[ { "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": 5513403883847680.0, "train_loss": 6.840919189453125, "eval_loss": 5.996738949337521, "eval_accuracy": 0.010311540149188241, "eval_loss_by_set": { "aqua_rat": 6.013797760009766, "gsm8k": 6.678097811612216, "math_qa": 5.683027903238933 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.015163002274450341, "math_qa": 0.0033500837520938024 } }, { "flos": 1.0966838213083136e+16, "train_loss": 6.072784423828125, "eval_loss": 5.932404698552312, "eval_accuracy": 0.012944273804300131, "eval_loss_by_set": { "aqua_rat": 5.967588424682617, "gsm8k": 6.650193647904829, "math_qa": 5.600486119588216 }, "eval_accuracy_by_set": { "aqua_rat": 0.09055118110236221, "gsm8k": 0.02122820318423048, "math_qa": 0.002680067001675042 } }, { "flos": 1.6546888715075584e+16, "train_loss": 6.030089111328125, "eval_loss": 5.923083537333721, "eval_accuracy": 0.015138218516893374, "eval_loss_by_set": { "aqua_rat": 5.959880828857422, "gsm8k": 6.590212735262784, "math_qa": 5.614249547322591 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.024260803639120546, "math_qa": 0.006700167504187605 } }, { "flos": 2.2032204049678336e+16, "train_loss": 6.002662353515625, "eval_loss": 5.916141355359876, "eval_accuracy": 0.014260640631856078, "eval_loss_by_set": { "aqua_rat": 5.942885398864746, "gsm8k": 6.610508311878551, "math_qa": 5.595661163330078 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.021986353297952996, "math_qa": 0.007370184254606365 } }, { "flos": 2.757186253173555e+16, "train_loss": 5.982556762695313, "eval_loss": 5.911307206024995, "eval_accuracy": 0.011627906976744186, "eval_loss_by_set": { "aqua_rat": 5.929320335388184, "gsm8k": 6.5985565185546875, "math_qa": 5.59481684366862 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.02047005307050796, "math_qa": 0.006700167504187605 } }, { "flos": 3.3115498153508864e+16, "train_loss": 5.969258422851563, "eval_loss": 5.904077684557116, "eval_accuracy": 0.011189118034225537, "eval_loss_by_set": { "aqua_rat": 5.9228057861328125, "gsm8k": 6.594404047185725, "math_qa": 5.586117426554362 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.017437452615617893, "math_qa": 0.005360134003350084 } }, { "flos": 3.863741305192448e+16, "train_loss": 5.943348388671875, "eval_loss": 5.897868079108161, "eval_accuracy": 0.01075032909170689, "eval_loss_by_set": { "aqua_rat": 5.925088882446289, "gsm8k": 6.610272494229403, "math_qa": 5.569080988566081 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.018953752843062926, "math_qa": 0.006030150753768844 } }, { "flos": 4.412820983853875e+16, "train_loss": 5.938201293945313, "eval_loss": 5.893890355084394, "eval_accuracy": 0.008995173321632294, "eval_loss_by_set": { "aqua_rat": 5.9270243644714355, "gsm8k": 6.591992464932528, "math_qa": 5.571165720621745 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.016679302501895376, "math_qa": 0.0036850921273031824 } }, { "flos": 4.967302013386752e+16, "train_loss": 5.920131225585937, "eval_loss": 5.894585944510795, "eval_accuracy": 0.008336989907854322, "eval_loss_by_set": { "aqua_rat": 5.9213762283325195, "gsm8k": 6.56707763671875, "math_qa": 5.584128061930339 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.017437452615617893, "math_qa": 0.003015075376884422 } }, { "flos": 5.521576991863603e+16, "train_loss": 5.92310791015625, "eval_loss": 5.888273831960317, "eval_accuracy": 0.008775778850372971, "eval_loss_by_set": { "aqua_rat": 5.937830448150635, "gsm8k": 6.593216635964134, "math_qa": 5.561045328776042 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.02122820318423048, "math_qa": 0.0020100502512562816 } }, { "flos": 6.076690670079181e+16, "train_loss": 5.913026123046875, "eval_loss": 5.890043671066697, "eval_accuracy": 0.007678806494076349, "eval_loss_by_set": { "aqua_rat": 5.915804862976074, "gsm8k": 6.6021811745383525, "math_qa": 5.561500549316406 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.018953752843062926, "math_qa": 0.001340033500837521 } }, { "flos": 6.630229920658227e+16, "train_loss": 5.88803466796875, "eval_loss": 5.887983270593591, "eval_accuracy": 0.007240017551557701, "eval_loss_by_set": { "aqua_rat": 5.929834365844727, "gsm8k": 6.595453435724432, "math_qa": 5.560238520304362 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.015163002274450341, "math_qa": 0.001340033500837521 } }, { "flos": 7.18316948642857e+16, "train_loss": 5.880645141601563, "eval_loss": 5.893956261712152, "eval_accuracy": 0.009214567792891619, "eval_loss_by_set": { "aqua_rat": 5.92902946472168, "gsm8k": 6.6295859596946025, "math_qa": 5.553869883219401 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.021986353297952996, "math_qa": 0.001340033500837521 } }, { "flos": 7.732061636080435e+16, "train_loss": 5.863912353515625, "eval_loss": 5.88888524029706, "eval_accuracy": 0.008775778850372971, "eval_loss_by_set": { "aqua_rat": 5.942164421081543, "gsm8k": 6.6277382590553975, "math_qa": 5.545804341634114 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.02122820318423048, "math_qa": 0.001340033500837521 } }, { "flos": 8.283943995650867e+16, "train_loss": 5.861953125, "eval_loss": 5.892995035326159, "eval_accuracy": 0.008336989907854322, "eval_loss_by_set": { "aqua_rat": 5.934550762176514, "gsm8k": 6.619213451038707, "math_qa": 5.556681950887044 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.019711902956785442, "math_qa": 0.0023450586264656616 } }, { "flos": 8.833782058162586e+16, "train_loss": 5.842238159179687, "eval_loss": 5.895121857926652, "eval_accuracy": 0.007678806494076349, "eval_loss_by_set": { "aqua_rat": 5.931084632873535, "gsm8k": 6.63817665793679, "math_qa": 5.551558176676433 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.02047005307050796, "math_qa": 0.001340033500837521 } }, { "flos": 9.390639224664883e+16, "train_loss": 5.83958251953125, "eval_loss": 5.903335055789432, "eval_accuracy": 0.008336989907854322, "eval_loss_by_set": { "aqua_rat": 5.928522109985352, "gsm8k": 6.624534606933594, "math_qa": 5.570686340332031 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.019711902956785442, "math_qa": 0.0016750418760469012 } }, { "flos": 9.936872950621798e+16, "train_loss": 5.835812377929687, "eval_loss": 5.913596720308871, "eval_accuracy": 0.007459412022817025, "eval_loss_by_set": { "aqua_rat": 5.940571308135986, "gsm8k": 6.623904141512784, "math_qa": 5.585791269938151 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.01592115238817286, "math_qa": 0.0016750418760469012 } }, { "flos": 1.049203199442944e+17, "train_loss": 5.831904907226562, "eval_loss": 5.9047325752876905, "eval_accuracy": 0.006801228609039052, "eval_loss_by_set": { "aqua_rat": 5.920589447021484, "gsm8k": 6.628042047674006, "math_qa": 5.5718943277994795 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.015163002274450341, "math_qa": 0.0020100502512562816 } }, { "flos": 1.1045608342788506e+17, "train_loss": 5.817382202148438, "eval_loss": 5.906452075855152, "eval_accuracy": 0.007678806494076349, "eval_loss_by_set": { "aqua_rat": 5.9373626708984375, "gsm8k": 6.638716264204546, "math_qa": 5.568255106608073 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.01819560272934041, "math_qa": 0.001340033500837521 } }, { "flos": 1.160410591836242e+17, "train_loss": 5.811625366210937, "eval_loss": 5.917300507828996, "eval_accuracy": 0.008995173321632294, "eval_loss_by_set": { "aqua_rat": 5.9485063552856445, "gsm8k": 6.644864169034091, "math_qa": 5.5812333424886065 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.017437452615617893, "math_qa": 0.0023450586264656616 } }, { "flos": 1.2157210357189837e+17, "train_loss": 5.802669677734375, "eval_loss": 5.905392234389846, "eval_accuracy": 0.008117595436594998, "eval_loss_by_set": { "aqua_rat": 5.922943592071533, "gsm8k": 6.6437766335227275, "math_qa": 5.565503438313802 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.02047005307050796, "math_qa": 0.0016750418760469012 } }, { "flos": 1.2704604261187584e+17, "train_loss": 5.796973876953125, "eval_loss": 5.903622730358227, "eval_accuracy": 0.007898200965335674, "eval_loss_by_set": { "aqua_rat": 5.920851230621338, "gsm8k": 6.658332824707031, "math_qa": 5.556278228759766 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.01819560272934041, "math_qa": 0.001340033500837521 } }, { "flos": 1.3259433612568166e+17, "train_loss": 5.799232788085938, "eval_loss": 5.9185216233537, "eval_accuracy": 0.008995173321632294, "eval_loss_by_set": { "aqua_rat": 5.9222307205200195, "gsm8k": 6.6687538840553975, "math_qa": 5.5743560791015625 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.02047005307050796, "math_qa": 0.003015075376884422 } }, { "flos": 1.3812000160428851e+17, "train_loss": 5.788406982421875, "eval_loss": 5.914422576491897, "eval_accuracy": 0.009872751206669592, "eval_loss_by_set": { "aqua_rat": 5.924260139465332, "gsm8k": 6.673408508300781, "math_qa": 5.565734227498372 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.021986353297952996, "math_qa": 0.002680067001675042 } }, { "flos": 1.436434412160942e+17, "train_loss": 5.7747021484375, "eval_loss": 5.921548379434122, "eval_accuracy": 0.009872751206669592, "eval_loss_by_set": { "aqua_rat": 5.927288055419922, "gsm8k": 6.662727355957031, "math_qa": 5.581363042195638 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.016679302501895376, "math_qa": 0.004690117252931323 } }, { "flos": 1.4918711871379866e+17, "train_loss": 5.7822503662109375, "eval_loss": 5.918978845750964, "eval_accuracy": 0.007678806494076349, "eval_loss_by_set": { "aqua_rat": 5.924814701080322, "gsm8k": 6.670995538884943, "math_qa": 5.573818206787109 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.017437452615617893, "math_qa": 0.0016750418760469012 } }, { "flos": 1.5471789520348774e+17, "train_loss": 5.770344848632813, "eval_loss": 5.931994257746516, "eval_accuracy": 0.007240017551557701, "eval_loss_by_set": { "aqua_rat": 5.938804626464844, "gsm8k": 6.68877549604936, "math_qa": 5.5845686594645185 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.013646702047005308, "math_qa": 0.003015075376884422 } }, { "flos": 1.6027012451794944e+17, "train_loss": 5.775986328125, "eval_loss": 5.925306913015005, "eval_accuracy": 0.008117595436594998, "eval_loss_by_set": { "aqua_rat": 5.922857761383057, "gsm8k": 6.679625077681108, "math_qa": 5.579781850179036 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.017437452615617893, "math_qa": 0.0033500837520938024 } }, { "flos": 1.6586431190479667e+17, "train_loss": 5.764375610351562, "eval_loss": 5.9301576872129695, "eval_accuracy": 0.007898200965335674, "eval_loss_by_set": { "aqua_rat": 5.927857398986816, "gsm8k": 6.7082297585227275, "math_qa": 5.573733011881511 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.016679302501895376, "math_qa": 0.004020100502512563 } }, { "flos": 1.7138053919277056e+17, "train_loss": 5.761889038085937, "eval_loss": 5.932596464414854, "eval_accuracy": 0.007678806494076349, "eval_loss_by_set": { "aqua_rat": 5.934412002563477, "gsm8k": 6.7048471624201, "math_qa": 5.578496932983398 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.013646702047005308, "math_qa": 0.004020100502512563 } }, { "flos": 1.769448448815268e+17, "train_loss": 5.751289672851563, "eval_loss": 5.93962963207348, "eval_accuracy": 0.009214567792891619, "eval_loss_by_set": { "aqua_rat": 5.933067321777344, "gsm8k": 6.702864213423296, "math_qa": 5.590360641479492 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.014404852160727824, "math_qa": 0.005695142378559464 } }, { "flos": 1.8247040728091853e+17, "train_loss": 5.745140380859375, "eval_loss": 5.941958839828904, "eval_accuracy": 0.010969723562966213, "eval_loss_by_set": { "aqua_rat": 5.930236339569092, "gsm8k": 6.713856090198863, "math_qa": 5.589149475097656 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.015163002274450341, "math_qa": 0.008040201005025126 } }, { "flos": 1.880275205100667e+17, "train_loss": 5.7523126220703125, "eval_loss": 5.935115659559095, "eval_accuracy": 0.01184730144800351, "eval_loss_by_set": { "aqua_rat": 5.95407772064209, "gsm8k": 6.703451676802202, "math_qa": 5.581381479899089 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.015163002274450341, "math_qa": 0.008375209380234505 } }, { "flos": 1.9350749827406234e+17, "train_loss": 5.734884033203125, "eval_loss": 5.93635486912083, "eval_accuracy": 0.007020623080298377, "eval_loss_by_set": { "aqua_rat": 5.941041946411133, "gsm8k": 6.717411388050426, "math_qa": 5.577980041503906 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.011372251705837756, "math_qa": 0.0036850921273031824 } }, { "flos": 1.990867445434286e+17, "train_loss": 5.749573974609375, "eval_loss": 5.9424943923950195, "eval_accuracy": 0.007240017551557701, "eval_loss_by_set": { "aqua_rat": 5.942192554473877, "gsm8k": 6.726764332164418, "math_qa": 5.583062489827474 }, "eval_accuracy_by_set": { "aqua_rat": 0.011811023622047244, "gsm8k": 0.016679302501895376, "math_qa": 0.002680067001675042 } }, { "flos": 2.0456080760058675e+17, "train_loss": 5.7327032470703125, "eval_loss": 5.95803503088049, "eval_accuracy": 0.010969723562966213, "eval_loss_by_set": { "aqua_rat": 5.9533843994140625, "gsm8k": 6.745434847745028, "math_qa": 5.597531000773112 }, "eval_accuracy_by_set": { "aqua_rat": 0.011811023622047244, "gsm8k": 0.01819560272934041, "math_qa": 0.007705192629815745 } }, { "flos": 2.100953142693724e+17, "train_loss": 5.737644653320313, "eval_loss": 5.94542493046941, "eval_accuracy": 0.011408512505484861, "eval_loss_by_set": { "aqua_rat": 5.9472551345825195, "gsm8k": 6.720628218217329, "math_qa": 5.5899709065755205 }, "eval_accuracy_by_set": { "aqua_rat": 0.011811023622047244, "gsm8k": 0.014404852160727824, "math_qa": 0.010050251256281407 } }, { "flos": 2.1558802768514253e+17, "train_loss": 5.722840576171875, "eval_loss": 5.940750379820128, "eval_accuracy": 0.010969723562966213, "eval_loss_by_set": { "aqua_rat": 5.955479621887207, "gsm8k": 6.739482532848012, "math_qa": 5.573437372843425 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.01061410159211524, "math_qa": 0.010720268006700168 } }, { "flos": 2.2109998899684966e+17, "train_loss": 5.7253076171875, "eval_loss": 5.948082279514622, "eval_accuracy": 0.01184730144800351, "eval_loss_by_set": { "aqua_rat": 5.952104568481445, "gsm8k": 6.7392966530539775, "math_qa": 5.585107167561849 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.018953752843062926, "math_qa": 0.009045226130653266 } }, { "flos": 2.2663340367020032e+17, "train_loss": 5.7129296875, "eval_loss": 5.965179804209116, "eval_accuracy": 0.013163668275559455, "eval_loss_by_set": { "aqua_rat": 5.951048851013184, "gsm8k": 6.739894520152699, "math_qa": 5.611279805501302 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.016679302501895376, "math_qa": 0.010050251256281407 } }, { "flos": 2.3217442258314854e+17, "train_loss": 5.721099243164063, "eval_loss": 5.956789738423115, "eval_accuracy": 0.012724879333040808, "eval_loss_by_set": { "aqua_rat": 5.955100059509277, "gsm8k": 6.75052920254794, "math_qa": 5.593133290608724 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.01819560272934041, "math_qa": 0.010050251256281407 } }, { "flos": 2.37729557442986e+17, "train_loss": 5.71685302734375, "eval_loss": 5.955248446077914, "eval_accuracy": 0.013821851689337429, "eval_loss_by_set": { "aqua_rat": 5.96649169921875, "gsm8k": 6.735325206409801, "math_qa": 5.5967763264973955 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.013646702047005308, "math_qa": 0.012730318257956449 } }, { "flos": 2.432647641914409e+17, "train_loss": 5.709388427734375, "eval_loss": 5.954228349634119, "eval_accuracy": 0.015577007459412023, "eval_loss_by_set": { "aqua_rat": 5.944568157196045, "gsm8k": 6.743594082919034, "math_qa": 5.593240737915039 }, "eval_accuracy_by_set": { "aqua_rat": 0.011811023622047244, "gsm8k": 0.018953752843062926, "math_qa": 0.01440536013400335 } }, { "flos": 2.4881979650893414e+17, "train_loss": 5.714486083984375, "eval_loss": 5.954681087184596, "eval_accuracy": 0.014260640631856078, "eval_loss_by_set": { "aqua_rat": 5.964715957641602, "gsm8k": 6.7640464089133525, "math_qa": 5.5828857421875 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.019711902956785442, "math_qa": 0.011725293132328308 } }, { "flos": 2.5435860995617587e+17, "train_loss": 5.71013916015625, "eval_loss": 5.980007145855878, "eval_accuracy": 0.01228609039052216, "eval_loss_by_set": { "aqua_rat": 5.963094234466553, "gsm8k": 6.777239712801847, "math_qa": 5.616018295288086 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.013646702047005308, "math_qa": 0.011390284757118929 } }, { "flos": 2.59921555750912e+17, "train_loss": 5.7069970703125, "eval_loss": 5.968016547125739, "eval_accuracy": 0.012724879333040808, "eval_loss_by_set": { "aqua_rat": 5.955905914306641, "gsm8k": 6.759778109463778, "math_qa": 5.6061350504557295 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.01592115238817286, "math_qa": 0.010385259631490788 } }, { "flos": 2.6544528419926835e+17, "train_loss": 5.698810424804687, "eval_loss": 5.9720452798379435, "eval_accuracy": 0.016673979815708645, "eval_loss_by_set": { "aqua_rat": 5.975536346435547, "gsm8k": 6.784991177645597, "math_qa": 5.599154154459636 }, "eval_accuracy_by_set": { "aqua_rat": 0.011811023622047244, "gsm8k": 0.01592115238817286, "math_qa": 0.01742043551088777 } }, { "flos": 2.7095407153014374e+17, "train_loss": 5.695626831054687, "eval_loss": 5.9710063161076725, "eval_accuracy": 0.01645458534444932, "eval_loss_by_set": { "aqua_rat": 5.973901271820068, "gsm8k": 6.784511219371449, "math_qa": 5.597908655802409 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.014404852160727824, "math_qa": 0.017085427135678392 } }, { "flos": 2.7652099446459597e+17, "train_loss": 5.69896484375, "eval_loss": 5.977478749043232, "eval_accuracy": 0.014260640631856078, "eval_loss_by_set": { "aqua_rat": 5.997686386108398, "gsm8k": 6.774889859286222, "math_qa": 5.610314687093099 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.016679302501895376, "math_qa": 0.01306532663316583 } }, { "flos": 2.8202230103618355e+17, "train_loss": 5.689412841796875, "eval_loss": 5.961891896015889, "eval_accuracy": 0.018867924528301886, "eval_loss_by_set": { "aqua_rat": 5.975263595581055, "gsm8k": 6.774635314941406, "math_qa": 5.58827018737793 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.016679302501895376, "math_qa": 0.019765494137353432 } }, { "flos": 2.875906874807419e+17, "train_loss": 5.681657104492188, "eval_loss": 5.978163899602117, "eval_accuracy": 0.01689337428696797, "eval_loss_by_set": { "aqua_rat": 5.969536781311035, "gsm8k": 6.7778237082741475, "math_qa": 5.612372080485026 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.017437452615617893, "math_qa": 0.01641541038525963 } }, { "flos": 2.931398260293632e+17, "train_loss": 5.690144653320313, "eval_loss": 5.986855429572028, "eval_accuracy": 0.017551557700745943, "eval_loss_by_set": { "aqua_rat": 5.975140571594238, "gsm8k": 6.782992276278409, "math_qa": 5.622935612996419 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.015163002274450341, "math_qa": 0.018425460636515914 } }, { "flos": 2.987170117881692e+17, "train_loss": 5.67990966796875, "eval_loss": 5.980372351569098, "eval_accuracy": 0.01908731899956121, "eval_loss_by_set": { "aqua_rat": 5.980127334594727, "gsm8k": 6.776780561967329, "math_qa": 5.61537233988444 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.017437452615617893, "math_qa": 0.019765494137353432 } }, { "flos": 3.0425708258708685e+17, "train_loss": 5.685537109375, "eval_loss": 5.989714132772909, "eval_accuracy": 0.021939447125932425, "eval_loss_by_set": { "aqua_rat": 5.993556976318359, "gsm8k": 6.777100996537642, "math_qa": 5.62850824991862 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.01819560272934041, "math_qa": 0.023785594639865997 } }, { "flos": 3.098297554090066e+17, "train_loss": 5.676035766601562, "eval_loss": 5.987073846765466, "eval_accuracy": 0.02150065818341378, "eval_loss_by_set": { "aqua_rat": 5.980886459350586, "gsm8k": 6.786362387917259, "math_qa": 5.621248881022136 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.014404852160727824, "math_qa": 0.022445561139028476 } }, { "flos": 3.153256632067031e+17, "train_loss": 5.672803344726563, "eval_loss": 5.981275274946883, "eval_accuracy": 0.015357612988152698, "eval_loss_by_set": { "aqua_rat": 5.968564510345459, "gsm8k": 6.792509599165483, "math_qa": 5.61051877339681 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.01819560272934041, "math_qa": 0.01306532663316583 } }, { "flos": 3.208680414768005e+17, "train_loss": 5.67459228515625, "eval_loss": 5.987826630875871, "eval_accuracy": 0.017112768758227294, "eval_loss_by_set": { "aqua_rat": 5.974301338195801, "gsm8k": 6.791245893998579, "math_qa": 5.620719909667969 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.025018953752843062, "math_qa": 0.012060301507537688 } }, { "flos": 3.264353563270185e+17, "train_loss": 5.669498901367188, "eval_loss": 5.989239228738321, "eval_accuracy": 0.017112768758227294, "eval_loss_by_set": { "aqua_rat": 5.991549968719482, "gsm8k": 6.80885800448331, "math_qa": 5.6133880615234375 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.019711902956785442, "math_qa": 0.01574539363484087 } }, { "flos": 3.319399603597476e+17, "train_loss": 5.66406005859375, "eval_loss": 5.996440578151393, "eval_accuracy": 0.02215884159719175, "eval_loss_by_set": { "aqua_rat": 5.990570068359375, "gsm8k": 6.81018759987571, "math_qa": 5.62396240234375 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.013646702047005308, "math_qa": 0.02579564489112228 } }, { "flos": 3.374718288448717e+17, "train_loss": 5.658338012695313, "eval_loss": 5.993585457672944, "eval_accuracy": 0.02150065818341378, "eval_loss_by_set": { "aqua_rat": 5.9920830726623535, "gsm8k": 6.814284584738991, "math_qa": 5.617556889851888 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.02122820318423048, "math_qa": 0.020770519262981575 } }, { "flos": 3.430224094287626e+17, "train_loss": 5.664517822265625, "eval_loss": 5.985902193430308, "eval_accuracy": 0.021281263712154455, "eval_loss_by_set": { "aqua_rat": 5.99191427230835, "gsm8k": 6.798990423029119, "math_qa": 5.612735748291016 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.01288855193328279, "math_qa": 0.025460636515912898 } }, { "flos": 3.485289096895529e+17, "train_loss": 5.6591357421875, "eval_loss": 5.991518433029587, "eval_accuracy": 0.023255813953488372, "eval_loss_by_set": { "aqua_rat": 5.986077308654785, "gsm8k": 6.812367525967685, "math_qa": 5.615749359130859 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.019711902956785442, "math_qa": 0.024790619765494137 } }, { "flos": 3.5406807371350016e+17, "train_loss": 5.66282470703125, "eval_loss": 6.005982167011982, "eval_accuracy": 0.0217200526546731, "eval_loss_by_set": { "aqua_rat": 5.984384536743164, "gsm8k": 6.84516698663885, "math_qa": 5.62315559387207 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.021986353297952996, "math_qa": 0.020770519262981575 } }, { "flos": 3.596225498327286e+17, "train_loss": 5.66167724609375, "eval_loss": 6.002040863037109, "eval_accuracy": 0.019745502413339184, "eval_loss_by_set": { "aqua_rat": 5.973321914672852, "gsm8k": 6.81340234929865, "math_qa": 5.632560094197591 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.016679302501895376, "math_qa": 0.020435510887772193 } }, { "flos": 3.652052379815117e+17, "train_loss": 5.658475341796875, "eval_loss": 6.009961308659734, "eval_accuracy": 0.02457218078104432, "eval_loss_by_set": { "aqua_rat": 6.010032653808594, "gsm8k": 6.820274353027344, "math_qa": 5.638561884562175 }, "eval_accuracy_by_set": { "aqua_rat": 0.011811023622047244, "gsm8k": 0.01819560272934041, "math_qa": 0.02847571189279732 } }, { "flos": 3.707522328045814e+17, "train_loss": 5.6571728515625, "eval_loss": 6.0190453400483, "eval_accuracy": 0.024791575252303643, "eval_loss_by_set": { "aqua_rat": 6.000940322875977, "gsm8k": 6.834090492942116, "math_qa": 5.646991729736328 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.018953752843062926, "math_qa": 0.02747068676716918 } }, { "flos": 3.762819785021194e+17, "train_loss": 5.6469488525390625, "eval_loss": 6.0064675099140885, "eval_accuracy": 0.020623080298376482, "eval_loss_by_set": { "aqua_rat": 5.9822587966918945, "gsm8k": 6.817178899591619, "math_qa": 5.636908849080403 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.01288855193328279, "math_qa": 0.024455611390284758 } }, { "flos": 3.817883756836946e+17, "train_loss": 5.6512548828125, "eval_loss": 6.018910124495223, "eval_accuracy": 0.018209741114523913, "eval_loss_by_set": { "aqua_rat": 6.006453514099121, "gsm8k": 6.847333041104403, "math_qa": 5.6402543385823565 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.017437452615617893, "math_qa": 0.017755443886097153 } }, { "flos": 3.8732383046651085e+17, "train_loss": 5.635723266601563, "eval_loss": 6.023000691388105, "eval_accuracy": 0.023255813953488372, "eval_loss_by_set": { "aqua_rat": 6.0053887367248535, "gsm8k": 6.837749827991832, "math_qa": 5.651041666666667 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.01819560272934041, "math_qa": 0.023785594639865997 } }, { "flos": 3.928273011647447e+17, "train_loss": 5.6455615234375, "eval_loss": 6.025350673778637, "eval_accuracy": 0.025449758666081616, "eval_loss_by_set": { "aqua_rat": 6.024247169494629, "gsm8k": 6.848542646928267, "math_qa": 5.648146311442058 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.01819560272934041, "math_qa": 0.02847571189279732 } }, { "flos": 3.983919982323958e+17, "train_loss": 5.64718505859375, "eval_loss": 6.021869659423828, "eval_accuracy": 0.02457218078104432, "eval_loss_by_set": { "aqua_rat": 6.021047592163086, "gsm8k": 6.847613941539418, "math_qa": 5.643472035725911 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.018953752843062926, "math_qa": 0.02579564489112228 } }, { "flos": 4.039862886984581e+17, "train_loss": 5.6452569580078125, "eval_loss": 6.024358336989944, "eval_accuracy": 0.0225976305397104, "eval_loss_by_set": { "aqua_rat": 6.019339561462402, "gsm8k": 6.863109241832387, "math_qa": 5.64034907023112 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.016679302501895376, "math_qa": 0.024120603015075376 } }, { "flos": 4.0952411322947994e+17, "train_loss": 5.6373358154296875, "eval_loss": 6.0186241768501905, "eval_accuracy": 0.02413339183852567, "eval_loss_by_set": { "aqua_rat": 6.011871337890625, "gsm8k": 6.847838661887429, "math_qa": 5.639130274454753 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.022744503411675512, "math_qa": 0.02512562814070352 } }, { "flos": 4.151230406496092e+17, "train_loss": 5.6424365234375, "eval_loss": 6.0187495463603256, "eval_accuracy": 0.02632733655111891, "eval_loss_by_set": { "aqua_rat": 6.001007080078125, "gsm8k": 6.85465517911044, "math_qa": 5.637104670206706 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.02122820318423048, "math_qa": 0.0288107202680067 } }, { "flos": 4.2064217348295885e+17, "train_loss": 5.644056396484375, "eval_loss": 6.013936223210515, "eval_accuracy": 0.02369460289600702, "eval_loss_by_set": { "aqua_rat": 5.9926300048828125, "gsm8k": 6.837579900568182, "math_qa": 5.638208389282227 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.014404852160727824, "math_qa": 0.02847571189279732 } }, { "flos": 4.261573705156526e+17, "train_loss": 5.6312548828125, "eval_loss": 6.025414750382707, "eval_accuracy": 0.02917946467749013, "eval_loss_by_set": { "aqua_rat": 6.019798278808594, "gsm8k": 6.840682289817116, "math_qa": 5.652218500773112 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.01819560272934041, "math_qa": 0.03484087102177554 } }, { "flos": 4.316475901660365e+17, "train_loss": 5.622442626953125, "eval_loss": 6.026229549098659, "eval_accuracy": 0.0298376480912681, "eval_loss_by_set": { "aqua_rat": 6.021768569946289, "gsm8k": 6.8594277121803975, "math_qa": 5.6447188059488935 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.017437452615617893, "math_qa": 0.035175879396984924 } }, { "flos": 4.371695464035123e+17, "train_loss": 5.633184814453125, "eval_loss": 6.0244744790566935, "eval_accuracy": 0.025449758666081616, "eval_loss_by_set": { "aqua_rat": 6.027095794677734, "gsm8k": 6.868778575550426, "math_qa": 5.6372833251953125 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.02047005307050796, "math_qa": 0.02680067001675042 } }, { "flos": 4.427191788733727e+17, "train_loss": 5.640474853515625, "eval_loss": 6.036164129102552, "eval_accuracy": 0.020842474769635806, "eval_loss_by_set": { "aqua_rat": 6.019740581512451, "gsm8k": 6.843016884543679, "math_qa": 5.667725245157878 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.019711902956785442, "math_qa": 0.020100502512562814 } }, { "flos": 4.483036392330363e+17, "train_loss": 5.635361938476563, "eval_loss": 6.026444718644425, "eval_accuracy": 0.023255813953488372, "eval_loss_by_set": { "aqua_rat": 6.012142181396484, "gsm8k": 6.839646079323509, "math_qa": 5.654919306437175 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.013646702047005308, "math_qa": 0.02613065326633166 } }, { "flos": 4.5386200981386035e+17, "train_loss": 5.627371215820313, "eval_loss": 6.015083364538245, "eval_accuracy": 0.028960070206230804, "eval_loss_by_set": { "aqua_rat": 6.021470069885254, "gsm8k": 6.828632007945668, "math_qa": 5.641674677530925 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.019711902956785442, "math_qa": 0.032160804020100506 } }, { "flos": 4.593660576483246e+17, "train_loss": 5.6181591796875, "eval_loss": 6.0442714175662475, "eval_accuracy": 0.028082492321193506, "eval_loss_by_set": { "aqua_rat": 6.036317825317383, "gsm8k": 6.856742858886719, "math_qa": 5.6725514729817705 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.022744503411675512, "math_qa": 0.03149078726968174 } }, { "flos": 4.648860151153951e+17, "train_loss": 5.610560302734375, "eval_loss": 6.035336107821078, "eval_accuracy": 0.02632733655111891, "eval_loss_by_set": { "aqua_rat": 6.015866279602051, "gsm8k": 6.86376328901811, "math_qa": 5.657262802124023 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.019711902956785442, "math_qa": 0.02981574539363484 } }, { "flos": 4.70404261574869e+17, "train_loss": 5.6230712890625, "eval_loss": 6.030392414814717, "eval_accuracy": 0.02874067573497148, "eval_loss_by_set": { "aqua_rat": 6.035831451416016, "gsm8k": 6.877993496981534, "math_qa": 5.641455332438151 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.024260803639120546, "math_qa": 0.03082077051926298 } }, { "flos": 4.759491958873784e+17, "train_loss": 5.633134765625, "eval_loss": 6.023565575883195, "eval_accuracy": 0.035103115401491886, "eval_loss_by_set": { "aqua_rat": 6.015255451202393, "gsm8k": 6.85492636940696, "math_qa": 5.64321772257487 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.02122820318423048, "math_qa": 0.04120603015075377 } }, { "flos": 4.8149895237441946e+17, "train_loss": 5.6199365234375, "eval_loss": 6.059473810969172, "eval_accuracy": 0.025230364194822292, "eval_loss_by_set": { "aqua_rat": 6.039253234863281, "gsm8k": 6.866681185635653, "math_qa": 5.691188812255859 