set": { "aqua_rat": 5.850130558013916, "gsm8k": 6.510727622292259, "math_qa": 5.548699696858724 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.02047005307050796, "math_qa": 0.010385259631490788 } }, { "flos": 1.8326919109683446e+18, "train_loss": 5.73072998046875, "eval_loss": 5.864069500484982, "eval_accuracy": 0.014041246160596753, "eval_loss_by_set": { "aqua_rat": 5.855013847351074, "gsm8k": 6.536793101917613, "math_qa": 5.5564924875895185 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.022744503411675512, "math_qa": 0.009045226130653266 } }, { "flos": 1.839600131788243e+18, "train_loss": 5.735078125, "eval_loss": 5.874137311368375, "eval_accuracy": 0.019306713470820535, "eval_loss_by_set": { "aqua_rat": 5.85476016998291, "gsm8k": 6.536766745827415, "math_qa": 5.5720469156901045 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.024260803639120546, "math_qa": 0.01507537688442211 } }, { "flos": 1.8465361732588012e+18, "train_loss": 5.734781494140625, "eval_loss": 5.847580316904429, "eval_accuracy": 0.015796401930671347, "eval_loss_by_set": { "aqua_rat": 5.849921226501465, "gsm8k": 6.522487293590199, "math_qa": 5.538052876790364 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.017437452615617893, "math_qa": 0.012395309882747068 } }, { "flos": 1.8534759653095506e+18, "train_loss": 5.735094604492187, "eval_loss": 5.844186628187025, "eval_accuracy": 0.016235190873189996, "eval_loss_by_set": { "aqua_rat": 5.851484298706055, "gsm8k": 6.515285145152699, "math_qa": 5.535991668701172 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.019711902956785442, "math_qa": 0.012060301507537688 } }, { "flos": 1.8604404668440248e+18, "train_loss": 5.740091552734375, "eval_loss": 5.86399794913627, "eval_accuracy": 0.01338306274681878, "eval_loss_by_set": { "aqua_rat": 5.8496503829956055, "gsm8k": 6.523202375932173, "math_qa": 5.563058217366536 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.01819560272934041, "math_qa": 0.009715242881072027 } }, { "flos": 1.8673984765354312e+18, "train_loss": 5.741624755859375, "eval_loss": 5.852657369665198, "eval_accuracy": 0.015138218516893374, "eval_loss_by_set": { "aqua_rat": 5.84610652923584, "gsm8k": 6.526826338334517, "math_qa": 5.544209162394206 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.021986353297952996, "math_qa": 0.011055276381909548 } }, { "flos": 1.8743608966213796e+18, "train_loss": 5.737940673828125, "eval_loss": 5.859424436414564, "eval_accuracy": 0.013602457218078104, "eval_loss_by_set": { "aqua_rat": 5.842185020446777, "gsm8k": 6.518016468394887, "math_qa": 5.559006373087565 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.018953752843062926, "math_qa": 0.009380234505862646 } }, { "flos": 1.8813730229007155e+18, "train_loss": 5.747899780273437, "eval_loss": 5.856668781589818, "eval_accuracy": 0.01689337428696797, "eval_loss_by_set": { "aqua_rat": 5.851840019226074, "gsm8k": 6.528832869096235, "math_qa": 5.5489959716796875 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.02350265352539803, "math_qa": 0.011390284757118929 } }, { "flos": 1.888283036332589e+18, "train_loss": 5.734426879882813, "eval_loss": 5.859874080967259, "eval_accuracy": 0.013821851689337429, "eval_loss_by_set": { "aqua_rat": 5.850152492523193, "gsm8k": 6.520609075372869, "math_qa": 5.557847340901692 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.019711902956785442, "math_qa": 0.008710217755443886 } }, { "flos": 1.895215718601851e+18, "train_loss": 5.736563110351563, "eval_loss": 5.857686455185349, "eval_accuracy": 0.017551557700745943, "eval_loss_by_set": { "aqua_rat": 5.849548816680908, "gsm8k": 6.515068054199219, "math_qa": 5.557064692179362 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.022744503411675512, "math_qa": 0.01373534338358459 } }, { "flos": 1.9021678962645402e+18, "train_loss": 5.737196044921875, "eval_loss": 5.87049607972841, "eval_accuracy": 0.015796401930671347, "eval_loss_by_set": { "aqua_rat": 5.852025985717773, "gsm8k": 6.5310446999289775, "math_qa": 5.569283803304036 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.02577710386656558, "math_qa": 0.008375209380234505 } }, { "flos": 1.9090956328789606e+18, "train_loss": 5.730874633789062, "eval_loss": 5.8625690872604785, "eval_accuracy": 0.014041246160596753, "eval_loss_by_set": { "aqua_rat": 5.852585792541504, "gsm8k": 6.540376143022017, "math_qa": 5.5527394612630205 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.02047005307050796, "math_qa": 0.008040201005025126 } }, { "flos": 1.9160264194570322e+18, "train_loss": 5.7418585205078125, "eval_loss": 5.845612242415145, "eval_accuracy": 0.015357612988152698, "eval_loss_by_set": { "aqua_rat": 5.844460487365723, "gsm8k": 6.510544516823509, "math_qa": 5.540947596232097 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.02047005307050796, "math_qa": 0.011390284757118929 } }, { "flos": 1.9229872729536594e+18, "train_loss": 5.744146118164062, "eval_loss": 5.856475520778346, "eval_accuracy": 0.017770952172005264, "eval_loss_by_set": { "aqua_rat": 5.84782600402832, "gsm8k": 6.5207907936789775, "math_qa": 5.55271848042806 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.022744503411675512, "math_qa": 0.01340033500837521 } }, { "flos": 1.9299098985569976e+18, "train_loss": 5.722872314453125, "eval_loss": 5.84351024112186, "eval_accuracy": 0.01228609039052216, "eval_loss_by_set": { "aqua_rat": 5.841317176818848, "gsm8k": 6.499269658868963, "math_qa": 5.5431365966796875 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.013646702047005308, "math_qa": 0.008375209380234505 } }, { "flos": 1.93689838748382e+18, "train_loss": 5.7438037109375, "eval_loss": 5.852712270375845, "eval_accuracy": 0.01601579640193067, "eval_loss_by_set": { "aqua_rat": 5.852073669433594, "gsm8k": 6.532731489701704, "math_qa": 5.54109001159668 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.01819560272934041, "math_qa": 0.012395309882747068 } }, { "flos": 1.9438947077466358e+18, "train_loss": 5.736912841796875, "eval_loss": 5.84330484029409, "eval_accuracy": 0.011627906976744186, "eval_loss_by_set": { "aqua_rat": 5.853123188018799, "gsm8k": 6.522900668057528, "math_qa": 5.531005223592122 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.019711902956785442, "math_qa": 0.005360134003350084 } }, { "flos": 1.9508006613606728e+18, "train_loss": 5.7321484375, "eval_loss": 5.865591100744299, "eval_accuracy": 0.01228609039052216, "eval_loss_by_set": { "aqua_rat": 5.851837158203125, "gsm8k": 6.531797929243608, "math_qa": 5.561392466227214 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.019711902956785442, "math_qa": 0.008040201005025126 } }, { "flos": 1.9577270584821678e+18, "train_loss": 5.728470458984375, "eval_loss": 5.846689971717629, "eval_accuracy": 0.012066695919262835, "eval_loss_by_set": { "aqua_rat": 5.842299938201904, "gsm8k": 6.502932461825284, "math_qa": 5.54627799987793 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.017437452615617893, "math_qa": 0.006700167504187605 } }, { "flos": 1.9646655727801467e+18, "train_loss": 5.737742919921875, "eval_loss": 5.860995911263131, "eval_accuracy": 0.013163668275559455, "eval_loss_by_set": { "aqua_rat": 5.857043743133545, "gsm8k": 6.543300281871449, "math_qa": 5.54860242207845 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.019711902956785442, "math_qa": 0.007035175879396985 } }, { "flos": 1.9716644485485036e+18, "train_loss": 5.72385498046875, "eval_loss": 5.844004141317831, "eval_accuracy": 0.014699429574374727, "eval_loss_by_set": { "aqua_rat": 5.84788703918457, "gsm8k": 6.5168540261008525, "math_qa": 5.535291035970052 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.017437452615617893, "math_qa": 0.012060301507537688 } }, { "flos": 1.9786297741798277e+18, "train_loss": 5.739600830078125, "eval_loss": 5.867814347550675, "eval_accuracy": 0.015577007459412023, "eval_loss_by_set": { "aqua_rat": 5.854759216308594, "gsm8k": 6.537357677112926, "math_qa": 5.562028249104817 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.02350265352539803, "math_qa": 0.008710217755443886 } }, { "flos": 1.9855007764237517e+18, "train_loss": 5.728941040039063, "eval_loss": 5.8591203689575195, "eval_accuracy": 0.014260640631856078, "eval_loss_by_set": { "aqua_rat": 5.846649646759033, "gsm8k": 6.518013000488281, "math_qa": 5.558167139689128 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.02047005307050796, "math_qa": 0.009045226130653266 } }, { "flos": 1.9924913059969106e+18, "train_loss": 5.733834838867187, "eval_loss": 5.863366410538957, "eval_accuracy": 0.019306713470820535, "eval_loss_by_set": { "aqua_rat": 5.854270935058594, "gsm8k": 6.527498418634588, "math_qa": 5.559730529785156 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.026535253980288095, "math_qa": 0.01373534338358459 } }, { "flos": 1.9993864196503634e+18, "train_loss": 5.737245483398437, "eval_loss": 5.842531616623337, "eval_accuracy": 0.01184730144800351, "eval_loss_by_set": { "aqua_rat": 5.843976020812988, "gsm8k": 6.5052573464133525, "math_qa": 5.538661956787109 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.01592115238817286, "math_qa": 0.006700167504187605 } }, { "flos": 2.0063107353233326e+18, "train_loss": 5.733111572265625, "eval_loss": 5.8490612442429, "eval_accuracy": 0.01645458534444932, "eval_loss_by_set": { "aqua_rat": 5.851134300231934, "gsm8k": 6.517540671608665, "math_qa": 5.542502085367839 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.01819560272934041, "math_qa": 0.012730318257956449 } }, { "flos": 2.01326994062626e+18, "train_loss": 5.728209228515625, "eval_loss": 5.861179532231511, "eval_accuracy": 0.014041246160596753, "eval_loss_by_set": { "aqua_rat": 5.84680700302124, "gsm8k": 6.517770940607244, "math_qa": 5.561439514160156 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.02047005307050796, "math_qa": 0.008710217755443886 } }, { "flos": 2.0202584912932372e+18, "train_loss": 5.74039794921875, "eval_loss": 5.851718077788481, "eval_accuracy": 0.011408512505484861, "eval_loss_by_set": { "aqua_rat": 5.85078239440918, "gsm8k": 6.530046636408025, "math_qa": 5.540895462036133 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.018953752843062926, "math_qa": 0.006365159128978224 } }, { "flos": 2.0271451352711823e+18, "train_loss": 5.72620361328125, "eval_loss": 5.856472170030749, "eval_accuracy": 0.012944273804300131, "eval_loss_by_set": { "aqua_rat": 5.848397254943848, "gsm8k": 6.504533247514204, "math_qa": 5.560117085774739 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.018953752843062926, "math_qa": 0.006700167504187605 } }, { "flos": 2.0341305328952934e+18, "train_loss": 5.731971435546875, "eval_loss": 5.859355565663931, "eval_accuracy": 0.013821851689337429, "eval_loss_by_set": { "aqua_rat": 5.849783897399902, "gsm8k": 6.534235174005682, "math_qa": 5.550833384195964 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.021986353297952996, "math_qa": 0.008710217755443886 } }, { "flos": 2.0409854606872412e+18, "train_loss": 5.732554931640625, "eval_loss": 5.841853322209539, "eval_accuracy": 0.013163668275559455, "eval_loss_by_set": { "aqua_rat": 5.840849876403809, "gsm8k": 6.5067970969460225, "math_qa": 5.537171045939128 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.018953752843062926, "math_qa": 0.007370184254606365 } }, { "flos": 2.0479511986354258e+18, "train_loss": 5.738382568359375, "eval_loss": 5.85136586266595, "eval_accuracy": 0.014041246160596753, "eval_loss_by_set": { "aqua_rat": 5.844911098480225, "gsm8k": 6.515472412109375, "math_qa": 5.547521591186523 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.02350265352539803, "math_qa": 0.007035175879396985 } }, { "flos": 2.0549235927091773e+18, "train_loss": 5.7259130859375, "eval_loss": 5.869949959419869, "eval_accuracy": 0.014260640631856078, "eval_loss_by_set": { "aqua_rat": 5.859733581542969, "gsm8k": 6.535634127530185, "math_qa": 5.565696080525716 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.024260803639120546, "math_qa": 0.007705192629815745 } }, { "flos": 2.0618404480239534e+18, "train_loss": 5.727548828125, "eval_loss": 5.844214336292164, "eval_accuracy": 0.015357612988152698, "eval_loss_by_set": { "aqua_rat": 5.843307018280029, "gsm8k": 6.506558504971591, "math_qa": 5.5407155354817705 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.024260803639120546, "math_qa": 0.008710217755443886 } }, { "flos": 2.068771069782655e+18, "train_loss": 5.73830322265625, "eval_loss": 5.86090459050359, "eval_accuracy": 0.013602457218078104, "eval_loss_by_set": { "aqua_rat": 5.848060607910156, "gsm8k": 6.517253528941762, "math_qa": 5.561148325602214 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.018953752843062926, "math_qa": 0.008375209380234505 } }, { "flos": 2.0757658234561495e+18, "train_loss": 5.73550048828125, "eval_loss": 5.847916139138712, "eval_accuracy": 0.012505484861781484, "eval_loss_by_set": { "aqua_rat": 5.849473476409912, "gsm8k": 6.519162264737216, "math_qa": 5.54013188680013 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.016679302501895376, "math_qa": 0.007705192629815745 } }, { "flos": 2.0827573215444337e+18, "train_loss": 5.73013427734375, "eval_loss": 5.846779514003444, "eval_accuracy": 0.014480035103115402, "eval_loss_by_set": { "aqua_rat": 5.849991321563721, "gsm8k": 6.5226662375710225, "math_qa": 5.536730448404948 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.01819560272934041, "math_qa": 0.010385259631490788 } }, { "flos": 2.089691776024576e+18, "train_loss": 5.7356884765625, "eval_loss": 5.862935117773108, "eval_accuracy": 0.014041246160596753, "eval_loss_by_set": { "aqua_rat": 5.848901271820068, "gsm8k": 6.52250879461115, "math_qa": 5.561800003051758 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.021986353297952996, "math_qa": 0.008040201005025126 } }, { "flos": 2.0965766681927352e+18, "train_loss": 5.7345751953125, "eval_loss": 5.868132539697595, "eval_accuracy": 0.010530934620447565, "eval_loss_by_set": { "aqua_rat": 5.844849109649658, "gsm8k": 6.514767039905895, "math_qa": 5.57369867960612 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.017437452615617893, "math_qa": 0.006030150753768844 } }, { "flos": 2.1034865168052388e+18, "train_loss": 5.727843017578125, "eval_loss": 5.854242067079286, "eval_accuracy": 0.01491882404563405, "eval_loss_by_set": { "aqua_rat": 5.842884063720703, "gsm8k": 6.516175703568892, "math_qa": 5.551802317301433 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.02122820318423048, "math_qa": 0.009380234505862646 } }, { "flos": 2.1104913067435622e+18, "train_loss": 5.728255615234375, "eval_loss": 5.847779712161502, "eval_accuracy": 0.012724879333040808, "eval_loss_by_set": { "aqua_rat": 5.845370292663574, "gsm8k": 6.5051116943359375, "math_qa": 5.546703338623047 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.018953752843062926, "math_qa": 0.007035175879396985 } }, { "flos": 2.117428131508781e+18, "train_loss": 5.721617431640625, "eval_loss": 5.862444362124881, "eval_accuracy": 0.012724879333040808, "eval_loss_by_set": { "aqua_rat": 5.853097438812256, "gsm8k": 6.51435643976385, "math_qa": 5.564430236816406 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.022744503411675512, "math_qa": 0.006030150753768844 } }, { "flos": 2.124371324099887e+18, "train_loss": 5.730731811523437, "eval_loss": 5.860254236169763, "eval_accuracy": 0.014041246160596753, "eval_loss_by_set": { "aqua_rat": 5.849666595458984, "gsm8k": 6.520557056773793, "math_qa": 5.5584977467854815 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.019711902956785442, "math_qa": 0.009380234505862646 } }, { "flos": 2.1313246968372265e+18, "train_loss": 5.75304931640625, "eval_loss": 5.85849395958153, "eval_accuracy": 0.01645458534444932, "eval_loss_by_set": { "aqua_rat": 5.843079566955566, "gsm8k": 6.520160328258168, "math_qa": 5.556514739990234 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.02577710386656558, "math_qa": 0.010720268006700168 } }, { "flos": 2.1382870965220803e+18, "train_loss": 5.72287109375, "eval_loss": 5.877913578136547, "eval_accuracy": 0.01491882404563405, "eval_loss_by_set": { "aqua_rat": 5.855323314666748, "gsm8k": 6.541179310191762, "math_qa": 5.575799306233724 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.021986353297952996, "math_qa": 0.009715242881072027 } }, { "flos": 2.1451937920917176e+18, "train_loss": 5.732115478515625, "eval_loss": 5.868025058024639, "eval_accuracy": 0.014041246160596753, "eval_loss_by_set": { "aqua_rat": 5.853637218475342, "gsm8k": 6.541921442205256, "math_qa": 5.560354868570964 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.02577710386656558, "math_qa": 0.006365159128978224 } }, { "flos": 2.152188875940823e+18, "train_loss": 5.73492919921875, "eval_loss": 5.870774294878985, "eval_accuracy": 0.01491882404563405, "eval_loss_by_set": { "aqua_rat": 5.8484601974487305, "gsm8k": 6.52392578125, "math_qa": 5.573272705078125 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.024260803639120546, "math_qa": 0.008375209380234505 } }, { "flos": 2.159145546139304e+18, "train_loss": 5.742755737304687, "eval_loss": 5.854151184494431, "eval_accuracy": 0.014041246160596753, "eval_loss_by_set": { "aqua_rat": 5.84481143951416, "gsm8k": 6.525301846590909, "math_qa": 5.547318776448567 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.02122820318423048, "math_qa": 0.008710217755443886 } }, { "flos": 2.1661143753901998e+18, "train_loss": 5.738258056640625, "eval_loss": 5.851778648995064, "eval_accuracy": 0.013602457218078104, "eval_loss_by_set": { "aqua_rat": 5.848610877990723, "gsm8k": 6.525303233753551, "math_qa": 5.543343861897786 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.019711902956785442, "math_qa": 0.009045226130653266 } }, { "flos": 2.1730899842469724e+18, "train_loss": 5.742506713867187, "eval_loss": 5.84521788519782, "eval_accuracy": 0.01338306274681878, "eval_loss_by_set": { "aqua_rat": 5.843783378601074, "gsm8k": 6.513018521395597, "math_qa": 5.539262135823567 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.01592115238817286, "math_qa": 0.010050251256281407 } }, { "flos": 2.180039523726e+18, "train_loss": 5.726429443359375, "eval_loss": 5.854534381144756, "eval_accuracy": 0.012944273804300131, "eval_loss_by_set": { "aqua_rat": 5.839876651763916, "gsm8k": 6.511545354669744, "math_qa": 5.554625829060872 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.017437452615617893, "math_qa": 0.008710217755443886 } }, { "flos": 2.18692738317969e+18, "train_loss": 5.727838745117188, "eval_loss": 5.853537275984481, "eval_accuracy": 0.013163668275559455, "eval_loss_by_set": { "aqua_rat": 5.84619140625, "gsm8k": 6.523314736106179, "math_qa": 5.547168095906575 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.022744503411675512, "math_qa": 0.007370184254606365 } }, { "flos": 2.1938754392843878e+18, "train_loss": 5.739254150390625, "eval_loss": 5.851998509587468, "eval_accuracy": 