[ { "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": 6336181641936896.0, "train_loss": 6.7849053955078125, "eval_loss": 6.045626356795028, "eval_accuracy": 0.007459412022817025, "eval_loss_by_set": { "aqua_rat": 5.999513626098633, "gsm8k": 6.665949041193182, "math_qa": 5.765154520670573 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.012130401819560273, "math_qa": 0.004020100502512563 } }, { "flos": 1.2690168607670272e+16, "train_loss": 6.037254638671875, "eval_loss": 5.966488528896022, "eval_accuracy": 0.012724879333040808, "eval_loss_by_set": { "aqua_rat": 5.945150852203369, "gsm8k": 6.57744737104936, "math_qa": 5.688243865966797 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.017437452615617893, "math_qa": 0.011390284757118929 } }, { "flos": 1.905439745979187e+16, "train_loss": 5.99583251953125, "eval_loss": 5.931760839513831, "eval_accuracy": 0.012505484861781484, "eval_loss_by_set": { "aqua_rat": 5.929096221923828, "gsm8k": 6.568258112127131, "math_qa": 5.640254974365234 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.016679302501895376, "math_qa": 0.010385259631490788 } }, { "flos": 2.5433114310344704e+16, "train_loss": 5.963706665039062, "eval_loss": 5.927127683484876, "eval_accuracy": 0.012066695919262835, "eval_loss_by_set": { "aqua_rat": 5.925230979919434, "gsm8k": 6.5514984130859375, "math_qa": 5.641115824381511 }, "eval_accuracy_by_set": { "aqua_rat": 0.011811023622047244, "gsm8k": 0.016679302501895376, "math_qa": 0.010050251256281407 } }, { "flos": 3.17442777677824e+16, "train_loss": 5.956167602539063, "eval_loss": 5.916997007421545, "eval_accuracy": 0.013602457218078104, "eval_loss_by_set": { "aqua_rat": 5.9059882164001465, "gsm8k": 6.547692038796165, "math_qa": 5.628845850626628 }, "eval_accuracy_by_set": { "aqua_rat": 0.011811023622047244, "gsm8k": 0.02047005307050796, "math_qa": 0.010720268006700168 } }, { "flos": 3.817066123912806e+16, "train_loss": 5.94796875, "eval_loss": 5.8974208316287475, "eval_accuracy": 0.013602457218078104, "eval_loss_by_set": { "aqua_rat": 5.911436080932617, "gsm8k": 6.551295887340199, "math_qa": 5.596560160319011 }, "eval_accuracy_by_set": { "aqua_rat": 0.011811023622047244, "gsm8k": 0.017437452615617893, "math_qa": 0.012060301507537688 } }, { "flos": 4.445095354538394e+16, "train_loss": 5.939705200195313, "eval_loss": 5.897520838557063, "eval_accuracy": 0.01338306274681878, "eval_loss_by_set": { "aqua_rat": 5.891210556030273, "gsm8k": 6.555301319469105, "math_qa": 5.596563975016276 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.02122820318423048, "math_qa": 0.007705192629815745 } }, { "flos": 5.081988109172736e+16, "train_loss": 5.932210083007813, "eval_loss": 5.904799616014635, "eval_accuracy": 0.012066695919262835, "eval_loss_by_set": { "aqua_rat": 5.8982625007629395, "gsm8k": 6.53600380637429, "math_qa": 5.616042455037435 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.014404852160727824, "math_qa": 0.009380234505862646 } }, { "flos": 5.710141034856448e+16, "train_loss": 5.907828369140625, "eval_loss": 5.874852618655643, "eval_accuracy": 0.009653356735410267, "eval_loss_by_set": { "aqua_rat": 5.8958940505981445, "gsm8k": 6.5248024680397725, "math_qa": 5.575205485026042 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.016679302501895376, "math_qa": 0.005025125628140704 } }, { "flos": 6.348051804114125e+16, "train_loss": 5.925845336914063, "eval_loss": 5.886215648135623, "eval_accuracy": 0.011627906976744186, "eval_loss_by_set": { "aqua_rat": 5.8912129402160645, "gsm8k": 6.531057184392756, "math_qa": 5.590246836344401 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.016679302501895376, "math_qa": 0.006700167504187605 } }, { "flos": 6.982848722082202e+16, "train_loss": 5.9109649658203125, "eval_loss": 5.891819618843697, "eval_accuracy": 0.010092145677928916, "eval_loss_by_set": { "aqua_rat": 5.88868522644043, "gsm8k": 6.552764892578125, "math_qa": 5.589147567749023 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.013646702047005308, "math_qa": 0.004690117252931323 } }, { "flos": 7.618702846250189e+16, "train_loss": 5.88840576171875, "eval_loss": 5.872086499188398, "eval_accuracy": 0.011189118034225537, "eval_loss_by_set": { "aqua_rat": 5.884160995483398, "gsm8k": 6.534729697487571, "math_qa": 5.567368825276692 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.01819560272934041, "math_qa": 0.003015075376884422 } }, { "flos": 8.256652807084442e+16, "train_loss": 5.89583251953125, "eval_loss": 5.868478929674303, "eval_accuracy": 0.011189118034225537, "eval_loss_by_set": { "aqua_rat": 5.88128662109375, "gsm8k": 6.515613209117543, "math_qa": 5.570808410644531 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.01819560272934041, "math_qa": 0.003015075376884422 } }, { "flos": 8.893409572316774e+16, "train_loss": 5.881857299804688, "eval_loss": 5.871764363469304, "eval_accuracy": 0.010311540149188241, "eval_loss_by_set": { "aqua_rat": 5.874081611633301, "gsm8k": 6.5357534235174, "math_qa": 5.567242940266927 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.01288855193328279, "math_qa": 0.004355108877721943 } }, { "flos": 9.523056556061491e+16, "train_loss": 5.872968139648438, "eval_loss": 5.873634338378906, "eval_accuracy": 0.011627906976744186, "eval_loss_by_set": { "aqua_rat": 5.881843566894531, "gsm8k": 6.522612831809304, "math_qa": 5.575501759847005 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.017437452615617893, "math_qa": 0.005025125628140704 } }, { "flos": 1.0165894780236595e+17, "train_loss": 5.879658203125, "eval_loss": 5.8718725152917814, "eval_accuracy": 0.010969723562966213, "eval_loss_by_set": { "aqua_rat": 5.875048637390137, "gsm8k": 6.532666293057528, "math_qa": 5.56874402364095 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.01061410159211524, "math_qa": 0.006365159128978224 } }, { "flos": 1.0798826716030566e+17, "train_loss": 5.862236328125, "eval_loss": 5.881784567961821, "eval_accuracy": 0.011627906976744186, "eval_loss_by_set": { "aqua_rat": 5.868838787078857, "gsm8k": 6.525218616832387, "math_qa": 5.5879561106363935 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.016679302501895376, "math_qa": 0.0036850921273031824 } }, { "flos": 1.1438746832050586e+17, "train_loss": 5.87038330078125, "eval_loss": 5.87465440904772, "eval_accuracy": 0.012505484861781484, "eval_loss_by_set": { "aqua_rat": 5.875598907470703, "gsm8k": 6.54366025057706, "math_qa": 5.56794802347819 }, "eval_accuracy_by_set": { "aqua_rat": 0.08267716535433071, "gsm8k": 0.013646702047005308, "math_qa": 0.006030150753768844 } }, { "flos": 1.2070287681624474e+17, "train_loss": 5.862427978515625, "eval_loss": 5.865326133934227, "eval_accuracy": 0.01228609039052216, "eval_loss_by_set": { "aqua_rat": 5.864109039306641, "gsm8k": 6.53326416015625, "math_qa": 5.559289296468099 }, "eval_accuracy_by_set": { "aqua_rat": 0.08661417322834646, "gsm8k": 0.019711902956785442, "math_qa": 0.002680067001675042 } }, { "flos": 1.2704606516045414e+17, "train_loss": 5.8607635498046875, "eval_loss": 5.863128713659338, "eval_accuracy": 0.012066695919262835, "eval_loss_by_set": { "aqua_rat": 5.864995002746582, "gsm8k": 6.552026228471235, "math_qa": 5.547228495279948 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.016679302501895376, "math_qa": 0.004690117252931323 } }, { "flos": 1.334095316558807e+17, "train_loss": 5.843106079101562, "eval_loss": 5.8491787781586515, "eval_accuracy": 0.010969723562966213, "eval_loss_by_set": { "aqua_rat": 5.8639631271362305, "gsm8k": 6.533249594948509, "math_qa": 5.534414291381836 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.015163002274450341, "math_qa": 0.0033500837520938024 } }, { "flos": 1.3974286895572582e+17, "train_loss": 5.85262451171875, "eval_loss": 5.854873167501913, "eval_accuracy": 0.01184730144800351, "eval_loss_by_set": { "aqua_rat": 5.854700565338135, "gsm8k": 6.53931288285689, "math_qa": 5.541186014811198 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.018953752843062926, "math_qa": 0.0033500837520938024 } }, { "flos": 1.461204519349125e+17, "train_loss": 5.85058837890625, "eval_loss": 5.858008358929609, "eval_accuracy": 0.014260640631856078, "eval_loss_by_set": { "aqua_rat": 5.863339424133301, "gsm8k": 6.536922801624645, "math_qa": 5.546394983927409 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.018953752843062926, "math_qa": 0.007370184254606365 } }, { "flos": 1.5248363013065933e+17, "train_loss": 5.8519921875, "eval_loss": 5.865532746186128, "eval_accuracy": 0.013163668275559455, "eval_loss_by_set": { "aqua_rat": 5.863689422607422, "gsm8k": 6.540304010564631, "math_qa": 5.556416193644206 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.01592115238817286, "math_qa": 0.006700167504187605 } }, { "flos": 1.5878477772436275e+17, "train_loss": 5.846947021484375, "eval_loss": 5.849176613060203, "eval_accuracy": 0.011189118034225537, "eval_loss_by_set": { "aqua_rat": 5.856812477111816, "gsm8k": 6.528665022416548, "math_qa": 5.537108103434245 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.01819560272934041, "math_qa": 0.003015075376884422 } }, { "flos": 1.651743753376891e+17, "train_loss": 5.84853271484375, "eval_loss": 5.850951890687685, "eval_accuracy": 0.011627906976744186, "eval_loss_by_set": { "aqua_rat": 5.859744071960449, "gsm8k": 6.524010398171165, "math_qa": 5.541734059651692 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.02047005307050796, "math_qa": 0.002680067001675042 } }, { "flos": 1.7146874278864486e+17, "train_loss": 5.827174072265625, "eval_loss": 5.8426053588454785, "eval_accuracy": 0.011189118034225537, "eval_loss_by_set": { "aqua_rat": 5.865306377410889, "gsm8k": 6.542631669477983, "math_qa": 5.51986821492513 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.018953752843062926, "math_qa": 0.0036850921273031824 } }, { "flos": 1.778158465324155e+17, "train_loss": 5.8374566650390625, "eval_loss": 5.847657796498892, "eval_accuracy": 0.01228609039052216, "eval_loss_by_set": { "aqua_rat": 5.854825973510742, "gsm8k": 6.536686290394176, "math_qa": 5.531255722045898 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.01819560272934041, "math_qa": 0.004690117252931323 } }, { "flos": 1.8416198176106086e+17, "train_loss": 5.832183227539063, "eval_loss": 5.853264112730284, "eval_accuracy": 0.012505484861781484, "eval_loss_by_set": { "aqua_rat": 5.849472999572754, "gsm8k": 6.529790704900568, "math_qa": 5.543505350748698 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.016679302501895376, "math_qa": 0.006030150753768844 } }, { "flos": 1.905020170624041e+17, "train_loss": 5.831320190429688, "eval_loss": 5.844371383254592, "eval_accuracy": 0.013163668275559455, "eval_loss_by_set": { "aqua_rat": 5.852842330932617, "gsm8k": 6.5084075927734375, "math_qa": 5.539315541585286 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.021986353297952996, "math_qa": 0.004020100502512563 } }, { "flos": 1.968440511341527e+17, "train_loss": 5.830760498046875, "eval_loss": 5.852883055403426, "eval_accuracy": 0.008995173321632294, "eval_loss_by_set": { "aqua_rat": 5.8574724197387695, "gsm8k": 6.515439813787287, "math_qa": 5.548828760782878 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.01061410159211524, "math_qa": 0.004355108877721943 } }, { "flos": 2.031974400256901e+17, "train_loss": 5.8229132080078125, "eval_loss": 5.856268315701871, "eval_accuracy": 0.01184730144800351, "eval_loss_by_set": { "aqua_rat": 5.847239017486572, "gsm8k": 6.543343977494673, "math_qa": 5.542111078898112 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.017437452615617893, "math_qa": 0.005025125628140704 } }, { "flos": 2.0960614111667814e+17, "train_loss": 5.82636474609375, "eval_loss": 5.850245553093988, "eval_accuracy": 0.012505484861781484, "eval_loss_by_set": { "aqua_rat": 5.8578386306762695, "gsm8k": 6.551427667791193, "math_qa": 5.528237660725911 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.02047005307050796, "math_qa": 0.004690117252931323 } }, { "flos": 2.15938839540138e+17, "train_loss": 5.837208862304688, "eval_loss": 5.853491396517367, "eval_accuracy": 0.01228609039052216, "eval_loss_by_set": { "aqua_rat": 5.855310440063477, "gsm8k": 6.547685102982954, "math_qa": 5.535167694091797 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.024260803639120546, "math_qa": 0.004355108877721943 } }, { "flos": 2.2228957038379008e+17, "train_loss": 5.831481323242188, "eval_loss": 5.83161364374934, "eval_accuracy": 0.013163668275559455, "eval_loss_by_set": { "aqua_rat": 5.864630699157715, "gsm8k": 6.541017705743963, "math_qa": 5.5037186940511065 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.018953752843062926, "math_qa": 0.006030150753768844 } }, { "flos": 2.286693384275886e+17, "train_loss": 5.824715576171875, "eval_loss": 5.850419895069019, "eval_accuracy": 0.011627906976744186, "eval_loss_by_set": { "aqua_rat": 5.8675336837768555, "gsm8k": 6.572817715731534, "math_qa": 5.517894744873047 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.01819560272934041, "math_qa": 0.004690117252931323 } }, { "flos": 2.3500234608869376e+17, "train_loss": 5.821588134765625, "eval_loss": 5.859298087455131, "eval_accuracy": 0.014260640631856078, "eval_loss_by_set": { "aqua_rat": 5.854587554931641, "gsm8k": 6.554852572354403, "math_qa": 5.540894826253255 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.022744503411675512, "math_qa": 0.005695142378559464 } }, { "flos": 2.4133896044858573e+17, "train_loss": 5.815418701171875, "eval_loss": 5.855567004229571, "eval_accuracy": 0.012505484861781484, "eval_loss_by_set": { "aqua_rat": 5.849855422973633, "gsm8k": 6.539099953391335, "math_qa": 5.542757034301758 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.017437452615617893, "math_qa": 0.006365159128978224 } }, { "flos": 2.4765842876216115e+17, "train_loss": 5.812449951171875, "eval_loss": 5.8409480017584725, "eval_accuracy": 0.010530934620447565, "eval_loss_by_set": { "aqua_rat": 5.848626136779785, "gsm8k": 6.527361089533025, "math_qa": 5.525702158610026 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.01592115238817286, "math_qa": 0.004690117252931323 } }, { "flos": 2.540026887007109e+17, "train_loss": 5.821253662109375, "eval_loss": 5.850727751448348, "eval_accuracy": 0.015796401930671347, "eval_loss_by_set": { "aqua_rat": 5.845686912536621, "gsm8k": 6.534681840376421, "math_qa": 5.537668863932292 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.019711902956785442, "math_qa": 0.010720268006700168 } }, { "flos": 2.6036984403617382e+17, "train_loss": 5.80904541015625, "eval_loss": 5.843262698199298, "eval_accuracy": 0.009653356735410267, "eval_loss_by_set": { "aqua_rat": 5.849703788757324, "gsm8k": 6.549496737393466, "math_qa": 5.519035339355469 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.017437452615617893, "math_qa": 0.0023450586264656616 } }, { "flos": 2.667188644091003e+17, "train_loss": 5.816728515625, "eval_loss": 5.8439816139839795, "eval_accuracy": 0.009653356735410267, "eval_loss_by_set": { "aqua_rat": 5.8537187576293945, "gsm8k": 6.548058249733665, "math_qa": 5.520468393961589 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.015163002274450341, "math_qa": 0.004355108877721943 } }, { "flos": 2.730251020759204e+17, "train_loss": 5.812466430664062, "eval_loss": 5.845418620753932, "eval_accuracy": 0.012066695919262835, "eval_loss_by_set": { "aqua_rat": 5.854683876037598, "gsm8k": 6.556569879705256, "math_qa": 5.5187021891276045 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.021986353297952996, "math_qa": 0.0036850921273031824 } }, { "flos": 2.794461683777536e+17, "train_loss": 5.811832275390625, "eval_loss": 5.844953691637194, "eval_accuracy": 0.011627906976744186, "eval_loss_by_set": { "aqua_rat": 5.862112045288086, "gsm8k": 6.535007823597301, "math_qa": 5.527249018351237 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.01592115238817286, "math_qa": 0.006030150753768844 } }, { "flos": 2.8575687817927066e+17, "train_loss": 5.81803955078125, "eval_loss": 5.840448379516602, "eval_accuracy": 0.007678806494076349, "eval_loss_by_set": { "aqua_rat": 5.853997230529785, "gsm8k": 6.54889609596946, "math_qa": 5.514614105224609 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.014404852160727824, "math_qa": 0.0033500837520938024 } }, { "flos": 2.9209897399117414e+17, "train_loss": 5.800515747070312, "eval_loss": 5.838458293193096, "eval_accuracy": 0.01075032909170689, "eval_loss_by_set": { "aqua_rat": 5.853900909423828, "gsm8k": 6.538065130060369, "math_qa": 5.516518274943034 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.02047005307050796, "math_qa": 0.004020100502512563 } }, { "flos": 2.9840844737898086e+17, "train_loss": 5.808658447265625, "eval_loss": 5.832410863927893, "eval_accuracy": 0.011189118034225537, "eval_loss_by_set": { "aqua_rat": 5.847118377685547, "gsm8k": 6.551755038174716, "math_qa": 5.501485824584961 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.019711902956785442, "math_qa": 0.0036850921273031824 } }, { "flos": 3.0476849293295616e+17, "train_loss": 5.800360107421875, "eval_loss": 5.840921556627428, "eval_accuracy": 0.009872751206669592, "eval_loss_by_set": { "aqua_rat": 5.847175598144531, "gsm8k": 6.536818764426491, "math_qa": 5.521447499593099 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.016679302501895376, "math_qa": 0.003015075376884422 } }, { "flos": 3.111994301433774e+17, "train_loss": 5.8013623046875, "eval_loss": 5.829337738655709, "eval_accuracy": 0.010530934620447565, "eval_loss_by_set": { "aqua_rat": 5.8523077964782715, "gsm8k": 6.552967418323863, "math_qa": 5.495759963989258 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.01592115238817286, "math_qa": 0.004020100502512563 } }, { "flos": 3.1752899646193664e+17, "train_loss": 5.8065087890625, "eval_loss": 5.845184429271801, "eval_accuracy": 0.009872751206669592, "eval_loss_by_set": { "aqua_rat": 5.849813461303711, "gsm8k": 6.55415829745206, "math_qa": 5.51985232035319 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.017437452615617893, "math_qa": 0.004020100502512563 } }, { "flos": 3.238826124498698e+17, "train_loss": 5.807597045898437, "eval_loss": 5.848777049296611, "eval_accuracy": 0.008995173321632294, "eval_loss_by_set": { "aqua_rat": 5.852899551391602, "gsm8k": 6.5538198297674, "math_qa": 5.525288899739583 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.014404852160727824, "math_qa": 0.003015075376884422 } }, { "flos": 3.3023076738688614e+17, "train_loss": 5.7985076904296875, "eval_loss": 5.839748666093156, "eval_accuracy": 0.008775778850372971, "eval_loss_by_set": { "aqua_rat": 5.846404552459717, "gsm8k": 6.558104775168679, "math_qa": 5.509947458902995 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.014404852160727824, "math_qa": 0.003015075376884422 } }, { "flos": 3.366636416275579e+17, "train_loss": 5.80540283203125, "eval_loss": 5.838149869764173, "eval_accuracy": 0.009433962264150943, "eval_loss_by_set": { "aqua_rat": 5.8498125076293945, "gsm8k": 6.526464288884943, "math_qa": 5.521700541178386 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.015163002274450341, "math_qa": 0.0023450586264656616 } }, { "flos": 3.4303019942569574e+17, "train_loss": 5.788732299804687, "eval_loss": 5.835124582857699, "eval_accuracy": 0.008775778850372971, "eval_loss_by_set": { "aqua_rat": 5.850534915924072, "gsm8k": 6.53445781360973, "math_qa": 5.513312657674153 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.014404852160727824, "math_qa": 0.003015075376884422 } }, { "flos": 3.493107805685023e+17, "train_loss": 5.796063232421875, "eval_loss": 5.846676955351958, "eval_accuracy": 0.007898200965335674, "eval_loss_by_set": { "aqua_rat": 5.847235679626465, "gsm8k": 6.54489482532848, "math_qa": 5.526613871256511 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.012130401819560273, "math_qa": 0.003015075376884422 } }, { "flos": 3.556748859403141e+17, "train_loss": 5.79754150390625, "eval_loss": 5.824769535580197, "eval_accuracy": 0.009214567792891619, "eval_loss_by_set": { "aqua_rat": 5.850372791290283, "gsm8k": 6.531708457253196, "math_qa": 5.4986222585042315 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.01592115238817286, "math_qa": 0.003015075376884422 } }, { "flos": 3.620550448261366e+17, "train_loss": 5.798233642578125, "eval_loss": 5.834419869087838, "eval_accuracy": 0.008117595436594998, "eval_loss_by_set": { "aqua_rat": 5.854244232177734, "gsm8k": 6.56391698663885, "math_qa": 5.498414993286133 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.014404852160727824, "math_qa": 0.0020100502512562816 } }, { "flos": 3.6841290638924186e+17, "train_loss": 5.79376953125, "eval_loss": 5.847140441069731, "eval_accuracy": 0.008336989907854322, "eval_loss_by_set": { "aqua_rat": 5.850313186645508, "gsm8k": 6.5692291259765625, "math_qa": 5.515918731689453 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.015163002274450341, "math_qa": 0.003015075376884422 } }, { "flos": 3.7468314202957414e+17, "train_loss": 5.79626708984375, "eval_loss": 5.83848710962244, "eval_accuracy": 0.007240017551557701, "eval_loss_by_set": { "aqua_rat": 5.852766990661621, "gsm8k": 6.555600946599787, "math_qa": 5.508619944254558 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.013646702047005308, "math_qa": 0.0023450586264656616 } }, { "flos": 3.810145422991688e+17, "train_loss": 5.788295288085937, "eval_loss": 5.83785054490373, "eval_accuracy": 0.006801228609039052, "eval_loss_by_set": { "aqua_rat": 5.854578495025635, "gsm8k": 6.5519887750799, "math_qa": 5.509143193562825 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.01288855193328279, "math_qa": 0.0020100502512562816 } }, { "flos": 3.8748420239785984e+17, "train_loss": 5.795794677734375, "eval_loss": 5.833714433618494, "eval_accuracy": 0.009872751206669592, "eval_loss_by_set": { "aqua_rat": 5.848048686981201, "gsm8k": 6.555439342151988, "math_qa": 5.501729329427083 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.019711902956785442, "math_qa": 0.003015075376884422 } }, { "flos": 3.9383884864107315e+17, "train_loss": 5.795849609375, "eval_loss": 5.828800201416016, "eval_accuracy": 0.008117595436594998, "eval_loss_by_set": { "aqua_rat": 5.847593307495117, "gsm8k": 6.547757929021662, "math_qa": 5.497711817423503 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.015163002274450341, "math_qa": 0.0016750418760469012 } }, { "flos": 4.0022380930033254e+17, "train_loss": 5.792353515625, "eval_loss": 5.841484636873813, "eval_accuracy": 0.007020623080298377, "eval_loss_by_set": { "aqua_rat": 5.848223686218262, "gsm8k": 6.54872616854581, "math_qa": 5.516770680745442 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.012130401819560273, "math_qa": 0.0016750418760469012 } }, { "flos": 4.065972089813729e+17, "train_loss": 5.792791137695312, "eval_loss": 5.828982997584987, "eval_accuracy": 0.008336989907854322, "eval_loss_by_set": { "aqua_rat": 5.853992462158203, "gsm8k": 6.5579306862571025, "math_qa": 5.4927978515625 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.016679302501895376, "math_qa": 0.0016750418760469012 } }, { "flos": 4.1296127355099546e+17, "train_loss": 5.79544189453125, "eval_loss": 5.839378717783335, "eval_accuracy": 0.008117595436594998, "eval_loss_by_set": { "aqua_rat": 5.849699974060059, "gsm8k": 6.558455727317116, "math_qa": 5.508941650390625 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.018953752843062926, "math_qa": 0.0020100502512562816 } }, { "flos": 4.1931278715243725e+17, "train_loss": 5.795130004882813, "eval_loss": 5.833799903457229, "eval_accuracy": 0.007898200965335674, "eval_loss_by_set": { "aqua_rat": 5.8481879234313965, "gsm8k": 6.565930453213778, "math_qa": 5.49704106648763 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.013646702047005308, "math_qa": 0.0023450586264656616 } }, { "flos": 4.256612513270989e+17, "train_loss": 5.783857421875, "eval_loss": 5.850983207290237, "eval_accuracy": 0.007459412022817025, "eval_loss_by_set": { "aqua_rat": 5.84988260269165, "gsm8k": 6.572216380726207, "math_qa": 5.520509719848633 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.01592115238817286, "math_qa": 0.0020100502512562816 } }, { "flos": 4.3203675285775974e+17, "train_loss": 5.787443237304688, "eval_loss": 5.838138889622044, "eval_accuracy": 0.007678806494076349, "eval_loss_by_set": { "aqua_rat": 5.8393707275390625, "gsm8k": 6.56207275390625, "math_qa": 5.506233215332031 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 4.3836512410166886e+17, "train_loss": 5.782335205078125, "eval_loss": 5.8544814651076855, "eval_accuracy": 0.009214567792891619, "eval_loss_by_set": { "aqua_rat": 5.84234619140625, "gsm8k": 6.5722808837890625, "math_qa": 5.526501337687175 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.02122820318423048, "math_qa": 0.001340033500837521 } }, { "flos": 4.447064575568773e+17, "train_loss": 5.784259033203125, "eval_loss": 5.83983106870909, "eval_accuracy": 0.008556384379113647, "eval_loss_by_set": { "aqua_rat": 5.853509902954102, "gsm8k": 6.565554532137784, "math_qa": 5.5060679117838545 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.018953752843062926, "math_qa": 0.0023450586264656616 } }, { "flos": 4.510321702160302e+17, "train_loss": 5.779348754882813, "eval_loss": 5.839234300561853, "eval_accuracy": 0.007678806494076349, "eval_loss_by_set": { "aqua_rat": 5.85223913192749, "gsm8k": 6.560568376020952, "math_qa": 5.50753911336263 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.01592115238817286, "math_qa": 0.0020100502512562816 } }, { "flos": 4.5743714112792166e+17, "train_loss": 5.781094970703125, "eval_loss": 5.841735659418879, "eval_accuracy": 0.008995173321632294, "eval_loss_by_set": { "aqua_rat": 5.848419666290283, "gsm8k": 6.558218522505327, "math_qa": 5.512790679931641 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.02122820318423048, "math_qa": 0.0016750418760469012 } }, { "flos": 4.637133118761861e+17, "train_loss": 5.785791625976563, "eval_loss": 5.838133425325961, "eval_accuracy": 0.005704256252742431, "eval_loss_by_set": { "aqua_rat": 5.848855972290039, "gsm8k": 6.5692006891424, "math_qa": 5.502167383829753 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.011372251705837756, "math_qa": 0.0016750418760469012 } }, { "flos": 4.699975813221581e+17, "train_loss": 5.767095947265625, "eval_loss": 5.8411174980369776, "eval_accuracy": 0.009214567792891619, "eval_loss_by_set": { "aqua_rat": 5.842717170715332, "gsm8k": 6.559209650213068, "math_qa": 5.511858622233073 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.02350265352539803, "math_qa": 0.001340033500837521 } }, { "flos": 4.7646211000867226e+17, "train_loss": 5.789156494140625, "eval_loss": 5.842941696579392, "eval_accuracy": 0.008117595436594998, "eval_loss_by_set": { "aqua_rat": 5.850883483886719, "gsm8k": 6.586485429243608, "math_qa": 5.501489003499349 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.01819560272934041, "math_qa": 0.0020100502512562816 } }, { "flos": 4.827636285801759e+17, "train_loss": 5.7795849609375, "eval_loss": 5.837698292087865, "eval_accuracy": 0.007898200965335674, "eval_loss_by_set": { "aqua_rat": 5.843686103820801, "gsm8k": 6.548349553888494, "math_qa": 5.511484146118164 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 4.891448590603387e+17, "train_loss": 5.7894775390625, "eval_loss": 5.845027459634317, "eval_accuracy": 0.00614304519526108, "eval_loss_by_set": { "aqua_rat": 5.8506059646606445, "gsm8k": 6.571082375266335, "math_qa": 5.511787414550781 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.011372251705837756, "math_qa": 0.001340033500837521 } }, { "flos": 4.954873054489477e+17, "train_loss": 5.771481323242187, "eval_loss": 5.841533093839078, "eval_accuracy": 0.005484861781483106, "eval_loss_by_set": { "aqua_rat": 5.850649833679199, "gsm8k": 6.57354736328125, "math_qa": 5.505266825358073 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.01061410159211524, "math_qa": 0.0016750418760469012 } }, { "flos": 5.018321425237279e+17, "train_loss": 5.776918334960937, "eval_loss": 5.838447570800781, "eval_accuracy": 0.007020623080298377, "eval_loss_by_set": { "aqua_rat": 5.848346710205078, "gsm8k": 6.574910944158381, "math_qa": 5.50007692972819 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.013646702047005308, "math_qa": 0.001340033500837521 } }, { "flos": 5.0815295033022874e+17, "train_loss": 5.77053955078125, "eval_loss": 5.835018106409021, "eval_accuracy": 0.007459412022817025, "eval_loss_by_set": { "aqua_rat": 5.855072975158691, "gsm8k": 6.560902682217685, "math_qa": 5.500649770100911 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.017437452615617893, "math_qa": 0.001340033500837521 } }, { "flos": 5.1445589107277824e+17, "train_loss": 5.778589477539063, "eval_loss": 5.84081456467912, "eval_accuracy": 0.006801228609039052, "eval_loss_by_set": { "aqua_rat": 5.847370624542236, "gsm8k": 6.558618025346235, "math_qa": 5.511274973551433 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.01288855193328279, "math_qa": 0.0016750418760469012 } }, { "flos": 5.207691150407762e+17, "train_loss": 5.778187866210938, "eval_loss": 5.833275150608372, "eval_accuracy": 0.007898200965335674, "eval_loss_by_set": { "aqua_rat": 5.845670700073242, "gsm8k": 6.546340248801491, "math_qa": 5.505420684814453 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.017437452615617893, "math_qa": 0.0016750418760469012 } }, { "flos": 5.27201330003968e+17, "train_loss": 5.768492431640625, "eval_loss": 5.85217607343519, "eval_accuracy": 0.006362439666520404, "eval_loss_by_set": { "aqua_rat": 5.85845422744751, "gsm8k": 6.58553036776456, "math_qa": 5.51553217569987 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.015163002274450341, "math_qa": 0.0016750418760469012 } }, { "flos": 5.3357172106041754e+17, "train_loss": 5.77388916015625, "eval_loss": 5.8476459915573535, "eval_accuracy": 0.008117595436594998, "eval_loss_by_set": { "aqua_rat": 5.859452247619629, "gsm8k": 6.582734541459517, "math_qa": 5.509746551513672 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.01819560272934041, "math_qa": 0.0020100502512562816 } }, { "flos": 5.3986470821625856e+17, "train_loss": 5.78014892578125, "eval_loss": 5.84168021743362, "eval_accuracy": 0.008336989907854322, "eval_loss_by_set": { "aqua_rat": 5.858468055725098, "gsm8k": 6.574529474431818, "math_qa": 5.504391988118489 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.01819560272934041, "math_qa": 0.0016750418760469012 } }, { "flos": 5.462312660143964e+17, "train_loss": 5.7715478515625, "eval_loss": 5.8393572214487435, "eval_accuracy": 0.005923650724001755, "eval_loss_by_set": { "aqua_rat": 5.859663009643555, "gsm8k": 6.566329262473366, "math_qa": 5.504469553629558 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.012130401819560273, "math_qa": 0.001340033500837521 } }, { "flos": 