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.017437452615617893, "math_qa": 0.02814070351758794 } }, { "flos": 4.870185598016553e+17, "train_loss": 5.614698486328125, "eval_loss": 6.052386283874512, "eval_accuracy": 0.03554190434401053, "eval_loss_by_set": { "aqua_rat": 6.056777477264404, "gsm8k": 6.89215781471946, "math_qa": 5.667125066121419 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.024260803639120546, "math_qa": 0.040871021775544386 } }, { "flos": 4.925292846996521e+17, "train_loss": 5.61375244140625, "eval_loss": 6.057968268523345, "eval_accuracy": 0.032250987275120664, "eval_loss_by_set": { "aqua_rat": 6.041445255279541, "gsm8k": 6.891633467240767, "math_qa": 5.677248636881511 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.018953752843062926, "math_qa": 0.03919597989949749 } }, { "flos": 4.980612562639913e+17, "train_loss": 5.616737060546875, "eval_loss": 6.042190448657887, "eval_accuracy": 0.02874067573497148, "eval_loss_by_set": { "aqua_rat": 6.036458969116211, "gsm8k": 6.878007368607954, "math_qa": 5.659585316975911 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.02122820318423048, "math_qa": 0.031825795644891124 } }, { "flos": 5.035747422890885e+17, "train_loss": 5.61484375, "eval_loss": 6.051265458802919, "eval_accuracy": 0.028521281263712155, "eval_loss_by_set": { "aqua_rat": 6.052529335021973, "gsm8k": 6.8900909423828125, "math_qa": 5.666698455810547 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.02047005307050796, "math_qa": 0.031825795644891124 } }, { "flos": 5.091159877615616e+17, "train_loss": 5.618634643554688, "eval_loss": 6.064906197625238, "eval_accuracy": 0.028960070206230804, "eval_loss_by_set": { "aqua_rat": 6.051388740539551, "gsm8k": 6.894468827681108, "math_qa": 5.6858164469401045 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.02577710386656558, "math_qa": 0.03015075376884422 } }, { "flos": 5.14668341093204e+17, "train_loss": 5.605787353515625, "eval_loss": 6.045856114980337, "eval_accuracy": 0.026107942079859586, "eval_loss_by_set": { "aqua_rat": 6.024931907653809, "gsm8k": 6.86857813054865, "math_qa": 5.67051887512207 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.021986353297952996, "math_qa": 0.027135678391959798 } }, { "flos": 5.201871034856243e+17, "train_loss": 5.605726928710937, "eval_loss": 6.058617385658058, "eval_accuracy": 0.031592803861342694, "eval_loss_by_set": { "aqua_rat": 6.055613040924072, "gsm8k": 6.897709239612926, "math_qa": 5.674283981323242 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.02350265352539803, "math_qa": 0.034170854271356785 } }, { "flos": 5.257386531215114e+17, "train_loss": 5.609656982421875, "eval_loss": 6.057915146286423, "eval_accuracy": 0.03466432645897324, "eval_loss_by_set": { "aqua_rat": 6.038349151611328, "gsm8k": 6.884287053888494, "math_qa": 5.680791854858398 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.021986353297952996, "math_qa": 0.04020100502512563 } }, { "flos": 5.31249171861078e+17, "train_loss": 5.598553466796875, "eval_loss": 6.074155137345597, "eval_accuracy": 0.02720491443615621, "eval_loss_by_set": { "aqua_rat": 6.057863235473633, "gsm8k": 6.90323916348544, "math_qa": 5.695515950520833 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.022744503411675512, "math_qa": 0.02814070351758794 } }, { "flos": 5.3683550804770816e+17, "train_loss": 5.6045654296875, "eval_loss": 6.063887003305796, "eval_accuracy": 0.032250987275120664, "eval_loss_by_set": { "aqua_rat": 6.066217422485352, "gsm8k": 6.897097500887784, "math_qa": 5.681804656982422 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.026535253980288095, "math_qa": 0.033165829145728645 } }, { "flos": 5.4239548602004275e+17, "train_loss": 5.61597900390625, "eval_loss": 6.06535259453026, "eval_accuracy": 0.027863097849934182, "eval_loss_by_set": { "aqua_rat": 6.054985523223877, "gsm8k": 6.899862116033381, "math_qa": 5.683732986450195 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.01819560272934041, "math_qa": 0.02948073701842546 } }, { "flos": 5.47938957359317e+17, "train_loss": 5.599671020507812, "eval_loss": 6.087551220043285, "eval_accuracy": 0.02720491443615621, "eval_loss_by_set": { "aqua_rat": 6.080905914306641, "gsm8k": 6.90536845814098, "math_qa": 5.7132720947265625 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.021986353297952996, "math_qa": 0.02914572864321608 } }, { "flos": 5.535279929328927e+17, "train_loss": 5.598541259765625, "eval_loss": 6.059256991824588, "eval_accuracy": 0.03247038174637999, "eval_loss_by_set": { "aqua_rat": 6.053701400756836, "gsm8k": 6.886110479181463, "math_qa": 5.680745442708333 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.018953752843062926, "math_qa": 0.037520938023450585 } }, { "flos": 5.5905819228635136e+17, "train_loss": 5.601924438476562, "eval_loss": 6.066868395418735, "eval_accuracy": 0.031592803861342694, "eval_loss_by_set": { "aqua_rat": 6.054234504699707, "gsm8k": 6.907018488103693, "math_qa": 5.682852427164714 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.024260803639120546, "math_qa": 0.03484087102177554 } }, { "flos": 5.646609524279214e+17, "train_loss": 5.60259521484375, "eval_loss": 6.045665380117056, "eval_accuracy": 0.035761298815269855, "eval_loss_by_set": { "aqua_rat": 6.041983604431152, "gsm8k": 6.880390514026988, "math_qa": 5.663389841715495 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.02122820318423048, "math_qa": 0.04120603015075377 } }, { "flos": 5.701959331537224e+17, "train_loss": 5.59992431640625, "eval_loss": 6.08093699893436, "eval_accuracy": 0.035103115401491886, "eval_loss_by_set": { "aqua_rat": 6.095311164855957, "gsm8k": 6.8986122824928975, "math_qa": 5.7049713134765625 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.017437452615617893, "math_qa": 0.040871021775544386 } }, { "flos": 5.7574424706862285e+17, "train_loss": 5.59584228515625, "eval_loss": 6.062598924379091, "eval_accuracy": 0.03466432645897324, "eval_loss_by_set": { "aqua_rat": 6.064791679382324, "gsm8k": 6.905163158069957, "math_qa": 5.676240921020508 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.028051554207733132, "math_qa": 0.03819095477386935 } }, { "flos": 5.812846883084698e+17, "train_loss": 5.5867462158203125, "eval_loss": 6.074744121448414, "eval_accuracy": 0.035761298815269855, "eval_loss_by_set": { "aqua_rat": 6.067672252655029, "gsm8k": 6.887356844815341, "math_qa": 5.7028859456380205 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.022744503411675512, "math_qa": 0.04053601340033501 } }, { "flos": 5.868047069788242e+17, "train_loss": 5.590261840820313, "eval_loss": 6.090348475688213, "eval_accuracy": 0.031812198332602015, "eval_loss_by_set": { "aqua_rat": 6.102644920349121, "gsm8k": 6.940049604936079, "math_qa": 5.699877421061198 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.017437452615617893, "math_qa": 0.03819095477386935 } }, { "flos": 5.922759058296668e+17, "train_loss": 5.599110107421875, "eval_loss": 6.071255091074351, "eval_accuracy": 0.03466432645897324, "eval_loss_by_set": { "aqua_rat": 6.079522132873535, "gsm8k": 6.915983026677912, "math_qa": 5.683399200439453 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.02047005307050796, "math_qa": 0.039530988274706864 } }, { "flos": 5.978440442398638e+17, "train_loss": 5.59514892578125, "eval_loss": 6.069357176084776, "eval_accuracy": 0.03312856516015796, "eval_loss_by_set": { "aqua_rat": 6.084384918212891, "gsm8k": 6.903651844371449, "math_qa": 5.685719807942708 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.021986353297952996, "math_qa": 0.03785594639865997 } }, { "flos": 6.03404475868119e+17, "train_loss": 5.58689208984375, "eval_loss": 6.058724738456108, "eval_accuracy": 0.030057042562527423, "eval_loss_by_set": { "aqua_rat": 6.063450813293457, "gsm8k": 6.921132867986506, "math_qa": 5.6630605061848955 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.025018953752843062, "math_qa": 0.032160804020100506 } }, { "flos": 6.089085237025833e+17, "train_loss": 5.583152465820312, "eval_loss": 6.074039046828811, "eval_accuracy": 0.030057042562527423, "eval_loss_by_set": { "aqua_rat": 6.072164535522461, "gsm8k": 6.927366083318537, "math_qa": 5.68308703104655 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.022744503411675512, "math_qa": 0.03149078726968174 } }, { "flos": 6.14440681024258e+17, "train_loss": 5.59379150390625, "eval_loss": 6.086018381892024, "eval_accuracy": 0.03773584905660377, "eval_loss_by_set": { "aqua_rat": 6.1033525466918945, "gsm8k": 6.937072060324929, "math_qa": 5.694507598876953 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.025018953752843062, "math_qa": 0.04288107202680067 } }, { "flos": 6.199182267630223e+17, "train_loss": 5.57670654296875, "eval_loss": 6.110799222379117, "eval_accuracy": 0.030715225976305396, "eval_loss_by_set": { "aqua_rat": 6.0757904052734375, "gsm8k": 6.931311173872515, "math_qa": 5.737648646036784 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.01819560272934041, "math_qa": 0.036515912897822446 } }, { "flos": 6.254749899523359e+17, "train_loss": 5.583927001953125, "eval_loss": 6.067854340012009, "eval_accuracy": 0.03532250987275121, "eval_loss_by_set": { "aqua_rat": 6.066035270690918, "gsm8k": 6.896120938387784, "math_qa": 5.68838373819987 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.02047005307050796, "math_qa": 0.040871021775544386 } }, { "flos": 6.310036844566282e+17, "train_loss": 5.586993408203125, "eval_loss": 6.060529837737212, "eval_accuracy": 0.03334795963141729, "eval_loss_by_set": { "aqua_rat": 6.0645270347595215, "gsm8k": 6.894719904119318, "math_qa": 5.677859624226888 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.022744503411675512, "math_qa": 0.0371859296482412 } }, { "flos": 6.365067637759672e+17, "train_loss": 5.58195068359375, "eval_loss": 6.089048024770376, "eval_accuracy": 0.02874067573497148, "eval_loss_by_set": { "aqua_rat": 6.105815887451172, "gsm8k": 6.9285888671875, "math_qa": 5.702861150105794 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.01819560272934041, "math_qa": 0.033165829145728645 } }, { "flos": 6.42025340411052e+17, "train_loss": 5.581143188476562, "eval_loss": 6.089085707793364, "eval_accuracy": 0.02917946467749013, "eval_loss_by_set": { "aqua_rat": 6.0924787521362305, "gsm8k": 6.920297102494673, "math_qa": 5.707831064860026 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.016679302501895376, "math_qa": 0.03350083752093802 } }, { "flos": 6.475409905627955e+17, "train_loss": 5.59107666015625, "eval_loss": 6.100875184342668, "eval_accuracy": 0.030715225976305396, "eval_loss_by_set": { "aqua_rat": 6.088519096374512, "gsm8k": 6.937344637784091, "math_qa": 5.718523025512695 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.019711902956785442, "math_qa": 0.034170854271356785 } }, { "flos": 6.530906230326559e+17, "train_loss": 5.584273681640625, "eval_loss": 6.090016854775919, "eval_accuracy": 0.030057042562527423, "eval_loss_by_set": { "aqua_rat": 6.081144332885742, "gsm8k": 6.933507745916193, "math_qa": 5.704156239827474 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.02122820318423048, "math_qa": 0.03283082077051926 } }, { "flos": 6.586373295560458e+17, "train_loss": 5.576837768554688, "eval_loss": 6.1095191336966845, "eval_accuracy": 0.035103115401491886, "eval_loss_by_set": { "aqua_rat": 6.101932525634766, "gsm8k": 6.950648914683949, "math_qa": 5.724633534749349 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.01819560272934041, "math_qa": 0.040871021775544386 } }, { "flos": 6.641865293079511e+17, "train_loss": 5.578623046875, "eval_loss": 6.099413124290672, "eval_accuracy": 0.03839403247038175, "eval_loss_by_set": { "aqua_rat": 6.099740028381348, "gsm8k": 6.9277732155539775, "math_qa": 5.719720840454102 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.028051554207733132, "math_qa": 0.04221105527638191 } }, { "flos": 6.696666509533512e+17, "train_loss": 5.564813842773438, "eval_loss": 6.105820578497809, "eval_accuracy": 0.03203159280386134, "eval_loss_by_set": { "aqua_rat": 6.097821235656738, "gsm8k": 6.91979356245561, "math_qa": 5.733416239420573 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.024260803639120546, "math_qa": 0.034170854271356785 } }, { "flos": 6.751842998755e+17, "train_loss": 5.57214111328125, "eval_loss": 6.091055844281171, "eval_accuracy": 0.028960070206230804, "eval_loss_by_set": { "aqua_rat": 6.083775520324707, "gsm8k": 6.922025507146662, "math_qa": 5.710801442464192 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.019711902956785442, "math_qa": 0.032160804020100506 } }, { "flos": 6.807348396572017e+17, "train_loss": 5.5695654296875, "eval_loss": 6.088710733362146, "eval_accuracy": 0.03532250987275121, "eval_loss_by_set": { "aqua_rat": 6.084420204162598, "gsm8k": 6.92551005970348, "math_qa": 5.705535252888997 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.024260803639120546, "math_qa": 0.03919597989949749 } }, { "flos": 6.862949829857772e+17, "train_loss": 5.57455078125, "eval_loss": 6.101168039682749, "eval_accuracy": 0.03378674857393594, "eval_loss_by_set": { "aqua_rat": 6.0842437744140625, "gsm8k": 6.921558033336293, "math_qa": 5.726566314697266 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.02122820318423048, "math_qa": 0.03785594639865997 } }, { "flos": 6.918209577020293e+17, "train_loss": 5.570874633789063, "eval_loss": 6.101469813166438, "eval_accuracy": 0.035761298815269855, "eval_loss_by_set": { "aqua_rat": 6.108182907104492, "gsm8k": 6.940854852849787, "math_qa": 5.716192245483398 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.024260803639120546, "math_qa": 0.03785594639865997 } }, { "flos": 6.973449127099105e+17, "train_loss": 5.561753540039063, "eval_loss": 6.106429332011455, "eval_accuracy": 0.03554190434401053, "eval_loss_by_set": { "aqua_rat": 6.110788345336914, "gsm8k": 6.956312699751421, "math_qa": 5.716536204020183 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.026535253980288095, "math_qa": 0.03886097152428811 } }, { "flos": 7.02851021054935e+17, "train_loss": 5.56560546875, "eval_loss": 6.122964085759343, "eval_accuracy": 0.03466432645897324, "eval_loss_by_set": { "aqua_rat": 6.123865127563477, "gsm8k": 6.981596513227983, "math_qa": 5.729349136352539 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.025018953752843062, "math_qa": 0.038525963149078725 } }, { "flos": 7.083736983100457e+17, "train_loss": 5.557626953125, "eval_loss": 6.110916395445128, "eval_accuracy": 0.03356735410267661, "eval_loss_by_set": { "aqua_rat": 6.099534034729004, "gsm8k": 6.950721740722656, "math_qa": 5.7269541422526045 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.024260803639120546, "math_qa": 0.0371859296482412 } }, { "flos": 7.139419816753889e+17, "train_loss": 5.57423095703125, "eval_loss": 6.104634001448348, "eval_accuracy": 0.035761298815269855, "eval_loss_by_set": { "aqua_rat": 6.094653129577637, "gsm8k": 6.937223261052912, "math_qa": 5.723862330118815 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.024260803639120546, "math_qa": 0.03819095477386935 } }, { "flos": 7.194590948003676e+17, "train_loss": 5.5656494140625, "eval_loss": 6.1104304597184464, "eval_accuracy": 0.035103115401491886, "eval_loss_by_set": { "aqua_rat": 6.115828037261963, "gsm8k": 6.970483259721235, "math_qa": 5.715789794921875 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.02047005307050796, "math_qa": 0.03919597989949749 } }, { "flos": 7.249702728174141e+17, "train_loss": 5.560442504882812, "eval_loss": 6.1026607461877775, "eval_accuracy": 0.03137340939008337, "eval_loss_by_set": { "aqua_rat": 6.108246326446533, "gsm8k": 6.957254583185369, "math_qa": 5.710506439208984 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.022744503411675512, "math_qa": 0.033165829145728645 } }, { "flos": 7.30522275572351e+17, "train_loss": 5.57130615234375, "eval_loss": 6.0991912532497095, "eval_accuracy": 0.03356735410267661, "eval_loss_by_set": { "aqua_rat": 6.099274635314941, "gsm8k": 6.957852450284091, "math_qa": 5.705631256103516 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.024260803639120546, "math_qa": 0.036180904522613064 } }, { "flos": 7.361188536453693e+17, "train_loss": 5.5719873046875, "eval_loss": 6.099880862880397, "eval_accuracy": 0.030715225976305396, "eval_loss_by_set": { "aqua_rat": 6.0894036293029785, "gsm8k": 6.940013538707387, "math_qa": 5.7156931559244795 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.01819560272934041, "math_qa": 0.03350083752093802 } }, { "flos": 7.416398827067802e+17, "train_loss": 5.5550341796875, "eval_loss": 6.128260174313107, "eval_accuracy": 0.03488372093023256, "eval_loss_by_set": { "aqua_rat": 6.1440229415893555, "gsm8k": 6.984827215021307, "math_qa": 5.734353383382161 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.021986353297952996, "math_qa": 0.03886097152428811 } }, { "flos": 7.47204043977261e+17, "train_loss": 5.5605419921875, "eval_loss": 6.108417639861235, "eval_accuracy": 0.03247038174637999, "eval_loss_by_set": { "aqua_rat": 6.122166156768799, "gsm8k": 6.963423295454546, "math_qa": 5.715394337972005 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.019711902956785442, "math_qa": 0.03685092127303183 } }, { "flos": 7.527249280835256e+17, "train_loss": 5.561251220703125, "eval_loss": 6.116814097842655, "eval_accuracy": 0.032250987275120664, "eval_loss_by_set": { "aqua_rat": 6.130131244659424, "gsm8k": 6.974331942471591, "math_qa": 5.722675323486328 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.017437452615617893, "math_qa": 0.03584589614740368 } }, { "flos": 7.582708303742894e+17, "train_loss": 5.554193725585938, "eval_loss": 6.137031348975929, "eval_accuracy": 0.03422553751645459, "eval_loss_by_set": { "aqua_rat": 6.136863708496094, "gsm8k": 6.980138605291193, "math_qa": 5.750621159871419 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.02047005307050796, "math_qa": 0.03819095477386935 } }, { "flos": 7.638017099431936e+17, "train_loss": 5.5647802734375, "eval_loss": 6.126860077316697, "eval_accuracy": 0.031592803861342694, "eval_loss_by_set": { "aqua_rat": 6.109484672546387, "gsm8k": 6.961381392045454, "math_qa": 5.745819091796875 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.01592115238817286, "math_qa": 0.03484087102177554 } }, { "flos": 7.693719711409766e+17, "train_loss": 5.5601513671875, "eval_loss": 6.119861808983055, "eval_accuracy": 0.035103115401491886, "eval_loss_by_set": { "aqua_rat": 6.113809585571289, "gsm8k": 6.977256774902344, "math_qa": 5.727393468221028 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.024260803639120546, "math_qa": 0.03886097152428811 } }, { "flos": 7.749811613854597e+17, "train_loss": 5.570889892578125, "eval_loss": 6.125994604987067, "eval_accuracy": 0.0370776656428258, "eval_loss_by_set": { "aqua_rat": 6.133508682250977, "gsm8k": 6.971676219593395, "math_qa": 5.737764358520508 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.02047005307050796, "math_qa": 0.04321608040201005 } }, { "flos": 7.805376357382226e+17, "train_loss": 5.562796020507813, "eval_loss": 6.120027335914406, "eval_accuracy": 0.03444493198771391, "eval_loss_by_set": { "aqua_rat": 6.121945381164551, "gsm8k": 6.949600913307884, "math_qa": 5.739646275838216 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.016679302501895376, "math_qa": 0.04053601340033501 } }, { "flos": 7.86056232774402e+17, "train_loss": 5.5556689453125, "eval_loss": 6.133612503876558, "eval_accuracy": 0.041465555068012284, "eval_loss_by_set": { "aqua_rat": 6.1460371017456055, "gsm8k": 6.995185852050781, "math_qa": 5.73768933614095 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.025018953752843062, "math_qa": 0.04723618090452261 } }, { "flos": 7.915898122671227e+17, "train_loss": 5.557935791015625, "eval_loss": 6.10964906537855, "eval_accuracy": 0.036858271171566474, "eval_loss_by_set": { "aqua_rat": 6.126377582550049, "gsm8k": 6.9662558815696025, "math_qa": 5.715643564860026 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.025018953752843062, "math_qa": 0.04020100502512563 } }, { "flos": 7.971243597380977e+17, "train_loss": 5.56429443359375, "eval_loss": 6.123503968522355, "eval_accuracy": 0.0370776656428258, "eval_loss_by_set": { "aqua_rat": 6.122668266296387, "gsm8k": 6.951338334517046, "math_qa": 5.744149525960286 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.024260803639120546, "math_qa": 0.04288107202680067 } }, { "flos": 8.026313335190323e+17, "train_loss": 5.5452587890625, "eval_loss": 6.105157542873073, "eval_accuracy": 0.03554190434401053, "eval_loss_by_set": { "aqua_rat": 6.141421318054199, "gsm8k": 6.97588417746804, "math_qa": 5.703052520751953 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.01819560272934041, "math_qa": 0.04020100502512563 } }, { "flos": 8.082017804741509e+17, "train_loss": 5.5584716796875, "eval_loss": 6.1164437886830925, "eval_accuracy": 0.030276437033786747, "eval_loss_by_set": { "aqua_rat": 6.125794410705566, "gsm8k": 6.974478288130327, "math_qa": 5.72239875793457 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.018953752843062926, "math_qa": 0.033165829145728645 } }, { "flos": 8.137700015624684e+17, "train_loss": 5.55750244140625, "eval_loss": 6.145255810505635, "eval_accuracy": 0.04322071083808688, "eval_loss_by_set": { "aqua_rat": 6.143104076385498, "gsm8k": 7.007661299272017, "math_qa": 5.750165939331055 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.026535253980288095, "math_qa": 0.048911222780569516 } }, { "flos": 8.19262034762793e+17, "train_loss": 5.547952880859375, "eval_loss": 6.1133258922680005, "eval_accuracy": 0.028960070206230804, "eval_loss_by_set": { "aqua_rat": 6.12061882019043, "gsm8k": 6.966692144220525, "math_qa": 5.721591949462891 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.017437452615617893, "math_qa": 0.032160804020100506 } }, { "flos": 8.248129245843292e+17, "train_loss": 5.55081787109375, "eval_loss": 6.114303305342391, "eval_accuracy": 0.03378674857393594, "eval_loss_by_set": { "aqua_rat": 6.10741662979126, "gsm8k": 6.964079423384233, "math_qa": 5.725396474202474 }, "eval_accuracy_by_set": { "aqua_rat": 0.08267716535433071, "gsm8k": 0.018953752843062926, "math_qa": 0.036180904522613064 } }, { "flos": 8.303559009286226e+17, "train_loss": 5.549072265625, "eval_loss": 6.102130683692726, "eval_accuracy": 0.02830188679245283, "eval_loss_by_set": { "aqua_rat": 6.102827072143555, "gsm8k": 6.933258056640625, "math_qa": 5.721139272054036 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.022744503411675512, "math_qa": 0.0288107202680067 } }, { "flos": 8.358979704979456e+17, "train_loss": 5.5396575927734375, "eval_loss": 6.1477881766654345, "eval_accuracy": 0.03532250987275121, "eval_loss_by_set": { "aqua_rat": 6.143104553222656, "gsm8k": 7.000497297807173, "math_qa": 5.75735346476237 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.016679302501895376, "math_qa": 0.04154103852596315 } }, { "flos": 8.41402121411625e+17, "train_loss": 5.554804077148438, "eval_loss": 6.142665089787664, "eval_accuracy": 0.03422553751645459, "eval_loss_by_set": { "aqua_rat": 6.160460472106934, "gsm8k": 6.997662630948153, "math_qa": 5.749308268229167 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.022744503411675512, "math_qa": 0.0371859296482412 } }, { "flos": 8.46938791670186e+17, "train_loss": 5.55167236328125, "eval_loss": 6.122999345934069, "eval_accuracy": 0.03751645458534445, "eval_loss_by_set": { "aqua_rat": 6.121801376342773, "gsm8k": 6.975345958362926, "math_qa": 5.73244031270345 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.02577710386656558, "math_qa": 0.04120603015075377 } }, { "flos": 8.52472515044311e+17, "train_loss": 5.540872192382812, "eval_loss": 6.118878467662914, "eval_accuracy": 0.03400614304519526, "eval_loss_by_set": { "aqua_rat": 6.131136417388916, "gsm8k": 6.995454268022017, "math_qa": 5.716093063354492 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.024260803639120546, "math_qa": 0.036180904522613064 } }, { "flos": 8.580127501257277e+17, "train_loss": 5.5460052490234375, "eval_loss": 6.132158485618797, "eval_accuracy": 0.03268977621763931, "eval_loss_by_set": { "aqua_rat": 6.1442766189575195, "gsm8k": 6.976762945001775, "math_qa": 5.744038263956706 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.02350265352539803, "math_qa": 0.035510887772194306 } }, { "flos": 8.635406618722304e+17, "train_loss": 5.543856811523438, "eval_loss": 6.161842758591111, "eval_accuracy": 0.03444493198771391, "eval_loss_by_set": { "aqua_rat": 6.149547576904297, "gsm8k": 7.017836137251421, "math_qa": 5.77053705851237 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.016679302501895376, "math_qa": 0.03919597989949749 } }, { "flos": 8.691289146880164e+17, "train_loss": 5.548448486328125, "eval_loss": 6.1426919730933935, "eval_accuracy": 0.03905221588415972, "eval_loss_by_set": { "aqua_rat": 6.143280506134033, "gsm8k": 7.009250987659801, "math_qa": 5.74547004699707 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.021986353297952996, "math_qa": 0.04623115577889447 } }, { "flos": 8.746338279583908e+17, "train_loss": 5.54406982421875, "eval_loss": 6.1391216484276026, "eval_accuracy": 0.03663887670030715, "eval_loss_by_set": { "aqua_rat": 6.149815559387207, "gsm8k": 6.990135886452415, "math_qa": 5.74818229675293 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.01819560272934041, "math_qa": 0.04388609715242881 } }, { "flos": 8.80202770601214e+17, "train_loss": 5.543187255859375, "eval_loss": 6.127598736737226, "eval_accuracy": 0.03422553751645459, "eval_loss_by_set": { "aqua_rat": 6.116878509521484, "gsm8k": 6.9639739990234375, "math_qa": 5.745153427124023 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.02047005307050796, "math_qa": 0.03819095477386935 } }, { "flos": 8.857931247297495e+17, "train_loss": 5.53760498046875, "eval_loss": 6.123637173626874, "eval_accuracy": 0.03751645458534445, "eval_loss_by_set": { "aqua_rat": 6.123293876647949, "gsm8k": 6.972265070134943, "math_qa": 5.734711329142253 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.01819560272934041, "math_qa": 0.044221105527638194 } }, { "flos": 8.913323708949463e+17, "train_loss": 5.542987670898437, "eval_loss": 6.121734748015532, "eval_accuracy": 0.0434401053093462, "eval_loss_by_set": { "aqua_rat": 6.12942361831665, "gsm8k": 6.956504821777344, "math_qa": 5.738491058349609 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.024260803639120546, "math_qa": 0.05058626465661641 } }, { "flos": 8.968882273092895e+17, "train_loss": 5.5492236328125, "eval_loss": 6.125256615716058, "eval_accuracy": 0.03444493198771391, "eval_loss_by_set": { "aqua_rat": 6.117612838745117, "gsm8k": 6.968408064408735, "math_qa": 5.739449183146159 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.02577710386656558, "math_qa": 0.035510887772194306 } }, { "flos": 9.024033620649574e+17, "train_loss": 5.534613037109375, "eval_loss": 6.144631463128167, "eval_accuracy": 0.040368582711715666, "eval_loss_by_set": { "aqua_rat": 6.158596038818359, "gsm8k": 7.008139176802202, "math_qa": 5.747693379720052 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.02122820318423048, "math_qa": 0.047571189279731994 } }, { "flos": 9.079151789583892e+17, "train_loss": 5.533917236328125, "eval_loss": 6.1474642882475985, "eval_accuracy": 0.040807371654234315, "eval_loss_by_set": { "aqua_rat": 6.127354621887207, "gsm8k": 6.994779413396662, "math_qa": 5.76078732808431 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.02350265352539803, "math_qa": 0.04723618090452261 } }, { "flos": 9.134701489988567e+17, "train_loss": 5.535982055664062, "eval_loss": 6.182687836724359, "eval_accuracy": 0.03773584905660377, "eval_loss_by_set": { "aqua_rat": 6.192209720611572, "gsm8k": 7.0624916770241475, "math_qa": 5.7786509195963545 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.022744503411675512, "math_qa": 0.04254606365159129 } }, { "flos": 9.19006860596478e+17, "train_loss": 5.534688720703125, "eval_loss": 6.12943272977262, "eval_accuracy": 0.03949100482667837, "eval_loss_by_set": { "aqua_rat": 6.137204170227051, "gsm8k": 6.980144153941762, "math_qa": 5.73887570699056 }, "eval_accuracy_by_set": { "aqua_rat": 0.08267716535433071, "gsm8k": 0.021986353297952996, "math_qa": 0.04355108877721943 } }, { "flos": 9.245392444776776e+17, "train_loss": 5.535819091796875, "eval_loss": 6.156501280294882, "eval_accuracy": 0.04168494953927161, "eval_loss_by_set": { "aqua_rat": 6.1571831703186035, "gsm8k": 7.023630315607244, "math_qa": 5.759010314941406 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.017437452615617893, "math_qa": 0.05058626465661641 } }, { "flos": 9.30084013970817e+17, "train_loss": 5.543106689453125, "eval_loss": 6.140723615079312, "eval_accuracy": 0.0388328214129004, "eval_loss_by_set": { "aqua_rat": 6.146519660949707, "gsm8k": 7.00992861661044, "math_qa": 5.741854985555013 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.021986353297952996, "math_qa": 0.04455611390284757 } }, { "flos": 9.356328019427328e+17, "train_loss": 5.542518310546875, "eval_loss": 6.1556840587306665, "eval_accuracy": 0.03356735410267661, "eval_loss_by_set": { "aqua_rat": 6.133077144622803, "gsm8k": 7.0046844482421875, "math_qa": 5.768442789713542 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.017437452615617893, "math_qa": 0.038525963149078725 } }, { "flos": 9.411825374918083e+17, "train_loss": 5.52811279296875, "eval_loss": 6.163449416289458, "eval_accuracy": 0.03839403247038175, "eval_loss_by_set": { "aqua_rat": 6.163527488708496, "gsm8k": 7.011856772682884, "math_qa": 5.774589538574219 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.022744503411675512, "math_qa": 0.04489112227805695 } }, { "flos": 9.467130251449467e+17, "train_loss": 5.534039306640625, "eval_loss": 6.1443037342380835, "eval_accuracy": 0.030715225976305396, "eval_loss_by_set": { "aqua_rat": 6.139608860015869, "gsm8k": 7.002812472256747, "math_qa": 5.751211802164714 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.026535253980288095, "math_qa": 0.03082077051926298 } }, { "flos": 9.522208648986624e+17, "train_loss": 5.53413818359375, "eval_loss": 6.175697172010267, "eval_accuracy": 0.03839403247038175, "eval_loss_by_set": { "aqua_rat": 6.178666114807129, "gsm8k": 7.036510120738637, "math_qa": 5.780910491943359 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.02122820318423048, "math_qa": 0.04455611390284757 } }, { "flos": 9.577272207411773e+17, "train_loss": 5.526158447265625, "eval_loss": 6.160489984460779, "eval_accuracy": 0.03971039929793769, "eval_loss_by_set": { "aqua_rat": 6.188379287719727, "gsm8k": 7.014161543412642, "math_qa": 5.766899744669597 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.024260803639120546, "math_qa": 0.044221105527638194 } }, { "flos": 9.632342363980431e+17, "train_loss": 5.526815185546875, "eval_loss": 6.157105832486539, "eval_accuracy": 0.040807371654234315, "eval_loss_by_set": { "aqua_rat": 6.164243698120117, "gsm8k": 7.019867636940696, "math_qa": 5.761078516642253 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.02047005307050796, "math_qa": 0.04824120603015075 } }, { "flos": 9.687838892689981e+17, "train_loss": 5.528507690429688, "eval_loss": 6.146571752187368, "eval_accuracy": 