[ { "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": 6000908441747456.0, "train_loss": 6.810490112304688, "eval_loss": 6.0108499011477905, "eval_accuracy": 0.009214567792891619, "eval_loss_by_set": { "aqua_rat": 6.001595973968506, "gsm8k": 6.679884477095171, "math_qa": 5.704980214436849 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.01592115238817286, "math_qa": 0.0036850921273031824 } }, { "flos": 1.193558258221056e+16, "train_loss": 6.04991455078125, "eval_loss": 5.941982836336703, "eval_accuracy": 0.011627906976744186, "eval_loss_by_set": { "aqua_rat": 5.9446306228637695, "gsm8k": 6.6212026422674, "math_qa": 5.630453109741211 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.01819560272934041, "math_qa": 0.007035175879396985 } }, { "flos": 1.791413142421504e+16, "train_loss": 6.008870849609375, "eval_loss": 5.92444203350995, "eval_accuracy": 0.015796401930671347, "eval_loss_by_set": { "aqua_rat": 5.937405586242676, "gsm8k": 6.593974720348012, "math_qa": 5.616492589314778 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.024260803639120546, "math_qa": 0.011055276381909548 } }, { "flos": 2.391909968379904e+16, "train_loss": 5.979757690429688, "eval_loss": 5.915986628145785, "eval_accuracy": 0.017770952172005264, "eval_loss_by_set": { "aqua_rat": 5.922208309173584, "gsm8k": 6.579054398970171, "math_qa": 5.611562093098958 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.025018953752843062, "math_qa": 0.01407035175879397 } }, { "flos": 2.991192982893363e+16, "train_loss": 5.958998413085937, "eval_loss": 5.903835915230416, "eval_accuracy": 0.013821851689337429, "eval_loss_by_set": { "aqua_rat": 5.918848037719727, "gsm8k": 6.585192593661222, "math_qa": 5.5902964274088545 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.015163002274450341, "math_qa": 0.010720268006700168 } }, { "flos": 3.5804996473716736e+16, "train_loss": 5.937138061523438, "eval_loss": 5.896987502639358, "eval_accuracy": 0.01689337428696797, "eval_loss_by_set": { "aqua_rat": 5.9197845458984375, "gsm8k": 6.583512739701704, "math_qa": 5.580430348714192 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.019711902956785442, "math_qa": 0.01507537688442211 } }, { "flos": 4.176409126135398e+16, "train_loss": 5.929097900390625, "eval_loss": 5.900942338479532, "eval_accuracy": 0.01733216322948662, "eval_loss_by_set": { "aqua_rat": 5.905661106109619, "gsm8k": 6.581753817471591, "math_qa": 5.588510513305664 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.018953752843062926, "math_qa": 0.012060301507537688 } }, { "flos": 4.775657136665395e+16, "train_loss": 5.9199169921875, "eval_loss": 5.88799644160915, "eval_accuracy": 0.017551557700745943, "eval_loss_by_set": { "aqua_rat": 5.913262844085693, "gsm8k": 6.562741366299716, "math_qa": 5.576632817586263 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.018953752843062926, "math_qa": 0.01407035175879397 } }, { "flos": 5.370750517955789e+16, "train_loss": 5.9119384765625, "eval_loss": 5.884633708644557, "eval_accuracy": 0.018429135585783237, "eval_loss_by_set": { "aqua_rat": 5.914624214172363, "gsm8k": 6.576950766823509, "math_qa": 5.564822514851888 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.019711902956785442, "math_qa": 0.01373534338358459 } }, { "flos": 5.973355582298522e+16, "train_loss": 5.90295166015625, "eval_loss": 5.8910013662802205, "eval_accuracy": 0.015796401930671347, "eval_loss_by_set": { "aqua_rat": 5.899083137512207, "gsm8k": 6.577962701970881, "math_qa": 5.575470606486003 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.017437452615617893, "math_qa": 0.011055276381909548 } }, { "flos": 6.570946701819904e+16, "train_loss": 5.906636962890625, "eval_loss": 5.881880373568149, "eval_accuracy": 0.015138218516893374, "eval_loss_by_set": { "aqua_rat": 5.894655227661133, "gsm8k": 6.571314725008878, "math_qa": 5.564825057983398 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.018953752843062926, "math_qa": 0.008710217755443886 } }, { "flos": 7.166468720846438e+16, "train_loss": 5.882612915039062, "eval_loss": 5.873746304898648, "eval_accuracy": 0.01601579640193067, "eval_loss_by_set": { "aqua_rat": 5.899791717529297, "gsm8k": 6.551302129572088, "math_qa": 5.561029434204102 }, "eval_accuracy_by_set": { "aqua_rat": 0.08267716535433071, "gsm8k": 0.014404852160727824, "math_qa": 0.011055276381909548 } }, { "flos": 7.760105141855846e+16, "train_loss": 5.876119384765625, "eval_loss": 5.869154285740208, "eval_accuracy": 0.01601579640193067, "eval_loss_by_set": { "aqua_rat": 5.910046577453613, "gsm8k": 6.556474859064275, "math_qa": 5.5507246653238935 }, "eval_accuracy_by_set": { "aqua_rat": 0.0984251968503937, "gsm8k": 0.02122820318423048, "math_qa": 0.006700167504187605 } }, { "flos": 8.360876040414822e+16, "train_loss": 5.866280517578125, "eval_loss": 5.890701603245091, "eval_accuracy": 0.014041246160596753, "eval_loss_by_set": { "aqua_rat": 5.899232864379883, "gsm8k": 6.570103732022372, "math_qa": 5.5785980224609375 }, "eval_accuracy_by_set": { "aqua_rat": 0.09448818897637795, "gsm8k": 0.017437452615617893, "math_qa": 0.005695142378559464 } }, { "flos": 8.960925706590618e+16, "train_loss": 5.86060791015625, "eval_loss": 5.896252039316538, "eval_accuracy": 0.014699429574374727, "eval_loss_by_set": { "aqua_rat": 5.892727851867676, "gsm8k": 6.595248135653409, "math_qa": 5.576172510782878 }, "eval_accuracy_by_set": { "aqua_rat": 0.08661417322834646, "gsm8k": 0.01592115238817286, "math_qa": 0.008040201005025126 } }, { "flos": 9.558601329593549e+16, "train_loss": 5.84941650390625, "eval_loss": 5.893153113287848, "eval_accuracy": 0.015577007459412023, "eval_loss_by_set": { "aqua_rat": 5.885675430297852, "gsm8k": 6.6188201904296875, "math_qa": 5.561178843180339 }, "eval_accuracy_by_set": { "aqua_rat": 0.08661417322834646, "gsm8k": 0.01592115238817286, "math_qa": 0.009380234505862646 } }, { "flos": 1.0156107945633382e+17, "train_loss": 5.845057373046875, "eval_loss": 5.890553190901473, "eval_accuracy": 0.012944273804300131, "eval_loss_by_set": { "aqua_rat": 5.875369071960449, "gsm8k": 6.61340956254439, "math_qa": 5.560509363810222 }, "eval_accuracy_by_set": { "aqua_rat": 0.09448818897637795, "gsm8k": 0.013646702047005308, "math_qa": 0.005695142378559464 } }, { "flos": 1.0751638232471962e+17, "train_loss": 5.843096923828125, "eval_loss": 5.869244188875766, "eval_accuracy": 0.01184730144800351, "eval_loss_by_set": { "aqua_rat": 5.901825904846191, "gsm8k": 6.581561001864347, "math_qa": 5.540050506591797 }, "eval_accuracy_by_set": { "aqua_rat": 0.1062992125984252, "gsm8k": 0.014404852160727824, "math_qa": 0.002680067001675042 } }, { "flos": 1.1343339555966157e+17, "train_loss": 5.82489990234375, "eval_loss": 5.883261113553433, "eval_accuracy": 0.014480035103115402, "eval_loss_by_set": { "aqua_rat": 5.879225254058838, "gsm8k": 6.600949374112216, "math_qa": 5.554656982421875 }, "eval_accuracy_by_set": { "aqua_rat": 0.09448818897637795, "gsm8k": 0.018953752843062926, "math_qa": 0.005695142378559464 } }, { "flos": 1.1941643693745766e+17, "train_loss": 5.827890625, "eval_loss": 5.895323031657451, "eval_accuracy": 0.01228609039052216, "eval_loss_by_set": { "aqua_rat": 5.871222972869873, "gsm8k": 6.622562755237926, "math_qa": 5.564013163248698 }, "eval_accuracy_by_set": { "aqua_rat": 0.1062992125984252, "gsm8k": 0.014404852160727824, "math_qa": 0.0033500837520938024 } }, { "flos": 1.2544994793907814e+17, "train_loss": 5.830020751953125, "eval_loss": 5.883715552252692, "eval_accuracy": 0.01228609039052216, "eval_loss_by_set": { "aqua_rat": 5.884305953979492, "gsm8k": 6.606342662464488, "math_qa": 5.552462259928386 }, "eval_accuracy_by_set": { "aqua_rat": 0.09448818897637795, "gsm8k": 0.01592115238817286, "math_qa": 0.0036850921273031824 } }, { "flos": 1.3139199975961395e+17, "train_loss": 5.823326416015625, "eval_loss": 5.875930167533256, "eval_accuracy": 0.014260640631856078, "eval_loss_by_set": { "aqua_rat": 5.880184173583984, "gsm8k": 6.594972090287642, "math_qa": 5.546014785766602 }, "eval_accuracy_by_set": { "aqua_rat": 0.0984251968503937, "gsm8k": 0.016679302501895376, "math_qa": 0.006030150753768844 } }, { "flos": 1.37379678091477e+17, "train_loss": 5.815711669921875, "eval_loss": 5.8929234066525025, "eval_accuracy": 0.011627906976744186, "eval_loss_by_set": { "aqua_rat": 5.885251998901367, "gsm8k": 6.63628526167436, "math_qa": 5.552855173746745 }, "eval_accuracy_by_set": { "aqua_rat": 0.09055118110236221, "gsm8k": 0.015163002274450341, "math_qa": 0.0033500837520938024 } }, { "flos": 1.433244502369239e+17, "train_loss": 5.810044555664063, "eval_loss": 5.8986493703481315, "eval_accuracy": 0.016235190873189996, "eval_loss_by_set": { "aqua_rat": 5.882749557495117, "gsm8k": 6.617326216264204, "math_qa": 5.570580800374349 }, "eval_accuracy_by_set": { "aqua_rat": 0.09448818897637795, "gsm8k": 0.024260803639120546, "math_qa": 0.006030150753768844 } }, { "flos": 1.492796500260946e+17, "train_loss": 5.81342041015625, "eval_loss": 5.888652028264226, "eval_accuracy": 0.010969723562966213, "eval_loss_by_set": { "aqua_rat": 5.882502555847168, "gsm8k": 6.621499495072798, "math_qa": 5.553276062011719 }, "eval_accuracy_by_set": { "aqua_rat": 0.09055118110236221, "gsm8k": 0.013646702047005308, "math_qa": 0.003015075376884422 } }, { "flos": 1.552931502382121e+17, "train_loss": 5.79952880859375, "eval_loss": 5.877214302887788, "eval_accuracy": 0.010969723562966213, "eval_loss_by_set": { "aqua_rat": 5.8772149085998535, "gsm8k": 6.629418113014915, "math_qa": 5.532454172770183 }, "eval_accuracy_by_set": { "aqua_rat": 0.09055118110236221, "gsm8k": 0.016679302501895376, "math_qa": 0.0016750418760469012 } }, { "flos": 1.6122215716932813e+17, "train_loss": 5.809129028320313, "eval_loss": 5.872309607428473, "eval_accuracy": 0.01184730144800351, "eval_loss_by_set": { "aqua_rat": 5.880426406860352, "gsm8k": 6.609073985706676, "math_qa": 5.533949534098308 }, "eval_accuracy_by_set": { "aqua_rat": 0.08661417322834646, "gsm8k": 0.018953752843062926, "math_qa": 0.0023450586264656616 } }, { "flos": 1.672383363672965e+17, "train_loss": 5.80126708984375, "eval_loss": 5.8766270199337525, "eval_accuracy": 0.013821851689337429, "eval_loss_by_set": { "aqua_rat": 5.888952255249023, "gsm8k": 6.62483700838956, "math_qa": 5.532670338948567 }, "eval_accuracy_by_set": { "aqua_rat": 0.09448818897637795, "gsm8k": 0.018953752843062926, "math_qa": 0.004690117252931323 } }, { "flos": 1.731757925728256e+17, "train_loss": 5.800050048828125, "eval_loss": 5.884289561091243, "eval_accuracy": 0.01228609039052216, "eval_loss_by_set": { "aqua_rat": 5.874222755432129, "gsm8k": 6.613127968528054, "math_qa": 5.551077524820964 }, "eval_accuracy_by_set": { "aqua_rat": 0.09055118110236221, "gsm8k": 0.02047005307050796, "math_qa": 0.0020100502512562816 } }, { "flos": 1.791335478675374e+17, "train_loss": 5.799901733398437, "eval_loss": 5.876015328072213, "eval_accuracy": 0.011408512505484861, "eval_loss_by_set": { "aqua_rat": 5.878791809082031, "gsm8k": 6.618623213334517, "math_qa": 5.535422007242839 }, "eval_accuracy_by_set": { "aqua_rat": 0.09448818897637795, "gsm8k": 0.016679302501895376, "math_qa": 0.0020100502512562816 } }, { "flos": 1.8508998407041843e+17, "train_loss": 5.7853271484375, "eval_loss": 5.894983291625977, "eval_accuracy": 0.012066695919262835, "eval_loss_by_set": { "aqua_rat": 5.882229804992676, "gsm8k": 6.635121432217685, "math_qa": 5.556816101074219 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.019711902956785442, "math_qa": 0.004020100502512563 } }, { "flos": 1.910303876972544e+17, "train_loss": 5.79060791015625, "eval_loss": 5.877085402205184, "eval_accuracy": 0.011408512505484861, "eval_loss_by_set": { "aqua_rat": 5.894010543823242, "gsm8k": 6.6221160888671875, "math_qa": 5.534202575683594 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.017437452615617893, "math_qa": 0.003015075376884422 } }, { "flos": 1.9699345962460774e+17, "train_loss": 5.787415771484375, "eval_loss": 5.8781843185424805, "eval_accuracy": 0.010969723562966213, "eval_loss_by_set": { "aqua_rat": 5.884498119354248, "gsm8k": 6.612427451393821, "math_qa": 5.541130065917969 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.019711902956785442, "math_qa": 0.001340033500837521 } }, { "flos": 2.029132339866501e+17, "train_loss": 5.7759765625, "eval_loss": 5.880337586274019, "eval_accuracy": 0.009214567792891619, "eval_loss_by_set": { "aqua_rat": 5.88774299621582, "gsm8k": 6.629890441894531, "math_qa": 5.5361754099528 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.011372251705837756, "math_qa": 0.0023450586264656616 } }, { "flos": 2.088618393904087e+17, "train_loss": 5.777073364257813, "eval_loss": 5.886001174514358, "eval_accuracy": 0.011627906976744186, "eval_loss_by_set": { "aqua_rat": 5.886631011962891, "gsm8k": 6.641523187810725, "math_qa": 5.5396677652994795 }, "eval_accuracy_by_set": { "aqua_rat": 0.0984251968503937, "gsm8k": 0.017437452615617893, "math_qa": 0.0016750418760469012 } }, { "flos": 2.14832000698155e+17, "train_loss": 5.77857177734375, "eval_loss": 5.901193515674488, "eval_accuracy": 0.010092145677928916, "eval_loss_by_set": { "aqua_rat": 5.876601219177246, "gsm8k": 6.639631791548296, "math_qa": 5.564791997273763 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.01592115238817286, "math_qa": 0.0036850921273031824 } }, { "flos": 2.2079074490908672e+17, "train_loss": 5.78380126953125, "eval_loss": 5.875571199365564, "eval_accuracy": 0.008775778850372971, "eval_loss_by_set": { "aqua_rat": 5.885975360870361, "gsm8k": 6.639796170321378, "math_qa": 5.524434407552083 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.014404852160727824, "math_qa": 0.002680067001675042 } }, { "flos": 2.267143321283461e+17, "train_loss": 5.7695068359375, "eval_loss": 5.888084540496001, "eval_accuracy": 0.009214567792891619, "eval_loss_by_set": { "aqua_rat": 5.882174015045166, "gsm8k": 6.642857638272372, "math_qa": 5.542639414469401 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.01592115238817286, "math_qa": 0.0016750418760469012 } }, { "flos": 2.327046481069998e+17, "train_loss": 5.767586669921875, "eval_loss": 5.877449602694125, "eval_accuracy": 0.009872751206669592, "eval_loss_by_set": { "aqua_rat": 5.887743949890137, "gsm8k": 6.63729511607777, "math_qa": 5.528329213460286 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.017437452615617893, "math_qa": 0.001340033500837521 } }, { "flos": 2.386968603137147e+17, "train_loss": 5.77108642578125, "eval_loss": 5.8846045829154345, "eval_accuracy": 0.010092145677928916, "eval_loss_by_set": { "aqua_rat": 5.876773834228516, "gsm8k": 6.61981201171875, "math_qa": 5.548287073771159 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.017437452615617893, "math_qa": 0.0023450586264656616 } }, { "flos": 2.446429306130268e+17, "train_loss": 5.762786254882813, "eval_loss": 5.884115270666174, "eval_accuracy": 0.01075032909170689, "eval_loss_by_set": { "aqua_rat": 5.885505676269531, "gsm8k": 6.646747935901988, "math_qa": 5.5344594319661455 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.01819560272934041, "math_qa": 0.002680067001675042 } }, { "flos": 2.506217886926766e+17, "train_loss": 5.7607080078125, "eval_loss": 5.901105726087415, "eval_accuracy": 0.01075032909170689, "eval_loss_by_set": { "aqua_rat": 5.8890838623046875, "gsm8k": 6.676890980113637, "math_qa": 5.546539306640625 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.019711902956785442, "math_qa": 0.004020100502512563 } }, { "flos": 2.56645654808363e+17, "train_loss": 5.76331787109375, "eval_loss": 5.9046024374059725, "eval_accuracy": 0.008995173321632294, "eval_loss_by_set": { "aqua_rat": 5.8824992179870605, "gsm8k": 6.663313432173296, "math_qa": 5.558701833089192 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.014404852160727824, "math_qa": 0.0020100502512562816 } }, { "flos": 2.62550777426346e+17, "train_loss": 5.752481689453125, "eval_loss": 5.880233326473752, "eval_accuracy": 0.009872751206669592, "eval_loss_by_set": { "aqua_rat": 5.89082670211792, "gsm8k": 6.644294738769531, "math_qa": 5.529155731201172 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.014404852160727824, "math_qa": 0.002680067001675042 } }, { "flos": 2.6856464861626368e+17, "train_loss": 5.753255004882813, "eval_loss": 5.896836409697661, "eval_accuracy": 0.010092145677928916, "eval_loss_by_set": { "aqua_rat": 5.882401466369629, "gsm8k": 6.631059820001775, "math_qa": 5.561520258585612 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.01819560272934041, "math_qa": 0.0020100502512562816 } }, { "flos": 2.7449060558372864e+17, "train_loss": 5.748008422851562, "eval_loss": 5.896911749968657, "eval_accuracy": 0.009653356735410267, "eval_loss_by_set": { "aqua_rat": 5.889486789703369, "gsm8k": 6.672588695179332, "math_qa": 5.542011896769206 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.016679302501895376, "math_qa": 0.0016750418760469012 } }, { "flos": 2.804323685677138e+17, "train_loss": 5.75547607421875, "eval_loss": 5.907972464690337, "eval_accuracy": 0.008995173321632294, "eval_loss_by_set": { "aqua_rat": 5.881104946136475, "gsm8k": 6.690108559348366, "math_qa": 5.5517323811848955 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.017437452615617893, "math_qa": 0.0020100502512562816 } }, { "flos": 2.86406569292202e+17, "train_loss": 5.740407104492188, "eval_loss": 5.903331241092166, "eval_accuracy": 0.011408512505484861, "eval_loss_by_set": { "aqua_rat": 5.891269683837891, "gsm8k": 6.684593894264915, "math_qa": 5.546257654825847 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.02047005307050796, "math_qa": 0.002680067001675042 } }, { "flos": 2.923352261834834e+17, "train_loss": 5.745005493164062, "eval_loss": 5.90000312392776, "eval_accuracy": 0.010969723562966213, "eval_loss_by_set": { "aqua_rat": 5.889819145202637, "gsm8k": 6.663710160688921, "math_qa": 5.550819396972656 }, "eval_accuracy_by_set": { "aqua_rat": 0.08267716535433071, "gsm8k": 0.01592115238817286, "math_qa": 0.002680067001675042 } }, { "flos": 