0.017551557700745943, "eval_loss_by_set": { "aqua_rat": 5.848138809204102, "gsm8k": 6.519868330522017, "math_qa": 5.546213150024414 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.02122820318423048, "math_qa": 0.01373534338358459 } }, { "flos": 2.2008052364093686e+18, "train_loss": 5.73612060546875, "eval_loss": 5.861904505136851, "eval_accuracy": 0.016235190873189996, "eval_loss_by_set": { "aqua_rat": 5.848267555236816, "gsm8k": 6.517281965775923, "math_qa": 5.562659581502278 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.02122820318423048, "math_qa": 0.011055276381909548 } }, { "flos": 2.207771695912059e+18, "train_loss": 5.731038818359375, "eval_loss": 5.842003332602011, "eval_accuracy": 0.013821851689337429, "eval_loss_by_set": { "aqua_rat": 5.842606544494629, "gsm8k": 6.513404846191406, "math_qa": 5.53422737121582 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.01819560272934041, "math_qa": 0.008710217755443886 } }, { "flos": 2.2147478609670963e+18, "train_loss": 5.726728515625, "eval_loss": 5.863938924428579, "eval_accuracy": 0.01338306274681878, "eval_loss_by_set": { "aqua_rat": 5.848947525024414, "gsm8k": 6.524299621582031, "math_qa": 5.562522888183594 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.016679302501895376, "math_qa": 0.009380234505862646 } }, { "flos": 2.2217003682685256e+18, "train_loss": 5.734737548828125, "eval_loss": 5.85039489333694, "eval_accuracy": 0.015357612988152698, "eval_loss_by_set": { "aqua_rat": 5.847772598266602, "gsm8k": 6.520648609508168, "math_qa": 5.543413798014323 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.019711902956785442, "math_qa": 0.011055276381909548 } }, { "flos": 2.2286151013325865e+18, "train_loss": 5.731727294921875, "eval_loss": 5.858657166764543, "eval_accuracy": 0.01338306274681878, "eval_loss_by_set": { "aqua_rat": 5.844050407409668, "gsm8k": 6.513438831676137, "math_qa": 5.559766133626302 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.02047005307050796, "math_qa": 0.008710217755443886 } }, { "flos": 2.2355867126485484e+18, "train_loss": 5.7238134765625, "eval_loss": 5.857663902076515, "eval_accuracy": 0.015357612988152698, "eval_loss_by_set": { "aqua_rat": 5.854784965515137, "gsm8k": 6.522686351429332, "math_qa": 5.553101857503255 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.017437452615617893, "math_qa": 0.011390284757118929 } }, { "flos": 2.2425241349510922e+18, "train_loss": 5.731267700195312, "eval_loss": 5.861077360204749, "eval_accuracy": 0.015357612988152698, "eval_loss_by_set": { "aqua_rat": 5.847651958465576, "gsm8k": 6.529808044433594, "math_qa": 5.555694580078125 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.021986353297952996, "math_qa": 0.009715242881072027 } }, { "flos": 2.2494680281587384e+18, "train_loss": 5.721590576171875, "eval_loss": 5.839927931089659, "eval_accuracy": 0.017770952172005264, "eval_loss_by_set": { "aqua_rat": 5.841275215148926, "gsm8k": 6.499929948286577, "math_qa": 5.537314732869466 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.02350265352539803, "math_qa": 0.012060301507537688 } }, { "flos": 2.2564585985340867e+18, "train_loss": 5.74083984375, "eval_loss": 5.861403387946051, "eval_accuracy": 0.016673979815708645, "eval_loss_by_set": { "aqua_rat": 5.856075286865234, "gsm8k": 6.530813043767756, "math_qa": 5.555034637451172 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.02047005307050796, "math_qa": 0.012060301507537688 } }, { "flos": 2.2634200501049098e+18, "train_loss": 5.742431640625, "eval_loss": 5.848411456958668, "eval_accuracy": 0.017551557700745943, "eval_loss_by_set": { "aqua_rat": 5.847986221313477, "gsm8k": 6.506411465731534, "math_qa": 5.546863555908203 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.016679302501895376, "math_qa": 0.01541038525963149 } }, { "flos": 2.2704328979387515e+18, "train_loss": 5.73358642578125, "eval_loss": 5.855464471353067, "eval_accuracy": 0.015577007459412023, "eval_loss_by_set": { "aqua_rat": 5.846230506896973, "gsm8k": 6.52748593417081, "math_qa": 5.548224131266276 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.02047005307050796, "math_qa": 0.010050251256281407 } }, { "flos": 2.277288876923945e+18, "train_loss": 5.728436279296875, "eval_loss": 5.841067391472894, "eval_accuracy": 0.015138218516893374, "eval_loss_by_set": { "aqua_rat": 5.849678993225098, "gsm8k": 6.511799205433238, "math_qa": 5.532931009928386 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.01592115238817286, "math_qa": 0.011725293132328308 } }, { "flos": 2.2842541198771487e+18, "train_loss": 5.726140747070312, "eval_loss": 5.858709593076964, "eval_accuracy": 0.01689337428696797, "eval_loss_by_set": { "aqua_rat": 5.8473663330078125, "gsm8k": 6.525378834117543, "math_qa": 5.554098129272461 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.021986353297952996, "math_qa": 0.011725293132328308 } }, { "flos": 2.291174725772116e+18, "train_loss": 5.72564697265625, "eval_loss": 5.865877048389332, "eval_accuracy": 0.015796401930671347, "eval_loss_by_set": { "aqua_rat": 5.851977348327637, "gsm8k": 6.53119590065696, "math_qa": 5.562097549438477 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.022744503411675512, "math_qa": 0.009715242881072027 } }, { "flos": 2.2980941779314934e+18, "train_loss": 5.724193725585938, "eval_loss": 5.862525733741554, "eval_accuracy": 0.012944273804300131, "eval_loss_by_set": { "aqua_rat": 5.850101470947266, "gsm8k": 6.53316913951527, "math_qa": 5.556182861328125 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.018953752843062926, "math_qa": 0.007370184254606365 } }, { "flos": 2.3049930840410685e+18, "train_loss": 5.714996337890625, "eval_loss": 5.849330154625145, "eval_accuracy": 0.014699429574374727, "eval_loss_by_set": { "aqua_rat": 5.846202373504639, "gsm8k": 6.52329531582919, "math_qa": 5.540690104166667 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.024260803639120546, "math_qa": 0.008375209380234505 } }, { "flos": 2.312000223326503e+18, "train_loss": 5.733660888671875, "eval_loss": 5.853077630738954, "eval_accuracy": 0.01228609039052216, "eval_loss_by_set": { "aqua_rat": 5.847903728485107, "gsm8k": 6.513069152832031, "math_qa": 5.551012674967448 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.01592115238817286, "math_qa": 0.008375209380234505 } }, { "flos": 2.318922313132671e+18, "train_loss": 5.728961181640625, "eval_loss": 5.860303930334143, "eval_accuracy": 0.015357612988152698, "eval_loss_by_set": { "aqua_rat": 5.847812652587891, "gsm8k": 6.522739757191051, "math_qa": 5.557728449503581 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.022744503411675512, "math_qa": 0.009715242881072027 } }, { "flos": 2.325842177608909e+18, "train_loss": 5.73671875, "eval_loss": 5.850900031424858, "eval_accuracy": 0.015138218516893374, "eval_loss_by_set": { "aqua_rat": 5.849625587463379, "gsm8k": 6.50829453901811, "math_qa": 5.549700419108073 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.01592115238817286, "math_qa": 0.012395309882747068 } }, { "flos": 2.3328483279781233e+18, "train_loss": 5.720328369140625, "eval_loss": 5.847131316726272, "eval_accuracy": 0.01645458534444932, "eval_loss_by_set": { "aqua_rat": 5.848259925842285, "gsm8k": 6.512872869318182, "math_qa": 5.5419057210286455 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.02122820318423048, "math_qa": 0.012730318257956449 } }, { "flos": 2.3398058636125143e+18, "train_loss": 5.725439453125, "eval_loss": 5.854332691914326, "eval_accuracy": 0.012066695919262835, "eval_loss_by_set": { "aqua_rat": 5.845876693725586, "gsm8k": 6.523041465065696, "math_qa": 5.548545837402344 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.01819560272934041, "math_qa": 0.007370184254606365 } }, { "flos": 2.3467930130464113e+18, "train_loss": 5.7351171875, "eval_loss": 5.849495707331477, "eval_accuracy": 0.014041246160596753, "eval_loss_by_set": { "aqua_rat": 5.843207359313965, "gsm8k": 6.506499550559304, "math_qa": 5.548892974853516 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.019711902956785442, "math_qa": 0.008710217755443886 } }, { "flos": 2.353684705758413e+18, "train_loss": 5.7348291015625, "eval_loss": 5.858246725958747, "eval_accuracy": 0.016673979815708645, "eval_loss_by_set": { "aqua_rat": 5.847878456115723, "gsm8k": 6.5320587158203125, "math_qa": 5.550280253092448 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.02047005307050796, "math_qa": 0.012730318257956449 } }, { "flos": 2.360652710375588e+18, "train_loss": 5.724559326171875, "eval_loss": 5.8498506288270695, "eval_accuracy": 0.014480035103115402, "eval_loss_by_set": { "aqua_rat": 5.847679138183594, "gsm8k": 6.502903331409801, "math_qa": 5.5507157643636065 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.02047005307050796, "math_qa": 0.009380234505862646 } }, { "flos": 2.3675872679349453e+18, "train_loss": 5.737033081054688, "eval_loss": 5.855655824815905, "eval_accuracy": 0.01733216322948662, "eval_loss_by_set": { "aqua_rat": 5.851273536682129, "gsm8k": 6.527067011052912, "math_qa": 5.548290888468425 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.024260803639120546, "math_qa": 0.011390284757118929 } }, { "flos": 2.3745486572287427e+18, "train_loss": 5.7240576171875, "eval_loss": 5.843472970498575, "eval_accuracy": 0.01338306274681878, "eval_loss_by_set": { "aqua_rat": 5.84581184387207, "gsm8k": 6.499846024946733, "math_qa": 5.542440414428711 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.017437452615617893, "math_qa": 0.008710217755443886 } }, { "flos": 2.381564472348115e+18, "train_loss": 5.732655029296875, "eval_loss": 5.85396671295166, "eval_accuracy": 0.013821851689337429, "eval_loss_by_set": { "aqua_rat": 5.846571445465088, "gsm8k": 6.511166659268466, "math_qa": 5.553366343180339 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.019711902956785442, "math_qa": 0.009045226130653266 } }, { "flos": 2.388556753194189e+18, "train_loss": 5.736946411132813, "eval_loss": 5.848055813763593, "eval_accuracy": 0.012505484861781484, "eval_loss_by_set": { "aqua_rat": 5.84281063079834, "gsm8k": 6.509424382990057, "math_qa": 5.545365651448567 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.01592115238817286, "math_qa": 0.008375209380234505 } }, { "flos": 2.395440656446128e+18, "train_loss": 5.723621826171875, "eval_loss": 5.847924258257891, "eval_accuracy": 0.01733216322948662, "eval_loss_by_set": { "aqua_rat": 5.851576805114746, "gsm8k": 6.508465853604403, "math_qa": 5.544871648152669 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.02047005307050796, "math_qa": 0.01340033500837521 } }, { "flos": 2.402330906585989e+18, "train_loss": 5.726679077148438, "eval_loss": 5.8497178876722185, "eval_accuracy": 0.013821851689337429, "eval_loss_by_set": { "aqua_rat": 5.851925849914551, "gsm8k": 6.51175967129794, "math_qa": 5.546098073323567 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.019711902956785442, "math_qa": 0.009380234505862646 } }, { "flos": 2.4093086586314424e+18, "train_loss": 5.728361206054688, "eval_loss": 5.840375384768924, "eval_accuracy": 0.012944273804300131, "eval_loss_by_set": { "aqua_rat": 5.842827796936035, "gsm8k": 6.5064170143821025, "math_qa": 5.534901936848958 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.02047005307050796, "math_qa": 0.007035175879396985 } }, { "flos": 2.416279301432279e+18, "train_loss": 5.733924560546875, "eval_loss": 5.852282189034127, "eval_accuracy": 0.01228609039052216, "eval_loss_by_set": { "aqua_rat": 5.8483171463012695, "gsm8k": 6.508845242587003, "math_qa": 5.551687876383464 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.018953752843062926, "math_qa": 0.006700167504187605 } }, { "flos": 2.423180123634139e+18, "train_loss": 5.72890625, "eval_loss": 5.854374112309636, "eval_accuracy": 0.014699429574374727, "eval_loss_by_set": { "aqua_rat": 5.843129634857178, "gsm8k": 6.513258500532671, "math_qa": 5.553322474161784 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.025018953752843062, "math_qa": 0.007705192629815745 } }, { "flos": 2.430181740128502e+18, "train_loss": 5.7223138427734375, "eval_loss": 5.847805126293285, "eval_accuracy": 0.014699429574374727, "eval_loss_by_set": { "aqua_rat": 5.848628997802734, "gsm8k": 6.504782243208452, "math_qa": 5.546621958414714 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.019711902956785442, "math_qa": 0.010050251256281407 } }, { "flos": 2.437082108674441e+18, "train_loss": 5.721657104492188, "eval_loss": 5.860149280444996, "eval_accuracy": 0.014480035103115402, "eval_loss_by_set": { "aqua_rat": 5.846294403076172, "gsm8k": 6.519464666193182, "math_qa": 5.5591176350911455 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.01819560272934041, "math_qa": 0.010385259631490788 } }, { "flos": 2.4440611798117253e+18, "train_loss": 5.73014404296875, "eval_loss": 5.847637176513672, "eval_accuracy": 0.015357612988152698, "eval_loss_by_set": { "aqua_rat": 5.847322463989258, "gsm8k": 6.508501226251775, "math_qa": 5.544767379760742 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.02047005307050796, "math_qa": 0.011055276381909548 } }, { "flos": 2.4510207759566766e+18, "train_loss": 5.73201416015625, "eval_loss": 5.849341882241739, "eval_accuracy": 0.01645458534444932, "eval_loss_by_set": { "aqua_rat": 5.845473289489746, "gsm8k": 6.509230873801491, "math_qa": 5.5472151438395185 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.021986353297952996, "math_qa": 0.011055276381909548 } }, { "flos": 2.457938991165473e+18, "train_loss": 5.7263946533203125, "eval_loss": 5.844969594800794, "eval_accuracy": 0.016673979815708645, "eval_loss_by_set": { "aqua_rat": 5.847425937652588, "gsm8k": 6.524410594593395, "math_qa": 5.53335444132487 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.02122820318423048, "math_qa": 0.011725293132328308 } }, { "flos": 2.46487214749175e+18, "train_loss": 5.725240478515625, "eval_loss": 5.849031242164406, "eval_accuracy": 0.013163668275559455, "eval_loss_by_set": { "aqua_rat": 5.851662635803223, "gsm8k": 6.517429698597301, "math_qa": 5.542462666829427 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.018953752843062926, "math_qa": 0.007705192629815745 } }, { "flos": 2.4717420164011786e+18, "train_loss": 5.722261962890625, "eval_loss": 5.853431443910341, "eval_accuracy": 0.011627906976744186, "eval_loss_by_set": { "aqua_rat": 5.846159934997559, "gsm8k": 6.518178766424006, "math_qa": 5.54936154683431 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.01288855193328279, "math_qa": 0.008375209380234505 } }, { "flos": 2.4787571518419763e+18, "train_loss": 5.7272021484375, "eval_loss": 5.849935222316432, "eval_accuracy": 0.01601579640193067, "eval_loss_by_set": { "aqua_rat": 5.847687721252441, "gsm8k": 6.515292080965909, "math_qa": 5.545167287190755 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.019711902956785442, "math_qa": 0.011725293132328308 } }, { "flos": 2.4856525747330744e+18, "train_loss": 5.726713256835938, "eval_loss": 5.848964562287202, "eval_accuracy": 0.01689337428696797, "eval_loss_by_set": { "aqua_rat": 5.843120098114014, "gsm8k": 6.525423916903409, "math_qa": 5.539407730102539 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.021986353297952996, "math_qa": 0.012060301507537688 } }, { "flos": 2.4926147886605926e+18, "train_loss": 5.733707275390625, "eval_loss": 5.8546600341796875, "eval_accuracy": 0.01689337428696797, "eval_loss_by_set": { "aqua_rat": 5.844573974609375, "gsm8k": 6.512265292080966, "math_qa": 5.554098129272461 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.021986353297952996, "math_qa": 0.011725293132328308 } }, { "flos": 2.499548707343565e+18, "train_loss": 5.7189794921875, "eval_loss": 5.842047794445141, "eval_accuracy": 0.019306713470820535, "eval_loss_by_set": { "aqua_rat": 5.842620372772217, "gsm8k": 6.492138255726207, "math_qa": 5.5440419514973955 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.021986353297952996, "math_qa": 0.01574539363484087 } }, { "flos": 2.5064653564999107e+18, "train_loss": 5.723258056640625, "eval_loss": 5.846981177458892, "eval_accuracy": 0.01645458534444932, "eval_loss_by_set": { "aqua_rat": 5.844807147979736, "gsm8k": 6.512099526145241, "math_qa": 5.542316436767578 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.019711902956785442, "math_qa": 0.012060301507537688 } }, { "flos": 2.513407106518876e+18, "train_loss": 5.726160278320313, "eval_loss": 5.861175769084209, "eval_accuracy": 0.013602457218078104, "eval_loss_by_set": { "aqua_rat": 5.85215425491333, "gsm8k": 6.535179831764915, "math_qa": 5.553009033203125 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.018953752843062926, "math_qa": 0.008375209380234505 } }, { "flos": 2.520321859984032e+18, "train_loss": 5.72673095703125, "eval_loss": 5.8540564872123095, "eval_accuracy": 0.015357612988152698, "eval_loss_by_set": { "aqua_rat": 5.852329254150391, "gsm8k": 6.526195179332387, "math_qa": 5.546136856079102 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.022744503411675512, "math_qa": 0.009715242881072027 } }, { "flos": 2.5272346968200315e+18, "train_loss": 5.72177978515625, "eval_loss": 5.842987112096838, "eval_accuracy": 0.015138218516893374, "eval_loss_by_set": { "aqua_rat": 5.840683937072754, "gsm8k": 6.513864690607244, "math_qa": 5.535693486531575 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.021986353297952996, "math_qa": 0.009380234505862646 } }, { "flos": 2.5341952410790134e+18, "train_loss": 5.727088623046875, "eval_loss": 5.865459828763394, "eval_accuracy": 0.015357612988152698, "eval_loss_by_set": { "aqua_rat": 5.850675106048584, "gsm8k": 6.521531538529829, "math_qa": 5.56599235534668 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.019711902956785442, "math_qa": 0.010720268006700168 } }, { "flos": 2.541149252692738e+18, "train_loss": 5.73310546875, "eval_loss": 5.854453421927787, "eval_accuracy": 0.014480035103115402, "eval_loss_by_set": { "aqua_rat": 5.84423828125, "gsm8k": 6.539704756303267, "math_qa": 5.541231155395508 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.018953752843062926, "math_qa": 0.010050251256281407 } }, { "flos": 2.548030559100076e+18, "train_loss": 5.727236328125, "eval_loss": 5.844461544139965, "eval_accuracy": 0.015577007459412023, "eval_loss_by_set": { "aqua_rat": 5.847491264343262, "gsm8k": 6.5081870339133525, "math_qa": 5.540001551310222 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.014404852160727824, "math_qa": 0.01340033500837521 } }, { "flos": 2.555042788458627e+18, "train_loss": 5.731373291015625, "eval_loss": 5.849794258942476, "eval_accuracy": 0.01338306274681878, "eval_loss_by_set": { "aqua_rat": 5.846540927886963, "gsm8k": 6.524134549227628, "math_qa": 5.540992736816406 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.01592115238817286, "math_qa": 0.009715242881072027 } }, { "flos": 2.5619697004393267e+18, "train_loss": 5.722967529296875, "eval_loss": 5.859696645994444, "eval_accuracy": 