0.03839403247038175, "eval_loss_by_set": { "aqua_rat": 6.1529951095581055, "gsm8k": 7.004020690917969, "math_qa": 5.753039042154948 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.02047005307050796, "math_qa": 0.04455611390284757 } }, { "flos": 9.74304918330409e+17, "train_loss": 5.5308056640625, "eval_loss": 6.165613200213458, "eval_accuracy": 0.03949100482667837, "eval_loss_by_set": { "aqua_rat": 6.154344081878662, "gsm8k": 7.017009388316762, "math_qa": 5.776329040527344 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.029567854435178165, "math_qa": 0.04254606365159129 } }, { "flos": 9.798290386945311e+17, "train_loss": 5.5223583984375, "eval_loss": 6.154430286304371, "eval_accuracy": 0.03532250987275121, "eval_loss_by_set": { "aqua_rat": 6.150722503662109, "gsm8k": 7.01111533425071, "math_qa": 5.762091954549153 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.018953752843062926, "math_qa": 0.03986599664991625 } }, { "flos": 9.853280581960335e+17, "train_loss": 5.5197296142578125, "eval_loss": 6.169390961930558, "eval_accuracy": 0.03773584905660377, "eval_loss_by_set": { "aqua_rat": 6.1507158279418945, "gsm8k": 7.007780595259233, "math_qa": 5.786685307820638 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.021986353297952996, "math_qa": 0.04221105527638191 } }, { "flos": 9.90861761169064e+17, "train_loss": 5.520908813476563, "eval_loss": 6.146310110349913, "eval_accuracy": 0.03466432645897324, "eval_loss_by_set": { "aqua_rat": 6.1562724113464355, "gsm8k": 7.006351124156605, "math_qa": 5.751294453938802 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.017437452615617893, "math_qa": 0.039530988274706864 } }, { "flos": 9.964087559921336e+17, "train_loss": 5.535855712890625, "eval_loss": 6.1169563499656885, "eval_accuracy": 0.03532250987275121, "eval_loss_by_set": { "aqua_rat": 6.128696441650391, "gsm8k": 6.971356478604403, "math_qa": 5.724377950032552 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.02122820318423048, "math_qa": 0.039530988274706864 } }, { "flos": 1.0019607587470705e+18, "train_loss": 5.53420166015625, "eval_loss": 6.154957049601787, "eval_accuracy": 0.036200087757788504, "eval_loss_by_set": { "aqua_rat": 6.155519962310791, "gsm8k": 7.0021840875799, "math_qa": 5.766597747802734 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.02047005307050796, "math_qa": 0.04120603015075377 } }, { "flos": 1.0075166156982845e+18, "train_loss": 5.527490234375, "eval_loss": 6.149836488672205, "eval_accuracy": 0.0388328214129004, "eval_loss_by_set": { "aqua_rat": 6.150232791900635, "gsm8k": 7.017560091885653, "math_qa": 5.752096811930339 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.01819560272934041, "math_qa": 0.04522613065326633 } }, { "flos": 1.0130261449847603e+18, "train_loss": 5.510205078125, "eval_loss": 6.154368503673656, "eval_accuracy": 0.0379552435278631, "eval_loss_by_set": { "aqua_rat": 6.143582820892334, "gsm8k": 7.003197409889915, "math_qa": 5.766220728556315 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.017437452615617893, "math_qa": 0.04489112227805695 } }, { "flos": 1.0185931709984276e+18, "train_loss": 5.53492919921875, "eval_loss": 6.140034417848329, "eval_accuracy": 0.03927161035541905, "eval_loss_by_set": { "aqua_rat": 6.141021251678467, "gsm8k": 6.9918601296164775, "math_qa": 5.749532063802083 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.02047005307050796, "math_qa": 0.044221105527638194 } }, { "flos": 1.0241443292554199e+18, "train_loss": 5.528623657226563, "eval_loss": 6.150050034394136, "eval_accuracy": 0.035980693286529176, "eval_loss_by_set": { "aqua_rat": 6.151738166809082, "gsm8k": 6.99144883589311, "math_qa": 5.764268239339192 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.01819560272934041, "math_qa": 0.04020100502512563 } }, { "flos": 1.029676960097239e+18, "train_loss": 5.535353393554687, "eval_loss": 6.1690046980574325, "eval_accuracy": 0.03927161035541905, "eval_loss_by_set": { "aqua_rat": 6.189781188964844, "gsm8k": 7.027562921697443, "math_qa": 5.773767471313477 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.02047005307050796, "math_qa": 0.04589614740368509 } }, { "flos": 1.03521379517517e+18, "train_loss": 5.52117919921875, "eval_loss": 6.183968518231366, "eval_accuracy": 0.04365949978060553, "eval_loss_by_set": { "aqua_rat": 6.183317184448242, "gsm8k": 7.0417397238991475, "math_qa": 5.79087766011556 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.018953752843062926, "math_qa": 0.052931323283082074 } }, { "flos": 1.040763283763626e+18, "train_loss": 5.525828857421875, "eval_loss": 6.174533586244325, "eval_accuracy": 0.041465555068012284, "eval_loss_by_set": { "aqua_rat": 6.174496650695801, "gsm8k": 7.027751575816762, "math_qa": 5.783478418986003 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.018953752843062926, "math_qa": 0.04958123953098827 } }, { "flos": 1.0462641168150692e+18, "train_loss": 5.522401123046875, "eval_loss": 6.175664076933989, "eval_accuracy": 0.03861342694164107, "eval_loss_by_set": { "aqua_rat": 6.186903953552246, "gsm8k": 7.02947998046875, "math_qa": 5.783395131429036 }, "eval_accuracy_by_set": { "aqua_rat": 0.08267716535433071, "gsm8k": 0.02577710386656558, "math_qa": 0.04053601340033501 } }, { "flos": 1.0518372427560387e+18, "train_loss": 5.522569580078125, "eval_loss": 6.188791249249433, "eval_accuracy": 0.03488372093023256, "eval_loss_by_set": { "aqua_rat": 6.1658406257629395, "gsm8k": 7.020724209872159, "math_qa": 5.809401194254558 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.019711902956785442, "math_qa": 0.03919597989949749 } }, { "flos": 1.0573791061669315e+18, "train_loss": 5.511574096679688, "eval_loss": 6.1740519033895955, "eval_accuracy": 0.03905221588415972, "eval_loss_by_set": { "aqua_rat": 6.176125526428223, "gsm8k": 7.00652451948686, "math_qa": 5.79232915242513 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.02047005307050796, "math_qa": 0.04489112227805695 } }, { "flos": 1.062884390415106e+18, "train_loss": 5.520496215820312, "eval_loss": 6.1651308987591715, "eval_accuracy": 0.03817463799912242, "eval_loss_by_set": { "aqua_rat": 6.170045375823975, "gsm8k": 7.020244945179332, "math_qa": 5.772794087727864 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.019711902956785442, "math_qa": 0.04489112227805695 } }, { "flos": 1.0684410505252045e+18, "train_loss": 5.5226953125, "eval_loss": 6.169051402323955, "eval_accuracy": 0.036858271171566474, "eval_loss_by_set": { "aqua_rat": 6.183206558227539, "gsm8k": 7.020395452325994, "math_qa": 5.777672449747722 }, "eval_accuracy_by_set": { "aqua_rat": 0.08267716535433071, "gsm8k": 0.019711902956785442, "math_qa": 0.04053601340033501 } }, { "flos": 1.0739623265472348e+18, "train_loss": 5.50961669921875, "eval_loss": 6.16909326089395, "eval_accuracy": 0.04190434401053093, "eval_loss_by_set": { "aqua_rat": 6.174158096313477, "gsm8k": 7.027073946866122, "math_qa": 5.775430043538411 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.02350265352539803, "math_qa": 0.04690117252931323 } }, { "flos": 1.0795092800312443e+18, "train_loss": 5.521181640625, "eval_loss": 6.1563603169209244, "eval_accuracy": 0.04300131636682756, "eval_loss_by_set": { "aqua_rat": 6.1586456298828125, "gsm8k": 7.029593034224077, "math_qa": 5.755938212076823 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.024260803639120546, "math_qa": 0.04958123953098827 } }, { "flos": 1.0850355843862364e+18, "train_loss": 5.512996215820312, "eval_loss": 6.148220474655564, "eval_accuracy": 0.040368582711715666, "eval_loss_by_set": { "aqua_rat": 6.174795150756836, "gsm8k": 6.979809847745028, "math_qa": 5.76486078898112 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.026535253980288095, "math_qa": 0.044221105527638194 } }, { "flos": 1.0906113275729019e+18, "train_loss": 5.5262744140625, "eval_loss": 6.173938184171109, "eval_accuracy": 0.03839403247038175, "eval_loss_by_set": { "aqua_rat": 6.176417350769043, "gsm8k": 7.027333346280185, "math_qa": 5.782592137654622 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.02122820318423048, "math_qa": 0.04388609715242881 } }, { "flos": 1.0961495638839132e+18, "train_loss": 5.523927612304687, "eval_loss": 6.181840664631611, "eval_accuracy": 0.03949100482667837, "eval_loss_by_set": { "aqua_rat": 6.192875385284424, "gsm8k": 7.025699268687855, "math_qa": 5.794152577718099 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.02047005307050796, "math_qa": 0.04589614740368509 } }, { "flos": 1.1016555900876882e+18, "train_loss": 5.5155908203125, "eval_loss": 6.1975295608108105, "eval_accuracy": 0.04475647213690215, "eval_loss_by_set": { "aqua_rat": 6.2041778564453125, "gsm8k": 7.042798128995028, "math_qa": 5.809560775756836 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.02350265352539803, "math_qa": 0.051926298157453935 } }, { "flos": 1.1072039040025887e+18, "train_loss": 5.52527587890625, "eval_loss": 6.208898363886653, "eval_accuracy": 0.04409828872312418, "eval_loss_by_set": { "aqua_rat": 6.205485820770264, "gsm8k": 7.045313054865057, "math_qa": 5.825826009114583 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.018953752843062926, "math_qa": 0.052931323283082074 } }, { "flos": 1.1127294664019804e+18, "train_loss": 5.522979125976563, "eval_loss": 6.190847190650734, "eval_accuracy": 0.0388328214129004, "eval_loss_by_set": { "aqua_rat": 6.210272789001465, "gsm8k": 7.055804859508168, "math_qa": 5.792789459228516 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.02047005307050796, "math_qa": 0.04489112227805695 } }, { "flos": 1.118300675713794e+18, "train_loss": 5.5102386474609375, "eval_loss": 6.171316456150365, "eval_accuracy": 0.03839403247038175, "eval_loss_by_set": { "aqua_rat": 6.180390357971191, "gsm8k": 7.042354930530895, "math_qa": 5.771334330240886 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.021986353297952996, "math_qa": 0.04288107202680067 } }, { "flos": 1.1238644456053801e+18, "train_loss": 5.517053833007813, "eval_loss": 6.198420859671928, "eval_accuracy": 0.03971039929793769, "eval_loss_by_set": { "aqua_rat": 6.211755752563477, "gsm8k": 7.048722700639204, "math_qa": 5.80758794148763 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.022744503411675512, "math_qa": 0.046566164154103855 } }, { "flos": 1.1293897401061868e+18, "train_loss": 5.516029663085938, "eval_loss": 6.196278365882668, "eval_accuracy": 0.03905221588415972, "eval_loss_by_set": { "aqua_rat": 6.22025728225708, "gsm8k": 7.047877225008878, "math_qa": 5.803963979085286 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.01819560272934041, "math_qa": 0.046566164154103855 } }, { "flos": 1.1348865133397934e+18, "train_loss": 5.512437133789063, "eval_loss": 6.1505854838603256, "eval_accuracy": 0.036200087757788504, "eval_loss_by_set": { "aqua_rat": 6.132320404052734, "gsm8k": 7.0099709250710225, "math_qa": 5.758222579956055 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.016679302501895376, "math_qa": 0.04288107202680067 } }, { "flos": 1.1404621121081836e+18, "train_loss": 5.521485595703125, "eval_loss": 6.1733602059854045, "eval_accuracy": 0.040368582711715666, "eval_loss_by_set": { "aqua_rat": 6.180357933044434, "gsm8k": 7.02691026167436, "math_qa": 5.781566619873047 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.021986353297952996, "math_qa": 0.04623115577889447 } }, { "flos": 1.1460344960935526e+18, "train_loss": 5.521544189453125, "eval_loss": 6.158786722131677, "eval_accuracy": 0.03971039929793769, "eval_loss_by_set": { "aqua_rat": 6.172375679016113, "gsm8k": 7.017315257679332, "math_qa": 5.764162063598633 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.022744503411675512, "math_qa": 0.04522613065326633 } }, { "flos": 1.1516006770724045e+18, "train_loss": 5.510902099609375, "eval_loss": 6.168619619833456, "eval_accuracy": 0.04322071083808688, "eval_loss_by_set": { "aqua_rat": 6.176668167114258, "gsm8k": 7.031176480379972, "math_qa": 5.772610346476237 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.019711902956785442, "math_qa": 0.05058626465661641 } }, { "flos": 1.157122488891605e+18, "train_loss": 5.509990844726563, "eval_loss": 6.201973837775153, "eval_accuracy": 0.041246160596752963, "eval_loss_by_set": { "aqua_rat": 6.247994422912598, "gsm8k": 7.059397610751065, "math_qa": 5.805152893066406 }, "eval_accuracy_by_set": { "aqua_rat": 0.08267716535433071, "gsm8k": 0.022744503411675512, "math_qa": 0.04589614740368509 } }, { "flos": 1.1626993858138604e+18, "train_loss": 5.524996337890625, "eval_loss": 6.18833031525483, "eval_accuracy": 0.03751645458534445, "eval_loss_by_set": { "aqua_rat": 6.1934614181518555, "gsm8k": 7.038529829545454, "math_qa": 5.798227945963542 }, "eval_accuracy_by_set": { "aqua_rat": 0.09055118110236221, "gsm8k": 0.017437452615617893, "math_qa": 0.04187604690117253 } }, { "flos": 1.1682566643992494e+18, "train_loss": 5.510103759765625, "eval_loss": 6.182789854101233, "eval_accuracy": 0.04058797718297499, "eval_loss_by_set": { "aqua_rat": 6.183751583099365, "gsm8k": 7.036393599076704, "math_qa": 5.79147466023763 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.02047005307050796, "math_qa": 0.04623115577889447 } }, { "flos": 1.17377847621845e+18, "train_loss": 5.504468994140625, "eval_loss": 6.161178434217298, "eval_accuracy": 0.03773584905660377, "eval_loss_by_set": { "aqua_rat": 6.1859941482543945, "gsm8k": 7.025773481889204, "math_qa": 5.762837727864583 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.021986353297952996, "math_qa": 0.04321608040201005 } }, { "flos": 1.179331447488512e+18, "train_loss": 5.504840087890625, "eval_loss": 6.172454138059874, "eval_accuracy": 0.04168494953927161, "eval_loss_by_set": { "aqua_rat": 6.182783603668213, "gsm8k": 7.01603906804865, "math_qa": 5.784950256347656 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.02047005307050796, "math_qa": 0.047906197654941376 } }, { "flos": 1.1848597511507804e+18, "train_loss": 5.506670532226562, "eval_loss": 6.178775838903479, "eval_accuracy": 0.04409828872312418, "eval_loss_by_set": { "aqua_rat": 6.199000358581543, "gsm8k": 7.044111772017046, "math_qa": 5.780478159586589 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.029567854435178165, "math_qa": 0.047906197654941376 } }, { "flos": 1.1903943812998758e+18, "train_loss": 5.503187255859375, "eval_loss": 6.181763803636706, "eval_accuracy": 0.04300131636682756, "eval_loss_by_set": { "aqua_rat": 6.191335201263428, "gsm8k": 7.0534210205078125, "math_qa": 5.781456629435222 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.025018953752843062, "math_qa": 0.048911222780569516 } }, { "flos": 1.1959247454727045e+18, "train_loss": 5.505816650390625, "eval_loss": 6.155354113192172, "eval_accuracy": 0.03839403247038175, "eval_loss_by_set": { "aqua_rat": 6.1729021072387695, "gsm8k": 7.0212180397727275, "math_qa": 5.7570374806722 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.021986353297952996, "math_qa": 0.04288107202680067 } }, { "flos": 1.201480313587368e+18, "train_loss": 5.50855224609375, "eval_loss": 6.184516700538429, "eval_accuracy": 0.040368582711715666, "eval_loss_by_set": { "aqua_rat": 6.188179016113281, "gsm8k": 7.050580111416903, "math_qa": 5.787265777587891 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.022744503411675512, "math_qa": 0.04489112227805695 } }, { "flos": 1.2070166338060943e+18, "train_loss": 5.511194458007813, "eval_loss": 6.171275164629962, "eval_accuracy": 0.03773584905660377, "eval_loss_by_set": { "aqua_rat": 6.184696197509766, "gsm8k": 7.0272910378196025, "math_qa": 5.77781613667806 }, "eval_accuracy_by_set": { "aqua_rat": 0.08661417322834646, "gsm8k": 0.019711902956785442, "math_qa": 0.04154103852596315 } }, { "flos": 1.212535272181334e+18, "train_loss": 5.490875244140625, "eval_loss": 6.170407192127125, "eval_accuracy": 0.03488372093023256, "eval_loss_by_set": { "aqua_rat": 6.185774326324463, "gsm8k": 7.04625771262429, "math_qa": 5.7676951090494795 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.021986353297952996, "math_qa": 0.03685092127303183 } }, { "flos": 1.2181031018907566e+18, "train_loss": 5.5095281982421875, "eval_loss": 6.192127794832797, "eval_accuracy": 0.03905221588415972, "eval_loss_by_set": { "aqua_rat": 6.2131547927856445, "gsm8k": 7.061767578125, "math_qa": 5.7917906443278 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.019711902956785442, "math_qa": 0.04489112227805695 } }, { "flos": 1.2236127959966024e+18, "train_loss": 5.50493408203125, "eval_loss": 6.186337187483504, "eval_accuracy": 0.041465555068012284, "eval_loss_by_set": { "aqua_rat": 6.21219539642334, "gsm8k": 7.041805614124645, "math_qa": 5.792092641194661 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.02122820318423048, "math_qa": 0.048576214405360134 } }, { "flos": 1.2291500439282647e+18, "train_loss": 5.511303100585938, "eval_loss": 6.173540682406039, "eval_accuracy": 0.035761298815269855, "eval_loss_by_set": { "aqua_rat": 6.184654235839844, "gsm8k": 7.0311806418678975, "math_qa": 5.779529571533203 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.02047005307050796, "math_qa": 0.03919597989949749 } }, { "flos": 1.2346696508186296e+18, "train_loss": 5.4960870361328125, "eval_loss": 6.1357170568930135, "eval_accuracy": 0.03927161035541905, "eval_loss_by_set": { "aqua_rat": 6.141624927520752, "gsm8k": 6.997952547940341, "math_qa": 5.740033467610677 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.02122820318423048, "math_qa": 0.04623115577889447 } }, { "flos": 1.2402034563340042e+18, "train_loss": 5.507097778320312, "eval_loss": 6.171898017058501, "eval_accuracy": 0.036200087757788504, "eval_loss_by_set": { "aqua_rat": 6.198645114898682, "gsm8k": 7.01677773215554, "math_qa": 5.782432556152344 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.02122820318423048, "math_qa": 0.039530988274706864 } }, { "flos": 1.2457450722474066e+18, "train_loss": 5.51012939453125, "eval_loss": 6.199518616135056, "eval_accuracy": 0.035761298815269855, "eval_loss_by_set": { "aqua_rat": 6.221993446350098, "gsm8k": 7.06751181862571, "math_qa": 5.799815495808919 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.017437452615617893, "math_qa": 0.04254606365159129 } }, { "flos": 1.251236734469931e+18, "train_loss": 5.494148559570313, "eval_loss": 6.173799050820841, "eval_accuracy": 0.03466432645897324, "eval_loss_by_set": { "aqua_rat": 6.179931640625, "gsm8k": 7.043144226074219, "math_qa": 5.774838129679362 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.021986353297952996, "math_qa": 0.037520938023450585 } }, { "flos": 1.2568070370067743e+18, "train_loss": 5.513682250976562, "eval_loss": 6.192519291027172, "eval_accuracy": 0.03422553751645459, "eval_loss_by_set": { "aqua_rat": 6.203158855438232, "gsm8k": 7.034731084650213, "math_qa": 5.80561892191569 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.01819560272934041, "math_qa": 0.03819095477386935 } }, { "flos": 1.2623859745753661e+18, "train_loss": 5.504461059570312, "eval_loss": 6.185607884381269, "eval_accuracy": 0.03663887670030715, "eval_loss_by_set": { "aqua_rat": 6.198222637176514, "gsm8k": 7.047585920854048, "math_qa": 5.789483388264974 }, "eval_accuracy_by_set": { "aqua_rat": 0.09055118110236221, "gsm8k": 0.022744503411675512, "math_qa": 0.03819095477386935 } }, { "flos": 1.267897029112103e+18, "train_loss": 5.495082397460937, "eval_loss": 6.207465713088577, "eval_accuracy": 0.041026766125493636, "eval_loss_by_set": { "aqua_rat": 6.218212127685547, "gsm8k": 7.048731023615057, "math_qa": 5.820990244547526 }, "eval_accuracy_by_set": { "aqua_rat": 0.08267716535433071, "gsm8k": 0.021986353297952996, "math_qa": 0.04589614740368509 } }, { "flos": 1.2734118132910653e+18, "train_loss": 5.5087451171875, "eval_loss": 6.203277536340662, "eval_accuracy": 0.03729706011408512, "eval_loss_by_set": { "aqua_rat": 6.225478172302246, "gsm8k": 7.060502485795454, "math_qa": 5.80853271484375 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.017437452615617893, "math_qa": 0.04355108877721943 } }, { "flos": 1.278949596483027e+18, "train_loss": 5.492587280273438, "eval_loss": 6.175937601037927, "eval_accuracy": 0.03817463799912242, "eval_loss_by_set": { "aqua_rat": 6.1927995681762695, "gsm8k": 7.031231273304332, "math_qa": 5.782522837320964 }, "eval_accuracy_by_set": { "aqua_rat": 0.09448818897637795, "gsm8k": 0.02350265352539803, "math_qa": 0.03986599664991625 } }, { "flos": 1.2845162311177994e+18, "train_loss": 5.5118646240234375, "eval_loss": 6.1817427454768, "eval_accuracy": 0.03817463799912242, "eval_loss_by_set": { "aqua_rat": 6.217461585998535, "gsm8k": 7.062991749156605, "math_qa": 5.774860382080078 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.026535253980288095, "math_qa": 0.040871021775544386 } }, { "flos": 1.2900565488773366e+18, "train_loss": 5.49267822265625, "eval_loss": 6.195336135658058, "eval_accuracy": 0.036419482229047825, "eval_loss_by_set": { "aqua_rat": 6.217199802398682, "gsm8k": 7.052482604980469, "math_qa": 5.800655364990234 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.015163002274450341, "math_qa": 0.04288107202680067 } }, { "flos": 1.2955301996176343e+18, "train_loss": 5.4890283203125, "eval_loss": 6.199562072753906, "eval_accuracy": 0.041465555068012284, "eval_loss_by_set": { "aqua_rat": 6.229534149169922, "gsm8k": 7.055804165926847, "math_qa": 5.804620107014974 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.021986353297952996, "math_qa": 0.05025125628140704 } }, { "flos": 1.3010578021264916e+18, "train_loss": 5.493203125, "eval_loss": 6.188179995562579, "eval_accuracy": 0.036419482229047825, "eval_loss_by_set": { "aqua_rat": 6.1982831954956055, "gsm8k": 7.047230807217685, "math_qa": 5.793606440226237 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.013646702047005308, "math_qa": 0.04355108877721943 } }, { "flos": 1.3065803559012925e+18, "train_loss": 5.491732177734375, "eval_loss": 6.216937271324364, "eval_accuracy": 0.03751645458534445, "eval_loss_by_set": { "aqua_rat": 6.22902250289917, "gsm8k": 7.079395640980113, "math_qa": 5.820636749267578 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.018953752843062926, "math_qa": 0.044221105527638194 } }, { "flos": 1.312136253654696e+18, "train_loss": 5.50585693359375, "eval_loss": 6.2252494966661605, "eval_accuracy": 0.0370776656428258, "eval_loss_by_set": { "aqua_rat": 6.235734462738037, "gsm8k": 7.068665937943892, "math_qa": 5.837809880574544 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.01819560272934041, "math_qa": 0.04254606365159129 } }, { "flos": 1.317649533521363e+18, "train_loss": 5.4955224609375, "eval_loss": 6.1759113105567724, "eval_accuracy": 0.03971039929793769, "eval_loss_by_set": { "aqua_rat": 6.192919731140137, "gsm8k": 7.032406893643466, "math_qa": 5.781933466593425 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.027293404094010616, "math_qa": 0.04254606365159129 } }, { "flos": 1.323166729324462e+18, "train_loss": 5.492574462890625, "eval_loss": 6.181222271274876, "eval_accuracy": 0.0388328214129004, "eval_loss_by_set": { "aqua_rat": 6.198452472686768, "gsm8k": 7.04320595481179, "math_qa": 5.7847105662028 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.024260803639120546, "math_qa": 0.04221105527638191 } }, { "flos": 1.3286568254945362e+18, "train_loss": 5.495016479492188, "eval_loss": 6.209800591339937, "eval_accuracy": 0.03839403247038175, "eval_loss_by_set": { "aqua_rat": 6.2303786277771, "gsm8k": 7.086642178622159, "math_qa": 5.80620002746582 }, "eval_accuracy_by_set": { "aqua_rat": 0.09055118110236221, "gsm8k": 0.017437452615617893, "math_qa": 0.04321608040201005 } }, { "flos": 1.3342056752066068e+18, "train_loss": 5.492667236328125, "eval_loss": 6.186417785850731, "eval_accuracy": 0.0370776656428258, "eval_loss_by_set": { "aqua_rat": 6.196104526519775, "gsm8k": 7.0519797585227275, "math_qa": 5.7888946533203125 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.017437452615617893, "math_qa": 0.04288107202680067 } }, { "flos": 1.3397913725168517e+18, "train_loss": 5.500286865234375, "eval_loss": 6.185239843420081, "eval_accuracy": 0.04212373848179026, "eval_loss_by_set": { "aqua_rat": 6.197956085205078, "gsm8k": 7.035207575017756, "math_qa": 5.7946116129557295 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.01819560272934041, "math_qa": 0.049916247906197656 } }, { "flos": 1.345336863027626e+18, "train_loss": 5.505311279296875, "eval_loss": 6.229687768059808, "eval_accuracy": 0.03905221588415972, "eval_loss_by_set": { "aqua_rat": 6.257844924926758, "gsm8k": 7.1078102805397725, "math_qa": 5.824868520100911 }, "eval_accuracy_by_set": { "aqua_rat": 0.09055118110236221, "gsm8k": 0.02047005307050796, "math_qa": 0.04288107202680067 } }, { "flos": 1.3508823535384003e+18, "train_loss": 5.488939819335937, "eval_loss": 6.19474560505635, "eval_accuracy": 0.036858271171566474, "eval_loss_by_set": { "aqua_rat": 6.221919059753418, "gsm8k": 7.050140380859375, "math_qa": 5.800425211588542 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.019711902956785442, "math_qa": 0.04221105527638191 } }, { "flos": 1.3564516875601183e+18, "train_loss": 5.49986083984375, "eval_loss": 6.1937600213128166, "eval_accuracy": 0.03729706011408512, "eval_loss_by_set": { "aqua_rat": 6.208915710449219, "gsm8k": 7.049500205300071, "math_qa": 5.800282796223958 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.014404852160727824, "math_qa": 0.04455611390284757 } }, { "flos": 1.3619557761967718e+18, "train_loss": 5.4917626953125, "eval_loss": 6.205446501035948, "eval_accuracy": 0.04014918824045634, "eval_loss_by_set": { "aqua_rat": 6.207254409790039, "gsm8k": 7.067997325550426, "math_qa": 5.809960047403972 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.02577710386656558, "math_qa": 0.044221105527638194 } }, { "flos": 1.3675563931496612e+18, "train_loss": 5.51213623046875, "eval_loss": 6.18776019843849, "eval_accuracy": 0.035980693286529176, "eval_loss_by_set": { "aqua_rat": 6.19014310836792, "gsm8k": 7.047047701748935, "math_qa": 5.793721516927083 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.021986353297952996, "math_qa": 0.04053601340033501 } }, { "flos": 1.373083583341658e+18, "train_loss": 5.4955615234375, "eval_loss": 6.201159580333813, "eval_accuracy": 0.03488372093023256, "eval_loss_by_set": { "aqua_rat": 6.207665920257568, "gsm8k": 7.064006458629262, "math_qa": 5.805145899454753 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.02047005307050796, "math_qa": 0.038525963149078725 } }, { "flos": 1.3786535149007012e+18, "train_loss": 5.489969482421875, "eval_loss": 6.204822024783573, "eval_accuracy": 0.04387889425186485, "eval_loss_by_set": { "aqua_rat": 6.222877502441406, "gsm8k": 7.070112748579546, "math_qa": 5.806725819905599 }, "eval_accuracy_by_set": { "aqua_rat": 0.08267716535433071, "gsm8k": 0.02577710386656558, "math_qa": 0.048576214405360134 } }, { "flos": 1.384160097839612e+18, "train_loss": 5.50328125, "eval_loss": 6.204567471066037, "eval_accuracy": 0.03905221588415972, "eval_loss_by_set": { "aqua_rat": 6.246160507202148, "gsm8k": 7.085187045010653, "math_qa": 5.797484079996745 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.018953752843062926, "math_qa": 0.04455611390284757 } }, { "flos": 1.389693553315152e+18, "train_loss": 5.492826538085938, "eval_loss": 6.204728513150601, "eval_accuracy": 0.0379552435278631, "eval_loss_by_set": { "aqua_rat": 6.213899612426758, "gsm8k": 7.087005615234375, "math_qa": 5.799587249755859 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.02047005307050796, "math_qa": 0.04321608040201005 } }, { "flos": 1.3952622071214244e+18, "train_loss": 5.483955078125, "eval_loss": 6.2099066553889095, "eval_accuracy": 0.03861342694164107, "eval_loss_by_set": { "aqua_rat": 6.217970848083496, "gsm8k": 7.080974925648082, "math_qa": 5.809995015462239 }, "eval_accuracy_by_set": { "aqua_rat": 0.09055118110236221, "gsm8k": 0.021986353297952996, "math_qa": 0.04154103852596315 } }, { "flos": 1.4008115926306652e+18, "train_loss": 5.492952270507812, "eval_loss": 6.21011782981254, "eval_accuracy": 0.036419482229047825, "eval_loss_by_set": { "aqua_rat": 6.218200206756592, "gsm8k": 7.06875957142223, "math_qa": 5.815900166829427 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.024260803639120546, "math_qa": 0.03986599664991625 } }, { "flos": 1.4062920643159e+18, "train_loss": 5.4835986328125, "eval_loss": 6.245974618035394, "eval_accuracy": 0.04322071083808688, "eval_loss_by_set": { "aqua_rat": 6.267563819885254, "gsm8k": 7.111219926313921, "math_qa": 5.847604751586914 }, "eval_accuracy_by_set": { "aqua_rat": 0.09448818897637795, "gsm8k": 0.021986353297952996, "math_qa": 0.04824120603015075 } }, { "flos": 1.4117701458518344e+18, "train_loss": 5.479738159179687, "eval_loss": 6.224021602321315, "eval_accuracy": 0.03751645458534445, "eval_loss_by_set": { "aqua_rat": 6.248693466186523, "gsm8k": 7.110093550248579, "math_qa": 5.815849304199219 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.022744503411675512, "math_qa": 0.04154103852596315 } }, { "flos": 1.417326517662253e+18, "train_loss": 5.497283935546875, "eval_loss": 6.219934979000607, "eval_accuracy": 0.03971039929793769, "eval_loss_by_set": { "aqua_rat": 6.241145133972168, "gsm8k": 7.097521695223722, "math_qa": 5.815940221150716 }, "eval_accuracy_by_set": { "aqua_rat": 0.08267716535433071, "gsm8k": 0.019711902956785442, "math_qa": 0.04489112227805695 } }, { "flos": 1.4228457127726285e+18, "train_loss": 5.482846069335937, "eval_loss": 6.2176728635220915, "eval_accuracy": 0.0388328214129004, "eval_loss_by_set": { "aqua_rat": 6.216767311096191, "gsm8k": 7.0789031982421875, "math_qa": 5.823017756144206 }, "eval_accuracy_by_set": { "aqua_rat": 0.08267716535433071, "gsm8k": 0.025018953752843062, "math_qa": 0.04120603015075377 } }, { "flos": 1.4284013012883866e+18, "train_loss": 5.491474609375, "eval_loss": 6.217659666731551, "eval_accuracy": 0.04387889425186485, "eval_loss_by_set": { "aqua_rat": 6.225617408752441, "gsm8k": 7.099354137073863, "math_qa": 5.812886555989583 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.024260803639120546, "math_qa": 0.05025125628140704 } }, { "flos": 1.433971047626965e+18, "train_loss": 5.49433837890625, "eval_loss": 6.218475805746542, "eval_accuracy": 0.03861342694164107, "eval_loss_by_set": { "aqua_rat": 6.228447914123535, "gsm8k": 7.089232011274858, "math_qa": 5.818548202514648 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.026535253980288095, "math_qa": 0.04120603015075377 } }, { "flos": 1.4394797737545564e+18, "train_loss": 5.492431640625, "eval_loss": 6.251178406380318, "eval_accuracy": 0.051118911803422554, "eval_loss_by_set": { "aqua_rat": 6.244601726531982, "gsm8k": 7.12305381081321, "math_qa": 5.8521169026692705 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.022744503411675512, "math_qa": 0.06164154103852596 } }, { "flos": 1.4450569181743022e+18, "train_loss": 5.4923944091796875, "eval_loss": 6.2073268374881225, "eval_accuracy": 0.03554190434401053, "eval_loss_by_set": { "aqua_rat": 6.214605331420898, "gsm8k": 7.076568603515625, "math_qa": 5.80831782023112 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.02350265352539803, "math_qa": 0.037520938023450585 } }, { "flos": 1.450563830215082e+18, "train_loss": 