2.983424616489288e+17, "train_loss": 5.747919921875, "eval_loss": 5.906692556432776, "eval_accuracy": 0.010092145677928916, "eval_loss_by_set": { "aqua_rat": 5.890969276428223, "gsm8k": 6.684030706232244, "math_qa": 5.5517228444417315 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.016679302501895376, "math_qa": 0.002680067001675042 } }, { "flos": 3.0434973791656346e+17, "train_loss": 5.749141235351562, "eval_loss": 5.903359335822028, "eval_accuracy": 0.010092145677928916, "eval_loss_by_set": { "aqua_rat": 5.887372016906738, "gsm8k": 6.684309525923296, "math_qa": 5.546756108601888 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.018953752843062926, "math_qa": 0.0023450586264656616 } }, { "flos": 3.1031326349983744e+17, "train_loss": 5.741430053710937, "eval_loss": 5.903665181752798, "eval_accuracy": 0.010311540149188241, "eval_loss_by_set": { "aqua_rat": 5.901796340942383, "gsm8k": 6.6737823486328125, "math_qa": 5.550850550333659 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.019711902956785442, "math_qa": 0.002680067001675042 } }, { "flos": 3.1627441933490586e+17, "train_loss": 5.745117797851562, "eval_loss": 5.903243296855205, "eval_accuracy": 0.010092145677928916, "eval_loss_by_set": { "aqua_rat": 5.879449844360352, "gsm8k": 6.6707846901633525, "math_qa": 5.553436279296875 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.017437452615617893, "math_qa": 0.0033500837520938024 } }, { "flos": 3.222221587658834e+17, "train_loss": 5.7411572265625, "eval_loss": 5.8934060174065666, "eval_accuracy": 0.009872751206669592, "eval_loss_by_set": { "aqua_rat": 5.890251159667969, "gsm8k": 6.664975946599787, "math_qa": 5.540032704671224 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.01819560272934041, "math_qa": 0.0023450586264656616 } }, { "flos": 3.282034483338936e+17, "train_loss": 5.74324462890625, "eval_loss": 5.9128117947965055, "eval_accuracy": 0.011408512505484861, "eval_loss_by_set": { "aqua_rat": 5.880929946899414, "gsm8k": 6.687490289861506, "math_qa": 5.560407638549805 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.02047005307050796, "math_qa": 0.0036850921273031824 } }, { "flos": 3.341323940617257e+17, "train_loss": 5.723519287109375, "eval_loss": 5.901376569593275, "eval_accuracy": 0.010969723562966213, "eval_loss_by_set": { "aqua_rat": 5.89057731628418, "gsm8k": 6.689000909978693, "math_qa": 5.541282018025716 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.017437452615617893, "math_qa": 0.003015075376884422 } }, { "flos": 3.401141576867512e+17, "train_loss": 5.725516357421875, "eval_loss": 5.907905114663614, "eval_accuracy": 0.010311540149188241, "eval_loss_by_set": { "aqua_rat": 5.890738487243652, "gsm8k": 6.71869520707564, "math_qa": 5.537723541259766 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.01592115238817286, "math_qa": 0.003015075376884422 } }, { "flos": 3.460900892830597e+17, "train_loss": 5.7330810546875, "eval_loss": 5.906316628327241, "eval_accuracy": 0.009872751206669592, "eval_loss_by_set": { "aqua_rat": 5.891308307647705, "gsm8k": 6.707501498135653, "math_qa": 5.54035758972168 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.015163002274450341, "math_qa": 0.004020100502512563 } }, { "flos": 3.520416619723489e+17, "train_loss": 5.730052490234375, "eval_loss": 5.909076948423643, "eval_accuracy": 0.009214567792891619, "eval_loss_by_set": { "aqua_rat": 5.892912864685059, "gsm8k": 6.699830488725142, "math_qa": 5.547995249430339 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.02122820318423048, "math_qa": 0.003015075376884422 } }, { "flos": 3.579800045517537e+17, "train_loss": 5.717431640625, "eval_loss": 5.897536045796162, "eval_accuracy": 0.011189118034225537, "eval_loss_by_set": { "aqua_rat": 5.8868303298950195, "gsm8k": 6.667089982466265, "math_qa": 5.545715967814128 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.017437452615617893, "math_qa": 0.004355108877721943 } }, { "flos": 3.6396391136546e+17, "train_loss": 5.734222412109375, "eval_loss": 5.911112244064744, "eval_accuracy": 0.01184730144800351, "eval_loss_by_set": { "aqua_rat": 5.8857927322387695, "gsm8k": 6.687765641645952, "math_qa": 5.5572560628255205 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.019711902956785442, "math_qa": 0.004355108877721943 } }, { "flos": 3.699335776782254e+17, "train_loss": 5.728629760742187, "eval_loss": 5.905184410713814, "eval_accuracy": 0.010530934620447565, "eval_loss_by_set": { "aqua_rat": 5.8871355056762695, "gsm8k": 6.680163990367543, "math_qa": 5.551489512125651 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.019711902956785442, "math_qa": 0.002680067001675042 } }, { "flos": 3.7591041604950426e+17, "train_loss": 5.727027587890625, "eval_loss": 5.897846170373865, "eval_accuracy": 0.011408512505484861, "eval_loss_by_set": { "aqua_rat": 5.894822120666504, "gsm8k": 6.683244185014204, "math_qa": 5.538124084472656 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.02122820318423048, "math_qa": 0.0033500837520938024 } }, { "flos": 3.8186378188763955e+17, "train_loss": 5.726023559570312, "eval_loss": 5.908478865752349, "eval_accuracy": 0.011189118034225537, "eval_loss_by_set": { "aqua_rat": 5.905213356018066, "gsm8k": 6.698831038041548, "math_qa": 5.546506245930989 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.01819560272934041, "math_qa": 0.004020100502512563 } }, { "flos": 3.878550454434529e+17, "train_loss": 5.7323681640625, "eval_loss": 5.9087190370301945, "eval_accuracy": 0.011627906976744186, "eval_loss_by_set": { "aqua_rat": 5.902244567871094, "gsm8k": 6.691325794566762, "math_qa": 5.550563812255859 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.017437452615617893, "math_qa": 0.005025125628140704 } }, { "flos": 3.938626309487329e+17, "train_loss": 5.7158447265625, "eval_loss": 5.907500086603938, "eval_accuracy": 0.013602457218078104, "eval_loss_by_set": { "aqua_rat": 5.901735305786133, "gsm8k": 6.702473033558238, "math_qa": 5.543617884318034 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.016679302501895376, "math_qa": 0.006700167504187605 } }, { "flos": 3.998285676192727e+17, "train_loss": 5.71840576171875, "eval_loss": 5.90376091003418, "eval_accuracy": 0.010092145677928916, "eval_loss_by_set": { "aqua_rat": 5.893610954284668, "gsm8k": 6.689335216175426, "math_qa": 5.544551849365234 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.012130401819560273, "math_qa": 0.004690117252931323 } }, { "flos": 4.057778323005112e+17, "train_loss": 5.715631103515625, "eval_loss": 5.913252753180426, "eval_accuracy": 0.010530934620447565, "eval_loss_by_set": { "aqua_rat": 5.896556854248047, "gsm8k": 6.707469593394887, "math_qa": 5.550628026326497 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.01592115238817286, "math_qa": 0.004690117252931323 } }, { "flos": 4.117451498030367e+17, "train_loss": 5.717726440429687, "eval_loss": 5.911292462735562, "eval_accuracy": 0.014260640631856078, "eval_loss_by_set": { "aqua_rat": 5.901349067687988, "gsm8k": 6.665745821866122, "math_qa": 5.5663299560546875 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.019711902956785442, "math_qa": 0.007370184254606365 } }, { "flos": 4.176759498829988e+17, "train_loss": 5.70611572265625, "eval_loss": 5.933554262728305, "eval_accuracy": 0.013821851689337429, "eval_loss_by_set": { "aqua_rat": 5.902788162231445, "gsm8k": 6.739988847212358, "math_qa": 5.5665022532145185 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.02047005307050796, "math_qa": 0.006365159128978224 } }, { "flos": 4.2367172744944026e+17, "train_loss": 5.7189178466796875, "eval_loss": 5.926208650743639, "eval_accuracy": 0.011189118034225537, "eval_loss_by_set": { "aqua_rat": 5.895758628845215, "gsm8k": 6.712129766290838, "math_qa": 5.568532307942708 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.014404852160727824, "math_qa": 0.007370184254606365 } }, { "flos": 4.296435992279122e+17, "train_loss": 5.702518920898438, "eval_loss": 5.922365394798485, "eval_accuracy": 0.01645458534444932, "eval_loss_by_set": { "aqua_rat": 5.901738166809082, "gsm8k": 6.745918273925781, "math_qa": 5.546622594197591 }, "eval_accuracy_by_set": { "aqua_rat": 0.08267716535433071, "gsm8k": 0.025018953752843062, "math_qa": 0.007035175879396985 } }, { "flos": 4.356149148081193e+17, "train_loss": 5.7143603515625, "eval_loss": 5.913277110537967, "eval_accuracy": 0.012944273804300131, "eval_loss_by_set": { "aqua_rat": 5.908543109893799, "gsm8k": 6.722029252485796, "math_qa": 5.542993545532227 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.016679302501895376, "math_qa": 0.006030150753768844 } }, { "flos": 4.415742366921523e+17, "train_loss": 5.706102905273437, "eval_loss": 5.916396656551877, "eval_accuracy": 0.012944273804300131, "eval_loss_by_set": { "aqua_rat": 5.905616283416748, "gsm8k": 6.718424016779119, "math_qa": 5.549699147542317 }, "eval_accuracy_by_set": { "aqua_rat": 0.08267716535433071, "gsm8k": 0.017437452615617893, "math_qa": 0.005025125628140704 } }, { "flos": 4.474856852600914e+17, "train_loss": 5.698836669921875, "eval_loss": 5.919310647088128, "eval_accuracy": 0.012944273804300131, "eval_loss_by_set": { "aqua_rat": 5.894545555114746, "gsm8k": 6.697651256214488, "math_qa": 5.564634958902995 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.015163002274450341, "math_qa": 0.008040201005025126 } }, { "flos": 4.5345094171518566e+17, "train_loss": 5.698563232421875, "eval_loss": 5.925348745810019, "eval_accuracy": 0.014699429574374727, "eval_loss_by_set": { "aqua_rat": 5.905149459838867, "gsm8k": 6.738533020019531, "math_qa": 5.554322560628255 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.021986353297952996, "math_qa": 0.008040201005025126 } }, { "flos": 4.594563013536645e+17, "train_loss": 5.711514282226562, "eval_loss": 5.924634160222234, "eval_accuracy": 0.011189118034225537, "eval_loss_by_set": { "aqua_rat": 5.906032562255859, "gsm8k": 6.732527299360796, "math_qa": 5.555899937947591 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.017437452615617893, "math_qa": 0.005025125628140704 } }, { "flos": 4.654011561772319e+17, "train_loss": 5.7092437744140625, "eval_loss": 5.927145700196962, "eval_accuracy": 0.013163668275559455, "eval_loss_by_set": { "aqua_rat": 5.900822162628174, "gsm8k": 6.712496670809659, "math_qa": 5.569386800130208 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.02122820318423048, "math_qa": 0.006365159128978224 } }, { "flos": 4.713052072008745e+17, "train_loss": 5.699661865234375, "eval_loss": 5.918557476353001, "eval_accuracy": 0.013163668275559455, "eval_loss_by_set": { "aqua_rat": 5.9071736335754395, "gsm8k": 6.728752136230469, "math_qa": 5.548166910807292 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.01819560272934041, "math_qa": 0.008375209380234505 } }, { "flos": 4.772315968862945e+17, "train_loss": 5.699795532226562, "eval_loss": 5.931105046658902, "eval_accuracy": 0.013602457218078104, "eval_loss_by_set": { "aqua_rat": 5.899515628814697, "gsm8k": 6.723772915926847, "math_qa": 5.570431391398112 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.016679302501895376, "math_qa": 0.009380234505862646 } }, { "flos": 4.8315835754951475e+17, "train_loss": 5.70438720703125, "eval_loss": 5.912017693390718, "eval_accuracy": 0.015138218516893374, "eval_loss_by_set": { "aqua_rat": 5.918019771575928, "gsm8k": 6.727865045720881, "math_qa": 5.537587483723958 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.017437452615617893, "math_qa": 0.010385259631490788 } }, { "flos": 4.890688381391995e+17, "train_loss": 5.700570678710937, "eval_loss": 5.928651809692383, "eval_accuracy": 0.01864853005704256, "eval_loss_by_set": { "aqua_rat": 5.918244361877441, "gsm8k": 6.744135769930753, "math_qa": 5.555755615234375 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.022744503411675512, "math_qa": 0.011725293132328308 } }, { "flos": 4.950379895927603e+17, "train_loss": 5.699705200195313, "eval_loss": 5.921727438230772, "eval_accuracy": 0.01338306274681878, "eval_loss_by_set": { "aqua_rat": 5.918485164642334, "gsm8k": 6.723121643066406, "math_qa": 5.5546919504801435 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.015163002274450341, "math_qa": 0.010385259631490788 } }, { "flos": 5.010553848033444e+17, "train_loss": 5.7048193359375, "eval_loss": 5.936411058580553, "eval_accuracy": 0.015357612988152698, "eval_loss_by_set": { "aqua_rat": 5.910099029541016, "gsm8k": 6.738840276544744, "math_qa": 5.570823669433594 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.022744503411675512, "math_qa": 0.008375209380234505 } }, { "flos": 5.070040927494472e+17, "train_loss": 5.689322509765625, "eval_loss": 5.936762113828917, "eval_accuracy": 0.01184730144800351, "eval_loss_by_set": { "aqua_rat": 5.908651351928711, "gsm8k": 6.743717540394176, "math_qa": 5.569250106811523 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.019711902956785442, "math_qa": 0.006365159128978224 } }, { "flos": 5.130092677043323e+17, "train_loss": 5.700362548828125, "eval_loss": 5.92353630065918, "eval_accuracy": 0.013163668275559455, "eval_loss_by_set": { "aqua_rat": 5.917853355407715, "gsm8k": 6.719212618741122, "math_qa": 5.559324900309245 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.017437452615617893, "math_qa": 0.008040201005025126 } }, { "flos": 5.189152965604147e+17, "train_loss": 5.6997747802734375, "eval_loss": 5.9278768075479045, "eval_accuracy": 0.018429135585783237, "eval_loss_by_set": { "aqua_rat": 5.908419609069824, "gsm8k": 6.724910389293324, "math_qa": 5.564191182454427 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.022744503411675512, "math_qa": 0.012395309882747068 } }, { "flos": 5.24846632437547e+17, "train_loss": 5.683509521484375, "eval_loss": 5.935092127000964, "eval_accuracy": 0.015357612988152698, "eval_loss_by_set": { "aqua_rat": 5.911745548248291, "gsm8k": 6.7309487082741475, "math_qa": 5.5722700754801435 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.01819560272934041, "math_qa": 0.010385259631490788 } }, { "flos": 5.30827880666497e+17, "train_loss": 5.694727783203125, "eval_loss": 5.92933701180123, "eval_accuracy": 0.014480035103115402, "eval_loss_by_set": { "aqua_rat": 5.913369178771973, "gsm8k": 6.732181895862926, "math_qa": 5.562697092692058 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.018953752843062926, "math_qa": 0.008710217755443886 } }, { "flos": 5.3681640403317555e+17, "train_loss": 5.697666015625, "eval_loss": 5.940735275680955, "eval_accuracy": 0.014260640631856078, "eval_loss_by_set": { "aqua_rat": 5.907203674316406, "gsm8k": 6.7432778098366475, "math_qa": 5.575697580973308 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.018953752843062926, "math_qa": 0.008040201005025126 } }, { "flos": 5.428115217852662e+17, "train_loss": 5.70104248046875, "eval_loss": 5.924360043293721, "eval_accuracy": 0.015138218516893374, "eval_loss_by_set": { "aqua_rat": 5.912985324859619, "gsm8k": 6.713990644975142, "math_qa": 5.563393910725911 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.019711902956785442, "math_qa": 0.009715242881072027 } }, { "flos": 5.488037753310413e+17, "train_loss": 5.6929638671875, "eval_loss": 5.923909316191802, "eval_accuracy": 0.017551557700745943, "eval_loss_by_set": { "aqua_rat": 5.9153547286987305, "gsm8k": 6.725496465509588, "math_qa": 5.557228088378906 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.016679302501895376, "math_qa": 0.01373534338358459 } }, { "flos": 5.5478724942679245e+17, "train_loss": 5.684339599609375, "eval_loss": 5.917870289570576, "eval_accuracy": 0.016673979815708645, "eval_loss_by_set": { "aqua_rat": 5.914129257202148, "gsm8k": 6.723848516290838, "math_qa": 5.548775355021159 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.016679302501895376, "math_qa": 0.012395309882747068 } }, { "flos": 5.60792403443712e+17, "train_loss": 5.69698486328125, "eval_loss": 5.947791563498007, "eval_accuracy": 0.012944273804300131, "eval_loss_by_set": { "aqua_rat": 5.916239261627197, "gsm8k": 6.7536537863991475, "math_qa": 5.581067403157552 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.014404852160727824, "math_qa": 0.010385259631490788 } }, { "flos": 5.6682094731565466e+17, "train_loss": 5.694147338867188, "eval_loss": 5.950687047597524, "eval_accuracy": 0.01491882404563405, "eval_loss_by_set": { "aqua_rat": 5.923396110534668, "gsm8k": 6.778088656338778, "math_qa": 5.5737355550130205 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.014404852160727824, "math_qa": 0.011725293132328308 } }, { "flos": 5.727916240194765e+17, "train_loss": 5.696395263671875, "eval_loss": 5.9247041135220915, "eval_accuracy": 0.015796401930671347, "eval_loss_by_set": { "aqua_rat": 5.9131975173950195, "gsm8k": 6.728144558993253, "math_qa": 5.557419459025065 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.016679302501895376, "math_qa": 0.011725293132328308 } }, { "flos": 5.787765406873682e+17, "train_loss": 5.69015625, "eval_loss": 5.926980843415132, "eval_accuracy": 0.01645458534444932, "eval_loss_by_set": { "aqua_rat": 5.9276604652404785, "gsm8k": 6.738122419877485, "math_qa": 5.555150985717773 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.016679302501895376, "math_qa": 0.012060301507537688 } }, { "flos": 5.847221165285704e+17, "train_loss": 5.692672119140625, "eval_loss": 5.9184895335017025, "eval_accuracy": 0.016673979815708645, "eval_loss_by_set": { "aqua_rat": 5.9285149574279785, "gsm8k": 6.699646689675071, "math_qa": 5.559623718261719 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.016679302501895376, "math_qa": 0.012395309882747068 } }, { "flos": 5.906654257007821e+17, "train_loss": 5.679080810546875, "eval_loss": 5.942468849388328, "eval_accuracy": 0.014699429574374727, "eval_loss_by_set": { "aqua_rat": 5.919098854064941, "gsm8k": 6.757360978560015, "math_qa": 5.570924123128255 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.016679302501895376, "math_qa": 0.012395309882747068 } }, { "flos": 5.966709506955018e+17, "train_loss": 5.678152465820313, "eval_loss": 