0.014480035103115402, "eval_loss_by_set": { "aqua_rat": 5.845126628875732, "gsm8k": 6.52745957808061, "math_qa": 5.554852803548177 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.019711902956785442, "math_qa": 0.010385259631490788 } }, { "flos": 2.568895005565387e+18, "train_loss": 5.7255316162109375, "eval_loss": 5.846852379876214, "eval_accuracy": 0.015577007459412023, "eval_loss_by_set": { "aqua_rat": 5.843660354614258, "gsm8k": 6.507237521084872, "math_qa": 5.544441858927409 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.02047005307050796, "math_qa": 0.011055276381909548 } }, { "flos": 2.575808728775262e+18, "train_loss": 5.724322509765625, "eval_loss": 5.853419922493599, "eval_accuracy": 0.017770952172005264, "eval_loss_by_set": { "aqua_rat": 5.84718656539917, "gsm8k": 6.50372938676314, "math_qa": 5.555880864461263 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.022744503411675512, "math_qa": 0.01340033500837521 } }, { "flos": 2.582672332938019e+18, "train_loss": 5.725796508789062, "eval_loss": 5.862339586824985, "eval_accuracy": 0.014699429574374727, "eval_loss_by_set": { "aqua_rat": 5.850625038146973, "gsm8k": 6.530211708762429, "math_qa": 5.557207743326823 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.01819560272934041, "math_qa": 0.010050251256281407 } }, { "flos": 2.589646437482496e+18, "train_loss": 5.72688720703125, "eval_loss": 5.84302907376676, "eval_accuracy": 0.01601579640193067, "eval_loss_by_set": { "aqua_rat": 5.8477277755737305, "gsm8k": 6.506846341219815, "math_qa": 5.538387934366862 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.018953752843062926, "math_qa": 0.011055276381909548 } }, { "flos": 2.59658200543291e+18, "train_loss": 5.729085693359375, "eval_loss": 5.852236283792032, "eval_accuracy": 0.014041246160596753, "eval_loss_by_set": { "aqua_rat": 5.843786716461182, "gsm8k": 6.524244828657671, "math_qa": 5.544936498006185 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.01819560272934041, "math_qa": 0.009715242881072027 } }, { "flos": 2.6034375930392084e+18, "train_loss": 5.709132690429687, "eval_loss": 5.86056121619972, "eval_accuracy": 0.015796401930671347, "eval_loss_by_set": { "aqua_rat": 5.850069999694824, "gsm8k": 6.536805586381392, "math_qa": 5.551490147908528 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.019711902956785442, "math_qa": 0.011725293132328308 } }, { "flos": 2.6103166735797453e+18, "train_loss": 5.723424072265625, "eval_loss": 5.8449387679228915, "eval_accuracy": 0.016673979815708645, "eval_loss_by_set": { "aqua_rat": 5.84043550491333, "gsm8k": 6.511370572176847, "math_qa": 5.539866129557292 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.021986353297952996, "math_qa": 0.011055276381909548 } }, { "flos": 2.6172548995780444e+18, "train_loss": 5.722080688476563, "eval_loss": 5.854985365996489, "eval_accuracy": 0.015357612988152698, "eval_loss_by_set": { "aqua_rat": 5.848555564880371, "gsm8k": 6.508279973810369, "math_qa": 5.556094487508138 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.02122820318423048, "math_qa": 0.009715242881072027 } }, { "flos": 2.6241719814523453e+18, "train_loss": 5.726043701171875, "eval_loss": 5.85204485300425, "eval_accuracy": 0.014260640631856078, "eval_loss_by_set": { "aqua_rat": 5.844830513000488, "gsm8k": 6.52349853515625, "math_qa": 5.5448964436848955 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.021986353297952996, "math_qa": 0.008710217755443886 } }, { "flos": 2.63116747708144e+18, "train_loss": 5.726357421875, "eval_loss": 5.861853986173062, "eval_accuracy": 0.01338306274681878, "eval_loss_by_set": { "aqua_rat": 5.853363990783691, "gsm8k": 6.526228471235796, "math_qa": 5.558056513468425 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.02047005307050796, "math_qa": 0.007705192629815745 } }, { "flos": 2.638111164667527e+18, "train_loss": 5.735430908203125, "eval_loss": 5.849921587351206, "eval_accuracy": 0.012505484861781484, "eval_loss_by_set": { "aqua_rat": 5.852795124053955, "gsm8k": 6.51689356023615, "math_qa": 5.543986638387044 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.02122820318423048, "math_qa": 0.006030150753768844 } }, { "flos": 2.6450771291752366e+18, "train_loss": 5.722236938476563, "eval_loss": 5.855202752190667, "eval_accuracy": 0.012944273804300131, "eval_loss_by_set": { "aqua_rat": 5.8540191650390625, "gsm8k": 6.524065884676847, "math_qa": 5.548739115397136 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.016679302501895376, "math_qa": 0.009380234505862646 } }, { "flos": 2.6519794766273577e+18, "train_loss": 5.732789916992187, "eval_loss": 5.846433845726219, "eval_accuracy": 0.014480035103115402, "eval_loss_by_set": { "aqua_rat": 5.844794273376465, "gsm8k": 6.499990289861506, "math_qa": 5.547023773193359 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.02047005307050796, "math_qa": 0.009380234505862646 } }, { "flos": 2.6588765069099663e+18, "train_loss": 5.719239501953125, "eval_loss": 5.848808958723739, "eval_accuracy": 0.013821851689337429, "eval_loss_by_set": { "aqua_rat": 5.846390724182129, "gsm8k": 6.52356650612571, "math_qa": 5.539746602376302 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.019711902956785442, "math_qa": 0.008375209380234505 } }, { "flos": 2.665895455207981e+18, "train_loss": 5.721738891601563, "eval_loss": 5.856254371436867, "eval_accuracy": 0.014699429574374727, "eval_loss_by_set": { "aqua_rat": 5.849456787109375, "gsm8k": 6.516755537553267, "math_qa": 5.554091135660808 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.018953752843062926, "math_qa": 0.010050251256281407 } }, { "flos": 2.672799616210043e+18, "train_loss": 5.721402587890625, "eval_loss": 5.858442151868665, "eval_accuracy": 0.013163668275559455, "eval_loss_by_set": { "aqua_rat": 5.851245880126953, "gsm8k": 6.524141485040838, "math_qa": 5.5539296468098955 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.016679302501895376, "math_qa": 0.009045226130653266 } }, { "flos": 2.679740665612468e+18, "train_loss": 5.726697998046875, "eval_loss": 5.851595775501148, "eval_accuracy": 0.015138218516893374, "eval_loss_by_set": { "aqua_rat": 5.8422980308532715, "gsm8k": 6.516569657759233, "math_qa": 5.547590891520183 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.01819560272934041, "math_qa": 0.011055276381909548 } }, { "flos": 2.686737192033714e+18, "train_loss": 5.72344482421875, "eval_loss": 5.845090659889015, "eval_accuracy": 0.014260640631856078, "eval_loss_by_set": { "aqua_rat": 5.84683895111084, "gsm8k": 6.501768632368608, "math_qa": 5.543967564900716 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.018953752843062926, "math_qa": 0.009045226130653266 } }, { "flos": 2.6935879365275156e+18, "train_loss": 5.727305908203125, "eval_loss": 5.8574136527808935, "eval_accuracy": 0.01228609039052216, "eval_loss_by_set": { "aqua_rat": 5.852196216583252, "gsm8k": 6.531840931285512, "math_qa": 5.548735936482747 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.01592115238817286, "math_qa": 0.009045226130653266 } }, { "flos": 2.700559856544252e+18, "train_loss": 5.717845458984375, "eval_loss": 5.847926784206081, "eval_accuracy": 0.014480035103115402, "eval_loss_by_set": { "aqua_rat": 5.849964141845703, "gsm8k": 6.514778137207031, "math_qa": 5.542116800944011 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.01819560272934041, "math_qa": 0.010385259631490788 } }, { "flos": 2.7074339296897925e+18, "train_loss": 5.7213067626953125, "eval_loss": 5.852321830955711, "eval_accuracy": 0.016235190873189996, "eval_loss_by_set": { "aqua_rat": 5.848382949829102, "gsm8k": 6.516436490145597, "math_qa": 5.548264185587565 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.016679302501895376, "math_qa": 0.01373534338358459 } }, { "flos": 2.7142969771174134e+18, "train_loss": 5.711409912109375, "eval_loss": 5.854352847949879, "eval_accuracy": 0.013163668275559455, "eval_loss_by_set": { "aqua_rat": 5.851716041564941, "gsm8k": 6.52550575949929, "math_qa": 5.546960830688477 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.016679302501895376, "math_qa": 0.009715242881072027 } }, { "flos": 2.721181457505583e+18, "train_loss": 5.71774169921875, "eval_loss": 5.8518864399677994, "eval_accuracy": 0.014260640631856078, "eval_loss_by_set": { "aqua_rat": 5.847755432128906, "gsm8k": 6.510222695090554, "math_qa": 5.550493240356445 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.017437452615617893, "math_qa": 0.010385259631490788 } }, { "flos": 2.7281274735008154e+18, "train_loss": 5.734964599609375, "eval_loss": 5.851611833314638, "eval_accuracy": 0.013602457218078104, "eval_loss_by_set": { "aqua_rat": 5.840806007385254, "gsm8k": 6.523317510431463, "math_qa": 5.544647216796875 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.015163002274450341, "math_qa": 0.010050251256281407 } }, { "flos": 2.7350819591715553e+18, "train_loss": 5.719287719726562, "eval_loss": 5.846818846625251, "eval_accuracy": 0.015138218516893374, "eval_loss_by_set": { "aqua_rat": 5.849902629852295, "gsm8k": 6.519357854669744, "math_qa": 5.5383148193359375 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.016679302501895376, "math_qa": 0.012060301507537688 } }, { "flos": 2.742078938711851e+18, "train_loss": 5.735986938476563, "eval_loss": 5.851058908410974, "eval_accuracy": 0.015357612988152698, "eval_loss_by_set": { "aqua_rat": 5.849493980407715, "gsm8k": 6.514925870028409, "math_qa": 5.546916961669922 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.01592115238817286, "math_qa": 0.012730318257956449 } }, { "flos": 2.7489738054046843e+18, "train_loss": 5.716741333007812, "eval_loss": 5.8586115450472445, "eval_accuracy": 0.012505484861781484, "eval_loss_by_set": { "aqua_rat": 5.848695755004883, "gsm8k": 6.527361089533025, "math_qa": 5.552927652994792 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.016679302501895376, "math_qa": 0.008375209380234505 } }, { "flos": 2.7559283941546394e+18, "train_loss": 5.7278759765625, "eval_loss": 5.851217708072147, "eval_accuracy": 0.013602457218078104, "eval_loss_by_set": { "aqua_rat": 5.8457560539245605, "gsm8k": 6.527673894708807, "math_qa": 5.5416304270426435 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.014404852160727824, "math_qa": 0.011390284757118929 } }, { "flos": 2.762808257989837e+18, "train_loss": 5.723468017578125, "eval_loss": 5.847235009476945, "eval_accuracy": 0.015138218516893374, "eval_loss_by_set": { "aqua_rat": 5.846676349639893, "gsm8k": 6.524278120561079, "math_qa": 5.536970138549805 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.01819560272934041, "math_qa": 0.012395309882747068 } }, { "flos": 2.7698815902374953e+18, "train_loss": 5.7304840087890625, "eval_loss": 5.858559943534233, "eval_accuracy": 0.015138218516893374, "eval_loss_by_set": { "aqua_rat": 5.851231575012207, "gsm8k": 6.524470936168324, "math_qa": 5.553961435953776 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.01592115238817286, "math_qa": 0.012395309882747068 } }, { "flos": 2.7767744989621125e+18, "train_loss": 5.722155151367187, "eval_loss": 5.851008105922389, "eval_accuracy": 0.016235190873189996, "eval_loss_by_set": { "aqua_rat": 5.847009181976318, "gsm8k": 6.516519026322798, "math_qa": 5.546315511067708 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.017437452615617893, "math_qa": 0.012730318257956449 } }, { "flos": 2.783697557283406e+18, "train_loss": 5.720614013671875, "eval_loss": 5.848112853797707, "eval_accuracy": 0.016235190873189996, "eval_loss_by_set": { "aqua_rat": 5.848290920257568, "gsm8k": 6.512514981356534, "math_qa": 5.543580373128255 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.017437452615617893, "math_qa": 0.01340033500837521 } }, { "flos": 2.790583932825895e+18, "train_loss": 5.724983520507813, "eval_loss": 5.854229231138487, "eval_accuracy": 0.012944273804300131, "eval_loss_by_set": { "aqua_rat": 5.852164268493652, "gsm8k": 6.527831337668679, "math_qa": 5.545667012532552 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.017437452615617893, "math_qa": 0.009380234505862646 } }, { "flos": 2.7975680532341064e+18, "train_loss": 5.718472900390625, "eval_loss": 5.850310067872743, "eval_accuracy": 0.018867924528301886, "eval_loss_by_set": { "aqua_rat": 5.843456745147705, "gsm8k": 6.524693575772372, "math_qa": 5.541788736979167 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.022744503411675512, "math_qa": 0.01474036850921273 } }, { "flos": 2.8045195920204104e+18, "train_loss": 5.727181396484375, "eval_loss": 5.857577710538297, "eval_accuracy": 0.01491882404563405, "eval_loss_by_set": { "aqua_rat": 5.850058555603027, "gsm8k": 6.532499833540483, "math_qa": 5.548865000406901 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.021986353297952996, "math_qa": 0.010385259631490788 } }, { "flos": 2.81147383019366e+18, "train_loss": 5.733985595703125, "eval_loss": 5.861100660788046, "eval_accuracy": 0.017770952172005264, "eval_loss_by_set": { "aqua_rat": 5.85078763961792, "gsm8k": 6.533061634410512, "math_qa": 5.553977966308594 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.018953752843062926, "math_qa": 0.01507537688442211 } }, { "flos": 2.818410964196524e+18, "train_loss": 5.718580932617187, "eval_loss": 5.8515048155913485, "eval_accuracy": 0.013821851689337429, "eval_loss_by_set": { "aqua_rat": 5.845707893371582, "gsm8k": 6.517735567959872, "math_qa": 5.546632130940755 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.016679302501895376, "math_qa": 0.009715242881072027 } }, { "flos": 2.825413425725702e+18, "train_loss": 5.72798828125, "eval_loss": 5.842168395583694, "eval_accuracy": 0.015138218516893374, "eval_loss_by_set": { "aqua_rat": 5.846575736999512, "gsm8k": 6.515872608531605, "math_qa": 5.53302001953125 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.01819560272934041, "math_qa": 0.011390284757118929 } }, { "flos": 2.832352599301161e+18, "train_loss": 5.71978271484375, "eval_loss": 5.859500317960172, "eval_accuracy": 0.01491882404563405, "eval_loss_by_set": { "aqua_rat": 5.852679252624512, "gsm8k": 6.528327941894531, "math_qa": 5.5535227457682295 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.021986353297952996, "math_qa": 0.010385259631490788 } }, { "flos": 2.8393282086948045e+18, "train_loss": 5.724302978515625, "eval_loss": 5.850309449273187, "eval_accuracy": 0.017770952172005264, "eval_loss_by_set": { "aqua_rat": 5.846878528594971, "gsm8k": 6.51186093417081, "math_qa": 5.547384262084961 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.022744503411675512, "math_qa": 0.01373534338358459 } }, { "flos": 2.8463305054046126e+18, "train_loss": 5.7261285400390625, "eval_loss": 5.861343796188767, "eval_accuracy": 0.017551557700745943, "eval_loss_by_set": { "aqua_rat": 5.8511505126953125, "gsm8k": 6.532301469282671, "math_qa": 5.554670969645183 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.018953752843062926, "math_qa": 0.01440536013400335 } }, { "flos": 2.853220364165579e+18, "train_loss": 5.727385864257813, "eval_loss": 5.845027614284206, "eval_accuracy": 0.01952610794207986, "eval_loss_by_set": { "aqua_rat": 5.844032287597656, "gsm8k": 6.5048439719460225, "math_qa": 5.542694727579753 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.02350265352539803, "math_qa": 0.01474036850921273 } }, { "flos": 2.8602298737360896e+18, "train_loss": 5.712117919921875, "eval_loss": 5.853151733810837, "eval_accuracy": 0.012724879333040808, "eval_loss_by_set": { "aqua_rat": 5.851933479309082, "gsm8k": 6.530879627574574, "math_qa": 5.5426279703776045 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.017437452615617893, "math_qa": 0.008040201005025126 } }, { "flos": 2.867076146632065e+18, "train_loss": 5.722989501953125, "eval_loss": 5.860224440291121, "eval_accuracy": 0.013163668275559455, "eval_loss_by_set": { "aqua_rat": 5.846960067749023, "gsm8k": 6.528826626864347, "math_qa": 5.554887135823567 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.021986353297952996, "math_qa": 0.007035175879396985 } }, { "flos": 2.874012311582933e+18, "train_loss": 5.7241259765625, "eval_loss": 5.8534259538392766, "eval_accuracy": 0.014480035103115402, "eval_loss_by_set": { "aqua_rat": 5.8524250984191895, "gsm8k": 6.520464116876775, "math_qa": 5.547783533732097 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.02047005307050796, "math_qa": 0.009715242881072027 } }, { "flos": 2.880940666135773e+18, "train_loss": 5.717205200195313, "eval_loss": 5.8563141178440405, "eval_accuracy": 0.012505484861781484, "eval_loss_by_set": { "aqua_rat": 5.850695610046387, "gsm8k": 6.515632629394531, "math_qa": 5.55459467569987 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.01819560272934041, "math_qa": 0.008040201005025126 } }, { "flos": 2.887854265328468e+18, "train_loss": 5.728367309570313, "eval_loss": 5.85314822841335, "eval_accuracy": 0.015577007459412023, "eval_loss_by_set": { "aqua_rat": 5.844674110412598, "gsm8k": 6.513975663618608, "math_qa": 5.550975163777669 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.02122820318423048, "math_qa": 0.010385259631490788 } }, { "flos": 2.894765288614527e+18, "train_loss": 5.719820556640625, "eval_loss": 5.844004940342259, "eval_accuracy": 0.014260640631856078, "eval_loss_by_set": { "aqua_rat": 5.8444037437438965, "gsm8k": 6.510690168900923, "math_qa": 5.538407643636067 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.01819560272934041, "math_qa": 0.009715242881072027 } }, { "flos": 2.901736467212534e+18, "train_loss": 5.7261895751953125, "eval_loss": 5.8501070125682935, "eval_accuracy": 0.015138218516893374, "eval_loss_by_set": { "aqua_rat": 5.851949214935303, "gsm8k": 6.511943470348012, "math_qa": 5.546611785888672 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.017437452615617893, "math_qa": 0.011390284757118929 } }, { "flos": 2.908638051771089e+18, "train_loss": 5.723509521484375, "eval_loss": 5.841482291350493, "eval_accuracy": 0.014480035103115402, "eval_loss_by_set": { "aqua_rat": 5.843678951263428, "gsm8k": 6.506376093084162, "math_qa": 5.536556243896484 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.019711902956785442, "math_qa": 0.009715242881072027 } }, { "flos": 2.915597112655741e+18, "train_loss": 5.7211962890625, "eval_loss": 5.852796090615763, "eval_accuracy": 0.012724879333040808, "eval_loss_by_set": { "aqua_rat": 5.849367141723633, "gsm8k": 6.529337102716619, "math_qa": 5.54300053914388 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.019711902956785442, "math_qa": 0.007035175879396985 } }, { "flos": 2.922578430060921e+18, "train_loss": 5.722086181640625, "eval_loss": 5.853303342252164, "eval_accuracy": 0.011408512505484861, "eval_loss_by_set": { "aqua_rat": 5.850713729858398, "gsm8k": 6.525113886052912, "math_qa": 5.545605977376302 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.018953752843062926, "math_qa": 0.005360134003350084 } }, { "flos": 2.9294924211693814e+18, "train_loss": 5.729437255859375, "eval_loss": 5.852095835917705, "eval_accuracy": 