5.486346435546875, "eval_loss": 6.206016257002547, "eval_accuracy": 0.041465555068012284, "eval_loss_by_set": { "aqua_rat": 6.224997043609619, "gsm8k": 7.061657992276278, "math_qa": 5.812265396118164 }, "eval_accuracy_by_set": { "aqua_rat": 0.09055118110236221, "gsm8k": 0.019711902956785442, "math_qa": 0.04690117252931323 } }, { "flos": 1.456071381669118e+18, "train_loss": 5.4827392578125, "eval_loss": 6.221411833891997, "eval_accuracy": 0.04168494953927161, "eval_loss_by_set": { "aqua_rat": 6.248348236083984, "gsm8k": 7.085949984463778, "math_qa": 5.822920481363933 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.021986353297952996, "math_qa": 0.047906197654941376 } }, { "flos": 1.4616350280803942e+18, "train_loss": 5.49506591796875, "eval_loss": 6.214880737098488, "eval_accuracy": 0.04058797718297499, "eval_loss_by_set": { "aqua_rat": 6.219998836517334, "gsm8k": 7.073672207919034, "math_qa": 5.820841471354167 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.019711902956785442, "math_qa": 0.046566164154103855 } }, { "flos": 1.4671606731579064e+18, "train_loss": 5.48431640625, "eval_loss": 6.211072870202966, "eval_accuracy": 0.041026766125493636, "eval_loss_by_set": { "aqua_rat": 6.224466323852539, "gsm8k": 7.087826815518466, "math_qa": 5.808111190795898 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.022744503411675512, "math_qa": 0.04690117252931323 } }, { "flos": 1.4727099759890268e+18, "train_loss": 5.47861572265625, "eval_loss": 6.218059178945181, "eval_accuracy": 0.04168494953927161, "eval_loss_by_set": { "aqua_rat": 6.218489646911621, "gsm8k": 7.0764243386008525, "math_qa": 5.824605941772461 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.01592115238817286, "math_qa": 0.050921273031825795 } }, { "flos": 1.4782131991897702e+18, "train_loss": 5.480216674804687, "eval_loss": 6.216074170293035, "eval_accuracy": 0.040368582711715666, "eval_loss_by_set": { "aqua_rat": 6.2149739265441895, "gsm8k": 7.077960621226918, "math_qa": 5.821134567260742 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.018953752843062926, "math_qa": 0.047571189279731994 } }, { "flos": 1.483771919810429e+18, "train_loss": 5.482207641601563, "eval_loss": 6.219704473340833, "eval_accuracy": 0.03751645458534445, "eval_loss_by_set": { "aqua_rat": 6.227168560028076, "gsm8k": 7.074572476473722, "math_qa": 5.827267964680989 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.02577710386656558, "math_qa": 0.040871021775544386 } }, { "flos": 1.4893290126384824e+18, "train_loss": 5.489996337890625, "eval_loss": 6.219933819126439, "eval_accuracy": 0.036858271171566474, "eval_loss_by_set": { "aqua_rat": 6.233921527862549, "gsm8k": 7.093410145152699, "math_qa": 5.8184248606363935 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.018953752843062926, "math_qa": 0.04221105527638191 } }, { "flos": 1.494866095213904e+18, "train_loss": 5.47658447265625, "eval_loss": 6.215785593599887, "eval_accuracy": 0.03949100482667837, "eval_loss_by_set": { "aqua_rat": 6.231298923492432, "gsm8k": 7.0839011452414775, "math_qa": 5.816606521606445 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.022744503411675512, "math_qa": 0.04388609715242881 } }, { "flos": 1.500367752362197e+18, "train_loss": 5.48000732421875, "eval_loss": 6.208154162845096, "eval_accuracy": 0.041465555068012284, "eval_loss_by_set": { "aqua_rat": 6.205813407897949, "gsm8k": 7.078737432306463, "math_qa": 5.809331893920898 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.021986353297952996, "math_qa": 0.047571189279731994 } }, { "flos": 1.505942423954522e+18, "train_loss": 5.487807006835937, "eval_loss": 6.227709589777766, "eval_accuracy": 0.04278192189556823, "eval_loss_by_set": { "aqua_rat": 6.237270355224609, "gsm8k": 7.096844759854403, "math_qa": 5.828559239705403 }, "eval_accuracy_by_set": { "aqua_rat": 0.08267716535433071, "gsm8k": 0.02047005307050796, "math_qa": 0.04924623115577889 } }, { "flos": 1.5115376007944602e+18, "train_loss": 5.492214965820312, "eval_loss": 6.2191176285614835, "eval_accuracy": 0.0379552435278631, "eval_loss_by_set": { "aqua_rat": 6.241420269012451, "gsm8k": 7.078036221590909, "math_qa": 5.823588053385417 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.016679302501895376, "math_qa": 0.04388609715242881 } }, { "flos": 1.5170711389481206e+18, "train_loss": 5.481697998046875, "eval_loss": 6.229166262858623, "eval_accuracy": 0.03949100482667837, "eval_loss_by_set": { "aqua_rat": 6.238187313079834, "gsm8k": 7.094200827858665, "math_qa": 5.831940333048503 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.022744503411675512, "math_qa": 0.044221105527638194 } }, { "flos": 1.5226583609717555e+18, "train_loss": 5.4949658203125, "eval_loss": 6.221255096229347, "eval_accuracy": 0.04014918824045634, "eval_loss_by_set": { "aqua_rat": 6.250289440155029, "gsm8k": 7.114846663041548, "math_qa": 5.809272766113281 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.02047005307050796, "math_qa": 0.045561139028475715 } }, { "flos": 1.5282130223114486e+18, "train_loss": 5.490176391601563, "eval_loss": 6.258983251210806, "eval_accuracy": 0.04234313295304958, "eval_loss_by_set": { "aqua_rat": 6.267058372497559, "gsm8k": 7.146643898703835, "math_qa": 5.8514658610026045 }, "eval_accuracy_by_set": { "aqua_rat": 0.08661417322834646, "gsm8k": 0.02577710386656558, "math_qa": 0.04589614740368509 } }, { "flos": 1.5337487653939446e+18, "train_loss": 5.4881103515625, "eval_loss": 6.2444441511824325, "eval_accuracy": 0.03927161035541905, "eval_loss_by_set": { "aqua_rat": 6.274890899658203, "gsm8k": 7.134728865189985, "math_qa": 5.833859761555989 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.018953752843062926, "math_qa": 0.04522613065326633 } }, { "flos": 1.539269979138949e+18, "train_loss": 5.48019775390625, "eval_loss": 6.208907359355205, "eval_accuracy": 0.035980693286529176, "eval_loss_by_set": { "aqua_rat": 6.223169326782227, "gsm8k": 7.088513461026278, "math_qa": 5.804566065470378 }, "eval_accuracy_by_set": { "aqua_rat": 0.08661417322834646, "gsm8k": 0.02122820318423048, "math_qa": 0.03819095477386935 } }, { "flos": 1.544823012149166e+18, "train_loss": 5.48472412109375, "eval_loss": 6.213199950553276, "eval_accuracy": 0.035761298815269855, "eval_loss_by_set": { "aqua_rat": 6.218136310577393, "gsm8k": 7.057943864302202, "math_qa": 5.825614293416341 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.022744503411675512, "math_qa": 0.03819095477386935 } }, { "flos": 1.5503151280276111e+18, "train_loss": 5.474888916015625, "eval_loss": 6.246385677440746, "eval_accuracy": 0.03751645458534445, "eval_loss_by_set": { "aqua_rat": 6.251299858093262, "gsm8k": 7.123878479003906, "math_qa": 5.843791961669922 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.017437452615617893, "math_qa": 0.04321608040201005 } }, { "flos": 1.5558535087568978e+18, "train_loss": 5.49625732421875, "eval_loss": 6.227069133036846, "eval_accuracy": 0.041465555068012284, "eval_loss_by_set": { "aqua_rat": 6.238494873046875, "gsm8k": 7.088200655850497, "math_qa": 5.831431706746419 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.022744503411675512, "math_qa": 0.04723618090452261 } }, { "flos": 1.561371302097322e+18, "train_loss": 5.470736694335938, "eval_loss": 6.226591213329418, "eval_accuracy": 0.03729706011408512, "eval_loss_by_set": { "aqua_rat": 6.244030952453613, "gsm8k": 7.097735318270597, "math_qa": 5.825863520304362 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.021986353297952996, "math_qa": 0.04154103852596315 } }, { "flos": 1.566929672678146e+18, "train_loss": 5.49093017578125, "eval_loss": 6.246090089952624, "eval_accuracy": 0.03905221588415972, "eval_loss_by_set": { "aqua_rat": 6.25594425201416, "gsm8k": 7.104124589399858, "math_qa": 5.85200309753418 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.019711902956785442, "math_qa": 0.045561139028475715 } }, { "flos": 1.5724353896442757e+18, "train_loss": 5.476226196289063, "eval_loss": 6.231816369134027, "eval_accuracy": 0.03663887670030715, "eval_loss_by_set": { "aqua_rat": 6.223669052124023, "gsm8k": 7.098595359108665, "math_qa": 5.835221608479817 }, "eval_accuracy_by_set": { "aqua_rat": 0.08267716535433071, "gsm8k": 0.015163002274450341, "math_qa": 0.04221105527638191 } }, { "flos": 1.5780098754792653e+18, "train_loss": 5.4727197265625, "eval_loss": 6.207981290044011, "eval_accuracy": 0.04014918824045634, "eval_loss_by_set": { "aqua_rat": 6.234155178070068, "gsm8k": 7.077429337935015, "math_qa": 5.807303110758464 }, "eval_accuracy_by_set": { "aqua_rat": 0.09055118110236221, "gsm8k": 0.018953752843062926, "math_qa": 0.04522613065326633 } }, { "flos": 1.583605835613864e+18, "train_loss": 5.48239990234375, "eval_loss": 6.246638194934742, "eval_accuracy": 0.045634050021939446, "eval_loss_by_set": { "aqua_rat": 6.266808986663818, "gsm8k": 7.10254599831321, "math_qa": 5.8526662190755205 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.029567854435178165, "math_qa": 0.05025125628140704 } }, { "flos": 1.5890756944349102e+18, "train_loss": 5.473804321289062, "eval_loss": 6.2567079131667676, "eval_accuracy": 0.03927161035541905, "eval_loss_by_set": { "aqua_rat": 6.266201496124268, "gsm8k": 7.123246626420454, "math_qa": 5.858753204345703 }, "eval_accuracy_by_set": { "aqua_rat": 0.08267716535433071, "gsm8k": 0.021986353297952996, "math_qa": 0.04321608040201005 } }, { "flos": 1.5946157238947676e+18, "train_loss": 5.4764251708984375, "eval_loss": 6.238567249194996, "eval_accuracy": 0.03949100482667837, "eval_loss_by_set": { "aqua_rat": 6.272193908691406, "gsm8k": 7.11313906582919, "math_qa": 5.834919611612956 }, "eval_accuracy_by_set": { "aqua_rat": 0.08661417322834646, "gsm8k": 0.01819560272934041, "math_qa": 0.04489112227805695 } }, { "flos": 1.6001445010771804e+18, "train_loss": 5.490181274414063, "eval_loss": 6.231666874241185, "eval_accuracy": 0.035980693286529176, "eval_loss_by_set": { "aqua_rat": 6.240056991577148, "gsm8k": 7.117690346457741, "math_qa": 5.824873606363933 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.022744503411675512, "math_qa": 0.038525963149078725 } }, { "flos": 1.6056737936556687e+18, "train_loss": 5.479192504882812, "eval_loss": 6.230936514364706, "eval_accuracy": 0.03532250987275121, "eval_loss_by_set": { "aqua_rat": 6.240835189819336, "gsm8k": 7.09662489457564, "math_qa": 5.833337783813477 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.022744503411675512, "math_qa": 0.03785594639865997 } }, { "flos": 1.6112416233650913e+18, "train_loss": 5.479896850585938, "eval_loss": 6.224423692033097, "eval_accuracy": 0.032250987275120664, "eval_loss_by_set": { "aqua_rat": 6.244974136352539, "gsm8k": 7.096477855335582, "math_qa": 5.823019663492839 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.01592115238817286, "math_qa": 0.036180904522613064 } }, { "flos": 1.616756820397785e+18, "train_loss": 5.482667846679687, "eval_loss": 6.259034362999168, "eval_accuracy": 0.03532250987275121, "eval_loss_by_set": { "aqua_rat": 6.269773960113525, "gsm8k": 7.130136663263494, "math_qa": 5.858884175618489 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.01592115238817286, "math_qa": 0.04020100502512563 } }, { "flos": 1.6223208377868616e+18, "train_loss": 5.484651489257812, "eval_loss": 6.2360331045614705, "eval_accuracy": 0.036419482229047825, "eval_loss_by_set": { "aqua_rat": 6.258786201477051, "gsm8k": 7.11492919921875, "math_qa": 5.831309636433919 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.018953752843062926, "math_qa": 0.040871021775544386 } }, { "flos": 1.6278472656221635e+18, "train_loss": 5.480840454101562, "eval_loss": 6.224604787053289, "eval_accuracy": 0.03532250987275121, "eval_loss_by_set": { "aqua_rat": 6.245200157165527, "gsm8k": 7.093590476296165, "math_qa": 5.82460339864095 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.025018953752843062, "math_qa": 0.036515912897822446 } }, { "flos": 1.633377197077037e+18, "train_loss": 5.478255615234375, "eval_loss": 6.253629272048538, "eval_accuracy": 0.03992979376919702, "eval_loss_by_set": { "aqua_rat": 6.278380393981934, "gsm8k": 7.123519203879616, "math_qa": 5.852867126464844 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.02122820318423048, "math_qa": 0.04489112227805695 } }, { "flos": 1.6389093339976172e+18, "train_loss": 5.46993408203125, "eval_loss": 6.23281986648972, "eval_accuracy": 0.035103115401491886, "eval_loss_by_set": { "aqua_rat": 6.247711658477783, "gsm8k": 7.091311368075284, "math_qa": 5.838103612263997 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.02350265352539803, "math_qa": 0.036515912897822446 } }, { "flos": 1.6444132787528663e+18, "train_loss": 5.485722045898438, "eval_loss": 6.268671757466084, "eval_accuracy": 0.036858271171566474, "eval_loss_by_set": { "aqua_rat": 6.283751487731934, "gsm8k": 7.156628695401278, "math_qa": 5.860434850056966 }, "eval_accuracy_by_set": { "aqua_rat": 0.08267716535433071, "gsm8k": 0.01592115238817286, "math_qa": 0.04221105527638191 } }, { "flos": 1.6499605210734264e+18, "train_loss": 5.480966186523437, "eval_loss": 6.243345930769637, "eval_accuracy": 0.03751645458534445, "eval_loss_by_set": { "aqua_rat": 6.255950927734375, "gsm8k": 7.101819125088778, "math_qa": 5.848828633626302 }, "eval_accuracy_by_set": { "aqua_rat": 0.08661417322834646, "gsm8k": 0.019711902956785442, "math_qa": 0.04120603015075377 } }, { "flos": 1.655500262233604e+18, "train_loss": 5.481188354492187, "eval_loss": 6.240593188517803, "eval_accuracy": 0.035761298815269855, "eval_loss_by_set": { "aqua_rat": 6.253612995147705, "gsm8k": 7.103743813254616, "math_qa": 5.8438975016276045 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.016679302501895376, "math_qa": 0.04154103852596315 } }, { "flos": 1.6610739862487695e+18, "train_loss": 5.471990966796875, "eval_loss": 6.245033109510267, "eval_accuracy": 0.036858271171566474, "eval_loss_by_set": { "aqua_rat": 6.264878273010254, "gsm8k": 7.1355507590553975, "math_qa": 5.835225423177083 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.019711902956785442, "math_qa": 0.04187604690117253 } }, { "flos": 1.6666064732091843e+18, "train_loss": 5.481376342773437, "eval_loss": 6.235367207913785, "eval_accuracy": 0.03663887670030715, "eval_loss_by_set": { "aqua_rat": 6.2598490715026855, "gsm8k": 7.108641190962358, "math_qa": 5.833076477050781 }, "eval_accuracy_by_set": { "aqua_rat": 0.08267716535433071, "gsm8k": 0.018953752843062926, "math_qa": 0.04053601340033501 } }, { "flos": 1.6721778060013076e+18, "train_loss": 5.487786865234375, "eval_loss": 6.202327882921374, "eval_accuracy": 0.0379552435278631, "eval_loss_by_set": { "aqua_rat": 6.229245185852051, "gsm8k": 7.069084167480469, "math_qa": 5.8028214772542315 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.021986353297952996, "math_qa": 0.04221105527638191 } }, { "flos": 1.6777592367984148e+18, "train_loss": 5.480923461914062, "eval_loss": 6.244417087451832, "eval_accuracy": 0.041465555068012284, "eval_loss_by_set": { "aqua_rat": 6.2522077560424805, "gsm8k": 7.1005096435546875, "math_qa": 5.851392110188802 }, "eval_accuracy_by_set": { "aqua_rat": 0.08661417322834646, "gsm8k": 0.02047005307050796, "math_qa": 0.04690117252931323 } }, { "flos": 1.6832634285142835e+18, "train_loss": 5.462181396484375, "eval_loss": 6.254767237482844, "eval_accuracy": 0.036200087757788504, "eval_loss_by_set": { "aqua_rat": 6.284948348999023, "gsm8k": 7.121903852982954, "math_qa": 5.854814529418945 }, "eval_accuracy_by_set": { "aqua_rat": 0.08661417322834646, "gsm8k": 0.018953752843062926, "math_qa": 0.039530988274706864 } }, { "flos": 1.6887802120005222e+18, "train_loss": 5.474765014648438, "eval_loss": 6.25524513141529, "eval_accuracy": 0.03905221588415972, "eval_loss_by_set": { "aqua_rat": 6.264599323272705, "gsm8k": 7.1389687278053975, "math_qa": 5.849425633748372 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.018953752843062926, "math_qa": 0.04489112227805695 } }, { "flos": 1.6942901332027638e+18, "train_loss": 5.47558837890625, "eval_loss": 6.242644026472762, "eval_accuracy": 0.04014918824045634, "eval_loss_by_set": { "aqua_rat": 6.255855560302734, "gsm8k": 7.116938504305753, "math_qa": 5.8408247629801435 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.025018953752843062, "math_qa": 0.04355108877721943 } }, { "flos": 1.6997933564035072e+18, "train_loss": 5.4631585693359375, "eval_loss": 6.254156860145363, "eval_accuracy": 0.0370776656428258, "eval_loss_by_set": { "aqua_rat": 6.2742438316345215, "gsm8k": 7.123682195490057, "math_qa": 5.853950500488281 }, "eval_accuracy_by_set": { "aqua_rat": 0.08267716535433071, "gsm8k": 0.018953752843062926, "math_qa": 0.04120603015075377 } }, { "flos": 1.7053319024890348e+18, "train_loss": 5.4741552734375, "eval_loss": 6.242973430736645, "eval_accuracy": 0.03949100482667837, "eval_loss_by_set": { "aqua_rat": 6.252790451049805, "gsm8k": 7.125810102982954, "math_qa": 5.837521870930989 }, "eval_accuracy_by_set": { "aqua_rat": 0.08661417322834646, "gsm8k": 0.02122820318423048, "math_qa": 0.04355108877721943 } }, { "flos": 1.7108681604307354e+18, "train_loss": 5.480070190429688, "eval_loss": 6.23962080156481, "eval_accuracy": 0.03817463799912242, "eval_loss_by_set": { "aqua_rat": 6.268617153167725, "gsm8k": 7.127112648703835, "math_qa": 5.830437342325847 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.02047005307050796, "math_qa": 0.04288107202680067 } }, { "flos": 1.7164204928244122e+18, "train_loss": 5.4660009765625, "eval_loss": 6.240409180924699, "eval_accuracy": 0.03466432645897324, "eval_loss_by_set": { "aqua_rat": 6.264483451843262, "gsm8k": 7.097980152476918, "math_qa": 5.845349629720052 }, "eval_accuracy_by_set": { "aqua_rat": 0.09448818897637795, "gsm8k": 0.02047005307050796, "math_qa": 0.03584589614740368 } }, { "flos": 1.7219789460833567e+18, "train_loss": 5.481473388671875, "eval_loss": 6.2458806424527555, "eval_accuracy": 0.03554190434401053, "eval_loss_by_set": { "aqua_rat": 6.257440567016602, "gsm8k": 7.108675870028409, "math_qa": 5.849469502766927 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.019711902956785442, "math_qa": 0.04120603015075377 } }, { "flos": 1.7274947202522808e+18, "train_loss": 5.462569580078125, "eval_loss": 6.216268900278452, "eval_accuracy": 0.040807371654234315, "eval_loss_by_set": { "aqua_rat": 6.239267349243164, "gsm8k": 7.074771534312855, "math_qa": 5.820871988932292 }, "eval_accuracy_by_set": { "aqua_rat": 0.08661417322834646, "gsm8k": 0.021986353297952996, "math_qa": 0.04522613065326633 } }, { "flos": 1.732999757002965e+18, "train_loss": 5.46286376953125, "eval_loss": 6.245678798572437, "eval_accuracy": 0.03905221588415972, "eval_loss_by_set": { "aqua_rat": 6.281271457672119, "gsm8k": 7.139910611239347, "math_qa": 5.83285649617513 }, "eval_accuracy_by_set": { "aqua_rat": 0.0984251968503937, "gsm8k": 0.017437452615617893, "math_qa": 0.04355108877721943 } }, { "flos": 1.7385380759920968e+18, "train_loss": 5.475717163085937, "eval_loss": 6.246723071948902, "eval_accuracy": 0.035103115401491886, "eval_loss_by_set": { "aqua_rat": 6.272975921630859, "gsm8k": 7.112557844682173, "math_qa": 5.847694396972656 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.022744503411675512, "math_qa": 0.038525963149078725 } }, { "flos": 1.7440622575595028e+18, "train_loss": 5.475922241210937, "eval_loss": 6.236102774336532, "eval_accuracy": 0.03334795963141729, "eval_loss_by_set": { "aqua_rat": 6.249264240264893, "gsm8k": 7.094669688831676, "math_qa": 5.8414961496988935 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.02047005307050796, "math_qa": 0.035510887772194306 } }, { "flos": 1.7495975673871729e+18, "train_loss": 5.475083618164063, "eval_loss": 6.24810097668622, "eval_accuracy": 0.03400614304519526, "eval_loss_by_set": { "aqua_rat": 6.2668280601501465, "gsm8k": 7.113827098499645, "math_qa": 5.849749247233073 }, "eval_accuracy_by_set": { "aqua_rat": 0.08661417322834646, "gsm8k": 0.013646702047005308, "math_qa": 0.038525963149078725 } }, { "flos": 1.7551540621410304e+18, "train_loss": 5.476600341796875, "eval_loss": 6.239499684926626, "eval_accuracy": 0.03400614304519526, "eval_loss_by_set": { "aqua_rat": 6.252246856689453, "gsm8k": 7.1253134987571025, "math_qa": 5.832439422607422 }, "eval_accuracy_by_set": { "aqua_rat": 0.0984251968503937, "gsm8k": 0.022744503411675512, "math_qa": 0.03350083752093802 } }, { "flos": 1.7606961317103534e+18, "train_loss": 5.478511962890625, "eval_loss": 6.219543250831398, "eval_accuracy": 0.035103115401491886, "eval_loss_by_set": { "aqua_rat": 6.2283477783203125, "gsm8k": 7.096698414195668, "math_qa": 5.816780090332031 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.022744503411675512, "math_qa": 0.03685092127303183 } }, { "flos": 1.766201746134139e+18, "train_loss": 5.46346435546875, "eval_loss": 6.236335264669882, "eval_accuracy": 0.041026766125493636, "eval_loss_by_set": { "aqua_rat": 6.239687442779541, "gsm8k": 7.1149139404296875, "math_qa": 5.8333740234375 }, "eval_accuracy_by_set": { "aqua_rat": 0.09055118110236221, "gsm8k": 0.019711902956785442, "math_qa": 0.04623115577889447 } }, { "flos": 1.7717554384218358e+18, "train_loss": 5.473785400390625, "eval_loss": 6.251266170192409, "eval_accuracy": 0.04278192189556823, "eval_loss_by_set": { "aqua_rat": 6.292078018188477, "gsm8k": 7.13141562721946, "math_qa": 5.844463348388672 }, "eval_accuracy_by_set": { "aqua_rat": 0.08267716535433071, "gsm8k": 0.02047005307050796, "math_qa": 0.04924623115577889 } }, { "flos": 1.7773477918576476e+18, "train_loss": 5.4740625, "eval_loss": 6.258139893815324, "eval_accuracy": 0.03839403247038175, "eval_loss_by_set": { "aqua_rat": 6.276358604431152, "gsm8k": 7.127342917702415, "math_qa": 5.858236948649089 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.022744503411675512, "math_qa": 0.04321608040201005 } }, { "flos": 1.7828401960357724e+18, "train_loss": 5.4672998046875, "eval_loss": 6.245008855252652, "eval_accuracy": 0.04278192189556823, "eval_loss_by_set": { "aqua_rat": 6.269991397857666, "gsm8k": 7.131357366388494, "math_qa": 5.836683909098308 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.02880970432145565, "math_qa": 0.046566164154103855 } }, { "flos": 1.7884106225897964e+18, "train_loss": 5.471463623046875, "eval_loss": 6.26275026476061, "eval_accuracy": 0.03400614304519526, "eval_loss_by_set": { "aqua_rat": 6.272493362426758, "gsm8k": 7.13652870871804, "math_qa": 5.861456553141276 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.022744503411675512, "math_qa": 0.036515912897822446 } }, { "flos": 1.793960503094018e+18, "train_loss": 5.4736669921875, "eval_loss": 6.239146619229703, "eval_accuracy": 0.04300131636682756, "eval_loss_by_set": { "aqua_rat": 6.26230525970459, "gsm8k": 7.121201255104759, "math_qa": 5.8329416910807295 }, "eval_accuracy_by_set": { "aqua_rat": 0.09055118110236221, "gsm8k": 0.02047005307050796, "math_qa": 0.048911222780569516 } }, { "flos": 1.799482830309294e+18, "train_loss": 5.476492919921875, "eval_loss": 6.262176642546782, "eval_accuracy": 0.03839403247038175, "eval_loss_by_set": { "aqua_rat": 6.29027795791626, "gsm8k": 7.1469338156960225, "math_qa": 5.854321161905925 }, "eval_accuracy_by_set": { "aqua_rat": 0.08267716535433071, "gsm8k": 0.018953752843062926, "math_qa": 0.04321608040201005 } }, { "flos": 1.8050108660729774e+18, "train_loss": 5.471226806640625, "eval_loss": 6.254862244064744, "eval_accuracy": 0.03663887670030715, "eval_loss_by_set": { "aqua_rat": 6.253045082092285, "gsm8k": 7.10712363503196, "math_qa": 5.864393870035808 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.01592115238817286, "math_qa": 0.04288107202680067 } }, { "flos": 1.8105306995228672e+18, "train_loss": 5.473397216796875, "eval_loss": 6.235773498947556, "eval_accuracy": 0.0379552435278631, "eval_loss_by_set": { "aqua_rat": 6.253876686096191, "gsm8k": 7.102991277521307, "math_qa": 5.836790084838867 }, "eval_accuracy_by_set": { "aqua_rat": 0.08267716535433071, "gsm8k": 0.024260803639120546, "math_qa": 0.04020100502512563 } }, { "flos": 1.815974901283029e+18, "train_loss": 5.452720947265625, "eval_loss": 6.234746056634027, "eval_accuracy": 0.03290917068889864, "eval_loss_by_set": { "aqua_rat": 6.230878829956055, "gsm8k": 7.082838578657671, "math_qa": 5.8463592529296875 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.017437452615617893, "math_qa": 0.036515912897822446 } }, { "flos": 1.8215369193648292e+18, "train_loss": 5.467059326171875, "eval_loss": 6.235266633935876, "eval_accuracy": 0.03861342694164107, "eval_loss_by_set": { "aqua_rat": 6.260460376739502, "gsm8k": 7.113426902077415, "math_qa": 5.830677032470703 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.017437452615617893, "math_qa": 0.04455611390284757 } }, { "flos": 1.827076001247527e+18, "train_loss": 5.468211669921875, "eval_loss": 6.236672762277964, "eval_accuracy": 0.036200087757788504, "eval_loss_by_set": { "aqua_rat": 6.2590155601501465, "gsm8k": 7.110959139737216, "math_qa": 5.834096272786458 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.022744503411675512, "math_qa": 0.03919597989949749 } }, { "flos": 1.8326062623411405e+18, "train_loss": 5.461381225585938, "eval_loss": 6.266267570289406, "eval_accuracy": 0.03992979376919702, "eval_loss_by_set": { "aqua_rat": 6.275143623352051, "gsm8k": 7.162151683460582, "math_qa": 5.8549143473307295 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.02122820318423048, "math_qa": 0.045561139028475715 } }, { "flos": 1.838104786847662e+18, "train_loss": 5.464769287109375, "eval_loss": 6.288619067217852, "eval_accuracy": 0.03773584905660377, "eval_loss_by_set": { "aqua_rat": 6.305906295776367, "gsm8k": 7.171635020862926, "math_qa": 5.882462819417317 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.022744503411675512, "math_qa": 0.04154103852596315 } }, { "flos": 1.8436201691008205e+18, "train_loss": 5.464757080078125, "eval_loss": 6.289921425484322, "eval_accuracy": 0.03751645458534445, "eval_loss_by_set": { "aqua_rat": 6.28675651550293, "gsm8k": 7.1583709716796875, "math_qa": 5.8921457926432295 }, "eval_accuracy_by_set": { "aqua_rat": 0.08661417322834646, "gsm8k": 0.01819560272934041, "math_qa": 0.04187604690117253 } }, { "flos": 1.8491836093536666e+18, "train_loss": 5.464457397460937, "eval_loss": 6.232622198156409, "eval_accuracy": 0.03839403247038175, "eval_loss_by_set": { "aqua_rat": 6.260030746459961, "gsm8k": 7.112658413973722, "math_qa": 5.826988220214844 }, "eval_accuracy_by_set": { "aqua_rat": 0.08267716535433071, "gsm8k": 0.026535253980288095, "math_qa": 0.03986599664991625 } }, { "flos": 1.854740537899221e+18, "train_loss": 5.470074462890625, "eval_loss": 6.247159133086333, "eval_accuracy": 0.041246160596752963, "eval_loss_by_set": { "aqua_rat": 6.290236473083496, "gsm8k": 7.13447362726385, "math_qa": 5.836883544921875 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.015163002274450341, "math_qa": 0.049916247906197656 } }, { "flos": 1.8602782384130621e+18, "train_loss": 5.466553955078125, "eval_loss": 6.242228843070365, "eval_accuracy": 0.04453707766564283, "eval_loss_by_set": { "aqua_rat": 6.244302749633789, "gsm8k": 7.098048817027699, "math_qa": 5.849805196126302 }, "eval_accuracy_by_set": { "aqua_rat": 0.09055118110236221, "gsm8k": 0.030326004548900682, "math_qa": 0.04690117252931323 } }, { "flos": 1.8657921990320456e+18, "train_loss": 5.47028076171875, "eval_loss": 6.260619885212666, "eval_accuracy": 0.03992979376919702, "eval_loss_by_set": { "aqua_rat": 6.28847074508667, "gsm8k": 7.151686234907671, "math_qa": 5.849893569946289 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.02350265352539803, "math_qa": 0.04455611390284757 } }, { "flos": 1.8713508375114547e+18, "train_loss": 5.475650634765625, "eval_loss": 6.245443447216137, "eval_accuracy": 0.03751645458534445, "eval_loss_by_set": { "aqua_rat": 6.256833076477051, "gsm8k": 7.126425309614702, "math_qa": 5.840710957845052 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.016679302501895376, "math_qa": 0.04455611390284757 } }, { "flos": 1.876861047013376e+18, "train_loss": 5.475193481445313, "eval_loss": 6.276517455642288, "eval_accuracy": 0.03971039929793769, "eval_loss_by_set": { "aqua_rat": 6.308413505554199, "gsm8k": 7.155804720791903, "math_qa": 5.870852788289388 }, "eval_accuracy_by_set": { "aqua_rat": 0.08267716535433071, "gsm8k": 0.01819560272934041, "math_qa": 0.045561139028475715 } }, { "flos": 1.8824056511502746e+18, "train_loss": 5.466649169921875, "eval_loss": 6.257043065251531, "eval_accuracy": 0.04058797718297499, "eval_loss_by_set": { "aqua_rat": 6.27912712097168, "gsm8k": 7.123319452459162, "math_qa": 5.8581593831380205 }, "eval_accuracy_by_set": { "aqua_rat": 0.08661417322834646, "gsm8k": 0.025018953752843062, "math_qa": 0.04355108877721943 } }, { "flos": 1.8879283493433508e+18, "train_loss": 5.464159545898437, "eval_loss": 6.246213242814347, "eval_accuracy": 0.04300131636682756, "eval_loss_by_set": { "aqua_rat": 6.25773811340332, "gsm8k": 7.122968500310725, "math_qa": 5.843406677246094 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.024260803639120546, "math_qa": 0.04924623115577889 } }, { "flos": 1.8934854421714043e+18, "train_loss": 5.460755004882812, "eval_loss": 6.256823153109164, "eval_accuracy": 0.040368582711715666, "eval_loss_by_set": { "aqua_rat": 6.2670440673828125, "gsm8k": 7.129286332563921, "math_qa": 5.85609245300293 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.01819560272934041, "math_qa": 0.047906197654941376 } }, { "flos": 1.8990314684793487e+18, "train_loss": 5.4713671875, "eval_loss": 6.262707194766483, "eval_accuracy": 0.041246160596752963, "eval_loss_by_set": { "aqua_rat": 6.275801181793213, "gsm8k": 7.133372913707387, "math_qa": 5.862560907999675 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.01592115238817286, "math_qa": 0.04924623115577889 } }, { "flos": 1.9045582678293217e+18, "train_loss": 5.476724853515625, "eval_loss": 6.227247624783902, "eval_accuracy": 0.03422553751645459, "eval_loss_by_set": { "aqua_rat": 6.253267765045166, "gsm8k": 7.109567815607244, "math_qa": 5.820682525634766 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.015163002274450341, "math_qa": 0.039530988274706864 } }, { "flos": 1.910070166864003e+18, "train_loss": 5.458046264648438, "eval_loss": 6.285518723565179, "eval_accuracy": 0.03971039929793769, "eval_loss_by_set": { "aqua_rat": 6.308574199676514, "gsm8k": 7.17839951948686, "math_qa": 5.87436040242513 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.025018953752843062, "math_qa": 0.04288107202680067 } }, { "flos": 1.9156227467551703e+18, "train_loss": 5.461805419921875, "eval_loss": 6.262588062801877, "eval_accuracy": 0.04058797718297499, "eval_loss_by_set": { "aqua_rat": 6.266326427459717, "gsm8k": 7.118864579634233, "math_qa": 5.8698164621988935 }, "eval_accuracy_by_set": { "aqua_rat": 0.08267716535433071, "gsm8k": 0.017437452615617893, "math_qa": 0.04723618090452261 } }, { "flos": 1.9211721730666004e+18, "train_loss": 5.473829956054687, "eval_loss": 6.284084938667916, "eval_accuracy": 0.03773584905660377, "eval_loss_by_set": { "aqua_rat": 6.293951034545898, "gsm8k": 7.161073858087713, "math_qa": 5.881309509277344 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.01592115238817286, "math_qa": 