5.949227590818663, "eval_accuracy": 0.014041246160596753, "eval_loss_by_set": { "aqua_rat": 5.922011852264404, "gsm8k": 6.763979131525213, "math_qa": 5.578067779541016 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.014404852160727824, "math_qa": 0.012060301507537688 } }, { "flos": 6.026072322274755e+17, "train_loss": 5.68257568359375, "eval_loss": 5.934872189083615, "eval_accuracy": 0.014699429574374727, "eval_loss_by_set": { "aqua_rat": 5.923179626464844, "gsm8k": 6.741900357333097, "math_qa": 5.565958658854167 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.014404852160727824, "math_qa": 0.011055276381909548 } }, { "flos": 6.085909124816568e+17, "train_loss": 5.672444458007813, "eval_loss": 5.942836426399849, "eval_accuracy": 0.01601579640193067, "eval_loss_by_set": { "aqua_rat": 5.91591215133667, "gsm8k": 6.751588994806463, "math_qa": 5.57440185546875 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.01819560272934041, "math_qa": 0.012730318257956449 } }, { "flos": 6.145447319757128e+17, "train_loss": 5.67932373046875, "eval_loss": 5.935757765898833, "eval_accuracy": 0.01689337428696797, "eval_loss_by_set": { "aqua_rat": 5.922450065612793, "gsm8k": 6.750041614879262, "math_qa": 5.563653310139974 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.013646702047005308, "math_qa": 0.01474036850921273 } }, { "flos": 6.205220030649467e+17, "train_loss": 5.683408203125, "eval_loss": 5.945175995697847, "eval_accuracy": 0.014480035103115402, "eval_loss_by_set": { "aqua_rat": 5.9291839599609375, "gsm8k": 6.7769775390625, "math_qa": 5.565266291300456 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.01819560272934041, "math_qa": 0.010385259631490788 } }, { "flos": 6.26503230892802e+17, "train_loss": 5.684932861328125, "eval_loss": 5.941149917808739, "eval_accuracy": 0.01601579640193067, "eval_loss_by_set": { "aqua_rat": 5.914638042449951, "gsm8k": 6.748242464932528, "math_qa": 5.573441823323567 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.018953752843062926, "math_qa": 0.01306532663316583 } }, { "flos": 6.32535793780392e+17, "train_loss": 5.68593505859375, "eval_loss": 5.947217838184254, "eval_accuracy": 0.015138218516893374, "eval_loss_by_set": { "aqua_rat": 5.931572914123535, "gsm8k": 6.749185735529119, "math_qa": 5.580952962239583 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.01288855193328279, "math_qa": 0.012060301507537688 } }, { "flos": 6.385255943629701e+17, "train_loss": 5.6728759765625, "eval_loss": 5.953559875488281, "eval_accuracy": 0.015577007459412023, "eval_loss_by_set": { "aqua_rat": 5.922985076904297, "gsm8k": 6.778927889737216, "math_qa": 5.577814102172852 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.02047005307050796, "math_qa": 0.011725293132328308 } }, { "flos": 6.444813095482163e+17, "train_loss": 5.674221801757812, "eval_loss": 5.935773333987674, "eval_accuracy": 0.01733216322948662, "eval_loss_by_set": { "aqua_rat": 5.933396339416504, "gsm8k": 6.756318525834517, "math_qa": 5.559888203938802 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.019711902956785442, "math_qa": 0.01340033500837521 } }, { "flos": 6.50395066661077e+17, "train_loss": 5.670057373046875, "eval_loss": 5.944669388435982, "eval_accuracy": 0.01689337428696797, "eval_loss_by_set": { "aqua_rat": 5.924145221710205, "gsm8k": 6.765780362215909, "math_qa": 5.570037206013997 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.019711902956785442, "math_qa": 0.01306532663316583 } }, { "flos": 6.563560990158356e+17, "train_loss": 5.6724072265625, "eval_loss": 5.940762983786093, "eval_accuracy": 0.015577007459412023, "eval_loss_by_set": { "aqua_rat": 5.9295973777771, "gsm8k": 6.7390899658203125, "math_qa": 5.575793584187825 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.017437452615617893, "math_qa": 0.011055276381909548 } }, { "flos": 6.623265695612273e+17, "train_loss": 5.6806982421875, "eval_loss": 5.9277642739785685, "eval_accuracy": 0.017551557700745943, "eval_loss_by_set": { "aqua_rat": 5.941394805908203, "gsm8k": 6.729217529296875, "math_qa": 5.559295654296875 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.02047005307050796, "math_qa": 0.01306532663316583 } }, { "flos": 6.683281378173256e+17, "train_loss": 5.6652069091796875, "eval_loss": 5.938000395491317, "eval_accuracy": 0.01908731899956121, "eval_loss_by_set": { "aqua_rat": 5.9386701583862305, "gsm8k": 6.745236483487216, "math_qa": 5.56796137491862 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.01819560272934041, "math_qa": 0.01574539363484087 } }, { "flos": 6.742796901055201e+17, "train_loss": 5.675859985351562, "eval_loss": 5.9468513694969385, "eval_accuracy": 0.016235190873189996, "eval_loss_by_set": { "aqua_rat": 5.932765960693359, "gsm8k": 6.751806085759943, "math_qa": 5.579087575276692 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.019711902956785442, "math_qa": 0.012395309882747068 } }, { "flos": 6.80290223032107e+17, "train_loss": 5.68092529296875, "eval_loss": 5.93808854592813, "eval_accuracy": 0.0217200526546731, "eval_loss_by_set": { "aqua_rat": 5.9435319900512695, "gsm8k": 6.772565668279475, "math_qa": 5.555166244506836 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.02122820318423048, "math_qa": 0.018760469011725293 } }, { "flos": 6.862811784240169e+17, "train_loss": 5.674825439453125, "eval_loss": 5.933936093304609, "eval_accuracy": 0.018867924528301886, "eval_loss_by_set": { "aqua_rat": 5.935227394104004, "gsm8k": 6.777317393909801, "math_qa": 5.547278722127278 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.01819560272934041, "math_qa": 0.01474036850921273 } }, { "flos": 6.922922052718428e+17, "train_loss": 5.6672607421875, "eval_loss": 5.955469054144782, "eval_accuracy": 0.02106186924089513, "eval_loss_by_set": { "aqua_rat": 5.932071208953857, "gsm8k": 6.773773886940696, "math_qa": 5.5823624928792315 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.016679302501895376, "math_qa": 0.018760469011725293 } }, { "flos": 6.983103215000617e+17, "train_loss": 5.669239501953125, "eval_loss": 5.951992756611592, "eval_accuracy": 0.01952610794207986, "eval_loss_by_set": { "aqua_rat": 5.934673309326172, "gsm8k": 6.783137928355824, "math_qa": 5.5724945068359375 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.02047005307050796, "math_qa": 0.01742043551088777 } }, { "flos": 7.042261804625428e+17, "train_loss": 5.6693572998046875, "eval_loss": 5.9482168249181795, "eval_accuracy": 0.018867924528301886, "eval_loss_by_set": { "aqua_rat": 5.926918029785156, "gsm8k": 6.748187672008168, "math_qa": 5.5833384195963545 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.02047005307050796, "math_qa": 0.01407035175879397 } }, { "flos": 7.102037194503619e+17, "train_loss": 5.662367553710937, "eval_loss": 5.953176137563345, "eval_accuracy": 0.014699429574374727, "eval_loss_by_set": { "aqua_rat": 5.936271667480469, "gsm8k": 6.766447587446733, "math_qa": 5.581835428873698 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.021986353297952996, "math_qa": 0.010720268006700168 } }, { "flos": 7.161670592763003e+17, "train_loss": 5.66787841796875, "eval_loss": 5.957673407889701, "eval_accuracy": 0.021281263712154455, "eval_loss_by_set": { "aqua_rat": 5.942582130432129, "gsm8k": 6.777783480557528, "math_qa": 5.583047231038411 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.021986353297952996, "math_qa": 0.018425460636515914 } }, { "flos": 7.221597659411251e+17, "train_loss": 5.661722412109375, "eval_loss": 5.955766626306482, "eval_accuracy": 0.01952610794207986, "eval_loss_by_set": { "aqua_rat": 5.932636260986328, "gsm8k": 6.780199917879972, "math_qa": 5.5798288981119795 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.02047005307050796, "math_qa": 0.01742043551088777 } }, { "flos": 7.281126163831849e+17, "train_loss": 5.67260986328125, "eval_loss": 5.953848813031171, "eval_accuracy": 0.01689337428696797, "eval_loss_by_set": { "aqua_rat": 5.942376136779785, "gsm8k": 6.779278841885653, "math_qa": 5.576482772827148 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.013646702047005308, "math_qa": 0.01574539363484087 } }, { "flos": 7.34154823619838e+17, "train_loss": 5.663889770507812, "eval_loss": 5.953544049649625, "eval_accuracy": 0.018867924528301886, "eval_loss_by_set": { "aqua_rat": 5.937378883361816, "gsm8k": 6.753239024769176, "math_qa": 5.588364283243815 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.019711902956785442, "math_qa": 0.01373534338358459 } }, { "flos": 7.400738361620562e+17, "train_loss": 5.655753784179687, "eval_loss": 5.964750960066512, "eval_accuracy": 0.01996489688459851, "eval_loss_by_set": { "aqua_rat": 5.935203552246094, "gsm8k": 6.785357388583097, "math_qa": 5.591101964314778 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.02122820318423048, "math_qa": 0.017085427135678392 } }, { "flos": 7.460877277530685e+17, "train_loss": 5.659617919921875, "eval_loss": 5.966851028236183, "eval_accuracy": 0.021281263712154455, "eval_loss_by_set": { "aqua_rat": 5.955259799957275, "gsm8k": 6.801035794344815, "math_qa": 5.585482279459636 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.01819560272934041, "math_qa": 0.018760469011725293 } }, { "flos": 7.520509644997919e+17, "train_loss": 5.66637451171875, "eval_loss": 5.957218324815905, "eval_accuracy": 0.018209741114523913, "eval_loss_by_set": { "aqua_rat": 5.934212684631348, "gsm8k": 6.782909740101207, "math_qa": 5.5806935628255205 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.02577710386656558, "math_qa": 0.01373534338358459 } }, { "flos": 7.579878441059615e+17, "train_loss": 5.653123168945313, "eval_loss": 5.968476243921228, "eval_accuracy": 0.015357612988152698, "eval_loss_by_set": { "aqua_rat": 5.936349391937256, "gsm8k": 6.796110673384233, "math_qa": 5.591821034749349 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.016679302501895376, "math_qa": 0.012730318257956449 } }, { "flos": 7.639620448304497e+17, "train_loss": 5.65587646484375, "eval_loss": 5.940109433354558, "eval_accuracy": 0.021939447125932425, "eval_loss_by_set": { "aqua_rat": 5.941638469696045, "gsm8k": 6.758191195401278, "math_qa": 5.5650278727213545 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.02350265352539803, "math_qa": 0.018425460636515914 } }, { "flos": 7.698483103945196e+17, "train_loss": 5.663402709960938, "eval_loss": 5.951039108070168, "eval_accuracy": 0.019745502413339184, "eval_loss_by_set": { "aqua_rat": 5.944115161895752, "gsm8k": 6.770810213955966, "math_qa": 5.575887680053711 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.019711902956785442, "math_qa": 0.018425460636515914 } }, { "flos": 7.758546594860892e+17, "train_loss": 5.6627880859375, "eval_loss": 5.942973265776763, "eval_accuracy": 0.017990346643264588, "eval_loss_by_set": { "aqua_rat": 5.951448440551758, "gsm8k": 6.757226423783735, "math_qa": 5.569067637125651 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.019711902956785442, "math_qa": 0.01440536013400335 } }, { "flos": 7.818376595248251e+17, "train_loss": 5.65591064453125, "eval_loss": 5.947021329725111, "eval_accuracy": 0.01952610794207986, "eval_loss_by_set": { "aqua_rat": 5.9488115310668945, "gsm8k": 6.753263993696733, "math_qa": 5.577344258626302 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.018953752843062926, "math_qa": 0.01675041876046901 } }, { "flos": 7.877877901788447e+17, "train_loss": 5.6664208984375, "eval_loss": 5.952332496643066, "eval_accuracy": 0.01733216322948662, "eval_loss_by_set": { "aqua_rat": 5.936773777008057, "gsm8k": 6.786487232555043, "math_qa": 5.571308135986328 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.017437452615617893, "math_qa": 0.016080402010050253 } }, { "flos": 7.937614964452229e+17, "train_loss": 5.66309326171875, "eval_loss": 5.963533556139147, "eval_accuracy": 0.01996489688459851, "eval_loss_by_set": { "aqua_rat": 5.949714660644531, "gsm8k": 6.79962158203125, "math_qa": 5.581478118896484 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.02047005307050796, "math_qa": 0.01641541038525963 } }, { "flos": 7.9973314166417e+17, "train_loss": 5.650869140625, "eval_loss": 5.947584616171347, "eval_accuracy": 0.01864853005704256, "eval_loss_by_set": { "aqua_rat": 5.955898284912109, "gsm8k": 6.772007335316051, "math_qa": 5.569031397501628 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.017437452615617893, "math_qa": 0.017085427135678392 } }, { "flos": 8.056755027223511e+17, "train_loss": 5.65957275390625, "eval_loss": 5.962688214070088, "eval_accuracy": 0.01645458534444932, "eval_loss_by_set": { "aqua_rat": 5.942418575286865, "gsm8k": 6.775222084738991, "math_qa": 5.591965993245442 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.022744503411675512, "math_qa": 0.010385259631490788 } }, { "flos": 8.116675909118853e+17, "train_loss": 5.649552001953125, "eval_loss": 5.951055114333694, "eval_accuracy": 0.017551557700745943, "eval_loss_by_set": { "aqua_rat": 5.948615074157715, "gsm8k": 6.780004327947443, "math_qa": 5.571323394775391 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.024260803639120546, "math_qa": 0.010720268006700168 } }, { "flos": 8.176118063221965e+17, "train_loss": 5.658164672851562, "eval_loss": 5.964469677693135, "eval_accuracy": 0.017551557700745943, "eval_loss_by_set": { "aqua_rat": 5.96394681930542, "gsm8k": 6.810034318403765, "math_qa": 5.576962788899739 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.016679302501895376, "math_qa": 0.01574539363484087 } }, { "flos": 8.23594765558743e+17, "train_loss": 5.652720336914062, "eval_loss": 5.945960689235378, "eval_accuracy": 0.01645458534444932, "eval_loss_by_set": { "aqua_rat": 5.945074081420898, "gsm8k": 6.766826282848012, "math_qa": 5.569804509480794 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.013646702047005308, "math_qa": 0.01474036850921273 } }, { "flos": 8.295642262499492e+17, "train_loss": 5.644412841796875, "eval_loss": 5.949443868688635, "eval_accuracy": 0.018429135585783237, "eval_loss_by_set": { "aqua_rat": 5.95090389251709, "gsm8k": 6.782651034268466, "math_qa": 5.567435582478841 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.02122820318423048, "math_qa": 0.01574539363484087 } }, { "flos": 8.355270925557432e+17, "train_loss": 5.654782104492187, "eval_loss": 5.94695251052444, "eval_accuracy": 0.016235190873189996, "eval_loss_by_set": { "aqua_rat": 5.944616317749023, "gsm8k": 6.784029873934659, "math_qa": 5.563486735026042 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.01819560272934041, "math_qa": 0.01407035175879397 } }, { "flos": 8.41541231644246e+17, "train_loss": 5.653460083007812, "eval_loss": 5.953035406164221, "eval_accuracy": 0.01864853005704256, "eval_loss_by_set": { "aqua_rat": 5.965642929077148, "gsm8k": 6.790008544921875, "math_qa": 5.568372090657552 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.021986353297952996, "math_qa": 0.01440536013400335 } }, { "flos": 8.475562775077192e+17, "train_loss": 5.654074096679688, "eval_loss": 5.966661143947292, "eval_accuracy": 0.018209741114523913, "eval_loss_by_set": { "aqua_rat": 5.952143669128418, "gsm8k": 6.800566933371804, "math_qa": 5.58566411336263 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.01592115238817286, "math_qa": 0.017085427135678392 } }, { "flos": 8.535612457673032e+17, "train_loss": 5.648212890625, "eval_loss": 5.960987658114047, "eval_accuracy": 0.017112768758227294, "eval_loss_by_set": { "aqua_rat": 5.9448442459106445, "gsm8k": 6.795110529119318, "math_qa": 5.580026626586914 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.017437452615617893, "math_qa": 0.01474036850921273 } }, { "flos": 8.594662239670108e+17, "train_loss": 5.643797607421875, "eval_loss": 5.973313202729097, "eval_accuracy": 0.018209741114523913, "eval_loss_by_set": { "aqua_rat": 5.964653015136719, "gsm8k": 6.820094715465199, "math_qa": 5.585926691691081 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.021986353297952996, "math_qa": 0.01474036850921273 } }, { "flos": 8.654288218373489e+17, "train_loss": 5.64626708984375, "eval_loss": 5.9630180822836385, "eval_accuracy": 0.01864853005704256, "eval_loss_by_set": { "aqua_rat": 5.954826831817627, "gsm8k": 6.788640802556818, "math_qa": 5.585290273030599 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.017437452615617893, "math_qa": 0.01742043551088777 } }, { "flos": 8.714029398837166e+17, "train_loss": 5.653111572265625, "eval_loss": 5.955826733563398, "eval_accuracy": 0.021281263712154455, "eval_loss_by_set": { "aqua_rat": 5.953531265258789, "gsm8k": 6.785120183771307, "math_qa": 5.575925191243489 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.021986353297952996, "math_qa": 0.018425460636515914 } }, { "flos": 8.773990878910874e+17, "train_loss": 5.65259765625, "eval_loss": 5.968776909080711, "eval_accuracy": 0.018429135585783237, "eval_loss_by_set": { "aqua_rat": 5.954523086547852, "gsm8k": 6.800906094637784, "math_qa": 5.588572184244792 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.021986353297952996, "math_qa": 0.01574539363484087 } }, { "flos": 8.833710219465851e+17, "train_loss": 5.650885009765625, "eval_loss": 5.9623836826633765, "eval_accuracy": 0.017112768758227294, "eval_loss_by_set": { "aqua_rat": 5.948694229125977, "gsm8k": 6.795983748002485, "math_qa": 5.581457773844401 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.019711902956785442, "math_qa": 0.012060301507537688 } }, { "flos": 8.893018424276419e+17, "train_loss": 5.64765869140625, "eval_loss": 5.959484796266298, "eval_accuracy": 0.017551557700745943, "eval_loss_by_set": { "aqua_rat": 5.953853130340576, "gsm8k": 6.786274303089488, "math_qa": 5.5810089111328125 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.016679302501895376, "math_qa": 0.01541038525963149 } }, { "flos": 8.952710352202629e+17, "train_loss": 5.64869873046875, "eval_loss": 5.972527478192304, "eval_accuracy": 0.02215884159719175, "eval_loss_by_set": { "aqua_rat": 5.962186813354492, "gsm8k": 6.8088462136008525, "math_qa": 5.590076446533203 