0.013602457218078104, "eval_loss_by_set": { "aqua_rat": 5.849702835083008, "gsm8k": 6.514425104314631, "math_qa": 5.548727671305339 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.018953752843062926, "math_qa": 0.008375209380234505 } }, { "flos": 2.9364061030401966e+18, "train_loss": 5.72064697265625, "eval_loss": 5.851657944756585, "eval_accuracy": 0.01491882404563405, "eval_loss_by_set": { "aqua_rat": 5.850196361541748, "gsm8k": 6.50717509876598, "math_qa": 5.551334381103516 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.02122820318423048, "math_qa": 0.009715242881072027 } }, { "flos": 2.9434490800696197e+18, "train_loss": 5.737152099609375, "eval_loss": 5.847071389894228, "eval_accuracy": 0.014699429574374727, "eval_loss_by_set": { "aqua_rat": 5.848879337310791, "gsm8k": 6.510061784224077, "math_qa": 5.543050130208333 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.018953752843062926, "math_qa": 0.010720268006700168 } }, { "flos": 2.95038965541503e+18, "train_loss": 5.728272705078125, "eval_loss": 5.85079948322193, "eval_accuracy": 0.015357612988152698, "eval_loss_by_set": { "aqua_rat": 5.8516526222229, "gsm8k": 6.514096346768466, "math_qa": 5.5467173258463545 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.02122820318423048, "math_qa": 0.010385259631490788 } }, { "flos": 2.957338185576743e+18, "train_loss": 5.724464721679688, "eval_loss": 5.852063565640836, "eval_accuracy": 0.015357612988152698, "eval_loss_by_set": { "aqua_rat": 5.853984832763672, "gsm8k": 6.5306528264826, "math_qa": 5.540883382161458 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.022744503411675512, "math_qa": 0.009715242881072027 } }, { "flos": 2.9643048093619323e+18, "train_loss": 5.722674560546875, "eval_loss": 5.8557003639839795, "eval_accuracy": 0.01491882404563405, "eval_loss_by_set": { "aqua_rat": 5.848454475402832, "gsm8k": 6.520539717240767, "math_qa": 5.551586151123047 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.01819560272934041, "math_qa": 0.011055276381909548 } }, { "flos": 2.9712033439568364e+18, "train_loss": 5.711908569335938, "eval_loss": 5.85065594234982, "eval_accuracy": 0.014041246160596753, "eval_loss_by_set": { "aqua_rat": 5.846216201782227, "gsm8k": 6.513270291415128, "math_qa": 5.5473276774088545 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.015163002274450341, "math_qa": 0.011055276381909548 } }, { "flos": 2.978201910487548e+18, "train_loss": 5.734833984375, "eval_loss": 5.854690139358108, "eval_accuracy": 0.014480035103115402, "eval_loss_by_set": { "aqua_rat": 5.8476104736328125, "gsm8k": 6.524469549005682, "math_qa": 5.548297882080078 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.017437452615617893, "math_qa": 0.010385259631490788 } }, { "flos": 2.985141723476263e+18, "train_loss": 5.7245855712890625, "eval_loss": 5.8494694426253036, "eval_accuracy": 0.014041246160596753, "eval_loss_by_set": { "aqua_rat": 5.850881099700928, "gsm8k": 6.5230865478515625, "math_qa": 5.540610631306966 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.02047005307050796, "math_qa": 0.008710217755443886 } }, { "flos": 2.99206183491312e+18, "train_loss": 5.727007446289062, "eval_loss": 5.845889529666385, "eval_accuracy": 0.012066695919262835, "eval_loss_by_set": { "aqua_rat": 5.849922180175781, "gsm8k": 6.526980313387784, "math_qa": 5.533386866251628 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.019711902956785442, "math_qa": 0.006030150753768844 } }, { "flos": 2.999060545325236e+18, "train_loss": 5.717681274414063, "eval_loss": 5.870333465369972, "eval_accuracy": 0.01338306274681878, "eval_loss_by_set": { "aqua_rat": 5.856975078582764, "gsm8k": 6.538030450994318, "math_qa": 5.565418879191081 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.018953752843062926, "math_qa": 0.007705192629815745 } }, { "flos": 3.0060063965010985e+18, "train_loss": 5.728329467773437, "eval_loss": 5.851855046040303, "eval_accuracy": 0.013821851689337429, "eval_loss_by_set": { "aqua_rat": 5.848750114440918, "gsm8k": 6.525071577592329, "math_qa": 5.543556213378906 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.018953752843062926, "math_qa": 0.009045226130653266 } }, { "flos": 3.0129261987003105e+18, "train_loss": 5.720888671875, "eval_loss": 5.859111528138857, "eval_accuracy": 0.014699429574374727, "eval_loss_by_set": { "aqua_rat": 5.852356910705566, "gsm8k": 6.528117786754262, "math_qa": 5.553046544392903 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.02122820318423048, "math_qa": 0.008710217755443886 } }, { "flos": 3.0199272584595374e+18, "train_loss": 5.733284912109375, "eval_loss": 5.850398888459077, "eval_accuracy": 0.01601579640193067, "eval_loss_by_set": { "aqua_rat": 5.849307537078857, "gsm8k": 6.517658580433238, "math_qa": 5.5446624755859375 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.021986353297952996, "math_qa": 0.011055276381909548 } }, { "flos": 3.026748595312263e+18, "train_loss": 5.70438720703125, "eval_loss": 5.841780662536621, "eval_accuracy": 0.012724879333040808, "eval_loss_by_set": { "aqua_rat": 5.844972133636475, "gsm8k": 6.508444352583452, "math_qa": 5.535960515340169 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.018953752843062926, "math_qa": 0.007705192629815745 } }, { "flos": 3.0336308090314424e+18, "train_loss": 5.72716796875, "eval_loss": 5.846207592938398, "eval_accuracy": 0.012724879333040808, "eval_loss_by_set": { "aqua_rat": 5.843198776245117, "gsm8k": 6.50310655073686, "math_qa": 5.545379638671875 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.015163002274450341, "math_qa": 0.008710217755443886 } }, { "flos": 3.0405763917718487e+18, "train_loss": 5.7139044189453125, "eval_loss": 5.850257383810507, "eval_accuracy": 0.01338306274681878, "eval_loss_by_set": { "aqua_rat": 5.84624719619751, "gsm8k": 6.513485995205966, "math_qa": 5.546611785888672 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.016679302501895376, "math_qa": 0.009045226130653266 } }, { "flos": 3.0474577185802813e+18, "train_loss": 5.719384765625, "eval_loss": 5.850983361940126, "eval_accuracy": 0.013821851689337429, "eval_loss_by_set": { "aqua_rat": 5.845632076263428, "gsm8k": 6.510030573064631, "math_qa": 5.549365997314453 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.015163002274450341, "math_qa": 0.010385259631490788 } }, { "flos": 3.0543798497255096e+18, "train_loss": 5.731885375976563, "eval_loss": 5.850615991128458, "eval_accuracy": 0.01338306274681878, "eval_loss_by_set": { "aqua_rat": 5.8459272384643555, "gsm8k": 6.516820040616122, "math_qa": 5.545663197835286 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.01592115238817286, "math_qa": 0.009715242881072027 } }, { "flos": 3.0613347686510756e+18, "train_loss": 5.709075317382813, "eval_loss": 5.842516254734349, "eval_accuracy": 0.014699429574374727, "eval_loss_by_set": { "aqua_rat": 5.849581718444824, "gsm8k": 6.512068314985796, "math_qa": 5.5350494384765625 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.01819560272934041, "math_qa": 0.010050251256281407 } }, { "flos": 3.068216981833384e+18, "train_loss": 5.71541748046875, "eval_loss": 5.838294596285434, "eval_accuracy": 0.01338306274681878, "eval_loss_by_set": { "aqua_rat": 5.84116792678833, "gsm8k": 6.500628384676847, "math_qa": 5.534485499064128 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.01288855193328279, "math_qa": 0.011055276381909548 } }, { "flos": 3.0751970628248535e+18, "train_loss": 5.729903564453125, "eval_loss": 5.857348570952544, "eval_accuracy": 0.012944273804300131, "eval_loss_by_set": { "aqua_rat": 5.845525741577148, "gsm8k": 6.521238153631037, "math_qa": 5.5540510813395185 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.016679302501895376, "math_qa": 0.008710217755443886 } }, { "flos": 3.08212622161032e+18, "train_loss": 5.713814086914063, "eval_loss": 5.847649419629896, "eval_accuracy": 0.016673979815708645, "eval_loss_by_set": { "aqua_rat": 5.844336986541748, "gsm8k": 6.509770480069247, "math_qa": 5.544453303019206 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.021986353297952996, "math_qa": 0.011725293132328308 } }, { "flos": 3.089105395826819e+18, "train_loss": 5.718836669921875, "eval_loss": 5.852153881176098, "eval_accuracy": 0.01601579640193067, "eval_loss_by_set": { "aqua_rat": 5.846717834472656, "gsm8k": 6.520428744229403, "math_qa": 5.546314239501953 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.02047005307050796, "math_qa": 0.011725293132328308 } }, { "flos": 3.096035172550705e+18, "train_loss": 5.724496459960937, "eval_loss": 5.8496280360866235, "eval_accuracy": 0.017112768758227294, "eval_loss_by_set": { "aqua_rat": 5.848440170288086, "gsm8k": 6.523712851784446, "math_qa": 5.540771484375 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.022744503411675512, "math_qa": 0.012395309882747068 } }, { "flos": 3.103067412698759e+18, "train_loss": 5.725963134765625, "eval_loss": 5.850852038409259, "eval_accuracy": 0.015357612988152698, "eval_loss_by_set": { "aqua_rat": 5.851324081420898, "gsm8k": 6.511938615278765, "math_qa": 5.547814687093099 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.016679302501895376, "math_qa": 0.012060301507537688 } }, { "flos": 3.109973923047932e+18, "train_loss": 5.721492919921875, "eval_loss": 5.855267138094516, "eval_accuracy": 0.01601579640193067, "eval_loss_by_set": { "aqua_rat": 5.847424507141113, "gsm8k": 6.528581792658025, "math_qa": 5.54731814066569 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.02122820318423048, "math_qa": 0.011390284757118929 } }, { "flos": 3.116892900613423e+18, "train_loss": 5.709722290039062, "eval_loss": 5.854997737987621, "eval_accuracy": 0.014480035103115402, "eval_loss_by_set": { "aqua_rat": 5.850035667419434, "gsm8k": 6.517400568181818, "math_qa": 5.551809946695964 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.019711902956785442, "math_qa": 0.009715242881072027 } }, { "flos": 3.123857360808837e+18, "train_loss": 5.7309130859375, "eval_loss": 5.848859116837785, "eval_accuracy": 0.015357612988152698, "eval_loss_by_set": { "aqua_rat": 5.846803665161133, "gsm8k": 6.512702941894531, "math_qa": 5.544768651326497 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.018953752843062926, "math_qa": 0.011055276381909548 } }, { "flos": 3.1308413163976786e+18, "train_loss": 5.7195062255859375, "eval_loss": 5.851907472352724, "eval_accuracy": 0.017770952172005264, "eval_loss_by_set": { "aqua_rat": 5.850025177001953, "gsm8k": 6.527543501420454, "math_qa": 5.542397816975911 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.024260803639120546, "math_qa": 0.012730318257956449 } }, { "flos": 3.1377560489248686e+18, "train_loss": 5.72058837890625, "eval_loss": 5.8477396836151945, "eval_accuracy": 0.015357612988152698, "eval_loss_by_set": { "aqua_rat": 5.854132175445557, "gsm8k": 6.515511946244673, "math_qa": 5.541144688924153 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.02350265352539803, "math_qa": 0.009045226130653266 } }, { "flos": 3.144681126954533e+18, "train_loss": 5.721769409179688, "eval_loss": 5.846272417016931, "eval_accuracy": 0.014041246160596753, "eval_loss_by_set": { "aqua_rat": 5.846473217010498, "gsm8k": 6.520762356844815, "math_qa": 5.5371144612630205 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.015163002274450341, "math_qa": 0.011055276381909548 } }, { "flos": 3.151599610061914e+18, "train_loss": 5.708832397460937, "eval_loss": 5.851454941002098, "eval_accuracy": 0.014041246160596753, "eval_loss_by_set": { "aqua_rat": 5.844716548919678, "gsm8k": 6.520547346635298, "math_qa": 5.54534912109375 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.018953752843062926, "math_qa": 0.009380234505862646 } }, { "flos": 3.158499340268339e+18, "train_loss": 5.732508544921875, "eval_loss": 5.8444894068949935, "eval_accuracy": 0.014041246160596753, "eval_loss_by_set": { "aqua_rat": 5.847140789031982, "gsm8k": 6.517190413041548, "math_qa": 5.535947163899739 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.019711902956785442, "math_qa": 0.008710217755443886 } }, { "flos": 3.165413743156789e+18, "train_loss": 5.714571533203125, "eval_loss": 5.845154633393159, "eval_accuracy": 0.012944273804300131, "eval_loss_by_set": { "aqua_rat": 5.846336364746094, "gsm8k": 6.505315607244318, "math_qa": 5.542482376098633 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.01592115238817286, "math_qa": 0.008040201005025126 } }, { "flos": 3.172375379948077e+18, "train_loss": 5.721288452148437, "eval_loss": 5.8689431628665405, "eval_accuracy": 0.012944273804300131, "eval_loss_by_set": { "aqua_rat": 5.862008571624756, "gsm8k": 6.556550459428267, "math_qa": 5.554367701212565 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.01819560272934041, "math_qa": 0.008040201005025126 } }, { "flos": 3.179306702323319e+18, "train_loss": 5.722686157226563, "eval_loss": 5.84550733824034, "eval_accuracy": 0.014260640631856078, "eval_loss_by_set": { "aqua_rat": 5.849054336547852, "gsm8k": 6.513918789950284, "math_qa": 5.538856506347656 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.014404852160727824, "math_qa": 0.011055276381909548 } }, { "flos": 3.186270400162038e+18, "train_loss": 5.722919921875, "eval_loss": 5.845430631895323, "eval_accuracy": 0.015796401930671347, "eval_loss_by_set": { "aqua_rat": 5.85136604309082, "gsm8k": 6.514341874556108, "math_qa": 5.538351694742839 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.018953752843062926, "math_qa": 0.012060301507537688 } }, { "flos": 3.193102494834098e+18, "train_loss": 5.724149169921875, "eval_loss": 5.858451740161793, "eval_accuracy": 0.016235190873189996, "eval_loss_by_set": { "aqua_rat": 5.851247787475586, "gsm8k": 6.52068467573686, "math_qa": 5.55552864074707 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.01819560272934041, "math_qa": 0.012730318257956449 } }, { "flos": 3.2000946930020516e+18, "train_loss": 5.7219189453125, "eval_loss": 5.860643799240525, "eval_accuracy": 0.014480035103115402, "eval_loss_by_set": { "aqua_rat": 5.8575334548950195, "gsm8k": 6.536787553267046, "math_qa": 5.551003774007161 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.02122820318423048, "math_qa": 0.009715242881072027 } }, { "flos": 3.207052764433613e+18, "train_loss": 5.727701416015625, "eval_loss": 5.84136625238367, "eval_accuracy": 0.016235190873189996, "eval_loss_by_set": { "aqua_rat": 5.8470940589904785, "gsm8k": 6.51248515735973, "math_qa": 5.533292770385742 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.018953752843062926, "math_qa": 0.012730318257956449 } }, { "flos": 3.213921129030746e+18, "train_loss": 5.713248901367187, "eval_loss": 5.844602919913627, "eval_accuracy": 0.012505484861781484, "eval_loss_by_set": { "aqua_rat": 5.845304012298584, "gsm8k": 6.51285830411044, "math_qa": 5.538260777791341 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.015163002274450341, "math_qa": 0.008710217755443886 } }, { "flos": 3.220964950558114e+18, "train_loss": 5.718267822265625, "eval_loss": 5.850479899226008, "eval_accuracy": 0.013821851689337429, "eval_loss_by_set": { "aqua_rat": 5.843962669372559, "gsm8k": 6.512693925337358, "math_qa": 5.547508239746094 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.017437452615617893, "math_qa": 0.009380234505862646 } }, { "flos": 3.227825525158314e+18, "train_loss": 5.719759521484375, "eval_loss": 5.851053005940205, "eval_accuracy": 0.012944273804300131, "eval_loss_by_set": { "aqua_rat": 5.842983722686768, "gsm8k": 6.519687999378551, "math_qa": 5.545267740885417 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.02122820318423048, "math_qa": 0.007370184254606365 } }, { "flos": 3.234764204812534e+18, "train_loss": 5.7076123046875, "eval_loss": 5.853530935339026, "eval_accuracy": 0.012944273804300131, "eval_loss_by_set": { "aqua_rat": 5.847016334533691, "gsm8k": 6.516897028142756, "math_qa": 5.550031026204427 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.014404852160727824, "math_qa": 0.009715242881072027 } }, { "flos": 3.241744347544158e+18, "train_loss": 5.716264038085938, "eval_loss": 5.857188843392037, "eval_accuracy": 0.015357612988152698, "eval_loss_by_set": { "aqua_rat": 5.84828519821167, "gsm8k": 6.519074179909446, "math_qa": 5.554566701253255 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.022744503411675512, "math_qa": 0.009715242881072027 } }, { "flos": 3.248672661294809e+18, "train_loss": 5.726255493164063, "eval_loss": 5.8449061110213, "eval_accuracy": 0.015357612988152698, "eval_loss_by_set": { "aqua_rat": 5.8497114181518555, "gsm8k": 6.51250527121804, "math_qa": 5.538522720336914 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.02047005307050796, "math_qa": 0.011055276381909548 } }, { "flos": 3.2556163896830853e+18, "train_loss": 5.7193145751953125, "eval_loss": 5.852507591247559, "eval_accuracy": 0.016235190873189996, "eval_loss_by_set": { "aqua_rat": 5.849931240081787, "gsm8k": 6.512340892444957, "math_qa": 5.550298690795898 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.018953752843062926, "math_qa": 0.012730318257956449 } }, { "flos": 3.2625606130663424e+18, "train_loss": 5.725988159179687, "eval_loss": 5.839037920977618, "eval_accuracy": 0.015577007459412023, "eval_loss_by_set": { "aqua_rat": 5.843635559082031, "gsm8k": 6.504820390181108, "math_qa": 5.533504486083984 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.02047005307050796, "math_qa": 0.011390284757118929 } }, { "flos": 3.2695383651117957e+18, "train_loss": 5.721602783203125, "eval_loss": 5.84359022088953, "eval_accuracy": 0.014041246160596753, "eval_loss_by_set": { "aqua_rat": 5.848694324493408, "gsm8k": 6.526709123091265, "math_qa": 5.530068715413411 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.02122820318423048, "math_qa": 0.008375209380234505 } }, { "flos": 3.276520033093681e+18, "train_loss": 5.722064208984375, "eval_loss": 5.852847846778664, "eval_accuracy": 0.01601579640193067, "eval_loss_by_set": { "aqua_rat": 5.850282669067383, "gsm8k": 6.518369501287287, "math_qa": 5.548030853271484 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.019711902956785442, "math_qa": 0.011725293132328308 } }, { "flos": 3.283391200156975e+18, "train_loss": 5.710958251953125, "eval_loss": 5.8518010216790275, "eval_accuracy": 0.014041246160596753, "eval_loss_by_set": { "aqua_rat": 5.848563194274902, "gsm8k": 6.520784551447088, "math_qa": 5.545453389485677 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.019711902956785442, "math_qa": 0.009715242881072027 } }, { "flos": 3.2903112085146173e+18, "train_loss": 5.717550048828125, "eval_loss": 5.855307347065693, "eval_accuracy": 0.015138218516893374, "eval_loss_by_set": { "aqua_rat": 5.8507890701293945, "gsm8k": 6.5216064453125, "math_qa": 5.550296783447266 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.02122820318423048, "math_qa": 0.010050251256281407 } }, { "flos": 3.2972453333560197e+18, "train_loss": 5.711036376953125, "eval_loss": 