0.04388609715242881 } }, { "flos": 1.9267089877434368e+18, "train_loss": 5.47512939453125, "eval_loss": 6.265427821391338, "eval_accuracy": 0.03992979376919702, "eval_loss_by_set": { "aqua_rat": 6.28714656829834, "gsm8k": 7.139096346768466, "math_qa": 5.863186518351237 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.02350265352539803, "math_qa": 0.04589614740368509 } }, { "flos": 1.9322152614447022e+18, "train_loss": 5.458359375, "eval_loss": 6.249234070649019, "eval_accuracy": 0.03992979376919702, "eval_loss_by_set": { "aqua_rat": 6.289316177368164, "gsm8k": 7.141985112970525, "math_qa": 5.836716334025065 }, "eval_accuracy_by_set": { "aqua_rat": 0.08267716535433071, "gsm8k": 0.02880970432145565, "math_qa": 0.04120603015075377 } }, { "flos": 1.9377368467043779e+18, "train_loss": 5.465885009765625, "eval_loss": 6.273573875427246, "eval_accuracy": 0.03663887670030715, "eval_loss_by_set": { "aqua_rat": 6.2969183921813965, "gsm8k": 7.139905062588778, "math_qa": 5.874560038248698 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.015163002274450341, "math_qa": 0.04254606365159129 } }, { "flos": 1.9432740114210488e+18, "train_loss": 5.468822021484375, "eval_loss": 6.268535124289023, "eval_accuracy": 0.03861342694164107, "eval_loss_by_set": { "aqua_rat": 6.296131610870361, "gsm8k": 7.157537286931818, "math_qa": 5.858776092529297 }, "eval_accuracy_by_set": { "aqua_rat": 0.08267716535433071, "gsm8k": 0.02122820318423048, "math_qa": 0.04254606365159129 } }, { "flos": 1.948815256893522e+18, "train_loss": 5.464672241210938, "eval_loss": 6.249930768399625, "eval_accuracy": 0.03861342694164107, "eval_loss_by_set": { "aqua_rat": 6.26296329498291, "gsm8k": 7.112056385387074, "math_qa": 5.8537038167317705 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.015163002274450341, "math_qa": 0.046566164154103855 } }, { "flos": 1.9543453118287053e+18, "train_loss": 5.46412109375, "eval_loss": 6.256407351107211, "eval_accuracy": 0.036858271171566474, "eval_loss_by_set": { "aqua_rat": 6.26630973815918, "gsm8k": 7.126588301225142, "math_qa": 5.856749216715495 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.02047005307050796, "math_qa": 0.040871021775544386 } }, { "flos": 1.9599156143655485e+18, "train_loss": 5.4780615234375, "eval_loss": 6.27559130900615, "eval_accuracy": 0.041026766125493636, "eval_loss_by_set": { "aqua_rat": 6.29946231842041, "gsm8k": 7.151316556063565, "math_qa": 5.8722279866536455 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.025018953752843062, "math_qa": 0.045561139028475715 } }, { "flos": 1.965466710345515e+18, "train_loss": 5.472530517578125, "eval_loss": 6.222662796845308, "eval_accuracy": 0.041465555068012284, "eval_loss_by_set": { "aqua_rat": 6.239027976989746, "gsm8k": 7.086993130770597, "math_qa": 5.82514762878418 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.027293404094010616, "math_qa": 0.04455611390284757 } }, { "flos": 1.9710392387491594e+18, "train_loss": 5.4670172119140625, "eval_loss": 6.279170139415844, "eval_accuracy": 0.04278192189556823, "eval_loss_by_set": { "aqua_rat": 6.318261623382568, "gsm8k": 7.159298289905895, "math_qa": 5.872520446777344 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.02577710386656558, "math_qa": 0.047571189279731994 } }, { "flos": 1.9765618752020808e+18, "train_loss": 5.458239135742187, "eval_loss": 6.258900204220334, "eval_accuracy": 0.035761298815269855, "eval_loss_by_set": { "aqua_rat": 6.271137237548828, "gsm8k": 7.136580033735796, "math_qa": 5.855610529581706 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.022744503411675512, "math_qa": 0.03819095477386935 } }, { "flos": 1.9821184112949985e+18, "train_loss": 5.4658251953125, "eval_loss": 6.23645120053678, "eval_accuracy": 0.03839403247038175, "eval_loss_by_set": { "aqua_rat": 6.244845867156982, "gsm8k": 7.109033757990057, "math_qa": 5.835817972819011 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.021986353297952996, "math_qa": 0.04254606365159129 } }, { "flos": 1.98766993999292e+18, "train_loss": 5.459937744140625, "eval_loss": 6.2902074762292814, "eval_accuracy": 0.03971039929793769, "eval_loss_by_set": { "aqua_rat": 6.3234968185424805, "gsm8k": 7.177777377041903, "math_qa": 5.8806304931640625 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.016679302501895376, "math_qa": 0.04723618090452261 } }, { "flos": 1.9932231174214124e+18, "train_loss": 5.461969604492188, "eval_loss": 6.2830164625838, "eval_accuracy": 0.04300131636682756, "eval_loss_by_set": { "aqua_rat": 6.302424430847168, "gsm8k": 7.179049405184659, "math_qa": 5.870717366536458 }, "eval_accuracy_by_set": { "aqua_rat": 0.08267716535433071, "gsm8k": 0.017437452615617893, "math_qa": 0.050921273031825795 } }, { "flos": 1.9987218072841748e+18, "train_loss": 5.452428588867187, "eval_loss": 6.273197174072266, "eval_accuracy": 0.04278192189556823, "eval_loss_by_set": { "aqua_rat": 6.310647964477539, "gsm8k": 7.165414983575994, "math_qa": 5.861143112182617 }, "eval_accuracy_by_set": { "aqua_rat": 0.09055118110236221, "gsm8k": 0.02577710386656558, "math_qa": 0.04623115577889447 } }, { "flos": 2.0042858858765353e+18, "train_loss": 5.464974365234375, "eval_loss": 6.280193199982515, "eval_accuracy": 0.03554190434401053, "eval_loss_by_set": { "aqua_rat": 6.299922466278076, "gsm8k": 7.17186806418679, "math_qa": 5.869864781697591 }, "eval_accuracy_by_set": { "aqua_rat": 0.08267716535433071, "gsm8k": 0.021986353297952996, "math_qa": 0.037520938023450585 } }, { "flos": 2.0098510161990124e+18, "train_loss": 5.464373779296875, "eval_loss": 6.2843133823291675, "eval_accuracy": 0.04300131636682756, "eval_loss_by_set": { "aqua_rat": 6.296300411224365, "gsm8k": 7.158689325506037, "math_qa": 5.882558822631836 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.024260803639120546, "math_qa": 0.04824120603015075 } }, { "flos": 2.0154219785502065e+18, "train_loss": 5.470543212890625, "eval_loss": 6.2508172215642155, "eval_accuracy": 0.041246160596752963, "eval_loss_by_set": { "aqua_rat": 6.28005313873291, "gsm8k": 7.129661560058594, "math_qa": 5.845577239990234 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.02122820318423048, "math_qa": 0.047906197654941376 } }, { "flos": 2.020972250433323e+18, "train_loss": 5.4524560546875, "eval_loss": 6.2989866669113574, "eval_accuracy": 0.04322071083808688, "eval_loss_by_set": { "aqua_rat": 6.3155741691589355, "gsm8k": 7.181448502974077, "math_qa": 5.8931427001953125 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.02350265352539803, "math_qa": 0.04924623115577889 } }, { "flos": 2.0264996467837501e+18, "train_loss": 5.464417724609375, "eval_loss": 6.268245155746873, "eval_accuracy": 0.04212373848179026, "eval_loss_by_set": { "aqua_rat": 6.294642925262451, "gsm8k": 7.149140791459517, "math_qa": 5.862301508585612 }, "eval_accuracy_by_set": { "aqua_rat": 0.08661417322834646, "gsm8k": 0.022744503411675512, "math_qa": 0.04690117252931323 } }, { "flos": 2.0320628395391058e+18, "train_loss": 5.464367065429688, "eval_loss": 6.273925368850295, "eval_accuracy": 0.04168494953927161, "eval_loss_by_set": { "aqua_rat": 6.287212371826172, "gsm8k": 7.149887778542259, "math_qa": 5.871335347493489 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.021986353297952996, "math_qa": 0.047571189279731994 } }, { "flos": 2.037611442290557e+18, "train_loss": 5.467232666015625, "eval_loss": 6.25993334280478, "eval_accuracy": 0.0370776656428258, "eval_loss_by_set": { "aqua_rat": 6.275956630706787, "gsm8k": 7.144346063787287, "math_qa": 5.85324223836263 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.01592115238817286, "math_qa": 0.04321608040201005 } }, { "flos": 2.0431390453362852e+18, "train_loss": 5.45631103515625, "eval_loss": 6.284267915261759, "eval_accuracy": 0.03663887670030715, "eval_loss_by_set": { "aqua_rat": 6.32765531539917, "gsm8k": 7.184763821688565, "math_qa": 5.8679250081380205 }, "eval_accuracy_by_set": { "aqua_rat": 0.08267716535433071, "gsm8k": 0.021986353297952996, "math_qa": 0.03919597989949749 } }, { "flos": 2.0486298829250888e+18, "train_loss": 5.450283813476562, "eval_loss": 6.294058541993837, "eval_accuracy": 0.04168494953927161, "eval_loss_by_set": { "aqua_rat": 6.326298236846924, "gsm8k": 7.1768105246803975, "math_qa": 5.886777242024739 }, "eval_accuracy_by_set": { "aqua_rat": 0.08267716535433071, "gsm8k": 0.024260803639120546, "math_qa": 0.04589614740368509 } }, { "flos": 2.0541660587255398e+18, "train_loss": 5.451119384765625, "eval_loss": 6.295315458967879, "eval_accuracy": 0.03773584905660377, "eval_loss_by_set": { "aqua_rat": 6.327013969421387, "gsm8k": 7.177233609286222, "math_qa": 5.888461430867513 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.019711902956785442, "math_qa": 0.04254606365159129 } }, { "flos": 2.0597274588689203e+18, "train_loss": 5.465167236328125, "eval_loss": 6.268663973421664, "eval_accuracy": 0.03729706011408512, "eval_loss_by_set": { "aqua_rat": 6.289421081542969, "gsm8k": 7.14574501731179, "math_qa": 5.864938735961914 }, "eval_accuracy_by_set": { "aqua_rat": 0.0984251968503937, "gsm8k": 0.01819560272934041, "math_qa": 0.04053601340033501 } }, { "flos": 2.065257658222379e+18, "train_loss": 5.463302001953125, "eval_loss": 6.245524380658124, "eval_accuracy": 0.04168494953927161, "eval_loss_by_set": { "aqua_rat": 6.2840375900268555, "gsm8k": 7.120072798295454, "math_qa": 5.841480255126953 }, "eval_accuracy_by_set": { "aqua_rat": 0.08661417322834646, "gsm8k": 0.02880970432145565, "math_qa": 0.04355108877721943 } }, { "flos": 2.0707366051942236e+18, "train_loss": 5.45495361328125, "eval_loss": 6.269935607910156, "eval_accuracy": 0.03817463799912242, "eval_loss_by_set": { "aqua_rat": 6.299678802490234, "gsm8k": 7.160433682528409, "math_qa": 5.859312057495117 }, "eval_accuracy_by_set": { "aqua_rat": 0.08661417322834646, "gsm8k": 0.01819560272934041, "math_qa": 0.04288107202680067 } }, { "flos": 2.0762813124103373e+18, "train_loss": 5.454754638671875, "eval_loss": 6.295702444540487, "eval_accuracy": 0.041465555068012284, "eval_loss_by_set": { "aqua_rat": 6.324823379516602, "gsm8k": 7.183758128773082, "math_qa": 5.886250178019206 }, "eval_accuracy_by_set": { "aqua_rat": 0.0984251968503937, "gsm8k": 0.024260803639120546, "math_qa": 0.044221105527638194 } }, { "flos": 2.0818377459609108e+18, "train_loss": 5.463245849609375, "eval_loss": 6.27462505649876, "eval_accuracy": 0.03751645458534445, "eval_loss_by_set": { "aqua_rat": 6.296780586242676, "gsm8k": 7.160253351384943, "math_qa": 5.866865793863933 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.01819560272934041, "math_qa": 0.04254606365159129 } }, { "flos": 2.0873771778834432e+18, "train_loss": 5.453858642578125, "eval_loss": 6.27801191484606, "eval_accuracy": 0.041246160596752963, "eval_loss_by_set": { "aqua_rat": 6.303018093109131, "gsm8k": 7.1525490500710225, "math_qa": 5.875098546346028 }, "eval_accuracy_by_set": { "aqua_rat": 0.09448818897637795, "gsm8k": 0.021986353297952996, "math_qa": 0.04522613065326633 } }, { "flos": 2.092865274746241e+18, "train_loss": 5.451932373046875, "eval_loss": 6.287707741196091, "eval_accuracy": 0.040807371654234315, "eval_loss_by_set": { "aqua_rat": 6.309520244598389, "gsm8k": 7.183626348322088, "math_qa": 5.875260670979817 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.024260803639120546, "math_qa": 0.04489112227805695 } }, { "flos": 2.09842440768376e+18, "train_loss": 5.458123779296875, "eval_loss": 6.2925516592489705, "eval_accuracy": 0.03817463799912242, "eval_loss_by_set": { "aqua_rat": 6.309849739074707, "gsm8k": 7.166218150745738, "math_qa": 5.890679677327474 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.022744503411675512, "math_qa": 0.04288107202680067 } }, { "flos": 2.10394527138893e+18, "train_loss": 5.4552197265625, "eval_loss": 6.304227133054991, "eval_accuracy": 0.0388328214129004, "eval_loss_by_set": { "aqua_rat": 6.328099727630615, "gsm8k": 7.188311490145597, "math_qa": 5.897032419840495 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.02577710386656558, "math_qa": 0.04187604690117253 } }, { "flos": 2.1094675363271803e+18, "train_loss": 5.44645751953125, "eval_loss": 6.266648163666597, "eval_accuracy": 0.0379552435278631, "eval_loss_by_set": { "aqua_rat": 6.283393859863281, "gsm8k": 7.141179865056818, "math_qa": 5.8644256591796875 }, "eval_accuracy_by_set": { "aqua_rat": 0.08267716535433071, "gsm8k": 0.016679302501895376, "math_qa": 0.04355108877721943 } }, { "flos": 2.1150522441843343e+18, "train_loss": 5.452394409179687, "eval_loss": 6.282959242124815, "eval_accuracy": 0.03992979376919702, "eval_loss_by_set": { "aqua_rat": 6.306916236877441, "gsm8k": 7.167583812366832, "math_qa": 5.875509897867839 }, "eval_accuracy_by_set": { "aqua_rat": 0.09055118110236221, "gsm8k": 0.018953752843062926, "math_qa": 0.04489112227805695 } }, { "flos": 2.1205440717630996e+18, "train_loss": 5.450106811523438, "eval_loss": 6.265059600005278, "eval_accuracy": 0.04014918824045634, "eval_loss_by_set": { "aqua_rat": 6.284088134765625, "gsm8k": 7.1368324973366475, "math_qa": 5.863911310831706 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.02350265352539803, "math_qa": 0.044221105527638194 } }, { "flos": 2.126031261850927e+18, "train_loss": 5.443221435546875, "eval_loss": 6.259742736816406, "eval_accuracy": 0.03817463799912242, "eval_loss_by_set": { "aqua_rat": 6.273372650146484, "gsm8k": 7.146399758078835, "math_qa": 5.852222442626953 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.02047005307050796, "math_qa": 0.04288107202680067 } }, { "flos": 2.1315337844351304e+18, "train_loss": 5.4457470703125, "eval_loss": 6.2890805940370305, "eval_accuracy": 0.0434401053093462, "eval_loss_by_set": { "aqua_rat": 6.307280540466309, "gsm8k": 7.173289905894887, "math_qa": 5.882301330566406 }, "eval_accuracy_by_set": { "aqua_rat": 0.09448818897637795, "gsm8k": 0.02350265352539803, "math_qa": 0.047906197654941376 } }, { "flos": 2.13710777581201e+18, "train_loss": 5.46592529296875, "eval_loss": 6.276094101570748, "eval_accuracy": 0.03861342694164107, "eval_loss_by_set": { "aqua_rat": 6.309694766998291, "gsm8k": 7.163516651500355, "math_qa": 5.86655871073405 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.022744503411675512, "math_qa": 0.04254606365159129 } }, { "flos": 2.142666043313619e+18, "train_loss": 5.463990478515625, "eval_loss": 6.299971013455777, "eval_accuracy": 0.0370776656428258, "eval_loss_by_set": { "aqua_rat": 6.3107171058654785, "gsm8k": 7.177100441672585, "math_qa": 5.897057851155599 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.025018953752843062, "math_qa": 0.040871021775544386 } }, { "flos": 2.1482195294428856e+18, "train_loss": 5.45293212890625, "eval_loss": 6.267572609153953, "eval_accuracy": 0.04256252742430891, "eval_loss_by_set": { "aqua_rat": 6.265549659729004, "gsm8k": 7.1378042047674, "math_qa": 5.868885040283203 }, "eval_accuracy_by_set": { "aqua_rat": 0.08661417322834646, "gsm8k": 0.025018953752843062, "math_qa": 0.046566164154103855 } }, { "flos": 2.1537675550581064e+18, "train_loss": 5.4545135498046875, "eval_loss": 6.29340326463854, "eval_accuracy": 0.04278192189556823, "eval_loss_by_set": { "aqua_rat": 6.308239936828613, "gsm8k": 7.176591352982954, "math_qa": 5.887372334798177 }, "eval_accuracy_by_set": { "aqua_rat": 0.08267716535433071, "gsm8k": 0.016679302501895376, "math_qa": 0.050921273031825795 } }, { "flos": 2.1592718498531901e+18, "train_loss": 5.441072387695312, "eval_loss": 6.3031594044453385, "eval_accuracy": 0.04212373848179026, "eval_loss_by_set": { "aqua_rat": 6.323735237121582, "gsm8k": 7.180034290660512, "math_qa": 5.899543762207031 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.025018953752843062, "math_qa": 0.04690117252931323 } }, { "flos": 2.1648211945602417e+18, "train_loss": 5.458466796875, "eval_loss": 6.283750740257469, "eval_accuracy": 0.04190434401053093, "eval_loss_by_set": { "aqua_rat": 6.307242393493652, "gsm8k": 7.17034218528054, "math_qa": 5.875438690185547 }, "eval_accuracy_by_set": { "aqua_rat": 0.08267716535433071, "gsm8k": 0.024260803639120546, "math_qa": 0.04623115577889447 } }, { "flos": 2.1703722288000532e+18, "train_loss": 5.457039794921875, "eval_loss": 6.2845981443250505, "eval_accuracy": 0.041026766125493636, "eval_loss_by_set": { "aqua_rat": 6.304254055023193, "gsm8k": 7.160301208496094, "math_qa": 5.8815962473551435 }, "eval_accuracy_by_set": { "aqua_rat": 0.08267716535433071, "gsm8k": 0.025018953752843062, "math_qa": 0.04455611390284757 } }, { "flos": 2.1759366585059901e+18, "train_loss": 5.46500732421875, "eval_loss": 6.304058229601061, "eval_accuracy": 0.04212373848179026, "eval_loss_by_set": { "aqua_rat": 6.340424537658691, "gsm8k": 7.202073530717329, "math_qa": 5.889437357584636 }, "eval_accuracy_by_set": { "aqua_rat": 0.08661417322834646, "gsm8k": 0.022744503411675512, "math_qa": 0.04690117252931323 } }, { "flos": 2.181428897864745e+18, "train_loss": 5.457535400390625, "eval_loss": 6.303731969884924, "eval_accuracy": 0.04234313295304958, "eval_loss_by_set": { "aqua_rat": 6.3352203369140625, "gsm8k": 7.195079456676137, "math_qa": 5.8925736745198565 }, "eval_accuracy_by_set": { "aqua_rat": 0.08267716535433071, "gsm8k": 0.02350265352539803, "math_qa": 0.04723618090452261 } }, { "flos": 2.186935356786475e+18, "train_loss": 5.448929443359375, "eval_loss": 6.3018911722544075, "eval_accuracy": 0.04300131636682756, "eval_loss_by_set": { "aqua_rat": 6.321379661560059, "gsm8k": 7.181388854980469, "math_qa": 5.897164026896159 }, "eval_accuracy_by_set": { "aqua_rat": 0.09055118110236221, "gsm8k": 0.018953752843062926, "math_qa": 0.04958123953098827 } }, { "flos": 2.192450656361513e+18, "train_loss": 5.449176025390625, "eval_loss": 6.287298795339224, "eval_accuracy": 0.041026766125493636, "eval_loss_by_set": { "aqua_rat": 6.295694828033447, "gsm8k": 7.183596524325284, "math_qa": 5.875796000162761 }, "eval_accuracy_by_set": { "aqua_rat": 0.08661417322834646, "gsm8k": 0.016679302501895376, "math_qa": 0.047906197654941376 } }, { "flos": 2.1979076764515697e+18, "train_loss": 5.441292114257813, "eval_loss": 6.291688042718011, "eval_accuracy": 0.03729706011408512, "eval_loss_by_set": { "aqua_rat": 6.316562652587891, "gsm8k": 7.1713783957741475, "math_qa": 5.886423746744792 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.02047005307050796, "math_qa": 0.04254606365159129 } }, { "flos": 2.203405665160921e+18, "train_loss": 5.446527709960938, "eval_loss": 6.283675838161159, "eval_accuracy": 0.03861342694164107, "eval_loss_by_set": { "aqua_rat": 6.312097549438477, "gsm8k": 7.175458041104403, "math_qa": 5.8725738525390625 }, "eval_accuracy_by_set": { "aqua_rat": 0.09448818897637795, "gsm8k": 0.014404852160727824, "math_qa": 0.04455611390284757 } }, { "flos": 2.2089689405943972e+18, "train_loss": 5.466500244140625, "eval_loss": 6.267520595241237, "eval_accuracy": 0.03949100482667837, "eval_loss_by_set": { "aqua_rat": 6.2826080322265625, "gsm8k": 7.13925517689098, "math_qa": 5.866718292236328 }, "eval_accuracy_by_set": { "aqua_rat": 0.10236220472440945, "gsm8k": 0.02122820318423048, "math_qa": 0.04221105527638191 } }, { "flos": 2.214531680230703e+18, "train_loss": 5.463145751953125, "eval_loss": 6.297533215703191, "eval_accuracy": 0.040368582711715666, "eval_loss_by_set": { "aqua_rat": 6.3144307136535645, "gsm8k": 7.1880409934303975, "math_qa": 5.887975692749023 }, "eval_accuracy_by_set": { "aqua_rat": 0.09055118110236221, "gsm8k": 0.02047005307050796, "math_qa": 0.04489112227805695 } }, { "flos": 2.220054069186134e+18, "train_loss": 5.453670654296875, "eval_loss": 6.276142790510848, "eval_accuracy": 0.03971039929793769, "eval_loss_by_set": { "aqua_rat": 6.296988487243652, "gsm8k": 7.164953058416193, "math_qa": 5.867034276326497 }, "eval_accuracy_by_set": { "aqua_rat": 0.08267716535433071, "gsm8k": 0.02350265352539803, "math_qa": 0.04321608040201005 } }, { "flos": 2.225592923972436e+18, "train_loss": 5.4587451171875, "eval_loss": 6.305180085671915, "eval_accuracy": 0.04387889425186485, "eval_loss_by_set": { "aqua_rat": 6.331485271453857, "gsm8k": 7.193872625177557, "math_qa": 5.895670572916667 }, "eval_accuracy_by_set": { "aqua_rat": 0.09448818897637795, "gsm8k": 0.022744503411675512, "math_qa": 0.048911222780569516 } }, { "flos": 2.231131222560473e+18, "train_loss": 5.46101318359375, "eval_loss": 6.281194970414445, "eval_accuracy": 0.04409828872312418, "eval_loss_by_set": { "aqua_rat": 6.302448749542236, "gsm8k": 7.169676347212358, "math_qa": 5.872203191121419 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.024260803639120546, "math_qa": 0.05025125628140704 } }, { "flos": 2.236733488780804e+18, "train_loss": 5.463505859375, "eval_loss": 6.295323217237318, "eval_accuracy": 0.03817463799912242, "eval_loss_by_set": { "aqua_rat": 6.309407711029053, "gsm8k": 7.172832835804332, "math_qa": 5.891957600911458 }, "eval_accuracy_by_set": { "aqua_rat": 0.09055118110236221, "gsm8k": 0.021986353297952996, "math_qa": 0.040871021775544386 } }, { "flos": 2.2421931057154621e+18, "train_loss": 5.43798095703125, "eval_loss": 6.277949126991066, "eval_accuracy": 0.03927161035541905, "eval_loss_by_set": { "aqua_rat": 6.292968273162842, "gsm8k": 7.155542547052557, "math_qa": 5.874467213948567 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.01819560272934041, "math_qa": 0.04522613065326633 } }, { "flos": 2.2477749080272404e+18, "train_loss": 5.4601904296875, "eval_loss": 6.286394686312289, "eval_accuracy": 0.04234313295304958, "eval_loss_by_set": { "aqua_rat": 6.313407897949219, "gsm8k": 7.166001753373579, "math_qa": 5.880990346272786 }, "eval_accuracy_by_set": { "aqua_rat": 0.09448818897637795, "gsm8k": 0.025018953752843062, "math_qa": 0.045561139028475715 } }, { "flos": 2.2533255712892518e+18, "train_loss": 5.457561645507813, "eval_loss": 6.293139612352526, "eval_accuracy": 0.04453707766564283, "eval_loss_by_set": { "aqua_rat": 6.338819980621338, "gsm8k": 7.195479653098366, "math_qa": 5.875760396321614 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.025018953752843062, "math_qa": 0.05025125628140704 } }, { "flos": 2.2589087748341105e+18, "train_loss": 5.46147216796875, "eval_loss": 6.30555585912756, "eval_accuracy": 0.04475647213690215, "eval_loss_by_set": { "aqua_rat": 6.324295997619629, "gsm8k": 7.187939036976207, "math_qa": 5.899568557739258 }, "eval_accuracy_by_set": { "aqua_rat": 0.08661417322834646, "gsm8k": 0.025018953752843062, "math_qa": 0.049916247906197656 } }, { "flos": 2.264450329007358e+18, "train_loss": 5.456587524414062, "eval_loss": 6.301279815467629, "eval_accuracy": 0.046072838964458095, "eval_loss_by_set": { "aqua_rat": 6.332667827606201, "gsm8k": 7.19826923717152, "math_qa": 5.88754399617513 }, "eval_accuracy_by_set": { "aqua_rat": 0.08661417322834646, "gsm8k": 0.022744503411675512, "math_qa": 0.052931323283082074 } }, { "flos": 2.2699962935751475e+18, "train_loss": 5.460751953125, "eval_loss": 6.295310432846482, "eval_accuracy": 0.040368582711715666, "eval_loss_by_set": { "aqua_rat": 6.320115566253662, "gsm8k": 7.181687788529829, "math_qa": 5.886987050374349 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.021986353297952996, "math_qa": 0.045561139028475715 } }, { "flos": 2.2755563746266972e+18, "train_loss": 5.436656494140625, "eval_loss": 6.295352987340979, "eval_accuracy": 0.040807371654234315, "eval_loss_by_set": { "aqua_rat": 6.318564414978027, "gsm8k": 7.181441567160866, "math_qa": 5.887294769287109 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.022744503411675512, "math_qa": 0.046566164154103855 } }, { "flos": 2.2811025861551063e+18, "train_loss": 5.45705322265625, "eval_loss": 6.305756697783599, "eval_accuracy": 0.040807371654234315, "eval_loss_by_set": { "aqua_rat": 6.319706916809082, "gsm8k": 7.1796347878196025, "math_qa": 5.904066721598308 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.026535253980288095, "math_qa": 0.04388609715242881 } }, { "flos": 2.2866177622498345e+18, "train_loss": 5.44505126953125, "eval_loss": 6.305795927305479, "eval_accuracy": 0.040368582711715666, "eval_loss_by_set": { "aqua_rat": 6.318960189819336, "gsm8k": 7.185465032404119, "math_qa": 5.901517232259114 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.017437452615617893, "math_qa": 0.04723618090452261 } }, { "flos": 2.2921662823231652e+18, "train_loss": 5.45962646484375, "eval_loss": 6.311938363152581, "eval_accuracy": 0.04234313295304958, "eval_loss_by_set": { "aqua_rat": 6.319283485412598, "gsm8k": 7.195148814808238, "math_qa": 5.906521479288737 }, "eval_accuracy_by_set": { "aqua_rat": 0.08267716535433071, "gsm8k": 0.025018953752843062, "math_qa": 0.046566164154103855 } }, { "flos": 2.2976873521867653e+18, "train_loss": 5.448397216796875, "eval_loss": 6.289020100155392, "eval_accuracy": 0.03949100482667837, "eval_loss_by_set": { "aqua_rat": 6.304025173187256, "gsm8k": 7.176196011629972, "math_qa": 5.881147384643555 }, "eval_accuracy_by_set": { "aqua_rat": 0.08661417322834646, "gsm8k": 0.02047005307050796, "math_qa": 0.04388609715242881 } }, { "flos": 2.3031990869389476e+18, "train_loss": 5.440006713867188, "eval_loss": 6.282176868335621, "eval_accuracy": 0.04278192189556823, "eval_loss_by_set": { "aqua_rat": 6.302486419677734, "gsm8k": 7.1636879660866475, "math_qa": 5.876458485921224 }, "eval_accuracy_by_set": { "aqua_rat": 0.09448818897637795, "gsm8k": 0.01819560272934041, "math_qa": 0.04924623115577889 } }, { "flos": 2.3087389923816243e+18, "train_loss": 5.448504638671875, "eval_loss": 6.280572221085832, "eval_accuracy": 0.04322071083808688, "eval_loss_by_set": { "aqua_rat": 6.304847717285156, "gsm8k": 7.158293984153054, "math_qa": 5.876260121663411 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.019711902956785442, "math_qa": 0.05058626465661641 } }, { "flos": 2.314345585781506e+18, "train_loss": 5.451399536132812, "eval_loss": 6.285153285877125, "eval_accuracy": 0.04629223343571742, "eval_loss_by_set": { "aqua_rat": 6.307066440582275, "gsm8k": 7.181936090642756, "math_qa": 5.872301737467448 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.02350265352539803, "math_qa": 0.05527638190954774 } }, { "flos": 2.319862018691039e+18, "train_loss": 5.45119140625, "eval_loss": 6.293610108865274, "eval_accuracy": 0.045634050021939446, "eval_loss_by_set": { "aqua_rat": 6.317079067230225, "gsm8k": 7.1894989013671875, "math_qa": 5.881038665771484 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.02577710386656558, "math_qa": 0.05159128978224456 } }, { "flos": 2.3254175454666424e+18, "train_loss": 5.464794921875, "eval_loss": 6.269284634976773, "eval_accuracy": 0.040368582711715666, "eval_loss_by_set": { "aqua_rat": 6.297306060791016, "gsm8k": 7.16567646373402, "math_qa": 5.856103261311849 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.02122820318423048, "math_qa": 0.04589614740368509 } }, { "flos": 2.3309357924629873e+18, "train_loss": 5.43670166015625, "eval_loss": 6.311553284928605, "eval_accuracy": 0.04278192189556823, "eval_loss_by_set": { "aqua_rat": 6.3335065841674805, "gsm8k": 7.190598921342329, "math_qa": 5.906827926635742 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.022744503411675512, "math_qa": 0.048576214405360134 } }, { "flos": 2.3364813860529766e+18, "train_loss": 5.455369262695313, "eval_loss": 6.29449563413053, "eval_accuracy": 0.04409828872312418, "eval_loss_by_set": { "aqua_rat": 6.318225383758545, "gsm8k": 7.173524336381392, "math_qa": 5.88962999979655 }, "eval_accuracy_by_set": { "aqua_rat": 0.10236220472440945, "gsm8k": 0.02350265352539803, "math_qa": 0.04824120603015075 } }, { "flos": 2.342007237288919e+18, "train_loss": 5.449594116210937, "eval_loss": 6.283439842430321, "eval_accuracy": 0.040368582711715666, "eval_loss_by_set": { "aqua_rat": 6.298847198486328, "gsm8k": 7.160194396972656, "math_qa": 5.88031005859375 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.02350265352539803, "math_qa": 0.04489112227805695 } }, { "flos": 2.347515282664194e+18, "train_loss": 5.442046508789063, "eval_loss": 6.306845278353305, "eval_accuracy": 0.041026766125493636, "eval_loss_by_set": { "aqua_rat": 6.326879501342773, "gsm8k": 7.194307500665838, "math_qa": 5.8984222412109375 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.02122820318423048, "math_qa": 0.04723618090452261 } }, { "flos": 2.3530577645503775e+18, "train_loss": 5.453768310546875, "eval_loss": 6.292692132898279, "eval_accuracy": 0.045414655550680125, "eval_loss_by_set": { "aqua_rat": 6.313371658325195, "gsm8k": 7.167884133078835, "math_qa": 5.889839172363281 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.021986353297952996, "math_qa": 0.053266331658291456 } }, { "flos": 2.358571828248576e+18, "train_loss": 5.441307373046875, "eval_loss": 6.321277721508129, "eval_accuracy": 0.04014918824045634, "eval_loss_by_set": { "aqua_rat": 6.332923889160156, "gsm8k": 7.201390353116122, "math_qa": 5.916922251383464 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.016679302501895376, "math_qa": 0.04723618090452261 } }, { "flos": 2.3640788020295107e+18, "train_loss": 5.443602294921875, "eval_loss": 6.301543158453864, "eval_accuracy": 0.04234313295304958, "eval_loss_by_set": { "aqua_rat": 6.330150604248047, "gsm8k": 7.186552567915483, "math_qa": 5.893529891967773 }, "eval_accuracy_by_set": { "aqua_rat": 0.09055118110236221, "gsm8k": 0.028051554207733132, "math_qa": 0.04455611390284757 } }, { "flos": 2.369629238731997e+18, "train_loss": 5.442761840820313, "eval_loss": 6.298583881275074, "eval_accuracy": 0.04475647213690215, "eval_loss_by_set": { "aqua_rat": 6.333257675170898, "gsm8k": 7.1848297119140625, "math_qa": 5.889498392740886 }, "eval_accuracy_by_set": { "aqua_rat": 0.0984251968503937, "gsm8k": 0.021986353297952996, "math_qa": 0.05025125628140704 } }, { "flos": 2.375140128449364e+18, "train_loss": 5.444600219726563, "eval_loss": 6.306864583814466, "eval_accuracy": 0.041246160596752963, "eval_loss_by_set": { "aqua_rat": 6.325012683868408, "gsm8k": 7.190164739435369, "math_qa": 5.900506337483724 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.02122820318423048, "math_qa": 0.04723618090452261 } }, { "flos": 2.380650997765636e+18, "train_loss": 5.438867797851563, "eval_loss": 6.304960585929252, "eval_accuracy": 0.0434401053093462, "eval_loss_by_set": { "aqua_rat": 6.322068691253662, "gsm8k": 7.190546209161932, "math_qa": 5.897641499837239 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.02350265352539803, "math_qa": 0.04924623115577889 } }, { "flos": 2.386220228708139e+18, "train_loss": 5.460296630859375, "eval_loss": 6.286440282254605, "eval_accuracy": 0.0434401053093462, "eval_loss_by_set": { "aqua_rat": 6.3006672859191895, "gsm8k": 7.175232627175071, "math_qa": 5.877891540527344 }, "eval_accuracy_by_set": { "aqua_rat": 0.08661417322834646, "gsm8k": 0.022744503411675512, "math_qa": 0.048911222780569516 } }, { "flos": 2.391717042743935e+18, "train_loss": 5.435772094726563, "eval_loss": 6.298179523364918, "eval_accuracy": 0.04256252742430891, "eval_loss_by_set": { "aqua_rat": 6.316755294799805, "gsm8k": 7.16787372935902, "math_qa": 5.898021697998047 }, "eval_accuracy_by_set": { "aqua_rat": 0.09448818897637795, "gsm8k": 0.019711902956785442, "math_qa": 0.04824120603015075 } }, { "flos": 2.3972827083267113e+18, "train_loss": 5.45064453125, "eval_loss": 6.2839470682917415, "eval_accuracy": 