5.525353196903465e+17, "train_loss": 5.77015869140625, "eval_loss": 5.833657032734639, "eval_accuracy": 0.008556384379113647, "eval_loss_by_set": { "aqua_rat": 5.855096817016602, "gsm8k": 6.562462546608665, "math_qa": 5.49783452351888 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.018953752843062926, "math_qa": 0.0016750418760469012 } }, { "flos": 5.588974466928476e+17, "train_loss": 5.77746826171875, "eval_loss": 5.840433378477354, "eval_accuracy": 0.006801228609039052, "eval_loss_by_set": { "aqua_rat": 5.855276107788086, "gsm8k": 6.5670318603515625, "math_qa": 5.506172180175781 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 5.651769149022536e+17, "train_loss": 5.771637573242187, "eval_loss": 5.843229603123021, "eval_accuracy": 0.008995173321632294, "eval_loss_by_set": { "aqua_rat": 5.854710578918457, "gsm8k": 6.5549448186701, "math_qa": 5.516070048014323 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.02122820318423048, "math_qa": 0.0016750418760469012 } }, { "flos": 5.7158821283784294e+17, "train_loss": 5.772491455078125, "eval_loss": 5.833652625212798, "eval_accuracy": 0.008336989907854322, "eval_loss_by_set": { "aqua_rat": 5.848351001739502, "gsm8k": 6.565921436656605, "math_qa": 5.496804555257161 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.019711902956785442, "math_qa": 0.001340033500837521 } }, { "flos": 5.779979237830164e+17, "train_loss": 5.7721240234375, "eval_loss": 5.8432144732088656, "eval_accuracy": 0.006581834137779728, "eval_loss_by_set": { "aqua_rat": 5.848937511444092, "gsm8k": 6.55413194136186, "math_qa": 5.516900380452474 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.014404852160727824, "math_qa": 0.001340033500837521 } }, { "flos": 5.843736314721075e+17, "train_loss": 5.784071044921875, "eval_loss": 5.838857341457057, "eval_accuracy": 0.006801228609039052, "eval_loss_by_set": { "aqua_rat": 5.845887184143066, "gsm8k": 6.571807861328125, "math_qa": 5.502335866292317 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.016679302501895376, "math_qa": 0.0016750418760469012 } }, { "flos": 5.906860522812211e+17, "train_loss": 5.768616333007812, "eval_loss": 5.84558543643436, "eval_accuracy": 0.007898200965335674, "eval_loss_by_set": { "aqua_rat": 5.848454475402832, "gsm8k": 6.566592129794034, "math_qa": 5.514884948730469 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.01592115238817286, "math_qa": 0.0020100502512562816 } }, { "flos": 5.97018524682027e+17, "train_loss": 5.76705078125, "eval_loss": 5.838122187434016, "eval_accuracy": 0.007678806494076349, "eval_loss_by_set": { "aqua_rat": 5.861186981201172, "gsm8k": 6.563113125887784, "math_qa": 5.503912607828776 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.017437452615617893, "math_qa": 0.0023450586264656616 } }, { "flos": 6.034318009869271e+17, "train_loss": 5.770086669921875, "eval_loss": 5.839583731986381, "eval_accuracy": 0.007459412022817025, "eval_loss_by_set": { "aqua_rat": 5.847541809082031, "gsm8k": 6.571596319025213, "math_qa": 5.503414789835612 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.016679302501895376, "math_qa": 0.0023450586264656616 } }, { "flos": 6.097573482898391e+17, "train_loss": 5.772010498046875, "eval_loss": 5.838450638023582, "eval_accuracy": 0.007459412022817025, "eval_loss_by_set": { "aqua_rat": 5.853068828582764, "gsm8k": 6.570539301091975, "math_qa": 5.501691818237305 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.01592115238817286, "math_qa": 0.0023450586264656616 } }, { "flos": 6.161450502119752e+17, "train_loss": 5.764474487304687, "eval_loss": 5.835246137670569, "eval_accuracy": 0.007898200965335674, "eval_loss_by_set": { "aqua_rat": 5.858547687530518, "gsm8k": 6.573880282315341, "math_qa": 5.494763692220052 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.01592115238817286, "math_qa": 0.0020100502512562816 } }, { "flos": 6.22520119024681e+17, "train_loss": 5.779044799804687, "eval_loss": 5.835372048455316, "eval_accuracy": 0.008556384379113647, "eval_loss_by_set": { "aqua_rat": 5.859206199645996, "gsm8k": 6.5504913330078125, "math_qa": 5.505622863769531 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.019711902956785442, "math_qa": 0.0016750418760469012 } }, { "flos": 6.288198449842094e+17, "train_loss": 5.76306884765625, "eval_loss": 5.835684595881282, "eval_accuracy": 0.007459412022817025, "eval_loss_by_set": { "aqua_rat": 5.859502792358398, "gsm8k": 6.575229991566051, "math_qa": 5.494741439819336 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.015163002274450341, "math_qa": 0.0016750418760469012 } }, { "flos": 6.352511741103964e+17, "train_loss": 5.772364501953125, "eval_loss": 5.839654303885795, "eval_accuracy": 0.008336989907854322, "eval_loss_by_set": { "aqua_rat": 5.857426643371582, "gsm8k": 6.548596468838778, "math_qa": 5.513241449991862 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.018953752843062926, "math_qa": 0.0016750418760469012 } }, { "flos": 6.415194523193836e+17, "train_loss": 5.75915283203125, "eval_loss": 5.83946029559986, "eval_accuracy": 0.007678806494076349, "eval_loss_by_set": { "aqua_rat": 5.858361721038818, "gsm8k": 6.569860284978693, "math_qa": 5.503118515014648 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.016679302501895376, "math_qa": 0.0016750418760469012 } }, { "flos": 6.478276683555144e+17, "train_loss": 5.762789916992188, "eval_loss": 5.837973620440509, "eval_accuracy": 0.007898200965335674, "eval_loss_by_set": { "aqua_rat": 5.860750198364258, "gsm8k": 6.5714111328125, "math_qa": 5.499916712443034 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.017437452615617893, "math_qa": 0.0020100502512562816 } }, { "flos": 6.541686925730775e+17, "train_loss": 5.76385986328125, "eval_loss": 5.841679341084248, "eval_accuracy": 0.005923650724001755, "eval_loss_by_set": { "aqua_rat": 5.8568267822265625, "gsm8k": 6.585209239612926, "math_qa": 5.499632517496745 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.01288855193328279, "math_qa": 0.0016750418760469012 } }, { "flos": 6.605446273585644e+17, "train_loss": 5.769010009765625, "eval_loss": 5.8335576444058805, "eval_accuracy": 0.010092145677928916, "eval_loss_by_set": { "aqua_rat": 5.858537673950195, "gsm8k": 6.571806474165483, "math_qa": 5.493111928304036 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.02350265352539803, "math_qa": 0.0020100502512562816 } }, { "flos": 6.668982020074373e+17, "train_loss": 5.7704638671875, "eval_loss": 5.840596070160737, "eval_accuracy": 0.007020623080298377, "eval_loss_by_set": { "aqua_rat": 5.852113723754883, "gsm8k": 6.5706870339133525, "math_qa": 5.505011240641276 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.015163002274450341, "math_qa": 0.0016750418760469012 } }, { "flos": 6.73152981671084e+17, "train_loss": 5.75508544921875, "eval_loss": 5.838096206252639, "eval_accuracy": 0.009214567792891619, "eval_loss_by_set": { "aqua_rat": 5.847938537597656, "gsm8k": 6.57109971479936, "math_qa": 5.501316070556641 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.02122820318423048, "math_qa": 0.0020100502512562816 } }, { "flos": 6.796385922045706e+17, "train_loss": 5.770562744140625, "eval_loss": 5.845432229944177, "eval_accuracy": 0.007459412022817025, "eval_loss_by_set": { "aqua_rat": 5.855587959289551, "gsm8k": 6.56725449995561, "math_qa": 5.513750712076823 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.017437452615617893, "math_qa": 0.0016750418760469012 } }, { "flos": 6.859563913864806e+17, "train_loss": 5.753179931640625, "eval_loss": 5.841560492644438, "eval_accuracy": 0.007898200965335674, "eval_loss_by_set": { "aqua_rat": 5.858465671539307, "gsm8k": 6.579861727627841, "math_qa": 5.501763661702474 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.01592115238817286, "math_qa": 0.0020100502512562816 } }, { "flos": 6.923140467911557e+17, "train_loss": 5.768797607421875, "eval_loss": 5.831701691086228, "eval_accuracy": 0.007678806494076349, "eval_loss_by_set": { "aqua_rat": 5.8572797775268555, "gsm8k": 6.567106073552912, "math_qa": 5.492509841918945 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.017437452615617893, "math_qa": 0.0016750418760469012 } }, { "flos": 6.986454057216901e+17, "train_loss": 5.753790283203125, "eval_loss": 5.848018491590345, "eval_accuracy": 0.007020623080298377, "eval_loss_by_set": { "aqua_rat": 5.857516288757324, "gsm8k": 6.561560890891335, "math_qa": 5.52018674214681 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.014404852160727824, "math_qa": 0.0016750418760469012 } }, { "flos": 7.05012890695893e+17, "train_loss": 5.760325927734375, "eval_loss": 5.829385087296769, "eval_accuracy": 0.008556384379113647, "eval_loss_by_set": { "aqua_rat": 5.862583160400391, "gsm8k": 6.578453757546165, "math_qa": 5.483295440673828 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.02047005307050796, "math_qa": 0.0016750418760469012 } }, { "flos": 7.113078760852685e+17, "train_loss": 5.762891845703125, "eval_loss": 5.828174900364232, "eval_accuracy": 0.009433962264150943, "eval_loss_by_set": { "aqua_rat": 5.860084533691406, "gsm8k": 6.571542913263494, "math_qa": 5.484805425008138 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.02350265352539803, "math_qa": 0.0016750418760469012 } }, { "flos": 7.176911058727076e+17, "train_loss": 5.751097412109375, "eval_loss": 5.8384789131783155, "eval_accuracy": 0.00614304519526108, "eval_loss_by_set": { "aqua_rat": 5.856143951416016, "gsm8k": 6.581609552556818, "math_qa": 5.496405283610026 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.01288855193328279, "math_qa": 0.0016750418760469012 } }, { "flos": 7.240457317148262e+17, "train_loss": 5.764850463867187, "eval_loss": 5.842019261540593, "eval_accuracy": 0.008117595436594998, "eval_loss_by_set": { "aqua_rat": 5.861932754516602, "gsm8k": 6.58551718971946, "math_qa": 5.499589920043945 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.019711902956785442, "math_qa": 0.0016750418760469012 } }, { "flos": 7.30505479565869e+17, "train_loss": 5.75206298828125, "eval_loss": 5.839856147766113, "eval_accuracy": 0.007240017551557701, "eval_loss_by_set": { "aqua_rat": 5.8615803718566895, "gsm8k": 6.562913374467329, "math_qa": 5.506644566853841 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.016679302501895376, "math_qa": 0.0020100502512562816 } }, { "flos": 7.367891310734213e+17, "train_loss": 5.759695434570313, "eval_loss": 5.840838097237252, "eval_accuracy": 0.008336989907854322, "eval_loss_by_set": { "aqua_rat": 5.854523658752441, "gsm8k": 6.585843172940341, "math_qa": 5.498236974080403 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.018953752843062926, "math_qa": 0.0016750418760469012 } }, { "flos": 7.4314359209617e+17, "train_loss": 5.753768310546875, "eval_loss": 5.839274896157755, "eval_accuracy": 0.007020623080298377, "eval_loss_by_set": { "aqua_rat": 5.857403755187988, "gsm8k": 6.557832197709517, "math_qa": 5.508425394694011 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.016679302501895376, "math_qa": 0.0016750418760469012 } }, { "flos": 7.495027926153298e+17, "train_loss": 5.76740234375, "eval_loss": 5.8355217753229915, "eval_accuracy": 0.008556384379113647, "eval_loss_by_set": { "aqua_rat": 5.857833385467529, "gsm8k": 6.555888782848012, "math_qa": 5.5034942626953125 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.016679302501895376, "math_qa": 0.003015075376884422 } }, { "flos": 7.558774083089859e+17, "train_loss": 5.759074096679687, "eval_loss": 5.84393547676705, "eval_accuracy": 0.010092145677928916, "eval_loss_by_set": { "aqua_rat": 5.85481071472168, "gsm8k": 6.568486993963068, "math_qa": 5.510943094889323 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.02577710386656558, "math_qa": 0.0020100502512562816 } }, { "flos": 7.622081289000059e+17, "train_loss": 5.756784057617187, "eval_loss": 5.852630615234375, "eval_accuracy": 0.008556384379113647, "eval_loss_by_set": { "aqua_rat": 5.86279296875, "gsm8k": 6.566979148171165, "math_qa": 5.524374008178711 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.018953752843062926, "math_qa": 0.0016750418760469012 } }, { "flos": 7.68547731483394e+17, "train_loss": 5.75287353515625, "eval_loss": 5.846035416061814, "eval_accuracy": 0.008556384379113647, "eval_loss_by_set": { "aqua_rat": 5.859964370727539, "gsm8k": 6.577441822398793, "math_qa": 5.509646733601888 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.017437452615617893, "math_qa": 0.0016750418760469012 } }, { "flos": 7.749094252310692e+17, "train_loss": 5.758126831054687, "eval_loss": 5.842249870300293, "eval_accuracy": 0.006801228609039052, "eval_loss_by_set": { "aqua_rat": 5.852534770965576, "gsm8k": 6.5755226828835225, "math_qa": 5.505309422810872 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.015163002274450341, "math_qa": 0.0020100502512562816 } }, { "flos": 7.813099658841948e+17, "train_loss": 5.752449340820313, "eval_loss": 5.845747509518185, "eval_accuracy": 0.009872751206669592, "eval_loss_by_set": { "aqua_rat": 5.86061954498291, "gsm8k": 6.593467712402344, "math_qa": 5.501803080240886 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.022744503411675512, "math_qa": 0.0016750418760469012 } }, { "flos": 7.876598312919368e+17, "train_loss": 5.75392578125, "eval_loss": 5.834204132492478, "eval_accuracy": 0.008775778850372971, "eval_loss_by_set": { "aqua_rat": 5.861708641052246, "gsm8k": 6.5765464089133525, "math_qa": 5.491671880086263 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.02122820318423048, "math_qa": 0.0016750418760469012 } }, { "flos": 7.939623801187205e+17, "train_loss": 5.75746826171875, "eval_loss": 5.8439856864310595, "eval_accuracy": 0.008336989907854322, "eval_loss_by_set": { "aqua_rat": 5.86065673828125, "gsm8k": 6.565820173783735, "math_qa": 5.511755625406901 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.02047005307050796, "math_qa": 0.0016750418760469012 } }, { "flos": 8.003593554121196e+17, "train_loss": 5.756728515625, "eval_loss": 5.830074928902291, "eval_accuracy": 0.010092145677928916, "eval_loss_by_set": { "aqua_rat": 5.872735977172852, "gsm8k": 6.576189908114347, "math_qa": 5.484550476074219 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.024260803639120546, "math_qa": 0.0020100502512562816 } }, { "flos": 8.067241614004716e+17, "train_loss": 5.756693725585937, "eval_loss": 5.840397190403294, "eval_accuracy": 0.009872751206669592, "eval_loss_by_set": { "aqua_rat": 5.867454528808594, "gsm8k": 6.578531438654119, "math_qa": 5.499830881754558 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.018953752843062926, "math_qa": 0.0033500837520938024 } }, { "flos": 8.131313377780695e+17, "train_loss": 5.752703857421875, "eval_loss": 5.84335961212983, "eval_accuracy": 0.008117595436594998, "eval_loss_by_set": { "aqua_rat": 5.8637800216674805, "gsm8k": 6.59466552734375, "math_qa": 5.4973093668619795 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.016679302501895376, "math_qa": 0.0023450586264656616 } }, { "flos": 8.194558961647616e+17, "train_loss": 5.752555541992187, "eval_loss": 5.843385490211281, "eval_accuracy": 0.010969723562966213, "eval_loss_by_set": { "aqua_rat": 5.876553535461426, "gsm8k": 6.582977988503196, "math_qa": 5.501641591389974 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.02577710386656558, "math_qa": 0.0023450586264656616 } }, { "flos": 8.258417426610258e+17, "train_loss": 5.750865478515625, "eval_loss": 5.842476045763171, "eval_accuracy": 0.008556384379113647, "eval_loss_by_set": { "aqua_rat": 5.869223594665527, "gsm8k": 6.578338623046875, "math_qa": 5.502976735432942 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.017437452615617893, "math_qa": 0.0033500837520938024 } }, { "flos": 8.321363372083773e+17, "train_loss": 5.754112548828125, "eval_loss": 5.848483730006862, "eval_accuracy": 0.008775778850372971, "eval_loss_by_set": { "aqua_rat": 5.856616973876953, "gsm8k": 6.584583629261363, "math_qa": 5.510426839192708 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.017437452615617893, "math_qa": 0.0020100502512562816 } }, { "flos": 8.385661620222689e+17, "train_loss": 5.749881591796875, "eval_loss": 5.839836429905247, "eval_accuracy": 0.010092145677928916, "eval_loss_by_set": { "aqua_rat": 5.877706527709961, "gsm8k": 6.560615539550781, "math_qa": 5.506323496500651 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.021986353297952996, "math_qa": 0.002680067001675042 } }, { "flos": 8.448607152305603e+17, "train_loss": 5.75061767578125, "eval_loss": 5.843316877210462, "eval_accuracy": 0.008117595436594998, "eval_loss_by_set": { "aqua_rat": 5.864953994750977, "gsm8k": 6.571791908957741, "math_qa": 5.50762939453125 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.017437452615617893, "math_qa": 0.0020100502512562816 } }, { "flos": 8.512098794848911e+17, "train_loss": 5.746463012695313, "eval_loss": 5.842908756153004, "eval_accuracy": 0.011189118034225537, "eval_loss_by_set": { "aqua_rat": 5.868680000305176, "gsm8k": 6.575589960271662, "math_qa": 5.5049489339192705 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.025018953752843062, "math_qa": 0.0033500837520938024 } }, { "flos": 8.575703786947871e+17, "train_loss": 5.74794189453125, "eval_loss": 5.848260157817119, "eval_accuracy": 0.009872751206669592, "eval_loss_by_set": { "aqua_rat": 5.859156608581543, "gsm8k": 6.587890625, "math_qa": 5.508354822794597 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.025018953752843062, "math_qa": 0.0016750418760469012 } }, { "flos": 8.639008104492564e+17, "train_loss": 5.752807006835938, "eval_loss": 5.832439706132218, "eval_accuracy": 0.008995173321632294, "eval_loss_by_set": { "aqua_rat": 5.863261699676514, "gsm8k": 6.563078446821733, "math_qa": 5.4949951171875 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.018953752843062926, "math_qa": 0.003015075376884422 } }, { "flos": 8.702961992891105e+17, "train_loss": 5.742869873046875, "eval_loss": 5.844405689755002, "eval_accuracy": 0.01075032909170689, "eval_loss_by_set": { "aqua_rat": 5.859553813934326, "gsm8k": 6.595164212313565, "math_qa": 5.499045689900716 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.02122820318423048, "math_qa": 0.004355108877721943 } }, { "flos": 8.766118139432796e+17, "train_loss": 5.748558349609375, "eval_loss": 5.846232285370698, "eval_accuracy": 0.008995173321632294, "eval_loss_by_set": { "aqua_rat": 5.864621162414551, "gsm8k": 6.600031766024503, "math_qa": 5.499208450317383 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.018953752843062926, "math_qa": 0.002680067001675042 } }, { "flos": 8.829232039602422e+17, "train_loss": 5.736900024414062, "eval_loss": 5.852045059204102, "eval_accuracy": 0.009433962264150943, "eval_loss_by_set": { "aqua_rat": 5.866021156311035, "gsm8k": 6.5974814675071025, "math_qa": 5.509222030639648 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.019711902956785442, "math_qa": 0.0033500837520938024 } }, { "flos": 8.892955728491315e+17, "train_loss": 5.752646484375, "eval_loss": 5.84989849296776, "eval_accuracy": 0.008336989907854322, "eval_loss_by_set": { "aqua_rat": 5.8782429695129395, "gsm8k": 6.592364224520597, "math_qa": 5.507239659627278 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.01819560272934041, "math_qa": 0.0016750418760469012 } }, { "flos": 8.956258607221965e+17, "train_loss": 5.749705200195312, "eval_loss": 5.838389602867332, "eval_accuracy": 0.008995173321632294, "eval_loss_by_set": { "aqua_rat": 5.869494915008545, "gsm8k": 6.574770147150213, "math_qa": 5.498289744059245 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.02047005307050796, "math_qa": 0.0016750418760469012 } }, { "flos": 9.020001462402417e+17, "train_loss": 5.751508178710938, "eval_loss": 5.854874430476008, "eval_accuracy": 0.008775778850372971, "eval_loss_by_set": { "aqua_rat": 5.860259056091309, "gsm8k": 6.576015125621449, "math_qa": 5.523902893066406 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.02047005307050796, "math_qa": 0.0016750418760469012 } }, { "flos": 9.083058486467625e+17, "train_loss": 5.743761596679687, "eval_loss": 5.838105047071302, "eval_accuracy": 0.010969723562966213, "eval_loss_by_set": { "aqua_rat": 5.8655924797058105, "gsm8k": 6.576113614169034, "math_qa": 5.497560501098633 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.022744503411675512, "math_qa": 0.0023450586264656616 } }, { "flos": 9.146905419443077e+17, "train_loss": 5.745386352539063, "eval_loss": 5.843233288945378, "eval_accuracy": 0.008995173321632294, "eval_loss_by_set": { "aqua_rat": 5.8632283210754395, "gsm8k": 6.570406827059659, "math_qa": 5.508279164632161 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.018953752843062926, "math_qa": 0.0020100502512562816 } }, { "flos": 9.210570793413509e+17, "train_loss": 5.7525830078125, "eval_loss": 5.846038921459301, "eval_accuracy": 0.009872751206669592, "eval_loss_by_set": { "aqua_rat": 5.872014999389648, "gsm8k": 6.584627324884588, "math_qa": 5.505354563395183 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.02122820318423048, "math_qa": 0.0016750418760469012 } }, { "flos": 9.273761766771261e+17, "train_loss": 5.744847412109375, "eval_loss": 5.842844473349081, "eval_accuracy": 0.009433962264150943, "eval_loss_by_set": { "aqua_rat": 5.864068984985352, "gsm8k": 6.567445234818892, "math_qa": 5.5089670817057295 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.019711902956785442, "math_qa": 0.0020100502512562816 } }, { "flos": 9.337984380536095e+17, "train_loss": 5.746480102539063, "eval_loss": 5.8479897267109635, "eval_accuracy": 0.009433962264150943, "eval_loss_by_set": { "aqua_rat": 5.8586626052856445, "gsm8k": 6.583873401988637, "math_qa": 5.509820302327474 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.019711902956785442, "math_qa": 0.0016750418760469012 } }, { "flos": 9.400886839465738e+17, "train_loss": 5.744608154296875, "eval_loss": 5.844652072803394, "eval_accuracy": 0.009872751206669592, "eval_loss_by_set": { "aqua_rat": 5.861781120300293, "gsm8k": 6.581548517400568, "math_qa": 5.505480448404948 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.021986353297952996, "math_qa": 0.0020100502512562816 } }, { "flos": 9.464234020784046e+17, "train_loss": 5.739625244140625, "eval_loss": 5.860201345907675, "eval_accuracy": 0.007898200965335674, "eval_loss_by_set": { "aqua_rat": 5.870855331420898, "gsm8k": 6.59362099387429, "math_qa": 5.523162841796875 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.016679302501895376, "math_qa": 0.0020100502512562816 } }, { "flos": 9.527827056767795e+17, "train_loss": 5.7309716796875, "eval_loss": 5.835406896230337, "eval_accuracy": 0.009653356735410267, "eval_loss_by_set": { "aqua_rat": 5.878436088562012, "gsm8k": 6.5985260009765625, "math_qa": 5.482058207194011 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.021986353297952996, "math_qa": 0.0020100502512562816 } }, { "flos": 9.591528905747988e+17, "train_loss": 5.745256958007812, "eval_loss": 5.833984014150259, "eval_accuracy": 0.008995173321632294, "eval_loss_by_set": { "aqua_rat": 5.8704423904418945, "gsm8k": 6.592155456542969, "math_qa": 5.483450571695964 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.019711902956785442, "math_qa": 0.0023450586264656616 } }, { "flos": 9.654876500456899e+17, "train_loss": 5.74080322265625, "eval_loss": 5.84394207516232, "eval_accuracy": 0.01075032909170689, "eval_loss_by_set": { "aqua_rat": 5.863801956176758, "gsm8k": 6.58188213001598, "math_qa": 5.504064559936523 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.02577710386656558, "math_qa": 0.0016750418760469012 } }, { "flos": 9.718267785720627e+17, "train_loss": 5.74234130859375, "eval_loss": 5.845031686731287, "eval_accuracy": 0.008775778850372971, "eval_loss_by_set": { "aqua_rat": 5.8637800216674805, "gsm8k": 6.580750205300071, "math_qa": 5.506265004475911 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.021986353297952996, "math_qa": 0.0016750418760469012 } }, { "flos": 9.781734495978783e+17, "train_loss": 5.73348388671875, "eval_loss": 5.833405829764701, "eval_accuracy": 0.009214567792891619, "eval_loss_by_set": { "aqua_rat": 5.864151954650879, "gsm8k": 6.5645530007102275, "math_qa": 5.495734532674153 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.02122820318423048, "math_qa": 0.0020100502512562816 } }, { "flos": 9.845480035513795e+17, "train_loss": 5.749096069335938, "eval_loss": 5.833390880275417, "eval_accuracy": 0.008775778850372971, "eval_loss_by_set": { "aqua_rat": 5.87155818939209, "gsm8k": 6.5684051513671875, "math_qa": 5.4933287302653 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.017437452615617893, "math_qa": 0.0020100502512562816 } }, { "flos": 9.90905473198719e+17, "train_loss": 5.744041748046875, "eval_loss": 5.836931847237252, "eval_accuracy": 0.009872751206669592, "eval_loss_by_set": { "aqua_rat": 5.859116554260254, "gsm8k": 6.574189619584517, "math_qa": 5.497173309326172 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.021986353297952996, "math_qa": 0.0023450586264656616 } }, { "flos": 9.972055287969874e+17, "train_loss": 5.7363525390625, "eval_loss": 5.838341429426864, "eval_accuracy": 0.010969723562966213, "eval_loss_by_set": { "aqua_rat": 5.870541572570801, "gsm8k": 6.57647080854936, "math_qa": 5.497348785400391 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.026535253980288095, "math_qa": 0.0020100502512562816 } }, { "flos": 1.0035665224649933e+18, "train_loss": 5.733084716796875, "eval_loss": 5.843147716006717, "eval_accuracy": 0.007678806494076349, "eval_loss_by_set": { "aqua_rat": 5.866779804229736, "gsm8k": 6.591709483753551, "math_qa": 5.498087565104167 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.015163002274450341, "math_qa": 0.0020100502512562816 } }, { "flos": 1.0099426419340739e+18, "train_loss": 5.736292114257813, "eval_loss": 5.841304315103067, "eval_accuracy": 0.009214567792891619, "eval_loss_by_set": { "aqua_rat": 5.875885963439941, "gsm8k": 6.581898775967685, "math_qa": 5.498983383178711 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.019711902956785442, "math_qa": 0.003015075376884422 } }, { "flos": 1.0162371747412705e+18, "train_loss": 5.73486083984375, "eval_loss": 5.847550521025786, "eval_accuracy": 0.010530934620447565, "eval_loss_by_set": { "aqua_rat": 5.863228797912598, "gsm8k": 6.581216291947798, "math_qa": 5.50998051961263 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.021986353297952996, "math_qa": 0.0020100502512562816 } }, { "flos": 1.0225914709446492e+18, "train_loss": 5.747984008789063, "eval_loss": 5.826867077801679, "eval_accuracy": 0.009653356735410267, "eval_loss_by_set": { "aqua_rat": 5.87138557434082, "gsm8k": 6.575854908336293, "math_qa": 5.479871114095052 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.019711902956785442, "math_qa": 0.002680067001675042 } }, { "flos": 1.0289573281262469e+18, "train_loss": 5.74415771484375, "eval_loss": 5.839379542582744, "eval_accuracy": 0.010530934620447565, "eval_loss_by_set": { "aqua_rat": 5.870516777038574, "gsm8k": 6.565179998224432, "math_qa": 5.504126230875651 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.025018953752843062, "math_qa": 0.0020100502512562816 } }, { "flos": 1.0352727575599514e+18, "train_loss": 5.729827880859375, "eval_loss": 5.850594597893792, "eval_accuracy": 0.008117595436594998, "eval_loss_by_set": { "aqua_rat": 5.870281219482422, "gsm8k": 6.579525340687145, "math_qa": 5.51486078898112 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.017437452615617893, "math_qa": 0.0020100502512562816 } }, { "flos": 1.04157318413602e+18, "train_loss": 5.74358642578125, "eval_loss": 5.856775129163587, "eval_accuracy": 0.009872751206669592, "eval_loss_by_set": { "aqua_rat": 5.860429763793945, "gsm8k": 6.57903428511186, "math_qa": 5.525435129801433 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.02047005307050796, "math_qa": 0.0036850921273031824 } }, { "flos": 1.0479382993620173e+18, "train_loss": 5.736708984375, "eval_loss": 5.835579382406698, "eval_accuracy": 0.008775778850372971, "eval_loss_by_set": { "aqua_rat": 5.871838569641113, "gsm8k": 6.560145984996449, "math_qa": 5.500464757283528 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.019711902956785442, "math_qa": 0.0016750418760469012 } }, { "flos": 1.0543062787943301e+18, "train_loss": 5.740974731445313, "eval_loss": 5.843617310395112, "eval_accuracy": 0.008995173321632294, "eval_loss_by_set": { "aqua_rat": 5.873617172241211, "gsm8k": 6.580418673428622, "math_qa": 5.503416697184245 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.01819560272934041, "math_qa": 0.0033500837520938024 } }, { "flos": 1.0606818216640512e+18, "train_loss": 5.738839111328125, "eval_loss": 5.847476340628959, "eval_accuracy": 0.010092145677928916, "eval_loss_by_set": { "aqua_rat": 5.865304946899414, "gsm8k": 6.57967792857777, "math_qa": 5.510398228963216 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.019711902956785442, "math_qa": 0.003015075376884422 } }, { "flos": 1.0669963437859144e+18, "train_loss": 5.742744140625, "eval_loss": 5.836789234264477, "eval_accuracy": 0.012066695919262835, "eval_loss_by_set": { "aqua_rat": 5.863749027252197, "gsm8k": 6.565164739435369, "math_qa": 5.500703811645508 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.02047005307050796, "math_qa": 0.004020100502512563 } }, { "flos": 1.07337071198208e+18, "train_loss": 5.737554931640625, "eval_loss": 5.826194015709129, "eval_accuracy": 0.011408512505484861, "eval_loss_by_set": { "aqua_rat": 5.878110408782959, "gsm8k": 6.557954268022017, "math_qa": 5.486477533976237 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.022744503411675512, "math_qa": 0.0023450586264656616 } }, { "flos": 1.0796654096086467e+18, "train_loss": 5.728143310546875, "eval_loss": 5.84783664909569, "eval_accuracy": 0.009433962264150943, "eval_loss_by_set": { "aqua_rat": 5.867904186248779, "gsm8k": 6.596257296475497, "math_qa": 5.5031382242838545 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.02122820318423048, "math_qa": 0.002680067001675042 } }, { "flos": 1.0860783766759014e+18, "train_loss": 5.7460174560546875, "eval_loss": 5.850114513087917, "eval_accuracy": 0.012944273804300131, "eval_loss_by_set": { "aqua_rat": 5.870871543884277, "gsm8k": 6.586712923916903, "math_qa": 5.5107771555582685 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.025018953752843062, "math_qa": 0.005695142378559464 } }, { "flos": 1.092424450164392e+18, "train_loss": 5.73748291015625, "eval_loss": 5.836964581463788, "eval_accuracy": 0.011627906976744186, "eval_loss_by_set": { "aqua_rat": 5.880290985107422, "gsm8k": 6.5836944580078125, "math_qa": 5.491102854410808 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.019711902956785442, "math_qa": 0.004355108877721943 } }, { "flos": 1.0987813222744064e+18, "train_loss": 5.731854248046875, "eval_loss": 5.833893363540237, "eval_accuracy": 