5.848485224955791, "eval_accuracy": 0.014041246160596753, "eval_loss_by_set": { "aqua_rat": 5.843907356262207, "gsm8k": 6.525908730246804, "math_qa": 5.538380940755208 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.02122820318423048, "math_qa": 0.008710217755443886 } }, { "flos": 3.3041956770676736e+18, "train_loss": 5.725208740234375, "eval_loss": 5.8653667037551465, "eval_accuracy": 0.013821851689337429, "eval_loss_by_set": { "aqua_rat": 5.8526411056518555, "gsm8k": 6.533174688165838, "math_qa": 5.5603485107421875 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.018953752843062926, "math_qa": 0.009045226130653266 } }, { "flos": 3.3111067626307584e+18, "train_loss": 5.706870727539062, "eval_loss": 5.85000569111592, "eval_accuracy": 0.014699429574374727, "eval_loss_by_set": { "aqua_rat": 5.8469085693359375, "gsm8k": 6.5229644775390625, "math_qa": 5.5418243408203125 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.02047005307050796, "math_qa": 0.009715242881072027 } }, { "flos": 3.318025266676105e+18, "train_loss": 5.730740966796875, "eval_loss": 5.850945498492266, "eval_accuracy": 0.011408512505484861, "eval_loss_by_set": { "aqua_rat": 5.8512372970581055, "gsm8k": 6.51785625110973, "math_qa": 5.545253753662109 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.016679302501895376, "math_qa": 0.007705192629815745 } }, { "flos": 3.324943111443972e+18, "train_loss": 5.715546875, "eval_loss": 5.847418089170714, "eval_accuracy": 0.01491882404563405, "eval_loss_by_set": { "aqua_rat": 5.847042083740234, "gsm8k": 6.5246054909446025, "math_qa": 5.537071863810222 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.021986353297952996, "math_qa": 0.009715242881072027 } }, { "flos": 3.3319015125142733e+18, "train_loss": 5.717381591796875, "eval_loss": 5.859721493076634, "eval_accuracy": 0.011189118034225537, "eval_loss_by_set": { "aqua_rat": 5.850480556488037, "gsm8k": 6.5319297096946025, "math_qa": 5.552396138509114 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.016679302501895376, "math_qa": 0.007035175879396985 } }, { "flos": 3.3388326491321795e+18, "train_loss": 5.717958984375, "eval_loss": 5.848772100500159, "eval_accuracy": 0.013602457218078104, "eval_loss_by_set": { "aqua_rat": 5.846216201782227, "gsm8k": 6.530557112260298, "math_qa": 5.536500295003255 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.018953752843062926, "math_qa": 0.008375209380234505 } }, { "flos": 3.3456819306527457e+18, "train_loss": 5.724528198242187, "eval_loss": 5.839275824057089, "eval_accuracy": 0.012724879333040808, "eval_loss_by_set": { "aqua_rat": 5.841147422790527, "gsm8k": 6.5158164284446025, "math_qa": 5.529038747151692 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.02047005307050796, "math_qa": 0.006365159128978224 } }, { "flos": 3.3526828878696284e+18, "train_loss": 5.721060791015625, "eval_loss": 5.856865341598923, "eval_accuracy": 0.014480035103115402, "eval_loss_by_set": { "aqua_rat": 5.848304748535156, "gsm8k": 6.52707949551669, "math_qa": 5.550397237141927 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.01819560272934041, "math_qa": 0.010385259631490788 } }, { "flos": 3.359636858681164e+18, "train_loss": 5.720974731445312, "eval_loss": 5.84480991879025, "eval_accuracy": 0.013163668275559455, "eval_loss_by_set": { "aqua_rat": 5.843583106994629, "gsm8k": 6.5114052512428975, "math_qa": 5.539389292399089 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.016679302501895376, "math_qa": 0.009715242881072027 } }, { "flos": 3.3666131268154163e+18, "train_loss": 5.730855712890625, "eval_loss": 5.853772807765651, "eval_accuracy": 0.012505484861781484, "eval_loss_by_set": { "aqua_rat": 5.844944953918457, "gsm8k": 6.512399846857244, "math_qa": 5.5526377360026045 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.018953752843062926, "math_qa": 0.007035175879396985 } }, { "flos": 3.373610539073667e+18, "train_loss": 5.715320434570312, "eval_loss": 5.849956203151393, "eval_accuracy": 0.013602457218078104, "eval_loss_by_set": { "aqua_rat": 5.845798492431641, "gsm8k": 6.521303350275213, "math_qa": 5.542601903279622 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.021986353297952996, "math_qa": 0.008375209380234505 } }, { "flos": 3.380575267167666e+18, "train_loss": 5.7107861328125, "eval_loss": 5.856966791926204, "eval_accuracy": 0.014699429574374727, "eval_loss_by_set": { "aqua_rat": 5.852142333984375, "gsm8k": 6.538020047274503, "math_qa": 5.545219421386719 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.022744503411675512, "math_qa": 0.009380234505862646 } }, { "flos": 3.387455439703638e+18, "train_loss": 5.7245263671875, "eval_loss": 5.860284083598369, "eval_accuracy": 0.014699429574374727, "eval_loss_by_set": { "aqua_rat": 5.85159969329834, "gsm8k": 6.527983925559304, "math_qa": 5.554978688557942 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.017437452615617893, "math_qa": 0.010385259631490788 } }, { "flos": 3.3944080296831877e+18, "train_loss": 5.71736572265625, "eval_loss": 5.858230436170423, "eval_accuracy": 0.010092145677928916, "eval_loss_by_set": { "aqua_rat": 5.8508195877075195, "gsm8k": 6.529521595348012, "math_qa": 5.5511728922526045 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.014404852160727824, "math_qa": 0.006365159128978224 } }, { "flos": 3.4014159109242225e+18, "train_loss": 5.726441650390625, "eval_loss": 5.864264050045529, "eval_accuracy": 0.011189118034225537, "eval_loss_by_set": { "aqua_rat": 5.85012149810791, "gsm8k": 6.531557950106534, "math_qa": 5.55959955851237 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.015163002274450341, "math_qa": 0.007370184254606365 } }, { "flos": 3.408374683509195e+18, "train_loss": 5.70992431640625, "eval_loss": 5.842866175883525, "eval_accuracy": 0.014260640631856078, "eval_loss_by_set": { "aqua_rat": 5.843527793884277, "gsm8k": 6.502467762340199, "math_qa": 5.540493647257487 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.02047005307050796, "math_qa": 0.009380234505862646 } }, { "flos": 3.4152684786076877e+18, "train_loss": 5.72573486328125, "eval_loss": 5.845962112014358, "eval_accuracy": 0.01338306274681878, "eval_loss_by_set": { "aqua_rat": 5.846652984619141, "gsm8k": 6.508770335804332, "math_qa": 5.542117436726888 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.018953752843062926, "math_qa": 0.008375209380234505 } }, { "flos": 3.4222223667411026e+18, "train_loss": 5.71897705078125, "eval_loss": 5.8532448845940666, "eval_accuracy": 0.013602457218078104, "eval_loss_by_set": { "aqua_rat": 5.849700927734375, "gsm8k": 6.523217634721235, "math_qa": 5.546469370524089 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.02047005307050796, "math_qa": 0.008040201005025126 } }, { "flos": 3.429137078867198e+18, "train_loss": 5.716627807617187, "eval_loss": 5.848713410867227, "eval_accuracy": 0.013163668275559455, "eval_loss_by_set": { "aqua_rat": 5.849002361297607, "gsm8k": 6.513689908114347, "math_qa": 5.543908437093099 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.01592115238817286, "math_qa": 0.009715242881072027 } }, { "flos": 3.436120786958549e+18, "train_loss": 5.71931884765625, "eval_loss": 5.849780830177101, "eval_accuracy": 0.010969723562966213, "eval_loss_by_set": { "aqua_rat": 5.844038009643555, "gsm8k": 6.511960116299716, "math_qa": 5.546760559082031 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.013646702047005308, "math_qa": 0.007370184254606365 } }, { "flos": 3.443056725349892e+18, "train_loss": 5.719122314453125, "eval_loss": 5.851335035788046, "eval_accuracy": 0.012944273804300131, "eval_loss_by_set": { "aqua_rat": 5.844737529754639, "gsm8k": 6.5195700905539775, "math_qa": 5.545610427856445 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.02047005307050796, "math_qa": 0.008040201005025126 } }, { "flos": 3.450014157905068e+18, "train_loss": 5.71246826171875, "eval_loss": 5.848992012642525, "eval_accuracy": 0.013163668275559455, "eval_loss_by_set": { "aqua_rat": 5.846160888671875, "gsm8k": 6.5242767333984375, "math_qa": 5.539722442626953 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.01819560272934041, "math_qa": 0.008375209380234505 } }, { "flos": 3.45698815937033e+18, "train_loss": 5.711409912109375, "eval_loss": 5.850697311195168, "eval_accuracy": 0.012724879333040808, "eval_loss_by_set": { "aqua_rat": 5.852837085723877, "gsm8k": 6.522297252308238, "math_qa": 5.542702356974284 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.014404852160727824, "math_qa": 0.009715242881072027 } }, { "flos": 3.4639109911320986e+18, "train_loss": 5.71954833984375, "eval_loss": 5.856522147719924, "eval_accuracy": 0.014699429574374727, "eval_loss_by_set": { "aqua_rat": 5.850992679595947, "gsm8k": 6.522395740855824, "math_qa": 5.551790873209636 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.018953752843062926, "math_qa": 0.010385259631490788 } }, { "flos": 3.470835842602238e+18, "train_loss": 5.720980834960938, "eval_loss": 5.859355307914115, "eval_accuracy": 0.01733216322948662, "eval_loss_by_set": { "aqua_rat": 5.85411262512207, "gsm8k": 6.525555697354403, "math_qa": 5.554450352986653 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.02350265352539803, "math_qa": 0.012060301507537688 } }, { "flos": 3.4776926456842813e+18, "train_loss": 5.706348876953125, "eval_loss": 5.841682305207124, "eval_accuracy": 0.01491882404563405, "eval_loss_by_set": { "aqua_rat": 5.8407301902771, "gsm8k": 6.496999567205256, "math_qa": 5.5414079030354815 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.021986353297952996, "math_qa": 0.009715242881072027 } }, { "flos": 3.484653025660764e+18, "train_loss": 5.7156396484375, "eval_loss": 5.844790020504513, "eval_accuracy": 0.016235190873189996, "eval_loss_by_set": { "aqua_rat": 5.850058555603027, "gsm8k": 6.520283092151988, "math_qa": 5.534749984741211 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.02350265352539803, "math_qa": 0.011055276381909548 } }, { "flos": 3.4916642451651297e+18, "train_loss": 5.721185302734375, "eval_loss": 5.859552409197833, "eval_accuracy": 0.012066695919262835, "eval_loss_by_set": { "aqua_rat": 5.854508876800537, "gsm8k": 6.5290000221946025, "math_qa": 5.553142547607422 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.016679302501895376, "math_qa": 0.008375209380234505 } }, { "flos": 3.4984673230381384e+18, "train_loss": 5.718728637695312, "eval_loss": 5.855432819675755, "eval_accuracy": 0.013163668275559455, "eval_loss_by_set": { "aqua_rat": 5.845217704772949, "gsm8k": 6.520547346635298, "math_qa": 5.551439921061198 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.015163002274450341, "math_qa": 0.009715242881072027 } }, { "flos": 3.505450083015459e+18, "train_loss": 5.71659423828125, "eval_loss": 5.850921991709116, "eval_accuracy": 0.012505484861781484, "eval_loss_by_set": { "aqua_rat": 5.855040550231934, "gsm8k": 6.5175392844460225, "math_qa": 5.545045852661133 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.017437452615617893, "math_qa": 0.008040201005025126 } }, { "flos": 3.5123787264048497e+18, "train_loss": 5.723089599609375, "eval_loss": 5.846040158658414, "eval_accuracy": 0.014041246160596753, "eval_loss_by_set": { "aqua_rat": 5.851968765258789, "gsm8k": 6.518773859197443, "math_qa": 5.537209828694661 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.02122820318423048, "math_qa": 0.008375209380234505 } }, { "flos": 3.519343227402453e+18, "train_loss": 5.7171240234375, "eval_loss": 5.856183747987489, "eval_accuracy": 0.013163668275559455, "eval_loss_by_set": { "aqua_rat": 5.850454330444336, "gsm8k": 6.514986905184659, "math_qa": 5.554709752400716 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.017437452615617893, "math_qa": 0.008710217755443886 } }, { "flos": 3.526345812411941e+18, "train_loss": 5.715230712890625, "eval_loss": 5.85450791023873, "eval_accuracy": 0.014041246160596753, "eval_loss_by_set": { "aqua_rat": 5.850579261779785, "gsm8k": 6.522078080610796, "math_qa": 5.548865636189778 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.022744503411675512, "math_qa": 0.007370184254606365 } }, { "flos": 3.5332817916054733e+18, "train_loss": 5.72285888671875, "eval_loss": 5.8519094828012825, "eval_accuracy": 0.01491882404563405, "eval_loss_by_set": { "aqua_rat": 5.847590446472168, "gsm8k": 6.521359530362216, "math_qa": 5.545438130696614 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.02122820318423048, "math_qa": 0.010050251256281407 } }, { "flos": 3.5402163083626414e+18, "train_loss": 5.721180419921875, "eval_loss": 5.8444686322598844, "eval_accuracy": 0.013602457218078104, "eval_loss_by_set": { "aqua_rat": 5.846348285675049, "gsm8k": 6.509549227627841, "math_qa": 5.539483388264974 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.018953752843062926, "math_qa": 0.008375209380234505 } }, { "flos": 3.5471217675185684e+18, "train_loss": 5.711865844726563, "eval_loss": 5.853451728820801, "eval_accuracy": 0.011627906976744186, "eval_loss_by_set": { "aqua_rat": 5.853039264678955, "gsm8k": 6.518420826305043, "math_qa": 5.548708597819011 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.01592115238817286, "math_qa": 0.007705192629815745 } }, { "flos": 3.554102281227993e+18, "train_loss": 5.719317626953125, "eval_loss": 5.849065909514556, "eval_accuracy": 0.013163668275559455, "eval_loss_by_set": { "aqua_rat": 5.8468146324157715, "gsm8k": 6.516563415527344, "math_qa": 5.543317159016927 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.017437452615617893, "math_qa": 0.009045226130653266 } }, { "flos": 3.5610087706392e+18, "train_loss": 5.7173046875, "eval_loss": 5.840992334726694, "eval_accuracy": 0.013602457218078104, "eval_loss_by_set": { "aqua_rat": 5.847886085510254, "gsm8k": 6.51679160378196, "math_qa": 5.530676523844401 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.02350265352539803, "math_qa": 0.007370184254606365 } }, { "flos": 3.5679646575430205e+18, "train_loss": 5.724408569335938, "eval_loss": 5.8592500428895695, "eval_accuracy": 0.014699429574374727, "eval_loss_by_set": { "aqua_rat": 5.849555969238281, "gsm8k": 6.527100996537642, "math_qa": 5.5539595286051435 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.02122820318423048, "math_qa": 0.009380234505862646 } }, { "flos": 3.5748879010847785e+18, "train_loss": 5.713772583007812, "eval_loss": 5.857398832166517, "eval_accuracy": 0.013602457218078104, "eval_loss_by_set": { "aqua_rat": 5.852166175842285, "gsm8k": 6.533595692027699, "math_qa": 5.547911326090495 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.017437452615617893, "math_qa": 0.009715242881072027 } }, { "flos": 3.5818235098373816e+18, "train_loss": 5.71761474609375, "eval_loss": 5.843355127283044, "eval_accuracy": 0.014480035103115402, "eval_loss_by_set": { "aqua_rat": 5.848243713378906, "gsm8k": 6.514930725097656, "math_qa": 5.535142262776692 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.02577710386656558, "math_qa": 0.008040201005025126 } }, { "flos": 3.5888210251748475e+18, "train_loss": 5.718797607421875, "eval_loss": 5.845186285070471, "eval_accuracy": 0.012724879333040808, "eval_loss_by_set": { "aqua_rat": 5.84547233581543, "gsm8k": 6.512250033291903, "math_qa": 5.539424896240234 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.02047005307050796, "math_qa": 0.007705192629815745 } }, { "flos": 3.595751811752919e+18, "train_loss": 5.727191772460937, "eval_loss": 5.84147716212917, "eval_accuracy": 0.01228609039052216, "eval_loss_by_set": { "aqua_rat": 5.848562240600586, "gsm8k": 6.522782759232954, "math_qa": 5.528621673583984 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.022744503411675512, "math_qa": 0.006030150753768844 } }, { "flos": 3.602592602660012e+18, "train_loss": 5.711817626953125, "eval_loss": 5.847088427157016, "eval_accuracy": 0.01491882404563405, "eval_loss_by_set": { "aqua_rat": 5.844517707824707, "gsm8k": 6.496463428844105, "math_qa": 5.549672444661458 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.024260803639120546, "math_qa": 0.008710217755443886 } }, { "flos": 3.6094973198603387e+18, "train_loss": 5.713753662109375, "eval_loss": 5.8463148941864835, "eval_accuracy": 0.012066695919262835, "eval_loss_by_set": { "aqua_rat": 5.852962017059326, "gsm8k": 6.520917025479403, "math_qa": 5.536568323771159 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.019711902956785442, "math_qa": 0.007035175879396985 } }, { "flos": 3.6164637578881925e+18, "train_loss": 5.712809448242187, "eval_loss": 5.854159819113241, "eval_accuracy": 0.013821851689337429, "eval_loss_by_set": { "aqua_rat": 5.851158618927002, "gsm8k": 6.524447354403409, "math_qa": 5.547194798787435 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.018953752843062926, "math_qa": 0.009715242881072027 } }, { "flos": 3.623403756097372e+18, "train_loss": 5.716553955078125, "eval_loss": 5.847075178816512, "eval_accuracy": 0.014041246160596753, "eval_loss_by_set": { "aqua_rat": 5.8490447998046875, "gsm8k": 6.519284335049716, "math_qa": 5.538815180460612 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.02047005307050796, "math_qa": 0.008710217755443886 } }, { "flos": 3.6303649188316447e+18, "train_loss": 5.711341552734375, "eval_loss": 5.859098022048538, "eval_accuracy": 0.013163668275559455, "eval_loss_by_set": { "aqua_rat": 5.856623649597168, "gsm8k": 6.5285186767578125, "math_qa": 5.552486419677734 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.019711902956785442, "math_qa": 0.008375209380234505 } }, { "flos": 3.637284041352282e+18, "train_loss": 5.71140625, "eval_loss": 5.861670880704312, "eval_accuracy": 0.010311540149188241, "eval_loss_by_set": { "aqua_rat": 5.847508430480957, "gsm8k": 6.534718600186435, "math_qa": 5.554370880126953 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.015163002274450341, "math_qa": 0.006700167504187605 } }, { "flos": 3.644237496767742e+18, "train_loss": 5.71868896484375, "eval_loss": 5.8564054128286, "eval_accuracy": 0.013821851689337429, "eval_loss_by_set": { "aqua_rat": 5.855146408081055, "gsm8k": 6.526907487349077, "math_qa": 5.549196879069011 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.02122820318423048, "math_qa": 0.008375209380234505 } }, { "flos": 3.651221411017523e+18, "train_loss": 5.725062866210937, "eval_loss": 5.850333033381282, "eval_accuracy": 0.01338306274681878, "eval_loss_by_set": { "aqua_rat": 5.84807014465332, "gsm8k": 6.521725047718395, "math_qa": 5.542800267537435 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.01819560272934041, "math_qa": 0.008710217755443886 } }, { "flos": 3.658095298405728e+18, "train_loss": 5.711596069335937, "eval_loss": 5.8471713194975985, "eval_accuracy": 0.011408512505484861, "eval_loss_by_set": { "aqua_rat": 5.850216865539551, "gsm8k": 6.520011901855469, "math_qa": 5.538532257080078 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.016679302501895376, "math_qa": 0.007705192629815745 } }, { "flos": 3.665018830784037e+18, "train_loss": 