0.03992979376919702, "eval_loss_by_set": { "aqua_rat": 6.312133312225342, "gsm8k": 7.155813043767756, "math_qa": 5.8819929758707685 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.02047005307050796, "math_qa": 0.045561139028475715 } }, { "flos": 2.4028170292381614e+18, "train_loss": 5.449603271484375, "eval_loss": 6.293909433725718, "eval_accuracy": 0.045634050021939446, "eval_loss_by_set": { "aqua_rat": 6.3236236572265625, "gsm8k": 7.176691228693182, "math_qa": 5.88682492574056 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.01819560272934041, "math_qa": 0.0559463986599665 } }, { "flos": 2.408360871018365e+18, "train_loss": 5.448679809570312, "eval_loss": 6.2991878148671745, "eval_accuracy": 0.040807371654234315, "eval_loss_by_set": { "aqua_rat": 6.32703161239624, "gsm8k": 7.190971374511719, "math_qa": 5.888133366902669 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.024260803639120546, "math_qa": 0.045561139028475715 } }, { "flos": 2.4138686076928655e+18, "train_loss": 5.431671752929687, "eval_loss": 6.307216953586888, "eval_accuracy": 0.040807371654234315, "eval_loss_by_set": { "aqua_rat": 6.331394195556641, "gsm8k": 7.208493319424716, "math_qa": 5.892117182413737 }, "eval_accuracy_by_set": { "aqua_rat": 0.08661417322834646, "gsm8k": 0.02122820318423048, "math_qa": 0.045561139028475715 } }, { "flos": 2.4194209400865423e+18, "train_loss": 5.45401611328125, "eval_loss": 6.298809592788284, "eval_accuracy": 0.04212373848179026, "eval_loss_by_set": { "aqua_rat": 6.311214923858643, "gsm8k": 7.193219965154475, "math_qa": 5.887837727864583 }, "eval_accuracy_by_set": { "aqua_rat": 0.08661417322834646, "gsm8k": 0.028051554207733132, "math_qa": 0.04455611390284757 } }, { "flos": 2.424958002260869e+18, "train_loss": 5.446646728515625, "eval_loss": 6.289835646345809, "eval_accuracy": 0.0434401053093462, "eval_loss_by_set": { "aqua_rat": 6.316198348999023, "gsm8k": 7.168501420454546, "math_qa": 5.88491694132487 }, "eval_accuracy_by_set": { "aqua_rat": 0.09448818897637795, "gsm8k": 0.02047005307050796, "math_qa": 0.04924623115577889 } }, { "flos": 2.43044158564991e+18, "train_loss": 5.430255126953125, "eval_loss": 6.297960023622255, "eval_accuracy": 0.04234313295304958, "eval_loss_by_set": { "aqua_rat": 6.323089599609375, "gsm8k": 7.181522716175426, "math_qa": 5.890899658203125 }, "eval_accuracy_by_set": { "aqua_rat": 0.09448818897637795, "gsm8k": 0.024260803639120546, "math_qa": 0.04589614740368509 } }, { "flos": 2.435928631856333e+18, "train_loss": 5.4338427734375, "eval_loss": 6.33153858700314, "eval_accuracy": 0.04256252742430891, "eval_loss_by_set": { "aqua_rat": 6.348650932312012, "gsm8k": 7.2251503684303975, "math_qa": 5.920540491739909 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.02350265352539803, "math_qa": 0.047906197654941376 } }, { "flos": 2.441462458309673e+18, "train_loss": 5.444368896484375, "eval_loss": 6.294650490219529, "eval_accuracy": 0.0434401053093462, "eval_loss_by_set": { "aqua_rat": 6.308379650115967, "gsm8k": 7.185118241743608, "math_qa": 5.885375340779622 }, "eval_accuracy_by_set": { "aqua_rat": 0.08267716535433071, "gsm8k": 0.019711902956785442, "math_qa": 0.05058626465661641 } }, { "flos": 2.447008113639817e+18, "train_loss": 5.444405517578125, "eval_loss": 6.307475218901763, "eval_accuracy": 0.04409828872312418, "eval_loss_by_set": { "aqua_rat": 6.334348678588867, "gsm8k": 7.199436534534801, "math_qa": 5.896420160929362 }, "eval_accuracy_by_set": { "aqua_rat": 0.08661417322834646, "gsm8k": 0.021986353297952996, "math_qa": 0.05025125628140704 } }, { "flos": 2.452484814343766e+18, "train_loss": 5.43596435546875, "eval_loss": 6.301987622235273, "eval_accuracy": 0.04409828872312418, "eval_loss_by_set": { "aqua_rat": 6.316888809204102, "gsm8k": 7.174940629438921, "math_qa": 5.900642395019531 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.02350265352539803, "math_qa": 0.05058626465661641 } }, { "flos": 2.4580270691335537e+18, "train_loss": 5.4450537109375, "eval_loss": 6.30943589597135, "eval_accuracy": 0.04168494953927161, "eval_loss_by_set": { "aqua_rat": 6.3308491706848145, "gsm8k": 7.2046356201171875, "math_qa": 5.897351582845052 }, "eval_accuracy_by_set": { "aqua_rat": 0.08661417322834646, "gsm8k": 0.02122820318423048, "math_qa": 0.04690117252931323 } }, { "flos": 2.4635047383526277e+18, "train_loss": 5.436778564453125, "eval_loss": 6.302178047798775, "eval_accuracy": 0.04058797718297499, "eval_loss_by_set": { "aqua_rat": 6.327663421630859, "gsm8k": 7.180498296564275, "math_qa": 5.897490819295247 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.02122820318423048, "math_qa": 0.04589614740368509 } }, { "flos": 2.4690112794156073e+18, "train_loss": 5.442400512695312, "eval_loss": 6.311300947859481, "eval_accuracy": 0.04190434401053093, "eval_loss_by_set": { "aqua_rat": 6.325702667236328, "gsm8k": 7.181254993785512, "math_qa": 5.9113718668619795 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.024260803639120546, "math_qa": 0.04723618090452261 } }, { "flos": 2.4745117828283105e+18, "train_loss": 5.429312133789063, "eval_loss": 6.299863042058171, "eval_accuracy": 0.04234313295304958, "eval_loss_by_set": { "aqua_rat": 6.314044952392578, "gsm8k": 7.162815440784801, "math_qa": 5.903161366780599 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.015163002274450341, "math_qa": 0.051926298157453935 } }, { "flos": 2.4800355735536927e+18, "train_loss": 5.443615112304688, "eval_loss": 6.3048295201482, "eval_accuracy": 0.04322071083808688, "eval_loss_by_set": { "aqua_rat": 6.335165977478027, "gsm8k": 7.199145923961293, "math_qa": 5.892406463623047 }, "eval_accuracy_by_set": { "aqua_rat": 0.08267716535433071, "gsm8k": 0.02122820318423048, "math_qa": 0.04958123953098827 } }, { "flos": 2.485566947580707e+18, "train_loss": 5.448048095703125, "eval_loss": 6.3213176985044734, "eval_accuracy": 0.040807371654234315, "eval_loss_by_set": { "aqua_rat": 6.338626384735107, "gsm8k": 7.200686368075284, "math_qa": 5.916831334431966 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.019711902956785442, "math_qa": 0.04824120603015075 } }, { "flos": 2.491016260351951e+18, "train_loss": 5.449788818359375, "eval_loss": 6.289212149542731, "eval_accuracy": 0.04234313295304958, "eval_loss_by_set": { "aqua_rat": 6.327940940856934, "gsm8k": 7.171543468128551, "math_qa": 5.881582895914714 }, "eval_accuracy_by_set": { "aqua_rat": 0.08267716535433071, "gsm8k": 0.019711902956785442, "math_qa": 0.048911222780569516 } }, { "flos": 2.496583451721859e+18, "train_loss": 5.447763671875, "eval_loss": 6.29889068088016, "eval_accuracy": 0.04014918824045634, "eval_loss_by_set": { "aqua_rat": 6.335877895355225, "gsm8k": 7.182798212224787, "math_qa": 5.890684127807617 }, "eval_accuracy_by_set": { "aqua_rat": 0.09448818897637795, "gsm8k": 0.01592115238817286, "math_qa": 0.04623115577889447 } }, { "flos": 2.5021215650894316e+18, "train_loss": 5.458458251953125, "eval_loss": 6.3170158540880355, "eval_accuracy": 0.04168494953927161, "eval_loss_by_set": { "aqua_rat": 6.358758449554443, "gsm8k": 7.213580044833097, "math_qa": 5.902612050374349 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.025018953752843062, "math_qa": 0.047571189279731994 } }, { "flos": 2.5076238815152046e+18, "train_loss": 5.442752685546875, "eval_loss": 6.321775745701146, "eval_accuracy": 0.046072838964458095, "eval_loss_by_set": { "aqua_rat": 6.3497514724731445, "gsm8k": 7.201536005193537, "math_qa": 5.916220982869466 }, "eval_accuracy_by_set": { "aqua_rat": 0.08661417322834646, "gsm8k": 0.021986353297952996, "math_qa": 0.053266331658291456 } }, { "flos": 2.5131802323876577e+18, "train_loss": 5.45018310546875, "eval_loss": 6.293169021606445, "eval_accuracy": 0.04475647213690215, "eval_loss_by_set": { "aqua_rat": 6.312695503234863, "gsm8k": 7.162316062233665, "math_qa": 5.893182754516602 }, "eval_accuracy_by_set": { "aqua_rat": 0.0984251968503937, "gsm8k": 0.026535253980288095, "math_qa": 0.04824120603015075 } }, { "flos": 2.518735161625936e+18, "train_loss": 5.454866943359375, "eval_loss": 6.312559488657358, "eval_accuracy": 0.04892496709082931, "eval_loss_by_set": { "aqua_rat": 6.33863639831543, "gsm8k": 7.183805292302912, "math_qa": 5.911065419514974 }, "eval_accuracy_by_set": { "aqua_rat": 0.0984251968503937, "gsm8k": 0.026535253980288095, "math_qa": 0.05460636515912898 } }, { "flos": 2.524247061197488e+18, "train_loss": 5.456975708007812, "eval_loss": 6.2876066774935335, "eval_accuracy": 0.04760860026327336, "eval_loss_by_set": { "aqua_rat": 6.325560569763184, "gsm8k": 7.172984730113637, "math_qa": 5.878645579020183 }, "eval_accuracy_by_set": { "aqua_rat": 0.08661417322834646, "gsm8k": 0.028051554207733132, "math_qa": 0.052931323283082074 } }, { "flos": 2.5297725409187594e+18, "train_loss": 5.442042846679687, "eval_loss": 6.26016023996714, "eval_accuracy": 0.04409828872312418, "eval_loss_by_set": { "aqua_rat": 6.292136192321777, "gsm8k": 7.156582919034091, "math_qa": 5.846635182698567 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.019711902956785442, "math_qa": 0.05226130653266332 } }, { "flos": 2.5353178666101637e+18, "train_loss": 5.435135498046875, "eval_loss": 6.315860129691459, "eval_accuracy": 0.04475647213690215, "eval_loss_by_set": { "aqua_rat": 6.350347518920898, "gsm8k": 7.20795371315696, "math_qa": 5.904109954833984 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.02350265352539803, "math_qa": 0.0525963149078727 } }, { "flos": 2.540830260639826e+18, "train_loss": 5.449444580078125, "eval_loss": 6.30133494815311, "eval_accuracy": 0.04212373848179026, "eval_loss_by_set": { "aqua_rat": 6.307206153869629, "gsm8k": 7.182071339000355, "math_qa": 5.897174835205078 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.019711902956785442, "math_qa": 0.049916247906197656 } }, { "flos": 2.546365344444842e+18, "train_loss": 5.452711181640625, "eval_loss": 6.288893055271458, "eval_accuracy": 0.041026766125493636, "eval_loss_by_set": { "aqua_rat": 6.327893257141113, "gsm8k": 7.19002949107777, "math_qa": 5.872622172037761 }, "eval_accuracy_by_set": { "aqua_rat": 0.08267716535433071, "gsm8k": 0.018953752843062926, "math_qa": 0.04723618090452261 } }, { "flos": 2.5519091862250455e+18, "train_loss": 5.447021484375, "eval_loss": 6.279132018218169, "eval_accuracy": 0.0434401053093462, "eval_loss_by_set": { "aqua_rat": 6.302156448364258, "gsm8k": 7.164509166370738, "math_qa": 5.871415456136067 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.02122820318423048, "math_qa": 0.05025125628140704 } }, { "flos": 2.557453192824619e+18, "train_loss": 5.454605712890625, "eval_loss": 6.297452978185706, "eval_accuracy": 0.04190434401053093, "eval_loss_by_set": { "aqua_rat": 6.315311431884766, "gsm8k": 7.174020940607244, "math_qa": 5.894204457600911 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.028051554207733132, "math_qa": 0.04522613065326633 } }, { "flos": 2.563053336257364e+18, "train_loss": 5.468993530273438, "eval_loss": 6.2966913790316195, "eval_accuracy": 0.045634050021939446, "eval_loss_by_set": { "aqua_rat": 6.323709487915039, "gsm8k": 7.17962022261186, "math_qa": 5.889764149983724 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.019711902956785442, "math_qa": 0.05527638190954774 } }, { "flos": 2.5685797844937605e+18, "train_loss": 5.444940795898438, "eval_loss": 6.312593099233267, "eval_accuracy": 0.04387889425186485, "eval_loss_by_set": { "aqua_rat": 6.332876205444336, "gsm8k": 7.189998279918324, "math_qa": 5.908758799235026 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.02047005307050796, "math_qa": 0.05226130653266332 } }, { "flos": 2.574138361233015e+18, "train_loss": 5.445009765625, "eval_loss": 6.330413921459301, "eval_accuracy": 0.041246160596752963, "eval_loss_by_set": { "aqua_rat": 6.352975845336914, "gsm8k": 7.214361017400568, "math_qa": 5.923391342163086 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.016679302501895376, "math_qa": 0.049916247906197656 } }, { "flos": 2.5796517033767076e+18, "train_loss": 5.439221801757813, "eval_loss": 6.304106660791345, "eval_accuracy": 0.041026766125493636, "eval_loss_by_set": { "aqua_rat": 6.321133136749268, "gsm8k": 7.194251320578835, "math_qa": 5.894704818725586 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.025018953752843062, "math_qa": 0.04690117252931323 } }, { "flos": 2.585193814285091e+18, "train_loss": 5.454011840820312, "eval_loss": 6.31176149522936, "eval_accuracy": 0.04300131636682756, "eval_loss_by_set": { "aqua_rat": 6.333913803100586, "gsm8k": 7.196775263006037, "math_qa": 5.904284159342448 }, "eval_accuracy_by_set": { "aqua_rat": 0.08267716535433071, "gsm8k": 0.022744503411675512, "math_qa": 0.048576214405360134 } }, { "flos": 2.590750762694869e+18, "train_loss": 5.452761840820313, "eval_loss": 6.337214109059927, "eval_accuracy": 0.04365949978060553, "eval_loss_by_set": { "aqua_rat": 6.375065326690674, "gsm8k": 7.241244229403409, "math_qa": 5.9197127024332685 }, "eval_accuracy_by_set": { "aqua_rat": 0.08267716535433071, "gsm8k": 0.02047005307050796, "math_qa": 0.05058626465661641 } }, { "flos": 2.5962993031692943e+18, "train_loss": 5.448712768554688, "eval_loss": 6.298956922582678, "eval_accuracy": 0.0443176831943835, "eval_loss_by_set": { "aqua_rat": 6.314783573150635, "gsm8k": 7.174212369051847, "math_qa": 5.8964792887369795 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.024260803639120546, "math_qa": 0.05159128978224456 } }, { "flos": 2.601802526370038e+18, "train_loss": 5.4321728515625, "eval_loss": 6.304955198958114, "eval_accuracy": 0.04365949978060553, "eval_loss_by_set": { "aqua_rat": 6.348542213439941, "gsm8k": 7.212059714577415, "math_qa": 5.885566711425781 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.021986353297952996, "math_qa": 0.05159128978224456 } }, { "flos": 2.607303153263051e+18, "train_loss": 5.44612548828125, "eval_loss": 6.306972580987054, "eval_accuracy": 0.04760860026327336, "eval_loss_by_set": { "aqua_rat": 6.336165904998779, "gsm8k": 7.198901089754972, "math_qa": 5.895739237467448 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.027293404094010616, "math_qa": 0.05393634840871022 } }, { "flos": 2.612855691815158e+18, "train_loss": 5.4497137451171875, "eval_loss": 6.320951178267196, "eval_accuracy": 0.045634050021939446, "eval_loss_by_set": { "aqua_rat": 6.343160152435303, "gsm8k": 7.208478060635653, "math_qa": 5.912317276000977 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.027293404094010616, "math_qa": 0.05159128978224456 } }, { "flos": 2.6183651593614787e+18, "train_loss": 5.42426025390625, "eval_loss": 6.314383171700142, "eval_accuracy": 0.04300131636682756, "eval_loss_by_set": { "aqua_rat": 6.326937675476074, "gsm8k": 7.190693248401988, "math_qa": 5.911694844563802 }, "eval_accuracy_by_set": { "aqua_rat": 0.09055118110236221, "gsm8k": 0.025018953752843062, "math_qa": 0.04690117252931323 } }, { "flos": 2.623924540333359e+18, "train_loss": 5.450826416015625, "eval_loss": 6.313869450543378, "eval_accuracy": 0.044975866608161476, "eval_loss_by_set": { "aqua_rat": 6.341241359710693, "gsm8k": 7.191227999600497, "math_qa": 5.909465789794922 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.022744503411675512, "math_qa": 0.051926298157453935 } }, { "flos": 2.629472174569685e+18, "train_loss": 5.43841552734375, "eval_loss": 6.291301314895217, "eval_accuracy": 0.03905221588415972, "eval_loss_by_set": { "aqua_rat": 6.313508987426758, "gsm8k": 7.179889332164418, "math_qa": 5.882181167602539 }, "eval_accuracy_by_set": { "aqua_rat": 0.08661417322834646, "gsm8k": 0.025018953752843062, "math_qa": 0.04120603015075377 } }, { "flos": 2.6349934505917153e+18, "train_loss": 5.44087890625, "eval_loss": 6.29761639156857, "eval_accuracy": 0.044975866608161476, "eval_loss_by_set": { "aqua_rat": 6.33204460144043, "gsm8k": 7.19019248268821, "math_qa": 5.885649998982747 }, "eval_accuracy_by_set": { "aqua_rat": 0.0984251968503937, "gsm8k": 0.022744503411675512, "math_qa": 0.05025125628140704 } }, { "flos": 2.6404629384349614e+18, "train_loss": 5.42208251953125, "eval_loss": 6.315540081745869, "eval_accuracy": 0.04300131636682756, "eval_loss_by_set": { "aqua_rat": 6.34198522567749, "gsm8k": 7.190034346147017, "math_qa": 5.912526448567708 }, "eval_accuracy_by_set": { "aqua_rat": 0.08661417322834646, "gsm8k": 0.025018953752843062, "math_qa": 0.04723618090452261 } }, { "flos": 2.6459940859024507e+18, "train_loss": 5.439862060546875, "eval_loss": 6.314858668559307, "eval_accuracy": 0.04256252742430891, "eval_loss_by_set": { "aqua_rat": 6.345141410827637, "gsm8k": 7.200415871360085, "math_qa": 5.906454722086589 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.025018953752843062, "math_qa": 0.047906197654941376 } }, { "flos": 2.6515432035131064e+18, "train_loss": 5.4392626953125, "eval_loss": 6.296689884082691, "eval_accuracy": 0.04387889425186485, "eval_loss_by_set": { "aqua_rat": 6.329312324523926, "gsm8k": 7.198502280495384, "math_qa": 5.8806406656901045 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.02122820318423048, "math_qa": 0.05226130653266332 } }, { "flos": 2.6571009969577e+18, "train_loss": 5.443544311523437, "eval_loss": 6.325838037439294, "eval_accuracy": 0.04387889425186485, "eval_loss_by_set": { "aqua_rat": 6.354366302490234, "gsm8k": 7.209747314453125, "math_qa": 5.918335596720378 }, "eval_accuracy_by_set": { "aqua_rat": 0.09055118110236221, "gsm8k": 0.02122820318423048, "math_qa": 0.049916247906197656 } }, { "flos": 2.662631114169909e+18, "train_loss": 5.43428466796875, "eval_loss": 6.294630927008551, "eval_accuracy": 0.04234313295304958, "eval_loss_by_set": { "aqua_rat": 6.322212219238281, "gsm8k": 7.180681402033025, "math_qa": 5.8862260182698565 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.021986353297952996, "math_qa": 0.048576214405360134 } }, { "flos": 2.6681578512428564e+18, "train_loss": 5.431851806640625, "eval_loss": 6.297025319692251, "eval_accuracy": 0.04322071083808688, "eval_loss_by_set": { "aqua_rat": 6.330299377441406, "gsm8k": 7.171316667036577, "math_qa": 5.893535614013672 }, "eval_accuracy_by_set": { "aqua_rat": 0.08267716535433071, "gsm8k": 0.018953752843062926, "math_qa": 0.05058626465661641 } }, { "flos": 2.67362000274509e+18, "train_loss": 5.424813232421875, "eval_loss": 6.307725261997533, "eval_accuracy": 0.04322071083808688, "eval_loss_by_set": { "aqua_rat": 6.346020221710205, "gsm8k": 7.187115062366832, "math_qa": 5.901480356852214 }, "eval_accuracy_by_set": { "aqua_rat": 0.08267716535433071, "gsm8k": 0.01592115238817286, "math_qa": 0.051926298157453935 } }, { "flos": 2.679125163512955e+18, "train_loss": 5.429536743164062, "eval_loss": 6.3116471574113175, "eval_accuracy": 0.04387889425186485, "eval_loss_by_set": { "aqua_rat": 6.3382568359375, "gsm8k": 7.1854636452414775, "math_qa": 5.9089304606119795 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.022744503411675512, "math_qa": 0.05025125628140704 } }, { "flos": 2.684663255942562e+18, "train_loss": 5.444752197265625, "eval_loss": 6.308558644475164, "eval_accuracy": 0.04278192189556823, "eval_loss_by_set": { "aqua_rat": 6.33176326751709, "gsm8k": 7.187715010209517, "math_qa": 5.903678258260091 }, "eval_accuracy_by_set": { "aqua_rat": 0.0984251968503937, "gsm8k": 0.018953752843062926, "math_qa": 0.048576214405360134 } }, { "flos": 2.690210930981077e+18, "train_loss": 5.443817138671875, "eval_loss": 6.337539775951488, "eval_accuracy": 0.04014918824045634, "eval_loss_by_set": { "aqua_rat": 6.35820198059082, "gsm8k": 7.218922008167613, "math_qa": 5.931851069132487 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.019711902956785442, "math_qa": 0.04589614740368509 } }, { "flos": 2.695789374091559e+18, "train_loss": 5.446848754882812, "eval_loss": 6.349352192234349, "eval_accuracy": 0.04782799473453269, "eval_loss_by_set": { "aqua_rat": 6.384020805358887, "gsm8k": 7.2441323020241475, "math_qa": 5.9363555908203125 }, "eval_accuracy_by_set": { "aqua_rat": 0.0984251968503937, "gsm8k": 0.02047005307050796, "math_qa": 0.05561139028475712 } }, { "flos": 2.701396832927351e+18, "train_loss": 5.45483642578125, "eval_loss": 6.352938729363519, "eval_accuracy": 0.04234313295304958, "eval_loss_by_set": { "aqua_rat": 6.375615119934082, "gsm8k": 7.240244778719815, "math_qa": 5.944367090861003 }, "eval_accuracy_by_set": { "aqua_rat": 0.09448818897637795, "gsm8k": 0.021986353297952996, "math_qa": 0.04690117252931323 } }, { "flos": 2.706883714314404e+18, "train_loss": 5.425339965820313, "eval_loss": 6.303142186757681, "eval_accuracy": 0.04673102237823607, "eval_loss_by_set": { "aqua_rat": 6.322558403015137, "gsm8k": 7.182236411354759, "math_qa": 5.898605982462565 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.022744503411675512, "math_qa": 0.05460636515912898 } }, { "flos": 2.7124189833398845e+18, "train_loss": 5.433050537109375, "eval_loss": 6.354952657544935, "eval_accuracy": 0.04190434401053093, "eval_loss_by_set": { "aqua_rat": 6.38273286819458, "gsm8k": 7.243211226029829, "math_qa": 5.945519129435222 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.018953752843062926, "math_qa": 0.049916247906197656 } }, { "flos": 2.7179069567223726e+18, "train_loss": 5.419430541992187, "eval_loss": 6.33984813174686, "eval_accuracy": 0.046072838964458095, "eval_loss_by_set": { "aqua_rat": 6.363186836242676, "gsm8k": 7.22565390846946, "math_qa": 5.931908925374349 }, "eval_accuracy_by_set": { "aqua_rat": 0.08661417322834646, "gsm8k": 0.02350265352539803, "math_qa": 0.0525963149078727 } }, { "flos": 2.723475837625041e+18, "train_loss": 5.45241455078125, "eval_loss": 6.3015713562836515, "eval_accuracy": 0.04190434401053093, "eval_loss_by_set": { "aqua_rat": 6.338698387145996, "gsm8k": 7.184201327237216, "math_qa": 5.893938700358073 }, "eval_accuracy_by_set": { "aqua_rat": 0.09055118110236221, "gsm8k": 0.02047005307050796, "math_qa": 0.04723618090452261 } }, { "flos": 2.729004120349344e+18, "train_loss": 5.432288818359375, "eval_loss": 6.299432342116897, "eval_accuracy": 0.03949100482667837, "eval_loss_by_set": { "aqua_rat": 6.326371192932129, "gsm8k": 7.180087002840909, "math_qa": 5.893554051717122 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.021986353297952996, "math_qa": 0.04489112227805695 } }, { "flos": 2.7345463547380367e+18, "train_loss": 5.444737548828125, "eval_loss": 6.310224945480759, "eval_accuracy": 0.04475647213690215, "eval_loss_by_set": { "aqua_rat": 6.341555595397949, "gsm8k": 7.19139931418679, "math_qa": 5.9037424723307295 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.025018953752843062, "math_qa": 0.05226130653266332 } }, { "flos": 2.740018789465719e+18, "train_loss": 5.429779052734375, "eval_loss": 6.331363446003682, "eval_accuracy": 0.041026766125493636, "eval_loss_by_set": { "aqua_rat": 6.360978603363037, "gsm8k": 7.22677265514027, "math_qa": 5.9184996287028 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.02047005307050796, "math_qa": 0.047571189279731994 } }, { "flos": 2.745585938959696e+18, "train_loss": 5.457803955078125, "eval_loss": 6.321280711405986, "eval_accuracy": 0.04322071083808688, "eval_loss_by_set": { "aqua_rat": 6.337461471557617, "gsm8k": 7.210353504527699, "math_qa": 5.9124406178792315 }, "eval_accuracy_by_set": { "aqua_rat": 0.08661417322834646, "gsm8k": 0.021986353297952996, "math_qa": 0.048911222780569516 } }, { "flos": 2.7511350565703516e+18, "train_loss": 5.4473583984375, "eval_loss": 6.306581858042124, "eval_accuracy": 0.04387889425186485, "eval_loss_by_set": { "aqua_rat": 6.341777801513672, "gsm8k": 7.192298195578835, "math_qa": 5.897695541381836 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.02350265352539803, "math_qa": 0.05025125628140704 } }, { "flos": 2.756622905935659e+18, "train_loss": 5.426509399414062, "eval_loss": 6.335066150974583, "eval_accuracy": 0.04387889425186485, "eval_loss_by_set": { "aqua_rat": 6.363663673400879, "gsm8k": 7.2133636474609375, "math_qa": 5.9301300048828125 }, "eval_accuracy_by_set": { "aqua_rat": 0.08267716535433071, "gsm8k": 0.021986353297952996, "math_qa": 0.05025125628140704 } }, { "flos": 2.762194527564333e+18, "train_loss": 5.440938720703125, "eval_loss": 6.347512064753352, "eval_accuracy": 0.04782799473453269, "eval_loss_by_set": { "aqua_rat": 6.37454891204834, "gsm8k": 7.236527182839134, "math_qa": 5.937793731689453 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.02577710386656558, "math_qa": 0.05494137353433836 } }, { "flos": 2.767713083798323e+18, "train_loss": 5.447625732421875, "eval_loss": 6.312421360531369, "eval_accuracy": 0.04387889425186485, "eval_loss_by_set": { "aqua_rat": 6.328135013580322, "gsm8k": 7.1837380149147725, "math_qa": 5.9117584228515625 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.029567854435178165, "math_qa": 0.047571189279731994 } }, { "flos": 2.7732886213634294e+18, "train_loss": 5.43972412109375, "eval_loss": 6.324646640468288, "eval_accuracy": 0.04629223343571742, "eval_loss_by_set": { "aqua_rat": 6.354465961456299, "gsm8k": 7.211832219904119, "math_qa": 5.915534973144531 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.02577710386656558, "math_qa": 0.053266331658291456 } }, { "flos": 2.7788292692985774e+18, "train_loss": 5.447620849609375, "eval_loss": 6.330914239625673, "eval_accuracy": 0.04826678367705134, "eval_loss_by_set": { "aqua_rat": 6.35829496383667, "gsm8k": 7.224839643998579, "math_qa": 5.918916702270508 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.02122820318423048, "math_qa": 0.05795644891122278 } }, { "flos": 2.7843524002096087e+18, "train_loss": 5.431702270507812, "eval_loss": 6.324739920126425, "eval_accuracy": 0.04322071083808688, "eval_loss_by_set": { "aqua_rat": 6.356531143188477, "gsm8k": 7.211118524724787, "math_qa": 5.915833791097005 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.02122820318423048, "math_qa": 0.05058626465661641 } }, { "flos": 2.7898942222814413e+18, "train_loss": 5.438353271484375, "eval_loss": 6.324903385059254, "eval_accuracy": 0.04300131636682756, "eval_loss_by_set": { "aqua_rat": 6.341813087463379, "gsm8k": 7.207028475674716, "math_qa": 5.919186909993489 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.025018953752843062, "math_qa": 0.048576214405360134 } }, { "flos": 2.7953818456240947e+18, "train_loss": 5.432070922851563, "eval_loss": 6.323666701445708, "eval_accuracy": 0.04234313295304958, "eval_loss_by_set": { "aqua_rat": 6.360842704772949, "gsm8k": 7.218916459517046, "math_qa": 5.910245895385742 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.027293404094010616, "math_qa": 0.04723618090452261 } }, { "flos": 2.8008839145523773e+18, "train_loss": 5.4389111328125, "eval_loss": 6.322598998611038, "eval_accuracy": 0.0443176831943835, "eval_loss_by_set": { "aqua_rat": 6.343745231628418, "gsm8k": 7.208440607244318, "math_qa": 5.914826075236003 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.02047005307050796, "math_qa": 0.05226130653266332 } }, { "flos": 2.806447972743643e+18, "train_loss": 5.446827392578125, "eval_loss": 6.313941904016443, "eval_accuracy": 0.04256252742430891, "eval_loss_by_set": { "aqua_rat": 6.3488874435424805, "gsm8k": 7.207455721768466, "math_qa": 5.90150260925293 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.02122820318423048, "math_qa": 0.048911222780569516 } }, { "flos": 2.811996905133834e+18, "train_loss": 5.44982666015625, "eval_loss": 6.3419296677048145, "eval_accuracy": 0.04278192189556823, "eval_loss_by_set": { "aqua_rat": 6.370491027832031, "gsm8k": 7.229640613902699, "math_qa": 5.932682037353516 }, "eval_accuracy_by_set": { "aqua_rat": 0.08267716535433071, "gsm8k": 0.022744503411675512, "math_qa": 0.04824120603015075 } }, { "flos": 2.817548598651126e+18, "train_loss": 5.44880615234375, "eval_loss": 6.326597651919803, "eval_accuracy": 0.04014918824045634, "eval_loss_by_set": { "aqua_rat": 6.359420299530029, "gsm8k": 7.227467623623935, "math_qa": 5.910963694254558 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.02122820318423048, "math_qa": 0.04522613065326633 } }, { "flos": 2.823057715620741e+18, "train_loss": 5.4347998046875, "eval_loss": 6.341458526817528, "eval_accuracy": 0.04212373848179026, "eval_loss_by_set": { "aqua_rat": 6.364822864532471, "gsm8k": 7.237295670942827, "math_qa": 5.9289194742838545 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.02577710386656558, "math_qa": 0.04723618090452261 } }, { "flos": 2.8286057616370565e+18, "train_loss": 5.4490087890625, "eval_loss": 6.3209856394174935, "eval_accuracy": 0.045414655550680125, "eval_loss_by_set": { "aqua_rat": 6.34821891784668, "gsm8k": 7.200345819646662, "math_qa": 5.915676116943359 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.022744503411675512, "math_qa": 0.0525963149078727 } }, { "flos": 2.834166770401542e+18, "train_loss": 5.44691650390625, "eval_loss": 6.323471765260439, "eval_accuracy": 0.041026766125493636, "eval_loss_by_set": { "aqua_rat": 6.344132900238037, "gsm8k": 7.203736045143821, "math_qa": 5.918295542399089 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.018953752843062926, "math_qa": 0.047906197654941376 } }, { "flos": 2.839725697717502e+18, "train_loss": 5.447489013671875, "eval_loss": 6.319655186421162, "eval_accuracy": 0.03949100482667837, "eval_loss_by_set": { "aqua_rat": 6.352280616760254, "gsm8k": 7.208608453924006, "math_qa": 5.909499486287435 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.02350265352539803, "math_qa": 0.044221105527638194 } }, { "flos": 2.8452080242917376e+18, "train_loss": 5.428018798828125, "eval_loss": 6.306926830394848, "eval_accuracy": 0.04475647213690215, "eval_loss_by_set": { "aqua_rat": 6.337779998779297, "gsm8k": 7.173784429376775, "math_qa": 5.907046000162761 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.02122820318423048, "math_qa": 0.05226130653266332 } }, { "flos": 2.850727054045872e+18, "train_loss": 5.431380004882812, "eval_loss": 6.3389248719086515, "eval_accuracy": 0.04914436156208864, "eval_loss_by_set": { "aqua_rat": 6.354674339294434, "gsm8k": 7.215265447443182, "math_qa": 5.935956319173177 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.026535253980288095, "math_qa": 0.05695142378559464 } }, { "flos": 2.856279098139869e+18, "train_loss": 5.446055908203125, "eval_loss": 6.319158708727038, "eval_accuracy": 0.0443176831943835, "eval_loss_by_set": { "aqua_rat": 6.335214614868164, "gsm8k": 7.190370039506392, "math_qa": 5.918515523274739 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.02350265352539803, "math_qa": 0.05125628140703518 } }, { "flos": 2.8617976951760486e+18, "train_loss": 5.4279833984375, "eval_loss": 6.3233333536096525, "eval_accuracy": 0.04190434401053093, "eval_loss_by_set": { "aqua_rat": 6.349483966827393, "gsm8k": 7.199559298428622, "math_qa": 5.9195505777994795 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.02047005307050796, "math_qa": 0.049916247906197656 } }, { "flos": 2.8673514497407713e+18, "train_loss": 5.432529296875, "eval_loss": 6.334754557222934, "eval_accuracy": 0.04278192189556823, "eval_loss_by_set": { "aqua_rat": 6.36259126663208, "gsm8k": 7.228917902166193, "math_qa": 5.922609965006511 }, "eval_accuracy_by_set": { "aqua_rat": 0.08267716535433071, "gsm8k": 0.021986353297952996, "math_qa": 0.048576214405360134 } }, { "flos": 2.872890695905968e+18, "train_loss": 