0.011408512505484861, "eval_loss_by_set": { "aqua_rat": 5.8701348304748535, "gsm8k": 6.573877507990057, "math_qa": 5.491713841756185 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.02047005307050796, "math_qa": 0.0036850921273031824 } }, { "flos": 1.1051657884755558e+18, "train_loss": 5.740037841796875, "eval_loss": 5.846772219683673, "eval_accuracy": 0.010092145677928916, "eval_loss_by_set": { "aqua_rat": 5.868453025817871, "gsm8k": 6.580242503773082, "math_qa": 5.508791605631511 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.02122820318423048, "math_qa": 0.0023450586264656616 } }, { "flos": 1.1114983843566715e+18, "train_loss": 5.737159423828125, "eval_loss": 5.844658104149071, "eval_accuracy": 0.009872751206669592, "eval_loss_by_set": { "aqua_rat": 5.87750244140625, "gsm8k": 6.5798728249289775, "math_qa": 5.504947662353516 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.02122820318423048, "math_qa": 0.002680067001675042 } }, { "flos": 1.117827558759465e+18, "train_loss": 5.733280029296875, "eval_loss": 5.844634288066143, "eval_accuracy": 0.010311540149188241, "eval_loss_by_set": { "aqua_rat": 5.870904922485352, "gsm8k": 6.577786532315341, "math_qa": 5.506416956583659 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.02122820318423048, "math_qa": 0.002680067001675042 } }, { "flos": 1.1242534058967695e+18, "train_loss": 5.73679931640625, "eval_loss": 5.834009325182116, "eval_accuracy": 0.009653356735410267, "eval_loss_by_set": { "aqua_rat": 5.878337860107422, "gsm8k": 6.5953896262428975, "math_qa": 5.4813493092854815 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.02122820318423048, "math_qa": 0.0023450586264656616 } }, { "flos": 1.130614255683371e+18, "train_loss": 5.74289794921875, "eval_loss": 5.843946405359216, "eval_accuracy": 0.007459412022817025, "eval_loss_by_set": { "aqua_rat": 5.870141983032227, "gsm8k": 6.5831992409446025, "math_qa": 5.502939224243164 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.016679302501895376, "math_qa": 0.0020100502512562816 } }, { "flos": 1.1369803807635538e+18, "train_loss": 5.73954345703125, "eval_loss": 5.857671660345954, "eval_accuracy": 0.009214567792891619, "eval_loss_by_set": { "aqua_rat": 5.870706081390381, "gsm8k": 6.58867783979936, "math_qa": 5.5215409596761065 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.02047005307050796, "math_qa": 0.0023450586264656616 } }, { "flos": 1.1433104002011628e+18, "train_loss": 5.731764526367187, "eval_loss": 5.847066956597406, "eval_accuracy": 0.008995173321632294, "eval_loss_by_set": { "aqua_rat": 5.866077899932861, "gsm8k": 6.577698447487571, "math_qa": 5.510609944661458 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.01819560272934041, "math_qa": 0.0023450586264656616 } }, { "flos": 1.149613464424022e+18, "train_loss": 5.732477416992188, "eval_loss": 5.827940760432063, "eval_accuracy": 0.011189118034225537, "eval_loss_by_set": { "aqua_rat": 5.870634078979492, "gsm8k": 6.570727955211293, "math_qa": 5.483938852945964 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.019711902956785442, "math_qa": 0.005360134003350084 } }, { "flos": 1.1559905320071332e+18, "train_loss": 5.7355517578125, "eval_loss": 5.846527331584209, "eval_accuracy": 0.009214567792891619, "eval_loss_by_set": { "aqua_rat": 5.8697285652160645, "gsm8k": 6.573697870427912, "math_qa": 5.51130739847819 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.019711902956785442, "math_qa": 0.0023450586264656616 } }, { "flos": 1.1623539985025597e+18, "train_loss": 5.7290887451171875, "eval_loss": 5.831654909494761, "eval_accuracy": 0.010311540149188241, "eval_loss_by_set": { "aqua_rat": 5.88795804977417, "gsm8k": 6.569380326704546, "math_qa": 5.488838831583659 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.02047005307050796, "math_qa": 0.002680067001675042 } }, { "flos": 1.1686711792091791e+18, "train_loss": 5.736987915039062, "eval_loss": 5.838750091758934, "eval_accuracy": 0.009653356735410267, "eval_loss_by_set": { "aqua_rat": 5.86845064163208, "gsm8k": 6.573101390491832, "math_qa": 5.499697367350261 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.02122820318423048, "math_qa": 0.003015075376884422 } }, { "flos": 1.1750358203781612e+18, "train_loss": 5.743927001953125, "eval_loss": 5.843814437453811, "eval_accuracy": 0.01338306274681878, "eval_loss_by_set": { "aqua_rat": 5.869684219360352, "gsm8k": 6.570340243252841, "math_qa": 5.508667627970378 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.029567854435178165, "math_qa": 0.0036850921273031824 } }, { "flos": 1.1813785137273897e+18, "train_loss": 5.730951538085938, "eval_loss": 5.8382771981729045, "eval_accuracy": 0.01075032909170689, "eval_loss_by_set": { "aqua_rat": 5.872057914733887, "gsm8k": 6.5934975363991475, "math_qa": 5.489319483439128 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.019711902956785442, "math_qa": 0.004020100502512563 } }, { "flos": 1.1877261328672358e+18, "train_loss": 5.734376220703125, "eval_loss": 5.842470787666939, "eval_accuracy": 0.010092145677928916, "eval_loss_by_set": { "aqua_rat": 5.876736640930176, "gsm8k": 6.589923511851918, "math_qa": 5.497032801310222 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.01819560272934041, "math_qa": 0.0033500837520938024 } }, { "flos": 1.1940639219006833e+18, "train_loss": 5.731685791015625, "eval_loss": 5.85742068935085, "eval_accuracy": 0.010969723562966213, "eval_loss_by_set": { "aqua_rat": 5.8673906326293945, "gsm8k": 6.583280389959162, "math_qa": 5.523904164632161 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.021986353297952996, "math_qa": 0.0036850921273031824 } }, { "flos": 1.20042606984115e+18, "train_loss": 5.731080322265625, "eval_loss": 5.846458125758815, "eval_accuracy": 0.011189118034225537, "eval_loss_by_set": { "aqua_rat": 5.87318229675293, "gsm8k": 6.576130260120738, "math_qa": 5.509798049926758 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.024260803639120546, "math_qa": 0.003015075376884422 } }, { "flos": 1.2067386141305733e+18, "train_loss": 5.731104736328125, "eval_loss": 5.851908503351985, "eval_accuracy": 0.009214567792891619, "eval_loss_by_set": { "aqua_rat": 5.866065979003906, "gsm8k": 6.592106212269176, "math_qa": 5.511471430460612 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.019711902956785442, "math_qa": 0.002680067001675042 } }, { "flos": 1.2130601230904852e+18, "train_loss": 5.725870361328125, "eval_loss": 5.834202843743402, "eval_accuracy": 0.011627906976744186, "eval_loss_by_set": { "aqua_rat": 5.873701095581055, "gsm8k": 6.580472079190341, "math_qa": 5.488871256510417 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.017437452615617893, "math_qa": 0.007370184254606365 } }, { "flos": 1.219395438759641e+18, "train_loss": 5.729169311523438, "eval_loss": 5.836916871972986, "eval_accuracy": 0.009653356735410267, "eval_loss_by_set": { "aqua_rat": 5.8773674964904785, "gsm8k": 6.575239008123225, "math_qa": 5.495148340861003 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.018953752843062926, "math_qa": 0.0036850921273031824 } }, { "flos": 1.2257320117804728e+18, "train_loss": 5.726469116210938, "eval_loss": 5.83571464950974, "eval_accuracy": 0.014260640631856078, "eval_loss_by_set": { "aqua_rat": 5.875000953674316, "gsm8k": 6.589221607555043, "math_qa": 5.487083435058594 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.029567854435178165, "math_qa": 0.004355108877721943 } }, { "flos": 1.2320424740844995e+18, "train_loss": 5.73289306640625, "eval_loss": 5.850400873132654, "eval_accuracy": 0.010092145677928916, "eval_loss_by_set": { "aqua_rat": 5.878366470336914, "gsm8k": 6.591891202059659, "math_qa": 5.508220672607422 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.02350265352539803, "math_qa": 0.002680067001675042 } }, { "flos": 1.238434729745711e+18, "train_loss": 5.72353271484375, "eval_loss": 5.85305067010828, "eval_accuracy": 0.009872751206669592, "eval_loss_by_set": { "aqua_rat": 5.871143817901611, "gsm8k": 6.592214410955256, "math_qa": 5.512759526570638 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.02047005307050796, "math_qa": 0.002680067001675042 } }, { "flos": 1.244754012838822e+18, "train_loss": 5.728684692382813, "eval_loss": 5.837476988096495, "eval_accuracy": 0.01075032909170689, "eval_loss_by_set": { "aqua_rat": 5.879631042480469, "gsm8k": 6.595611572265625, "math_qa": 5.4864857991536455 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.02122820318423048, "math_qa": 0.0033500837520938024 } }, { "flos": 1.2511277834976625e+18, "train_loss": 5.724302978515625, "eval_loss": 5.84898667722135, "eval_accuracy": 0.011189118034225537, "eval_loss_by_set": { "aqua_rat": 5.868481159210205, "gsm8k": 6.588292208584872, "math_qa": 5.508513768513997 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.02577710386656558, "math_qa": 0.0020100502512562816 } }, { "flos": 1.2575004412231025e+18, "train_loss": 5.725809936523437, "eval_loss": 5.842264072315113, "eval_accuracy": 0.009872751206669592, "eval_loss_by_set": { "aqua_rat": 5.872374534606934, "gsm8k": 6.571011629971591, "math_qa": 5.505745569864909 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.017437452615617893, "math_qa": 0.002680067001675042 } }, { "flos": 1.263844762901807e+18, "train_loss": 5.729273681640625, "eval_loss": 5.831288775882205, "eval_accuracy": 0.012944273804300131, "eval_loss_by_set": { "aqua_rat": 5.8801164627075195, "gsm8k": 6.578180486505682, "math_qa": 5.484894434611003 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.028051554207733132, "math_qa": 0.0033500837520938024 } }, { "flos": 1.270172062551376e+18, "train_loss": 5.719057006835937, "eval_loss": 5.833060754312052, "eval_accuracy": 0.008556384379113647, "eval_loss_by_set": { "aqua_rat": 5.877028465270996, "gsm8k": 6.569338018243963, "math_qa": 5.491936365763347 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.01819560272934041, "math_qa": 0.0020100502512562816 } }, { "flos": 1.2765289341245194e+18, "train_loss": 5.724267578125, "eval_loss": 5.847815565160803, "eval_accuracy": 0.011408512505484861, "eval_loss_by_set": { "aqua_rat": 5.874674320220947, "gsm8k": 6.601973100142046, "math_qa": 5.499921798706055 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.022744503411675512, "math_qa": 0.004355108877721943 } }, { "flos": 1.2828385932696617e+18, "train_loss": 5.728148193359375, "eval_loss": 5.839256312396075, "eval_accuracy": 0.01228609039052216, "eval_loss_by_set": { "aqua_rat": 5.8754353523254395, "gsm8k": 6.577045093883168, "math_qa": 5.498088200887044 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.018953752843062926, "math_qa": 0.006030150753768844 } }, { "flos": 1.2892222353739612e+18, "train_loss": 5.724771728515625, "eval_loss": 5.843344765740472, "eval_accuracy": 0.01338306274681878, "eval_loss_by_set": { "aqua_rat": 5.877825736999512, "gsm8k": 6.600702459161932, "math_qa": 5.493349075317383 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.022744503411675512, "math_qa": 0.006700167504187605 } }, { "flos": 1.295597530746192e+18, "train_loss": 5.721458129882812, "eval_loss": 5.846197721120474, "eval_accuracy": 0.009653356735410267, "eval_loss_by_set": { "aqua_rat": 5.8708367347717285, "gsm8k": 6.596883600408381, "math_qa": 5.500080108642578 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.016679302501895376, "math_qa": 0.0033500837520938024 } }, { "flos": 1.301932722935038e+18, "train_loss": 5.74052001953125, "eval_loss": 5.846400853749868, "eval_accuracy": 0.012505484861781484, "eval_loss_by_set": { "aqua_rat": 5.88675594329834, "gsm8k": 6.584978970614347, "math_qa": 5.504522959391276 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.024260803639120546, "math_qa": 0.004020100502512563 } }, { "flos": 1.3082806303745638e+18, "train_loss": 5.724971313476562, "eval_loss": 5.841821567432301, "eval_accuracy": 0.011408512505484861, "eval_loss_by_set": { "aqua_rat": 5.872145652770996, "gsm8k": 6.5755462646484375, "math_qa": 5.50300407409668 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.01819560272934041, "math_qa": 0.004355108877721943 } }, { "flos": 1.3146352148776223e+18, "train_loss": 5.719453125, "eval_loss": 5.84595876126676, "eval_accuracy": 0.011189118034225537, "eval_loss_by_set": { "aqua_rat": 5.874457359313965, "gsm8k": 6.585796009410512, "math_qa": 5.504491806030273 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.02350265352539803, "math_qa": 0.0016750418760469012 } }, { "flos": 1.3210029677504102e+18, "train_loss": 5.720608520507812, "eval_loss": 5.847674034737252, "eval_accuracy": 0.012944273804300131, "eval_loss_by_set": { "aqua_rat": 5.880204200744629, "gsm8k": 6.5806121826171875, "math_qa": 5.509033203125 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.022744503411675512, "math_qa": 0.004690117252931323 } }, { "flos": 1.327305290017669e+18, "train_loss": 5.726805419921875, "eval_loss": 5.843283292409536, "eval_accuracy": 0.008995173321632294, "eval_loss_by_set": { "aqua_rat": 5.8771843910217285, "gsm8k": 6.595536665482954, "math_qa": 5.495675404866536 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.014404852160727824, "math_qa": 0.0033500837520938024 } }, { "flos": 1.333715145381118e+18, "train_loss": 5.724612426757813, "eval_loss": 5.848234047760835, "eval_accuracy": 0.009872751206669592, "eval_loss_by_set": { "aqua_rat": 5.8840107917785645, "gsm8k": 6.601766412908381, "math_qa": 5.499883651733398 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.02047005307050796, "math_qa": 0.0036850921273031824 } }, { "flos": 1.340075912489599e+18, "train_loss": 5.723666381835938, "eval_loss": 5.840088457674594, "eval_accuracy": 0.012944273804300131, "eval_loss_by_set": { "aqua_rat": 5.879809379577637, "gsm8k": 6.580419367009943, "math_qa": 5.497460047403972 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.02047005307050796, "math_qa": 0.007035175879396985 } }, { "flos": 1.3464146292359823e+18, "train_loss": 5.7343310546875, "eval_loss": 5.8430627874425936, "eval_accuracy": 0.010969723562966213, "eval_loss_by_set": { "aqua_rat": 5.88033390045166, "gsm8k": 6.58637792413885, "math_qa": 5.499270757039388 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.017437452615617893, "math_qa": 0.005025125628140704 } }, { "flos": 1.3527651335201096e+18, "train_loss": 5.7246466064453125, "eval_loss": 5.836748793318465, "eval_accuracy": 0.010092145677928916, "eval_loss_by_set": { "aqua_rat": 5.889970779418945, "gsm8k": 6.579188953746449, "math_qa": 5.492028554280599 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.017437452615617893, "math_qa": 0.0036850921273031824 } }, { "flos": 1.359105704618623e+18, "train_loss": 5.72000244140625, "eval_loss": 5.848521670779666, "eval_accuracy": 0.010969723562966213, "eval_loss_by_set": { "aqua_rat": 5.874614715576172, "gsm8k": 6.591859297318892, "math_qa": 5.5056508382161455 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.01819560272934041, "math_qa": 0.004355108877721943 } }, { "flos": 1.3654301599261e+18, "train_loss": 5.7256402587890625, "eval_loss": 5.851678745166676, "eval_accuracy": 0.007240017551557701, "eval_loss_by_set": { "aqua_rat": 5.8814802169799805, "gsm8k": 6.583750638094815, "math_qa": 5.513662338256836 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.014404852160727824, "math_qa": 0.003015075376884422 } }, { "flos": 1.3717027245124485e+18, "train_loss": 5.71593994140625, "eval_loss": 5.845399908117346, "eval_accuracy": 0.010311540149188241, "eval_loss_by_set": { "aqua_rat": 5.881437301635742, "gsm8k": 6.591684514825994, "math_qa": 5.500349680582683 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.022744503411675512, "math_qa": 0.0016750418760469012 } }, { "flos": 1.378075794554749e+18, "train_loss": 5.719173583984375, "eval_loss": 5.847956116135056, "eval_accuracy": 0.011189118034225537, "eval_loss_by_set": { "aqua_rat": 5.870846748352051, "gsm8k": 6.595155889337713, "math_qa": 5.503582000732422 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.02122820318423048, "math_qa": 0.005360134003350084 } }, { "flos": 1.3843590546834063e+18, "train_loss": 5.722015991210937, "eval_loss": 5.844232739628972, "eval_accuracy": 0.009653356735410267, "eval_loss_by_set": { "aqua_rat": 5.878025531768799, "gsm8k": 6.59400107643821, "math_qa": 5.497772852579753 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.016679302501895376, "math_qa": 0.002680067001675042 } }, { "flos": 1.390801038012842e+18, "train_loss": 5.732957153320313, "eval_loss": 5.83618705337112, "eval_accuracy": 0.008336989907854322, "eval_loss_by_set": { "aqua_rat": 5.876835823059082, "gsm8k": 6.596633217551491, "math_qa": 5.484261830647786 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.012130401819560273, "math_qa": 0.004020100502512563 } }, { "flos": 1.3971098311852032e+18, "train_loss": 5.716550903320313, "eval_loss": 5.843704197857831, "eval_accuracy": 0.010092145677928916, "eval_loss_by_set": { "aqua_rat": 5.873378276824951, "gsm8k": 6.583643826571378, "math_qa": 5.502092361450195 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.01592115238817286, "math_qa": 0.005360134003350084 } }, { "flos": 1.4034824889106432e+18, "train_loss": 5.726326904296875, "eval_loss": 5.839442227337812, "eval_accuracy": 0.013602457218078104, "eval_loss_by_set": { "aqua_rat": 5.8755292892456055, "gsm8k": 6.572641546075994, "math_qa": 5.500385284423828 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.018953752843062926, "math_qa": 0.007370184254606365 } }, { "flos": 1.4098505714221711e+18, "train_loss": 5.724058837890625, "eval_loss": 5.838237685126227, "eval_accuracy": 0.010530934620447565, "eval_loss_by_set": { "aqua_rat": 5.8815693855285645, "gsm8k": 6.58035625110973, "math_qa": 5.494489034016927 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.022744503411675512, "math_qa": 0.0033500837520938024 } }, { "flos": 1.4162342339275653e+18, "train_loss": 5.721983642578125, "eval_loss": 5.84345580436088, "eval_accuracy": 0.009214567792891619, "eval_loss_by_set": { "aqua_rat": 5.873108863830566, "gsm8k": 6.592654835094105, "math_qa": 5.497601826985677 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.01819560272934041, "math_qa": 0.003015075376884422 } }, { "flos": 1.4226509515750113e+18, "train_loss": 5.725145263671875, "eval_loss": 5.8427228927612305, "eval_accuracy": 0.01075032909170689, "eval_loss_by_set": { "aqua_rat": 5.870425701141357, "gsm8k": 6.582156094637784, "math_qa": 5.5015074412028 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.017437452615617893, "math_qa": 0.007035175879396985 } }, { "flos": 1.4290227642656358e+18, "train_loss": 5.734613037109375, "eval_loss": 5.833951537673538, "eval_accuracy": 0.011627906976744186, "eval_loss_by_set": { "aqua_rat": 5.878283500671387, "gsm8k": 6.568271983753551, "math_qa": 5.493693669637044 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.02122820318423048, "math_qa": 0.004355108877721943 } }, { "flos": 1.4353304241035018e+18, "train_loss": 5.72257568359375, "eval_loss": 5.845410011910103, "eval_accuracy": 0.012944273804300131, "eval_loss_by_set": { "aqua_rat": 5.881059646606445, "gsm8k": 6.59656455300071, "math_qa": 5.498160044352214 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.025018953752843062, "math_qa": 0.005360134003350084 } }, { "flos": 1.441706997765374e+18, "train_loss": 5.7286279296875, "eval_loss": 5.847547015628299, "eval_accuracy": 0.01338306274681878, "eval_loss_by_set": { "aqua_rat": 5.87758731842041, "gsm8k": 6.6164398193359375, "math_qa": 5.492634455362956 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.018953752843062926, "math_qa": 0.008375209380234505 } }, { "flos": 1.4480442714027459e+18, "train_loss": 5.72301513671875, "eval_loss": 5.8331728239317195, "eval_accuracy": 0.012066695919262835, "eval_loss_by_set": { "aqua_rat": 5.8799943923950195, "gsm8k": 6.58026747270064, "math_qa": 5.486852645874023 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.018953752843062926, "math_qa": 0.008040201005025126 } }, { "flos": 1.4543929411989668e+18, "train_loss": 5.7168115234375, "eval_loss": 5.8491084382340714, "eval_accuracy": 0.013602457218078104, "eval_loss_by_set": { "aqua_rat": 5.879587650299072, "gsm8k": 6.583787397904829, "math_qa": 5.509840647379558 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.016679302501895376, "math_qa": 0.009380234505862646 } }, { "flos": 1.4607638884536812e+18, "train_loss": 5.72572021484375, "eval_loss": 5.852129704243428, "eval_accuracy": 0.01075032909170689, "eval_loss_by_set": { "aqua_rat": 5.874773979187012, "gsm8k": 6.574505892666903, "math_qa": 5.519153594970703 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.016679302501895376, "math_qa": 0.005695142378559464 } }, { "flos": 1.4670986275234775e+18, "train_loss": 5.71256103515625, "eval_loss": 5.843078767931139, "eval_accuracy": 0.011627906976744186, "eval_loss_by_set": { "aqua_rat": 5.883234977722168, "gsm8k": 6.588643854314631, "math_qa": 5.49801508585612 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.017437452615617893, "math_qa": 0.008040201005025126 } }, { "flos": 1.4734772820970045e+18, "train_loss": 5.724515380859375, "eval_loss": 5.839692296208562, "eval_accuracy": 0.01338306274681878, "eval_loss_by_set": { "aqua_rat": 5.87620735168457, "gsm8k": 6.571144104003906, "math_qa": 5.501400629679362 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.01819560272934041, "math_qa": 0.009045226130653266 } }, { "flos": 1.4797633446918226e+18, "train_loss": 5.718538818359375, "eval_loss": 5.83607021537987, "eval_accuracy": 0.012944273804300131, "eval_loss_by_set": { "aqua_rat": 5.87810754776001, "gsm8k": 6.59539170698686, "math_qa": 5.48454475402832 }, "eval_accuracy_by_set": { "aqua_rat": 0.011811023622047244, "gsm8k": 0.019711902956785442, "math_qa": 0.010050251256281407 } }, { "flos": 1.4861617625573622e+18, "train_loss": 5.720941162109375, "eval_loss": 5.837228001774968, "eval_accuracy": 0.015796401930671347, "eval_loss_by_set": { "aqua_rat": 5.870813369750977, "gsm8k": 6.572556929154829, "math_qa": 5.497403462727864 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.024260803639120546, "math_qa": 0.010385259631490788 } }, { "flos": 1.4925756981397422e+18, "train_loss": 5.725093994140625, "eval_loss": 5.8423210607992635, "eval_accuracy": 0.016235190873189996, "eval_loss_by_set": { "aqua_rat": 5.877251148223877, "gsm8k": 6.584808349609375, "math_qa": 5.499103546142578 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.02122820318423048, "math_qa": 0.012395309882747068 } }, { "flos": 1.498865758812242e+18, "train_loss": 5.722674560546875, "eval_loss": 5.842221646695523, "eval_accuracy": 0.014480035103115402, "eval_loss_by_set": { "aqua_rat": 5.883445739746094, "gsm8k": 6.5722573020241475, "math_qa": 5.504186630249023 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.015163002274450341, "math_qa": 0.012730318257956449 } }, { "flos": 1.5051991379880182e+18, "train_loss": 5.711724853515625, "eval_loss": 5.846810856380978, "eval_accuracy": 0.016235190873189996, "eval_loss_by_set": { "aqua_rat": 5.87376070022583, "gsm8k": 6.609882007945668, "math_qa": 5.494824091593425 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.019711902956785442, "math_qa": 0.01440536013400335 } }, { "flos": 1.5115242117707858e+18, "train_loss": 5.725618896484375, "eval_loss": 5.843957437051309, "eval_accuracy": 0.01645458534444932, "eval_loss_by_set": { "aqua_rat": 5.878044128417969, "gsm8k": 6.596918279474432, "math_qa": 5.496009826660156 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.025018953752843062, "math_qa": 0.011055276381909548 } }, { "flos": 1.517896581196546e+18, "train_loss": 5.723401489257813, "eval_loss": 5.853589573421994, "eval_accuracy": 0.01228609039052216, "eval_loss_by_set": { "aqua_rat": 5.8756585121154785, "gsm8k": 6.5885231711647725, "math_qa": 5.51490592956543 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.01592115238817286, "math_qa": 0.009045226130653266 } }, { "flos": 1.5242690531646505e+18, "train_loss": 5.72028564453125, "eval_loss": 5.8367280702333195, "eval_accuracy": 0.014041246160596753, "eval_loss_by_set": { "aqua_rat": 5.882682800292969, "gsm8k": 6.581712202592329, "math_qa": 5.491447448730469 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.017437452615617893, "math_qa": 0.011725293132328308 } }, { "flos": 1.5305750852099113e+18, "train_loss": 5.7285302734375, "eval_loss": 5.836178392977328, "eval_accuracy": 0.011627906976744186, "eval_loss_by_set": { "aqua_rat": 5.8848161697387695, "gsm8k": 6.580273021351207, "math_qa": 5.491081873575847 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.02047005307050796, "math_qa": 0.006030150753768844 } }, { "flos": 1.5369374178339717e+18, "train_loss": 5.717700805664062, "eval_loss": 5.847870079246727, "eval_accuracy": 0.012505484861781484, "eval_loss_by_set": { "aqua_rat": 5.881401062011719, "gsm8k": 6.617292230779475, "math_qa": 5.492424011230469 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.017437452615617893, "math_qa": 0.009380234505862646 } }, { "flos": 1.5432258501769953e+18, "train_loss": 5.717725830078125, "eval_loss": 5.845110558174752, "eval_accuracy": 0.008775778850372971, "eval_loss_by_set": { "aqua_rat": 5.881413459777832, "gsm8k": 6.601180336692116, "math_qa": 5.495553334554036 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.015163002274450341, "math_qa": 0.004020100502512563 } }, { "flos": 1.5496170755829268e+18, "train_loss": 5.723927001953125, "eval_loss": 5.846091502421611, "eval_accuracy": 0.010530934620447565, "eval_loss_by_set": { "aqua_rat": 5.872591018676758, "gsm8k": 6.583886580033735, "math_qa": 5.505727132161458 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.01819560272934041, "math_qa": 0.005360134003350084 } }, { "flos": 1.5559811192145838e+18, "train_loss": 5.720005493164063, "eval_loss": 5.8488850722441805, "eval_accuracy": 0.008995173321632294, "eval_loss_by_set": { "aqua_rat": 5.875699520111084, "gsm8k": 6.59461142800071, "math_qa": 5.504859288533528 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.01819560272934041, "math_qa": 0.0036850921273031824 } }, { "flos": 1.5623470789385257e+18, "train_loss": 5.717556762695312, "eval_loss": 5.856233390601906, "eval_accuracy": 0.008556384379113647, "eval_loss_by_set": { "aqua_rat": 5.883927345275879, "gsm8k": 6.596875277432528, "math_qa": 5.514464696248372 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.01592115238817286, "math_qa": 0.004355108877721943 } }, { "flos": 1.5687133070979236e+18, "train_loss": 5.720347900390625, "eval_loss": 5.836384799029376, "eval_accuracy": 0.012066695919262835, "eval_loss_by_set": { "aqua_rat": 5.8792314529418945, "gsm8k": 6.5870888449928975, "math_qa": 5.488741556803386 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.01592115238817286, "math_qa": 0.008710217755443886 } }, { "flos": 1.5751559910438994e+18, "train_loss": 5.710362548828125, "eval_loss": 5.838281373719911, "eval_accuracy": 0.016235190873189996, "eval_loss_by_set": { "aqua_rat": 5.880443572998047, "gsm8k": 6.584025989879262, "math_qa": 5.492968241373698 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.01819560272934041, "math_qa": 0.01340033500837521 } }, { "flos": 1.5814353969762796e+18, "train_loss": 5.714877319335938, "eval_loss": 5.847363085360141, "eval_accuracy": 0.01184730144800351, "eval_loss_by_set": { "aqua_rat": 5.88588809967041, "gsm8k": 6.5940024636008525, "math_qa": 5.501942952473958 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.01819560272934041, "math_qa": 0.008375209380234505 } }, { "flos": 1.5878232223787254e+18, "train_loss": 5.709629516601563, "eval_loss": 5.844878016291438, "eval_accuracy": 0.010311540149188241, "eval_loss_by_set": { "aqua_rat": 5.888383865356445, "gsm8k": 6.6012046120383525, "math_qa": 5.4946028391520185 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.015163002274450341, "math_qa": 0.006700167504187605 } }, { "flos": 1.5942091934290412e+18, "train_loss": 5.720501708984375, "eval_loss": 5.8457291577313395, "eval_accuracy": 0.015577007459412023, "eval_loss_by_set": { "aqua_rat": 5.884881019592285, "gsm8k": 6.596300992098722, "math_qa": 5.498454411824544 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.02047005307050796, "math_qa": 0.011725293132328308 } }, { "flos": 1.6005609958670336e+18, "train_loss": 5.714364624023437, "eval_loss": 5.830293784270415, "eval_accuracy": 0.013602457218078104, "eval_loss_by_set": { "aqua_rat": 5.882384777069092, "gsm8k": 6.579434481534091, "math_qa": 5.482596715291341 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.018953752843062926, "math_qa": 0.009380234505862646 } }, { "flos": 1.6068915102996234e+18, "train_loss": 5.719678955078125, "eval_loss": 5.836224427094331, "eval_accuracy": 0.015796401930671347, "eval_loss_by_set": { "aqua_rat": 5.877172470092773, "gsm8k": 6.580214066938921, "math_qa": 5.4918168385823565 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.021986353297952996, "math_qa": 0.012060301507537688 } }, { "flos": 1.6132708037495357e+18, "train_loss": 5.717760009765625, "eval_loss": 5.845682092615076, "eval_accuracy": 0.013602457218078104, "eval_loss_by_set": { "aqua_rat": 5.8818206787109375, "gsm8k": 6.592855280095881, "math_qa": 5.500216166178386 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.019711902956785442, "math_qa": 0.010720268006700168 } }, { "flos": 1.6196379800229642e+18, "train_loss": 5.718222045898438, "eval_loss": 5.844638102763408, "eval_accuracy": 0.014480035103115402, "eval_loss_by_set": { "aqua_rat": 5.868686676025391, "gsm8k": 6.5668251731178975, "math_qa": 5.5116316477457685 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.02047005307050796, "math_qa": 0.010050251256281407 } }, { "flos": 1.625937643705467e+18, "train_loss": 5.7239013671875, "eval_loss": 5.846551379641971, "eval_accuracy": 0.015577007459412023, "eval_loss_by_set": { "aqua_rat": 5.873724937438965, "gsm8k": 6.598853371360085, "math_qa": 5.499481836954753 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.022744503411675512, "math_qa": 0.012060301507537688 } }, { "flos": 1.6322961436080865e+18, "train_loss": 5.716204833984375, "eval_loss": 5.844726820249815, "eval_accuracy": 0.01645458534444932, "eval_loss_by_set": { "aqua_rat": 5.878659248352051, "gsm8k": 6.595848777077415, "math_qa": 5.4976348876953125 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.021986353297952996, "math_qa": 0.01340033500837521 } }, { "flos": 1.6387016712551137e+18, "train_loss": 5.71306396484375, "eval_loss": 5.84615132615373, "eval_accuracy": 0.012066695919262835, "eval_loss_by_set": { "aqua_rat": 5.876509189605713, "gsm8k": 6.603124445134943, "math_qa": 5.496675491333008 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.014404852160727824, "math_qa": 0.009380234505862646 } }, { "flos": 1.6450342461982638e+18, "train_loss": 5.717125244140625, "eval_loss": 