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.019711902956785442, "math_qa": 0.021440536013400336 } }, { "flos": 9.012499963791278e+17, "train_loss": 5.63621337890625, "eval_loss": 5.964422225952148, "eval_accuracy": 0.01645458534444932, "eval_loss_by_set": { "aqua_rat": 5.953368186950684, "gsm8k": 6.7938454367897725, "math_qa": 5.585191090901692 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.019711902956785442, "math_qa": 0.012730318257956449 } }, { "flos": 9.071919451204485e+17, "train_loss": 5.6456671142578125, "eval_loss": 5.961653168137009, "eval_accuracy": 0.018429135585783237, "eval_loss_by_set": { "aqua_rat": 5.947173118591309, "gsm8k": 6.803733825683594, "math_qa": 5.576906204223633 }, "eval_accuracy_by_set": { "aqua_rat": 0.011811023622047244, "gsm8k": 0.022744503411675512, "math_qa": 0.017085427135678392 } }, { "flos": 9.131297723037778e+17, "train_loss": 5.651341552734375, "eval_loss": 5.952743788023253, "eval_accuracy": 0.016673979815708645, "eval_loss_by_set": { "aqua_rat": 5.954575538635254, "gsm8k": 6.79633886163885, "math_qa": 5.5659434000651045 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.016679302501895376, "math_qa": 0.01574539363484087 } }, { "flos": 9.190700105743729e+17, "train_loss": 5.644981689453125, "eval_loss": 5.96588794605152, "eval_accuracy": 0.016673979815708645, "eval_loss_by_set": { "aqua_rat": 5.969181060791016, "gsm8k": 6.791170293634588, "math_qa": 5.587359110514323 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.02047005307050796, "math_qa": 0.01407035175879397 } }, { "flos": 9.250189660179661e+17, "train_loss": 5.641000366210937, "eval_loss": 5.967720083288245, "eval_accuracy": 0.018867924528301886, "eval_loss_by_set": { "aqua_rat": 5.975640296936035, "gsm8k": 6.799267161976207, "math_qa": 5.585934321085612 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.02122820318423048, "math_qa": 0.01474036850921273 } }, { "flos": 9.309840372525957e+17, "train_loss": 5.648408203125, "eval_loss": 5.9713154612360775, "eval_accuracy": 0.021939447125932425, "eval_loss_by_set": { "aqua_rat": 5.945559024810791, "gsm8k": 6.808780323375355, "math_qa": 5.589623769124349 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.025018953752843062, "math_qa": 0.01742043551088777 } }, { "flos": 9.369271198652826e+17, "train_loss": 5.639891967773438, "eval_loss": 5.961983603400153, "eval_accuracy": 0.017112768758227294, "eval_loss_by_set": { "aqua_rat": 5.961125373840332, "gsm8k": 6.803599964488637, "math_qa": 5.576314290364583 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.02047005307050796, "math_qa": 0.012395309882747068 } }, { "flos": 9.428921089586627e+17, "train_loss": 5.634590454101563, "eval_loss": 5.975339477126663, "eval_accuracy": 0.017990346643264588, "eval_loss_by_set": { "aqua_rat": 5.954165458679199, "gsm8k": 6.825117631392046, "math_qa": 5.587622324625651 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.02350265352539803, "math_qa": 0.01541038525963149 } }, { "flos": 9.488482976640532e+17, "train_loss": 5.632342529296875, "eval_loss": 5.973963299313107, "eval_accuracy": 0.01733216322948662, "eval_loss_by_set": { "aqua_rat": 5.956046104431152, "gsm8k": 6.814423301003196, "math_qa": 5.5902455647786455 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.02047005307050796, "math_qa": 0.01507537688442211 } }, { "flos": 9.547377989491098e+17, "train_loss": 5.642298583984375, "eval_loss": 5.952676773071289, "eval_accuracy": 0.020184291355857833, "eval_loss_by_set": { "aqua_rat": 5.962174415588379, "gsm8k": 6.799351085316051, "math_qa": 5.563826243082683 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.017437452615617893, "math_qa": 0.019765494137353432 } }, { "flos": 9.607126176120177e+17, "train_loss": 5.6361376953125, "eval_loss": 5.968116579829036, "eval_accuracy": 0.020184291355857833, "eval_loss_by_set": { "aqua_rat": 5.96281099319458, "gsm8k": 6.826850891113281, "math_qa": 5.574972152709961 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.02047005307050796, "math_qa": 0.018090452261306532 } }, { "flos": 9.66705736056832e+17, "train_loss": 5.63875732421875, "eval_loss": 5.9605829135791675, "eval_accuracy": 0.017112768758227294, "eval_loss_by_set": { "aqua_rat": 5.946019649505615, "gsm8k": 6.798637390136719, "math_qa": 5.577688217163086 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.01819560272934041, "math_qa": 0.01541038525963149 } }, { "flos": 9.727410606083932e+17, "train_loss": 5.64510986328125, "eval_loss": 5.968393506230535, "eval_accuracy": 0.017770952172005264, "eval_loss_by_set": { "aqua_rat": 5.963318347930908, "gsm8k": 6.797443043101918, "math_qa": 5.58883539835612 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.018953752843062926, "math_qa": 0.01541038525963149 } }, { "flos": 9.787042361518326e+17, "train_loss": 5.646268920898438, "eval_loss": 5.975068659395785, "eval_accuracy": 0.01908731899956121, "eval_loss_by_set": { "aqua_rat": 5.955220699310303, "gsm8k": 6.8139801025390625, "math_qa": 5.592221577962239 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.022744503411675512, "math_qa": 0.01541038525963149 } }, { "flos": 9.847127901722378e+17, "train_loss": 5.63760498046875, "eval_loss": 5.974220069679054, "eval_accuracy": 0.023255813953488372, "eval_loss_by_set": { "aqua_rat": 5.9598846435546875, "gsm8k": 6.803644353693182, "math_qa": 5.595261891682942 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.02577710386656558, "math_qa": 0.021105527638190954 } }, { "flos": 9.90683013220139e+17, "train_loss": 5.63095458984375, "eval_loss": 5.976033597379117, "eval_accuracy": 0.022378236068451074, "eval_loss_by_set": { "aqua_rat": 5.9621429443359375, "gsm8k": 6.823012612082741, "math_qa": 5.588992436726888 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.02577710386656558, "math_qa": 0.019430485762144054 } }, { "flos": 9.967202334628905e+17, "train_loss": 5.64400390625, "eval_loss": 5.982437649288693, "eval_accuracy": 0.019745502413339184, "eval_loss_by_set": { "aqua_rat": 5.977022171020508, "gsm8k": 6.829305475408381, "math_qa": 5.594741185506185 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.02350265352539803, "math_qa": 0.01742043551088777 } }, { "flos": 1.0026517550973583e+18, "train_loss": 5.630194091796875, "eval_loss": 5.990989221108927, "eval_accuracy": 0.02215884159719175, "eval_loss_by_set": { "aqua_rat": 5.9625654220581055, "gsm8k": 6.831480546431108, "math_qa": 5.608132680257161 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.021986353297952996, "math_qa": 0.021105527638190954 } }, { "flos": 1.0086343020170445e+18, "train_loss": 5.640753173828125, "eval_loss": 5.979552191656989, "eval_accuracy": 0.018429135585783237, "eval_loss_by_set": { "aqua_rat": 5.9655609130859375, "gsm8k": 6.834071072665128, "math_qa": 5.58906364440918 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.02122820318423048, "math_qa": 0.01641541038525963 } }, { "flos": 1.0145661532902523e+18, "train_loss": 5.629281005859375, "eval_loss": 5.982133349856815, "eval_accuracy": 0.01996489688459851, "eval_loss_by_set": { "aqua_rat": 5.968768119812012, "gsm8k": 6.826296719637784, "math_qa": 5.5963389078776045 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.02577710386656558, "math_qa": 0.01407035175879397 } }, { "flos": 1.0205595600347464e+18, "train_loss": 5.644408569335938, "eval_loss": 5.977991516525681, "eval_accuracy": 0.018209741114523913, "eval_loss_by_set": { "aqua_rat": 5.9655656814575195, "gsm8k": 6.819319985129616, "math_qa": 5.593418121337891 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.021986353297952996, "math_qa": 0.01507537688442211 } }, { "flos": 1.0265130080141312e+18, "train_loss": 5.627467651367187, "eval_loss": 5.975303830327214, "eval_accuracy": 0.019306713470820535, "eval_loss_by_set": { "aqua_rat": 5.966655254364014, "gsm8k": 6.831919583407315, "math_qa": 5.5834089914957685 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.01819560272934041, "math_qa": 0.018760469011725293 } }, { "flos": 1.0324525247302205e+18, "train_loss": 5.616495361328125, "eval_loss": 5.972254211838181, "eval_accuracy": 0.02106186924089513, "eval_loss_by_set": { "aqua_rat": 5.956334114074707, "gsm8k": 6.817974437366832, "math_qa": 5.585959116617839 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.028051554207733132, "math_qa": 0.01641541038525963 } }, { "flos": 1.0383874871703634e+18, "train_loss": 5.62794189453125, "eval_loss": 5.975507401131295, "eval_accuracy": 0.020842474769635806, "eval_loss_by_set": { "aqua_rat": 5.964291095733643, "gsm8k": 6.814110495827415, "math_qa": 5.592082341512044 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.018953752843062926, "math_qa": 0.019095477386934675 } }, { "flos": 1.044342193038295e+18, "train_loss": 5.637259521484375, "eval_loss": 5.977113156705289, "eval_accuracy": 0.023255813953488372, "eval_loss_by_set": { "aqua_rat": 5.962053298950195, "gsm8k": 6.813558405095881, "math_qa": 5.594997406005859 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.02577710386656558, "math_qa": 0.021440536013400336 } }, { "flos": 1.0503275220230472e+18, "train_loss": 5.639046630859375, "eval_loss": 5.973440866212587, "eval_accuracy": 0.01689337428696797, "eval_loss_by_set": { "aqua_rat": 5.975658893585205, "gsm8k": 6.8119423606178975, "math_qa": 5.588942845662435 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.02047005307050796, "math_qa": 0.01440536013400335 } }, { "flos": 1.0563159423105106e+18, "train_loss": 5.629716796875, "eval_loss": 5.9662663227802994, "eval_accuracy": 0.018209741114523913, "eval_loss_by_set": { "aqua_rat": 5.956703186035156, "gsm8k": 6.803509105335582, "math_qa": 5.583326975504558 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.019711902956785442, "math_qa": 0.016080402010050253 } }, { "flos": 1.0622796740522148e+18, "train_loss": 5.627310791015625, "eval_loss": 5.963151055413324, "eval_accuracy": 0.02106186924089513, "eval_loss_by_set": { "aqua_rat": 5.963592529296875, "gsm8k": 6.818608370694247, "math_qa": 5.5710296630859375 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.02350265352539803, "math_qa": 0.018090452261306532 } }, { "flos": 1.068239757756072e+18, "train_loss": 5.634095458984375, "eval_loss": 5.973144273500185, "eval_accuracy": 0.021939447125932425, "eval_loss_by_set": { "aqua_rat": 5.965510368347168, "gsm8k": 6.821193348277699, "math_qa": 5.585091272989909 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.02047005307050796, "math_qa": 0.021775544388609715 } }, { "flos": 1.07420153152956e+18, "train_loss": 5.61652587890625, "eval_loss": 5.980669279356261, "eval_accuracy": 0.020184291355857833, "eval_loss_by_set": { "aqua_rat": 5.975893020629883, "gsm8k": 6.839742487127131, "math_qa": 5.58732541402181 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.02122820318423048, "math_qa": 0.018425460636515914 } }, { "flos": 1.0801536400160195e+18, "train_loss": 5.620340576171875, "eval_loss": 5.980249044057485, "eval_accuracy": 0.020184291355857833, "eval_loss_by_set": { "aqua_rat": 5.945611953735352, "gsm8k": 6.810011430220171, "math_qa": 5.602827707926433 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.02350265352539803, "math_qa": 0.018090452261306532 } }, { "flos": 1.0860764235395236e+18, "train_loss": 5.623882446289063, "eval_loss": 5.990095628274454, "eval_accuracy": 0.01952610794207986, "eval_loss_by_set": { "aqua_rat": 5.959866046905518, "gsm8k": 6.842754017223012, "math_qa": 5.601812998453776 }, "eval_accuracy_by_set": { "aqua_rat": 0.011811023622047244, "gsm8k": 0.022744503411675512, "math_qa": 0.018760469011725293 } }, { "flos": 1.092096311978623e+18, "train_loss": 5.63265380859375, "eval_loss": 5.979169587831239, "eval_accuracy": 0.018867924528301886, "eval_loss_by_set": { "aqua_rat": 5.968378067016602, "gsm8k": 6.83369237726385, "math_qa": 5.588412602742513 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.019711902956785442, "math_qa": 0.01675041876046901 } }, { "flos": 1.0980396211508347e+18, "train_loss": 5.631455078125, "eval_loss": 5.982901985580857, "eval_accuracy": 0.01908731899956121, "eval_loss_by_set": { "aqua_rat": 5.976430416107178, "gsm8k": 6.838199268687855, "math_qa": 5.591430028279622 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.022744503411675512, "math_qa": 0.01641541038525963 } }, { "flos": 1.1040098855377961e+18, "train_loss": 5.638499755859375, "eval_loss": 5.975711667859876, "eval_accuracy": 0.019306713470820535, "eval_loss_by_set": { "aqua_rat": 5.965109825134277, "gsm8k": 6.825148148970171, "math_qa": 5.587270100911458 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.024260803639120546, "math_qa": 0.017085427135678392 } }, { "flos": 1.1099729988042097e+18, "train_loss": 5.6255615234375, "eval_loss": 5.987591227969608, "eval_accuracy": 0.01996489688459851, "eval_loss_by_set": { "aqua_rat": 5.965315341949463, "gsm8k": 6.836298162286932, "math_qa": 5.600456873575847 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.024260803639120546, "math_qa": 0.01675041876046901 } }, { "flos": 1.1158985439916851e+18, "train_loss": 5.623702392578125, "eval_loss": 5.985566061896247, "eval_accuracy": 0.021281263712154455, "eval_loss_by_set": { "aqua_rat": 5.965092658996582, "gsm8k": 6.826340415261009, "math_qa": 5.601917266845703 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.024260803639120546, "math_qa": 0.019095477386934675 } }, { "flos": 1.1219143108727931e+18, "train_loss": 5.634583740234375, "eval_loss": 5.993282369665198, "eval_accuracy": 0.02369460289600702, "eval_loss_by_set": { "aqua_rat": 5.983023643493652, "gsm8k": 6.838174993341619, "math_qa": 5.606894810994466 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.02577710386656558, "math_qa": 0.021775544388609715 } }, { "flos": 1.1278709741720699e+18, "train_loss": 5.627092895507812, "eval_loss": 5.9688321706411, "eval_accuracy": 0.0225976305397104, "eval_loss_by_set": { "aqua_rat": 5.968805313110352, "gsm8k": 6.816411798650568, "math_qa": 5.580360412597656 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.022744503411675512, "math_qa": 0.021440536013400336 } }, { "flos": 1.1337920472248484e+18, "train_loss": 5.62124267578125, "eval_loss": 5.990839081841546, "eval_accuracy": 0.022817025010969723, "eval_loss_by_set": { "aqua_rat": 5.974462985992432, "gsm8k": 6.822929382324219, "math_qa": 5.610829035441081 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.02122820318423048, "math_qa": 0.021775544388609715 } }, { "flos": 1.1397776650461512e+18, "train_loss": 5.629730224609375, "eval_loss": 5.970034135354532, "eval_accuracy": 0.023255813953488372, "eval_loss_by_set": { "aqua_rat": 5.963659763336182, "gsm8k": 6.8288796164772725, "math_qa": 5.576927820841472 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.026535253980288095, "math_qa": 0.021105527638190954 } }, { "flos": 1.1457397689952502e+18, "train_loss": 5.623486328125, "eval_loss": 5.972579981829669, "eval_accuracy": 0.02413339183852567, "eval_loss_by_set": { "aqua_rat": 5.975708484649658, "gsm8k": 6.817176125266335, "math_qa": 5.585212707519531 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.019711902956785442, "math_qa": 0.022780569514237858 } }, { "flos": 1.1517232017519411e+18, "train_loss": 5.62552734375, "eval_loss": 5.973921234543259, "eval_accuracy": 0.020184291355857833, "eval_loss_by_set": { "aqua_rat": 5.971835136413574, "gsm8k": 6.8138580322265625, "math_qa": 5.589124043782552 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.018953752843062926, "math_qa": 0.018425460636515914 } }, { "flos": 1.1576407507840532e+18, "train_loss": 5.609715576171875, "eval_loss": 5.982013186892948, "eval_accuracy": 0.022378236068451074, "eval_loss_by_set": { "aqua_rat": 5.975471496582031, "gsm8k": 6.832106156782671, "math_qa": 5.592932383219401 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.017437452615617893, "math_qa": 0.023115577889447236 } }, { "flos": 1.1635350125034865e+18, "train_loss": 5.611422119140625, "eval_loss": 5.97578443063272, "eval_accuracy": 0.02369460289600702, "eval_loss_by_set": { "aqua_rat": 5.9579949378967285, "gsm8k": 6.818050037730824, "math_qa": 5.591228485107422 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.027293404094010616, "math_qa": 0.020435510887772193 } }, { "flos": 1.1694526028746588e+18, "train_loss": 5.628419799804687, "eval_loss": 5.976820481790079, "eval_accuracy": 0.023475208424747696, "eval_loss_by_set": { "aqua_rat": 5.979416370391846, "gsm8k": 6.821604642001065, "math_qa": 5.5894114176432295 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.02577710386656558, "math_qa": 0.019430485762144054 } }, { "flos": 1.1754777462062449e+18, "train_loss": 5.6188720703125, "eval_loss": 5.989399265598607, "eval_accuracy": 0.02215884159719175, "eval_loss_by_set": { "aqua_rat": 5.972560882568359, "gsm8k": 6.822445262562145, "math_qa": 5.608989715576172 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.018953752843062926, "math_qa": 0.021105527638190954 } }, { "flos": 1.1814077629915464e+18, "train_loss": 5.6115869140625, "eval_loss": 5.995227349771036, "eval_accuracy": 0.0225976305397104, "eval_loss_by_set": { "aqua_rat": 5.973511695861816, "gsm8k": 6.84526894309304, "math_qa": 5.607434590657552 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.02350265352539803, "math_qa": 0.019430485762144054 } }, { "flos": 1.1873635399169475e+18, "train_loss": 5.61710693359375, "eval_loss": 5.987927978103225, "eval_accuracy": 0.023036419482229047, "eval_loss_by_set": { "aqua_rat": 5.996493339538574, "gsm8k": 6.855969515713778, "math_qa": 5.589361826578776 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.02047005307050796, "math_qa": 0.022445561139028476 } }, { "flos": 1.1933212952116593e+18, "train_loss": 5.621068725585937, "eval_loss": 5.982445227133261, "eval_accuracy": 0.024352786309784994, "eval_loss_by_set": { "aqua_rat": 5.976864814758301, "gsm8k": 6.833835948597301, "math_qa": 5.592689514160156 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.019711902956785442, "math_qa": 0.024120603015075376 } }, { "flos": 