5.711761474609375, "eval_loss": 5.840624989690007, "eval_accuracy": 0.013821851689337429, "eval_loss_by_set": { "aqua_rat": 5.843276023864746, "gsm8k": 6.515040310946378, "math_qa": 5.531297047932942 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.018953752843062926, "math_qa": 0.009380234505862646 } }, { "flos": 3.6720294940901376e+18, "train_loss": 5.717332153320313, "eval_loss": 5.850678263483821, "eval_accuracy": 0.01338306274681878, "eval_loss_by_set": { "aqua_rat": 5.848090171813965, "gsm8k": 6.517499056729403, "math_qa": 5.545267740885417 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.022744503411675512, "math_qa": 0.007370184254606365 } }, { "flos": 3.678954304221217e+18, "train_loss": 5.7140771484375, "eval_loss": 5.8475772239066455, "eval_accuracy": 0.014480035103115402, "eval_loss_by_set": { "aqua_rat": 5.8486433029174805, "gsm8k": 6.508762706409801, "math_qa": 5.544445037841797 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.017437452615617893, "math_qa": 0.011055276381909548 } }, { "flos": 3.6859106651820524e+18, "train_loss": 5.703963623046875, "eval_loss": 5.84227213988433, "eval_accuracy": 0.012724879333040808, "eval_loss_by_set": { "aqua_rat": 5.84639310836792, "gsm8k": 6.505000721324574, "math_qa": 5.538178126017253 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.018953752843062926, "math_qa": 0.008375209380234505 } }, { "flos": 3.6927580504745574e+18, "train_loss": 5.7104931640625, "eval_loss": 5.844591553146775, "eval_accuracy": 0.014260640631856078, "eval_loss_by_set": { "aqua_rat": 5.8520097732543945, "gsm8k": 6.520506425337358, "math_qa": 5.534179051717122 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.02122820318423048, "math_qa": 0.009380234505862646 } }, { "flos": 3.699681211875066e+18, "train_loss": 5.719613647460937, "eval_loss": 5.860302693135029, "eval_accuracy": 0.01228609039052216, "eval_loss_by_set": { "aqua_rat": 5.852573394775391, "gsm8k": 6.531008633700284, "math_qa": 5.553539911905925 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.015163002274450341, "math_qa": 0.009045226130653266 } }, { "flos": 3.7066014671933276e+18, "train_loss": 5.714849853515625, "eval_loss": 5.858922649074245, "eval_accuracy": 0.013163668275559455, "eval_loss_by_set": { "aqua_rat": 5.852967262268066, "gsm8k": 6.531154285777699, "math_qa": 5.551312764485677 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.018953752843062926, "math_qa": 0.008375209380234505 } }, { "flos": 3.713644423284785e+18, "train_loss": 5.708201904296875, "eval_loss": 5.856636717512801, "eval_accuracy": 0.014041246160596753, "eval_loss_by_set": { "aqua_rat": 5.852658271789551, "gsm8k": 6.526657798073509, "math_qa": 5.549875259399414 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.02122820318423048, "math_qa": 0.008710217755443886 } }, { "flos": 3.7205620205551616e+18, "train_loss": 5.719560546875, "eval_loss": 5.846785983523807, "eval_accuracy": 0.01338306274681878, "eval_loss_by_set": { "aqua_rat": 5.848363876342773, "gsm8k": 6.510484175248579, "math_qa": 5.542459487915039 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.018953752843062926, "math_qa": 0.008710217755443886 } }, { "flos": 3.727453548984664e+18, "train_loss": 5.7177587890625, "eval_loss": 5.846671181756097, "eval_accuracy": 0.014041246160596753, "eval_loss_by_set": { "aqua_rat": 5.8476667404174805, "gsm8k": 6.515797008167613, "math_qa": 5.539905548095703 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.01819560272934041, "math_qa": 0.010050251256281407 } }, { "flos": 3.734399688460206e+18, "train_loss": 5.711512451171875, "eval_loss": 5.848849760519491, "eval_accuracy": 0.012944273804300131, "eval_loss_by_set": { "aqua_rat": 5.847588062286377, "gsm8k": 6.518735018643466, "math_qa": 5.541924158732097 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.017437452615617893, "math_qa": 0.009045226130653266 } }, { "flos": 3.7413799342710456e+18, "train_loss": 5.719820556640625, "eval_loss": 5.854123579489218, "eval_accuracy": 0.012724879333040808, "eval_loss_by_set": { "aqua_rat": 5.851541042327881, "gsm8k": 6.529894742098722, "math_qa": 5.544610341389974 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.01819560272934041, "math_qa": 0.008710217755443886 } }, { "flos": 3.748244156372222e+18, "train_loss": 5.725557861328125, "eval_loss": 5.8535894187721045, "eval_accuracy": 0.012066695919262835, "eval_loss_by_set": { "aqua_rat": 5.849074840545654, "gsm8k": 6.521115389737216, "math_qa": 5.5480162302653 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.018953752843062926, "math_qa": 0.007035175879396985 } }, { "flos": 3.75516690545587e+18, "train_loss": 5.7036285400390625, "eval_loss": 5.848666603500779, "eval_accuracy": 0.011408512505484861, "eval_loss_by_set": { "aqua_rat": 5.849212169647217, "gsm8k": 6.520312222567472, "math_qa": 5.540783564249675 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.016679302501895376, "math_qa": 0.007035175879396985 } }, { "flos": 3.762131695290024e+18, "train_loss": 5.709354248046875, "eval_loss": 5.851537240518106, "eval_accuracy": 0.011408512505484861, "eval_loss_by_set": { "aqua_rat": 5.853796005249023, "gsm8k": 6.522943670099432, "math_qa": 5.543621063232422 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.015163002274450341, "math_qa": 0.008375209380234505 } }, { "flos": 3.769049683939295e+18, "train_loss": 5.720657958984375, "eval_loss": 5.835600672541438, "eval_accuracy": 0.013163668275559455, "eval_loss_by_set": { "aqua_rat": 5.843610763549805, "gsm8k": 6.501529346812855, "math_qa": 5.529715855916341 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.01592115238817286, "math_qa": 0.010050251256281407 } }, { "flos": 3.7760266322889933e+18, "train_loss": 5.720006103515625, "eval_loss": 5.858828673491606, "eval_accuracy": 0.013821851689337429, "eval_loss_by_set": { "aqua_rat": 5.849771499633789, "gsm8k": 6.522573297674006, "math_qa": 5.555367151896159 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.02047005307050796, "math_qa": 0.009045226130653266 } }, { "flos": 3.782990082630222e+18, "train_loss": 5.714677734375, "eval_loss": 5.8472208847870695, "eval_accuracy": 0.01338306274681878, "eval_loss_by_set": { "aqua_rat": 5.854158878326416, "gsm8k": 6.520321932705966, "math_qa": 5.538138071695964 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.02047005307050796, "math_qa": 0.008040201005025126 } }, { "flos": 3.789893460337623e+18, "train_loss": 5.7108349609375, "eval_loss": 5.84421699111526, "eval_accuracy": 0.01338306274681878, "eval_loss_by_set": { "aqua_rat": 5.8490705490112305, "gsm8k": 6.516390713778409, "math_qa": 5.535732905069987 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.014404852160727824, "math_qa": 0.010720268006700168 } }, { "flos": 3.7968446898862817e+18, "train_loss": 5.715681762695312, "eval_loss": 5.849587595140612, "eval_accuracy": 0.01338306274681878, "eval_loss_by_set": { "aqua_rat": 5.848832607269287, "gsm8k": 6.520120794122869, "math_qa": 5.5423227945963545 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.019711902956785442, "math_qa": 0.008710217755443886 } }, { "flos": 3.803763235270689e+18, "train_loss": 5.716915893554687, "eval_loss": 5.847528354541676, "eval_accuracy": 0.016235190873189996, "eval_loss_by_set": { "aqua_rat": 5.8501691818237305, "gsm8k": 6.519981384277344, "math_qa": 5.539100646972656 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.02047005307050796, "math_qa": 0.011725293132328308 } }, { "flos": 3.810718854275924e+18, "train_loss": 5.71200439453125, "eval_loss": 5.8505094115798535, "eval_accuracy": 0.014480035103115402, "eval_loss_by_set": { "aqua_rat": 5.849368572235107, "gsm8k": 6.524799693714488, "math_qa": 5.541554768880208 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.019711902956785442, "math_qa": 0.009715242881072027 } }, { "flos": 3.8176073939450593e+18, "train_loss": 5.718575439453125, "eval_loss": 5.847327722085489, "eval_accuracy": 0.014480035103115402, "eval_loss_by_set": { "aqua_rat": 5.846865653991699, "gsm8k": 6.523769031871449, "math_qa": 5.537330627441406 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.02122820318423048, "math_qa": 0.008710217755443886 } }, { "flos": 3.824598211817898e+18, "train_loss": 5.72286865234375, "eval_loss": 5.8583837457605314, "eval_accuracy": 0.012724879333040808, "eval_loss_by_set": { "aqua_rat": 5.851771354675293, "gsm8k": 6.525174227627841, "math_qa": 5.553322474161784 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.017437452615617893, "math_qa": 0.008040201005025126 } }, { "flos": 3.831484216919458e+18, "train_loss": 5.713013305664062, "eval_loss": 5.846928751146471, "eval_accuracy": 0.012944273804300131, "eval_loss_by_set": { "aqua_rat": 5.8459696769714355, "gsm8k": 6.512727217240767, "math_qa": 5.541851043701172 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.02122820318423048, "math_qa": 0.007370184254606365 } }, { "flos": 3.8384924283361034e+18, "train_loss": 5.719020385742187, "eval_loss": 5.850503199809307, "eval_accuracy": 0.012724879333040808, "eval_loss_by_set": { "aqua_rat": 5.845660209655762, "gsm8k": 6.520768599076704, "math_qa": 5.543701807657878 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.018953752843062926, "math_qa": 0.008040201005025126 } }, { "flos": 3.845503750919684e+18, "train_loss": 5.725208740234375, "eval_loss": 5.859509957803263, "eval_accuracy": 0.011627906976744186, "eval_loss_by_set": { "aqua_rat": 5.852514266967773, "gsm8k": 6.533850236372515, "math_qa": 5.5510203043619795 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.017437452615617893, "math_qa": 0.007035175879396985 } }, { "flos": 3.852410034709332e+18, "train_loss": 5.71127685546875, "eval_loss": 5.845542495315139, "eval_accuracy": 0.015357612988152698, "eval_loss_by_set": { "aqua_rat": 5.846889495849609, "gsm8k": 6.519694935191762, "math_qa": 5.536443710327148 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.022744503411675512, "math_qa": 0.009380234505862646 } }, { "flos": 3.8593342682410516e+18, "train_loss": 5.7201385498046875, "eval_loss": 5.8446515057538, "eval_accuracy": 0.013602457218078104, "eval_loss_by_set": { "aqua_rat": 5.8501129150390625, "gsm8k": 6.515246304598722, "math_qa": 5.536840438842773 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.02047005307050796, "math_qa": 0.008710217755443886 } }, { "flos": 3.8662544204800983e+18, "train_loss": 5.69899658203125, "eval_loss": 5.840591636863914, "eval_accuracy": 0.01228609039052216, "eval_loss_by_set": { "aqua_rat": 5.847599029541016, "gsm8k": 6.51538779518821, "math_qa": 5.5307261149088545 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.015163002274450341, "math_qa": 0.008710217755443886 } }, { "flos": 3.8731331509808005e+18, "train_loss": 5.71243896484375, "eval_loss": 5.846288010880754, "eval_accuracy": 0.012505484861781484, "eval_loss_by_set": { "aqua_rat": 5.845861434936523, "gsm8k": 6.51723896373402, "math_qa": 5.538804372151692 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.017437452615617893, "math_qa": 0.007705192629815745 } }, { "flos": 3.880124586792059e+18, "train_loss": 5.710491943359375, "eval_loss": 5.857919847643053, "eval_accuracy": 0.012944273804300131, "eval_loss_by_set": { "aqua_rat": 5.852931976318359, "gsm8k": 6.524354414506392, "math_qa": 5.552886327107747 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.016679302501895376, "math_qa": 0.009045226130653266 } }, { "flos": 3.8870861822442865e+18, "train_loss": 5.718820190429687, "eval_loss": 5.859422889915672, "eval_accuracy": 0.01491882404563405, "eval_loss_by_set": { "aqua_rat": 5.852265357971191, "gsm8k": 6.532354181463068, "math_qa": 5.551592508951823 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.018953752843062926, "math_qa": 0.010385259631490788 } }, { "flos": 3.893999410996052e+18, "train_loss": 5.711138916015625, "eval_loss": 5.848989125844595, "eval_accuracy": 0.013163668275559455, "eval_loss_by_set": { "aqua_rat": 5.849544525146484, "gsm8k": 6.5146352594549, "math_qa": 5.54385503133138 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.018953752843062926, "math_qa": 0.007705192629815745 } }, { "flos": 3.9009076114148557e+18, "train_loss": 5.71498291015625, "eval_loss": 5.850413296673749, "eval_accuracy": 0.01338306274681878, "eval_loss_by_set": { "aqua_rat": 5.850405693054199, "gsm8k": 6.523257168856534, "math_qa": 5.5420271555582685 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.017437452615617893, "math_qa": 0.009380234505862646 } }, { "flos": 3.907898882406744e+18, "train_loss": 5.716111450195313, "eval_loss": 5.846624838339316, "eval_accuracy": 0.014041246160596753, "eval_loss_by_set": { "aqua_rat": 5.850910186767578, "gsm8k": 6.518359791148793, "math_qa": 5.538389205932617 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.02047005307050796, "math_qa": 0.009045226130653266 } }, { "flos": 3.9148086896801874e+18, "train_loss": 5.716041259765625, "eval_loss": 5.85417010333087, "eval_accuracy": 0.015796401930671347, "eval_loss_by_set": { "aqua_rat": 5.8517303466796875, "gsm8k": 6.535451715642756, "math_qa": 5.5421193440755205 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.021986353297952996, "math_qa": 0.010050251256281407 } }, { "flos": 3.921670006235988e+18, "train_loss": 5.707357788085938, "eval_loss": 5.8546623023780615, "eval_accuracy": 0.013602457218078104, "eval_loss_by_set": { "aqua_rat": 5.850009918212891, "gsm8k": 6.523845325816762, "math_qa": 5.548341115315755 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.02122820318423048, "math_qa": 0.007705192629815745 } }, { "flos": 3.928629499838595e+18, "train_loss": 5.7190008544921875, "eval_loss": 5.851056794862489, "eval_accuracy": 0.014480035103115402, "eval_loss_by_set": { "aqua_rat": 5.849340438842773, "gsm8k": 6.521480213512074, "math_qa": 5.543922424316406 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.022744503411675512, "math_qa": 0.008710217755443886 } }, { "flos": 3.9356035839819776e+18, "train_loss": 5.713978271484375, "eval_loss": 5.853447011999182, "eval_accuracy": 0.012505484861781484, "eval_loss_by_set": { "aqua_rat": 5.848736763000488, "gsm8k": 6.531919999556108, "math_qa": 5.5428727467854815 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.01592115238817286, "math_qa": 0.009045226130653266 } }, { "flos": 3.9424807070911693e+18, "train_loss": 5.717276000976563, "eval_loss": 5.843057529346363, "eval_accuracy": 0.012944273804300131, "eval_loss_by_set": { "aqua_rat": 5.846266746520996, "gsm8k": 6.5202789306640625, "math_qa": 5.532396952311198 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.01592115238817286, "math_qa": 0.009715242881072027 } }, { "flos": 3.949482055686947e+18, "train_loss": 5.710661010742188, "eval_loss": 5.85696808067528, "eval_accuracy": 0.011627906976744186, "eval_loss_by_set": { "aqua_rat": 5.849621772766113, "gsm8k": 6.523850874467329, "math_qa": 5.5519256591796875 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.01819560272934041, "math_qa": 0.006700167504187605 } }, { "flos": 3.956410842957742e+18, "train_loss": 5.718746948242187, "eval_loss": 5.85564087532662, "eval_accuracy": 0.01184730144800351, "eval_loss_by_set": { "aqua_rat": 5.849570274353027, "gsm8k": 6.532784895463423, "math_qa": 5.545789082845052 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.018953752843062926, "math_qa": 0.006365159128978224 } }, { "flos": 3.9633477912032707e+18, "train_loss": 5.703734130859375, "eval_loss": 5.852792121268608, "eval_accuracy": 0.014041246160596753, "eval_loss_by_set": { "aqua_rat": 5.850823402404785, "gsm8k": 6.52622500332919, "math_qa": 5.544299443562825 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.025018953752843062, "math_qa": 0.008040201005025126 } }, { "flos": 3.970305512594997e+18, "train_loss": 5.71670166015625, "eval_loss": 5.855686806343697, "eval_accuracy": 0.01338306274681878, "eval_loss_by_set": { "aqua_rat": 5.847227096557617, "gsm8k": 6.5216827392578125, "math_qa": 5.551143646240234 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.021986353297952996, "math_qa": 0.007370184254606365 } }, { "flos": 3.9772129710582006e+18, "train_loss": 5.71416015625, "eval_loss": 5.8446282567204655, "eval_accuracy": 0.013821851689337429, "eval_loss_by_set": { "aqua_rat": 5.848446846008301, "gsm8k": 6.51593017578125, "math_qa": 5.536629994710286 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.01819560272934041, "math_qa": 0.009715242881072027 } }, { "flos": 3.984168837560926e+18, "train_loss": 5.71767578125, "eval_loss": 5.853620322974953, "eval_accuracy": 0.014041246160596753, "eval_loss_by_set": { "aqua_rat": 5.853243827819824, "gsm8k": 6.529601357199929, "math_qa": 5.543827056884766 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.02047005307050796, "math_qa": 0.009045226130653266 } }, { "flos": 3.991088000883753e+18, "train_loss": 5.707049560546875, "eval_loss": 5.857805870674752, "eval_accuracy": 0.016673979815708645, "eval_loss_by_set": { "aqua_rat": 5.8533220291137695, "gsm8k": 6.529472351074219, "math_qa": 5.550332387288411 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.024260803639120546, "math_qa": 0.011055276381909548 } }, { "flos": 3.998016788154548e+18, "train_loss": 5.715177001953125, "eval_loss": 5.842461869523332, "eval_accuracy": 0.013163668275559455, "eval_loss_by_set": { "aqua_rat": 5.850128173828125, "gsm8k": 6.517263932661577, "math_qa": 5.532538731892903 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.014404852160727824, "math_qa": 0.010050251256281407 } }, { "flos": 4.0049913259538514e+18, "train_loss": 5.7093359375, "eval_loss": 5.856874001992716, "eval_accuracy": 0.012505484861781484, "eval_loss_by_set": { "aqua_rat": 5.853954315185547, "gsm8k": 6.5303871848366475, "math_qa": 5.548423767089844 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.017437452615617893, "math_qa": 0.008040201005025126 } }, { "flos": 4.011935796297728e+18, "train_loss": 5.726058349609375, "eval_loss": 5.8458343196559595, "eval_accuracy": 0.01228609039052216, "eval_loss_by_set": { "aqua_rat": 5.847260475158691, "gsm8k": 6.514767733487216, "math_qa": 5.539120992024739 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.015163002274450341, "math_qa": 0.009045226130653266 } }, { "flos": 4.018798823324254e+18, "train_loss": 5.716797485351562, "eval_loss": 5.84652380041174, "eval_accuracy": 0.01228609039052216, "eval_loss_by_set": { "aqua_rat": 5.844989776611328, "gsm8k": 6.510937083851207, "math_qa": 5.542128880818685 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.01819560272934041, "math_qa": 0.008040201005025126 } }, { "flos": 4.025785169062396e+18, "train_loss": 5.712924194335938, "eval_loss": 5.855722582018053, "eval_accuracy": 0.012724879333040808, "eval_loss_by_set": { "aqua_rat": 5.854961395263672, "gsm8k": 6.5255043723366475, "math_qa": 5.5488026936848955 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.016679302501895376, "math_qa": 0.009045226130653266 } }, { "flos": 