5.851626138429384, "eval_accuracy": 0.010969723562966213, "eval_loss_by_set": { "aqua_rat": 5.87218713760376, "gsm8k": 6.595088611949574, "math_qa": 5.509159088134766 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.017437452615617893, "math_qa": 0.007370184254606365 } }, { "flos": 1.651369541466325e+18, "train_loss": 5.711387939453125, "eval_loss": 5.841629363395072, "eval_accuracy": 0.014480035103115402, "eval_loss_by_set": { "aqua_rat": 5.886812686920166, "gsm8k": 6.596142161976207, "math_qa": 5.492045720418294 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.02350265352539803, "math_qa": 0.008710217755443886 } }, { "flos": 1.657756315675525e+18, "train_loss": 5.724666137695312, "eval_loss": 5.848882804045806, "eval_accuracy": 0.011408512505484861, "eval_loss_by_set": { "aqua_rat": 5.882630825042725, "gsm8k": 6.600269664417613, "math_qa": 5.501684824625651 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.017437452615617893, "math_qa": 0.007705192629815745 } }, { "flos": 1.6640484781976453e+18, "train_loss": 5.701630859375, "eval_loss": 5.837380641215557, "eval_accuracy": 0.012944273804300131, "eval_loss_by_set": { "aqua_rat": 5.881926536560059, "gsm8k": 6.599580938165838, "math_qa": 5.484326680501302 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.022744503411675512, "math_qa": 0.006700167504187605 } }, { "flos": 1.6704440318568694e+18, "train_loss": 5.719580078125, "eval_loss": 5.848978455002244, "eval_accuracy": 0.011189118034225537, "eval_loss_by_set": { "aqua_rat": 5.876347541809082, "gsm8k": 6.603477478027344, "math_qa": 5.500885645548503 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.01819560272934041, "math_qa": 0.006700167504187605 } }, { "flos": 1.6767355351015096e+18, "train_loss": 5.702225341796875, "eval_loss": 5.840943877761428, "eval_accuracy": 0.01075032909170689, "eval_loss_by_set": { "aqua_rat": 5.884762763977051, "gsm8k": 6.605624112215909, "math_qa": 5.486813863118489 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.01288855193328279, "math_qa": 0.008375209380234505 } }, { "flos": 1.6830854622494065e+18, "train_loss": 5.720343017578125, "eval_loss": 5.849942542411186, "eval_accuracy": 0.008336989907854322, "eval_loss_by_set": { "aqua_rat": 5.86936092376709, "gsm8k": 6.603145252574574, "math_qa": 5.503106435139974 }, "eval_accuracy_by_set": { "aqua_rat": 0.011811023622047244, "gsm8k": 0.014404852160727824, "math_qa": 0.005360134003350084 } }, { "flos": 1.689455750226641e+18, "train_loss": 5.712192993164063, "eval_loss": 5.847299936655405, "eval_accuracy": 0.01184730144800351, "eval_loss_by_set": { "aqua_rat": 5.882999420166016, "gsm8k": 6.60393662886186, "math_qa": 5.4975331624348955 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.01592115238817286, "math_qa": 0.009380234505862646 } }, { "flos": 1.6957570422386196e+18, "train_loss": 5.7133984375, "eval_loss": 5.845277992454735, "eval_accuracy": 0.011627906976744186, "eval_loss_by_set": { "aqua_rat": 5.87685489654541, "gsm8k": 6.591512506658381, "math_qa": 5.500622431437175 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.01592115238817286, "math_qa": 0.008040201005025126 } }, { "flos": 1.7020683699785564e+18, "train_loss": 5.707566528320313, "eval_loss": 5.837945267960832, "eval_accuracy": 0.013163668275559455, "eval_loss_by_set": { "aqua_rat": 5.884540557861328, "gsm8k": 6.583070234818892, "math_qa": 5.492546717325847 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.02047005307050796, "math_qa": 0.008710217755443886 } }, { "flos": 1.7083970912623002e+18, "train_loss": 5.716405639648437, "eval_loss": 5.842722067961821, "eval_accuracy": 0.014041246160596753, "eval_loss_by_set": { "aqua_rat": 5.87367582321167, "gsm8k": 6.594934636896307, "math_qa": 5.495378494262695 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.018953752843062926, "math_qa": 0.009715242881072027 } }, { "flos": 1.7147709236612956e+18, "train_loss": 5.718179931640625, "eval_loss": 5.841542939882021, "eval_accuracy": 0.01338306274681878, "eval_loss_by_set": { "aqua_rat": 5.886877059936523, "gsm8k": 6.584195917302912, "math_qa": 5.497382481892903 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.01819560272934041, "math_qa": 0.010050251256281407 } }, { "flos": 1.7210291656054538e+18, "train_loss": 5.702039794921875, "eval_loss": 5.830771497777991, "eval_accuracy": 0.014041246160596753, "eval_loss_by_set": { "aqua_rat": 5.875734806060791, "gsm8k": 6.580257068980824, "math_qa": 5.483510335286458 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.02122820318423048, "math_qa": 0.010720268006700168 } }, { "flos": 1.7273412562389565e+18, "train_loss": 5.69921875, "eval_loss": 5.83662613018139, "eval_accuracy": 0.01733216322948662, "eval_loss_by_set": { "aqua_rat": 5.88381814956665, "gsm8k": 6.583648681640625, "math_qa": 5.490308125813802 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.01819560272934041, "math_qa": 0.01574539363484087 } }, { "flos": 1.7336928525185188e+18, "train_loss": 5.72206787109375, "eval_loss": 5.83518056611757, "eval_accuracy": 0.014699429574374727, "eval_loss_by_set": { "aqua_rat": 5.882534503936768, "gsm8k": 6.605503429066051, "math_qa": 5.478169759114583 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.02122820318423048, "math_qa": 0.011055276381909548 } }, { "flos": 1.7399859631546696e+18, "train_loss": 5.705970458984375, "eval_loss": 5.84447886492755, "eval_accuracy": 0.01338306274681878, "eval_loss_by_set": { "aqua_rat": 5.881232261657715, "gsm8k": 6.600614374334162, "math_qa": 5.494853973388672 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.02122820318423048, "math_qa": 0.008710217755443886 } }, { "flos": 1.7463409390366228e+18, "train_loss": 5.710986938476562, "eval_loss": 5.851397230818465, "eval_accuracy": 0.011408512505484861, "eval_loss_by_set": { "aqua_rat": 5.886743545532227, "gsm8k": 6.612741643732244, "math_qa": 5.499502182006836 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.01819560272934041, "math_qa": 0.007035175879396985 } }, { "flos": 1.7527230558906614e+18, "train_loss": 5.710133056640625, "eval_loss": 5.844821981481604, "eval_accuracy": 0.012505484861781484, "eval_loss_by_set": { "aqua_rat": 5.880782127380371, "gsm8k": 6.612842213023793, "math_qa": 5.489816029866536 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.018953752843062926, "math_qa": 0.008040201005025126 } }, { "flos": 1.7590110759168246e+18, "train_loss": 5.701642456054688, "eval_loss": 5.844820770057472, "eval_accuracy": 0.011408512505484861, "eval_loss_by_set": { "aqua_rat": 5.878119945526123, "gsm8k": 6.600112221457741, "math_qa": 5.495870590209961 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.01592115238817286, "math_qa": 0.007705192629815745 } }, { "flos": 1.765403723493802e+18, "train_loss": 5.72253173828125, "eval_loss": 5.844975136421822, "eval_accuracy": 0.012505484861781484, "eval_loss_by_set": { "aqua_rat": 5.883199691772461, "gsm8k": 6.6121673583984375, "math_qa": 5.49015998840332 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.019711902956785442, "math_qa": 0.009045226130653266 } }, { "flos": 1.7717686739004293e+18, "train_loss": 5.705731201171875, "eval_loss": 5.83608645361823, "eval_accuracy": 0.011627906976744186, "eval_loss_by_set": { "aqua_rat": 5.887898921966553, "gsm8k": 6.59023701060902, "math_qa": 5.486116409301758 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.018953752843062926, "math_qa": 0.007370184254606365 } }, { "flos": 1.7781778903874929e+18, "train_loss": 5.714169921875, "eval_loss": 5.848413622057116, "eval_accuracy": 0.015357612988152698, "eval_loss_by_set": { "aqua_rat": 5.881038665771484, "gsm8k": 6.598512129350142, "math_qa": 5.501899719238281 }, "eval_accuracy_by_set": { "aqua_rat": 0.011811023622047244, "gsm8k": 0.024260803639120546, "math_qa": 0.011725293132328308 } }, { "flos": 1.784498245074944e+18, "train_loss": 5.7250128173828125, "eval_loss": 5.838612350257668, "eval_accuracy": 0.014041246160596753, "eval_loss_by_set": { "aqua_rat": 5.8840718269348145, "gsm8k": 6.584432428533381, "math_qa": 5.492989857991536 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.01592115238817286, "math_qa": 0.011055276381909548 } }, { "flos": 1.7908718095753544e+18, "train_loss": 5.7111663818359375, "eval_loss": 5.837638133280986, "eval_accuracy": 0.012944273804300131, "eval_loss_by_set": { "aqua_rat": 5.884458541870117, "gsm8k": 6.589207042347301, "math_qa": 5.489267349243164 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.01819560272934041, "math_qa": 0.009715242881072027 } }, { "flos": 1.7971911130695598e+18, "train_loss": 5.713194580078125, "eval_loss": 5.84212622771392, "eval_accuracy": 0.012944273804300131, "eval_loss_by_set": { "aqua_rat": 5.8768815994262695, "gsm8k": 6.5966796875, "math_qa": 5.4933929443359375 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.016679302501895376, "math_qa": 0.009380234505862646 } }, { "flos": 1.8035734774210888e+18, "train_loss": 5.713685302734375, "eval_loss": 5.843543697047878, "eval_accuracy": 0.012944273804300131, "eval_loss_by_set": { "aqua_rat": 5.884199142456055, "gsm8k": 6.596597844904119, "math_qa": 5.495005925496419 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.016679302501895376, "math_qa": 0.011055276381909548 } }, { "flos": 1.8099381389911654e+18, "train_loss": 5.702999267578125, "eval_loss": 5.8497212899697795, "eval_accuracy": 0.010311540149188241, "eval_loss_by_set": { "aqua_rat": 5.873713493347168, "gsm8k": 6.599917325106534, "math_qa": 5.503882090250651 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.01592115238817286, "math_qa": 0.006700167504187605 } }, { "flos": 1.816311744830636e+18, "train_loss": 5.71896484375, "eval_loss": 5.844663052945523, "eval_accuracy": 0.012066695919262835, "eval_loss_by_set": { "aqua_rat": 5.887031555175781, "gsm8k": 6.59168174050071, "math_qa": 5.498748779296875 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.02047005307050796, "math_qa": 0.007035175879396985 } }, { "flos": 1.822627689123545e+18, "train_loss": 5.7018280029296875, "eval_loss": 5.841322048290356, "eval_accuracy": 0.014480035103115402, "eval_loss_by_set": { "aqua_rat": 5.884732246398926, "gsm8k": 6.606929432262074, "math_qa": 5.4868011474609375 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.01819560272934041, "math_qa": 0.012395309882747068 } }, { "flos": 1.8290111868095693e+18, "train_loss": 5.7077294921875, "eval_loss": 5.834684011098501, "eval_accuracy": 0.009872751206669592, "eval_loss_by_set": { "aqua_rat": 5.890514373779297, "gsm8k": 6.60265419699929, "math_qa": 5.478045145670573 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.018953752843062926, "math_qa": 0.005025125628140704 } }, { "flos": 1.8352990833554227e+18, "train_loss": 5.71782958984375, "eval_loss": 5.839264586165145, "eval_accuracy": 0.013602457218078104, "eval_loss_by_set": { "aqua_rat": 5.882081031799316, "gsm8k": 6.58789686723189, "math_qa": 5.492573420206706 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.018953752843062926, "math_qa": 0.010385259631490788 } }, { "flos": 1.841678542161576e+18, "train_loss": 5.705829467773437, "eval_loss": 5.835206418424039, "eval_accuracy": 0.010092145677928916, "eval_loss_by_set": { "aqua_rat": 5.888795852661133, "gsm8k": 6.59001991965554, "math_qa": 5.484784444173177 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.02047005307050796, "math_qa": 0.004020100502512563 } }, { "flos": 1.8479969802198712e+18, "train_loss": 5.717266845703125, "eval_loss": 5.85265690571553, "eval_accuracy": 0.010530934620447565, "eval_loss_by_set": { "aqua_rat": 5.889543533325195, "gsm8k": 6.612979542125355, "math_qa": 5.501101811726888 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.018953752843062926, "math_qa": 0.006030150753768844 } }, { "flos": 1.8543618688863437e+18, "train_loss": 5.711239013671875, "eval_loss": 5.84545171583021, "eval_accuracy": 0.012505484861781484, "eval_loss_by_set": { "aqua_rat": 5.88480281829834, "gsm8k": 6.599334023215554, "math_qa": 5.49664306640625 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.02047005307050796, "math_qa": 0.008375209380234505 } }, { "flos": 1.8607132176684155e+18, "train_loss": 5.723646240234375, "eval_loss": 5.8373600727802994, "eval_accuracy": 0.014260640631856078, "eval_loss_by_set": { "aqua_rat": 5.882488250732422, "gsm8k": 6.582150545987216, "math_qa": 5.492237091064453 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.02047005307050796, "math_qa": 0.010385259631490788 } }, { "flos": 1.867110172023849e+18, "train_loss": 5.709675903320313, "eval_loss": 5.843254811054951, "eval_accuracy": 0.013821851689337429, "eval_loss_by_set": { "aqua_rat": 5.888021469116211, "gsm8k": 6.599684975363991, "math_qa": 5.49282709757487 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.017437452615617893, "math_qa": 0.011055276381909548 } }, { "flos": 1.87347027985485e+18, "train_loss": 5.713226928710937, "eval_loss": 5.855287654979809, "eval_accuracy": 0.012724879333040808, "eval_loss_by_set": { "aqua_rat": 5.878664970397949, "gsm8k": 6.608637723055753, "math_qa": 5.508054097493489 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.017437452615617893, "math_qa": 0.010050251256281407 } }, { "flos": 1.879769820057043e+18, "train_loss": 5.718699951171875, "eval_loss": 5.845688716785328, "eval_accuracy": 0.012944273804300131, "eval_loss_by_set": { "aqua_rat": 5.8826985359191895, "gsm8k": 6.582620794122869, "math_qa": 5.504844029744466 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.017437452615617893, "math_qa": 0.010720268006700168 } }, { "flos": 1.8861297625318031e+18, "train_loss": 5.701884155273437, "eval_loss": 5.851865613782728, "eval_accuracy": 0.012944273804300131, "eval_loss_by_set": { "aqua_rat": 5.884052276611328, "gsm8k": 6.59402812610973, "math_qa": 5.509025573730469 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.01819560272934041, "math_qa": 0.010385259631490788 } }, { "flos": 1.8924942388814152e+18, "train_loss": 5.70799072265625, "eval_loss": 5.8324811265275285, "eval_accuracy": 0.016235190873189996, "eval_loss_by_set": { "aqua_rat": 5.881316184997559, "gsm8k": 6.580745350230824, "math_qa": 5.485457102457683 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.02122820318423048, "math_qa": 0.01373534338358459 } }, { "flos": 1.898844495668052e+18, "train_loss": 5.723231201171875, "eval_loss": 5.84049974905478, "eval_accuracy": 0.008556384379113647, "eval_loss_by_set": { "aqua_rat": 5.890309810638428, "gsm8k": 6.592305963689631, "math_qa": 5.491771062215169 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.012130401819560273, "math_qa": 0.006365159128978224 } }, { "flos": 1.9052050566181028e+18, "train_loss": 5.70713134765625, "eval_loss": 5.842813646471178, "eval_accuracy": 0.010530934620447565, "eval_loss_by_set": { "aqua_rat": 5.883384704589844, "gsm8k": 6.585893804376775, "math_qa": 5.498854319254558 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.01592115238817286, "math_qa": 0.006700167504187605 } }, { "flos": 1.911559373222576e+18, "train_loss": 5.7029541015625, "eval_loss": 5.844369965630609, "eval_accuracy": 0.009653356735410267, "eval_loss_by_set": { "aqua_rat": 5.891870975494385, "gsm8k": 6.590878573330966, "math_qa": 5.49826176961263 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.018953752843062926, "math_qa": 0.004020100502512563 } }, { "flos": 1.9179159151569797e+18, "train_loss": 5.715970458984375, "eval_loss": 5.8455862096838045, "eval_accuracy": 0.01075032909170689, "eval_loss_by_set": { "aqua_rat": 5.889347076416016, "gsm8k": 6.595569957386363, "math_qa": 5.498196919759114 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.016679302501895376, "math_qa": 0.007035175879396985 } }, { "flos": 1.9242708502367437e+18, "train_loss": 5.710127563476562, "eval_loss": 5.839032044281831, "eval_accuracy": 0.008775778850372971, "eval_loss_by_set": { "aqua_rat": 5.888006210327148, "gsm8k": 6.607532848011363, "math_qa": 5.482721328735352 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.013646702047005308, "math_qa": 0.006700167504187605 } }, { "flos": 1.930662735457026e+18, "train_loss": 5.702567138671875, "eval_loss": 5.848467105143779, "eval_accuracy": 0.012724879333040808, "eval_loss_by_set": { "aqua_rat": 5.878030300140381, "gsm8k": 6.587553544477983, "math_qa": 5.507255554199219 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.019711902956785442, "math_qa": 0.008710217755443886 } }, { "flos": 1.9370178557572547e+18, "train_loss": 5.7119873046875, "eval_loss": 5.840320561383222, "eval_accuracy": 0.01491882404563405, "eval_loss_by_set": { "aqua_rat": 5.886739253997803, "gsm8k": 6.594193198464134, "math_qa": 5.490927378336589 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.01819560272934041, "math_qa": 0.012395309882747068 } }, { "flos": 1.9433051134267228e+18, "train_loss": 5.707081909179688, "eval_loss": 5.853277464170714, "eval_accuracy": 0.012944273804300131, "eval_loss_by_set": { "aqua_rat": 5.876068115234375, "gsm8k": 6.60841855135831, "math_qa": 5.505271911621094 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.019711902956785442, "math_qa": 0.009715242881072027 } }, { "flos": 1.9496598418111857e+18, "train_loss": 5.7040576171875, "eval_loss": 5.85195711496714, "eval_accuracy": 0.012724879333040808, "eval_loss_by_set": { "aqua_rat": 5.890776634216309, "gsm8k": 6.613696011629972, "math_qa": 5.499591827392578 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.01819560272934041, "math_qa": 0.009045226130653266 } }, { "flos": 1.956016775661355e+18, "train_loss": 5.709314575195313, "eval_loss": 5.832391017192119, "eval_accuracy": 0.01491882404563405, "eval_loss_by_set": { "aqua_rat": 5.8803205490112305, "gsm8k": 6.5977325439453125, "math_qa": 5.4776153564453125 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.016679302501895376, "math_qa": 0.01407035175879397 } }, { "flos": 1.962375358242095e+18, "train_loss": 5.713192138671875, "eval_loss": 5.856773737314585, "eval_accuracy": 0.012724879333040808, "eval_loss_by_set": { "aqua_rat": 5.878161430358887, "gsm8k": 6.604687777432528, "math_qa": 5.512197494506836 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.018953752843062926, "math_qa": 0.009380234505862646 } }, { "flos": 1.9686639140654285e+18, "train_loss": 5.702835693359375, "eval_loss": 5.83763109671103, "eval_accuracy": 0.012724879333040808, "eval_loss_by_set": { "aqua_rat": 5.8942694664001465, "gsm8k": 6.5924155495383525, "math_qa": 5.486968358357747 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.015163002274450341, "math_qa": 0.008375209380234505 } }, { "flos": 1.975055242550575e+18, "train_loss": 5.714432983398438, "eval_loss": 5.84795111578864, "eval_accuracy": 0.011189118034225537, "eval_loss_by_set": { "aqua_rat": 5.884986877441406, "gsm8k": 6.610569347034801, "math_qa": 5.495331446329753 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.01819560272934041, "math_qa": 0.007705192629815745 } }, { "flos": 1.9814175139713516e+18, "train_loss": 5.705414428710937, "eval_loss": 5.834379969416438, "eval_accuracy": 0.013821851689337429, "eval_loss_by_set": { "aqua_rat": 5.880376815795898, "gsm8k": 6.580531033602628, "math_qa": 5.4885609944661455 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.015163002274450341, "math_qa": 0.012730318257956449 } }, { "flos": 1.9878586109269115e+18, "train_loss": 5.71692138671875, "eval_loss": 5.852489059035842, "eval_accuracy": 0.015357612988152698, "eval_loss_by_set": { "aqua_rat": 5.880556106567383, "gsm8k": 6.604922901500355, "math_qa": 5.5052846272786455 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.01819560272934041, "math_qa": 0.01306532663316583 } }, { "flos": 1.9941813761647575e+18, "train_loss": 5.7009210205078125, "eval_loss": 5.8466765687272355, "eval_accuracy": 0.008995173321632294, "eval_loss_by_set": { "aqua_rat": 5.879268169403076, "gsm8k": 6.593625155362216, "math_qa": 5.501609166463216 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.015163002274450341, "math_qa": 0.004690117252931323 } }, { "flos": 2.0005179282476237e+18, "train_loss": 5.707302856445312, "eval_loss": 5.844621245925491, "eval_accuracy": 0.012724879333040808, "eval_loss_by_set": { "aqua_rat": 5.875100135803223, "gsm8k": 6.603811784224077, "math_qa": 5.494119008382161 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.019711902956785442, "math_qa": 0.009045226130653266 } }, { "flos": 2.006899735864017e+18, "train_loss": 5.706260375976562, "eval_loss": 5.848849270794843, "eval_accuracy": 0.015357612988152698, "eval_loss_by_set": { "aqua_rat": 5.884638786315918, "gsm8k": 6.598812450062145, "math_qa": 5.502133687337239 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.01592115238817286, "math_qa": 0.01340033500837521 } }, { "flos": 2.013245397035647e+18, "train_loss": 5.697874755859375, "eval_loss": 5.853022755803289, "eval_accuracy": 0.015138218516893374, "eval_loss_by_set": { "aqua_rat": 5.878596305847168, "gsm8k": 6.603595386851918, "math_qa": 5.506879170735677 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.016679302501895376, "math_qa": 0.01373534338358459 } }, { "flos": 2.0195860712133755e+18, "train_loss": 5.7176220703125, "eval_loss": 5.856792681926006, "eval_accuracy": 0.009653356735410267, "eval_loss_by_set": { "aqua_rat": 5.888815402984619, "gsm8k": 6.60270205411044, "math_qa": 5.512248992919922 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.01592115238817286, "math_qa": 0.005695142378559464 } }, { "flos": 2.02594261368465e+18, "train_loss": 5.696708374023437, "eval_loss": 5.840629912711479, "eval_accuracy": 0.014480035103115402, "eval_loss_by_set": { "aqua_rat": 5.882822513580322, "gsm8k": 6.583134044300426, "math_qa": 5.496799468994141 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.016679302501895376, "math_qa": 0.012060301507537688 } }, { "flos": 2.0323295323121254e+18, "train_loss": 5.707012939453125, "eval_loss": 5.846391394331649, "eval_accuracy": 0.01996489688459851, "eval_loss_by_set": { "aqua_rat": 5.884719371795654, "gsm8k": 6.604633678089488, "math_qa": 5.495669682820638 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.017437452615617893, "math_qa": 0.020435510887772193 } }, { "flos": 2.0386862600038646e+18, "train_loss": 5.706559448242188, "eval_loss": 5.854451153729413, "eval_accuracy": 0.015357612988152698, "eval_loss_by_set": { "aqua_rat": 5.881549835205078, "gsm8k": 6.601497303355824, "math_qa": 5.509796778361003 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.015163002274450341, "math_qa": 0.01440536013400335 } }, { "flos": 2.0450113133855375e+18, "train_loss": 5.703408203125, "eval_loss": 5.836762943783322, "eval_accuracy": 0.01645458534444932, "eval_loss_by_set": { "aqua_rat": 5.87864351272583, "gsm8k": 6.593190973455256, "math_qa": 5.4865767161051435 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.014404852160727824, "math_qa": 0.01641541038525963 } }, { "flos": 2.0513805501695263e+18, "train_loss": 5.70986083984375, "eval_loss": 5.8493692552721175, "eval_accuracy": 0.012066695919262835, "eval_loss_by_set": { "aqua_rat": 5.883726119995117, "gsm8k": 6.607173572887074, "math_qa": 5.499179204305013 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.016679302501895376, "math_qa": 0.009380234505862646 } }, { "flos": 2.0577893956787896e+18, "train_loss": 5.7084033203125, "eval_loss": 5.846545477171202, "eval_accuracy": 0.011627906976744186, "eval_loss_by_set": { "aqua_rat": 5.885128498077393, "gsm8k": 6.6061623313210225, "math_qa": 5.495172500610352 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.01819560272934041, "math_qa": 0.007705192629815745 } }, { "flos": 2.0641808889833062e+18, "train_loss": 5.707520751953125, "eval_loss": 5.844962197381097, "eval_accuracy": 0.010530934620447565, "eval_loss_by_set": { "aqua_rat": 5.883559226989746, "gsm8k": 6.596534729003906, "math_qa": 5.497275034586589 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.017437452615617893, "math_qa": 0.006700167504187605 } }, { "flos": 2.070493309255549e+18, "train_loss": 5.699586791992187, "eval_loss": 5.840395076854809, "eval_accuracy": 0.015357612988152698, "eval_loss_by_set": { "aqua_rat": 5.893584251403809, "gsm8k": 6.587818492542613, "math_qa": 5.493393580118815 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.014404852160727824, "math_qa": 0.01474036850921273 } }, { "flos": 2.0768679453502996e+18, "train_loss": 5.714462890625, "eval_loss": 5.839855580716519, "eval_accuracy": 0.012944273804300131, "eval_loss_by_set": { "aqua_rat": 5.888650417327881, "gsm8k": 6.594961686567827, "math_qa": 5.489699045817058 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.01819560272934041, "math_qa": 0.010385259631490788 } }, { "flos": 2.0832372444113142e+18, "train_loss": 5.6929150390625, "eval_loss": 5.834031646316116, "eval_accuracy": 0.009872751206669592, "eval_loss_by_set": { "aqua_rat": 5.886628150939941, "gsm8k": 6.599438060413707, "math_qa": 5.478837331136067 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.01819560272934041, "math_qa": 0.005695142378559464 } }, { "flos": 2.08953008714888e+18, "train_loss": 5.69928466796875, "eval_loss": 5.851549921809016, "eval_accuracy": 0.012944273804300131, "eval_loss_by_set": { "aqua_rat": 5.886676788330078, "gsm8k": 6.617618907581676, "math_qa": 5.497507731119792 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.015163002274450341, "math_qa": 0.011390284757118929 } }, { "flos": 2.0959553163477647e+18, "train_loss": 5.716085205078125, "eval_loss": 5.848989821769096, "eval_accuracy": 0.01908731899956121, "eval_loss_by_set": { "aqua_rat": 5.877904415130615, "gsm8k": 6.602412830699574, "math_qa": 5.501261393229167 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.022744503411675512, "math_qa": 0.01440536013400335 } }, { "flos": 2.1022666032855122e+18, "train_loss": 5.708472900390625, "eval_loss": 5.849573444675755, "eval_accuracy": 0.011627906976744186, "eval_loss_by_set": { "aqua_rat": 5.88156795501709, "gsm8k": 6.604192560369318, "math_qa": 5.501040140787761 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.01592115238817286, "math_qa": 0.009045226130653266 } }, { "flos": 2.1086370560821166e+18, "train_loss": 5.698964233398438, "eval_loss": 5.852080937978384, "eval_accuracy": 0.017990346643264588, "eval_loss_by_set": { "aqua_rat": 5.88643741607666, "gsm8k": 6.602084073153409, "math_qa": 5.505466461181641 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.02122820318423048, "math_qa": 0.01507537688442211 } }, { "flos": 2.114985581996933e+18, "train_loss": 5.697572021484375, "eval_loss": 5.843114672480403, "eval_accuracy": 0.01338306274681878, "eval_loss_by_set": { "aqua_rat": 5.887744426727295, "gsm8k": 6.58989784934304, "math_qa": 5.497119903564453 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.01592115238817286, "math_qa": 0.011055276381909548 } }, { "flos": 2.1213113150571807e+18, "train_loss": 5.698578491210937, "eval_loss": 5.852584581117372, "eval_accuracy": 0.01228609039052216, "eval_loss_by_set": { "aqua_rat": 5.891562461853027, "gsm8k": 6.598526694557884, "math_qa": 5.5074462890625 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.016679302501895376, "math_qa": 0.009715242881072027 } }, { "flos": 2.127647743659737e+18, "train_loss": 5.69541259765625, "eval_loss": 5.849079724904653, "eval_accuracy": 0.011627906976744186, "eval_loss_by_set": { "aqua_rat": 5.889012813568115, "gsm8k": 6.614980524236506, "math_qa": 5.494714101155599 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.013646702047005308, "math_qa": 0.010050251256281407 } }, { "flos": 2.1339438011803238e+18, "train_loss": 5.706329345703125, "eval_loss": 5.841288076864706, "eval_accuracy": 0.015357612988152698, "eval_loss_by_set": { "aqua_rat": 5.900991439819336, "gsm8k": 6.5919057672674, "math_qa": 5.492279688517253 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.021986353297952996, "math_qa": 0.012060301507537688 } }, { "flos": 2.1403143978583327e+18, "train_loss": 5.708023681640625, "eval_loss": 5.846699843535552, "eval_accuracy": 0.016235190873189996, "eval_loss_by_set": { "aqua_rat": 5.890524864196777, "gsm8k": 6.595761385830966, "math_qa": 5.499727884928386 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.02122820318423048, "math_qa": 0.01407035175879397 } }, { "flos": 2.1466733922190623e+18, "train_loss": 5.695440063476562, "eval_loss": 5.831364296578072, "eval_accuracy": 0.019306713470820535, "eval_loss_by_set": { "aqua_rat": 5.884042739868164, "gsm8k": 6.588756908069957, "math_qa": 5.479836146036784 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.024260803639120546, "math_qa": 0.01675041876046901 } }, { "flos": 2.1530045251269427e+18, "train_loss": 5.70705322265625, "eval_loss": 5.845177830876531, "eval_accuracy": 0.013602457218078104, "eval_loss_by_set": { "aqua_rat": 5.883981704711914, "gsm8k": 6.611059015447443, "math_qa": 5.490915298461914 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.017437452615617893, "math_qa": 0.011390284757118929 } }, { "flos": 2.1593346063047066e+18, "train_loss": 5.7108203125, "eval_loss": 5.843861322145204, "eval_accuracy": 0.012724879333040808, "eval_loss_by_set": { "aqua_rat": 5.890693187713623, "gsm8k": 6.59374306418679, "math_qa": 5.496262868245442 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.017437452615617893, "math_qa": 0.009715242881072027 } }, { "flos": 2.1657380321021133e+18, "train_loss": 5.708992919921875, "eval_loss": 5.849450394913957, "eval_accuracy": 0.014260640631856078, "eval_loss_by_set": { "aqua_rat": 5.885189056396484, "gsm8k": 6.609767567027699, "math_qa": 5.497993469238281 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.01819560272934041, "math_qa": 0.012060301507537688 } }, { "flos": 2.172121880364843e+18, "train_loss": 5.693583984375, "eval_loss": 5.844947505641628, "eval_accuracy": 0.018429135585783237, "eval_loss_by_set": { "aqua_rat": 5.885560989379883, "gsm8k": 6.605878656560725, "math_qa": 5.4928029378255205 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.016679302501895376, "math_qa": 0.018760469011725293 } }, { "flos": 2.178461111970431e+18, "train_loss": 5.718143310546875, "eval_loss": 5.849040314957902, "eval_accuracy": 0.017770952172005264, "eval_loss_by_set": { "aqua_rat": 5.881054878234863, "gsm8k": 6.598529468883168, "math_qa": 5.502856572469075 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.017437452615617893, "math_qa": 0.018090452261306532 } }, { "flos": 2.1847985713651384e+18, "train_loss": 5.69440673828125, "eval_loss": 5.854306349883208, "eval_accuracy": 0.013821851689337429, "eval_loss_by_set": { "aqua_rat": 5.884932518005371, "gsm8k": 6.598647377707741, "math_qa": 5.510597864786784 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.017437452615617893, "math_qa": 0.011055276381909548 } }, { "flos": 2.1911031812393533e+18, "train_loss": 5.702713623046875, "eval_loss": 5.853505624307169, "eval_accuracy": 