1.1993345892653466e+18, "train_loss": 5.621685180664063, "eval_loss": 5.9833896482313005, "eval_accuracy": 0.024791575252303643, "eval_loss_by_set": { "aqua_rat": 5.975797176361084, "gsm8k": 6.852702747691762, "math_qa": 5.58558718363444 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.021986353297952996, "math_qa": 0.022780569514237858 } }, { "flos": 1.20530843995e+18, "train_loss": 5.621856689453125, "eval_loss": 5.971965377395217, "eval_accuracy": 0.018429135585783237, "eval_loss_by_set": { "aqua_rat": 5.95799446105957, "gsm8k": 6.822936318137429, "math_qa": 5.583101272583008 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.017437452615617893, "math_qa": 0.017085427135678392 } }, { "flos": 1.2112560150984786e+18, "train_loss": 5.621129150390625, "eval_loss": 5.980907002010861, "eval_accuracy": 0.020403685827117157, "eval_loss_by_set": { "aqua_rat": 5.972257137298584, "gsm8k": 6.838646628639915, "math_qa": 5.588497161865234 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.016679302501895376, "math_qa": 0.020770519262981575 } }, { "flos": 1.217193615722283e+18, "train_loss": 5.611815185546875, "eval_loss": 5.975696950345426, "eval_accuracy": 0.02150065818341378, "eval_loss_by_set": { "aqua_rat": 5.971993923187256, "gsm8k": 6.820753617720171, "math_qa": 5.588687896728516 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.019711902956785442, "math_qa": 0.019430485762144054 } }, { "flos": 1.2232116498092524e+18, "train_loss": 5.626792602539062, "eval_loss": 6.000604681066565, "eval_accuracy": 0.01996489688459851, "eval_loss_by_set": { "aqua_rat": 5.97462272644043, "gsm8k": 6.85050478848544, "math_qa": 5.613232294718425 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.019711902956785442, "math_qa": 0.018090452261306532 } }, { "flos": 1.229171589631705e+18, "train_loss": 5.613175659179688, "eval_loss": 5.9846474415547135, "eval_accuracy": 0.023475208424747696, "eval_loss_by_set": { "aqua_rat": 5.971604347229004, "gsm8k": 6.832277471368963, "math_qa": 5.597237269083659 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.018953752843062926, "math_qa": 0.022445561139028476 } }, { "flos": 1.235121266629804e+18, "train_loss": 5.618433837890625, "eval_loss": 5.981061548800082, "eval_accuracy": 0.020403685827117157, "eval_loss_by_set": { "aqua_rat": 5.971999645233154, "gsm8k": 6.81745008988814, "math_qa": 5.598471959431966 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.019711902956785442, "math_qa": 0.018425460636515914 } }, { "flos": 1.24109019152384e+18, "train_loss": 5.62496826171875, "eval_loss": 5.985936345280828, "eval_accuracy": 0.020842474769635806, "eval_loss_by_set": { "aqua_rat": 5.984661102294922, "gsm8k": 6.85007754239169, "math_qa": 5.589977900187175 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.02047005307050796, "math_qa": 0.020770519262981575 } }, { "flos": 1.2471185088362578e+18, "train_loss": 5.62529541015625, "eval_loss": 5.994754791259766, "eval_accuracy": 0.017990346643264588, "eval_loss_by_set": { "aqua_rat": 5.980295181274414, "gsm8k": 6.839663418856534, "math_qa": 5.608709971110026 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.016679302501895376, "math_qa": 0.01641541038525963 } }, { "flos": 1.253124177712382e+18, "train_loss": 5.615114135742187, "eval_loss": 5.99805785514213, "eval_accuracy": 0.0225976305397104, "eval_loss_by_set": { "aqua_rat": 5.978390693664551, "gsm8k": 6.865124789151278, "math_qa": 5.602291107177734 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.018953752843062926, "math_qa": 0.024120603015075376 } }, { "flos": 1.2590455390648402e+18, "train_loss": 5.61211669921875, "eval_loss": 5.99041443902093, "eval_accuracy": 0.022378236068451074, "eval_loss_by_set": { "aqua_rat": 5.986176490783691, "gsm8k": 6.84267148104581, "math_qa": 5.600149790445964 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.019711902956785442, "math_qa": 0.021105527638190954 } }, { "flos": 1.265028807539032e+18, "train_loss": 5.612462768554687, "eval_loss": 5.99615478515625, "eval_accuracy": 0.024791575252303643, "eval_loss_by_set": { "aqua_rat": 5.981178283691406, "gsm8k": 6.83338095925071, "math_qa": 5.613674163818359 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.02047005307050796, "math_qa": 0.02579564489112228 } }, { "flos": 1.2709985774678835e+18, "train_loss": 5.611728515625, "eval_loss": 6.000202282055004, "eval_accuracy": 0.02150065818341378, "eval_loss_by_set": { "aqua_rat": 5.989971160888672, "gsm8k": 6.847285877574574, "math_qa": 5.6128082275390625 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.022744503411675512, "math_qa": 0.019765494137353432 } }, { "flos": 1.276969336312955e+18, "train_loss": 5.61741455078125, "eval_loss": 5.978246740392737, "eval_accuracy": 0.02632733655111891, "eval_loss_by_set": { "aqua_rat": 5.974876403808594, "gsm8k": 6.842858054421165, "math_qa": 5.582247416178386 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.025018953752843062, "math_qa": 0.024790619765494137 } }, { "flos": 1.2829163552631685e+18, "train_loss": 5.6188916015625, "eval_loss": 5.983481020540805, "eval_accuracy": 0.01952610794207986, "eval_loss_by_set": { "aqua_rat": 5.979162216186523, "gsm8k": 6.840266141024503, "math_qa": 5.591147740681966 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.02047005307050796, "math_qa": 0.017085427135678392 } }, { "flos": 1.2888858776945295e+18, "train_loss": 5.611021728515625, "eval_loss": 5.9916256569527295, "eval_accuracy": 0.0225976305397104, "eval_loss_by_set": { "aqua_rat": 5.977780342102051, "gsm8k": 6.845148259943182, "math_qa": 5.601581573486328 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.026535253980288095, "math_qa": 0.019095477386934675 } }, { "flos": 1.2948266727002604e+18, "train_loss": 5.611514892578125, "eval_loss": 5.985512553034602, "eval_accuracy": 0.02457218078104432, "eval_loss_by_set": { "aqua_rat": 5.9759321212768555, "gsm8k": 6.824726451526988, "math_qa": 5.60167121887207 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.02577710386656558, "math_qa": 0.022445561139028476 } }, { "flos": 1.3007816255288115e+18, "train_loss": 5.613795776367187, "eval_loss": 6.010296718494312, "eval_accuracy": 0.023036419482229047, "eval_loss_by_set": { "aqua_rat": 5.992880344390869, "gsm8k": 6.872419877485796, "math_qa": 5.616608301798503 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.02350265352539803, "math_qa": 0.021105527638190954 } }, { "flos": 1.3067800611431383e+18, "train_loss": 5.61179931640625, "eval_loss": 5.988352131199193, "eval_accuracy": 0.020842474769635806, "eval_loss_by_set": { "aqua_rat": 5.973265647888184, "gsm8k": 6.826532537286932, "math_qa": 5.6054433186848955 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.017437452615617893, "math_qa": 0.020435510887772193 } }, { "flos": 1.3127192691584532e+18, "train_loss": 5.60788818359375, "eval_loss": 5.990222466958536, "eval_accuracy": 0.023255813953488372, "eval_loss_by_set": { "aqua_rat": 5.982701301574707, "gsm8k": 6.834365151145241, "math_qa": 5.603950500488281 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.02047005307050796, "math_qa": 0.022110552763819097 } }, { "flos": 1.3186634233654804e+18, "train_loss": 5.61055419921875, "eval_loss": 5.988555341153531, "eval_accuracy": 0.025010969723562967, "eval_loss_by_set": { "aqua_rat": 5.984749794006348, "gsm8k": 6.822424455122515, "math_qa": 5.606682459513347 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.021986353297952996, "math_qa": 0.023785594639865997 } }, { "flos": 1.3246414981504696e+18, "train_loss": 5.615233154296875, "eval_loss": 5.99818466805123, "eval_accuracy": 0.02457218078104432, "eval_loss_by_set": { "aqua_rat": 5.987885475158691, "gsm8k": 6.865162242542613, "math_qa": 5.601678212483724 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.02047005307050796, "math_qa": 0.02579564489112228 } }, { "flos": 1.3305974608332063e+18, "train_loss": 5.619163208007812, "eval_loss": 5.99282625559214, "eval_accuracy": 0.023036419482229047, "eval_loss_by_set": { "aqua_rat": 5.9901838302612305, "gsm8k": 6.845642783425071, "math_qa": 5.602172215779622 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.019711902956785442, "math_qa": 0.021775544388609715 } }, { "flos": 1.3365745053629153e+18, "train_loss": 5.612196655273437, "eval_loss": 5.9947749730702995, "eval_accuracy": 0.0225976305397104, "eval_loss_by_set": { "aqua_rat": 5.978063106536865, "gsm8k": 6.85116923939098, "math_qa": 5.60365358988444 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.02577710386656558, "math_qa": 0.019765494137353432 } }, { "flos": 1.342545243270021e+18, "train_loss": 5.608642578125, "eval_loss": 6.007130236239047, "eval_accuracy": 0.02150065818341378, "eval_loss_by_set": { "aqua_rat": 6.001011848449707, "gsm8k": 6.863060691139915, "math_qa": 5.615338643391927 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.01592115238817286, "math_qa": 0.022110552763819097 } }, { "flos": 1.348518866858279e+18, "train_loss": 5.614238891601563, "eval_loss": 5.9923304995974975, "eval_accuracy": 0.022378236068451074, "eval_loss_by_set": { "aqua_rat": 5.978361129760742, "gsm8k": 6.82825400612571, "math_qa": 5.610363006591797 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.019711902956785442, "math_qa": 0.021775544388609715 } }, { "flos": 1.354520723414057e+18, "train_loss": 5.6135986328125, "eval_loss": 5.996352118414801, "eval_accuracy": 0.02215884159719175, "eval_loss_by_set": { "aqua_rat": 5.989955902099609, "gsm8k": 6.849384654651988, "math_qa": 5.60591189066569 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.025018953752843062, "math_qa": 0.019095477386934675 } }, { "flos": 1.3604631048733327e+18, "train_loss": 5.609867553710938, "eval_loss": 5.9924459972897095, "eval_accuracy": 0.0217200526546731, "eval_loss_by_set": { "aqua_rat": 5.97857141494751, "gsm8k": 6.861475857821378, "math_qa": 5.595296859741211 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.02577710386656558, "math_qa": 0.018760469011725293 } }, { "flos": 1.366471226175783e+18, "train_loss": 5.611605224609375, "eval_loss": 6.004195419517723, "eval_accuracy": 0.02413339183852567, "eval_loss_by_set": { "aqua_rat": 6.009328365325928, "gsm8k": 6.883630232377485, "math_qa": 5.600693384806315 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.027293404094010616, "math_qa": 0.019765494137353432 } }, { "flos": 1.372438564079403e+18, "train_loss": 5.6187286376953125, "eval_loss": 5.997408377157675, "eval_accuracy": 0.021939447125932425, "eval_loss_by_set": { "aqua_rat": 5.983915328979492, "gsm8k": 6.865617231889204, "math_qa": 5.600603739420573 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.02350265352539803, "math_qa": 0.018760469011725293 } }, { "flos": 1.3784302399520768e+18, "train_loss": 5.6147900390625, "eval_loss": 6.0083505269643425, "eval_accuracy": 0.02413339183852567, "eval_loss_by_set": { "aqua_rat": 6.005581855773926, "gsm8k": 6.8841025612571025, "math_qa": 5.607194900512695 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.024260803639120546, "math_qa": 0.023115577889447236 } }, { "flos": 1.3843525080795054e+18, "train_loss": 5.602310791015625, "eval_loss": 5.992822518219819, "eval_accuracy": 0.023913997367266345, "eval_loss_by_set": { "aqua_rat": 5.991186618804932, "gsm8k": 6.86542441628196, "math_qa": 5.593016306559245 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.028051554207733132, "math_qa": 0.021105527638190954 } }, { "flos": 1.3902980012425871e+18, "train_loss": 5.60830322265625, "eval_loss": 5.980817897899731, "eval_accuracy": 0.022817025010969723, "eval_loss_by_set": { "aqua_rat": 5.983799934387207, "gsm8k": 6.832437688654119, "math_qa": 5.590243657430013 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.027293404094010616, "math_qa": 0.019765494137353432 } }, { "flos": 1.396257384329904e+18, "train_loss": 5.596536865234375, "eval_loss": 6.003949474644017, "eval_accuracy": 0.02106186924089513, "eval_loss_by_set": { "aqua_rat": 5.999998569488525, "gsm8k": 6.853933160955256, "math_qa": 5.614702860514323 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.02047005307050796, "math_qa": 0.021440536013400336 } }, { "flos": 1.402208874341073e+18, "train_loss": 5.602060546875, "eval_loss": 5.989880304078798, "eval_accuracy": 0.02215884159719175, "eval_loss_by_set": { "aqua_rat": 5.983123302459717, "gsm8k": 6.821182944557884, "math_qa": 5.609429677327474 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.01819560272934041, "math_qa": 0.020770519262981575 } }, { "flos": 1.4081427447857807e+18, "train_loss": 5.6012353515625, "eval_loss": 5.992562422881255, "eval_accuracy": 0.023475208424747696, "eval_loss_by_set": { "aqua_rat": 5.994690895080566, "gsm8k": 6.853673761541193, "math_qa": 5.597709019978841 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.028051554207733132, "math_qa": 0.020435510887772193 } }, { "flos": 1.4140213653080637e+18, "train_loss": 5.589249267578125, "eval_loss": 5.998706095927471, "eval_accuracy": 0.020403685827117157, "eval_loss_by_set": { "aqua_rat": 5.995689392089844, "gsm8k": 6.858042630282315, "math_qa": 5.605094909667969 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.018953752843062926, "math_qa": 0.020100502512562814 } }, { "flos": 1.420011928784208e+18, "train_loss": 5.6038580322265625, "eval_loss": 5.993809596912281, "eval_accuracy": 0.019306713470820535, "eval_loss_by_set": { "aqua_rat": 5.9848198890686035, "gsm8k": 6.855242642489347, "math_qa": 5.599735260009766 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.018953752843062926, "math_qa": 0.019430485762144054 } }, { "flos": 1.425968735964889e+18, "train_loss": 5.60458984375, "eval_loss": 6.003415494351773, "eval_accuracy": 0.02150065818341378, "eval_loss_by_set": { "aqua_rat": 6.005588531494141, "gsm8k": 6.86383680863814, "math_qa": 5.608874638875325 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.024260803639120546, "math_qa": 0.018090452261306532 } }, { "flos": 1.431899659525161e+18, "train_loss": 5.603374633789063, "eval_loss": 6.002527236938477, "eval_accuracy": 0.023255813953488372, "eval_loss_by_set": { "aqua_rat": 5.989041328430176, "gsm8k": 6.869596307927912, "math_qa": 5.606244405110677 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.022744503411675512, "math_qa": 0.022780569514237858 } }, { "flos": 1.4378686053571625e+18, "train_loss": 5.607548828125, "eval_loss": 6.009455371547389, "eval_accuracy": 0.023913997367266345, "eval_loss_by_set": { "aqua_rat": 6.003621578216553, "gsm8k": 6.87792275168679, "math_qa": 5.611893971761067 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.028051554207733132, "math_qa": 0.021105527638190954 } }, { "flos": 1.4437854532358636e+18, "train_loss": 5.597901611328125, "eval_loss": 5.997644115138698, "eval_accuracy": 0.02106186924089513, "eval_loss_by_set": { "aqua_rat": 5.988615989685059, "gsm8k": 6.860128922895952, "math_qa": 5.603090922037761 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.025018953752843062, "math_qa": 0.017085427135678392 } }, { "flos": 1.4496713891611935e+18, "train_loss": 5.597880859375, "eval_loss": 6.000987491092166, "eval_accuracy": 0.02215884159719175, "eval_loss_by_set": { "aqua_rat": 5.986728668212891, "gsm8k": 6.869129527698863, "math_qa": 5.60427729288737 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.02350265352539803, "math_qa": 0.021775544388609715 } }, { "flos": 1.4556176242798756e+18, "train_loss": 5.607899780273438, "eval_loss": 5.997611612886996, "eval_accuracy": 0.019306713470820535, "eval_loss_by_set": { "aqua_rat": 5.996250629425049, "gsm8k": 6.858126553622159, "math_qa": 5.603322347005208 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.019711902956785442, "math_qa": 0.019095477386934675 } }, { "flos": 1.4616293726822072e+18, "train_loss": 5.60853515625, "eval_loss": 6.0155238589724975, "eval_accuracy": 0.019745502413339184, "eval_loss_by_set": { "aqua_rat": 6.000143051147461, "gsm8k": 6.870070023970171, "math_qa": 5.625138600667317 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.021986353297952996, "math_qa": 0.01675041876046901 } }, { "flos": 1.4676403587278438e+18, "train_loss": 5.610443115234375, "eval_loss": 5.998524949357316, "eval_accuracy": 0.02106186924089513, "eval_loss_by_set": { "aqua_rat": 5.99449348449707, "gsm8k": 6.852299083362926, "math_qa": 5.607547760009766 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.02350265352539803, "math_qa": 0.019765494137353432 } }, { "flos": 1.473605347284353e+18, "train_loss": 5.606019287109375, "eval_loss": 5.997327185965873, "eval_accuracy": 0.019306713470820535, "eval_loss_by_set": { "aqua_rat": 5.985487937927246, "gsm8k": 6.844256314364347, "math_qa": 5.610137939453125 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.022744503411675512, "math_qa": 0.01574539363484087 } }, { "flos": 1.4796169926074696e+18, "train_loss": 5.614207153320312, "eval_loss": 5.997540293513118, "eval_accuracy": 0.019306713470820535, "eval_loss_by_set": { "aqua_rat": 5.983395576477051, "gsm8k": 6.852125688032671, "math_qa": 5.607034047444661 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.02047005307050796, "math_qa": 0.017755443886097153 } }, { "flos": 1.485576788011647e+18, "train_loss": 5.614270629882813, "eval_loss": 6.016230737840807, "eval_accuracy": 0.019745502413339184, "eval_loss_by_set": { "aqua_rat": 6.002405643463135, "gsm8k": 6.885638843883168, "math_qa": 5.618904113769531 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.018953752843062926, "math_qa": 0.018090452261306532 } }, { "flos": 1.4915858778292224e+18, "train_loss": 5.60620361328125, "eval_loss": 6.005192292703165, "eval_accuracy": 0.023913997367266345, "eval_loss_by_set": { "aqua_rat": 5.991916179656982, "gsm8k": 6.866252552379262, "math_qa": 5.611646016438802 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.022744503411675512, "math_qa": 0.023115577889447236 } }, { "flos": 1.497602098366251e+18, "train_loss": 5.611807861328125, "eval_loss": 5.999738048862767, "eval_accuracy": 0.022817025010969723, "eval_loss_by_set": { "aqua_rat": 