5.43796142578125, "eval_loss": 6.335235544153162, "eval_accuracy": 0.0388328214129004, "eval_loss_by_set": { "aqua_rat": 6.362006187438965, "gsm8k": 7.212370439009233, "math_qa": 5.9309844970703125 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.02350265352539803, "math_qa": 0.04321608040201005 } }, { "flos": 2.8783657274782515e+18, "train_loss": 5.43713623046875, "eval_loss": 6.32623713725322, "eval_accuracy": 0.040807371654234315, "eval_loss_by_set": { "aqua_rat": 6.347585678100586, "gsm8k": 7.208478754216975, "math_qa": 5.920097351074219 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.017437452615617893, "math_qa": 0.049916247906197656 } }, { "flos": 2.883886241143587e+18, "train_loss": 5.42606201171875, "eval_loss": 6.3358639382027295, "eval_accuracy": 0.04300131636682756, "eval_loss_by_set": { "aqua_rat": 6.3595476150512695, "gsm8k": 7.229368730024858, "math_qa": 5.924367268880208 }, "eval_accuracy_by_set": { "aqua_rat": 0.09448818897637795, "gsm8k": 0.02047005307050796, "math_qa": 0.048576214405360134 } }, { "flos": 2.8893885785073254e+18, "train_loss": 5.426738891601563, "eval_loss": 6.346412478266536, "eval_accuracy": 0.03971039929793769, "eval_loss_by_set": { "aqua_rat": 6.376511096954346, "gsm8k": 7.236375288529829, "math_qa": 5.936004638671875 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.01819560272934041, "math_qa": 0.04623115577889447 } }, { "flos": 2.8949683197716726e+18, "train_loss": 5.44123779296875, "eval_loss": 6.322786047651961, "eval_accuracy": 0.0434401053093462, "eval_loss_by_set": { "aqua_rat": 6.349799633026123, "gsm8k": 7.204311024058949, "math_qa": 5.916502634684245 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.02350265352539803, "math_qa": 0.04958123953098827 } }, { "flos": 2.900487617424392e+18, "train_loss": 5.42525634765625, "eval_loss": 6.320734848847261, "eval_accuracy": 0.0443176831943835, "eval_loss_by_set": { "aqua_rat": 6.331219673156738, "gsm8k": 7.17859510941939, "math_qa": 5.926675160725911 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.02577710386656558, "math_qa": 0.049916247906197656 } }, { "flos": 2.9060800530014536e+18, "train_loss": 5.441395263671875, "eval_loss": 6.329969354577966, "eval_accuracy": 0.046511627906976744, "eval_loss_by_set": { "aqua_rat": 6.367277145385742, "gsm8k": 7.223633506081321, "math_qa": 5.917264302571614 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.017437452615617893, "math_qa": 0.05661641541038526 } }, { "flos": 2.9116035956924744e+18, "train_loss": 5.443275756835938, "eval_loss": 6.326543163608861, "eval_accuracy": 0.04300131636682756, "eval_loss_by_set": { "aqua_rat": 6.346571445465088, "gsm8k": 7.209054426713423, "math_qa": 5.920389811197917 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.02047005307050796, "math_qa": 0.05058626465661641 } }, { "flos": 2.917171919860007e+18, "train_loss": 5.4318896484375, "eval_loss": 6.343659014315219, "eval_accuracy": 0.04234313295304958, "eval_loss_by_set": { "aqua_rat": 6.367339134216309, "gsm8k": 7.236388466574929, "math_qa": 5.932518005371094 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.02047005307050796, "math_qa": 0.05025125628140704 } }, { "flos": 2.922704180260897e+18, "train_loss": 5.430947265625, "eval_loss": 6.317031911901526, "eval_accuracy": 0.03927161035541905, "eval_loss_by_set": { "aqua_rat": 6.340363502502441, "gsm8k": 7.1922760009765625, "math_qa": 5.913934071858724 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.019711902956785442, "math_qa": 0.04489112227805695 } }, { "flos": 2.9282320302672445e+18, "train_loss": 5.438165893554688, "eval_loss": 6.320730827950142, "eval_accuracy": 0.04256252742430891, "eval_loss_by_set": { "aqua_rat": 6.3510541915893555, "gsm8k": 7.215985384854403, "math_qa": 5.907878875732422 }, "eval_accuracy_by_set": { "aqua_rat": 0.09055118110236221, "gsm8k": 0.018953752843062926, "math_qa": 0.048911222780569516 } }, { "flos": 2.933767464112095e+18, "train_loss": 5.4329156494140625, "eval_loss": 6.341243125296928, "eval_accuracy": 0.04322071083808688, "eval_loss_by_set": { "aqua_rat": 6.366277694702148, "gsm8k": 7.23403583873402, "math_qa": 5.929960250854492 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.02350265352539803, "math_qa": 0.05058626465661641 } }, { "flos": 2.9393114916496343e+18, "train_loss": 5.4313507080078125, "eval_loss": 6.3257236996212525, "eval_accuracy": 0.04256252742430891, "eval_loss_by_set": { "aqua_rat": 6.352479934692383, "gsm8k": 7.209919322620738, "math_qa": 5.918237686157227 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.019711902956785442, "math_qa": 0.05125628140703518 } }, { "flos": 2.944795446553346e+18, "train_loss": 5.42647216796875, "eval_loss": 6.340079487981023, "eval_accuracy": 0.04212373848179026, "eval_loss_by_set": { "aqua_rat": 6.371148109436035, "gsm8k": 7.233915155584162, "math_qa": 5.927815755208333 }, "eval_accuracy_by_set": { "aqua_rat": 0.09055118110236221, "gsm8k": 0.021986353297952996, "math_qa": 0.04690117252931323 } }, { "flos": 2.950307036350382e+18, "train_loss": 5.426798095703125, "eval_loss": 6.309025687140387, "eval_accuracy": 0.0434401053093462, "eval_loss_by_set": { "aqua_rat": 6.318060874938965, "gsm8k": 7.185360301624645, "math_qa": 5.906619389851888 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.016679302501895376, "math_qa": 0.05226130653266332 } }, { "flos": 2.9558060145128243e+18, "train_loss": 5.4229443359375, "eval_loss": 6.355608012225177, "eval_accuracy": 0.0443176831943835, "eval_loss_by_set": { "aqua_rat": 6.384339809417725, "gsm8k": 7.259314103560015, "math_qa": 5.939015070597331 }, "eval_accuracy_by_set": { "aqua_rat": 0.09448818897637795, "gsm8k": 0.019711902956785442, "math_qa": 0.050921273031825795 } }, { "flos": 2.961374647918002e+18, "train_loss": 5.438258666992187, "eval_loss": 6.344742852288324, "eval_accuracy": 0.04673102237823607, "eval_loss_by_set": { "aqua_rat": 6.370258331298828, "gsm8k": 7.232915704900568, "math_qa": 5.935537338256836 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.022744503411675512, "math_qa": 0.05561139028475712 } }, { "flos": 2.96691488353629e+18, "train_loss": 5.4330078125, "eval_loss": 6.334821649499841, "eval_accuracy": 0.03905221588415972, "eval_loss_by_set": { "aqua_rat": 6.366861343383789, "gsm8k": 7.222996104847301, "math_qa": 5.925071716308594 }, "eval_accuracy_by_set": { "aqua_rat": 0.09055118110236221, "gsm8k": 0.022744503411675512, "math_qa": 0.04187604690117253 } }, { "flos": 2.972396365612581e+18, "train_loss": 5.413983154296875, "eval_loss": 6.330671052674989, "eval_accuracy": 0.03861342694164107, "eval_loss_by_set": { "aqua_rat": 6.353654861450195, "gsm8k": 7.221325267444957, "math_qa": 5.920539220174153 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.019711902956785442, "math_qa": 0.04388609715242881 } }, { "flos": 2.977887780874486e+18, "train_loss": 5.435949096679687, "eval_loss": 6.3283775948189405, "eval_accuracy": 0.04322071083808688, "eval_loss_by_set": { "aqua_rat": 6.344932556152344, "gsm8k": 7.230486089533025, "math_qa": 5.9135316212972 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.02350265352539803, "math_qa": 0.049916247906197656 } }, { "flos": 2.983449798956286e+18, "train_loss": 5.437428588867188, "eval_loss": 6.330971228109823, "eval_accuracy": 0.04322071083808688, "eval_loss_by_set": { "aqua_rat": 6.360321998596191, "gsm8k": 7.226264953613281, "math_qa": 5.918182373046875 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.02047005307050796, "math_qa": 0.050921273031825795 } }, { "flos": 2.988999287544742e+18, "train_loss": 5.434364013671875, "eval_loss": 6.338675730937236, "eval_accuracy": 0.044975866608161476, "eval_loss_by_set": { "aqua_rat": 6.358304977416992, "gsm8k": 7.227143721147017, "math_qa": 5.92982546488444 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.019711902956785442, "math_qa": 0.053266331658291456 } }, { "flos": 2.9945239845082235e+18, "train_loss": 5.434201049804687, "eval_loss": 6.329394108540303, "eval_accuracy": 0.04365949978060553, "eval_loss_by_set": { "aqua_rat": 6.356348991394043, "gsm8k": 7.2276999733664775, "math_qa": 5.915424346923828 }, "eval_accuracy_by_set": { "aqua_rat": 0.09448818897637795, "gsm8k": 0.021986353297952996, "math_qa": 0.048911222780569516 } }, { "flos": 3.000053256685617e+18, "train_loss": 5.450205078125, "eval_loss": 6.350767419144914, "eval_accuracy": 0.040368582711715666, "eval_loss_by_set": { "aqua_rat": 6.379086017608643, "gsm8k": 7.249487443403765, "math_qa": 5.93649419148763 }, "eval_accuracy_by_set": { "aqua_rat": 0.08661417322834646, "gsm8k": 0.017437452615617893, "math_qa": 0.046566164154103855 } }, { "flos": 3.0056214783108055e+18, "train_loss": 5.443775024414062, "eval_loss": 6.348816278818491, "eval_accuracy": 0.045414655550680125, "eval_loss_by_set": { "aqua_rat": 6.384360313415527, "gsm8k": 7.2484657981178975, "math_qa": 5.933514912923177 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.019711902956785442, "math_qa": 0.054271356783919596 } }, { "flos": 3.01112709219772e+18, "train_loss": 5.425498046875, "eval_loss": 6.325499225307155, "eval_accuracy": 0.04365949978060553, "eval_loss_by_set": { "aqua_rat": 6.3522257804870605, "gsm8k": 7.218134099786932, "math_qa": 5.914147694905599 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.025018953752843062, "math_qa": 0.04924623115577889 } }, { "flos": 3.016661248826671e+18, "train_loss": 5.43806396484375, "eval_loss": 6.32797215435956, "eval_accuracy": 0.04168494953927161, "eval_loss_by_set": { "aqua_rat": 6.342963218688965, "gsm8k": 7.207091591574929, "math_qa": 5.9237931569417315 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.02350265352539803, "math_qa": 0.04690117252931323 } }, { "flos": 3.02222005212545e+18, "train_loss": 5.434689331054687, "eval_loss": 6.332239176775958, "eval_accuracy": 0.04365949978060553, "eval_loss_by_set": { "aqua_rat": 6.3480353355407715, "gsm8k": 7.21198827570135, "math_qa": 5.927704493204753 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.021986353297952996, "math_qa": 0.05125628140703518 } }, { "flos": 3.0277729616553574e+18, "train_loss": 5.44435302734375, "eval_loss": 6.334199235245988, "eval_accuracy": 0.04629223343571742, "eval_loss_by_set": { "aqua_rat": 6.356330871582031, "gsm8k": 7.224211259321733, "math_qa": 5.924432754516602 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.021986353297952996, "math_qa": 0.05460636515912898 } }, { "flos": 3.033302254233846e+18, "train_loss": 5.440316162109375, "eval_loss": 6.3378560865247575, "eval_accuracy": 0.04168494953927161, "eval_loss_by_set": { "aqua_rat": 6.363969802856445, "gsm8k": 7.233051646839488, "math_qa": 5.925381978352864 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.018953752843062926, "math_qa": 0.04924623115577889 } }, { "flos": 3.038893824911868e+18, "train_loss": 5.443402099609375, "eval_loss": 6.330795468510808, "eval_accuracy": 0.04365949978060553, "eval_loss_by_set": { "aqua_rat": 6.350902080535889, "gsm8k": 7.210415926846591, "math_qa": 5.925960540771484 }, "eval_accuracy_by_set": { "aqua_rat": 0.09055118110236221, "gsm8k": 0.022744503411675512, "math_qa": 0.048911222780569516 } }, { "flos": 3.0443963888351314e+18, "train_loss": 5.436068725585938, "eval_loss": 6.320318531345677, "eval_accuracy": 0.0451952610794208, "eval_loss_by_set": { "aqua_rat": 6.354252815246582, "gsm8k": 7.213654951615767, "math_qa": 5.908044815063477 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.02350265352539803, "math_qa": 0.0525963149078727 } }, { "flos": 3.049985877527757e+18, "train_loss": 5.4431494140625, "eval_loss": 6.333621153960356, "eval_accuracy": 0.04300131636682756, "eval_loss_by_set": { "aqua_rat": 6.356359481811523, "gsm8k": 7.204940102317116, "math_qa": 5.932371775309245 }, "eval_accuracy_by_set": { "aqua_rat": 0.08267716535433071, "gsm8k": 0.022744503411675512, "math_qa": 0.048576214405360134 } }, { "flos": 3.055511790503854e+18, "train_loss": 5.438467407226563, "eval_loss": 6.329581415331042, "eval_accuracy": 0.041026766125493636, "eval_loss_by_set": { "aqua_rat": 6.363743305206299, "gsm8k": 7.210454767400568, "math_qa": 5.923000971476237 }, "eval_accuracy_by_set": { "aqua_rat": 0.08661417322834646, "gsm8k": 0.02122820318423048, "math_qa": 0.04589614740368509 } }, { "flos": 3.06107420050142e+18, "train_loss": 5.435392456054688, "eval_loss": 6.343019021523966, "eval_accuracy": 0.040368582711715666, "eval_loss_by_set": { "aqua_rat": 6.369651794433594, "gsm8k": 7.232981595126065, "math_qa": 5.932900110880534 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.024260803639120546, "math_qa": 0.04589614740368509 } }, { "flos": 3.0666354975655854e+18, "train_loss": 5.4417578125, "eval_loss": 6.353698833568676, "eval_accuracy": 0.04212373848179026, "eval_loss_by_set": { "aqua_rat": 6.378328323364258, "gsm8k": 7.240651910955256, "math_qa": 5.945126215616862 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.02122820318423048, "math_qa": 0.04824120603015075 } }, { "flos": 3.0721897261873234e+18, "train_loss": 5.437515869140625, "eval_loss": 6.32433625814077, "eval_accuracy": 0.04234313295304958, "eval_loss_by_set": { "aqua_rat": 6.3533549308776855, "gsm8k": 7.21551513671875, "math_qa": 5.913461049397786 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.02047005307050796, "math_qa": 0.04958123953098827 } }, { "flos": 3.0777297760482755e+18, "train_loss": 5.431866455078125, "eval_loss": 6.3278494912224845, "eval_accuracy": 0.041026766125493636, "eval_loss_by_set": { "aqua_rat": 6.36159086227417, "gsm8k": 7.215496410023082, "math_qa": 5.91819953918457 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.024260803639120546, "math_qa": 0.04589614740368509 } }, { "flos": 3.0832295783075676e+18, "train_loss": 5.42412841796875, "eval_loss": 6.339948963474583, "eval_accuracy": 0.04782799473453269, "eval_loss_by_set": { "aqua_rat": 6.37404727935791, "gsm8k": 7.237468372691762, "math_qa": 5.925744374593099 }, "eval_accuracy_by_set": { "aqua_rat": 0.08661417322834646, "gsm8k": 0.025018953752843062, "math_qa": 0.05460636515912898 } }, { "flos": 3.088780179829424e+18, "train_loss": 5.43157958984375, "eval_loss": 6.333776113149282, "eval_accuracy": 0.04629223343571742, "eval_loss_by_set": { "aqua_rat": 6.362216949462891, "gsm8k": 7.223872098055753, "math_qa": 5.923445383707683 }, "eval_accuracy_by_set": { "aqua_rat": 0.08267716535433071, "gsm8k": 0.017437452615617893, "math_qa": 0.0559463986599665 } }, { "flos": 3.0943089779498025e+18, "train_loss": 5.425355834960937, "eval_loss": 6.358014802674989, "eval_accuracy": 0.04300131636682756, "eval_loss_by_set": { "aqua_rat": 6.386682510375977, "gsm8k": 7.24934179132635, "math_qa": 5.9471009572347 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.018953752843062926, "math_qa": 0.053266331658291456 } }, { "flos": 3.0998281934612726e+18, "train_loss": 5.433675537109375, "eval_loss": 6.349267856494801, "eval_accuracy": 0.0451952610794208, "eval_loss_by_set": { "aqua_rat": 6.384673118591309, "gsm8k": 7.236210216175426, "math_qa": 5.939802169799805 }, "eval_accuracy_by_set": { "aqua_rat": 0.08661417322834646, "gsm8k": 0.02577710386656558, "math_qa": 0.05025125628140704 } }, { "flos": 3.1053466047401165e+18, "train_loss": 5.435457763671875, "eval_loss": 6.3316969742646085, "eval_accuracy": 0.04256252742430891, "eval_loss_by_set": { "aqua_rat": 6.35683012008667, "gsm8k": 7.213785344904119, "math_qa": 5.925312042236328 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.021986353297952996, "math_qa": 0.04924623115577889 } }, { "flos": 3.1108697560522424e+18, "train_loss": 5.433941650390625, "eval_loss": 6.3284166181409685, "eval_accuracy": 0.0443176831943835, "eval_loss_by_set": { "aqua_rat": 6.34615421295166, "gsm8k": 7.217100663618608, "math_qa": 5.919624964396159 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.018953752843062926, "math_qa": 0.052931323283082074 } }, { "flos": 3.116391959250338e+18, "train_loss": 5.431695556640625, "eval_loss": 6.349067894188133, "eval_accuracy": 0.04782799473453269, "eval_loss_by_set": { "aqua_rat": 6.380542755126953, "gsm8k": 7.239982604980469, "math_qa": 5.938109079996745 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.021986353297952996, "math_qa": 0.05728643216080402 } }, { "flos": 3.121977573882462e+18, "train_loss": 5.438585205078125, "eval_loss": 6.325198225072913, "eval_accuracy": 0.041246160596752963, "eval_loss_by_set": { "aqua_rat": 6.360832691192627, "gsm8k": 7.220144098455256, "math_qa": 5.912045160929362 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.022744503411675512, "math_qa": 0.04824120603015075 } }, { "flos": 3.1275410554743685e+18, "train_loss": 5.43281982421875, "eval_loss": 6.361699078534101, "eval_accuracy": 0.04058797718297499, "eval_loss_by_set": { "aqua_rat": 6.3914947509765625, "gsm8k": 7.269921736283735, "math_qa": 5.9429473876953125 }, "eval_accuracy_by_set": { "aqua_rat": 0.08267716535433071, "gsm8k": 0.016679302501895376, "math_qa": 0.047571189279731994 } }, { "flos": 3.1330649278041293e+18, "train_loss": 5.422867431640625, "eval_loss": 6.339689564060521, "eval_accuracy": 0.040807371654234315, "eval_loss_by_set": { "aqua_rat": 6.383225440979004, "gsm8k": 7.237383755770597, "math_qa": 5.924618403116862 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.015163002274450341, "math_qa": 0.05058626465661641 } }, { "flos": 3.138642237043245e+18, "train_loss": 5.427957763671875, "eval_loss": 6.358494062681456, "eval_accuracy": 0.04365949978060553, "eval_loss_by_set": { "aqua_rat": 6.394560813903809, "gsm8k": 7.251459295099432, "math_qa": 5.9462127685546875 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.01819560272934041, "math_qa": 0.052931323283082074 } }, { "flos": 3.14421501294438e+18, "train_loss": 5.445001831054688, "eval_loss": 6.368471506479624, "eval_accuracy": 0.04409828872312418, "eval_loss_by_set": { "aqua_rat": 6.395843505859375, "gsm8k": 7.265043085271662, "math_qa": 5.955261866251628 }, "eval_accuracy_by_set": { "aqua_rat": 0.08267716535433071, "gsm8k": 0.02047005307050796, "math_qa": 0.05125628140703518 } }, { "flos": 3.149760255957664e+18, "train_loss": 5.439005737304687, "eval_loss": 6.348770064276618, "eval_accuracy": 0.04300131636682756, "eval_loss_by_set": { "aqua_rat": 6.395544528961182, "gsm8k": 7.2473532936789775, "math_qa": 5.933021545410156 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.01819560272934041, "math_qa": 0.05226130653266332 } }, { "flos": 3.1552894250558423e+18, "train_loss": 5.4296337890625, "eval_loss": 6.341281246494603, "eval_accuracy": 0.04695041684949539, "eval_loss_by_set": { "aqua_rat": 6.364083766937256, "gsm8k": 7.224703008478338, "math_qa": 5.934479395548503 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.02350265352539803, "math_qa": 0.05460636515912898 } }, { "flos": 3.1608039005340303e+18, "train_loss": 5.42648193359375, "eval_loss": 6.347135775798076, "eval_accuracy": 0.04387889425186485, "eval_loss_by_set": { "aqua_rat": 6.385436534881592, "gsm8k": 7.241144353693182, "math_qa": 5.934190114339192 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.02047005307050796, "math_qa": 0.05226130653266332 } }, { "flos": 3.1663534718006067e+18, "train_loss": 5.442657470703125, "eval_loss": 6.329491048245816, "eval_accuracy": 0.04278192189556823, "eval_loss_by_set": { "aqua_rat": 6.3724894523620605, "gsm8k": 7.221404335715554, "math_qa": 5.9171142578125 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.028051554207733132, "math_qa": 0.048576214405360134 } }, { "flos": 3.171881012569309e+18, "train_loss": 5.4344580078125, "eval_loss": 6.353544802279086, "eval_accuracy": 0.03992979376919702, "eval_loss_by_set": { "aqua_rat": 6.39158821105957, "gsm8k": 7.24779649214311, "math_qa": 5.9405091603597 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.019711902956785442, "math_qa": 0.04589614740368509 } }, { "flos": 3.1774205056951255e+18, "train_loss": 5.421739501953125, "eval_loss": 6.3495282095831795, "eval_accuracy": 0.04212373848179026, "eval_loss_by_set": { "aqua_rat": 6.384988307952881, "gsm8k": 7.24566650390625, "math_qa": 5.935843149820964 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.01819560272934041, "math_qa": 0.05058626465661641 } }, { "flos": 3.182935393490174e+18, "train_loss": 5.4351739501953125, "eval_loss": 6.344406024829762, "eval_accuracy": 0.04892496709082931, "eval_loss_by_set": { "aqua_rat": 6.367773056030273, "gsm8k": 7.228067571466619, "math_qa": 5.937447230021159 }, "eval_accuracy_by_set": { "aqua_rat": 0.0984251968503937, "gsm8k": 0.028051554207733132, "math_qa": 0.05393634840871022 } }, { "flos": 3.188453475130278e+18, "train_loss": 5.420572509765625, "eval_loss": 6.357030404580606, "eval_accuracy": 0.044975866608161476, "eval_loss_by_set": { "aqua_rat": 6.390104293823242, "gsm8k": 7.244741266424006, "math_qa": 5.947406768798828 }, "eval_accuracy_by_set": { "aqua_rat": 0.10236220472440945, "gsm8k": 0.022744503411675512, "math_qa": 0.049916247906197656 } }, { "flos": 3.193994947162276e+18, "train_loss": 5.426647338867188, "eval_loss": 6.353331179232211, "eval_accuracy": 0.04256252742430891, "eval_loss_by_set": { "aqua_rat": 6.39427375793457, "gsm8k": 7.257983814586293, "math_qa": 5.93528683980306 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.024260803639120546, "math_qa": 0.047906197654941376 } }, { "flos": 3.1995273723825357e+18, "train_loss": 5.439571533203125, "eval_loss": 6.339899836359797, "eval_accuracy": 0.041026766125493636, "eval_loss_by_set": { "aqua_rat": 6.363319396972656, "gsm8k": 7.22840049050071, "math_qa": 5.930718739827474 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.021986353297952996, "math_qa": 0.04623115577889447 } }, { "flos": 3.205041930001973e+18, "train_loss": 5.424683227539062, "eval_loss": 6.35932716163429, "eval_accuracy": 0.04256252742430891, "eval_loss_by_set": { "aqua_rat": 6.3936920166015625, "gsm8k": 7.2659912109375, "math_qa": 5.940909067789714 }, "eval_accuracy_by_set": { "aqua_rat": 0.08267716535433071, "gsm8k": 0.021986353297952996, "math_qa": 0.04824120603015075 } }, { "flos": 3.2106182916639293e+18, "train_loss": 5.44046142578125, "eval_loss": 6.345128600661819, "eval_accuracy": 0.04234313295304958, "eval_loss_by_set": { "aqua_rat": 6.369433403015137, "gsm8k": 7.235267639160156, "math_qa": 5.935122807820638 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.021986353297952996, "math_qa": 0.048576214405360134 } }, { "flos": 3.2161549619224904e+18, "train_loss": 5.429779052734375, "eval_loss": 6.340953620704445, "eval_accuracy": 0.04168494953927161, "eval_loss_by_set": { "aqua_rat": 6.365213394165039, "gsm8k": 7.244645552201704, "math_qa": 5.924739837646484 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.019711902956785442, "math_qa": 0.04924623115577889 } }, { "flos": 3.2216754755878257e+18, "train_loss": 5.431697998046875, "eval_loss": 6.354849738043708, "eval_accuracy": 0.04212373848179026, "eval_loss_by_set": { "aqua_rat": 6.377559661865234, "gsm8k": 7.247261047363281, "math_qa": 5.943935394287109 }, "eval_accuracy_by_set": { "aqua_rat": 0.08267716535433071, "gsm8k": 0.022744503411675512, "math_qa": 0.04723618090452261 } }, { "flos": 3.227205530523009e+18, "train_loss": 5.42727294921875, "eval_loss": 6.338854351559201, "eval_accuracy": 0.0451952610794208, "eval_loss_by_set": { "aqua_rat": 6.364558219909668, "gsm8k": 7.226049943403765, "math_qa": 5.930081049601237 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.024260803639120546, "math_qa": 0.05159128978224456 } }, { "flos": 3.232757636357161e+18, "train_loss": 5.430083618164063, "eval_loss": 6.3399652017129435, "eval_accuracy": 0.045634050021939446, "eval_loss_by_set": { "aqua_rat": 6.372535705566406, "gsm8k": 7.232899752530185, "math_qa": 5.927989323933919 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.024260803639120546, "math_qa": 0.05226130653266332 } }, { "flos": 3.23826121013461e+18, "train_loss": 5.431099853515625, "eval_loss": 6.340127017046954, "eval_accuracy": 0.036858271171566474, "eval_loss_by_set": { "aqua_rat": 6.364897727966309, "gsm8k": 7.233524669300426, "math_qa": 5.9285888671875 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.018953752843062926, "math_qa": 0.04254606365159129 } }, { "flos": 3.2437767362691727e+18, "train_loss": 5.429647827148438, "eval_loss": 6.349573805525496, "eval_accuracy": 0.04212373848179026, "eval_loss_by_set": { "aqua_rat": 6.381536483764648, "gsm8k": 7.2440573952414775, "math_qa": 5.936938603719075 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.025018953752843062, "math_qa": 0.047571189279731994 } }, { "flos": 3.2493658330460324e+18, "train_loss": 5.447823486328125, "eval_loss": 6.357394553519584, "eval_accuracy": 0.04409828872312418, "eval_loss_by_set": { "aqua_rat": 6.386781692504883, "gsm8k": 7.25974551114169, "math_qa": 5.941368103027344 }, "eval_accuracy_by_set": { "aqua_rat": 0.08661417322834646, "gsm8k": 0.02350265352539803, "math_qa": 0.04958123953098827 } }, { "flos": 3.2549238122479616e+18, "train_loss": 5.43475341796875, "eval_loss": 6.342446146784602, "eval_accuracy": 0.04760860026327336, "eval_loss_by_set": { "aqua_rat": 6.375582695007324, "gsm8k": 7.235185102982954, "math_qa": 5.93051274617513 }, "eval_accuracy_by_set": { "aqua_rat": 0.09055118110236221, "gsm8k": 0.02350265352539803, "math_qa": 0.05460636515912898 } }, { "flos": 3.2604162577651466e+18, "train_loss": 5.429605712890625, "eval_loss": 6.344875026393581, "eval_accuracy": 0.04190434401053093, "eval_loss_by_set": { "aqua_rat": 6.371818542480469, "gsm8k": 7.232020984996449, "math_qa": 5.936021169026692 }, "eval_accuracy_by_set": { "aqua_rat": 0.08267716535433071, "gsm8k": 0.02047005307050796, "math_qa": 0.047906197654941376 } }, { "flos": 3.266006282254942e+18, "train_loss": 5.437955322265625, "eval_loss": 6.354206600704709, "eval_accuracy": 0.04234313295304958, "eval_loss_by_set": { "aqua_rat": 6.398769378662109, "gsm8k": 7.255321155894887, "math_qa": 5.937482198079427 }, "eval_accuracy_by_set": { "aqua_rat": 0.08661417322834646, "gsm8k": 0.01819560272934041, "math_qa": 0.04924623115577889 } }, { "flos": 3.271542540196643e+18, "train_loss": 5.431285400390625, "eval_loss": 6.3421266143386426, "eval_accuracy": 0.0434401053093462, "eval_loss_by_set": { "aqua_rat": 6.370502948760986, "gsm8k": 7.228694568980824, "math_qa": 5.933418273925781 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.01819560272934041, "math_qa": 0.05159128978224456 } }, { "flos": 3.27709355403536e+18, "train_loss": 5.43432861328125, "eval_loss": 6.350933281151024, "eval_accuracy": 0.04629223343571742, "eval_loss_by_set": { "aqua_rat": 6.38038444519043, "gsm8k": 7.24791856245561, "math_qa": 5.937360763549805 }, "eval_accuracy_by_set": { "aqua_rat": 0.09055118110236221, "gsm8k": 0.02122820318423048, "math_qa": 0.05360134003350084 } }, { "flos": 3.282641929690415e+18, "train_loss": 5.424346923828125, "eval_loss": 6.330374537287532, "eval_accuracy": 0.041026766125493636, "eval_loss_by_set": { "aqua_rat": 6.357549667358398, "gsm8k": 7.2142417214133525, "math_qa": 5.923004150390625 }, "eval_accuracy_by_set": { "aqua_rat": 0.08267716535433071, "gsm8k": 0.017437452615617893, "math_qa": 0.047906197654941376 } }, { "flos": 3.288166997631697e+18, "train_loss": 5.43313720703125, "eval_loss": 6.340230168523015, "eval_accuracy": 0.041026766125493636, "eval_loss_by_set": { "aqua_rat": 6.3677825927734375, "gsm8k": 7.23688437721946, "math_qa": 5.926967620849609 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.018953752843062926, "math_qa": 0.048576214405360134 } }, { "flos": 3.293675681883357e+18, "train_loss": 5.4340625, "eval_loss": 6.354538994866449, "eval_accuracy": 0.044975866608161476, "eval_loss_by_set": { "aqua_rat": 6.382118225097656, "gsm8k": 7.253403403542259, "math_qa": 5.940261205037435 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.022744503411675512, "math_qa": 0.0525963149078727 } }, { "flos": 3.299183562439262e+18, "train_loss": 5.421400146484375, "eval_loss": 6.3482708544344515, "eval_accuracy": 0.04256252742430891, "eval_loss_by_set": { "aqua_rat": 6.38671350479126, "gsm8k": 7.25196006081321, "math_qa": 5.93087641398112 }, "eval_accuracy_by_set": { "aqua_rat": 0.08267716535433071, "gsm8k": 0.019711902956785442, "math_qa": 0.04924623115577889 } }, { "flos": 3.30471137110655e+18, "train_loss": 5.428482666015625, "eval_loss": 6.350519979322279, "eval_accuracy": 0.04475647213690215, "eval_loss_by_set": { "aqua_rat": 6.380177021026611, "gsm8k": 7.24709736217152, "math_qa": 5.937117258707683 }, "eval_accuracy_by_set": { "aqua_rat": 0.10236220472440945, "gsm8k": 0.02047005307050796, "math_qa": 0.05058626465661641 } }, { "flos": 3.3102221577447014e+18, "train_loss": 5.425987548828125, "eval_loss": 6.344611374107567, "eval_accuracy": 0.04168494953927161, "eval_loss_by_set": { "aqua_rat": 6.371469020843506, "gsm8k": 7.244758605957031, "math_qa": 5.929805755615234 }, "eval_accuracy_by_set": { "aqua_rat": 0.09055118110236221, "gsm8k": 0.01592115238817286, "math_qa": 0.048911222780569516 } }, { "flos": 3.315740322062926e+18, "train_loss": 5.4255517578125, "eval_loss": 6.358769236384211, "eval_accuracy": 0.04673102237823607, "eval_loss_by_set": { "aqua_rat": 6.388741493225098, "gsm8k": 7.259518710049716, "math_qa": 5.943428039550781 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.019711902956785442, "math_qa": 0.0559463986599665 } }, { "flos": 3.321277425039442e+18, "train_loss": 5.427535400390625, "eval_loss": 6.363886291916306, "eval_accuracy": 0.04365949978060553, "eval_loss_by_set": { "aqua_rat": 6.401768684387207, "gsm8k": 7.261970520019531, "math_qa": 5.949107487996419 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.01819560272934041, "math_qa": 0.05226130653266332 } }, { "flos": 3.3267472634593935e+18, "train_loss": 5.40984130859375, "eval_loss": 6.353506552206503, "eval_accuracy": 0.04300131636682756, "eval_loss_by_set": { "aqua_rat": 6.377960205078125, "gsm8k": 7.252655029296875, "math_qa": 5.939359029134114 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.022744503411675512, "math_qa": 0.04924623115577889 } }, { "flos": 3.3322946705993236e+18, "train_loss": 5.437589721679688, "eval_loss": 6.347535726186392, "eval_accuracy": 0.04629223343571742, "eval_loss_by_set": { "aqua_rat": 6.372213363647461, "gsm8k": 7.234881314364347, "math_qa": 5.938779195149739 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.019711902956785442, "math_qa": 0.05527638190954774 } }, { "flos": 3.3378937419008573e+18, "train_loss": 5.438416748046875, "eval_loss": 6.346644066475533, "eval_accuracy": 0.04387889425186485, "eval_loss_by_set": { "aqua_rat": 6.3721208572387695, "gsm8k": 7.245310003107244, "math_qa": 5.9326324462890625 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.02047005307050796, "math_qa": 0.051926298157453935 } }, { "flos": 3.343359870542807e+18, "train_loss": 5.4178076171875, "eval_loss": 6.347674601786846, "eval_accuracy": 0.046072838964458095, "eval_loss_by_set": { "aqua_rat": 6.377799987792969, "gsm8k": 7.240486145019531, "math_qa": 5.9359588623046875 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.01819560272934041, "math_qa": 0.05661641541038526 } }, { "flos": 3.3489460209721016e+18, "train_loss": 5.445382080078125, "eval_loss": 6.363227689588392, "eval_accuracy": 