0.015138218516893374, "eval_loss_by_set": { "aqua_rat": 5.888113021850586, "gsm8k": 6.605295354669744, "math_qa": 5.506051381429036 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.013646702047005308, "math_qa": 0.01474036850921273 } }, { "flos": 2.1974127781074698e+18, "train_loss": 5.699509887695313, "eval_loss": 5.845437384940483, "eval_accuracy": 0.01645458534444932, "eval_loss_by_set": { "aqua_rat": 5.887978553771973, "gsm8k": 6.617125771262429, "math_qa": 5.4882017771403 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.019711902956785442, "math_qa": 0.01407035175879397 } }, { "flos": 2.2037835396048486e+18, "train_loss": 5.707636108398438, "eval_loss": 5.861371736268739, "eval_accuracy": 0.011627906976744186, "eval_loss_by_set": { "aqua_rat": 5.882242202758789, "gsm8k": 6.606036793101918, "math_qa": 5.518327713012695 }, "eval_accuracy_by_set": { "aqua_rat": 0.011811023622047244, "gsm8k": 0.019711902956785442, "math_qa": 0.008040201005025126 } }, { "flos": 2.2101893764895212e+18, "train_loss": 5.710049438476562, "eval_loss": 5.852035805985734, "eval_accuracy": 0.013163668275559455, "eval_loss_by_set": { "aqua_rat": 5.8868842124938965, "gsm8k": 6.6072609641335225, "math_qa": 5.502986907958984 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.016679302501895376, "math_qa": 0.012060301507537688 } }, { "flos": 2.2165529256630682e+18, "train_loss": 5.701461181640625, "eval_loss": 5.848599872073612, "eval_accuracy": 0.011408512505484861, "eval_loss_by_set": { "aqua_rat": 5.884400367736816, "gsm8k": 6.60565879128196, "math_qa": 5.4986311594645185 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.01819560272934041, "math_qa": 0.007705192629815745 } }, { "flos": 2.2228481177477448e+18, "train_loss": 5.692740478515625, "eval_loss": 5.853427139488426, "eval_accuracy": 0.013163668275559455, "eval_loss_by_set": { "aqua_rat": 5.888537883758545, "gsm8k": 6.605442393909801, "math_qa": 5.50582758585612 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.019711902956785442, "math_qa": 0.010050251256281407 } }, { "flos": 2.229231120975659e+18, "train_loss": 5.70669921875, "eval_loss": 5.845474526688859, "eval_accuracy": 0.009872751206669592, "eval_loss_by_set": { "aqua_rat": 5.878995418548584, "gsm8k": 6.59100341796875, "math_qa": 5.500980377197266 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.014404852160727824, "math_qa": 0.006365159128978224 } }, { "flos": 2.2356626970624655e+18, "train_loss": 5.701373291015625, "eval_loss": 5.844872861295133, "eval_accuracy": 0.012724879333040808, "eval_loss_by_set": { "aqua_rat": 5.89924430847168, "gsm8k": 6.588713212446733, "math_qa": 5.4994150797526045 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.01819560272934041, "math_qa": 0.009045226130653266 } }, { "flos": 2.241990449831084e+18, "train_loss": 5.698740234375, "eval_loss": 5.846422659384237, "eval_accuracy": 0.010092145677928916, "eval_loss_by_set": { "aqua_rat": 5.896841049194336, "gsm8k": 6.6173248291015625, "math_qa": 5.488890965779622 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.015163002274450341, "math_qa": 0.006700167504187605 } }, { "flos": 2.2483195834316882e+18, "train_loss": 5.705621337890625, "eval_loss": 5.840307338817699, "eval_accuracy": 0.013821851689337429, "eval_loss_by_set": { "aqua_rat": 5.88411808013916, "gsm8k": 6.594395030628551, "math_qa": 5.4910329182942705 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.018953752843062926, "math_qa": 0.010385259631490788 } }, { "flos": 2.2546380214899835e+18, "train_loss": 5.700506591796875, "eval_loss": 5.854876028524862, "eval_accuracy": 0.010969723562966213, "eval_loss_by_set": { "aqua_rat": 5.886903762817383, "gsm8k": 6.615445917302912, "math_qa": 5.503612518310547 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.019711902956785442, "math_qa": 0.006700167504187605 } }, { "flos": 2.2610266715261501e+18, "train_loss": 5.704786376953125, "eval_loss": 5.845178088626346, "eval_accuracy": 0.016235190873189996, "eval_loss_by_set": { "aqua_rat": 5.887404441833496, "gsm8k": 6.590978449041193, "math_qa": 5.499834060668945 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.017437452615617893, "math_qa": 0.01574539363484087 } }, { "flos": 2.2674131987747308e+18, "train_loss": 5.69666015625, "eval_loss": 5.852472717697556, "eval_accuracy": 0.01075032909170689, "eval_loss_by_set": { "aqua_rat": 5.878209114074707, "gsm8k": 6.60915097323331, "math_qa": 5.503517150878906 }, "eval_accuracy_by_set": { "aqua_rat": 0.011811023622047244, "gsm8k": 0.02122820318423048, "math_qa": 0.006030150753768844 } }, { "flos": 2.2737665259261133e+18, "train_loss": 5.703889770507812, "eval_loss": 5.840946017084895, "eval_accuracy": 0.01228609039052216, "eval_loss_by_set": { "aqua_rat": 5.888468265533447, "gsm8k": 6.600798866965554, "math_qa": 5.488719940185547 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.015163002274450341, "math_qa": 0.009715242881072027 } }, { "flos": 2.280026807979737e+18, "train_loss": 5.696318359375, "eval_loss": 5.842025602186048, "eval_accuracy": 0.013163668275559455, "eval_loss_by_set": { "aqua_rat": 5.882729530334473, "gsm8k": 6.606949546120384, "math_qa": 5.488043467203776 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.01819560272934041, "math_qa": 0.010720268006700168 } }, { "flos": 2.2864220932035052e+18, "train_loss": 5.694293212890625, "eval_loss": 5.8492629592483105, "eval_accuracy": 0.010311540149188241, "eval_loss_by_set": { "aqua_rat": 5.890068054199219, "gsm8k": 6.609692660245028, "math_qa": 5.497332255045573 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.017437452615617893, "math_qa": 0.006700167504187605 } }, { "flos": 2.292813627847082e+18, "train_loss": 5.69908447265625, "eval_loss": 5.852968963416847, "eval_accuracy": 0.013602457218078104, "eval_loss_by_set": { "aqua_rat": 5.887954235076904, "gsm8k": 6.606264287775213, "math_qa": 5.504793167114258 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.01819560272934041, "math_qa": 0.011390284757118929 } }, { "flos": 2.299158959379972e+18, "train_loss": 5.701655883789062, "eval_loss": 5.850327362885347, "eval_accuracy": 0.014260640631856078, "eval_loss_by_set": { "aqua_rat": 5.888954162597656, "gsm8k": 6.611466841264204, "math_qa": 5.498252868652344 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.017437452615617893, "math_qa": 0.012730318257956449 } }, { "flos": 2.3054970367130993e+18, "train_loss": 5.695081787109375, "eval_loss": 5.852514034992939, "eval_accuracy": 0.012724879333040808, "eval_loss_by_set": { "aqua_rat": 5.88650369644165, "gsm8k": 6.612181923606179, "math_qa": 5.5015004475911455 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.018953752843062926, "math_qa": 0.009715242881072027 } }, { "flos": 2.3118384936486175e+18, "train_loss": 5.696580810546875, "eval_loss": 5.850421750867689, "eval_accuracy": 0.01228609039052216, "eval_loss_by_set": { "aqua_rat": 5.889082908630371, "gsm8k": 6.622320001775568, "math_qa": 5.4934132893880205 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.02122820318423048, "math_qa": 0.009045226130653266 } }, { "flos": 2.3181804455791165e+18, "train_loss": 5.6969482421875, "eval_loss": 5.849817662625699, "eval_accuracy": 0.008995173321632294, "eval_loss_by_set": { "aqua_rat": 5.885490894317627, "gsm8k": 6.599881258877841, "math_qa": 5.503065745035808 }, "eval_accuracy_by_set": { "aqua_rat": 0.011811023622047244, "gsm8k": 0.014404852160727824, "math_qa": 0.006365159128978224 } }, { "flos": 2.324557286602703e+18, "train_loss": 5.6944287109375, "eval_loss": 5.849423202308449, "eval_accuracy": 0.01228609039052216, "eval_loss_by_set": { "aqua_rat": 5.8887410163879395, "gsm8k": 6.601627003062855, "math_qa": 5.501386642456055 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.017437452615617893, "math_qa": 0.009715242881072027 } }, { "flos": 2.330898579255722e+18, "train_loss": 5.695086669921875, "eval_loss": 5.854906468778043, "eval_accuracy": 0.01075032909170689, "eval_loss_by_set": { "aqua_rat": 5.8783345222473145, "gsm8k": 6.613495566628196, "math_qa": 5.50526746114095 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.01819560272934041, "math_qa": 0.006700167504187605 } }, { "flos": 2.33727945969605e+18, "train_loss": 5.697818603515625, "eval_loss": 5.841066154273781, "eval_accuracy": 0.010530934620447565, "eval_loss_by_set": { "aqua_rat": 5.887555122375488, "gsm8k": 6.607566833496094, "math_qa": 5.485879262288411 }, "eval_accuracy_by_set": { "aqua_rat": 0.011811023622047244, "gsm8k": 0.018953752843062926, "math_qa": 0.006700167504187605 } }, { "flos": 2.343533353522692e+18, "train_loss": 5.68811767578125, "eval_loss": 5.84349688968143, "eval_accuracy": 0.012724879333040808, "eval_loss_by_set": { "aqua_rat": 5.887136459350586, "gsm8k": 6.601178949529475, "math_qa": 5.4925893147786455 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.013646702047005308, "math_qa": 0.012060301507537688 } }, { "flos": 2.3498701735041434e+18, "train_loss": 5.702135009765625, "eval_loss": 5.847699500418998, "eval_accuracy": 0.014041246160596753, "eval_loss_by_set": { "aqua_rat": 5.889304161071777, "gsm8k": 6.6109841086647725, "math_qa": 5.494393666585286 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.02047005307050796, "math_qa": 0.010385259631490788 } }, { "flos": 2.356279266510897e+18, "train_loss": 5.71048095703125, "eval_loss": 5.856114928786819, "eval_accuracy": 0.01228609039052216, "eval_loss_by_set": { "aqua_rat": 5.895041465759277, "gsm8k": 6.610035289417613, "math_qa": 5.50732421875 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.016679302501895376, "math_qa": 0.009045226130653266 } }, { "flos": 2.362642382966489e+18, "train_loss": 5.708695068359375, "eval_loss": 5.83998932709565, "eval_accuracy": 0.01491882404563405, "eval_loss_by_set": { "aqua_rat": 5.887332916259766, "gsm8k": 6.595251603560015, "math_qa": 5.489882151285808 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.011372251705837756, "math_qa": 0.016080402010050253 } }, { "flos": 2.369002778560299e+18, "train_loss": 5.6959814453125, "eval_loss": 5.852960586547852, "eval_accuracy": 0.012944273804300131, "eval_loss_by_set": { "aqua_rat": 5.890275001525879, "gsm8k": 6.617176402698863, "math_qa": 5.499585469563802 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.01819560272934041, "math_qa": 0.010050251256281407 } }, { "flos": 2.3753442773717484e+18, "train_loss": 5.698948364257813, "eval_loss": 5.852313067461993, "eval_accuracy": 0.014699429574374727, "eval_loss_by_set": { "aqua_rat": 5.8855438232421875, "gsm8k": 6.619252985174006, "math_qa": 5.498029708862305 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.019711902956785442, "math_qa": 0.012060301507537688 } }, { "flos": 2.3817000778874225e+18, "train_loss": 5.693133544921875, "eval_loss": 5.845323949246793, "eval_accuracy": 0.01733216322948662, "eval_loss_by_set": { "aqua_rat": 5.890678882598877, "gsm8k": 6.610719854181463, "math_qa": 5.4907379150390625 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.014404852160727824, "math_qa": 0.017085427135678392 } }, { "flos": 2.3879630797290865e+18, "train_loss": 5.699403076171875, "eval_loss": 5.845100789456754, "eval_accuracy": 0.015577007459412023, "eval_loss_by_set": { "aqua_rat": 5.888309001922607, "gsm8k": 6.613324252041903, "math_qa": 5.489397684733073 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.02047005307050796, "math_qa": 0.01306532663316583 } }, { "flos": 2.3943199105000407e+18, "train_loss": 5.704949951171875, "eval_loss": 5.856224317808409, "eval_accuracy": 0.014699429574374727, "eval_loss_by_set": { "aqua_rat": 5.885586738586426, "gsm8k": 6.613269459117543, "math_qa": 5.506798426310222 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.019711902956785442, "math_qa": 0.011725293132328308 } }, { "flos": 2.4006635106242396e+18, "train_loss": 5.701809692382812, "eval_loss": 5.853459358215332, "eval_accuracy": 0.012066695919262835, "eval_loss_by_set": { "aqua_rat": 5.888073444366455, "gsm8k": 6.605925126509233, "math_qa": 5.5056947072347 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.019711902956785442, "math_qa": 0.008375209380234505 } }, { "flos": 2.4069758074161725e+18, "train_loss": 5.692313232421875, "eval_loss": 5.845460685523781, "eval_accuracy": 0.017551557700745943, "eval_loss_by_set": { "aqua_rat": 5.888352394104004, "gsm8k": 6.602254694158381, "math_qa": 5.495022455851237 }, "eval_accuracy_by_set": { "aqua_rat": 0.011811023622047244, "gsm8k": 0.019711902956785442, "math_qa": 0.017085427135678392 } }, { "flos": 2.4133675487550505e+18, "train_loss": 5.704451904296875, "eval_loss": 5.850213025067304, "eval_accuracy": 0.013602457218078104, "eval_loss_by_set": { "aqua_rat": 5.894105911254883, "gsm8k": 6.618732105601918, "math_qa": 5.494317372639974 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.015163002274450341, "math_qa": 0.012060301507537688 } }, { "flos": 2.4197089444872847e+18, "train_loss": 5.694718017578125, "eval_loss": 5.838582837903822, "eval_accuracy": 0.014699429574374727, "eval_loss_by_set": { "aqua_rat": 5.88482666015625, "gsm8k": 6.595563715154475, "math_qa": 5.48777961730957 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.016679302501895376, "math_qa": 0.01306532663316583 } }, { "flos": 2.426008897006338e+18, "train_loss": 5.692742919921875, "eval_loss": 5.851116231969885, "eval_accuracy": 0.01338306274681878, "eval_loss_by_set": { "aqua_rat": 5.896628379821777, "gsm8k": 6.620340520685369, "math_qa": 5.494762420654297 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.017437452615617893, "math_qa": 0.010385259631490788 } }, { "flos": 2.4323530125266125e+18, "train_loss": 5.6962432861328125, "eval_loss": 5.854904071704762, "eval_accuracy": 0.01228609039052216, "eval_loss_by_set": { "aqua_rat": 5.898038864135742, "gsm8k": 6.618276422674006, "math_qa": 5.501430511474609 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.01819560272934041, "math_qa": 0.009380234505862646 } }, { "flos": 2.4386807448941363e+18, "train_loss": 5.6953668212890625, "eval_loss": 5.8568974572259025, "eval_accuracy": 0.015577007459412023, "eval_loss_by_set": { "aqua_rat": 5.896414756774902, "gsm8k": 6.618424155495384, "math_qa": 5.504571278889974 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.018953752843062926, "math_qa": 0.01306532663316583 } }, { "flos": 2.4449848393722757e+18, "train_loss": 5.699610595703125, "eval_loss": 5.840648908872862, "eval_accuracy": 0.01338306274681878, "eval_loss_by_set": { "aqua_rat": 5.8871564865112305, "gsm8k": 6.609341708096591, "math_qa": 5.484455744425456 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.016679302501895376, "math_qa": 0.011390284757118929 } }, { "flos": 2.451319577905201e+18, "train_loss": 5.686866455078125, "eval_loss": 5.863652048884211, "eval_accuracy": 0.013821851689337429, "eval_loss_by_set": { "aqua_rat": 5.892731666564941, "gsm8k": 6.6046600341796875, "math_qa": 5.521600087483724 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.01819560272934041, "math_qa": 0.010385259631490788 } }, { "flos": 2.457686794980819e+18, "train_loss": 5.704265747070313, "eval_loss": 5.844156471458641, "eval_accuracy": 0.01491882404563405, "eval_loss_by_set": { "aqua_rat": 5.891587257385254, "gsm8k": 6.604297291148793, "math_qa": 5.4918060302734375 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.01592115238817286, "math_qa": 0.012730318257956449 } }, { "flos": 2.4639997097111716e+18, "train_loss": 5.693060302734375, "eval_loss": 5.853412576623865, "eval_accuracy": 0.011627906976744186, "eval_loss_by_set": { "aqua_rat": 5.887585639953613, "gsm8k": 6.614333412863991, "math_qa": 5.501809438069661 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.018953752843062926, "math_qa": 0.007705192629815745 } }, { "flos": 2.4703296260695654e+18, "train_loss": 5.69614990234375, "eval_loss": 5.835945258269438, "eval_accuracy": 0.014041246160596753, "eval_loss_by_set": { "aqua_rat": 5.894827365875244, "gsm8k": 6.593888716264204, "math_qa": 5.4836476643880205 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.02047005307050796, "math_qa": 0.010720268006700168 } }, { "flos": 2.476676420575691e+18, "train_loss": 5.689715576171875, "eval_loss": 5.847228411081675, "eval_accuracy": 0.013821851689337429, "eval_loss_by_set": { "aqua_rat": 5.895748615264893, "gsm8k": 6.617234663529829, "math_qa": 5.490265528361003 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.01819560272934041, "math_qa": 0.010720268006700168 } }, { "flos": 2.483013570732753e+18, "train_loss": 5.700509033203125, "eval_loss": 5.841607583535684, "eval_accuracy": 0.01228609039052216, "eval_loss_by_set": { "aqua_rat": 5.889747619628906, "gsm8k": 6.6061789772727275, "math_qa": 5.4871673583984375 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.015163002274450341, "math_qa": 0.009045226130653266 } }, { "flos": 2.489322322566054e+18, "train_loss": 5.686846923828125, "eval_loss": 5.843541274199614, "eval_accuracy": 0.01075032909170689, "eval_loss_by_set": { "aqua_rat": 5.890471458435059, "gsm8k": 6.596615878018466, "math_qa": 5.4944712320963545 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.014404852160727824, "math_qa": 0.008375209380234505 } }, { "flos": 2.4956540530112594e+18, "train_loss": 5.70845703125, "eval_loss": 5.8435592393617375, "eval_accuracy": 0.014260640631856078, "eval_loss_by_set": { "aqua_rat": 5.8918070793151855, "gsm8k": 6.603438637473366, "math_qa": 5.491260528564453 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.01288855193328279, "math_qa": 0.01440536013400335 } }, { "flos": 2.5020658046027694e+18, "train_loss": 5.704989624023438, "eval_loss": 5.850383578120051, "eval_accuracy": 0.015138218516893374, "eval_loss_by_set": { "aqua_rat": 5.889315128326416, "gsm8k": 6.6107704856178975, "math_qa": 5.498628616333008 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.01819560272934041, "math_qa": 0.01306532663316583 } }, { "flos": 2.508446664105132e+18, "train_loss": 5.709246826171875, "eval_loss": 5.84433669012946, "eval_accuracy": 0.01601579640193067, "eval_loss_by_set": { "aqua_rat": 5.893246650695801, "gsm8k": 6.607298417524858, "math_qa": 5.490570068359375 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.018953752843062926, "math_qa": 0.01440536013400335 } }, { "flos": 2.5147814445139886e+18, "train_loss": 5.68831298828125, "eval_loss": 5.846116658803579, "eval_accuracy": 0.013163668275559455, "eval_loss_by_set": { "aqua_rat": 5.886434555053711, "gsm8k": 6.605310613458807, "math_qa": 5.494792938232422 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.017437452615617893, "math_qa": 0.009715242881072027 } }, { "flos": 2.521139140720853e+18, "train_loss": 5.695611572265625, "eval_loss": 5.8497489722999365, "eval_accuracy": 0.014260640631856078, "eval_loss_by_set": { "aqua_rat": 5.886333465576172, "gsm8k": 6.611203280362216, "math_qa": 5.497700373331706 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.021986353297952996, "math_qa": 0.010720268006700168 } }, { "flos": 2.527473343993479e+18, "train_loss": 5.694125366210938, "eval_loss": 5.857046849018818, "eval_accuracy": 0.011408512505484861, "eval_loss_by_set": { "aqua_rat": 5.89363956451416, "gsm8k": 6.628242492675781, "math_qa": 5.500532786051433 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.017437452615617893, "math_qa": 0.007370184254606365 } }, { "flos": 2.533864652077531e+18, "train_loss": 5.705314331054687, "eval_loss": 5.841960211057921, "eval_accuracy": 0.021939447125932425, "eval_loss_by_set": { "aqua_rat": 5.893021106719971, "gsm8k": 6.596363414417613, "math_qa": 5.491937001546224 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.018953752843062926, "math_qa": 0.023785594639865997 } }, { "flos": 2.5401966090822615e+18, "train_loss": 5.701419677734375, "eval_loss": 5.84220620748159, "eval_accuracy": 0.013163668275559455, "eval_loss_by_set": { "aqua_rat": 5.885593891143799, "gsm8k": 6.6003196022727275, "math_qa": 5.491121927897136 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.016679302501895376, "math_qa": 0.011055276381909548 } }, { "flos": 2.546489451819827e+18, "train_loss": 5.686505126953125, "eval_loss": 5.852798436139081, "eval_accuracy": 0.012505484861781484, "eval_loss_by_set": { "aqua_rat": 5.894198894500732, "gsm8k": 6.617471174760298, "math_qa": 5.498873392740886 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.015163002274450341, "math_qa": 0.010050251256281407 } }, { "flos": 2.5528586059256955e+18, "train_loss": 5.694210205078125, "eval_loss": 5.841941627296242, "eval_accuracy": 0.013163668275559455, "eval_loss_by_set": { "aqua_rat": 5.895221710205078, "gsm8k": 6.612191633744673, "math_qa": 5.484470367431641 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.01592115238817286, "math_qa": 0.011390284757118929 } }, { "flos": 2.559264381070213e+18, "train_loss": 5.703233642578125, "eval_loss": 5.852122590348527, "eval_accuracy": 0.013163668275559455, "eval_loss_by_set": { "aqua_rat": 5.899788856506348, "gsm8k": 6.619294600053267, "math_qa": 5.496529897054036 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.021986353297952996, "math_qa": 0.008710217755443886 } }, { "flos": 2.5655762242062254e+18, "train_loss": 5.69339599609375, "eval_loss": 5.84710033519848, "eval_accuracy": 0.019745502413339184, "eval_loss_by_set": { "aqua_rat": 5.9008941650390625, "gsm8k": 6.613074562766335, "math_qa": 5.491545995076497 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.02047005307050796, "math_qa": 0.018760469011725293 } }, { "flos": 2.571958237981049e+18, "train_loss": 5.69809326171875, "eval_loss": 5.85657668758083, "eval_accuracy": 0.010092145677928916, "eval_loss_by_set": { "aqua_rat": 5.8964619636535645, "gsm8k": 6.61780409379439, "math_qa": 5.504357020060222 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.017437452615617893, "math_qa": 0.005360134003350084 } }, { "flos": 2.5783257234921226e+18, "train_loss": 5.69049072265625, "eval_loss": 5.852853517274599, "eval_accuracy": 0.013821851689337429, "eval_loss_by_set": { "aqua_rat": 5.89288330078125, "gsm8k": 6.623796636408025, "math_qa": 5.496168772379558 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.01819560272934041, "math_qa": 0.010720268006700168 } }, { "flos": 2.5846240068795105e+18, "train_loss": 5.69259033203125, "eval_loss": 5.8508540746327995, "eval_accuracy": 0.01601579640193067, "eval_loss_by_set": { "aqua_rat": 5.892026424407959, "gsm8k": 6.60623515735973, "math_qa": 5.501206715901692 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.022744503411675512, "math_qa": 0.011725293132328308 } }, { "flos": 2.5909772105505833e+18, "train_loss": 5.6924200439453125, "eval_loss": 5.855277912036793, "eval_accuracy": 0.01645458534444932, "eval_loss_by_set": { "aqua_rat": 5.892717361450195, "gsm8k": 6.608743840997869, "math_qa": 5.506819407145183 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.016679302501895376, "math_qa": 0.01541038525963149 } }, { "flos": 2.597326993280205e+18, "train_loss": 5.705574340820313, "eval_loss": 5.842551618009, "eval_accuracy": 0.011627906976744186, "eval_loss_by_set": { "aqua_rat": 5.888047218322754, "gsm8k": 6.608392888849432, "math_qa": 5.487749735514323 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.014404852160727824, "math_qa": 0.009380234505862646 } }, { "flos": 2.603734808534188e+18, "train_loss": 5.69917236328125, "eval_loss": 5.8554976179793075, "eval_accuracy": 0.01601579640193067, "eval_loss_by_set": { "aqua_rat": 5.8958282470703125, "gsm8k": 6.625414761629972, "math_qa": 5.499258041381836 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.02122820318423048, "math_qa": 0.01340033500837521 } }, { "flos": 2.610067074239693e+18, "train_loss": 5.69438232421875, "eval_loss": 5.850984341389424, "eval_accuracy": 0.011408512505484861, "eval_loss_by_set": { "aqua_rat": 5.8889546394348145, "gsm8k": 6.6155007102272725, "math_qa": 5.497416814168294 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.014404852160727824, "math_qa": 0.009045226130653266 } }, { "flos": 2.616424564288127e+18, "train_loss": 5.69774658203125, "eval_loss": 5.850585241575499, "eval_accuracy": 0.010969723562966213, "eval_loss_by_set": { "aqua_rat": 5.8931756019592285, "gsm8k": 6.630505648526278, "math_qa": 5.489572525024414 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.017437452615617893, "math_qa": 0.007035175879396985 } }, { "flos": 2.6227577781076623e+18, "train_loss": 5.701859130859375, "eval_loss": 5.853010796211861, "eval_accuracy": 0.013163668275559455, "eval_loss_by_set": { "aqua_rat": 5.891356468200684, "gsm8k": 6.610850941051137, "math_qa": 5.502471923828125 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.01061410159211524, "math_qa": 0.01373534338358459 } }, { "flos": 2.6291196168104837e+18, "train_loss": 5.69064697265625, "eval_loss": 5.839334127065298, "eval_accuracy": 0.01601579640193067, "eval_loss_by_set": { "aqua_rat": 5.89533805847168, "gsm8k": 6.595154502175071, "math_qa": 5.48824946085612 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.016679302501895376, "math_qa": 0.01507537688442211 } }, { "flos": 2.635437230235058e+18, "train_loss": 5.690831298828125, "eval_loss": 5.850163124703072, "eval_accuracy": 0.011408512505484861, "eval_loss_by_set": { "aqua_rat": 5.89781379699707, "gsm8k": 6.610055403275923, "math_qa": 5.497908274332683 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.01288855193328279, "math_qa": 0.009380234505862646 } }, { "flos": 2.6418200686436024e+18, "train_loss": 5.68924072265625, "eval_loss": 5.849927850671716, "eval_accuracy": 0.02215884159719175, "eval_loss_by_set": { "aqua_rat": 5.889657974243164, "gsm8k": 6.618298617276278, "math_qa": 5.494447072347005 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.014404852160727824, "math_qa": 0.02512562814070352 } }, { "flos": 2.6481267395652485e+18, "train_loss": 5.7001513671875, "eval_loss": 5.846516299892116, "eval_accuracy": 0.021281263712154455, "eval_loss_by_set": { "aqua_rat": 5.8954033851623535, "gsm8k": 6.601327375932173, "math_qa": 5.496487299601237 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.02047005307050796, "math_qa": 0.021775544388609715 } }, { "flos": 2.6545224575069716e+18, "train_loss": 5.695284423828125, "eval_loss": 5.856437683105469, "eval_accuracy": 0.016673979815708645, "eval_loss_by_set": { "aqua_rat": 5.894172668457031, "gsm8k": 6.629045659845525, "math_qa": 5.4991811116536455 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.015163002274450341, "math_qa": 0.01675041876046901 } }, { "flos": 2.660826057527001e+18, "train_loss": 5.6839892578125, "eval_loss": 5.846267597095387, "eval_accuracy": 0.017770952172005264, "eval_loss_by_set": { "aqua_rat": 5.895193099975586, "gsm8k": 6.610433405095881, "math_qa": 5.4919478098551435 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.013646702047005308, "math_qa": 0.018090452261306532 } }, { "flos": 2.667239848691106e+18, "train_loss": 5.70067138671875, "eval_loss": 5.852895478944521, "eval_accuracy": 0.012505484861781484, "eval_loss_by_set": { "aqua_rat": 5.889829635620117, "gsm8k": 6.621327486905185, "math_qa": 5.49761962890625 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.021986353297952996, "math_qa": 0.007035175879396985 } }, { "flos": 2.6735213983490376e+18, "train_loss": 5.690155029296875, "eval_loss": 5.847245654544315, "eval_accuracy": 0.01228609039052216, "eval_loss_by_set": { "aqua_rat": 5.8865156173706055, "gsm8k": 6.605042891068892, "math_qa": 5.496649424235026 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.01819560272934041, "math_qa": 0.009045226130653266 } }, { "flos": 2.6799715013141463e+18, "train_loss": 5.7025439453125, "eval_loss": 5.845294127593169, "eval_accuracy": 0.017551557700745943, "eval_loss_by_set": { "aqua_rat": 5.891580581665039, "gsm8k": 6.602207530628551, "math_qa": 5.494518280029297 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.01288855193328279, "math_qa": 0.017085427135678392 } }, { "flos": 2.68631293784857e+18, "train_loss": 5.7001806640625, "eval_loss": 5.842719619338577, "eval_accuracy": 0.014260640631856078, "eval_loss_by_set": { "aqua_rat": 5.883556365966797, "gsm8k": 6.597444014115767, "math_qa": 5.493401209513347 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.017437452615617893, "math_qa": 0.010385259631490788 } }, { "flos": 2.692717063725646e+18, "train_loss": 5.68893798828125, "eval_loss": 5.858770834433066, "eval_accuracy": 0.015577007459412023, "eval_loss_by_set": { "aqua_rat": 5.895404815673828, "gsm8k": 6.621664567427202, "math_qa": 5.50605837504069 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.015163002274450341, "math_qa": 0.01440536013400335 } }, { "flos": 2.699059386633945e+18, "train_loss": 5.699010009765625, "eval_loss": 5.846015775525892, "eval_accuracy": 0.017551557700745943, "eval_loss_by_set": { "aqua_rat": 5.8911638259887695, "gsm8k": 6.619074734774503, "math_qa": 5.487934748331706 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.019711902956785442, "math_qa": 0.01541038525963149 } }, { "flos": 2.7053983294029824e+18, "train_loss": 5.702869873046875, "eval_loss": 5.845800245130384, "eval_accuracy": 0.016235190873189996, "eval_loss_by_set": { "aqua_rat": 5.894954681396484, "gsm8k": 6.613121726296165, "math_qa": 5.490015029907227 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.01819560272934041, "math_qa": 0.01541038525963149 } }, { "flos": 2.711743475715408e+18, "train_loss": 5.69562744140625, "eval_loss": 5.849709485028241, "eval_accuracy": 0.014041246160596753, "eval_loss_by_set": { "aqua_rat": 5.896207809448242, "gsm8k": 6.610802390358665, "math_qa": 5.497000376383464 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.014404852160727824, "math_qa": 0.01340033500837521 } }, { "flos": 2.7181085700034396e+18, "train_loss": 5.69580810546875, "eval_loss": 5.838411795126425, "eval_accuracy": 0.010530934620447565, "eval_loss_by_set": { "aqua_rat": 5.892431259155273, "gsm8k": 6.6054229736328125, "math_qa": 5.482363382975261 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.01819560272934041, "math_qa": 0.005695142378559464 } }, { "flos": 2.724469440191136e+18, "train_loss": 5.6903228759765625, "eval_loss": 5.852735648284087, "eval_accuracy": 0.013602457218078104, "eval_loss_by_set": { "aqua_rat": 5.888314723968506, "gsm8k": 6.618698813698509, "math_qa": 5.498704274495442 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.017437452615617893, "math_qa": 0.011055276381909548 } }, { "flos": 2.73078750673476e+18, "train_loss": 5.694823608398438, "eval_loss": 5.842731321180189, "eval_accuracy": 0.01733216322948662, "eval_loss_by_set": { "aqua_rat": 5.8892927169799805, "gsm8k": 6.610391096635298, "math_qa": 5.487007141113281 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.016679302501895376, "math_qa": 0.01742043551088777 } }, { "flos": 2.737112497839407e+18, "train_loss": 5.6927337646484375, "eval_loss": 