5.991407871246338, "gsm8k": 6.870262839577415, "math_qa": 5.601441701253255 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.02122820318423048, "math_qa": 0.022445561139028476 } }, { "flos": 1.5035765052491694e+18, "train_loss": 5.59845947265625, "eval_loss": 6.003845446818584, "eval_accuracy": 0.02150065818341378, "eval_loss_by_set": { "aqua_rat": 5.995823383331299, "gsm8k": 6.86279296875, "math_qa": 5.610829671223958 }, "eval_accuracy_by_set": { "aqua_rat": 0.015748031496062992, "gsm8k": 0.018953752843062926, "math_qa": 0.023115577889447236 } }, { "flos": 1.5095781556465172e+18, "train_loss": 5.615565185546875, "eval_loss": 6.001571913023253, "eval_accuracy": 0.020403685827117157, "eval_loss_by_set": { "aqua_rat": 5.993596076965332, "gsm8k": 6.866750543767756, "math_qa": 5.605696360270183 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.02047005307050796, "math_qa": 0.019430485762144054 } }, { "flos": 1.5155310683656028e+18, "train_loss": 5.603991088867187, "eval_loss": 5.995868476661476, "eval_accuracy": 0.025449758666081616, "eval_loss_by_set": { "aqua_rat": 5.993398666381836, "gsm8k": 6.8445892333984375, "math_qa": 5.607077280680339 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.02350265352539803, "math_qa": 0.023785594639865997 } }, { "flos": 1.5215243108275978e+18, "train_loss": 5.604806518554687, "eval_loss": 5.994349041500607, "eval_accuracy": 0.023036419482229047, "eval_loss_by_set": { "aqua_rat": 5.978629112243652, "gsm8k": 6.865312749689275, "math_qa": 5.59646733601888 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.022744503411675512, "math_qa": 0.023115577889447236 } }, { "flos": 1.5275437257465528e+18, "train_loss": 5.616377563476562, "eval_loss": 6.010704092077307, "eval_accuracy": 0.0217200526546731, "eval_loss_by_set": { "aqua_rat": 6.00557804107666, "gsm8k": 6.87514911998402, "math_qa": 5.614927291870117 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.02122820318423048, "math_qa": 0.021440536013400336 } }, { "flos": 1.533520543716737e+18, "train_loss": 5.595499267578125, "eval_loss": 6.011199976946856, "eval_accuracy": 0.022817025010969723, "eval_loss_by_set": { "aqua_rat": 6.001114368438721, "gsm8k": 6.879373723810369, "math_qa": 5.614127477010091 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.02122820318423048, "math_qa": 0.021440536013400336 } }, { "flos": 1.5395031937156383e+18, "train_loss": 5.607960815429688, "eval_loss": 5.999400345054832, "eval_accuracy": 0.02413339183852567, "eval_loss_by_set": { "aqua_rat": 6.000926494598389, "gsm8k": 6.872757651589134, "math_qa": 5.598984400431315 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.02122820318423048, "math_qa": 0.024455611390284758 } }, { "flos": 1.54546057803255e+18, "train_loss": 5.603230590820313, "eval_loss": 6.002314825315733, "eval_accuracy": 0.023255813953488372, "eval_loss_by_set": { "aqua_rat": 5.997314929962158, "gsm8k": 6.853701504794034, "math_qa": 5.612512588500977 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.021986353297952996, "math_qa": 0.022780569514237858 } }, { "flos": 1.5514256487303086e+18, "train_loss": 5.60654052734375, "eval_loss": 6.011622815518765, "eval_accuracy": 0.023475208424747696, "eval_loss_by_set": { "aqua_rat": 6.003909111022949, "gsm8k": 6.885812932794744, "math_qa": 5.611595153808594 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.018953752843062926, "math_qa": 0.023450586264656615 } }, { "flos": 1.55736805112755e+18, "train_loss": 5.6067236328125, "eval_loss": 5.999768592215873, "eval_accuracy": 0.021281263712154455, "eval_loss_by_set": { "aqua_rat": 6.001151084899902, "gsm8k": 6.847442626953125, "math_qa": 5.611136118570964 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.01819560272934041, "math_qa": 0.021105527638190954 } }, { "flos": 1.56333505939243e+18, "train_loss": 5.593788452148438, "eval_loss": 6.004177402805638, "eval_accuracy": 0.0217200526546731, "eval_loss_by_set": { "aqua_rat": 6.004558563232422, "gsm8k": 6.874105280095881, "math_qa": 5.605428695678711 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.016679302501895376, "math_qa": 0.022110552763819097 } }, { "flos": 1.5692753803411456e+18, "train_loss": 5.59174072265625, "eval_loss": 6.012149604591164, "eval_accuracy": 0.023255813953488372, "eval_loss_by_set": { "aqua_rat": 6.000982284545898, "gsm8k": 6.878523393110796, "math_qa": 5.6159922281901045 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.022744503411675512, "math_qa": 0.021440536013400336 } }, { "flos": 1.5752315486454415e+18, "train_loss": 5.603515625, "eval_loss": 5.994737161172403, "eval_accuracy": 0.023036419482229047, "eval_loss_by_set": { "aqua_rat": 5.976715087890625, "gsm8k": 6.84601454301314, "math_qa": 5.606070200602214 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.02350265352539803, "math_qa": 0.022445561139028476 } }, { "flos": 1.5811726732899123e+18, "train_loss": 5.5937957763671875, "eval_loss": 6.014976630339751, "eval_accuracy": 0.02215884159719175, "eval_loss_by_set": { "aqua_rat": 6.011732578277588, "gsm8k": 6.881580699573863, "math_qa": 5.618053436279297 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.017437452615617893, "math_qa": 0.023450586264656615 } }, { "flos": 1.5871720774193644e+18, "train_loss": 5.591842041015625, "eval_loss": 6.013897406088339, "eval_accuracy": 0.021281263712154455, "eval_loss_by_set": { "aqua_rat": 6.002127647399902, "gsm8k": 6.874268965287642, "math_qa": 5.620541254679362 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.022744503411675512, "math_qa": 0.019765494137353432 } }, { "flos": 1.5931874529215775e+18, "train_loss": 5.601514892578125, "eval_loss": 5.99501169050062, "eval_accuracy": 0.020184291355857833, "eval_loss_by_set": { "aqua_rat": 5.993554592132568, "gsm8k": 6.859079534357244, "math_qa": 5.599102020263672 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.01819560272934041, "math_qa": 0.020100502512562814 } }, { "flos": 1.599123528295121e+18, "train_loss": 5.600864868164063, "eval_loss": 6.002902984619141, "eval_accuracy": 0.023475208424747696, "eval_loss_by_set": { "aqua_rat": 5.997262954711914, "gsm8k": 6.86895751953125, "math_qa": 5.606431325276692 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.021986353297952996, "math_qa": 0.023450586264656615 } }, { "flos": 1.6050995629706445e+18, "train_loss": 5.605450439453125, "eval_loss": 6.006307808128563, "eval_accuracy": 0.019306713470820535, "eval_loss_by_set": { "aqua_rat": 5.999190330505371, "gsm8k": 6.8562143499201, "math_qa": 5.617360432942708 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.021986353297952996, "math_qa": 0.017085427135678392 } }, { "flos": 1.6110719914842522e+18, "train_loss": 5.60101806640625, "eval_loss": 6.002187496907002, "eval_accuracy": 0.023913997367266345, "eval_loss_by_set": { "aqua_rat": 6.012125492095947, "gsm8k": 6.8521575927734375, "math_qa": 5.611789703369141 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.02350265352539803, "math_qa": 0.020435510887772193 } }, { "flos": 1.6170080051176407e+18, "train_loss": 5.5990673828125, "eval_loss": 6.007883974023767, "eval_accuracy": 0.02215884159719175, "eval_loss_by_set": { "aqua_rat": 5.9957451820373535, "gsm8k": 6.875883622602983, "math_qa": 5.611062367757161 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.019711902956785442, "math_qa": 0.021775544388609715 } }, { "flos": 1.6229739621892751e+18, "train_loss": 5.606005859375, "eval_loss": 5.995098681063266, "eval_accuracy": 0.023255813953488372, "eval_loss_by_set": { "aqua_rat": 6.005257606506348, "gsm8k": 6.8410422585227275, "math_qa": 5.606527964274089 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.02047005307050796, "math_qa": 0.022780569514237858 } }, { "flos": 1.6289213719815127e+18, "train_loss": 5.5933837890625, "eval_loss": 5.999098081846495, "eval_accuracy": 0.02413339183852567, "eval_loss_by_set": { "aqua_rat": 6.009105682373047, "gsm8k": 6.855842590332031, "math_qa": 5.605589548746745 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.02350265352539803, "math_qa": 0.021440536013400336 } }, { "flos": 1.63489540734976e+18, "train_loss": 5.60164794921875, "eval_loss": 6.0007340714738175, "eval_accuracy": 0.023036419482229047, "eval_loss_by_set": { "aqua_rat": 5.990833282470703, "gsm8k": 6.874110135165128, "math_qa": 5.6012617746988935 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.02047005307050796, "math_qa": 0.022445561139028476 } }, { "flos": 1.6407855480480727e+18, "train_loss": 5.586175537109375, "eval_loss": 5.995327820649019, "eval_accuracy": 0.020623080298376482, "eval_loss_by_set": { "aqua_rat": 5.982263565063477, "gsm8k": 6.860857183283025, "math_qa": 5.59971555074056 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.021986353297952996, "math_qa": 0.018760469011725293 } }, { "flos": 1.6467309800078705e+18, "train_loss": 5.604068603515625, "eval_loss": 6.008343645044275, "eval_accuracy": 0.02106186924089513, "eval_loss_by_set": { "aqua_rat": 5.998782634735107, "gsm8k": 6.860264864834872, "math_qa": 5.618676503499349 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.018953752843062926, "math_qa": 0.020100502512562814 } }, { "flos": 1.6527083541763195e+18, "train_loss": 5.595689697265625, "eval_loss": 6.015870068524335, "eval_accuracy": 0.02106186924089513, "eval_loss_by_set": { "aqua_rat": 5.996015548706055, "gsm8k": 6.893164201216265, "math_qa": 5.615431467692058 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.02350265352539803, "math_qa": 0.019430485762144054 } }, { "flos": 1.6586780419639214e+18, "train_loss": 5.598004150390625, "eval_loss": 6.018563038594014, "eval_accuracy": 0.023913997367266345, "eval_loss_by_set": { "aqua_rat": 6.001169204711914, "gsm8k": 6.878936767578125, "math_qa": 5.625674565633138 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.022744503411675512, "math_qa": 0.022780569514237858 } }, { "flos": 1.6646703363118858e+18, "train_loss": 5.598292846679687, "eval_loss": 6.022036294679384, "eval_accuracy": 0.02215884159719175, "eval_loss_by_set": { "aqua_rat": 6.009500980377197, "gsm8k": 6.887939453125, "math_qa": 5.626208623250325 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.01819560272934041, "math_qa": 0.023115577889447236 } }, { "flos": 1.6706703583797576e+18, "train_loss": 5.592496337890625, "eval_loss": 6.0052155417365, "eval_accuracy": 0.02215884159719175, "eval_loss_by_set": { "aqua_rat": 5.996984958648682, "gsm8k": 6.853092540394176, "math_qa": 5.61729113260905 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.02047005307050796, "math_qa": 0.020435510887772193 } }, { "flos": 1.6766631063836426e+18, "train_loss": 5.608038330078125, "eval_loss": 6.012937494226404, "eval_accuracy": 0.023913997367266345, "eval_loss_by_set": { "aqua_rat": 6.005537033081055, "gsm8k": 6.894566622647372, "math_qa": 5.609474182128906 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.02577710386656558, "math_qa": 0.022110552763819097 } }, { "flos": 1.682616245662253e+18, "train_loss": 5.605010986328125, "eval_loss": 6.024063522751267, "eval_accuracy": 0.02413339183852567, "eval_loss_by_set": { "aqua_rat": 6.023895263671875, "gsm8k": 6.886793656782671, "math_qa": 5.628659566243489 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.02577710386656558, "math_qa": 0.022780569514237858 } }, { "flos": 1.6886133004445942e+18, "train_loss": 5.590848388671875, "eval_loss": 6.022804466453758, "eval_accuracy": 0.023913997367266345, "eval_loss_by_set": { "aqua_rat": 6.006477355957031, "gsm8k": 6.892397793856534, "math_qa": 5.625601450602214 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.019711902956785442, "math_qa": 0.025460636515912898 } }, { "flos": 1.6945679026964398e+18, "train_loss": 5.587139892578125, "eval_loss": 6.012457151670714, "eval_accuracy": 0.020403685827117157, "eval_loss_by_set": { "aqua_rat": 6.013553619384766, "gsm8k": 6.876328901811079, "math_qa": 5.616424560546875 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.01819560272934041, "math_qa": 0.018760469011725293 } }, { "flos": 1.7005458948033085e+18, "train_loss": 5.5986328125, "eval_loss": 6.011712357804582, "eval_accuracy": 0.023036419482229047, "eval_loss_by_set": { "aqua_rat": 5.993263244628906, "gsm8k": 6.879422968084162, "math_qa": 5.615549087524414 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.017437452615617893, "math_qa": 0.022445561139028476 } }, { "flos": 1.706501651327615e+18, "train_loss": 5.588348388671875, "eval_loss": 6.0258976704365494, "eval_accuracy": 0.020842474769635806, "eval_loss_by_set": { "aqua_rat": 6.014698028564453, "gsm8k": 6.89287636496804, "math_qa": 5.629465738932292 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.022744503411675512, "math_qa": 0.019765494137353432 } }, { "flos": 1.7124653830693192e+18, "train_loss": 5.595509033203125, "eval_loss": 6.01025998914564, "eval_accuracy": 0.02413339183852567, "eval_loss_by_set": { "aqua_rat": 5.995889663696289, "gsm8k": 6.87105282870206, "math_qa": 5.61692746480306 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.025018953752843062, "math_qa": 0.022780569514237858 } }, { "flos": 1.718397625184551e+18, "train_loss": 5.5906005859375, "eval_loss": 6.004175340807116, "eval_accuracy": 0.020403685827117157, "eval_loss_by_set": { "aqua_rat": 6.004020690917969, "gsm8k": 6.858630787242543, "math_qa": 5.612562815348308 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.01819560272934041, "math_qa": 0.019765494137353432 } }, { "flos": 1.7243691469231882e+18, "train_loss": 5.591798706054687, "eval_loss": 6.010948490452122, "eval_accuracy": 0.023255813953488372, "eval_loss_by_set": { "aqua_rat": 5.998666763305664, "gsm8k": 6.860169844193892, "math_qa": 5.622745513916016 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.014404852160727824, "math_qa": 0.02680067001675042 } }, { "flos": 1.7303520030805197e+18, "train_loss": 5.591536865234375, "eval_loss": 6.014799942841401, "eval_accuracy": 0.023475208424747696, "eval_loss_by_set": { "aqua_rat": 6.003565788269043, "gsm8k": 6.8766326904296875, "math_qa": 5.620729446411133 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.02350265352539803, "math_qa": 0.022110552763819097 } }, { "flos": 1.736320742754091e+18, "train_loss": 5.589204711914062, "eval_loss": 6.020913459159233, "eval_accuracy": 0.025449758666081616, "eval_loss_by_set": { "aqua_rat": 6.012936592102051, "gsm8k": 6.877054387872869, "math_qa": 5.629180272420247 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.02047005307050796, "math_qa": 0.02512562814070352 } }, { "flos": 1.7422942219240735e+18, "train_loss": 5.5923004150390625, "eval_loss": 6.017469895852579, "eval_accuracy": 0.026546731022378235, "eval_loss_by_set": { "aqua_rat": 6.024281024932861, "gsm8k": 6.872473976828835, "math_qa": 5.6250254313151045 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.022744503411675512, "math_qa": 0.026465661641541037 } }, { "flos": 1.7482742756152443e+18, "train_loss": 5.582835693359375, "eval_loss": 6.025620383185309, "eval_accuracy": 0.025888547608600262, "eval_loss_by_set": { "aqua_rat": 6.017369270324707, "gsm8k": 6.905522433194247, "math_qa": 5.623019536336263 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.025018953752843062, "math_qa": 0.024120603015075376 } }, { "flos": 1.7542338031208366e+18, "train_loss": 5.583807373046875, "eval_loss": 6.015112000542718, "eval_accuracy": 0.02215884159719175, "eval_loss_by_set": { "aqua_rat": 6.0071492195129395, "gsm8k": 6.877342917702415, "math_qa": 5.620586395263672 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.017437452615617893, "math_qa": 0.024120603015075376 } }, { "flos": 1.7602587198928978e+18, "train_loss": 5.598756103515625, "eval_loss": 6.003827378556535, "eval_accuracy": 0.026985519964896884, "eval_loss_by_set": { "aqua_rat": 6.014669418334961, "gsm8k": 6.8655783913352275, "math_qa": 5.607954661051433 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.02350265352539803, "math_qa": 0.026465661641541037 } }, { "flos": 1.7662172375443046e+18, "train_loss": 5.597861328125, "eval_loss": 5.998583948290026, "eval_accuracy": 0.02457218078104432, "eval_loss_by_set": { "aqua_rat": 5.998793125152588, "gsm8k": 6.85852675004439, "math_qa": 5.6044260660807295 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.017437452615617893, "math_qa": 0.026465661641541037 } }, { "flos": 1.7721823297168998e+18, "train_loss": 5.591316528320313, "eval_loss": 6.007614445041966, "eval_accuracy": 0.023475208424747696, "eval_loss_by_set": { "aqua_rat": 5.997343063354492, "gsm8k": 6.87518310546875, "math_qa": 5.6108347574869795 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.02350265352539803, "math_qa": 0.023115577889447236 } }, { "flos": 1.7781229599032607e+18, "train_loss": 5.587189331054687, "eval_loss": 6.006308632927972, "eval_accuracy": 0.020623080298376482, "eval_loss_by_set": { "aqua_rat": 6.001402854919434, "gsm8k": 6.887007973410866, "math_qa": 5.603063583374023 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.01819560272934041, "math_qa": 0.018425460636515914 } }, { "flos": 1.784097696424919e+18, "train_loss": 5.58741455078125, "eval_loss": 6.010638855599068, "eval_accuracy": 0.02720491443615621, "eval_loss_by_set": { "aqua_rat": 6.012969493865967, "gsm8k": 6.860454906116832, "math_qa": 5.6209456125895185 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.021986353297952996, "math_qa": 0.027135678391959798 } }, { "flos": 1.7900474555642675e+18, "train_loss": 5.57740234375, "eval_loss": 6.017655011769888, "eval_accuracy": 0.026985519964896884, "eval_loss_by_set": { "aqua_rat": 6.018958568572998, "gsm8k": 6.910890752618963, "math_qa": 5.608146667480469 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.022744503411675512, "math_qa": 0.026465661641541037 } }, { "flos": 1.79597982169668e+18, "train_loss": 5.594341430664063, "eval_loss": 5.9964853235193205, "eval_accuracy": 0.028082492321193506, "eval_loss_by_set": { "aqua_rat": 6.010105133056641, "gsm8k": 6.855816927823153, "math_qa": 5.601490020751953 