4.0327234154617897e+18, "train_loss": 5.712283935546875, "eval_loss": 5.849718351621886, "eval_accuracy": 0.013602457218078104, "eval_loss_by_set": { "aqua_rat": 5.851099014282227, "gsm8k": 6.524372447620738, "math_qa": 5.54038683573405 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.019711902956785442, "math_qa": 0.009045226130653266 } }, { "flos": 4.039622485853864e+18, "train_loss": 5.71009521484375, "eval_loss": 5.844089636931548, "eval_accuracy": 0.01228609039052216, "eval_loss_by_set": { "aqua_rat": 5.846264362335205, "gsm8k": 6.516797152432528, "math_qa": 5.535584131876628 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.016679302501895376, "math_qa": 0.008375209380234505 } }, { "flos": 4.046573365362688e+18, "train_loss": 5.7176806640625, "eval_loss": 5.851321503922746, "eval_accuracy": 0.013821851689337429, "eval_loss_by_set": { "aqua_rat": 5.850983619689941, "gsm8k": 6.520476601340554, "math_qa": 5.544653574625651 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.019711902956785442, "math_qa": 0.009045226130653266 } }, { "flos": 4.053482740455047e+18, "train_loss": 5.704076538085937, "eval_loss": 5.847562996116844, "eval_accuracy": 0.012066695919262835, "eval_loss_by_set": { "aqua_rat": 5.848250389099121, "gsm8k": 6.520665949041193, "math_qa": 5.539000193277995 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.016679302501895376, "math_qa": 0.008375209380234505 } }, { "flos": 4.060373382510674e+18, "train_loss": 5.720253295898438, "eval_loss": 5.846004202559188, "eval_accuracy": 0.013602457218078104, "eval_loss_by_set": { "aqua_rat": 5.848057270050049, "gsm8k": 6.517509460449219, "math_qa": 5.5380598704020185 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.021986353297952996, "math_qa": 0.008040201005025126 } }, { "flos": 4.067335328539607e+18, "train_loss": 5.710125122070313, "eval_loss": 5.84585834193874, "eval_accuracy": 0.012944273804300131, "eval_loss_by_set": { "aqua_rat": 5.84616756439209, "gsm8k": 6.519122730601918, "math_qa": 5.537253061930339 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.022744503411675512, "math_qa": 0.006365159128978224 } }, { "flos": 4.0742916895004426e+18, "train_loss": 5.7118902587890625, "eval_loss": 5.852354462082322, "eval_accuracy": 0.013163668275559455, "eval_loss_by_set": { "aqua_rat": 5.853884696960449, "gsm8k": 6.519227461381392, "math_qa": 5.546576817830403 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.02122820318423048, "math_qa": 0.007705192629815745 } }, { "flos": 4.08126604154241e+18, "train_loss": 5.711314086914062, "eval_loss": 5.855776606379329, "eval_accuracy": 0.013163668275559455, "eval_loss_by_set": { "aqua_rat": 5.85223388671875, "gsm8k": 6.526867259632457, "math_qa": 5.548488616943359 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.018953752843062926, "math_qa": 0.009045226130653266 } }, { "flos": 4.0882055039544197e+18, "train_loss": 5.711491088867188, "eval_loss": 5.853340303575671, "eval_accuracy": 0.014260640631856078, "eval_loss_by_set": { "aqua_rat": 5.848753929138184, "gsm8k": 6.511419122869318, "math_qa": 5.552103042602539 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.024260803639120546, "math_qa": 0.008710217755443886 } }, { "flos": 4.0951252234755113e+18, "train_loss": 5.7198193359375, "eval_loss": 5.853643056508657, "eval_accuracy": 0.015357612988152698, "eval_loss_by_set": { "aqua_rat": 5.8524017333984375, "gsm8k": 6.522671786221591, "math_qa": 5.547108332316081 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.024260803639120546, "math_qa": 0.009380234505862646 } }, { "flos": 4.101969518002176e+18, "train_loss": 5.708536987304687, "eval_loss": 5.85458974580507, "eval_accuracy": 0.014260640631856078, "eval_loss_by_set": { "aqua_rat": 5.853352069854736, "gsm8k": 6.524236505681818, "math_qa": 5.547771453857422 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.02047005307050796, "math_qa": 0.010050251256281407 } }, { "flos": 4.108927322072023e+18, "train_loss": 5.72853271484375, "eval_loss": 5.848089372789538, "eval_accuracy": 0.012944273804300131, "eval_loss_by_set": { "aqua_rat": 5.853399276733398, "gsm8k": 6.51598496870561, "math_qa": 5.541528065999349 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.017437452615617893, "math_qa": 0.008710217755443886 } }, { "flos": 4.115899922304205e+18, "train_loss": 5.711428833007813, "eval_loss": 5.851013235143713, "eval_accuracy": 0.011408512505484861, "eval_loss_by_set": { "aqua_rat": 5.8496599197387695, "gsm8k": 6.523015108975497, "math_qa": 5.543125152587891 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.01288855193328279, "math_qa": 0.008375209380234505 } }, { "flos": 4.122844103811531e+18, "train_loss": 5.71811767578125, "eval_loss": 5.849962543796849, "eval_accuracy": 0.01338306274681878, "eval_loss_by_set": { "aqua_rat": 5.8539228439331055, "gsm8k": 6.52153847434304, "math_qa": 5.541826883951823 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.01819560272934041, "math_qa": 0.009045226130653266 } }, { "flos": 4.1297984864030556e+18, "train_loss": 5.717611694335938, "eval_loss": 5.843962488947688, "eval_accuracy": 0.013163668275559455, "eval_loss_by_set": { "aqua_rat": 5.847391128540039, "gsm8k": 6.513934048739347, "math_qa": 5.536606470743815 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.017437452615617893, "math_qa": 0.009045226130653266 } }, { "flos": 4.1366755885742817e+18, "train_loss": 5.70572021484375, "eval_loss": 5.845446174209182, "eval_accuracy": 0.01491882404563405, "eval_loss_by_set": { "aqua_rat": 5.848571300506592, "gsm8k": 6.51427529074929, "math_qa": 5.538639068603516 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.01592115238817286, "math_qa": 0.011390284757118929 } }, { "flos": 4.143662511448654e+18, "train_loss": 5.715603637695312, "eval_loss": 5.84781247216302, "eval_accuracy": 0.012724879333040808, "eval_loss_by_set": { "aqua_rat": 5.84951639175415, "gsm8k": 6.519423051313921, "math_qa": 5.539848963419597 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.018953752843062926, "math_qa": 0.007370184254606365 } }, { "flos": 4.1506681050827325e+18, "train_loss": 5.718936767578125, "eval_loss": 5.8539987512536955, "eval_accuracy": 0.01228609039052216, "eval_loss_by_set": { "aqua_rat": 5.850757598876953, "gsm8k": 6.514835704456676, "math_qa": 5.551385243733724 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.017437452615617893, "math_qa": 0.007705192629815745 } }, { "flos": 4.1575968102122783e+18, "train_loss": 5.713856811523438, "eval_loss": 5.855629379684861, "eval_accuracy": 0.013821851689337429, "eval_loss_by_set": { "aqua_rat": 5.854732513427734, "gsm8k": 6.536188299005682, "math_qa": 5.543781280517578 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.019711902956785442, "math_qa": 0.009045226130653266 } }, { "flos": 4.164603434101637e+18, "train_loss": 5.710504150390625, "eval_loss": 5.8505835662017, "eval_accuracy": 0.014260640631856078, "eval_loss_by_set": { "aqua_rat": 5.849859237670898, "gsm8k": 6.521310286088423, "math_qa": 5.543227513631185 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.019711902956785442, "math_qa": 0.009715242881072027 } }, { "flos": 4.171476991851102e+18, "train_loss": 5.722965698242188, "eval_loss": 5.847449689298062, "eval_accuracy": 0.012505484861781484, "eval_loss_by_set": { "aqua_rat": 5.850743293762207, "gsm8k": 6.522347883744673, "math_qa": 5.5378468831380205 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.01819560272934041, "math_qa": 0.008040201005025126 } }, { "flos": 4.1784392057786204e+18, "train_loss": 5.702514038085938, "eval_loss": 5.859873385042758, "eval_accuracy": 0.012724879333040808, "eval_loss_by_set": { "aqua_rat": 5.854404449462891, "gsm8k": 6.531768798828125, "math_qa": 5.552377065022786 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.018953752843062926, "math_qa": 0.008040201005025126 } }, { "flos": 4.185329105878647e+18, "train_loss": 5.712012939453125, "eval_loss": 5.84730576180123, "eval_accuracy": 0.013821851689337429, "eval_loss_by_set": { "aqua_rat": 5.850598335266113, "gsm8k": 6.52234510941939, "math_qa": 5.537638346354167 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.019711902956785442, "math_qa": 0.008710217755443886 } }, { "flos": 4.1922702379591926e+18, "train_loss": 5.715165405273438, "eval_loss": 5.843060725444072, "eval_accuracy": 0.01491882404563405, "eval_loss_by_set": { "aqua_rat": 5.849076271057129, "gsm8k": 6.521308898925781, "math_qa": 5.5316956837972 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.018953752843062926, "math_qa": 0.010720268006700168 } }, { "flos": 4.199245187538485e+18, "train_loss": 5.71355224609375, "eval_loss": 5.854658745430611, "eval_accuracy": 0.012066695919262835, "eval_loss_by_set": { "aqua_rat": 5.849291801452637, "gsm8k": 6.524571505459872, "math_qa": 5.548062642415364 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.014404852160727824, "math_qa": 0.009045226130653266 } }, { "flos": 4.206183062960079e+18, "train_loss": 5.722421264648437, "eval_loss": 5.854956240267367, "eval_accuracy": 0.012944273804300131, "eval_loss_by_set": { "aqua_rat": 5.848459243774414, "gsm8k": 6.526037042791193, "math_qa": 5.547918955485026 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.016679302501895376, "math_qa": 0.009380234505862646 } }, { "flos": 4.213129903052161e+18, "train_loss": 5.722940673828125, "eval_loss": 5.847410665976034, "eval_accuracy": 0.01228609039052216, "eval_loss_by_set": { "aqua_rat": 5.848339080810547, "gsm8k": 6.522134954279119, "math_qa": 5.538084665934245 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.015163002274450341, "math_qa": 0.008375209380234505 } }, { "flos": 4.220065037747749e+18, "train_loss": 5.70781005859375, "eval_loss": 5.849933057217984, "eval_accuracy": 0.013602457218078104, "eval_loss_by_set": { "aqua_rat": 5.847411155700684, "gsm8k": 6.520541104403409, "math_qa": 5.5427811940511065 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.019711902956785442, "math_qa": 0.008375209380234505 } }, { "flos": 4.226988982442918e+18, "train_loss": 5.7114801025390625, "eval_loss": 5.850438092205976, "eval_accuracy": 0.01228609039052216, "eval_loss_by_set": { "aqua_rat": 5.8519439697265625, "gsm8k": 6.522299333052202, "math_qa": 5.542376200358073 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.01592115238817286, "math_qa": 0.008710217755443886 } }, { "flos": 4.233972896692699e+18, "train_loss": 5.718336181640625, "eval_loss": 5.856434847857501, "eval_accuracy": 0.010969723562966213, "eval_loss_by_set": { "aqua_rat": 5.851540565490723, "gsm8k": 6.530017505992543, "math_qa": 5.548117319742839 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.016679302501895376, "math_qa": 0.006365159128978224 } }, { "flos": 4.2409060943580365e+18, "train_loss": 5.721056518554687, "eval_loss": 5.850450464197107, "eval_accuracy": 0.012724879333040808, "eval_loss_by_set": { "aqua_rat": 5.850303649902344, "gsm8k": 6.51863583651456, "math_qa": 5.544211069742839 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.013646702047005308, "math_qa": 0.010385259631490788 } }, { "flos": 4.2478686996644495e+18, "train_loss": 5.709140625, "eval_loss": 5.853947974540092, "eval_accuracy": 0.012066695919262835, "eval_loss_by_set": { "aqua_rat": 5.85227108001709, "gsm8k": 6.522593411532315, "math_qa": 5.547625223795573 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.016679302501895376, "math_qa": 0.008375209380234505 } }, { "flos": 4.2547972399746253e+18, "train_loss": 5.7138525390625, "eval_loss": 5.85392225110853, "eval_accuracy": 0.012066695919262835, "eval_loss_by_set": { "aqua_rat": 5.850318908691406, "gsm8k": 6.525724931196733, "math_qa": 5.546312967936198 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.01592115238817286, "math_qa": 0.008375209380234505 } }, { "flos": 4.261701029998887e+18, "train_loss": 5.710439453125, "eval_loss": 5.846827996743692, "eval_accuracy": 0.013821851689337429, "eval_loss_by_set": { "aqua_rat": 5.847264289855957, "gsm8k": 6.516225641424006, "math_qa": 5.539984385172526 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.018953752843062926, "math_qa": 0.009380234505862646 } }, { "flos": 4.2686618013542646e+18, "train_loss": 5.706011962890625, "eval_loss": 5.8521429525839315, "eval_accuracy": 0.014041246160596753, "eval_loss_by_set": { "aqua_rat": 5.845661163330078, "gsm8k": 6.525706898082387, "math_qa": 5.543966293334961 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.02047005307050796, "math_qa": 0.010050251256281407 } }, { "flos": 4.275643097821479e+18, "train_loss": 5.710862426757813, "eval_loss": 5.852461479805611, "eval_accuracy": 0.012505484861781484, "eval_loss_by_set": { "aqua_rat": 5.84867000579834, "gsm8k": 6.520437067205256, "math_qa": 5.546621958414714 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.018953752843062926, "math_qa": 0.007705192629815745 } }, { "flos": 4.2825294943019336e+18, "train_loss": 5.714603271484375, "eval_loss": 5.854808034123601, "eval_accuracy": 0.014260640631856078, "eval_loss_by_set": { "aqua_rat": 5.852557182312012, "gsm8k": 6.52712665904652, "math_qa": 5.5468495686848955 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.022744503411675512, "math_qa": 0.009045226130653266 } }, { "flos": 4.289512460437684e+18, "train_loss": 5.722109985351563, "eval_loss": 5.847760252050452, "eval_accuracy": 0.014260640631856078, "eval_loss_by_set": { "aqua_rat": 5.85004186630249, "gsm8k": 6.523224570534446, "math_qa": 5.53798230489095 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.02047005307050796, "math_qa": 0.009380234505862646 } }, { "flos": 4.2964150757883904e+18, "train_loss": 5.7105810546875, "eval_loss": 5.854383004678263, "eval_accuracy": 0.01228609039052216, "eval_loss_by_set": { "aqua_rat": 5.852170944213867, "gsm8k": 6.526480241255327, "math_qa": 5.546522776285808 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.019711902956785442, "math_qa": 0.007035175879396985 } }, { "flos": 4.303419412607664e+18, "train_loss": 5.720274658203125, "eval_loss": 5.854082494168668, "eval_accuracy": 0.015357612988152698, "eval_loss_by_set": { "aqua_rat": 5.851379871368408, "gsm8k": 6.530541853471235, "math_qa": 5.54426383972168 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.022744503411675512, "math_qa": 0.010720268006700168 } }, { "flos": 4.3103520127356764e+18, "train_loss": 5.708951416015625, "eval_loss": 5.84813844835436, "eval_accuracy": 0.012724879333040808, "eval_loss_by_set": { "aqua_rat": 5.849077224731445, "gsm8k": 6.51995156028054, "math_qa": 5.5401458740234375 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.01819560272934041, "math_qa": 0.008375209380234505 } }, { "flos": 4.317193256761819e+18, "train_loss": 5.70948486328125, "eval_loss": 5.85221545760696, "eval_accuracy": 0.015357612988152698, "eval_loss_by_set": { "aqua_rat": 5.850225925445557, "gsm8k": 6.524170615456321, "math_qa": 5.54440180460612 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.021986353297952996, "math_qa": 0.010385259631490788 } }, { "flos": 4.3241933689438863e+18, "train_loss": 5.7210626220703125, "eval_loss": 5.848850868843697, "eval_accuracy": 0.014041246160596753, "eval_loss_by_set": { "aqua_rat": 5.848432540893555, "gsm8k": 6.520566073330966, "math_qa": 5.541016260782878 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.02122820318423048, "math_qa": 0.009045226130653266 } }, { "flos": 4.3311254332747284e+18, "train_loss": 5.71514404296875, "eval_loss": 5.849881558804898, "eval_accuracy": 0.012724879333040808, "eval_loss_by_set": { "aqua_rat": 5.848236083984375, "gsm8k": 6.518482555042613, "math_qa": 5.543576558430989 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.016679302501895376, "math_qa": 0.008710217755443886 } }, { "flos": 4.3380452354739405e+18, "train_loss": 5.711263427734375, "eval_loss": 5.850402419631545, "eval_accuracy": 0.014041246160596753, "eval_loss_by_set": { "aqua_rat": 5.8505706787109375, "gsm8k": 6.5264060280539775, "math_qa": 5.5405534108479815 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.02350265352539803, "math_qa": 0.007705192629815745 } }, { "flos": 4.34499642422041e+18, "train_loss": 5.7104638671875, "eval_loss": 5.848499143445814, "eval_accuracy": 0.01338306274681878, "eval_loss_by_set": { "aqua_rat": 5.8465375900268555, "gsm8k": 6.518782875754616, "math_qa": 5.541449228922526 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.02047005307050796, "math_qa": 0.007705192629815745 } }, { "flos": 4.3519125993197404e+18, "train_loss": 5.709259033203125, "eval_loss": 5.849143595308871, "eval_accuracy": 0.014041246160596753, "eval_loss_by_set": { "aqua_rat": 5.848957538604736, "gsm8k": 6.524716463955966, "math_qa": 5.53952153523763 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.021986353297952996, "math_qa": 0.007705192629815745 } }, { "flos": 4.358884829110993e+18, "train_loss": 5.71499755859375, "eval_loss": 5.848979486001505, "eval_accuracy": 0.012724879333040808, "eval_loss_by_set": { "aqua_rat": 5.849846839904785, "gsm8k": 6.521247863769531, "math_qa": 5.540784200032552 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.01592115238817286, "math_qa": 0.008710217755443886 } }, { "flos": 4.3658311543438705e+18, "train_loss": 5.723480834960937, "eval_loss": 5.849272238241659, "eval_accuracy": 0.015577007459412023, "eval_loss_by_set": { "aqua_rat": 5.847522735595703, "gsm8k": 6.519514604048296, "math_qa": 5.542223612467448 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.02122820318423048, "math_qa": 0.010050251256281407 } }, { "flos": 4.372747700421001e+18, "train_loss": 5.7030322265625, "eval_loss": 5.854113991196091, "eval_accuracy": 0.012505484861781484, "eval_loss_by_set": { "aqua_rat": 5.853686809539795, "gsm8k": 6.528033863414418, "math_qa": 5.54526964823405 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.01819560272934041, "math_qa": 0.008040201005025126 } }, { "flos": 4.379669419249369e+18, "train_loss": 5.71197021484375, "eval_loss": 5.846786911423142, "eval_accuracy": 0.01338306274681878, "eval_loss_by_set": { "aqua_rat": 5.849662780761719, "gsm8k": 6.519846135919744, "math_qa": 5.538061777750651 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.017437452615617893, "math_qa": 0.008375209380234505 } }, { "flos": 4.3866077483268833e+18, "train_loss": 5.705831298828125, "eval_loss": 5.850863430951093, "eval_accuracy": 0.013821851689337429, "eval_loss_by_set": { "aqua_rat": 5.851698875427246, "gsm8k": 6.526676524769176, "math_qa": 5.541046142578125 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.018953752843062926, "math_qa": 0.008710217755443886 } }, { "flos": 4.393531054145667e+18, "train_loss": 5.7203125, "eval_loss": 5.849538596900734, "eval_accuracy": 0.014699429574374727, "eval_loss_by_set": { "aqua_rat": 5.850825309753418, "gsm8k": 6.519199718128551, "math_qa": 5.542503356933594 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.019711902956785442, "math_qa": 0.009380234505862646 } }, { "flos": 4.4004957613017006e+18, "train_loss": 5.707923583984375, "eval_loss": 5.851349444002719, "eval_accuracy": 0.014480035103115402, "eval_loss_by_set": { "aqua_rat": 5.851412773132324, "gsm8k": 6.523387562144887, "math_qa": 5.543326695760091 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.019711902956785442, "math_qa": 0.009715242881072027 } }, { "flos": 4.4073850842654966e+18, "train_loss": 5.713508911132813, "eval_loss": 5.8491035667625635, "eval_accuracy": 0.011189118034225537, "eval_loss_by_set": { "aqua_rat": 5.8489532470703125, "gsm8k": 6.515900351784446, "math_qa": 5.543500900268555 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.014404852160727824, "math_qa": 0.008040201005025126 } }, { "flos": 4.4143603017433743e+18, "train_loss": 5.716484375, "eval_loss": 5.851963661812447, "eval_accuracy": 0.012066695919262835, "eval_loss_by_set": { "aqua_rat": 5.85304069519043, "gsm8k": 6.522900668057528, "math_qa": 5.544361114501953 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.02047005307050796, "math_qa": 0.006365159128978224 } }, { "flos": 4.421161236964573e+18, "train_loss": 5.70478515625, "eval_loss": 5.847749271908322, "eval_accuracy": 0.015796401930671347, "eval_loss_by_set": { "aqua_rat": 5.847507953643799, "gsm8k": 6.517406116832387, "math_qa": 5.540843327840169 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.02122820318423048, "math_qa": 0.010385259631490788 } }, { "flos": 4.428084645862572e+18, "train_loss": 5.710292358398437, "eval_loss": 5.852991877375422, "eval_accuracy": 0.01338306274681878, "eval_loss_by_set": { "aqua_rat": 5.851779937744141, "gsm8k": 6.52764268354936, "math_qa": 5.543877919514974 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.01819560272934041, "math_qa": 0.008710217755443886 } }, { "flos": 4.435029301963784e+18, "train_loss": 5.718594970703125, "eval_loss": 5.851323308171453, "eval_accuracy": 0.014699429574374727, "eval_loss_by_set": { "aqua_rat": 5.8507843017578125, "gsm8k": 6.526983087713068, "math_qa": 5.541690826416016 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.019711902956785442, "math_qa": 0.010050251256281407 } }, { "flos": 4.4420237463996334e+18, "train_loss": 5.718780517578125, "eval_loss": 5.846984218906712, "eval_accuracy": 0.012944273804300131, "eval_loss_by_set": { "aqua_rat": 5.847301006317139, "gsm8k": 6.514849576083097, "math_qa": 5.540852864583333 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.01819560272934041, "math_qa": 0.008375209380234505 } }, { "flos": 4.449008855724065e+18, "train_loss": 5.7245330810546875, "eval_loss": 5.8473629307102515, "eval_accuracy": 0.012066695919262835, "eval_loss_by_set": { "aqua_rat": 5.850149154663086, "gsm8k": 6.526195179332387, "math_qa": 5.535999298095703 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.017437452615617893, "math_qa": 0.008375209380234505 } }, { "flos": 4.4559280807870464e+18, "train_loss": 5.71281494140625, "eval_loss": 5.849444157368428, "eval_accuracy": 0.012724879333040808, "eval_loss_by_set": { "aqua_rat": 5.84720516204834, "gsm8k": 6.519798278808594, "math_qa": 5.542385101318359 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.018953752843062926, "math_qa": 0.007705192629815745 } }, { "flos": 4.4629130870322627e+18, "train_loss": 5.707775268554688, "eval_loss": 5.852039362933184, "eval_accuracy": 0.013602457218078104, "eval_loss_by_set": { "aqua_rat": 5.850416660308838, "gsm8k": 6.519115794788707, "math_qa": 5.546431223551433 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.017437452615617893, "math_qa": 0.009715242881072027 } }, { "flos": 4.4698114568077967e+18, "train_loss": 5.724158935546875, "eval_loss": 5.846995482573638, "eval_accuracy": 0.014480035103115402, "eval_loss_by_set": { "aqua_rat": 5.849050521850586, "gsm8k": 6.523848100142046, "math_qa": 5.536600112915039 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.02122820318423048, "math_qa": 0.009045226130653266 } }, { "flos": 4.476687302164218e+18, "train_loss": 5.719879760742187, "eval_loss": 5.850395615036423, "eval_accuracy": 0.014260640631856078, "eval_loss_by_set": { "aqua_rat": 5.848628997802734, "gsm8k": 6.523800936612216, "math_qa": 5.541898727416992 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.01592115238817286, "math_qa": 0.011390284757118929 } }, { "flos": 4.483658295004889e+18, "train_loss": 5.707615356445313, "eval_loss": 5.847911576966982, "eval_accuracy": 0.013163668275559455, "eval_loss_by_set": { "aqua_rat": 5.847424507141113, "gsm8k": 6.51952500776811, "math_qa": 5.54012934366862 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.01592115238817286, "math_qa": 0.010050251256281407 } }, { "flos": 4.4905386946372567e+18, "train_loss": 5.720823974609375, "eval_loss": 5.853911863790976, "eval_accuracy": 0.013821851689337429, "eval_loss_by_set": { "aqua_rat": 5.850050449371338, "gsm8k": 6.522779984907671, "math_qa": 5.547669092814128 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.014404852160727824, "math_qa": 0.011055276381909548 } }, { "flos": 4.497505689937117e+18, "train_loss": 5.722110595703125, "eval_loss": 5.849281981184676, "eval_accuracy": 0.01491882404563405, "eval_loss_by_set": { "aqua_rat": 5.84902286529541, "gsm8k": 6.5195534446022725, "math_qa": 5.54209582010905 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.018953752843062926, "math_qa": 0.011055276381909548 } }, { "flos": 4.504438743184179e+18, "train_loss": 5.694150390625, "eval_loss": 5.848266833537334, "eval_accuracy": 0.014260640631856078, "eval_loss_by_set": { "aqua_rat": 5.847614765167236, "gsm8k": 6.521424727006392, "math_qa": 5.5397904713948565 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.018953752843062926, "math_qa": 0.010385259631490788 } }, { "flos": 4.511324974845264e+18, "train_loss": 5.715780029296875, "eval_loss": 5.8499530586036474, "eval_accuracy": 0.014041246160596753, "eval_loss_by_set": { "aqua_rat": 5.849459648132324, "gsm8k": 6.523436112837358, "math_qa": 5.541314442952474 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.019711902956785442, "math_qa": 0.009380234505862646 } }, { "flos": 4.518290588776268e+18, "train_loss": 5.705718383789063, "eval_loss": 5.849752890097128, "eval_accuracy": 0.014480035103115402, "eval_loss_by_set": { "aqua_rat": 5.848182678222656, "gsm8k": 6.522207086736506, "math_qa": 5.541675567626953 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.01819560272934041, "math_qa": 0.010385259631490788 } }, { "flos": 4.5252646525185556e+18, "train_loss": 5.718896484375, "eval_loss": 5.8496904373168945, "eval_accuracy": 0.01338306274681878, "eval_loss_by_set": { "aqua_rat": 5.847645282745361, "gsm8k": 6.520525845614347, "math_qa": 5.542394638061523 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.016679302501895376, "math_qa": 0.009715242881072027 } }, { "flos": 4.532229647974269e+18, "train_loss": 5.714677734375, "eval_loss": 5.848216752748232, "eval_accuracy": 0.014480035103115402, "eval_loss_by_set": { "aqua_rat": 5.848267555236816, "gsm8k": 6.520541104403409, "math_qa": 5.540063858032227 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.01592115238817286, "math_qa": 0.011390284757118929 } }, { "flos": 4.5391809397999534e+18, "train_loss": 5.720321044921875, "eval_loss": 5.85180697569976, "eval_accuracy": 0.01338306274681878, "eval_loss_by_set": { "aqua_rat": 5.850901126861572, "gsm8k": 6.521142439408735, "math_qa": 5.545103708902995 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.01592115238817286, "math_qa": 0.009715242881072027 } }, { "flos": 4.5462098416846766e+18, "train_loss": 5.70995849609375, "eval_loss": 5.85454291266364, "eval_accuracy": 0.012724879333040808, "eval_loss_by_set": { "aqua_rat": 5.850383758544922, "gsm8k": 6.528646989302202, "math_qa": 5.545925140380859 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.017437452615617893, "math_qa": 0.008375209380234505 } }, { "flos": 4.553054259691651e+18, "train_loss": 5.70628662109375, "eval_loss": 5.851812671970677, "eval_accuracy": 0.013821851689337429, "eval_loss_by_set": { "aqua_rat": 5.850266456604004, "gsm8k": 6.522171714089134, "math_qa": 5.54469362894694 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.017437452615617893, "math_qa": 0.009715242881072027 } }, { "flos": 4.559984427794432e+18, "train_loss": 5.706472778320313, "eval_loss": 5.847332954406738, "eval_accuracy": 0.015138218516893374, "eval_loss_by_set": { "aqua_rat": 5.848717212677002, "gsm8k": 6.516368519176137, "math_qa": 5.540576299031575 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.019711902956785442, "math_qa": 0.011055276381909548 } }, { "flos": 4.5669208815818506e+18, "train_loss": 5.712454833984375, "eval_loss": 5.847760870650008, "eval_accuracy": 0.014480035103115402, "eval_loss_by_set": { "aqua_rat": 5.84967565536499, "gsm8k": 6.519319014115767, "math_qa": 5.539803822835286 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.01592115238817286, "math_qa": 0.011390284757118929 } }, { "flos": 4.5738477731614556e+18, "train_loss": 5.716461791992187, "eval_loss": 5.853071058118665, "eval_accuracy": 0.01228609039052216, "eval_loss_by_set": { "aqua_rat": 5.851650238037109, "gsm8k": 6.519927284934304, "math_qa": 5.547547022501628 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.01592115238817286, "math_qa": 0.008710217755443886 } }, { "flos": 4.58082742143497e+18, "train_loss": 5.721173095703125, "eval_loss": 5.847484073123416, "eval_accuracy": 0.014480035103115402, "eval_loss_by_set": { "aqua_rat": 5.850048065185547, "gsm8k": 6.518098310990767, "math_qa": 5.539905548095703 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.017437452615617893, "math_qa": 0.011055276381909548 } }, { "flos": 4.587814839304323e+18, "train_loss": 5.700009765625, "eval_loss": 5.848838032902898, "eval_accuracy": 0.012944273804300131, "eval_loss_by_set": { "aqua_rat": 5.847664833068848, "gsm8k": 6.52036562832919, "math_qa": 5.541152318318685 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.014404852160727824, "math_qa": 0.009715242881072027 } }, { "flos": 4.59469194201242e+18, "train_loss": 5.714853515625, "eval_loss": 5.850381593446474, "eval_accuracy": 0.01338306274681878, "eval_loss_by_set": { "aqua_rat": 5.851192474365234, "gsm8k": 6.521867231889204, "math_qa": 5.542549769083659 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.014404852160727824, "math_qa": 0.010050251256281407 } }, { "flos": 4.601700750966391e+18, "train_loss": 5.714987182617188, "eval_loss": 5.851780994518383, "eval_accuracy": 0.014041246160596753, "eval_loss_by_set": { "aqua_rat": 5.852240085601807, "gsm8k": 6.524189342151988, "math_qa": 5.543555577596028 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.01592115238817286, "math_qa": 0.010385259631490788 } }, { "flos": 4.608667230870176e+18, "train_loss": 5.717027587890625, "eval_loss": 5.852011422853212, "eval_accuracy": 0.014480035103115402, "eval_loss_by_set": { "aqua_rat": 5.8502583503723145, "gsm8k": 6.522141196511009, "math_qa": 5.54501469930013 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.018953752843062926, "math_qa": 0.009380234505862646 } }, { "flos": 4.615580726983655e+18, "train_loss": 5.700714111328125, "eval_loss": 5.851226136491105, "eval_accuracy": 0.01338306274681878, "eval_loss_by_set": { "aqua_rat": 5.847155570983887, "gsm8k": 6.5195229270241475, "math_qa": 5.5452626546223955 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.017437452615617893, "math_qa": 0.009380234505862646 } }, { "flos": 4.622516232657043e+18, "train_loss": 5.71841064453125, "eval_loss": 5.851526724325644, "eval_accuracy": 0.015138218516893374, "eval_loss_by_set": { "aqua_rat": 5.849233627319336, "gsm8k": 6.519660949707031, "math_qa": 5.5454896291097 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.021986353297952996, "math_qa": 0.009380234505862646 } }, { "flos": 4.629438425542427e+18, "train_loss": 5.717030029296875, "eval_loss": 5.852163417919262, "eval_accuracy": 0.013163668275559455, "eval_loss_by_set": { "aqua_rat": 5.848870277404785, "gsm8k": 6.525411432439631, "math_qa": 5.5438658396403 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.014404852160727824, "math_qa": 0.009715242881072027 } }, { "flos": 4.636352869769937e+18, "train_loss": 5.709822998046875, "eval_loss": 5.849325953303157, "eval_accuracy": 0.013821851689337429, "eval_loss_by_set": { "aqua_rat": 5.852071762084961, "gsm8k": 6.5214621803977275, "math_qa": 5.541034698486328 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.014404852160727824, "math_qa": 0.010720268006700168 } }, { "flos": 4.643270158339539e+18, "train_loss": 5.708756713867188, "eval_loss": 5.849089235872836, "eval_accuracy": 0.012944273804300131, "eval_loss_by_set": { "aqua_rat": 5.84831428527832, "gsm8k": 6.524459145285866, "math_qa": 5.539609273274739 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.014404852160727824, "math_qa": 0.010385259631490788 } }, { "flos": 4.650265303928799e+18, "train_loss": 5.704203491210937, "eval_loss": 5.850621197674726, "eval_accuracy": 0.014041246160596753, "eval_loss_by_set": { "aqua_rat": 5.850727081298828, "gsm8k": 6.525874744762074, "math_qa": 5.541121164957683 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.016679302501895376, "math_qa": 0.010385259631490788 } }, { "flos": 4.657155533130695e+18, "train_loss": 5.71665771484375, "eval_loss": 5.848496565947661, "eval_accuracy": 0.012724879333040808, "eval_loss_by_set": { "aqua_rat": 5.851132392883301, "gsm8k": 6.5216827392578125, "math_qa": 5.539733250935872 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.01592115238817286, "math_qa": 0.009045226130653266 } }, { "flos": 4.664064269346669e+18, "train_loss": 5.71387939453125, "eval_loss": 5.847905751821157, "eval_accuracy": 0.013821851689337429, "eval_loss_by_set": { "aqua_rat": 5.850372314453125, "gsm8k": 6.518619884144176, "math_qa": 5.540289560953776 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.01592115238817286, "math_qa": 0.010720268006700168 } }, { "flos": 4.671004679872709e+18, "train_loss": 5.710675659179688, "eval_loss": 5.848666732375686, "eval_accuracy": 0.015357612988152698, "eval_loss_by_set": { "aqua_rat": 5.84998893737793, "gsm8k": 6.52112440629439, "math_qa": 5.540346781412761 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.02122820318423048, "math_qa": 0.011055276381909548 } }, { "flos": 4.677927841273217e+18, "train_loss": 5.706234130859375, "eval_loss": 5.847877193141628, "eval_accuracy": 0.013602457218078104, "eval_loss_by_set": { "aqua_rat": 5.849237442016602, "gsm8k": 6.520117326216265, "math_qa": 5.539653778076172 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.018953752843062926, "math_qa": 0.009380234505862646 } }, { "flos": 4.684912105562833e+18, "train_loss": 5.714022216796875, "eval_loss": 5.853095699001003, "eval_accuracy": 0.013821851689337429, "eval_loss_by_set": { "aqua_rat": 5.851415634155273, "gsm8k": 6.527759898792613, "math_qa": 5.544014612833659 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.01819560272934041, "math_qa": 0.009715242881072027 } }, { "flos": 4.691855648730644e+18, "train_loss": 5.70941650390625, "eval_loss": 5.85042938026222, "eval_accuracy": 0.013163668275559455, "eval_loss_by_set": { "aqua_rat": 5.8492841720581055, "gsm8k": 6.521412242542613, "math_qa": 5.542991002400716 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.019711902956785442, "math_qa": 0.008710217755443886 } }, { "flos": 4.698805456108257e+18, "train_loss": 5.716930541992188, "eval_loss": 5.852279224911252, "eval_accuracy": 0.015138218516893374, "eval_loss_by_set": { "aqua_rat": 5.851237773895264, "gsm8k": 6.524456370960582, "math_qa": 5.544284820556641 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.02047005307050796, "math_qa": 0.010385259631490788 } }, { "flos": 4.705738179716579e+18, "train_loss": 5.718963623046875, "eval_loss": 5.847947507291226, "eval_accuracy": 0.01338306274681878, "eval_loss_by_set": { "aqua_rat": 5.846303939819336, "gsm8k": 6.519276705655185, "math_qa": 5.54039192199707 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.015163002274450341, "math_qa": 0.010720268006700168 } }, { "flos": 4.712692974624965e+18, "train_loss": 5.7108935546875, "eval_loss": 5.850301613678804, "eval_accuracy": 0.013602457218078104, "eval_loss_by_set": { "aqua_rat": 5.84910249710083, "gsm8k": 6.521800648082387, "math_qa": 5.542631149291992 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.017437452615617893, "math_qa": 0.010050251256281407 } }, { "flos": 4.71968801713501e+18, "train_loss": 5.7093017578125, "eval_loss": 5.850379196373192, "eval_accuracy": 0.013163668275559455, "eval_loss_by_set": { "aqua_rat": 5.8508620262146, "gsm8k": 6.52265028520064, "math_qa": 5.542214711507161 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.016679302501895376, "math_qa": 0.009380234505862646 } }, { "flos": 4.726603553357955e+18, "train_loss": 5.722625122070313, "eval_loss": 5.850017212532662, "eval_accuracy": 0.013163668275559455, "eval_loss_by_set": { "aqua_rat": 5.849238872528076, "gsm8k": 6.520118713378906, "math_qa": 5.542952219645183 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.014404852160727824, "math_qa": 0.009715242881072027 } }, { "flos": 4.733518801281221e+18, "train_loss": 5.706488037109375, "eval_loss": 5.849912488782728, "eval_accuracy": 0.01338306274681878, "eval_loss_by_set": { "aqua_rat": 5.850376129150391, "gsm8k": 6.522422790527344, "math_qa": 5.541639963785808 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.016679302501895376, "math_qa": 0.009045226130653266 } }, { "flos": 4.740465517892993e+18, "train_loss": 5.712162475585938, "eval_loss": 5.8495429528726115, "eval_accuracy": 0.012944273804300131, "eval_loss_by_set": { "aqua_rat": 5.849040508270264, "gsm8k": 6.522762645374645, "math_qa": 5.541025797526042 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.017437452615617893, "math_qa": 0.008710217755443886 } }, { "flos": 4.747355355715994e+18, "train_loss": 5.716873779296875, "eval_loss": 5.849664224160684, "eval_accuracy": 0.014480035103115402, "eval_loss_by_set": { "aqua_rat": 5.848484039306641, "gsm8k": 6.5223256891424, "math_qa": 5.541459401448567 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.02047005307050796, "math_qa": 0.010050251256281407 } }, { "flos": 4.754265843204882e+18, "train_loss": 5.713170166015625, "eval_loss": 5.849798305614574, "eval_accuracy": 0.012066695919262835, "eval_loss_by_set": { "aqua_rat": 5.847599983215332, "gsm8k": 6.521555813876065, "math_qa": 5.542092641194661 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.014404852160727824, "math_qa": 0.009045226130653266 } }, { "flos": 4.757755080004862e+18, "train_loss": 5.713170166015625, "eval_loss": 5.850616248878273, "eval_accuracy": 0.014260640631856078, "eval_loss_by_set": { "aqua_rat": 5.848583221435547, "gsm8k": 6.521996238014915, "math_qa": 5.543069839477539 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.018953752843062926, "math_qa": 0.010050251256281407 } } ]