5.84756495501544, "eval_accuracy": 0.012944273804300131, "eval_loss_by_set": { "aqua_rat": 5.893826484680176, "gsm8k": 6.608741066672585, "math_qa": 5.4948374430338545 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.016679302501895376, "math_qa": 0.010385259631490788 } }, { "flos": 2.743474047705678e+18, "train_loss": 5.691026611328125, "eval_loss": 5.860868015804806, "eval_accuracy": 0.009214567792891619, "eval_loss_by_set": { "aqua_rat": 5.894033908843994, "gsm8k": 6.636984391645952, "math_qa": 5.502384185791016 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.015163002274450341, "math_qa": 0.005360134003350084 } }, { "flos": 2.749807158445998e+18, "train_loss": 5.6936883544921875, "eval_loss": 5.853283083116686, "eval_accuracy": 0.018867924528301886, "eval_loss_by_set": { "aqua_rat": 5.895646095275879, "gsm8k": 6.615549260919744, "math_qa": 5.500380833943685 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.017437452615617893, "math_qa": 0.018425460636515914 } }, { "flos": 2.756207781240373e+18, "train_loss": 5.700359497070313, "eval_loss": 5.844466467161436, "eval_accuracy": 0.01184730144800351, "eval_loss_by_set": { "aqua_rat": 5.888285160064697, "gsm8k": 6.606291337446733, "math_qa": 5.491645177205403 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.016679302501895376, "math_qa": 0.007370184254606365 } }, { "flos": 2.7625785636757176e+18, "train_loss": 5.694139404296875, "eval_loss": 5.846582077644967, "eval_accuracy": 0.013821851689337429, "eval_loss_by_set": { "aqua_rat": 5.895876407623291, "gsm8k": 6.608121004971591, "math_qa": 5.493435541788737 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.017437452615617893, "math_qa": 0.011055276381909548 } }, { "flos": 2.768891107965141e+18, "train_loss": 5.6970452880859375, "eval_loss": 5.8463467778386295, "eval_accuracy": 0.011408512505484861, "eval_loss_by_set": { "aqua_rat": 5.891256332397461, "gsm8k": 6.614880648526278, "math_qa": 5.490359624226888 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.016679302501895376, "math_qa": 0.008040201005025126 } }, { "flos": 2.7752185928351744e+18, "train_loss": 5.695658569335937, "eval_loss": 5.8505985930159286, "eval_accuracy": 0.016673979815708645, "eval_loss_by_set": { "aqua_rat": 5.89111852645874, "gsm8k": 6.611272638494318, "math_qa": 5.498579661051433 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.02122820318423048, "math_qa": 0.01340033500837521 } }, { "flos": 2.7815724767216927e+18, "train_loss": 5.695302734375, "eval_loss": 5.8489433752523885, "eval_accuracy": 0.017990346643264588, "eval_loss_by_set": { "aqua_rat": 5.886173725128174, "gsm8k": 6.602387168190696, "math_qa": 5.500512440999349 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.02047005307050796, "math_qa": 0.01574539363484087 } }, { "flos": 2.787893469748658e+18, "train_loss": 5.691138916015625, "eval_loss": 5.8458439594990494, "eval_accuracy": 0.02457218078104432, "eval_loss_by_set": { "aqua_rat": 5.8944091796875, "gsm8k": 6.6166860407049, "math_qa": 5.488494237263997 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.02047005307050796, "math_qa": 0.02613065326633166 } }, { "flos": 2.794254030698709e+18, "train_loss": 5.692386474609375, "eval_loss": 5.855280463759963, "eval_accuracy": 0.012944273804300131, "eval_loss_by_set": { "aqua_rat": 5.891032695770264, "gsm8k": 6.614209261807528, "math_qa": 5.504458745320638 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.014404852160727824, "math_qa": 0.011725293132328308 } }, { "flos": 2.800548769127465e+18, "train_loss": 5.686062622070312, "eval_loss": 5.844985265989561, "eval_accuracy": 0.01733216322948662, "eval_loss_by_set": { "aqua_rat": 5.894175052642822, "gsm8k": 6.611891313032671, "math_qa": 5.489387512207031 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.016679302501895376, "math_qa": 0.016080402010050253 } }, { "flos": 2.80686803128261e+18, "train_loss": 5.682366943359375, "eval_loss": 5.854434245341533, "eval_accuracy": 0.01075032909170689, "eval_loss_by_set": { "aqua_rat": 5.888614654541016, "gsm8k": 6.622662630948153, "math_qa": 5.499481201171875 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.01592115238817286, "math_qa": 0.007035175879396985 } }, { "flos": 2.8132161448805663e+18, "train_loss": 5.69708740234375, "eval_loss": 5.843376288542876, "eval_accuracy": 0.017770952172005264, "eval_loss_by_set": { "aqua_rat": 5.892427921295166, "gsm8k": 6.607202009721235, "math_qa": 5.4892018636067705 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.015163002274450341, "math_qa": 0.018090452261306532 } }, { "flos": 2.8195268960211436e+18, "train_loss": 5.687561645507812, "eval_loss": 5.848403440939413, "eval_accuracy": 0.013163668275559455, "eval_loss_by_set": { "aqua_rat": 5.89831018447876, "gsm8k": 6.612849148837003, "math_qa": 5.493873596191406 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.01592115238817286, "math_qa": 0.010720268006700168 } }, { "flos": 2.8259073641446113e+18, "train_loss": 5.696270751953125, "eval_loss": 5.84309315037083, "eval_accuracy": 0.015796401930671347, "eval_loss_by_set": { "aqua_rat": 5.889608383178711, "gsm8k": 6.601349570534446, "math_qa": 5.491682688395183 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.02122820318423048, "math_qa": 0.012395309882747068 } }, { "flos": 2.8322489445604393e+18, "train_loss": 5.691463623046875, "eval_loss": 5.855861638043378, "eval_accuracy": 0.01338306274681878, "eval_loss_by_set": { "aqua_rat": 5.901124477386475, "gsm8k": 6.62432237104936, "math_qa": 5.499878565470378 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.01592115238817286, "math_qa": 0.012060301507537688 } }, { "flos": 2.838660283835089e+18, "train_loss": 5.68152587890625, "eval_loss": 5.852842640232396, "eval_accuracy": 0.01601579640193067, "eval_loss_by_set": { "aqua_rat": 5.896660804748535, "gsm8k": 6.616262262517756, "math_qa": 5.499290466308594 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.01592115238817286, "math_qa": 0.016080402010050253 } }, { "flos": 2.844988284101198e+18, "train_loss": 5.6946875, "eval_loss": 5.855149810378616, "eval_accuracy": 0.015796401930671347, "eval_loss_by_set": { "aqua_rat": 5.893460273742676, "gsm8k": 6.62462685324929, "math_qa": 5.499280293782552 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.018953752843062926, "math_qa": 0.01340033500837521 } }, { "flos": 2.8513389322667295e+18, "train_loss": 5.692657470703125, "eval_loss": 5.855052947998047, "eval_accuracy": 0.017112768758227294, "eval_loss_by_set": { "aqua_rat": 5.89301872253418, "gsm8k": 6.619300148703835, "math_qa": 5.501609166463216 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.01819560272934041, "math_qa": 0.01675041876046901 } }, { "flos": 2.857704253651157e+18, "train_loss": 5.699345703125, "eval_loss": 5.8522169267809065, "eval_accuracy": 0.017551557700745943, "eval_loss_by_set": { "aqua_rat": 5.8866987228393555, "gsm8k": 6.61713964288885, "math_qa": 5.4987538655598955 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.015163002274450341, "math_qa": 0.018760469011725293 } }, { "flos": 2.864071512065835e+18, "train_loss": 5.690308837890625, "eval_loss": 5.855036580884779, "eval_accuracy": 0.014041246160596753, "eval_loss_by_set": { "aqua_rat": 5.88993501663208, "gsm8k": 6.617055025967685, "math_qa": 5.502869923909505 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.014404852160727824, "math_qa": 0.01373534338358459 } }, { "flos": 2.870479389596844e+18, "train_loss": 5.692997436523438, "eval_loss": 5.8488753035261825, "eval_accuracy": 0.02830188679245283, "eval_loss_by_set": { "aqua_rat": 5.894386291503906, "gsm8k": 6.605073408647017, "math_qa": 5.498491923014323 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.021986353297952996, "math_qa": 0.03149078726968174 } }, { "flos": 2.8768308623960965e+18, "train_loss": 5.68419921875, "eval_loss": 5.8568671716226115, "eval_accuracy": 0.01996489688459851, "eval_loss_by_set": { "aqua_rat": 5.895057201385498, "gsm8k": 6.608577381480824, "math_qa": 5.5091508229573565 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.019711902956785442, "math_qa": 0.019430485762144054 } }, { "flos": 2.883253391671165e+18, "train_loss": 5.703057861328125, "eval_loss": 5.845434343492663, "eval_accuracy": 0.02150065818341378, "eval_loss_by_set": { "aqua_rat": 5.889017105102539, "gsm8k": 6.603213223544034, "math_qa": 5.494487126668294 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.021986353297952996, "math_qa": 0.021105527638190954 } }, { "flos": 2.8895425863708836e+18, "train_loss": 5.67859619140625, "eval_loss": 5.847240576872954, "eval_accuracy": 0.023255813953488372, "eval_loss_by_set": { "aqua_rat": 5.895981311798096, "gsm8k": 6.611695723100142, "math_qa": 5.492803573608398 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.013646702047005308, "math_qa": 0.02814070351758794 } }, { "flos": 2.8959685779264635e+18, "train_loss": 5.705029296875, "eval_loss": 5.847819019008327, "eval_accuracy": 0.018429135585783237, "eval_loss_by_set": { "aqua_rat": 5.8922247886657715, "gsm8k": 6.6061553955078125, "math_qa": 5.496547698974609 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.012130401819560273, "math_qa": 0.021440536013400336 } }, { "flos": 2.9022881901214433e+18, "train_loss": 5.686984252929688, "eval_loss": 5.844267767828864, "eval_accuracy": 0.020184291355857833, "eval_loss_by_set": { "aqua_rat": 5.899784088134766, "gsm8k": 6.606463345614347, "math_qa": 5.490301767985026 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.02047005307050796, "math_qa": 0.020100502512562814 } }, { "flos": 2.9086675453115105e+18, "train_loss": 5.694365844726563, "eval_loss": 5.851551571407834, "eval_accuracy": 0.017551557700745943, "eval_loss_by_set": { "aqua_rat": 5.897678375244141, "gsm8k": 6.6155478737571025, "math_qa": 5.49754269917806 }, "eval_accuracy_by_set": { "aqua_rat": 0.011811023622047244, "gsm8k": 0.01819560272934041, "math_qa": 0.017755443886097153 } }, { "flos": 2.9150137632182764e+18, "train_loss": 5.693758544921875, "eval_loss": 5.8513008323875635, "eval_accuracy": 0.01996489688459851, "eval_loss_by_set": { "aqua_rat": 5.896488189697266, "gsm8k": 6.614614313299006, "math_qa": 5.497683207194011 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.019711902956785442, "math_qa": 0.019765494137353432 } }, { "flos": 2.921332138999546e+18, "train_loss": 5.687133178710938, "eval_loss": 5.847618566977011, "eval_accuracy": 0.023036419482229047, "eval_loss_by_set": { "aqua_rat": 5.901196479797363, "gsm8k": 6.60169150612571, "math_qa": 5.497536977132161 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.01819560272934041, "math_qa": 0.024790619765494137 } }, { "flos": 2.92765974788676e+18, "train_loss": 5.68791259765625, "eval_loss": 5.848576777690166, "eval_accuracy": 0.019745502413339184, "eval_loss_by_set": { "aqua_rat": 5.8871660232543945, "gsm8k": 6.609999916770241, "math_qa": 5.496375401814778 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.018953752843062926, "math_qa": 0.019430485762144054 } }, { "flos": 2.934070035968164e+18, "train_loss": 5.695242919921875, "eval_loss": 5.844802340945682, "eval_accuracy": 0.020623080298376482, "eval_loss_by_set": { "aqua_rat": 5.895944595336914, "gsm8k": 6.59676083651456, "math_qa": 5.495892842610677 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.018953752843062926, "math_qa": 0.021775544388609715 } }, { "flos": 2.940421158190711e+18, "train_loss": 5.6884222412109375, "eval_loss": 5.856805646741712, "eval_accuracy": 0.015796401930671347, "eval_loss_by_set": { "aqua_rat": 5.892759323120117, "gsm8k": 6.630777532404119, "math_qa": 5.499072392781575 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.01592115238817286, "math_qa": 0.01507537688442211 } }, { "flos": 2.9467553405253714e+18, "train_loss": 5.687813110351563, "eval_loss": 5.846451991313213, "eval_accuracy": 0.014480035103115402, "eval_loss_by_set": { "aqua_rat": 5.890002250671387, "gsm8k": 6.60226093639027, "math_qa": 5.496410369873047 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.015163002274450341, "math_qa": 0.01306532663316583 } }, { "flos": 2.953074417460052e+18, "train_loss": 5.693372802734375, "eval_loss": 5.846036782135835, "eval_accuracy": 0.02150065818341378, "eval_loss_by_set": { "aqua_rat": 5.89670991897583, "gsm8k": 6.621370488947088, "math_qa": 5.486452738444011 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.01819560272934041, "math_qa": 0.021775544388609715 } }, { "flos": 2.9594459627889623e+18, "train_loss": 5.6849658203125, "eval_loss": 5.851326736243996, "eval_accuracy": 0.011627906976744186, "eval_loss_by_set": { "aqua_rat": 5.895239353179932, "gsm8k": 6.61187119917436, "math_qa": 5.49908447265625 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.013646702047005308, "math_qa": 0.010385259631490788 } }, { "flos": 2.96579885722239e+18, "train_loss": 5.68975830078125, "eval_loss": 5.856810028488572, "eval_accuracy": 0.017990346643264588, "eval_loss_by_set": { "aqua_rat": 5.886561393737793, "gsm8k": 6.612050836736506, "math_qa": 5.5081787109375 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.017437452615617893, "math_qa": 0.017755443886097153 } }, { "flos": 2.972193215270093e+18, "train_loss": 5.69636962890625, "eval_loss": 5.846395853403452, "eval_accuracy": 0.020842474769635806, "eval_loss_by_set": { "aqua_rat": 5.889547348022461, "gsm8k": 6.617155595259233, "math_qa": 5.489535013834636 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.02047005307050796, "math_qa": 0.019765494137353432 } }, { "flos": 2.9784652848614605e+18, "train_loss": 5.691395263671875, "eval_loss": 5.848749186541583, "eval_accuracy": 0.019745502413339184, "eval_loss_by_set": { "aqua_rat": 5.891496181488037, "gsm8k": 6.6083595969460225, "math_qa": 5.497032165527344 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.016679302501895376, "math_qa": 0.020770519262981575 } }, { "flos": 2.9848902257606656e+18, "train_loss": 5.693231201171875, "eval_loss": 5.847570238886653, "eval_accuracy": 0.022378236068451074, "eval_loss_by_set": { "aqua_rat": 5.899569988250732, "gsm8k": 6.613308993252841, "math_qa": 5.492273330688477 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.01819560272934041, "math_qa": 0.023785594639865997 } }, { "flos": 2.991195392370016e+18, "train_loss": 5.69407958984375, "eval_loss": 5.847903535172746, "eval_accuracy": 0.02106186924089513, "eval_loss_by_set": { "aqua_rat": 5.899754524230957, "gsm8k": 6.614131580699574, "math_qa": 5.492394765218099 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.015163002274450341, "math_qa": 0.023785594639865997 } }, { "flos": 2.997577385743745e+18, "train_loss": 5.694868774414062, "eval_loss": 5.853277773470492, "eval_accuracy": 0.022378236068451074, "eval_loss_by_set": { "aqua_rat": 5.891660690307617, "gsm8k": 6.610700433904475, "math_qa": 5.502927144368489 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.015163002274450341, "math_qa": 0.025460636515912898 } }, { "flos": 3.003937267015221e+18, "train_loss": 5.6819091796875, "eval_loss": 5.852919990951951, "eval_accuracy": 0.02215884159719175, "eval_loss_by_set": { "aqua_rat": 5.894952297210693, "gsm8k": 6.628060774369673, "math_qa": 5.494144439697266 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.022744503411675512, "math_qa": 0.022110552763819097 } }, { "flos": 3.0102437113773425e+18, "train_loss": 5.68967529296875, "eval_loss": 5.84812102446685, "eval_accuracy": 0.02632733655111891, "eval_loss_by_set": { "aqua_rat": 5.895957946777344, "gsm8k": 6.603367198597301, "math_qa": 5.497980117797852 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.013646702047005308, "math_qa": 0.032160804020100506 } }, { "flos": 3.016605756238594e+18, "train_loss": 5.69359130859375, "eval_loss": 5.851879377622862, "eval_accuracy": 0.019745502413339184, "eval_loss_by_set": { "aqua_rat": 5.8895673751831055, "gsm8k": 6.616389881480824, "math_qa": 5.498338063557942 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.01288855193328279, "math_qa": 0.022110552763819097 } }, { "flos": 3.0229640505196544e+18, "train_loss": 5.69855712890625, "eval_loss": 5.85285387812434, "eval_accuracy": 0.017770952172005264, "eval_loss_by_set": { "aqua_rat": 5.892500877380371, "gsm8k": 6.617998296564275, "math_qa": 5.4988587697347 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.015163002274450341, "math_qa": 0.018425460636515914 } }, { "flos": 3.029302437090427e+18, "train_loss": 5.692156372070312, "eval_loss": 5.8453792881321265, "eval_accuracy": 0.013163668275559455, "eval_loss_by_set": { "aqua_rat": 5.893003463745117, "gsm8k": 6.609472101384943, "math_qa": 5.491201400756836 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.017437452615617893, "math_qa": 0.010720268006700168 } }, { "flos": 3.035641833515385e+18, "train_loss": 5.68783935546875, "eval_loss": 5.848179379025021, "eval_accuracy": 0.023475208424747696, "eval_loss_by_set": { "aqua_rat": 5.900932312011719, "gsm8k": 6.61394639448686, "math_qa": 5.492806752522786 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.017437452615617893, "math_qa": 0.025460636515912898 } }, { "flos": 3.0419893087738266e+18, "train_loss": 5.689066772460937, "eval_loss": 5.853780617585054, "eval_accuracy": 0.020623080298376482, "eval_loss_by_set": { "aqua_rat": 5.895390033721924, "gsm8k": 6.615509033203125, "math_qa": 5.501187642415364 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.018953752843062926, "math_qa": 0.021775544388609715 } }, { "flos": 3.0483138258214584e+18, "train_loss": 5.685413818359375, "eval_loss": 5.855513753117742, "eval_accuracy": 0.020842474769635806, "eval_loss_by_set": { "aqua_rat": 5.893540382385254, "gsm8k": 6.6112892844460225, "math_qa": 5.505947748819987 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.013646702047005308, "math_qa": 0.023115577889447236 } }, { "flos": 3.0546496778246554e+18, "train_loss": 5.695525512695313, "eval_loss": 5.847150854162268, "eval_accuracy": 0.020184291355857833, "eval_loss_by_set": { "aqua_rat": 5.8916778564453125, "gsm8k": 6.614789789373225, "math_qa": 5.491605758666992 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.014404852160727824, "math_qa": 0.022110552763819097 } }, { "flos": 3.0610240256197263e+18, "train_loss": 5.690599975585937, "eval_loss": 5.845673741521062, "eval_accuracy": 0.020403685827117157, "eval_loss_by_set": { "aqua_rat": 5.894197463989258, "gsm8k": 6.608894348144531, "math_qa": 5.491820653279622 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.019711902956785442, "math_qa": 0.020435510887772193 } }, { "flos": 3.0673680998009405e+18, "train_loss": 5.690408935546875, "eval_loss": 5.847399917808739, "eval_accuracy": 0.014041246160596753, "eval_loss_by_set": { "aqua_rat": 5.892444133758545, "gsm8k": 6.615192760120738, "math_qa": 5.491741180419922 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.01819560272934041, "math_qa": 0.011055276381909548 } }, { "flos": 3.0737027561926164e+18, "train_loss": 5.689891357421875, "eval_loss": 5.843763763840134, "eval_accuracy": 0.015577007459412023, "eval_loss_by_set": { "aqua_rat": 5.891726493835449, "gsm8k": 6.615482677112926, "math_qa": 5.486062367757161 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.018953752843062926, "math_qa": 0.01407035175879397 } }, { "flos": 3.0800372891039826e+18, "train_loss": 5.691824951171875, "eval_loss": 5.848525073077227, "eval_accuracy": 0.017551557700745943, "eval_loss_by_set": { "aqua_rat": 5.894571304321289, "gsm8k": 6.608781987970525, "math_qa": 5.496236801147461 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.017437452615617893, "math_qa": 0.01675041876046901 } }, { "flos": 3.086384454587908e+18, "train_loss": 5.69866455078125, "eval_loss": 5.848626910029231, "eval_accuracy": 0.013821851689337429, "eval_loss_by_set": { "aqua_rat": 5.892953395843506, "gsm8k": 6.627401872114702, "math_qa": 5.4879945119222 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.019711902956785442, "math_qa": 0.010385259631490788 } }, { "flos": 3.0928012549134746e+18, "train_loss": 5.699117431640625, "eval_loss": 5.84741870777027, "eval_accuracy": 0.015577007459412023, "eval_loss_by_set": { "aqua_rat": 5.8887786865234375, "gsm8k": 6.612178455699574, "math_qa": 5.493457158406575 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.014404852160727824, "math_qa": 0.01507537688442211 } }, { "flos": 3.099156767129469e+18, "train_loss": 5.6819580078125, "eval_loss": 5.852208214837152, "eval_accuracy": 0.01908731899956121, "eval_loss_by_set": { "aqua_rat": 5.893083572387695, "gsm8k": 6.616944052956321, "math_qa": 5.498298009236653 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.01592115238817286, "math_qa": 0.020100502512562814 } }, { "flos": 3.1054651066459095e+18, "train_loss": 5.6840869140625, "eval_loss": 5.847108763617438, "eval_accuracy": 0.016673979815708645, "eval_loss_by_set": { "aqua_rat": 5.890929698944092, "gsm8k": 6.61394639448686, "math_qa": 5.491989771525065 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.02047005307050796, "math_qa": 0.01340033500837521 } }, { "flos": 3.111772622602371e+18, "train_loss": 5.687322387695312, "eval_loss": 5.847940573821196, "eval_accuracy": 0.01733216322948662, "eval_loss_by_set": { "aqua_rat": 5.899177074432373, "gsm8k": 6.611392628062855, "math_qa": 5.493755340576172 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.02047005307050796, "math_qa": 0.01541038525963149 } }, { "flos": 3.1181332039535165e+18, "train_loss": 5.682894287109375, "eval_loss": 5.8519759564786344, "eval_accuracy": 0.020184291355857833, "eval_loss_by_set": { "aqua_rat": 5.894611835479736, "gsm8k": 6.618463689630682, "math_qa": 5.4971160888671875 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.02047005307050796, "math_qa": 0.019430485762144054 } }, { "flos": 3.1244646455621714e+18, "train_loss": 5.69004638671875, "eval_loss": 5.852446633416253, "eval_accuracy": 0.012724879333040808, "eval_loss_by_set": { "aqua_rat": 5.894957542419434, "gsm8k": 6.624090021306818, "math_qa": 5.4952341715494795 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.014404852160727824, "math_qa": 0.011055276381909548 } }, { "flos": 3.130829534228644e+18, "train_loss": 5.694320068359375, "eval_loss": 5.857978511501003, "eval_accuracy": 0.014699429574374727, "eval_loss_by_set": { "aqua_rat": 5.894514083862305, "gsm8k": 6.627681385387074, "math_qa": 5.502153396606445 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.015163002274450341, "math_qa": 0.01340033500837521 } }, { "flos": 3.1371803885526057e+18, "train_loss": 5.68634765625, "eval_loss": 5.845113290322794, "eval_accuracy": 0.015796401930671347, "eval_loss_by_set": { "aqua_rat": 5.891302108764648, "gsm8k": 6.607342806729403, "math_qa": 5.491909027099609 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.014404852160727824, "math_qa": 0.016080402010050253 } }, { "flos": 3.1435161992167424e+18, "train_loss": 5.692227783203125, "eval_loss": 5.850147505064268, "eval_accuracy": 0.020184291355857833, "eval_loss_by_set": { "aqua_rat": 5.89255428314209, "gsm8k": 6.603633533824574, "math_qa": 5.50126584370931 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.016679302501895376, "math_qa": 0.021775544388609715 } }, { "flos": 3.149931783529693e+18, "train_loss": 5.683433837890625, "eval_loss": 5.853804510992926, "eval_accuracy": 0.015357612988152698, "eval_loss_by_set": { "aqua_rat": 5.89483642578125, "gsm8k": 6.61378964510831, "math_qa": 5.502058664957683 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.01819560272934041, "math_qa": 0.01340033500837521 } }, { "flos": 3.1562412161153106e+18, "train_loss": 5.695252685546875, "eval_loss": 5.849680230424211, "eval_accuracy": 0.01645458534444932, "eval_loss_by_set": { "aqua_rat": 5.889811038970947, "gsm8k": 6.618969310413707, "math_qa": 5.49374516805013 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.02122820318423048, "math_qa": 0.01407035175879397 } }, { "flos": 3.1626378617699697e+18, "train_loss": 5.693051147460937, "eval_loss": 5.852138106887405, "eval_accuracy": 0.014480035103115402, "eval_loss_by_set": { "aqua_rat": 5.893831253051758, "gsm8k": 6.611405112526634, "math_qa": 5.5006663004557295 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.016679302501895376, "math_qa": 0.012060301507537688 } }, { "flos": 3.1689527344685384e+18, "train_loss": 5.697141723632813, "eval_loss": 5.8512223217938395, "eval_accuracy": 0.01864853005704256, "eval_loss_by_set": { "aqua_rat": 5.897122383117676, "gsm8k": 6.610252380371094, "math_qa": 5.499508539835612 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.01592115238817286, "math_qa": 0.019430485762144054 } }, { "flos": 3.1752754385031004e+18, "train_loss": 5.679315185546875, "eval_loss": 5.847096520501214, "eval_accuracy": 0.01952610794207986, "eval_loss_by_set": { "aqua_rat": 5.890256881713867, "gsm8k": 6.62285683371804, "math_qa": 5.487943013509114 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.018953752843062926, "math_qa": 0.019430485762144054 } }, { "flos": 3.181681172308558e+18, "train_loss": 5.69995361328125, "eval_loss": 5.849997340021907, "eval_accuracy": 0.023036419482229047, "eval_loss_by_set": { "aqua_rat": 5.89332389831543, "gsm8k": 6.622093894264915, "math_qa": 5.492509206136067 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.016679302501895376, "math_qa": 0.02579564489112228 } }, { "flos": 3.1879906456963645e+18, "train_loss": 5.683516845703125, "eval_loss": 5.853724892074998, "eval_accuracy": 0.020403685827117157, "eval_loss_by_set": { "aqua_rat": 5.891185283660889, "gsm8k": 6.624631014737216, "math_qa": 5.497271219889323 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.018953752843062926, "math_qa": 0.019430485762144054 } }, { "flos": 3.1943596140448973e+18, "train_loss": 5.70221923828125, "eval_loss": 5.853119025359282, "eval_accuracy": 0.013821851689337429, "eval_loss_by_set": { "aqua_rat": 5.89635705947876, "gsm8k": 6.623476895419034, "math_qa": 5.496435165405273 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.015163002274450341, "math_qa": 0.012730318257956449 } }, { "flos": 3.200660844316721e+18, "train_loss": 5.683984375, "eval_loss": 5.848412487957929, "eval_accuracy": 0.01908731899956121, "eval_loss_by_set": { "aqua_rat": 5.900480270385742, "gsm8k": 6.613628040660512, "math_qa": 5.493349711100261 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.018953752843062926, "math_qa": 0.019430485762144054 } }, { "flos": 3.2069960155676017e+18, "train_loss": 5.695399780273437, "eval_loss": 5.854424012673868, "eval_accuracy": 0.01864853005704256, "eval_loss_by_set": { "aqua_rat": 5.896871089935303, "gsm8k": 6.6208343505859375, "math_qa": 5.49961535135905 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.016679302501895376, "math_qa": 0.018425460636515914 } }, { "flos": 3.2133298682635223e+18, "train_loss": 5.690369873046875, "eval_loss": 5.843708605379672, "eval_accuracy": 0.02150065818341378, "eval_loss_by_set": { "aqua_rat": 5.898510932922363, "gsm8k": 6.61547157981179, "math_qa": 5.4854170481363935 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.01592115238817286, "math_qa": 0.023450586264656615 } }, { "flos": 3.219723319536255e+18, "train_loss": 5.692159423828125, "eval_loss": 5.85478164054252, "eval_accuracy": 0.020623080298376482, "eval_loss_by_set": { "aqua_rat": 5.892149925231934, "gsm8k": 6.614705866033381, "math_qa": 5.503369013468425 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.024260803639120546, "math_qa": 0.018090452261306532 } }, { "flos": 3.226135895224615e+18, "train_loss": 5.695617065429688, "eval_loss": 5.852523906810863, "eval_accuracy": 0.013163668275559455, "eval_loss_by_set": { "aqua_rat": 5.89891242980957, "gsm8k": 6.623476895419034, "math_qa": 5.4953047434488935 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.01819560272934041, "math_qa": 0.010385259631490788 } }, { "flos": 3.232464719587574e+18, "train_loss": 5.7000360107421875, "eval_loss": 5.854465407294196, "eval_accuracy": 0.013821851689337429, "eval_loss_by_set": { "aqua_rat": 5.895042896270752, "gsm8k": 6.625393954190341, "math_qa": 5.49774169921875 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.015163002274450341, "math_qa": 0.011725293132328308 } }, { "flos": 3.238825157057315e+18, "train_loss": 5.675521240234375, "eval_loss": 5.849781912726325, "eval_accuracy": 0.018429135585783237, "eval_loss_by_set": { "aqua_rat": 5.893816947937012, "gsm8k": 6.625040227716619, "math_qa": 5.490785598754883 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.018953752843062926, "math_qa": 0.017755443886097153 } }, { "flos": 3.2451761966017413e+18, "train_loss": 5.688980712890625, "eval_loss": 5.853418015144967, "eval_accuracy": 0.011408512505484861, "eval_loss_by_set": { "aqua_rat": 5.896364688873291, "gsm8k": 6.616456465287642, "math_qa": 5.500113169352214 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.017437452615617893, "math_qa": 0.008375209380234505 } }, { "flos": 3.2515822192437494e+18, "train_loss": 5.703771362304687, "eval_loss": 5.857673645019531, "eval_accuracy": 0.01228609039052216, "eval_loss_by_set": { "aqua_rat": 5.897708892822266, "gsm8k": 6.628520618785512, "math_qa": 5.5010325113932295 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.018953752843062926, "math_qa": 0.009045226130653266 } }, { "flos": 3.257923985416913e+18, "train_loss": 5.687686767578125, "eval_loss": 5.860761358931258, "eval_accuracy": 0.012505484861781484, "eval_loss_by_set": { "aqua_rat": 5.889642238616943, "gsm8k": 6.639507640491832, "math_qa": 5.5014292399088545 }, "eval_accuracy_by_set": { "aqua_rat": 0.011811023622047244, "gsm8k": 0.02047005307050796, "math_qa": 0.009045226130653266 } }, { "flos": 3.264280919267082e+18, "train_loss": 5.69550048828125, "eval_loss": 5.848164532635663, "eval_accuracy": 0.014041246160596753, "eval_loss_by_set": { "aqua_rat": 5.898441314697266, "gsm8k": 6.599429043856534, "math_qa": 5.499645233154297 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.016679302501895376, "math_qa": 0.012060301507537688 } }, { "flos": 3.270657347973808e+18, "train_loss": 5.683162841796875, "eval_loss": 5.850398398734428, "eval_accuracy": 0.01491882404563405, "eval_loss_by_set": { "aqua_rat": 5.898351669311523, "gsm8k": 6.621678439053622, "math_qa": 5.492898941040039 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.01819560272934041, "math_qa": 0.01340033500837521 } }, { "flos": 3.2769373310424187e+18, "train_loss": 5.681253662109375, "eval_loss": 5.854848449294631, "eval_accuracy": 0.01689337428696797, "eval_loss_by_set": { "aqua_rat": 5.9001569747924805, "gsm8k": 6.62012342973189, "math_qa": 5.500321706136067 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.016679302501895376, "math_qa": 0.017085427135678392 } }, { "flos": 3.2833236317314744e+18, "train_loss": 5.6979248046875, "eval_loss": 5.848431767644109, "eval_accuracy": 