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.025018953752843062, "math_qa": 0.027135678391959798 } }, { "flos": 1.8019810184381071e+18, "train_loss": 5.583768310546875, "eval_loss": 6.021877701218064, "eval_accuracy": 0.025230364194822292, "eval_loss_by_set": { "aqua_rat": 6.004560470581055, "gsm8k": 6.89295127175071, "math_qa": 5.624078750610352 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.01819560272934041, "math_qa": 0.026465661641541037 } }, { "flos": 1.8079457390960312e+18, "train_loss": 5.59267333984375, "eval_loss": 6.00946011414399, "eval_accuracy": 0.027863097849934182, "eval_loss_by_set": { "aqua_rat": 6.007070064544678, "gsm8k": 6.870536804199219, "math_qa": 5.614999135335286 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.02350265352539803, "math_qa": 0.02814070351758794 } }, { "flos": 1.8139189917064888e+18, "train_loss": 5.588728637695312, "eval_loss": 6.025220690546809, "eval_accuracy": 0.025669153137340937, "eval_loss_by_set": { "aqua_rat": 6.010135173797607, "gsm8k": 6.898223183371804, "math_qa": 5.626351674397786 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.02122820318423048, "math_qa": 0.02512562814070352 } }, { "flos": 1.8198337377355694e+18, "train_loss": 5.572628173828125, "eval_loss": 6.018991805411674, "eval_accuracy": 0.02676612549363756, "eval_loss_by_set": { "aqua_rat": 6.004989147186279, "gsm8k": 6.893220381303267, "math_qa": 5.619470596313477 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.02577710386656558, "math_qa": 0.02613065326633166 } }, { "flos": 1.825779395718021e+18, "train_loss": 5.59313720703125, "eval_loss": 6.0173198596851245, "eval_accuracy": 0.025449758666081616, "eval_loss_by_set": { "aqua_rat": 6.005193710327148, "gsm8k": 6.885083285245028, "math_qa": 5.62060546875 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.018953752843062926, "math_qa": 0.026465661641541037 } }, { "flos": 1.8317733801356165e+18, "train_loss": 5.594383544921875, "eval_loss": 6.019055856240763, "eval_accuracy": 0.027863097849934182, "eval_loss_by_set": { "aqua_rat": 6.01329231262207, "gsm8k": 6.869153109463778, "math_qa": 5.6299082438151045 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.02122820318423048, "math_qa": 0.03015075376884422 } }, { "flos": 1.8376914649648988e+18, "train_loss": 5.576475830078125, "eval_loss": 6.03147790238664, "eval_accuracy": 0.02830188679245283, "eval_loss_by_set": { "aqua_rat": 6.029309272766113, "gsm8k": 6.890751231800426, "math_qa": 5.637825012207031 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.024260803639120546, "math_qa": 0.02814070351758794 } }, { "flos": 1.8436508072500265e+18, "train_loss": 5.583973999023438, "eval_loss": 6.006098901903307, "eval_accuracy": 0.022817025010969723, "eval_loss_by_set": { "aqua_rat": 5.99419641494751, "gsm8k": 6.86951307816939, "math_qa": 5.611359278361003 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.018953752843062926, "math_qa": 0.023785594639865997 } }, { "flos": 1.8496235036622193e+18, "train_loss": 5.59498291015625, "eval_loss": 6.006763561351879, "eval_accuracy": 0.025888547608600262, "eval_loss_by_set": { "aqua_rat": 5.998134613037109, "gsm8k": 6.858465021306818, "math_qa": 5.617119471232097 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.019711902956785442, "math_qa": 0.026465661641541037 } }, { "flos": 1.855547234762883e+18, "train_loss": 5.5802783203125, "eval_loss": 6.026005667609137, "eval_accuracy": 0.027863097849934182, "eval_loss_by_set": { "aqua_rat": 6.024317741394043, "gsm8k": 6.8694374778053975, "math_qa": 5.639573415120442 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.02047005307050796, "math_qa": 0.02747068676716918 } }, { "flos": 1.861549153058816e+18, "train_loss": 5.591625366210938, "eval_loss": 6.006230096559267, "eval_accuracy": 0.028521281263712155, "eval_loss_by_set": { "aqua_rat": 6.0102763175964355, "gsm8k": 6.864740545099432, "math_qa": 5.612408955891927 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.026535253980288095, "math_qa": 0.0288107202680067 } }, { "flos": 1.8674461968433152e+18, "train_loss": 5.581766967773437, "eval_loss": 6.01147783124769, "eval_accuracy": 0.025010969723562967, "eval_loss_by_set": { "aqua_rat": 5.998999118804932, "gsm8k": 6.868999134410512, "math_qa": 5.619487126668294 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.015163002274450341, "math_qa": 0.02780569514237856 } }, { "flos": 1.8734635920538993e+18, "train_loss": 5.584125366210937, "eval_loss": 6.0161251377415015, "eval_accuracy": 0.021939447125932425, "eval_loss_by_set": { "aqua_rat": 6.009988784790039, "gsm8k": 6.899553472345525, "math_qa": 5.611731847127278 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.013646702047005308, "math_qa": 0.024790619765494137 } }, { "flos": 1.879360059239039e+18, "train_loss": 5.587919921875, "eval_loss": 6.027552475800386, "eval_accuracy": 0.023036419482229047, "eval_loss_by_set": { "aqua_rat": 6.037411689758301, "gsm8k": 6.911886735395952, "math_qa": 5.621411005655925 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.02122820318423048, "math_qa": 0.022445561139028476 } }, { "flos": 1.8853102097572823e+18, "train_loss": 5.585326538085938, "eval_loss": 6.00776043453732, "eval_accuracy": 0.023255813953488372, "eval_loss_by_set": { "aqua_rat": 6.022809982299805, "gsm8k": 6.871935757723722, "math_qa": 5.61042594909668 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.018953752843062926, "math_qa": 0.023785594639865997 } }, { "flos": 1.891294693707219e+18, "train_loss": 5.5920343017578125, "eval_loss": 6.032548878643964, "eval_accuracy": 0.025669153137340937, "eval_loss_by_set": { "aqua_rat": 6.014244556427002, "gsm8k": 6.904558355158025, "math_qa": 5.634403228759766 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.01819560272934041, "math_qa": 0.02914572864321608 } }, { "flos": 1.8972889250854339e+18, "train_loss": 5.59012451171875, "eval_loss": 6.019439748815588, "eval_accuracy": 0.0298376480912681, "eval_loss_by_set": { "aqua_rat": 6.017403602600098, "gsm8k": 6.902428366921165, "math_qa": 5.614906311035156 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.015163002274450341, "math_qa": 0.034170854271356785 } }, { "flos": 1.903220549262246e+18, "train_loss": 5.589896240234375, "eval_loss": 6.0248898171089795, "eval_accuracy": 0.029618253620008774, "eval_loss_by_set": { "aqua_rat": 6.011967658996582, "gsm8k": 6.908526333895597, "math_qa": 5.6209665934244795 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.018953752843062926, "math_qa": 0.032160804020100506 } }, { "flos": 1.9091648065484882e+18, "train_loss": 5.58756591796875, "eval_loss": 6.022622185784417, "eval_accuracy": 0.026985519964896884, "eval_loss_by_set": { "aqua_rat": 6.030891418457031, "gsm8k": 6.900311556729403, "math_qa": 5.619658788045247 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.018953752843062926, "math_qa": 0.02814070351758794 } }, { "flos": 1.915119450139394e+18, "train_loss": 5.586236572265625, "eval_loss": 6.0167081420486035, "eval_accuracy": 0.024791575252303643, "eval_loss_by_set": { "aqua_rat": 6.016089916229248, "gsm8k": 6.894583268599077, "math_qa": 5.614400227864583 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.018953752843062926, "math_qa": 0.025460636515912898 } }, { "flos": 1.9210771023548908e+18, "train_loss": 5.582626953125, "eval_loss": 6.023507195550042, "eval_accuracy": 0.030495831505046072, "eval_loss_by_set": { "aqua_rat": 6.0215301513671875, "gsm8k": 6.9040069580078125, "math_qa": 5.620109558105469 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.022744503411675512, "math_qa": 0.03082077051926298 } }, { "flos": 1.9270209467874017e+18, "train_loss": 5.588312377929688, "eval_loss": 6.019830265560666, "eval_accuracy": 0.02720491443615621, "eval_loss_by_set": { "aqua_rat": 6.01377534866333, "gsm8k": 6.875640175559304, "math_qa": 5.628088633219401 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.02122820318423048, "math_qa": 0.0288107202680067 } }, { "flos": 1.9329780632057283e+18, "train_loss": 5.585303955078125, "eval_loss": 6.035364640725626, "eval_accuracy": 0.02457218078104432, "eval_loss_by_set": { "aqua_rat": 6.046118259429932, "gsm8k": 6.908961209383878, "math_qa": 5.634070078531901 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.016679302501895376, "math_qa": 0.026465661641541037 } }, { "flos": 1.9389451332107633e+18, "train_loss": 5.5937939453125, "eval_loss": 6.020693598566829, "eval_accuracy": 0.025888547608600262, "eval_loss_by_set": { "aqua_rat": 6.019275665283203, "gsm8k": 6.896749323064631, "math_qa": 5.619286219278972 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.017437452615617893, "math_qa": 0.02780569514237856 } }, { "flos": 1.9449423528124744e+18, "train_loss": 5.592305908203125, "eval_loss": 6.03140165999129, "eval_accuracy": 0.025449758666081616, "eval_loss_by_set": { "aqua_rat": 6.030168533325195, "gsm8k": 6.910036260431463, "math_qa": 5.628796895345052 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.02122820318423048, "math_qa": 0.02512562814070352 } }, { "flos": 1.9509185732453335e+18, "train_loss": 5.5809088134765625, "eval_loss": 6.01832204251676, "eval_accuracy": 0.025010969723562967, "eval_loss_by_set": { "aqua_rat": 6.034502983093262, "gsm8k": 6.888091347434304, "math_qa": 5.618329366048177 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.019711902956785442, "math_qa": 0.024790619765494137 } }, { "flos": 1.956903943032275e+18, "train_loss": 5.592039794921875, "eval_loss": 6.015179634094238, "eval_accuracy": 0.02874067573497148, "eval_loss_by_set": { "aqua_rat": 6.013687610626221, "gsm8k": 6.882603038441051, "math_qa": 5.617734909057617 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.02047005307050796, "math_qa": 0.02981574539363484 } }, { "flos": 1.9628818320599286e+18, "train_loss": 5.58947021484375, "eval_loss": 6.014148170883591, "eval_accuracy": 0.025669153137340937, "eval_loss_by_set": { "aqua_rat": 6.005256175994873, "gsm8k": 6.881364302201704, "math_qa": 5.617415110270183 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.02047005307050796, "math_qa": 0.025460636515912898 } }, { "flos": 1.968839113297625e+18, "train_loss": 5.59296142578125, "eval_loss": 6.030292871836069, "eval_accuracy": 0.026546731022378235, "eval_loss_by_set": { "aqua_rat": 6.041142463684082, "gsm8k": 6.901134837757457, "math_qa": 5.630252838134766 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.019711902956785442, "math_qa": 0.02780569514237856 } }, { "flos": 1.9748649368446566e+18, "train_loss": 5.581895141601563, "eval_loss": 6.011867780943175, "eval_accuracy": 0.02830188679245283, "eval_loss_by_set": { "aqua_rat": 6.003897666931152, "gsm8k": 6.893655256791548, "math_qa": 5.608379364013672 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.02047005307050796, "math_qa": 0.02948073701842546 } }, { "flos": 1.980841363435946e+18, "train_loss": 5.5871923828125, "eval_loss": 6.026540008751121, "eval_accuracy": 0.02457218078104432, "eval_loss_by_set": { "aqua_rat": 6.0316853523254395, "gsm8k": 6.902635054154829, "math_qa": 5.6245676676432295 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.019711902956785442, "math_qa": 0.024790619765494137 } }, { "flos": 1.9868120605408625e+18, "train_loss": 5.588199462890625, "eval_loss": 6.019059103888434, "eval_accuracy": 0.023913997367266345, "eval_loss_by_set": { "aqua_rat": 6.008954048156738, "gsm8k": 6.879356384277344, "math_qa": 5.625598271687825 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.01819560272934041, "math_qa": 0.025460636515912898 } }, { "flos": 1.9927260028741878e+18, "train_loss": 5.573662109375, "eval_loss": 6.02324171324034, "eval_accuracy": 0.024791575252303643, "eval_loss_by_set": { "aqua_rat": 6.014799118041992, "gsm8k": 6.895088195800781, "math_qa": 5.624348958333333 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.013646702047005308, "math_qa": 0.02914572864321608 } }, { "flos": 1.9987118472550154e+18, "train_loss": 5.585098876953125, "eval_loss": 6.024734548620276, "eval_accuracy": 0.02676612549363756, "eval_loss_by_set": { "aqua_rat": 6.01503849029541, "gsm8k": 6.899153275923296, "math_qa": 5.624767303466797 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.019711902956785442, "math_qa": 0.02680067001675042 } }, { "flos": 2.0047492119160422e+18, "train_loss": 5.599828491210937, "eval_loss": 6.0099431115227775, "eval_accuracy": 0.023036419482229047, "eval_loss_by_set": { "aqua_rat": 6.005358695983887, "gsm8k": 6.877040516246449, "math_qa": 5.612905502319336 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.01819560272934041, "math_qa": 0.022445561139028476 } }, { "flos": 2.0107016709792072e+18, "train_loss": 5.58742919921875, "eval_loss": 6.028727918057828, "eval_accuracy": 0.025669153137340937, "eval_loss_by_set": { "aqua_rat": 6.014426231384277, "gsm8k": 6.906554482199929, "math_qa": 5.627582550048828 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.018953752843062926, "math_qa": 0.02780569514237856 } }, { "flos": 2.016715212530385e+18, "train_loss": 5.599507446289063, "eval_loss": 6.027240856273754, "eval_accuracy": 0.030276437033786747, "eval_loss_by_set": { "aqua_rat": 6.028007507324219, "gsm8k": 6.903189225630327, "math_qa": 5.62570063273112 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.025018953752843062, "math_qa": 0.03149078726968174 } }, { "flos": 2.022675791229223e+18, "train_loss": 5.582464599609375, "eval_loss": 6.022344589233398, "eval_accuracy": 0.028521281263712155, "eval_loss_by_set": { "aqua_rat": 6.0112714767456055, "gsm8k": 6.889202464710582, "math_qa": 5.625957489013672 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.021986353297952996, "math_qa": 0.03149078726968174 } }, { "flos": 2.028624747209687e+18, "train_loss": 5.589513549804687, "eval_loss": 6.0202216328801335, "eval_accuracy": 0.02830188679245283, "eval_loss_by_set": { "aqua_rat": 6.020458698272705, "gsm8k": 6.903805125843395, "math_qa": 5.615226109822591 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.02047005307050796, "math_qa": 0.02948073701842546 } }, { "flos": 2.0345619151155364e+18, "train_loss": 5.58630126953125, "eval_loss": 6.021904455648886, "eval_accuracy": 0.028960070206230804, "eval_loss_by_set": { "aqua_rat": 6.014065742492676, "gsm8k": 6.89710166237571, "math_qa": 5.621425628662109 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.02047005307050796, "math_qa": 0.03082077051926298 } }, { "flos": 2.0404845955598254e+18, "train_loss": 5.58516845703125, "eval_loss": 6.030668207117029, "eval_accuracy": 0.02720491443615621, "eval_loss_by_set": { "aqua_rat": 6.023248672485352, "gsm8k": 6.90656211159446, "math_qa": 5.62983512878418 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.018953752843062926, "math_qa": 0.02847571189279732 } }, { "flos": 2.0464709134607974e+18, "train_loss": 5.584453125, "eval_loss": 6.034432900918497, "eval_accuracy": 0.02676612549363756, "eval_loss_by_set": { "aqua_rat": 6.028480529785156, "gsm8k": 6.915037675337358, "math_qa": 5.63131841023763 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.017437452615617893, "math_qa": 0.02948073701842546 } }, { "flos": 2.0524254330345226e+18, "train_loss": 5.578494262695313, "eval_loss": 6.022591358906514, "eval_accuracy": 0.03312856516015796, "eval_loss_by_set": { "aqua_rat": 6.022405624389648, "gsm8k": 6.882763255726207, "math_qa": 5.6283613840738935 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.026535253980288095, "math_qa": 0.03450586264656617 } }, { "flos": 2.0583762433671168e+18, "train_loss": 5.57645263671875, "eval_loss": 6.038315901885161, "eval_accuracy": 0.026107942079859586, "eval_loss_by_set": { "aqua_rat": 6.039952278137207, "gsm8k": 6.91332314231179, "math_qa": 5.637134552001953 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.01592115238817286, "math_qa": 0.0288107202680067 } }, { "flos": 2.0643560490239263e+18, "train_loss": 5.58785400390625, "eval_loss": 6.024500382913126, "eval_accuracy": 0.030495831505046072, "eval_loss_by_set": { "aqua_rat": 6.030981540679932, "gsm8k": 6.889066522771662, "math_qa": 5.6277008056640625 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.01592115238817286, "math_qa": 0.0338358458961474 } }, { "flos": 2.070322583231791e+18, "train_loss": 5.5824365234375, "eval_loss": 6.028757894361341, "eval_accuracy": 0.027424308907415533, "eval_loss_by_set": { "aqua_rat": 6.020687580108643, "gsm8k": 6.892262545498935, "math_qa": 5.633657455444336 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.018953752843062926, "math_qa": 0.02847571189279732 } }, { "flos": 2.0762551759237284e+18, "train_loss": 5.576314697265625, "eval_loss": 6.020966761821025, "eval_accuracy": 0.027863097849934182, "eval_loss_by_set": { "aqua_rat": 6.018233299255371, "gsm8k": 6.899071433327415, "math_qa": 5.618729909261067 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.022744503411675512, "math_qa": 0.0288107202680067 } }, { "flos": 2.0822158990408417e+18, "train_loss": 5.5889825439453125, "eval_loss": 6.02890478598105, "eval_accuracy": 0.026107942079859586, "eval_loss_by_set": { "aqua_rat": 6.030847549438477, "gsm8k": 6.912625399502841, "math_qa": 5.623704274495442 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.018953752843062926, "math_qa": 0.027135678391959798 } }, { "flos": 2.088115663150252e+18, "train_loss": 5.573121337890625, "eval_loss": 6.039205473822516, "eval_accuracy": 0.029398859148749453, "eval_loss_by_set": { "aqua_rat": 6.015439510345459, "gsm8k": 6.888089266690341, "math_qa": 5.652114232381185 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.02047005307050796, "math_qa": 0.03149078726968174 } }, { "flos": 2.0941669585377034e+18, "train_loss": 5.584075317382813, "eval_loss": 6.024955285562052, "eval_accuracy": 0.028082492321193506, "eval_loss_by_set": { "aqua_rat": 6.0209150314331055, "gsm8k": 6.905133334073153, "math_qa": 5.621877034505208 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.018953752843062926, "math_qa": 0.02981574539363484 } }, { "flos": 2.100160881215144e+18, "train_loss": 5.58455322265625, "eval_loss": 