0.045634050021939446, "eval_loss_by_set": { "aqua_rat": 6.399968147277832, "gsm8k": 7.26198994029652, "math_qa": 5.948233286539714 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.022744503411675512, "math_qa": 0.052931323283082074 } }, { "flos": 3.354523722126983e+18, "train_loss": 5.448060913085937, "eval_loss": 6.349843514932169, "eval_accuracy": 0.04870557261956999, "eval_loss_by_set": { "aqua_rat": 6.373395919799805, "gsm8k": 7.237437855113637, "math_qa": 5.941066741943359 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.024260803639120546, "math_qa": 0.05728643216080402 } }, { "flos": 3.360070057672573e+18, "train_loss": 5.429219970703125, "eval_loss": 6.360587893305598, "eval_accuracy": 0.04190434401053093, "eval_loss_by_set": { "aqua_rat": 6.397705554962158, "gsm8k": 7.262602372602983, "math_qa": 5.944071451822917 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.018953752843062926, "math_qa": 0.04958123953098827 } }, { "flos": 3.3656673363621315e+18, "train_loss": 5.440103759765625, "eval_loss": 6.3646104657972185, "eval_accuracy": 0.045414655550680125, "eval_loss_by_set": { "aqua_rat": 6.4007768630981445, "gsm8k": 7.261412880637429, "math_qa": 5.950562159220378 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.019711902956785442, "math_qa": 0.05393634840871022 } }, { "flos": 3.371188262344327e+18, "train_loss": 5.4296923828125, "eval_loss": 6.362217980462152, "eval_accuracy": 0.04278192189556823, "eval_loss_by_set": { "aqua_rat": 6.393144607543945, "gsm8k": 7.262099526145241, "math_qa": 5.947195053100586 }, "eval_accuracy_by_set": { "aqua_rat": 0.09055118110236221, "gsm8k": 0.022744503411675512, "math_qa": 0.047571189279731994 } }, { "flos": 3.3767351744892764e+18, "train_loss": 5.42864501953125, "eval_loss": 6.369702055647567, "eval_accuracy": 0.04804738920579201, "eval_loss_by_set": { "aqua_rat": 6.400843620300293, "gsm8k": 7.276422674005682, "math_qa": 5.951526641845703 }, "eval_accuracy_by_set": { "aqua_rat": 0.09448818897637795, "gsm8k": 0.027293404094010616, "math_qa": 0.053266331658291456 } }, { "flos": 3.38227856315043e+18, "train_loss": 5.42738525390625, "eval_loss": 6.355919915276605, "eval_accuracy": 0.04300131636682756, "eval_loss_by_set": { "aqua_rat": 6.390476226806641, "gsm8k": 7.257924166592685, "math_qa": 5.939621607462565 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.019711902956785442, "math_qa": 0.05058626465661641 } }, { "flos": 3.387828484456841e+18, "train_loss": 5.43251220703125, "eval_loss": 6.365809492162756, "eval_accuracy": 0.04190434401053093, "eval_loss_by_set": { "aqua_rat": 6.406944751739502, "gsm8k": 7.267885381525213, "math_qa": 5.948930104573567 }, "eval_accuracy_by_set": { "aqua_rat": 0.08267716535433071, "gsm8k": 0.02122820318423048, "math_qa": 0.047571189279731994 } }, { "flos": 3.393353923375923e+18, "train_loss": 5.428033447265625, "eval_loss": 6.353851318359375, "eval_accuracy": 0.04278192189556823, "eval_loss_by_set": { "aqua_rat": 6.384880065917969, "gsm8k": 7.248902754350142, "math_qa": 5.941033681233724 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.02350265352539803, "math_qa": 0.048911222780569516 } }, { "flos": 3.398918208663585e+18, "train_loss": 5.4279931640625, "eval_loss": 6.358609070649019, "eval_accuracy": 0.044975866608161476, "eval_loss_by_set": { "aqua_rat": 6.390588760375977, "gsm8k": 7.25629286332564, "math_qa": 5.94450569152832 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.01819560272934041, "math_qa": 0.05494137353433836 } }, { "flos": 3.4044765996455035e+18, "train_loss": 5.434534912109375, "eval_loss": 6.3502018645003036, "eval_accuracy": 0.04300131636682756, "eval_loss_by_set": { "aqua_rat": 6.374841213226318, "gsm8k": 7.239379189231179, "math_qa": 5.940608978271484 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.018953752843062926, "math_qa": 0.05159128978224456 } }, { "flos": 3.4100366602959585e+18, "train_loss": 5.431773681640625, "eval_loss": 6.3518049910261825, "eval_accuracy": 0.04629223343571742, "eval_loss_by_set": { "aqua_rat": 6.38360595703125, "gsm8k": 7.2505881569602275, "math_qa": 5.937212626139323 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.02350265352539803, "math_qa": 0.054271356783919596 } }, { "flos": 3.4155863754439393e+18, "train_loss": 5.43342041015625, "eval_loss": 6.361211647858491, "eval_accuracy": 0.04365949978060553, "eval_loss_by_set": { "aqua_rat": 6.38566255569458, "gsm8k": 7.256306041370738, "math_qa": 5.948922475179036 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.02122820318423048, "math_qa": 0.05226130653266332 } }, { "flos": 3.4211006861027574e+18, "train_loss": 5.42015869140625, "eval_loss": 6.352874807409338, "eval_accuracy": 0.0443176831943835, "eval_loss_by_set": { "aqua_rat": 6.379014015197754, "gsm8k": 7.242679942737926, "math_qa": 5.942869186401367 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.025018953752843062, "math_qa": 0.05025125628140704 } }, { "flos": 3.4267271045348065e+18, "train_loss": 5.441014404296875, "eval_loss": 6.354396845843341, "eval_accuracy": 0.0434401053093462, "eval_loss_by_set": { "aqua_rat": 6.37429666519165, "gsm8k": 7.249149669300426, "math_qa": 5.942643483479817 }, "eval_accuracy_by_set": { "aqua_rat": 0.09055118110236221, "gsm8k": 0.016679302501895376, "math_qa": 0.05125628140703518 } }, { "flos": 3.4322379319751475e+18, "train_loss": 5.4206884765625, "eval_loss": 6.349239400915198, "eval_accuracy": 0.04738920579201404, "eval_loss_by_set": { "aqua_rat": 6.369193077087402, "gsm8k": 7.236876054243608, "math_qa": 5.940743128458659 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.025018953752843062, "math_qa": 0.05460636515912898 } }, { "flos": 3.437762464119259e+18, "train_loss": 5.42376953125, "eval_loss": 6.361682556770943, "eval_accuracy": 0.0434401053093462, "eval_loss_by_set": { "aqua_rat": 6.390746593475342, "gsm8k": 7.25761621648615, "math_qa": 5.94862429300944 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.02122820318423048, "math_qa": 0.05058626465661641 } }, { "flos": 3.4433312827449016e+18, "train_loss": 5.426530151367188, "eval_loss": 6.348960077440417, "eval_accuracy": 0.045414655550680125, "eval_loss_by_set": { "aqua_rat": 6.381626605987549, "gsm8k": 7.244623357599432, "math_qa": 5.9357255299886065 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.024260803639120546, "math_qa": 0.0525963149078727 } }, { "flos": 3.4488528680045773e+18, "train_loss": 5.4323187255859375, "eval_loss": 6.349405958845809, "eval_accuracy": 0.045414655550680125, "eval_loss_by_set": { "aqua_rat": 6.371892929077148, "gsm8k": 7.243189031427557, "math_qa": 5.9378814697265625 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.021986353297952996, "math_qa": 0.05360134003350084 } }, { "flos": 3.4543725575730627e+18, "train_loss": 5.4277685546875, "eval_loss": 6.36140910999195, "eval_accuracy": 0.04278192189556823, "eval_loss_by_set": { "aqua_rat": 6.394892692565918, "gsm8k": 7.260405106977983, "math_qa": 5.9465789794921875 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.021986353297952996, "math_qa": 0.048911222780569516 } }, { "flos": 3.4599264769571553e+18, "train_loss": 5.430880737304688, "eval_loss": 6.348489297402872, "eval_accuracy": 0.04936375603334796, "eval_loss_by_set": { "aqua_rat": 6.374973297119141, "gsm8k": 7.24205918745561, "math_qa": 5.936729431152344 }, "eval_accuracy_by_set": { "aqua_rat": 0.09055118110236221, "gsm8k": 0.024260803639120546, "math_qa": 0.05695142378559464 } }, { "flos": 3.465498222066139e+18, "train_loss": 5.429990234375, "eval_loss": 6.3571597434378955, "eval_accuracy": 0.04629223343571742, "eval_loss_by_set": { "aqua_rat": 6.385554313659668, "gsm8k": 7.250828136097301, "math_qa": 5.9451955159505205 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.018953752843062926, "math_qa": 0.05561139028475712 } }, { "flos": 3.4710503692393513e+18, "train_loss": 5.43191162109375, "eval_loss": 6.354473500638394, "eval_accuracy": 0.04387889425186485, "eval_loss_by_set": { "aqua_rat": 6.3832831382751465, "gsm8k": 7.250302401455966, "math_qa": 5.941484451293945 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.018953752843062926, "math_qa": 0.05226130653266332 } }, { "flos": 3.4766592711841546e+18, "train_loss": 5.4359283447265625, "eval_loss": 6.357604026794434, "eval_accuracy": 0.045853444493198774, "eval_loss_by_set": { "aqua_rat": 6.384454250335693, "gsm8k": 7.258187727494673, "math_qa": 5.942598978678386 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.02122820318423048, "math_qa": 0.05527638190954774 } }, { "flos": 3.4821779095593943e+18, "train_loss": 5.424684448242187, "eval_loss": 6.356797037897883, "eval_accuracy": 0.0451952610794208, "eval_loss_by_set": { "aqua_rat": 6.390379905700684, "gsm8k": 7.251155506480824, "math_qa": 5.944084167480469 }, "eval_accuracy_by_set": { "aqua_rat": 0.08267716535433071, "gsm8k": 0.01819560272934041, "math_qa": 0.05393634840871022 } }, { "flos": 3.4876960325385585e+18, "train_loss": 5.423302001953125, "eval_loss": 6.357494869747677, "eval_accuracy": 0.04453707766564283, "eval_loss_by_set": { "aqua_rat": 6.3819122314453125, "gsm8k": 7.249683726917613, "math_qa": 5.946540196736653 }, "eval_accuracy_by_set": { "aqua_rat": 0.08267716535433071, "gsm8k": 0.02047005307050796, "math_qa": 0.051926298157453935 } }, { "flos": 3.49319575211973e+18, "train_loss": 5.427156982421875, "eval_loss": 6.3500312341226115, "eval_accuracy": 0.04365949978060553, "eval_loss_by_set": { "aqua_rat": 6.374663829803467, "gsm8k": 7.239234230735085, "math_qa": 5.940427144368489 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.02047005307050796, "math_qa": 0.051926298157453935 } }, { "flos": 3.4987597899099013e+18, "train_loss": 5.426988525390625, "eval_loss": 6.372655404580606, "eval_accuracy": 0.045414655550680125, "eval_loss_by_set": { "aqua_rat": 6.406660079956055, "gsm8k": 7.269976529208097, "math_qa": 5.958549499511719 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.02122820318423048, "math_qa": 0.054271356783919596 } }, { "flos": 3.50427484252432e+18, "train_loss": 5.4305181884765625, "eval_loss": 6.358881769953547, "eval_accuracy": 0.045414655550680125, "eval_loss_by_set": { "aqua_rat": 6.3919525146484375, "gsm8k": 7.260026411576704, "math_qa": 5.943101247151692 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.019711902956785442, "math_qa": 0.05393634840871022 } }, { "flos": 3.5098065053878845e+18, "train_loss": 5.425474853515625, "eval_loss": 6.362529445338893, "eval_accuracy": 0.045853444493198774, "eval_loss_by_set": { "aqua_rat": 6.392322540283203, "gsm8k": 7.268162814053622, "math_qa": 5.94496472676595 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.02047005307050796, "math_qa": 0.05460636515912898 } }, { "flos": 3.515335014671712e+18, "train_loss": 5.425476684570312, "eval_loss": 6.358939041962495, "eval_accuracy": 0.04936375603334796, "eval_loss_by_set": { "aqua_rat": 6.382842063903809, "gsm8k": 7.252062710848722, "math_qa": 5.947598775227864 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.025018953752843062, "math_qa": 0.0576214405360134 } }, { "flos": 3.5208283669638676e+18, "train_loss": 5.423005981445312, "eval_loss": 6.362379692696236, "eval_accuracy": 0.045414655550680125, "eval_loss_by_set": { "aqua_rat": 6.396655082702637, "gsm8k": 7.262752879749645, "math_qa": 5.946852366129558 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.02122820318423048, "math_qa": 0.05393634840871022 } }, { "flos": 3.5264048934451937e+18, "train_loss": 5.432561645507812, "eval_loss": 6.347167015075684, "eval_accuracy": 0.04716981132075472, "eval_loss_by_set": { "aqua_rat": 6.374974727630615, "gsm8k": 7.241471724076704, "math_qa": 5.934960047403972 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.02577710386656558, "math_qa": 0.05460636515912898 } }, { "flos": 3.5319348249000673e+18, "train_loss": 5.4190234375, "eval_loss": 6.374196207201159, "eval_accuracy": 0.044975866608161476, "eval_loss_by_set": { "aqua_rat": 6.408145427703857, "gsm8k": 7.274436950683594, "math_qa": 5.958756764729817 }, "eval_accuracy_by_set": { "aqua_rat": 0.08661417322834646, "gsm8k": 0.01819560272934041, "math_qa": 0.053266331658291456 } }, { "flos": 3.5374558330235126e+18, "train_loss": 5.42592041015625, "eval_loss": 6.366893794085528, "eval_accuracy": 0.04673102237823607, "eval_loss_by_set": { "aqua_rat": 6.399122714996338, "gsm8k": 7.265765103426847, "math_qa": 5.95222536722819 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.021986353297952996, "math_qa": 0.05661641541038526 } }, { "flos": 3.543054595624272e+18, "train_loss": 5.43769775390625, "eval_loss": 6.348601186597669, "eval_accuracy": 0.04322071083808688, "eval_loss_by_set": { "aqua_rat": 6.385725498199463, "gsm8k": 7.251472473144531, "math_qa": 5.931691487630208 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.02122820318423048, "math_qa": 0.05025125628140704 } }, { "flos": 3.5485994059196006e+18, "train_loss": 5.4308538818359375, "eval_loss": 6.370705192153518, "eval_accuracy": 0.04387889425186485, "eval_loss_by_set": { "aqua_rat": 6.405256748199463, "gsm8k": 7.274325284090909, "math_qa": 5.953666687011719 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.018953752843062926, "math_qa": 0.052931323283082074 } }, { "flos": 3.5541126449840783e+18, "train_loss": 5.430348510742188, "eval_loss": 6.360059274209513, "eval_accuracy": 0.04629223343571742, "eval_loss_by_set": { "aqua_rat": 6.392129898071289, "gsm8k": 7.254336270419034, "math_qa": 5.947509765625 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.014404852160727824, "math_qa": 0.05795644891122278 } }, { "flos": 3.5596347456398295e+18, "train_loss": 5.4341650390625, "eval_loss": 6.3585515408902555, "eval_accuracy": 0.04695041684949539, "eval_loss_by_set": { "aqua_rat": 6.395265579223633, "gsm8k": 7.256687511097301, "math_qa": 5.943846384684245 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.021986353297952996, "math_qa": 0.05661641541038526 } }, { "flos": 3.565207809840644e+18, "train_loss": 5.440382690429687, "eval_loss": 6.361506797171928, "eval_accuracy": 0.04168494953927161, "eval_loss_by_set": { "aqua_rat": 6.394521713256836, "gsm8k": 7.259383461692116, "math_qa": 5.947228749593099 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.022744503411675512, "math_qa": 0.048911222780569516 } }, { "flos": 3.5707615230663066e+18, "train_loss": 5.418509521484375, "eval_loss": 6.367315859407992, "eval_accuracy": 0.04453707766564283, "eval_loss_by_set": { "aqua_rat": 6.399969100952148, "gsm8k": 7.266406666148793, "math_qa": 5.952511469523112 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.02122820318423048, "math_qa": 0.051926298157453935 } }, { "flos": 3.5762344527889695e+18, "train_loss": 5.411549072265625, "eval_loss": 6.357589335054965, "eval_accuracy": 0.045853444493198774, "eval_loss_by_set": { "aqua_rat": 6.384827136993408, "gsm8k": 7.247675115411932, "math_qa": 5.947363535563151 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.018953752843062926, "math_qa": 0.05494137353433836 } }, { "flos": 3.5817857957295555e+18, "train_loss": 5.430350341796875, "eval_loss": 6.368416760418866, "eval_accuracy": 0.045414655550680125, "eval_loss_by_set": { "aqua_rat": 6.40367317199707, "gsm8k": 7.26291933926669, "math_qa": 5.955498377482097 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.024260803639120546, "math_qa": 0.051926298157453935 } }, { "flos": 3.587325639968948e+18, "train_loss": 5.433489379882812, "eval_loss": 6.371185122309504, "eval_accuracy": 0.0434401053093462, "eval_loss_by_set": { "aqua_rat": 6.412662982940674, "gsm8k": 7.267381147904829, "math_qa": 5.956972122192383 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.024260803639120546, "math_qa": 0.05025125628140704 } }, { "flos": 3.592897282535588e+18, "train_loss": 5.437363891601563, "eval_loss": 6.348179894524652, "eval_accuracy": 0.04409828872312418, "eval_loss_by_set": { "aqua_rat": 6.376691818237305, "gsm8k": 7.242183338512074, "math_qa": 5.936052322387695 }, "eval_accuracy_by_set": { "aqua_rat": 0.08661417322834646, "gsm8k": 0.026535253980288095, "math_qa": 0.04824120603015075 } }, { "flos": 3.598432799058559e+18, "train_loss": 5.430953369140625, "eval_loss": 6.356089050705369, "eval_accuracy": 0.045853444493198774, "eval_loss_by_set": { "aqua_rat": 6.392266273498535, "gsm8k": 7.26105429909446, "math_qa": 5.9382985432942705 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.02350265352539803, "math_qa": 0.053266331658291456 } }, { "flos": 3.6039454400488407e+18, "train_loss": 5.416226196289062, "eval_loss": 6.358875609732963, "eval_accuracy": 0.04870557261956999, "eval_loss_by_set": { "aqua_rat": 6.399590015411377, "gsm8k": 7.262413718483665, "math_qa": 5.94136110941569 }, "eval_accuracy_by_set": { "aqua_rat": 0.09448818897637795, "gsm8k": 0.026535253980288095, "math_qa": 0.05460636515912898 } }, { "flos": 3.609502882916729e+18, "train_loss": 5.43884765625, "eval_loss": 6.356517533998232, "eval_accuracy": 0.04278192189556823, "eval_loss_by_set": { "aqua_rat": 6.392693519592285, "gsm8k": 7.249171863902699, "math_qa": 5.944369633992513 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.018953752843062926, "math_qa": 0.05159128978224456 } }, { "flos": 3.6150335149881426e+18, "train_loss": 5.414219970703125, "eval_loss": 6.3517758395220785, "eval_accuracy": 0.04914436156208864, "eval_loss_by_set": { "aqua_rat": 6.380781650543213, "gsm8k": 7.244098316539418, "math_qa": 5.940377553304036 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.025018953752843062, "math_qa": 0.05829145728643216 } }, { "flos": 3.620561612491981e+18, "train_loss": 5.425382080078125, "eval_loss": 6.360514563483161, "eval_accuracy": 0.0443176831943835, "eval_loss_by_set": { "aqua_rat": 6.390649795532227, "gsm8k": 7.259701815518466, "math_qa": 5.945875803629558 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.021986353297952996, "math_qa": 0.05125628140703518 } }, { "flos": 3.626102136409948e+18, "train_loss": 5.434713134765625, "eval_loss": 6.351249282424514, "eval_accuracy": 0.04409828872312418, "eval_loss_by_set": { "aqua_rat": 6.382198333740234, "gsm8k": 7.24059365012429, "math_qa": 5.941054026285808 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.02122820318423048, "math_qa": 0.05226130653266332 } }, { "flos": 3.6316484515544433e+18, "train_loss": 5.425370483398438, "eval_loss": 6.356853459332441, "eval_accuracy": 0.04475647213690215, "eval_loss_by_set": { "aqua_rat": 6.390573024749756, "gsm8k": 7.252511457963423, "math_qa": 5.943533579508464 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.02880970432145565, "math_qa": 0.04958123953098827 } }, { "flos": 3.6371849569936343e+18, "train_loss": 5.42605712890625, "eval_loss": 6.3731486861770215, "eval_accuracy": 0.045414655550680125, "eval_loss_by_set": { "aqua_rat": 6.415644645690918, "gsm8k": 7.273822437633168, "math_qa": 5.956798553466797 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.025018953752843062, "math_qa": 0.052931323283082074 } }, { "flos": 3.642768634595508e+18, "train_loss": 5.438367309570313, "eval_loss": 6.34193381747684, "eval_accuracy": 0.040368582711715666, "eval_loss_by_set": { "aqua_rat": 6.375393390655518, "gsm8k": 7.233806956898082, "math_qa": 5.930370330810547 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.025018953752843062, "math_qa": 0.04489112227805695 } }, { "flos": 3.648273424385573e+18, "train_loss": 5.428626708984375, "eval_loss": 6.361850403450631, "eval_accuracy": 0.04475647213690215, "eval_loss_by_set": { "aqua_rat": 6.397532939910889, "gsm8k": 7.256723577325994, "math_qa": 5.948726654052734 }, "eval_accuracy_by_set": { "aqua_rat": 0.09055118110236221, "gsm8k": 0.022744503411675512, "math_qa": 0.05058626465661641 } }, { "flos": 3.653806879861113e+18, "train_loss": 5.426583251953125, "eval_loss": 6.359528773539775, "eval_accuracy": 0.0451952610794208, "eval_loss_by_set": { "aqua_rat": 6.396857261657715, "gsm8k": 7.25237343528054, "math_qa": 5.947197596232097 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.022744503411675512, "math_qa": 0.053266331658291456 } }, { "flos": 3.6593515253370716e+18, "train_loss": 5.422451171875, "eval_loss": 6.3571135804459855, "eval_accuracy": 0.041465555068012284, "eval_loss_by_set": { "aqua_rat": 6.383681774139404, "gsm8k": 7.244116349653765, "math_qa": 5.948356628417969 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.017437452615617893, "math_qa": 0.049916247906197656 } }, { "flos": 3.6648858054463324e+18, "train_loss": 5.4313525390625, "eval_loss": 6.36949534029574, "eval_accuracy": 0.040807371654234315, "eval_loss_by_set": { "aqua_rat": 6.402115821838379, "gsm8k": 7.2664406516335225, "math_qa": 5.955677032470703 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.024260803639120546, "math_qa": 0.04690117252931323 } }, { "flos": 3.670450358632579e+18, "train_loss": 5.429869384765625, "eval_loss": 6.361161360869536, "eval_accuracy": 0.04475647213690215, "eval_loss_by_set": { "aqua_rat": 6.391156196594238, "gsm8k": 7.252993496981534, "math_qa": 5.9499053955078125 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.021986353297952996, "math_qa": 0.0525963149078727 } }, { "flos": 3.676000341679145e+18, "train_loss": 5.446245727539062, "eval_loss": 6.362560736166464, "eval_accuracy": 0.04782799473453269, "eval_loss_by_set": { "aqua_rat": 6.397616386413574, "gsm8k": 7.258505387739702, "math_qa": 5.948998133341472 }, "eval_accuracy_by_set": { "aqua_rat": 0.08267716535433071, "gsm8k": 0.02122820318423048, "math_qa": 0.05661641541038526 } }, { "flos": 3.68156036099054e+18, "train_loss": 5.431611328125, "eval_loss": 6.354584049534154, "eval_accuracy": 0.045853444493198774, "eval_loss_by_set": { "aqua_rat": 6.387029647827148, "gsm8k": 7.251298384232954, "math_qa": 5.94088617960612 }, "eval_accuracy_by_set": { "aqua_rat": 0.08661417322834646, "gsm8k": 0.022744503411675512, "math_qa": 0.0525963149078727 } }, { "flos": 3.687050559702958e+18, "train_loss": 5.420138549804688, "eval_loss": 6.3603422061817065, "eval_accuracy": 0.04322071083808688, "eval_loss_by_set": { "aqua_rat": 6.3909478187561035, "gsm8k": 7.256780450994318, "math_qa": 5.946924209594727 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.024260803639120546, "math_qa": 0.05025125628140704 } }, { "flos": 3.6926352466221466e+18, "train_loss": 5.432710571289062, "eval_loss": 6.360634468697213, "eval_accuracy": 0.04453707766564283, "eval_loss_by_set": { "aqua_rat": 6.392726898193359, "gsm8k": 7.256831082430753, "math_qa": 5.947203318277995 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.022744503411675512, "math_qa": 0.05226130653266332 } }, { "flos": 3.6981575738374226e+18, "train_loss": 5.4322882080078125, "eval_loss": 6.35476658795331, "eval_accuracy": 0.04234313295304958, "eval_loss_by_set": { "aqua_rat": 6.386126518249512, "gsm8k": 7.247751409357244, "math_qa": 5.942868550618489 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.022744503411675512, "math_qa": 0.048576214405360134 } }, { "flos": 3.7036908644935926e+18, "train_loss": 5.412916870117187, "eval_loss": 6.375573544888883, "eval_accuracy": 0.04387889425186485, "eval_loss_by_set": { "aqua_rat": 6.411436080932617, "gsm8k": 7.273738514293324, "math_qa": 5.960926055908203 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.019711902956785442, "math_qa": 0.0525963149078727 } }, { "flos": 3.7092207138072166e+18, "train_loss": 5.42458984375, "eval_loss": 6.366618671932736, "eval_accuracy": 0.046511627906976744, "eval_loss_by_set": { "aqua_rat": 6.396569728851318, "gsm8k": 7.260819175026634, "math_qa": 5.954280853271484 }, "eval_accuracy_by_set": { "aqua_rat": 0.08267716535433071, "gsm8k": 0.02350265352539803, "math_qa": 0.05360134003350084 } }, { "flos": 3.714754705079927e+18, "train_loss": 5.418201904296875, "eval_loss": 6.36260259473646, "eval_accuracy": 0.0434401053093462, "eval_loss_by_set": { "aqua_rat": 6.395461082458496, "gsm8k": 7.257856195623225, "math_qa": 5.94953982035319 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.02122820318423048, "math_qa": 0.050921273031825795 } }, { "flos": 3.7203029572546724e+18, "train_loss": 5.424076538085938, "eval_loss": 6.363120929614918, "eval_accuracy": 0.041465555068012284, "eval_loss_by_set": { "aqua_rat": 6.396760940551758, "gsm8k": 7.254968816583807, "math_qa": 5.95155398050944 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.02047005307050796, "math_qa": 0.048576214405360134 } }, { "flos": 3.7258169382747505e+18, "train_loss": 5.432144775390625, "eval_loss": 6.36103359428612, "eval_accuracy": 0.04365949978060553, "eval_loss_by_set": { "aqua_rat": 6.392820835113525, "gsm8k": 7.259090076793324, "math_qa": 5.946775436401367 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.02122820318423048, "math_qa": 0.05159128978224456 } }, { "flos": 3.7313365451651154e+18, "train_loss": 5.425346069335937, "eval_loss": 6.36305839950974, "eval_accuracy": 0.045634050021939446, "eval_loss_by_set": { "aqua_rat": 6.397629737854004, "gsm8k": 7.258197437633168, "math_qa": 5.9499053955078125 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.018953752843062926, "math_qa": 0.05460636515912898 } }, { "flos": 3.7367976868131635e+18, "train_loss": 5.4004736328125, "eval_loss": 6.3654277389113965, "eval_accuracy": 0.041246160596752963, "eval_loss_by_set": { "aqua_rat": 6.396475791931152, "gsm8k": 7.260076349431818, "math_qa": 5.952793121337891 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.019711902956785442, "math_qa": 0.048576214405360134 } }, { "flos": 3.7423587777188987e+18, "train_loss": 5.426907958984375, "eval_loss": 6.370192321571144, "eval_accuracy": 0.0434401053093462, "eval_loss_by_set": { "aqua_rat": 6.402627468109131, "gsm8k": 7.268019242720171, "math_qa": 5.955985387166341 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.019711902956785442, "math_qa": 0.050921273031825795 } }, { "flos": 3.747862289756193e+18, "train_loss": 5.412334594726563, "eval_loss": 6.361757690842087, "eval_accuracy": 0.0434401053093462, "eval_loss_by_set": { "aqua_rat": 6.392922401428223, "gsm8k": 7.254395224831321, "math_qa": 5.950035095214844 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.022744503411675512, "math_qa": 0.05125628140703518 } }, { "flos": 3.7534249880534385e+18, "train_loss": 5.423538818359375, "eval_loss": 6.362615533777185, "eval_accuracy": 0.04409828872312418, "eval_loss_by_set": { "aqua_rat": 6.38862419128418, "gsm8k": 7.252600929953835, "math_qa": 5.952538172403972 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.018953752843062926, "math_qa": 0.0525963149078727 } }, { "flos": 3.7589814624062013e+18, "train_loss": 5.431995239257812, "eval_loss": 6.362146377563477, "eval_accuracy": 0.04365949978060553, "eval_loss_by_set": { "aqua_rat": 6.3940935134887695, "gsm8k": 7.256735368208452, "math_qa": 5.949464162190755 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.02047005307050796, "math_qa": 0.05226130653266332 } }, { "flos": 3.764497153897005e+18, "train_loss": 5.4064404296875, "eval_loss": 6.365504960756044, "eval_accuracy": 0.044975866608161476, "eval_loss_by_set": { "aqua_rat": 6.393830299377441, "gsm8k": 7.257343639026988, "math_qa": 5.954385121663411 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.024260803639120546, "math_qa": 0.05159128978224456 } }, { "flos": 3.770000954233979e+18, "train_loss": 5.425289916992187, "eval_loss": 6.362461863337336, "eval_accuracy": 0.045634050021939446, "eval_loss_by_set": { "aqua_rat": 6.396172523498535, "gsm8k": 7.2570578835227275, "math_qa": 5.949629465738933 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.024260803639120546, "math_qa": 0.05393634840871022 } }, { "flos": 3.775571483867218e+18, "train_loss": 5.427889404296875, "eval_loss": 6.3576575614310595, "eval_accuracy": 0.04212373848179026, "eval_loss_by_set": { "aqua_rat": 6.388828277587891, "gsm8k": 7.252337369051847, "math_qa": 5.944998423258464 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.02122820318423048, "math_qa": 0.048911222780569516 } }, { "flos": 3.7811314623764234e+18, "train_loss": 5.422881469726563, "eval_loss": 6.3613739013671875, "eval_accuracy": 0.04716981132075472, "eval_loss_by_set": { "aqua_rat": 6.392303466796875, "gsm8k": 7.259295376864347, "math_qa": 5.947249094645183 }, "eval_accuracy_by_set": { "aqua_rat": 0.08267716535433071, "gsm8k": 0.01819560272934041, "math_qa": 0.05695142378559464 } }, { "flos": 3.786623928294703e+18, "train_loss": 5.410179443359375, "eval_loss": 6.364196313394083, "eval_accuracy": 0.04848617814831066, "eval_loss_by_set": { "aqua_rat": 6.399977684020996, "gsm8k": 7.260997425426137, "math_qa": 5.950180689493815 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.025018953752843062, "math_qa": 0.0576214405360134 } }, { "flos": 3.792127337252782e+18, "train_loss": 5.425931396484375, "eval_loss": 6.363374967832823, "eval_accuracy": 0.04804738920579201, "eval_loss_by_set": { "aqua_rat": 6.397005081176758, "gsm8k": 7.260638150301847, "math_qa": 5.949326833089192 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.02350265352539803, "math_qa": 0.05695142378559464 } }, { "flos": 3.797622626575188e+18, "train_loss": 5.414988403320312, "eval_loss": 6.362630096641746, "eval_accuracy": 0.04936375603334796, "eval_loss_by_set": { "aqua_rat": 6.394257068634033, "gsm8k": 7.258155129172585, "math_qa": 5.949545542399089 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.025018953752843062, "math_qa": 0.05829145728643216 } }, { "flos": 3.8031132376044667e+18, "train_loss": 5.423661499023438, "eval_loss": 6.359099671647355, "eval_accuracy": 0.04212373848179026, "eval_loss_by_set": { "aqua_rat": 6.389887809753418, "gsm8k": 7.251789439808238, "math_qa": 5.947384516398112 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.018953752843062926, "math_qa": 0.04924623115577889 } }, { "flos": 3.808712721222861e+18, "train_loss": 5.42624755859375, "eval_loss": 6.360584619882944, "eval_accuracy": 0.04738920579201404, "eval_loss_by_set": { "aqua_rat": 6.391156196594238, "gsm8k": 7.255585410378196, "math_qa": 5.94782829284668 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.02577710386656558, "math_qa": 0.054271356783919596 } }, { "flos": 3.8142629313658225e+18, "train_loss": 5.421724853515625, "eval_loss": 6.361867079863677, "eval_accuracy": 0.045853444493198774, "eval_loss_by_set": { "aqua_rat": 6.3924360275268555, "gsm8k": 7.255939136851918, "math_qa": 5.949536641438802 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.022744503411675512, "math_qa": 0.053266331658291456 } }, { "flos": 3.819772295832928e+18, "train_loss": 5.4221728515625, "eval_loss": 6.362283912864891, "eval_accuracy": 0.04453707766564283, "eval_loss_by_set": { "aqua_rat": 6.3942461013793945, "gsm8k": 7.2574920654296875, "math_qa": 5.949316660563151 }, "eval_accuracy_by_set": { "aqua_rat": 0.08661417322834646, "gsm8k": 0.02577710386656558, "math_qa": 0.04924623115577889 } }, { "flos": 3.819772295832928e+18, "train_loss": 5.4221728515625, "eval_loss": 6.362283912864891, "eval_accuracy": 0.04453707766564283, "eval_loss_by_set": { "aqua_rat": 6.3942461013793945, "gsm8k": 7.2574920654296875, "math_qa": 5.949316660563151 }, "eval_accuracy_by_set": { "aqua_rat": 0.08661417322834646, "gsm8k": 0.02577710386656558, "math_qa": 0.04924623115577889 } } ]