0.01864853005704256, "eval_loss_by_set": { "aqua_rat": 5.889904022216797, "gsm8k": 6.619258533824574, "math_qa": 5.491680145263672 }, "eval_accuracy_by_set": { "aqua_rat": 0.011811023622047244, "gsm8k": 0.016679302501895376, "math_qa": 0.020100502512562814 } }, { "flos": 3.2895823681337426e+18, "train_loss": 5.689835205078125, "eval_loss": 5.8472380251497835, "eval_accuracy": 0.010969723562966213, "eval_loss_by_set": { "aqua_rat": 5.895155906677246, "gsm8k": 6.621251886541193, "math_qa": 5.488488515218099 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.01288855193328279, "math_qa": 0.009045226130653266 } }, { "flos": 3.295995726579892e+18, "train_loss": 5.687745971679687, "eval_loss": 5.853444795350771, "eval_accuracy": 0.014041246160596753, "eval_loss_by_set": { "aqua_rat": 5.89759635925293, "gsm8k": 6.619231484153054, "math_qa": 5.498779932657878 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.014404852160727824, "math_qa": 0.01373534338358459 } }, { "flos": 3.3023468284013445e+18, "train_loss": 5.695557861328125, "eval_loss": 5.843252439756651, "eval_accuracy": 0.018867924528301886, "eval_loss_by_set": { "aqua_rat": 5.893627166748047, "gsm8k": 6.601912064985796, "math_qa": 5.491335550944011 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.02047005307050796, "math_qa": 0.018425460636515914 } }, { "flos": 3.3086879760992174e+18, "train_loss": 5.6870166015625, "eval_loss": 5.851797542056522, "eval_accuracy": 0.013602457218078104, "eval_loss_by_set": { "aqua_rat": 5.894763469696045, "gsm8k": 6.611030578613281, "math_qa": 5.500235239664714 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.018953752843062926, "math_qa": 0.010050251256281407 } }, { "flos": 3.315038356903035e+18, "train_loss": 5.685133666992187, "eval_loss": 5.856651821651974, "eval_accuracy": 0.013163668275559455, "eval_loss_by_set": { "aqua_rat": 5.88929557800293, "gsm8k": 6.61730263449929, "math_qa": 5.505299886067708 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.018953752843062926, "math_qa": 0.009715242881072027 } }, { "flos": 3.3214230292626145e+18, "train_loss": 5.692523193359375, "eval_loss": 5.846343349766087, "eval_accuracy": 0.01601579640193067, "eval_loss_by_set": { "aqua_rat": 5.899837017059326, "gsm8k": 6.6098175048828125, "math_qa": 5.491959889729817 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.01592115238817286, "math_qa": 0.016080402010050253 } }, { "flos": 3.327785403762606e+18, "train_loss": 5.6943017578125, "eval_loss": 5.856473123705065, "eval_accuracy": 0.015357612988152698, "eval_loss_by_set": { "aqua_rat": 5.89760160446167, "gsm8k": 6.632123080166903, "math_qa": 5.497539520263672 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.019711902956785442, "math_qa": 0.012395309882747068 } }, { "flos": 3.3340573289356984e+18, "train_loss": 5.68181884765625, "eval_loss": 5.852114290804477, "eval_accuracy": 0.012944273804300131, "eval_loss_by_set": { "aqua_rat": 5.896697998046875, "gsm8k": 6.608011419122869, "math_qa": 5.501946131388347 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.013646702047005308, "math_qa": 0.011055276381909548 } }, { "flos": 3.3404199090572493e+18, "train_loss": 5.692882080078125, "eval_loss": 5.857223871591929, "eval_accuracy": 0.01228609039052216, "eval_loss_by_set": { "aqua_rat": 5.901789665222168, "gsm8k": 6.623354131525213, "math_qa": 5.50236701965332 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.017437452615617893, "math_qa": 0.009380234505862646 } }, { "flos": 3.3468139374662124e+18, "train_loss": 5.694171142578125, "eval_loss": 5.851287274747281, "eval_accuracy": 0.011189118034225537, "eval_loss_by_set": { "aqua_rat": 5.896637916564941, "gsm8k": 6.618236888538707, "math_qa": 5.495989481608073 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.01592115238817286, "math_qa": 0.008710217755443886 } }, { "flos": 3.3531466777656033e+18, "train_loss": 5.6839971923828125, "eval_loss": 5.851441795761521, "eval_accuracy": 0.010311540149188241, "eval_loss_by_set": { "aqua_rat": 5.89794397354126, "gsm8k": 6.616535533558238, "math_qa": 5.496898651123047 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.016679302501895376, "math_qa": 0.006700167504187605 } }, { "flos": 3.359514554118701e+18, "train_loss": 5.686259765625, "eval_loss": 5.856931815276274, "eval_accuracy": 0.01184730144800351, "eval_loss_by_set": { "aqua_rat": 5.895444393157959, "gsm8k": 6.6316750266335225, "math_qa": 5.4986317952473955 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.017437452615617893, "math_qa": 0.007705192629815745 } }, { "flos": 3.3658234917093376e+18, "train_loss": 5.687666015625, "eval_loss": 5.852012840477196, "eval_accuracy": 0.010530934620447565, "eval_loss_by_set": { "aqua_rat": 5.896080017089844, "gsm8k": 6.609111439098012, "math_qa": 5.501337051391602 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.013646702047005308, "math_qa": 0.008375209380234505 } }, { "flos": 3.372206041281331e+18, "train_loss": 5.689342651367188, "eval_loss": 5.850627538320181, "eval_accuracy": 0.010530934620447565, "eval_loss_by_set": { "aqua_rat": 5.90183162689209, "gsm8k": 6.6324615478515625, "math_qa": 5.488019943237305 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.02047005307050796, "math_qa": 0.005360134003350084 } }, { "flos": 3.37853329959184e+18, "train_loss": 5.680617065429687, "eval_loss": 5.853442011652766, "eval_accuracy": 0.01689337428696797, "eval_loss_by_set": { "aqua_rat": 5.892372131347656, "gsm8k": 6.613096063787287, "math_qa": 5.502023061116536 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.01819560272934041, "math_qa": 0.016080402010050253 } }, { "flos": 3.3848962098890015e+18, "train_loss": 5.688688354492188, "eval_loss": 5.860803165951291, "eval_accuracy": 0.014260640631856078, "eval_loss_by_set": { "aqua_rat": 5.895618915557861, "gsm8k": 6.62801777232777, "math_qa": 5.506261825561523 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.019711902956785442, "math_qa": 0.011725293132328308 } }, { "flos": 3.391204178964513e+18, "train_loss": 5.687468872070313, "eval_loss": 5.8502971546069995, "eval_accuracy": 0.014260640631856078, "eval_loss_by_set": { "aqua_rat": 5.893468856811523, "gsm8k": 6.610411210493608, "math_qa": 5.498313903808594 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.02047005307050796, "math_qa": 0.011390284757118929 } }, { "flos": 3.397566636142625e+18, "train_loss": 5.678138427734375, "eval_loss": 5.854593612052299, "eval_accuracy": 0.01601579640193067, "eval_loss_by_set": { "aqua_rat": 5.895423412322998, "gsm8k": 6.625258012251421, "math_qa": 5.49796994527181 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.02047005307050796, "math_qa": 0.01306532663316583 } }, { "flos": 3.4038936061534536e+18, "train_loss": 5.686761474609375, "eval_loss": 5.852449932613888, "eval_accuracy": 0.016235190873189996, "eval_loss_by_set": { "aqua_rat": 5.902823448181152, "gsm8k": 6.624545010653409, "math_qa": 5.494375228881836 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.01592115238817286, "math_qa": 0.01541038525963149 } }, { "flos": 3.410229643377115e+18, "train_loss": 5.687160034179687, "eval_loss": 5.860887553240802, "eval_accuracy": 0.015577007459412023, "eval_loss_by_set": { "aqua_rat": 5.893674373626709, "gsm8k": 6.624203768643466, "math_qa": 5.508302052815755 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.019711902956785442, "math_qa": 0.01373534338358459 } }, { "flos": 3.416610091099488e+18, "train_loss": 5.687626953125, "eval_loss": 5.852293426926072, "eval_accuracy": 0.013821851689337429, "eval_loss_by_set": { "aqua_rat": 5.895110130310059, "gsm8k": 6.632098804820668, "math_qa": 5.49131457010905 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.015163002274450341, "math_qa": 0.012395309882747068 } }, { "flos": 3.4229813679929426e+18, "train_loss": 5.682162475585938, "eval_loss": 5.8530409013902815, "eval_accuracy": 0.011627906976744186, "eval_loss_by_set": { "aqua_rat": 5.894556999206543, "gsm8k": 6.623992226340554, "math_qa": 5.496228535970052 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.01592115238817286, "math_qa": 0.008710217755443886 } }, { "flos": 3.4293100892766863e+18, "train_loss": 5.69119384765625, "eval_loss": 5.856575218406883, "eval_accuracy": 0.01338306274681878, "eval_loss_by_set": { "aqua_rat": 5.894306182861328, "gsm8k": 6.62470106645064, "math_qa": 5.501373291015625 }, "eval_accuracy_by_set": { "aqua_rat": 0.011811023622047244, "gsm8k": 0.019711902956785442, "math_qa": 0.010720268006700168 } }, { "flos": 3.4356437562152714e+18, "train_loss": 5.68196533203125, "eval_loss": 5.852293194951238, "eval_accuracy": 0.014699429574374727, "eval_loss_by_set": { "aqua_rat": 5.895330905914307, "gsm8k": 6.604637839577415, "math_qa": 5.503882090250651 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.017437452615617893, "math_qa": 0.01306532663316583 } }, { "flos": 3.442010169595134e+18, "train_loss": 5.68859375, "eval_loss": 5.857841569024163, "eval_accuracy": 0.01733216322948662, "eval_loss_by_set": { "aqua_rat": 5.895280361175537, "gsm8k": 6.624466635964134, "math_qa": 5.5033518473307295 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.018953752843062926, "math_qa": 0.01675041876046901 } }, { "flos": 3.448348350544347e+18, "train_loss": 5.685494995117187, "eval_loss": 5.857689986357817, "eval_accuracy": 0.013163668275559455, "eval_loss_by_set": { "aqua_rat": 5.896878242492676, "gsm8k": 6.611837907270952, "math_qa": 5.50877316792806 }, "eval_accuracy_by_set": { "aqua_rat": 0.011811023622047244, "gsm8k": 0.01819560272934041, "math_qa": 0.011055276381909548 } }, { "flos": 3.4547136719287747e+18, "train_loss": 5.694371948242187, "eval_loss": 5.844244080620843, "eval_accuracy": 0.014699429574374727, "eval_loss_by_set": { "aqua_rat": 5.892380237579346, "gsm8k": 6.610136552290483, "math_qa": 5.489198684692383 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.015163002274450341, "math_qa": 0.01373534338358459 } }, { "flos": 3.461108545372553e+18, "train_loss": 5.6906787109375, "eval_loss": 5.859062968073665, "eval_accuracy": 0.014699429574374727, "eval_loss_by_set": { "aqua_rat": 5.896265983581543, "gsm8k": 6.624052567915483, "math_qa": 5.505342483520508 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.015163002274450341, "math_qa": 0.01373534338358459 } }, { "flos": 3.46743143462758e+18, "train_loss": 5.682694091796875, "eval_loss": 5.853073532516892, "eval_accuracy": 0.019306713470820535, "eval_loss_by_set": { "aqua_rat": 5.893165588378906, "gsm8k": 6.619902177290483, "math_qa": 5.498269399007161 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.02047005307050796, "math_qa": 0.018425460636515914 } }, { "flos": 3.473831954879611e+18, "train_loss": 5.677534790039062, "eval_loss": 5.855383744110933, "eval_accuracy": 0.014699429574374727, "eval_loss_by_set": { "aqua_rat": 5.894351005554199, "gsm8k": 6.6233041936701, "math_qa": 5.500172932942708 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.017437452615617893, "math_qa": 0.012730318257956449 } }, { "flos": 3.4801341944687493e+18, "train_loss": 5.687314453125, "eval_loss": 5.852609995249155, "eval_accuracy": 0.015138218516893374, "eval_loss_by_set": { "aqua_rat": 5.901344299316406, "gsm8k": 6.618082219904119, "math_qa": 5.497707366943359 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.017437452615617893, "math_qa": 0.01373534338358459 } }, { "flos": 3.486517382917128e+18, "train_loss": 5.688829345703125, "eval_loss": 5.852436658498403, "eval_accuracy": 0.01908731899956121, "eval_loss_by_set": { "aqua_rat": 5.895108699798584, "gsm8k": 6.616266424005682, "math_qa": 5.498792012532552 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.01819560272934041, "math_qa": 0.018760469011725293 } }, { "flos": 3.4928006017067254e+18, "train_loss": 5.681544189453125, "eval_loss": 5.848513061935837, "eval_accuracy": 0.016673979815708645, "eval_loss_by_set": { "aqua_rat": 5.8947343826293945, "gsm8k": 6.606276078657671, "math_qa": 5.497353235880534 }, "eval_accuracy_by_set": { "aqua_rat": 0.011811023622047244, "gsm8k": 0.019711902956785442, "math_qa": 0.01574539363484087 } }, { "flos": 3.4991992053296005e+18, "train_loss": 5.69056396484375, "eval_loss": 5.849725413966823, "eval_accuracy": 0.017990346643264588, "eval_loss_by_set": { "aqua_rat": 5.893252372741699, "gsm8k": 6.613866632634943, "math_qa": 5.495866775512695 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.01592115238817286, "math_qa": 0.018760469011725293 } }, { "flos": 3.505605907650183e+18, "train_loss": 5.68761962890625, "eval_loss": 5.8565123016769824, "eval_accuracy": 0.015138218516893374, "eval_loss_by_set": { "aqua_rat": 5.895076274871826, "gsm8k": 6.621572321111506, "math_qa": 5.502646128336589 }, "eval_accuracy_by_set": { "aqua_rat": 0.011811023622047244, "gsm8k": 0.018953752843062926, "math_qa": 0.01373534338358459 } }, { "flos": 3.5118879104271647e+18, "train_loss": 5.684188232421875, "eval_loss": 5.854779217694257, "eval_accuracy": 0.01689337428696797, "eval_loss_by_set": { "aqua_rat": 5.89752197265625, "gsm8k": 6.618544145063921, "math_qa": 5.501158396402995 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.014404852160727824, "math_qa": 0.01742043551088777 } }, { "flos": 3.518237425258201e+18, "train_loss": 5.685076904296875, "eval_loss": 5.856653857875514, "eval_accuracy": 0.015357612988152698, "eval_loss_by_set": { "aqua_rat": 5.890767574310303, "gsm8k": 6.613591974431818, "math_qa": 5.50688107808431 }, "eval_accuracy_by_set": { "aqua_rat": 0.011811023622047244, "gsm8k": 0.019711902956785442, "math_qa": 0.01373534338358459 } }, { "flos": 3.5246272907701125e+18, "train_loss": 5.691031494140625, "eval_loss": 5.8553828162115975, "eval_accuracy": 0.01601579640193067, "eval_loss_by_set": { "aqua_rat": 5.897549629211426, "gsm8k": 6.61846923828125, "math_qa": 5.5021209716796875 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.016679302501895376, "math_qa": 0.01507537688442211 } }, { "flos": 3.5308895302550815e+18, "train_loss": 5.675589599609375, "eval_loss": 5.854138451653558, "eval_accuracy": 0.01733216322948662, "eval_loss_by_set": { "aqua_rat": 5.895238876342773, "gsm8k": 6.614709333939985, "math_qa": 5.502118428548177 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.016679302501895376, "math_qa": 0.017085427135678392 } }, { "flos": 3.5373740278551675e+18, "train_loss": 5.687510375976562, "eval_loss": 5.8558668961396085, "eval_accuracy": 0.013602457218078104, "eval_loss_by_set": { "aqua_rat": 5.897494792938232, "gsm8k": 6.621418346058238, "math_qa": 5.501520156860352 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.012130401819560273, "math_qa": 0.01340033500837521 } }, { "flos": 3.543640430237188e+18, "train_loss": 5.6830224609375, "eval_loss": 5.852763459489152, "eval_accuracy": 0.015357612988152698, "eval_loss_by_set": { "aqua_rat": 5.894803047180176, "gsm8k": 6.610718467018821, "math_qa": 5.501864115397136 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.016679302501895376, "math_qa": 0.01440536013400335 } }, { "flos": 3.5499481110130196e+18, "train_loss": 5.68863525390625, "eval_loss": 5.853209495544434, "eval_accuracy": 0.012944273804300131, "eval_loss_by_set": { "aqua_rat": 5.897061824798584, "gsm8k": 6.6252829811789775, "math_qa": 5.495688120524089 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.014404852160727824, "math_qa": 0.011390284757118929 } }, { "flos": 3.556353350360367e+18, "train_loss": 5.6814599609375, "eval_loss": 5.856741338162808, "eval_accuracy": 0.012505484861781484, "eval_loss_by_set": { "aqua_rat": 5.8954339027404785, "gsm8k": 6.623612143776634, "math_qa": 5.502034505208333 }, "eval_accuracy_by_set": { "aqua_rat": 0.011811023622047244, "gsm8k": 0.02047005307050796, "math_qa": 0.009045226130653266 } }, { "flos": 3.562669748309197e+18, "train_loss": 5.687731323242187, "eval_loss": 5.850563513266073, "eval_accuracy": 0.015577007459412023, "eval_loss_by_set": { "aqua_rat": 5.890995979309082, "gsm8k": 6.609431873668324, "math_qa": 5.499379475911458 }, "eval_accuracy_by_set": { "aqua_rat": 0.011811023622047244, "gsm8k": 0.02047005307050796, "math_qa": 0.01373534338358459 } }, { "flos": 3.56906460081501e+18, "train_loss": 5.682640380859375, "eval_loss": 5.855755522444442, "eval_accuracy": 0.019745502413339184, "eval_loss_by_set": { "aqua_rat": 5.901690483093262, "gsm8k": 6.630450162020597, "math_qa": 5.496859232584636 }, "eval_accuracy_by_set": { "aqua_rat": 0.011811023622047244, "gsm8k": 0.022744503411675512, "math_qa": 0.019095477386934675 } }, { "flos": 3.575372466811306e+18, "train_loss": 5.683126220703125, "eval_loss": 5.846853307775549, "eval_accuracy": 0.01338306274681878, "eval_loss_by_set": { "aqua_rat": 5.8890533447265625, "gsm8k": 6.6084677956321025, "math_qa": 5.494263331095378 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.01592115238817286, "math_qa": 0.011055276381909548 } }, { "flos": 3.581766495220269e+18, "train_loss": 5.696571044921875, "eval_loss": 5.847498223588273, "eval_accuracy": 0.01645458534444932, "eval_loss_by_set": { "aqua_rat": 5.898443698883057, "gsm8k": 6.611525102095171, "math_qa": 5.49307378133138 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.016679302501895376, "math_qa": 0.01507537688442211 } }, { "flos": 3.588125675338334e+18, "train_loss": 5.6897021484375, "eval_loss": 5.851729831180057, "eval_accuracy": 0.015138218516893374, "eval_loss_by_set": { "aqua_rat": 5.900197982788086, "gsm8k": 6.620296131480824, "math_qa": 5.495431264241536 }, "eval_accuracy_by_set": { "aqua_rat": 0.011811023622047244, "gsm8k": 0.01592115238817286, "math_qa": 0.01507537688442211 } }, { "flos": 3.5944804450618573e+18, "train_loss": 5.682783203125, "eval_loss": 5.8591512216104045, "eval_accuracy": 0.015577007459412023, "eval_loss_by_set": { "aqua_rat": 5.894915580749512, "gsm8k": 6.625925237482244, "math_qa": 5.504732767740886 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.016679302501895376, "math_qa": 0.01507537688442211 } }, { "flos": 3.6008554317333135e+18, "train_loss": 5.691292724609375, "eval_loss": 5.850961685180664, "eval_accuracy": 0.01601579640193067, "eval_loss_by_set": { "aqua_rat": 5.904183387756348, "gsm8k": 6.611020174893466, "math_qa": 5.498166402180989 }, "eval_accuracy_by_set": { "aqua_rat": 0.011811023622047244, "gsm8k": 0.019711902956785442, "math_qa": 0.01474036850921273 } }, { "flos": 3.6071563935696814e+18, "train_loss": 5.680805053710937, "eval_loss": 5.848887005367795, "eval_accuracy": 0.015577007459412023, "eval_loss_by_set": { "aqua_rat": 5.899352073669434, "gsm8k": 6.616476579145952, "math_qa": 5.492869695027669 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.017437452615617893, "math_qa": 0.01306532663316583 } }, { "flos": 3.613558808976032e+18, "train_loss": 5.699246826171875, "eval_loss": 5.855933292492016, "eval_accuracy": 0.01491882404563405, "eval_loss_by_set": { "aqua_rat": 5.897861003875732, "gsm8k": 6.614152388139204, "math_qa": 5.504922231038411 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.015163002274450341, "math_qa": 0.01440536013400335 } }, { "flos": 3.6199382881832796e+18, "train_loss": 5.690609130859375, "eval_loss": 5.854117934768264, "eval_accuracy": 0.010969723562966213, "eval_loss_by_set": { "aqua_rat": 5.896999359130859, "gsm8k": 6.617976795543324, "math_qa": 5.5004425048828125 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.013646702047005308, "math_qa": 0.008710217755443886 } }, { "flos": 3.6263197870988984e+18, "train_loss": 5.69214111328125, "eval_loss": 5.8502748076980176, "eval_accuracy": 0.016235190873189996, "eval_loss_by_set": { "aqua_rat": 5.894932270050049, "gsm8k": 6.609777277166193, "math_qa": 5.4984480539957685 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.016679302501895376, "math_qa": 0.01574539363484087 } }, { "flos": 3.6327011002571817e+18, "train_loss": 5.683782958984375, "eval_loss": 5.850539387883367, "eval_accuracy": 0.014041246160596753, "eval_loss_by_set": { "aqua_rat": 5.899430274963379, "gsm8k": 6.614210648970171, "math_qa": 5.496449152628581 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.016679302501895376, "math_qa": 0.012730318257956449 } }, { "flos": 3.63900066139734e+18, "train_loss": 5.671670532226562, "eval_loss": 5.849723145768449, "eval_accuracy": 0.017990346643264588, "eval_loss_by_set": { "aqua_rat": 5.902071952819824, "gsm8k": 6.613729997114702, "math_qa": 5.495190938313802 }, "eval_accuracy_by_set": { "aqua_rat": 0.011811023622047244, "gsm8k": 0.015163002274450341, "math_qa": 0.019765494137353432 } }, { "flos": 3.645315204457169e+18, "train_loss": 5.685980224609375, "eval_loss": 5.854953636994233, "eval_accuracy": 0.013602457218078104, "eval_loss_by_set": { "aqua_rat": 5.895888805389404, "gsm8k": 6.619572032581676, "math_qa": 5.501092274983724 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.01819560272934041, "math_qa": 0.010385259631490788 } }, { "flos": 3.6517024940624445e+18, "train_loss": 5.688372802734375, "eval_loss": 5.853981121166332, "eval_accuracy": 0.014480035103115402, "eval_loss_by_set": { "aqua_rat": 5.899042129516602, "gsm8k": 6.62688584761186, "math_qa": 5.495978037516276 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.019711902956785442, "math_qa": 0.011725293132328308 } }, { "flos": 3.6580478255953347e+18, "train_loss": 5.695313720703125, "eval_loss": 5.85147728791108, "eval_accuracy": 0.015577007459412023, "eval_loss_by_set": { "aqua_rat": 5.8965559005737305, "gsm8k": 6.620706731622869, "math_qa": 5.495157241821289 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.018953752843062926, "math_qa": 0.01407035175879397 } }, { "flos": 3.664375207386153e+18, "train_loss": 5.685520629882813, "eval_loss": 5.860889847214158, "eval_accuracy": 0.014260640631856078, "eval_loss_by_set": { "aqua_rat": 5.896783828735352, "gsm8k": 6.620028409090909, "math_qa": 5.509960174560547 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.016679302501895376, "math_qa": 0.012395309882747068 } }, { "flos": 3.670710667473584e+18, "train_loss": 5.6858282470703125, "eval_loss": 5.848658149306838, "eval_accuracy": 0.015357612988152698, "eval_loss_by_set": { "aqua_rat": 5.9006266593933105, "gsm8k": 6.614422191273082, "math_qa": 5.4933522542317705 }, "eval_accuracy_by_set": { "aqua_rat": 0.011811023622047244, "gsm8k": 0.017437452615617893, "math_qa": 0.01474036850921273 } }, { "flos": 3.6769993886531584e+18, "train_loss": 5.67818359375, "eval_loss": 5.853183411263131, "eval_accuracy": 0.013602457218078104, "eval_loss_by_set": { "aqua_rat": 5.896464824676514, "gsm8k": 6.625098488547585, "math_qa": 5.495782216389974 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.02047005307050796, "math_qa": 0.010050251256281407 } }, { "flos": 3.6833661526097265e+18, "train_loss": 5.683704223632812, "eval_loss": 5.854337460285908, "eval_accuracy": 0.012944273804300131, "eval_loss_by_set": { "aqua_rat": 5.899954319000244, "gsm8k": 6.625889171253551, "math_qa": 5.496908187866211 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.019711902956785442, "math_qa": 0.009380234505862646 } }, { "flos": 3.6896870634954424e+18, "train_loss": 5.68593994140625, "eval_loss": 5.851308796856855, "eval_accuracy": 0.013163668275559455, "eval_loss_by_set": { "aqua_rat": 5.893946170806885, "gsm8k": 6.62295185435902, "math_qa": 5.494085947672526 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.019711902956785442, "math_qa": 0.008710217755443886 } }, { "flos": 3.696142854070993e+18, "train_loss": 5.69425048828125, "eval_loss": 5.861718358220281, "eval_accuracy": 0.015577007459412023, "eval_loss_by_set": { "aqua_rat": 5.898149490356445, "gsm8k": 6.630931507457387, "math_qa": 5.506126403808594 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.017437452615617893, "math_qa": 0.01407035175879397 } }, { "flos": 3.702473203147342e+18, "train_loss": 5.674892578125, "eval_loss": 5.850996636055611, "eval_accuracy": 0.014480035103115402, "eval_loss_by_set": { "aqua_rat": 5.892989158630371, "gsm8k": 6.611652721058238, "math_qa": 5.498863220214844 }, "eval_accuracy_by_set": { "aqua_rat": 0.011811023622047244, "gsm8k": 0.01819560272934041, "math_qa": 0.01306532663316583 } }, { "flos": 3.7088599365543526e+18, "train_loss": 5.695228881835938, "eval_loss": 5.854511828035922, "eval_accuracy": 0.017551557700745943, "eval_loss_by_set": { "aqua_rat": 5.895688056945801, "gsm8k": 6.6217041015625, "math_qa": 5.49945068359375 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.022744503411675512, "math_qa": 0.01373534338358459 } }, { "flos": 3.7151922435989176e+18, "train_loss": 5.68756103515625, "eval_loss": 5.855545482119998, "eval_accuracy": 0.012724879333040808, "eval_loss_by_set": { "aqua_rat": 5.903294086456299, "gsm8k": 6.632795160466975, "math_qa": 5.495326995849609 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.01592115238817286, "math_qa": 0.010385259631490788 } }, { "flos": 3.7216011712494305e+18, "train_loss": 5.691856079101562, "eval_loss": 5.848411044558963, "eval_accuracy": 0.014041246160596753, "eval_loss_by_set": { "aqua_rat": 5.893007278442383, "gsm8k": 6.619685779918324, "math_qa": 5.491193771362305 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.018953752843062926, "math_qa": 0.011725293132328308 } }, { "flos": 3.727928367819784e+18, "train_loss": 5.688435668945313, "eval_loss": 5.851510640737173, "eval_accuracy": 0.01338306274681878, "eval_loss_by_set": { "aqua_rat": 5.897439956665039, "gsm8k": 6.621769298206676, "math_qa": 5.494647979736328 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.01819560272934041, "math_qa": 0.010385259631490788 } }, { "flos": 3.7343001391713485e+18, "train_loss": 5.6885205078125, "eval_loss": 5.85294331731023, "eval_accuracy": 0.019306713470820535, "eval_loss_by_set": { "aqua_rat": 5.899454116821289, "gsm8k": 6.61840126731179, "math_qa": 5.498232523600261 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.02122820318423048, "math_qa": 0.018090452261306532 } }, { "flos": 3.7406143316544717e+18, "train_loss": 5.673017578125, "eval_loss": 5.852394748378444, "eval_accuracy": 0.01228609039052216, "eval_loss_by_set": { "aqua_rat": 5.896599292755127, "gsm8k": 6.622354680841619, "math_qa": 5.495812733968099 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.02047005307050796, "math_qa": 0.007705192629815745 } }, { "flos": 3.7469928214086287e+18, "train_loss": 5.678466186523438, "eval_loss": 5.852937182864627, "eval_accuracy": 0.012944273804300131, "eval_loss_by_set": { "aqua_rat": 5.899989128112793, "gsm8k": 6.6247780539772725, "math_qa": 5.495255788167317 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.017437452615617893, "math_qa": 0.010050251256281407 } }, { "flos": 3.7533332690268324e+18, "train_loss": 5.688018798828125, "eval_loss": 5.860518584380278, "eval_accuracy": 0.011627906976744186, "eval_loss_by_set": { "aqua_rat": 5.900348663330078, "gsm8k": 6.62740742076527, "math_qa": 5.505708694458008 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.01592115238817286, "math_qa": 0.009380234505862646 } }, { "flos": 3.759708668015149e+18, "train_loss": 5.69242919921875, "eval_loss": 5.85020433889853, "eval_accuracy": 0.014699429574374727, "eval_loss_by_set": { "aqua_rat": 5.9007086753845215, "gsm8k": 6.622569691051137, "math_qa": 5.491994857788086 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.01592115238817286, "math_qa": 0.01373534338358459 } }, { "flos": 3.7660381725935534e+18, "train_loss": 5.682992553710937, "eval_loss": 5.848145407599372, "eval_accuracy": 0.017990346643264588, "eval_loss_by_set": { "aqua_rat": 5.901364326477051, "gsm8k": 6.605201721191406, "math_qa": 5.496726353963216 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.018953752843062926, "math_qa": 0.017085427135678392 } }, { "flos": 3.7723697586204836e+18, "train_loss": 5.676351928710938, "eval_loss": 5.854673127870302, "eval_accuracy": 0.012724879333040808, "eval_loss_by_set": { "aqua_rat": 5.899904251098633, "gsm8k": 6.622634194113991, "math_qa": 5.498921712239583 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.02047005307050796, "math_qa": 0.008375209380234505 } }, { "flos": 3.7787431991037133e+18, "train_loss": 5.6906689453125, "eval_loss": 5.856172974045212, "eval_accuracy": 0.012066695919262835, "eval_loss_by_set": { "aqua_rat": 5.897702217102051, "gsm8k": 6.6257781982421875, "math_qa": 5.499976476033528 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.016679302501895376, "math_qa": 0.009380234505862646 } }, { "flos": 3.7850674691907256e+18, "train_loss": 5.68130126953125, "eval_loss": 5.856073972341177, "eval_accuracy": 0.017551557700745943, "eval_loss_by_set": { "aqua_rat": 5.901943683624268, "gsm8k": 6.6126792214133525, "math_qa": 5.505474090576172 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.019711902956785442, "math_qa": 0.016080402010050253 } }, { "flos": 3.791439447237591e+18, "train_loss": 5.6884814453125, "eval_loss": 5.852169243065086, "eval_accuracy": 0.015357612988152698, "eval_loss_by_set": { "aqua_rat": 5.897832870483398, "gsm8k": 6.62541406804865, "math_qa": 5.493960062662761 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01592115238817286, "math_qa": 0.01574539363484087 } }, { "flos": 3.7977945879389143e+18, "train_loss": 5.68904052734375, "eval_loss": 5.850714296907992, "eval_accuracy": 0.01338306274681878, "eval_loss_by_set": { "aqua_rat": 5.899633407592773, "gsm8k": 6.621163801713423, "math_qa": 5.4935150146484375 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.017437452615617893, "math_qa": 0.010720268006700168 } }, { "flos": 3.804118280889696e+18, "train_loss": 5.682437744140625, "eval_loss": 5.8506487253549935, "eval_accuracy": 0.014260640631856078, "eval_loss_by_set": { "aqua_rat": 5.901994705200195, "gsm8k": 6.615841952237216, "math_qa": 5.495656331380208 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.01819560272934041, "math_qa": 0.011725293132328308 } }, { "flos": 3.810436142348632e+18, "train_loss": 5.677395629882812, "eval_loss": 5.854106129826726, "eval_accuracy": 0.015357612988152698, "eval_loss_by_set": { "aqua_rat": 5.897124290466309, "gsm8k": 6.6161887428977275, "math_qa": 5.501233418782552 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.01819560272934041, "math_qa": 0.01407035175879397 } }, { "flos": 3.8167766103679304e+18, "train_loss": 5.689749755859375, "eval_loss": 5.849142925159351, "eval_accuracy": 0.012944273804300131, "eval_loss_by_set": { "aqua_rat": 5.90138578414917, "gsm8k": 6.62041612104936, "math_qa": 5.491289138793945 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.01288855193328279, "math_qa": 0.012395309882747068 } }, { "flos": 3.823141210197852e+18, "train_loss": 5.6920166015625, "eval_loss": 5.856959446056469, "eval_accuracy": 0.01601579640193067, "eval_loss_by_set": { "aqua_rat": 5.9016547203063965, "gsm8k": 6.623759876598012, "math_qa": 5.501784642537435 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.01592115238817286, "math_qa": 0.01574539363484087 } }, { "flos": 3.8295016884697825e+18, "train_loss": 5.6796240234375, "eval_loss": 5.859106527792441, "eval_accuracy": 0.013163668275559455, "eval_loss_by_set": { "aqua_rat": 5.8972320556640625, "gsm8k": 6.62444374778054, "math_qa": 5.505149841308594 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.018953752843062926, "math_qa": 0.010050251256281407 } }, { "flos": 3.83588228007356e+18, "train_loss": 5.699959716796875, "eval_loss": 5.849794748667124, "eval_accuracy": 0.016673979815708645, "eval_loss_by_set": { "aqua_rat": 5.8997802734375, "gsm8k": 6.62183241410689, "math_qa": 5.4917786916097 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.02047005307050796, "math_qa": 0.01440536013400335 } }, { "flos": 3.842187920203055e+18, "train_loss": 5.689619140625, "eval_loss": 5.854693438555743, "eval_accuracy": 0.01491882404563405, "eval_loss_by_set": { "aqua_rat": 5.8978729248046875, "gsm8k": 6.622272838245738, "math_qa": 5.499287923177083 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.01592115238817286, "math_qa": 0.01373534338358459 } }, { "flos": 3.8485873892618404e+18, "train_loss": 5.6840972900390625, "eval_loss": 5.858570511276658, "eval_accuracy": 0.01601579640193067, "eval_loss_by_set": { "aqua_rat": 5.896203994750977, "gsm8k": 6.623951305042613, "math_qa": 5.504634857177734 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.018953752843062926, "math_qa": 0.01440536013400335 } }, { "flos": 3.854981726908449e+18, "train_loss": 5.680401611328125, "eval_loss": 5.851723335884713, "eval_accuracy": 0.01491882404563405, "eval_loss_by_set": { "aqua_rat": 5.893768310546875, "gsm8k": 6.620992487127131, "math_qa": 5.495637893676758 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.019711902956785442, "math_qa": 0.012730318257956449 } }, { "flos": 3.8613109839893627e+18, "train_loss": 5.68809814453125, "eval_loss": 5.850690944774731, "eval_accuracy": 0.01338306274681878, "eval_loss_by_set": { "aqua_rat": 5.895207405090332, "gsm8k": 6.619029651988637, "math_qa": 5.494825998942058 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.017437452615617893, "math_qa": 0.010385259631490788 } }, { "flos": 3.8677139566677197e+18, "train_loss": 5.686661376953125, "eval_loss": 5.852470913448849, "eval_accuracy": 0.012066695919262835, "eval_loss_by_set": { "aqua_rat": 5.899534225463867, "gsm8k": 6.617452448064631, "math_qa": 5.497932434082031 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.016679302501895376, "math_qa": 0.009380234505862646 } }, { "flos": 3.8739806682873856e+18, "train_loss": 5.6734716796875, "eval_loss": 5.850166166150892, "eval_accuracy": 0.01228609039052216, "eval_loss_by_set": { "aqua_rat": 5.904393196105957, "gsm8k": 6.615787159312855, "math_qa": 5.49473762512207 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.014404852160727824, "math_qa": 0.011055276381909548 } }, { "flos": 3.880358766662648e+18, "train_loss": 5.697325439453125, "eval_loss": 5.856035748043576, "eval_accuracy": 0.011189118034225537, "eval_loss_by_set": { "aqua_rat": 5.896365165710449, "gsm8k": 6.622265208851207, "math_qa": 5.501486460367839 }, "eval_accuracy_by_set": { "aqua_rat": 0.011811023622047244, "gsm8k": 0.015163002274450341, "math_qa": 0.009380234505862646 } }, { "flos": 3.8867085289911747e+18, "train_loss": 5.681903076171875, "eval_loss": 5.8527519380724105, "eval_accuracy": 0.012944273804300131, "eval_loss_by_set": { "aqua_rat": 5.89514684677124, "gsm8k": 6.617301940917969, "math_qa": 5.498800277709961 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.01819560272934041, "math_qa": 0.010385259631490788 } }, { "flos": 3.8930777453740687e+18, "train_loss": 5.68675048828125, "eval_loss": 5.851517393782332, "eval_accuracy": 0.013163668275559455, "eval_loss_by_set": { "aqua_rat": 5.906548500061035, "gsm8k": 6.613924199884588, "math_qa": 5.497495015462239 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.012130401819560273, "math_qa": 0.012730318257956449 } }, { "flos": 3.899462829513638e+18, "train_loss": 5.683863525390625, "eval_loss": 5.855063154890731, "eval_accuracy": 0.015577007459412023, "eval_loss_by_set": { "aqua_rat": 5.8996429443359375, "gsm8k": 6.6198598688299, "math_qa": 5.500816345214844 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.018953752843062926, "math_qa": 0.012730318257956449 } }, { "flos": 3.905774404751065e+18, "train_loss": 5.67935791015625, "eval_loss": 5.854846284196183, "eval_accuracy": 0.015357612988152698, "eval_loss_by_set": { "aqua_rat": 5.899670600891113, "gsm8k": 6.6226279518821025, "math_qa": 5.4992109934488935 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.01592115238817286, "math_qa": 0.01373534338358459 } }, { "flos": 3.9121743065278054e+18, "train_loss": 5.69531982421875, "eval_loss": 5.854787517238307, "eval_accuracy": 0.014041246160596753, "eval_loss_by_set": { "aqua_rat": 5.902695655822754, "gsm8k": 6.6228790283203125, "math_qa": 5.4987532297770185 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.01592115238817286, "math_qa": 0.012060301507537688 } }, { "flos": 3.9185350736362865e+18, "train_loss": 5.68491455078125, "eval_loss": 5.856757447526261, "eval_accuracy": 0.016235190873189996, "eval_loss_by_set": { "aqua_rat": 5.903983116149902, "gsm8k": 6.619922984730113, "math_qa": 5.503037770589192 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.024260803639120546, "math_qa": 0.011390284757118929 } }, { "flos": 3.9249532547938386e+18, "train_loss": 5.6882666015625, "eval_loss": 5.857279236252244, "eval_accuracy": 0.01184730144800351, "eval_loss_by_set": { "aqua_rat": 5.899323463439941, "gsm8k": 6.626745050603693, "math_qa": 5.5011037190755205 }, "eval_accuracy_by_set": { "aqua_rat": 0.011811023622047244, "gsm8k": 0.01819560272934041, "math_qa": 0.009045226130653266 } }, { "flos": 3.9311723615328666e+18, "train_loss": 5.674517822265625, "eval_loss": 5.850359478512326, "eval_accuracy": 0.01338306274681878, "eval_loss_by_set": { "aqua_rat": 5.9029951095581055, "gsm8k": 6.61831318248402, "math_qa": 5.493994394938151 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.018953752843062926, "math_qa": 0.010050251256281407 } }, { "flos": 3.937570305341391e+18, "train_loss": 5.690054931640625, "eval_loss": 5.853636561213313, "eval_accuracy": 0.017551557700745943, "eval_loss_by_set": { "aqua_rat": 5.898065567016602, "gsm8k": 6.622625177556818, "math_qa": 5.497481028238933 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.019711902956785442, "math_qa": 0.016080402010050253 } }, { "flos": 3.9438843743442043e+18, "train_loss": 5.684569091796875, "eval_loss": 5.85324137919658, "eval_accuracy": 0.01601579640193067, "eval_loss_by_set": { "aqua_rat": 5.898334503173828, "gsm8k": 6.62218614058061, "math_qa": 5.497050603230794 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.017437452615617893, "math_qa": 0.01541038525963149 } }, { "flos": 3.950251488340607e+18, "train_loss": 5.681551513671875, "eval_loss": 5.856590116346204, "eval_accuracy": 0.01601579640193067, "eval_loss_by_set": { "aqua_rat": 5.897828102111816, "gsm8k": 6.623464410955256, "math_qa": 5.501669565836589 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.018953752843062926, "math_qa": 0.01407035175879397 } }, { "flos": 3.956572996763648e+18, "train_loss": 5.690211181640625, "eval_loss": 5.858702479182063, "eval_accuracy": 0.01733216322948662, "eval_loss_by_set": { "aqua_rat": 5.903345108032227, "gsm8k": 6.625690806995738, "math_qa": 5.503445943196614 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.019711902956785442, "math_qa": 0.01507537688442211 } }, { "flos": 3.9628900539899576e+18, "train_loss": 5.681521606445313, "eval_loss": 5.853873020893818, "eval_accuracy": 0.015138218516893374, "eval_loss_by_set": { "aqua_rat": 5.901135444641113, "gsm8k": 6.613460193980824, "math_qa": 5.501790364583333 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.013646702047005308, "math_qa": 0.01507537688442211 } }, { "flos": 3.969229759652561e+18, "train_loss": 5.691213989257813, "eval_loss": 5.850706512863572, "eval_accuracy": 0.017990346643264588, "eval_loss_by_set": { "aqua_rat": 5.900588035583496, "gsm8k": 6.618874983354048, "math_qa": 5.494472503662109 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.02122820318423048, "math_qa": 0.01574539363484087 } }, { "flos": 3.97561278328157e+18, "train_loss": 5.689796142578125, "eval_loss": 5.850388578466467, "eval_accuracy": 0.017551557700745943, "eval_loss_by_set": { "aqua_rat": 5.901782512664795, "gsm8k": 6.614834872159091, "math_qa": 5.495734532674153 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.01819560272934041, "math_qa": 0.017085427135678392 } }, { "flos": 3.9818941681201316e+18, "train_loss": 5.680028076171875, "eval_loss": 5.849486814962851, "eval_accuracy": 0.01689337428696797, "eval_loss_by_set": { "aqua_rat": 5.901144504547119, "gsm8k": 6.619516546075994, "math_qa": 5.492251714070638 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.018953752843062926, "math_qa": 0.016080402010050253 } }, { "flos": 3.9882925038444216e+18, "train_loss": 5.688905029296875, "eval_loss": 5.8591509896355705, "eval_accuracy": 0.014699429574374727, "eval_loss_by_set": { "aqua_rat": 5.8983941078186035, "gsm8k": 6.627668207341975, "math_qa": 5.50364367167155 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.01819560272934041, "math_qa": 0.012730318257956449 } }, { "flos": 3.994648716140085e+18, "train_loss": 5.67914794921875, "eval_loss": 5.84978673264787, "eval_accuracy": 0.01491882404563405, "eval_loss_by_set": { "aqua_rat": 5.905670642852783, "gsm8k": 6.6258156516335225, "math_qa": 5.489449818929036 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.018953752843062926, "math_qa": 0.012730318257956449 } }, { "flos": 4.000985350901072e+18, "train_loss": 5.689886474609375, "eval_loss": 5.851806099350388, "eval_accuracy": 0.01645458534444932, "eval_loss_by_set": { "aqua_rat": 5.9019598960876465, "gsm8k": 6.615083174272017, "math_qa": 5.497791290283203 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.016679302501895376, "math_qa": 0.016080402010050253 } }, { "flos": 4.00732581892037e+18, "train_loss": 5.680284423828125, "eval_loss": 5.852891458047403, "eval_accuracy": 0.016235190873189996, "eval_loss_by_set": { "aqua_rat": 5.900653839111328, "gsm8k": 6.619037974964488, "math_qa": 5.497760772705078 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.02350265352539803, "math_qa": 0.012730318257956449 } }, { "flos": 4.0136570135684055e+18, "train_loss": 5.672960815429687, "eval_loss": 5.850627100145495, "eval_accuracy": 0.016235190873189996, "eval_loss_by_set": { "aqua_rat": 5.9032883644104, "gsm8k": 6.616351040926847, "math_qa": 5.4952818552653 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.01819560272934041, "math_qa": 0.01507537688442211 } }, { "flos": 4.0200571005656105e+18, "train_loss": 5.685081787109375, "eval_loss": 5.857917785644531, "eval_accuracy": 0.015796401930671347, "eval_loss_by_set": { "aqua_rat": 5.899406433105469, "gsm8k": 6.624269658868963, "math_qa": 5.503215789794922 }, "eval_accuracy_by_set": { "aqua_rat": 0.011811023622047244, "gsm8k": 0.02047005307050796, "math_qa": 0.01407035175879397 } }, { "flos": 4.026357526604808e+18, "train_loss": 5.694236450195312, "eval_loss": 5.85569361093882, "eval_accuracy": 0.014260640631856078, "eval_loss_by_set": { "aqua_rat": 5.901815414428711, "gsm8k": 6.624834234064275, "math_qa": 5.499327341715495 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.019711902956785442, "math_qa": 0.011725293132328308 } }, { "flos": 4.032710174077616e+18, "train_loss": 5.6770849609375, "eval_loss": 5.8549414969779345, "eval_accuracy": 0.014260640631856078, "eval_loss_by_set": { "aqua_rat": 5.899444580078125, "gsm8k": 6.619255065917969, "math_qa": 5.500922520955403 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.016679302501895376, "math_qa": 0.012730318257956449 } }, { "flos": 4.039068056041816e+18, "train_loss": 5.68736572265625, "eval_loss": 5.853065568047601, "eval_accuracy": 0.016235190873189996, "eval_loss_by_set": { "aqua_rat": 5.900636196136475, "gsm8k": 6.6257455999201, "math_qa": 5.494956334431966 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.02122820318423048, "math_qa": 0.01407035175879397 } }, { "flos": 4.045403578406273e+18, "train_loss": 5.674356689453125, "eval_loss": 5.85297561336208, "eval_accuracy": 0.016235190873189996, "eval_loss_by_set": { "aqua_rat": 5.902767658233643, "gsm8k": 6.62261962890625, "math_qa": 5.496072769165039 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.016679302501895376, "math_qa": 0.01541038525963149 } }, { "flos": 4.051723623856079e+18, "train_loss": 5.685250244140625, "eval_loss": 5.85655740789465, "eval_accuracy": 0.016235190873189996, "eval_loss_by_set": { "aqua_rat": 5.898184299468994, "gsm8k": 6.627878362482244, "math_qa": 5.499566396077474 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.01592115238817286, "math_qa": 0.016080402010050253 } }, { "flos": 4.0580544265883484e+18, "train_loss": 5.68658935546875, "eval_loss": 5.8536264058705925, "eval_accuracy": 0.017112768758227294, "eval_loss_by_set": { "aqua_rat": 5.901467323303223, "gsm8k": 6.621991937810725, "math_qa": 5.4974721272786455 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.021986353297952996, "math_qa": 0.01373534338358459 } }, { "flos": 4.06441844928204e+18, "train_loss": 5.682324829101563, "eval_loss": 5.850664654293576, "eval_accuracy": 0.014699429574374727, "eval_loss_by_set": { "aqua_rat": 5.901671409606934, "gsm8k": 6.620513916015625, "math_qa": 5.493566513061523 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.017437452615617893, "math_qa": 0.01340033500837521 } }, { "flos": 4.070750632846295e+18, "train_loss": 5.669017944335938, "eval_loss": 5.852427843454722, "eval_accuracy": 0.015577007459412023, "eval_loss_by_set": { "aqua_rat": 5.900698184967041, "gsm8k": 6.626241510564631, "math_qa": 5.493740717569987 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.017437452615617893, "math_qa": 0.01407035175879397 } }, { "flos": 4.0770669481170043e+18, "train_loss": 5.68080810546875, "eval_loss": 5.852693222664498, "eval_accuracy": 0.014699429574374727, "eval_loss_by_set": { "aqua_rat": 5.89953088760376, "gsm8k": 6.621926741166548, "math_qa": 5.496224721272786 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.016679302501895376, "math_qa": 0.012395309882747068 } }, { "flos": 4.083507344992895e+18, "train_loss": 5.70033447265625, "eval_loss": 5.856191222732131, "eval_accuracy": 0.014260640631856078, "eval_loss_by_set": { "aqua_rat": 5.89865779876709, "gsm8k": 6.62372519753196, "math_qa": 5.500865936279297 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.01819560272934041, "math_qa": 0.011390284757118929 } }, { "flos": 4.0898878335174574e+18, "train_loss": 5.68560546875, "eval_loss": 5.849564371882258, "eval_accuracy": 0.01601579640193067, "eval_loss_by_set": { "aqua_rat": 5.903506278991699, "gsm8k": 6.618818109685725, "math_qa": 5.492494583129883 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.017437452615617893, "math_qa": 0.01440536013400335 } }, { "flos": 4.096220985059967e+18, "train_loss": 5.682381591796875, "eval_loss": 5.852435343974346, "eval_accuracy": 0.015357612988152698, "eval_loss_by_set": { "aqua_rat": 5.902835845947266, "gsm8k": 6.6186301491477275, "math_qa": 5.497062683105469 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.014404852160727824, "math_qa": 0.01507537688442211 } }, { "flos": 4.1026022160770007e+18, "train_loss": 5.692911987304687, "eval_loss": 5.851130562859613, "eval_accuracy": 0.015138218516893374, "eval_loss_by_set": { "aqua_rat": 5.898694038391113, "gsm8k": 6.618417913263494, "math_qa": 5.495493570963542 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.01592115238817286, "math_qa": 0.01407035175879397 } }, { "flos": 4.1089434877920543e+18, "train_loss": 5.684615478515625, "eval_loss": 5.855340210167137, "eval_accuracy": 0.014699429574374727, "eval_loss_by_set": { "aqua_rat": 5.900618076324463, "gsm8k": 6.627399097789418, "math_qa": 5.4977067311604815 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.016679302501895376, "math_qa": 0.012395309882747068 } }, { "flos": 4.115272271352824e+18, "train_loss": 5.684630126953125, "eval_loss": 5.85158092911179, "eval_accuracy": 0.016235190873189996, "eval_loss_by_set": { "aqua_rat": 5.896752834320068, "gsm8k": 6.61913438276811, "math_qa": 5.496021270751953 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.015163002274450341, "math_qa": 0.01574539363484087 } }, { "flos": 4.1216097715497206e+18, "train_loss": 5.682783203125, "eval_loss": 5.853032034796637, "eval_accuracy": 0.01338306274681878, "eval_loss_by_set": { "aqua_rat": 5.898745536804199, "gsm8k": 6.6185829856178975, "math_qa": 5.498345057169597 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.016679302501895376, "math_qa": 0.011390284757118929 } }, { "flos": 4.127916524612616e+18, "train_loss": 5.684732666015625, "eval_loss": 5.854461773021801, "eval_accuracy": 0.013602457218078104, "eval_loss_by_set": { "aqua_rat": 5.901887893676758, "gsm8k": 6.6210479736328125, "math_qa": 5.499157587687175 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.016679302501895376, "math_qa": 0.011390284757118929 } }, { "flos": 4.1342907070514463e+18, "train_loss": 5.66876953125, "eval_loss": 5.854397490217879, "eval_accuracy": 0.015357612988152698, "eval_loss_by_set": { "aqua_rat": 5.89786434173584, "gsm8k": 6.625687339089134, "math_qa": 5.497267405192058 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.01592115238817286, "math_qa": 0.01373534338358459 } }, { "flos": 4.1405614371498885e+18, "train_loss": 5.676666259765625, "eval_loss": 5.853594316018595, "eval_accuracy": 0.014260640631856078, "eval_loss_by_set": { "aqua_rat": 5.899939060211182, "gsm8k": 6.621221368963068, "math_qa": 5.497903188069661 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.01592115238817286, "math_qa": 0.01306532663316583 } }, { "flos": 4.146934115276423e+18, "train_loss": 5.68471923828125, "eval_loss": 5.853341669649692, "eval_accuracy": 0.016235190873189996, "eval_loss_by_set": { "aqua_rat": 5.902589321136475, "gsm8k": 6.6243674538352275, "math_qa": 5.495850880940755 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.015163002274450341, "math_qa": 0.01641541038525963 } }, { "flos": 4.153286659670016e+18, "train_loss": 5.68383056640625, "eval_loss": 5.855898264292124, "eval_accuracy": 0.015138218516893374, "eval_loss_by_set": { "aqua_rat": 5.899013519287109, "gsm8k": 6.625751842151988, "math_qa": 5.4994557698567705 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.01592115238817286, "math_qa": 0.01440536013400335 } }, { "flos": 4.159639141786583e+18, "train_loss": 5.683724365234375, "eval_loss": 5.857113735095875, "eval_accuracy": 0.014041246160596753, "eval_loss_by_set": { "aqua_rat": 5.900278568267822, "gsm8k": 6.625884316184304, "math_qa": 5.501163482666016 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.01592115238817286, "math_qa": 0.012395309882747068 } }, { "flos": 4.1659996608607027e+18, "train_loss": 5.68109619140625, "eval_loss": 5.854531288146973, "eval_accuracy": 0.017112768758227294, "eval_loss_by_set": { "aqua_rat": 5.900221347808838, "gsm8k": 6.625460537997159, "math_qa": 5.497381210327148 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.01819560272934041, "math_qa": 0.01675041876046901 } }, { "flos": 4.1723792222092e+18, "train_loss": 5.682440185546875, "eval_loss": 5.851636680396828, "eval_accuracy": 0.01491882404563405, "eval_loss_by_set": { "aqua_rat": 5.898257255554199, "gsm8k": 6.623234835537997, "math_qa": 5.494102478027344 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.02047005307050796, "math_qa": 0.012395309882747068 } }, { "flos": 4.178714908856156e+18, "train_loss": 5.6833642578125, "eval_loss": 5.8545267259752425, "eval_accuracy": 0.01645458534444932, "eval_loss_by_set": { "aqua_rat": 5.899503707885742, "gsm8k": 6.626384388316762, "math_qa": 5.497010548909505 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.02047005307050796, "math_qa": 0.01407035175879397 } }, { "flos": 4.1851128532015514e+18, "train_loss": 5.6827459716796875, "eval_loss": 5.851451693354426, "eval_accuracy": 0.01601579640193067, "eval_loss_by_set": { "aqua_rat": 5.89956521987915, "gsm8k": 6.618392250754616, "math_qa": 5.495927810668945 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.01288855193328279, "math_qa": 0.01675041876046901 } }, { "flos": 4.1914789165415793e+18, "train_loss": 5.6863031005859375, "eval_loss": 5.8546376872707055, "eval_accuracy": 0.017770952172005264, "eval_loss_by_set": { "aqua_rat": 5.899649143218994, "gsm8k": 6.622777765447443, "math_qa": 5.498822530110677 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.021986353297952996, "math_qa": 0.01574539363484087 } }, { "flos": 4.1978638772008387e+18, "train_loss": 5.685313720703125, "eval_loss": 5.853985167838432, "eval_accuracy": 0.017112768758227294, "eval_loss_by_set": { "aqua_rat": 5.899715900421143, "gsm8k": 6.623414473100142, "math_qa": 5.497519175211589 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.02047005307050796, "math_qa": 0.01507537688442211 } }, { "flos": 4.20413415364336e+18, "train_loss": 5.681722412109375, "eval_loss": 5.851387436325486, "eval_accuracy": 0.016673979815708645, "eval_loss_by_set": { "aqua_rat": 5.903331756591797, "gsm8k": 6.618534434925426, "math_qa": 5.495449701944987 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.019711902956785442, "math_qa": 0.01507537688442211 } }, { "flos": 4.2105638957791314e+18, "train_loss": 5.685621337890625, "eval_loss": 5.855559168635188, "eval_accuracy": 0.015138218516893374, "eval_loss_by_set": { "aqua_rat": 5.898622512817383, "gsm8k": 6.624022050337358, "math_qa": 5.499758402506511 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.019711902956785442, "math_qa": 0.012395309882747068 } }, { "flos": 4.2169140908256133e+18, "train_loss": 5.676787719726563, "eval_loss": 5.856042861938477, "eval_accuracy": 0.015357612988152698, "eval_loss_by_set": { "aqua_rat": 5.902215003967285, "gsm8k": 6.623644742098722, "math_qa": 5.500377655029297 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.01592115238817286, "math_qa": 0.01474036850921273 } }, { "flos": 4.223259710658183e+18, "train_loss": 5.680311279296875, "eval_loss": 5.855258039526038, "eval_accuracy": 0.01645458534444932, "eval_loss_by_set": { "aqua_rat": 5.896572589874268, "gsm8k": 6.624971563165838, "math_qa": 5.499029795328776 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.018953752843062926, "math_qa": 0.01507537688442211 } }, { "flos": 4.229610070524035e+18, "train_loss": 5.678779296875, "eval_loss": 5.854460767797522, "eval_accuracy": 0.018867924528301886, "eval_loss_by_set": { "aqua_rat": 5.899488925933838, "gsm8k": 6.620927290482954, "math_qa": 5.499411265055339 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.021986353297952996, "math_qa": 0.017085427135678392 } }, { "flos": 4.2359837375667896e+18, "train_loss": 5.694102172851562, "eval_loss": 5.854335501387313, "eval_accuracy": 0.01491882404563405, "eval_loss_by_set": { "aqua_rat": 5.9014363288879395, "gsm8k": 6.622021761807528, "math_qa": 5.498554229736328 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.017437452615617893, "math_qa": 0.01373534338358459 } }, { "flos": 4.2423449577943204e+18, "train_loss": 5.698726196289062, "eval_loss": 5.8533039866267025, "eval_accuracy": 0.014480035103115402, "eval_loss_by_set": { "aqua_rat": 5.897730350494385, "gsm8k": 6.622141751376065, "math_qa": 5.4972178141276045 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.015163002274450341, "math_qa": 0.01373534338358459 } }, { "flos": 4.24870230396135e+18, "train_loss": 5.67007568359375, "eval_loss": 5.855631544783309, "eval_accuracy": 0.01491882404563405, "eval_loss_by_set": { "aqua_rat": 5.900915145874023, "gsm8k": 6.626163829456676, "math_qa": 5.498697280883789 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.018953752843062926, "math_qa": 0.012395309882747068 } }, { "flos": 4.255107130991837e+18, "train_loss": 5.6909722900390625, "eval_loss": 5.854894225661819, "eval_accuracy": 0.015577007459412023, "eval_loss_by_set": { "aqua_rat": 5.897418022155762, "gsm8k": 6.620278791947798, "math_qa": 5.50054931640625 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.01592115238817286, "math_qa": 0.01474036850921273 } }, { "flos": 4.2614186858281697e+18, "train_loss": 5.685722045898437, "eval_loss": 5.853777034862621, "eval_accuracy": 0.017112768758227294, "eval_loss_by_set": { "aqua_rat": 5.898184776306152, "gsm8k": 6.621637517755682, "math_qa": 5.498140335083008 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.017437452615617893, "math_qa": 0.017085427135678392 } }, { "flos": 4.267751404652724e+18, "train_loss": 5.677457275390625, "eval_loss": 5.8516710384472, "eval_accuracy": 0.017112768758227294, "eval_loss_by_set": { "aqua_rat": 5.900979518890381, "gsm8k": 6.6174233176491475, "math_qa": 5.496592203776042 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.015163002274450341, "math_qa": 0.01675041876046901 } }, { "flos": 4.2741005898450207e+18, "train_loss": 5.686796264648438, "eval_loss": 5.852025315568254, "eval_accuracy": 0.014480035103115402, "eval_loss_by_set": { "aqua_rat": 5.897485733032227, "gsm8k": 6.619236339222301, "math_qa": 5.496598561604817 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.015163002274450341, "math_qa": 0.01340033500837521 } }, { "flos": 4.280337007449735e+18, "train_loss": 5.6840380859375, "eval_loss": 5.854055481988031, "eval_accuracy": 0.015577007459412023, "eval_loss_by_set": { "aqua_rat": 5.899265766143799, "gsm8k": 6.623083634810015, "math_qa": 5.497816721598308 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.015163002274450341, "math_qa": 0.01507537688442211 } }, { "flos": 4.286688026593067e+18, "train_loss": 5.6609039306640625, "eval_loss": 5.853715278006889, "eval_accuracy": 0.014260640631856078, "eval_loss_by_set": { "aqua_rat": 5.900010108947754, "gsm8k": 6.6232077858664775, "math_qa": 5.497173309326172 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.015163002274450341, "math_qa": 0.01373534338358459 } }, { "flos": 4.29305489362885e+18, "train_loss": 5.692225341796875, "eval_loss": 5.854032593804437, "eval_accuracy": 0.013821851689337429, "eval_loss_by_set": { "aqua_rat": 5.898186206817627, "gsm8k": 6.62232069535689, "math_qa": 5.498221079508464 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.016679302501895376, "math_qa": 0.011725293132328308 } }, { "flos": 4.299411312082944e+18, "train_loss": 5.67110107421875, "eval_loss": 5.854174072678025, "eval_accuracy": 0.014480035103115402, "eval_loss_by_set": { "aqua_rat": 5.8988237380981445, "gsm8k": 6.623074618252841, "math_qa": 5.498040517171224 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.014404852160727824, "math_qa": 0.01407035175879397 } }, { "flos": 4.3058380246561587e+18, "train_loss": 5.687081909179687, "eval_loss": 5.854110434248641, "eval_accuracy": 0.014041246160596753, "eval_loss_by_set": { "aqua_rat": 5.896799564361572, "gsm8k": 6.624352195046165, "math_qa": 5.497525533040364 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.015163002274450341, "math_qa": 0.01306532663316583 } }, { "flos": 4.312194484449313e+18, "train_loss": 5.680595703125, "eval_loss": 5.8524881826864705, "eval_accuracy": 0.015138218516893374, "eval_loss_by_set": { "aqua_rat": 5.900284767150879, "gsm8k": 6.621056990189985, "math_qa": 5.496244430541992 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.018953752843062926, "math_qa": 0.01306532663316583 } }, { "flos": 4.3185035251191644e+18, "train_loss": 5.68541015625, "eval_loss": 5.852797920639451, "eval_accuracy": 0.015357612988152698, "eval_loss_by_set": { "aqua_rat": 5.899594783782959, "gsm8k": 6.622587724165483, "math_qa": 5.49607785542806 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.017437452615617893, "math_qa": 0.01407035175879397 } }, { "flos": 4.3249021700811e+18, "train_loss": 5.683215942382812, "eval_loss": 5.853658469947609, "eval_accuracy": 0.01491882404563405, "eval_loss_by_set": { "aqua_rat": 5.897952079772949, "gsm8k": 6.621662486683238, "math_qa": 5.497965494791667 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.014404852160727824, "math_qa": 0.01440536013400335 } }, { "flos": 4.3312392375600415e+18, "train_loss": 5.690803833007813, "eval_loss": 5.85477707837079, "eval_accuracy": 0.014699429574374727, "eval_loss_by_set": { "aqua_rat": 5.898584842681885, "gsm8k": 6.622799266468395, "math_qa": 5.49911626180013 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.017437452615617893, "math_qa": 0.01306532663316583 } }, { "flos": 4.337537747506954e+18, "train_loss": 5.670098876953125, "eval_loss": 5.853280015893884, "eval_accuracy": 0.014480035103115402, "eval_loss_by_set": { "aqua_rat": 5.89804220199585, "gsm8k": 6.622495477849787, "math_qa": 5.496992746988933 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.014404852160727824, "math_qa": 0.01407035175879397 } }, { "flos": 4.3438819865075384e+18, "train_loss": 5.689051513671875, "eval_loss": 5.853098972423656, "eval_accuracy": 0.013821851689337429, "eval_loss_by_set": { "aqua_rat": 5.897523403167725, "gsm8k": 6.620787880637429, "math_qa": 5.497539520263672 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.016679302501895376, "math_qa": 0.012395309882747068 } }, { "flos": 4.350195767210672e+18, "train_loss": 5.678204345703125, "eval_loss": 5.852135013889622, "eval_accuracy": 0.015577007459412023, "eval_loss_by_set": { "aqua_rat": 5.900266647338867, "gsm8k": 6.61957411332564, "math_qa": 5.496381123860677 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.01819560272934041, "math_qa": 0.01373534338358459 } }, { "flos": 4.356563746642985e+18, "train_loss": 5.689013671875, "eval_loss": 5.853217150713946, "eval_accuracy": 0.013821851689337429, "eval_loss_by_set": { "aqua_rat": 5.89958381652832, "gsm8k": 6.621448863636363, "math_qa": 5.497247060139974 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.014404852160727824, "math_qa": 0.01340033500837521 } }, { "flos": 4.362835507533578e+18, "train_loss": 5.675773315429687, "eval_loss": 5.854098371557288, "eval_accuracy": 0.014480035103115402, "eval_loss_by_set": { "aqua_rat": 5.900162220001221, "gsm8k": 6.621011907404119, "math_qa": 5.498757680257161 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.014404852160727824, "math_qa": 0.01407035175879397 } }, { "flos": 4.362835507533578e+18, "train_loss": 5.675773315429687, "eval_loss": 5.854098371557288, "eval_accuracy": 0.014480035103115402, "eval_loss_by_set": { "aqua_rat": 5.900162220001221, "gsm8k": 6.621011907404119, "math_qa": 5.498757680257161 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.014404852160727824, "math_qa": 0.01407035175879397 } } ]