6.0266902253434464, "eval_accuracy": 0.030276437033786747, "eval_loss_by_set": { "aqua_rat": 6.028383731842041, "gsm8k": 6.921277132901278, "math_qa": 5.616530100504558 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.01819560272934041, "math_qa": 0.03450586264656617 } }, { "flos": 2.1060975337249178e+18, "train_loss": 5.571456298828125, "eval_loss": 6.020833427841599, "eval_accuracy": 0.02632733655111891, "eval_loss_by_set": { "aqua_rat": 6.009365558624268, "gsm8k": 6.891528042879972, "math_qa": 5.622720718383789 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.02047005307050796, "math_qa": 0.02579564489112228 } }, { "flos": 2.1120367417402327e+18, "train_loss": 5.575186157226563, "eval_loss": 6.032665046485695, "eval_accuracy": 0.028082492321193506, "eval_loss_by_set": { "aqua_rat": 6.030271530151367, "gsm8k": 6.9122446233576, "math_qa": 5.629723866780599 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.01819560272934041, "math_qa": 0.03082077051926298 } }, { "flos": 2.117998556852781e+18, "train_loss": 5.577747802734375, "eval_loss": 6.011467495480099, "eval_accuracy": 0.025888547608600262, "eval_loss_by_set": { "aqua_rat": 6.003511428833008, "gsm8k": 6.884355718439275, "math_qa": 5.612056732177734 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.02047005307050796, "math_qa": 0.027135678391959798 } }, { "flos": 2.123983843961602e+18, "train_loss": 5.5774755859375, "eval_loss": 6.023336075447701, "eval_accuracy": 0.031154014918824045, "eval_loss_by_set": { "aqua_rat": 6.040390491485596, "gsm8k": 6.908749667080966, "math_qa": 5.616100311279297 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.02047005307050796, "math_qa": 0.03350083752093802 } }, { "flos": 2.129921692082897e+18, "train_loss": 5.5757598876953125, "eval_loss": 6.0112172461844775, "eval_accuracy": 0.025669153137340937, "eval_loss_by_set": { "aqua_rat": 6.009738445281982, "gsm8k": 6.890811573375355, "math_qa": 5.608193079630534 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.016679302501895376, "math_qa": 0.02680067001675042 } }, { "flos": 2.1359420755169772e+18, "train_loss": 5.589041137695313, "eval_loss": 6.021560153445682, "eval_accuracy": 0.026107942079859586, "eval_loss_by_set": { "aqua_rat": 6.029172897338867, "gsm8k": 6.896663318980824, "math_qa": 5.619836807250977 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.017437452615617893, "math_qa": 0.02780569514237856 } }, { "flos": 2.141984674132525e+18, "train_loss": 5.590685424804687, "eval_loss": 6.01960800789498, "eval_accuracy": 0.031812198332602015, "eval_loss_by_set": { "aqua_rat": 6.018033027648926, "gsm8k": 6.906211853027344, "math_qa": 5.613379160563151 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.018953752843062926, "math_qa": 0.03484087102177554 } }, { "flos": 2.147978143154045e+18, "train_loss": 5.586216430664063, "eval_loss": 6.0218709481729045, "eval_accuracy": 0.030276437033786747, "eval_loss_by_set": { "aqua_rat": 6.023009300231934, "gsm8k": 6.887716813520952, "math_qa": 5.624930063883464 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.017437452615617893, "math_qa": 0.03249581239530988 } }, { "flos": 2.153923512836817e+18, "train_loss": 5.584864501953125, "eval_loss": 6.032161996171281, "eval_accuracy": 0.027643703378674857, "eval_loss_by_set": { "aqua_rat": 6.017089366912842, "gsm8k": 6.89269395308061, "math_qa": 5.639007568359375 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.016679302501895376, "math_qa": 0.03082077051926298 } }, { "flos": 2.1599229991075185e+18, "train_loss": 5.578046875, "eval_loss": 6.037787257014094, "eval_accuracy": 0.02917946467749013, "eval_loss_by_set": { "aqua_rat": 6.04011344909668, "gsm8k": 6.938443270596591, "math_qa": 5.624792734781901 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.02047005307050796, "math_qa": 0.03149078726968174 } }, { "flos": 2.1658889567160238e+18, "train_loss": 5.58218505859375, "eval_loss": 6.027551908750792, "eval_accuracy": 0.027863097849934182, "eval_loss_by_set": { "aqua_rat": 6.037626266479492, "gsm8k": 6.903535322709517, "math_qa": 5.625219980875651 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.017437452615617893, "math_qa": 0.030485762144053602 } }, { "flos": 2.1717571286566175e+18, "train_loss": 5.572103271484375, "eval_loss": 6.033109561817066, "eval_accuracy": 0.025010969723562967, "eval_loss_by_set": { "aqua_rat": 6.0222673416137695, "gsm8k": 6.910686839710582, "math_qa": 5.6317901611328125 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.01819560272934041, "math_qa": 0.02680067001675042 } }, { "flos": 2.1776867336619295e+18, "train_loss": 5.569619140625, "eval_loss": 6.027079401789485, "eval_accuracy": 0.027643703378674857, "eval_loss_by_set": { "aqua_rat": 6.0143890380859375, "gsm8k": 6.909638838334517, "math_qa": 5.623630523681641 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.022744503411675512, "math_qa": 0.02747068676716918 } }, { "flos": 2.1836900531909427e+18, "train_loss": 5.586160888671875, "eval_loss": 6.01229595493626, "eval_accuracy": 0.028082492321193506, "eval_loss_by_set": { "aqua_rat": 6.001561164855957, "gsm8k": 6.878454034978693, "math_qa": 5.616201400756836 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.025018953752843062, "math_qa": 0.02747068676716918 } }, { "flos": 2.1897208433307812e+18, "train_loss": 5.5906610107421875, "eval_loss": 6.029694067465292, "eval_accuracy": 0.026546731022378235, "eval_loss_by_set": { "aqua_rat": 6.030282020568848, "gsm8k": 6.907395796342329, "math_qa": 5.6273651123046875 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.018953752843062926, "math_qa": 0.02814070351758794 } }, { "flos": 2.195674517869691e+18, "train_loss": 5.582273559570313, "eval_loss": 6.035788871146537, "eval_accuracy": 0.030057042562527423, "eval_loss_by_set": { "aqua_rat": 6.034523010253906, "gsm8k": 6.911747325550426, "math_qa": 5.634413401285808 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.022744503411675512, "math_qa": 0.031825795644891124 } }, { "flos": 2.2016499550078894e+18, "train_loss": 5.582489013671875, "eval_loss": 6.006508878759436, "eval_accuracy": 0.028521281263712155, "eval_loss_by_set": { "aqua_rat": 6.01637601852417, "gsm8k": 6.889038779518821, "math_qa": 5.601193745930989 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.019711902956785442, "math_qa": 0.031155778894472363 } }, { "flos": 2.2076160972999885e+18, "train_loss": 5.571673583984375, "eval_loss": 6.019238652409734, "eval_accuracy": 0.029618253620008774, "eval_loss_by_set": { "aqua_rat": 6.020606994628906, "gsm8k": 6.869628212668679, "math_qa": 5.62936274210612 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.025018953752843062, "math_qa": 0.02847571189279732 } }, { "flos": 2.213527031008723e+18, "train_loss": 5.565152587890625, "eval_loss": 6.025974015931825, "eval_accuracy": 0.02874067573497148, "eval_loss_by_set": { "aqua_rat": 6.025677680969238, "gsm8k": 6.903526999733665, "math_qa": 5.623786926269531 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.025018953752843062, "math_qa": 0.02914572864321608 } }, { "flos": 2.2195556162197258e+18, "train_loss": 5.586314697265625, "eval_loss": 6.028437691765863, "eval_accuracy": 0.03312856516015796, "eval_loss_by_set": { "aqua_rat": 6.030499458312988, "gsm8k": 6.901485096324574, "math_qa": 5.628119150797526 }, "eval_accuracy_by_set": { "aqua_rat": 0.08267716535433071, "gsm8k": 0.019711902956785442, "math_qa": 0.03484087102177554 } }, { "flos": 2.225486518842032e+18, "train_loss": 5.578250122070313, "eval_loss": 6.033939696647026, "eval_accuracy": 0.0298376480912681, "eval_loss_by_set": { "aqua_rat": 6.030064105987549, "gsm8k": 6.914346174760298, "math_qa": 5.630743026733398 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.021986353297952996, "math_qa": 0.03082077051926298 } }, { "flos": 2.2314772471375462e+18, "train_loss": 5.581502685546875, "eval_loss": 6.027427544464937, "eval_accuracy": 0.030495831505046072, "eval_loss_by_set": { "aqua_rat": 6.01947546005249, "gsm8k": 6.916564247824929, "math_qa": 5.620569229125977 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.02350265352539803, "math_qa": 0.031825795644891124 } }, { "flos": 2.237404523196842e+18, "train_loss": 5.57634765625, "eval_loss": 6.028708793021537, "eval_accuracy": 0.03312856516015796, "eval_loss_by_set": { "aqua_rat": 6.0322113037109375, "gsm8k": 6.900047995827415, "math_qa": 5.629053115844727 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.022744503411675512, "math_qa": 0.035175879396984924 } }, { "flos": 2.2433832164571218e+18, "train_loss": 5.580035400390625, "eval_loss": 6.034272709408322, "eval_accuracy": 0.0298376480912681, "eval_loss_by_set": { "aqua_rat": 6.024193286895752, "gsm8k": 6.921465093439275, "math_qa": 5.628482818603516 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.02577710386656558, "math_qa": 0.03015075376884422 } }, { "flos": 2.2493566129489838e+18, "train_loss": 5.588121948242187, "eval_loss": 6.018945204245077, "eval_accuracy": 0.029398859148749453, "eval_loss_by_set": { "aqua_rat": 6.0215067863464355, "gsm8k": 6.8880393288352275, "math_qa": 5.6203969319661455 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.01819560272934041, "math_qa": 0.03249581239530988 } }, { "flos": 2.255356883051217e+18, "train_loss": 5.571441650390625, "eval_loss": 6.0286357467238965, "eval_accuracy": 0.026107942079859586, "eval_loss_by_set": { "aqua_rat": 6.025237083435059, "gsm8k": 6.925335970791903, "math_qa": 5.617931365966797 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.017437452615617893, "math_qa": 0.02948073701842546 } }, { "flos": 2.26127814132446e+18, "train_loss": 5.575040893554688, "eval_loss": 6.019872923155089, "eval_accuracy": 0.029398859148749453, "eval_loss_by_set": { "aqua_rat": 6.024639129638672, "gsm8k": 6.897447065873579, "math_qa": 5.617254257202148 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.02122820318423048, "math_qa": 0.030485762144053602 } }, { "flos": 2.267237895926448e+18, "train_loss": 5.58183349609375, "eval_loss": 6.017615421398266, "eval_accuracy": 0.02676612549363756, "eval_loss_by_set": { "aqua_rat": 6.020366191864014, "gsm8k": 6.908923062411222, "math_qa": 5.608870188395183 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.019711902956785442, "math_qa": 0.02747068676716918 } }, { "flos": 2.2732382068308705e+18, "train_loss": 5.5813525390625, "eval_loss": 6.026617333695695, "eval_accuracy": 0.030715225976305396, "eval_loss_by_set": { "aqua_rat": 6.023605823516846, "gsm8k": 6.887981761585582, "math_qa": 5.632076263427734 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.021986353297952996, "math_qa": 0.03149078726968174 } }, { "flos": 2.2792135822289142e+18, "train_loss": 5.574580078125, "eval_loss": 6.030623667948955, "eval_accuracy": 0.027863097849934182, "eval_loss_by_set": { "aqua_rat": 6.02747917175293, "gsm8k": 6.897120389071378, "math_qa": 5.63374137878418 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.022744503411675512, "math_qa": 0.02847571189279732 } }, { "flos": 2.2851372725273887e+18, "train_loss": 5.573726806640625, "eval_loss": 6.029200373469172, "eval_accuracy": 0.02676612549363756, "eval_loss_by_set": { "aqua_rat": 6.034156799316406, "gsm8k": 6.920648748224432, "math_qa": 5.620206832885742 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.018953752843062926, "math_qa": 0.02747068676716918 } }, { "flos": 2.2911206435439247e+18, "train_loss": 5.58155029296875, "eval_loss": 6.0385405823991105, "eval_accuracy": 0.02917946467749013, "eval_loss_by_set": { "aqua_rat": 6.045344829559326, "gsm8k": 6.920491998845881, "math_qa": 5.633745829264323 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.02122820318423048, "math_qa": 0.031155778894472363 } }, { "flos": 2.2971152254988452e+18, "train_loss": 5.5864111328125, "eval_loss": 6.036915237839158, "eval_accuracy": 0.02917946467749013, "eval_loss_by_set": { "aqua_rat": 6.028039932250977, "gsm8k": 6.917620572176847, "math_qa": 5.6339982350667315 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.017437452615617893, "math_qa": 0.033165829145728645 } }, { "flos": 2.303063439523709e+18, "train_loss": 5.5718994140625, "eval_loss": 6.0207649437156885, "eval_accuracy": 0.029398859148749453, "eval_loss_by_set": { "aqua_rat": 6.02044677734375, "gsm8k": 6.89299912886186, "math_qa": 5.6210174560546875 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.02350265352539803, "math_qa": 0.02948073701842546 } }, { "flos": 2.3089950846384865e+18, "train_loss": 5.5794873046875, "eval_loss": 6.034611109140757, "eval_accuracy": 0.03268977621763931, "eval_loss_by_set": { "aqua_rat": 6.0439653396606445, "gsm8k": 6.92219335382635, "math_qa": 5.627023061116536 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.02122820318423048, "math_qa": 0.03484087102177554 } }, { "flos": 2.3149614540269814e+18, "train_loss": 5.57924072265625, "eval_loss": 6.025737298501505, "eval_accuracy": 0.031592803861342694, "eval_loss_by_set": { "aqua_rat": 6.0197649002075195, "gsm8k": 6.899783047762784, "math_qa": 5.625630696614583 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.02047005307050796, "math_qa": 0.03350083752093802 } }, { "flos": 2.3209957064473313e+18, "train_loss": 5.579932861328125, "eval_loss": 6.025367427516628, "eval_accuracy": 0.031154014918824045, "eval_loss_by_set": { "aqua_rat": 6.022710800170898, "gsm8k": 6.902273004705256, "math_qa": 5.623673756917317 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.018953752843062926, "math_qa": 0.03484087102177554 } }, { "flos": 2.326936624396501e+18, "train_loss": 5.572109985351562, "eval_loss": 6.018153783437368, "eval_accuracy": 0.032250987275120664, "eval_loss_by_set": { "aqua_rat": 6.00882625579834, "gsm8k": 6.879391756924716, "math_qa": 5.624197006225586 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.02122820318423048, "math_qa": 0.03450586264656617 } }, { "flos": 2.332916059612381e+18, "train_loss": 5.571551513671875, "eval_loss": 6.019822094891523, "eval_accuracy": 0.03290917068889864, "eval_loss_by_set": { "aqua_rat": 6.030206680297852, "gsm8k": 6.888258500532671, "math_qa": 5.620923360188802 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.025018953752843062, "math_qa": 0.03484087102177554 } }, { "flos": 2.338902666349904e+18, "train_loss": 5.573778686523437, "eval_loss": 6.033219157038508, "eval_accuracy": 0.028960070206230804, "eval_loss_by_set": { "aqua_rat": 6.034022331237793, "gsm8k": 6.919438448819247, "math_qa": 5.6269683837890625 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.02047005307050796, "math_qa": 0.03082077051926298 } }, { "flos": 2.344851622330368e+18, "train_loss": 5.569758911132812, "eval_loss": 6.0289817758508635, "eval_accuracy": 0.03093462044756472, "eval_loss_by_set": { "aqua_rat": 6.04213285446167, "gsm8k": 6.915063337846235, "math_qa": 5.62176513671875 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.021986353297952996, "math_qa": 0.033165829145728645 } }, { "flos": 2.3508569411666575e+18, "train_loss": 5.586759033203125, "eval_loss": 6.020954596029745, "eval_accuracy": 0.031154014918824045, "eval_loss_by_set": { "aqua_rat": 6.020068168640137, "gsm8k": 6.8837432861328125, "math_qa": 5.625583648681641 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.024260803639120546, "math_qa": 0.03149078726968174 } }, { "flos": 2.356844599097426e+18, "train_loss": 5.572198486328125, "eval_loss": 6.027584385227513, "eval_accuracy": 0.03203159280386134, "eval_loss_by_set": { "aqua_rat": 6.030876159667969, "gsm8k": 6.90521864457564, "math_qa": 5.62506103515625 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.02122820318423048, "math_qa": 0.03484087102177554 } }, { "flos": 2.3627960483064054e+18, "train_loss": 5.579658203125, "eval_loss": 6.02982301969786, "eval_accuracy": 0.030276437033786747, "eval_loss_by_set": { "aqua_rat": 6.0226922035217285, "gsm8k": 6.922423622824929, "math_qa": 5.62130864461263 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.02880970432145565, "math_qa": 0.02981574539363484 } }, { "flos": 2.3688487862659973e+18, "train_loss": 5.583211669921875, "eval_loss": 6.027108115118903, "eval_accuracy": 0.029398859148749453, "eval_loss_by_set": { "aqua_rat": 6.029759407043457, "gsm8k": 6.904559048739347, "math_qa": 5.624722162882487 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.021986353297952996, "math_qa": 0.03082077051926298 } }, { "flos": 2.3747774018182185e+18, "train_loss": 5.57493896484375, "eval_loss": 6.027129018628919, "eval_accuracy": 0.029398859148749453, "eval_loss_by_set": { "aqua_rat": 6.028101444244385, "gsm8k": 6.9026711203835225, "math_qa": 5.6257578531901045 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.02047005307050796, "math_qa": 0.03283082077051926 } }, { "flos": 2.380774436199465e+18, "train_loss": 5.572783203125, "eval_loss": 6.033358238838814, "eval_accuracy": 0.030495831505046072, "eval_loss_by_set": { "aqua_rat": 6.032784461975098, "gsm8k": 6.921600341796875, "math_qa": 5.62629508972168 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.02122820318423048, "math_qa": 0.03283082077051926 } }, { "flos": 2.386725411351429e+18, "train_loss": 5.565310668945313, "eval_loss": 6.035684147396603, "eval_accuracy": 0.030276437033786747, "eval_loss_by_set": { "aqua_rat": 6.036209583282471, "gsm8k": 6.92071533203125, "math_qa": 5.630001068115234 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.018953752843062926, "math_qa": 0.0338358458961474 } }, { "flos": 2.392677499436794e+18, "train_loss": 5.56940185546875, "eval_loss": 6.034939173105601, "eval_accuracy": 0.031592803861342694, "eval_loss_by_set": { "aqua_rat": 6.063443183898926, "gsm8k": 6.915194424715909, "math_qa": 5.629113515218099 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.025018953752843062, "math_qa": 0.03450586264656617 } }, { "flos": 2.3986454144766444e+18, "train_loss": 5.575137939453125, "eval_loss": 6.039184003262906, "eval_accuracy": 0.03247038174637999, "eval_loss_by_set": { "aqua_rat": 6.040581703186035, "gsm8k": 6.921083623712713, "math_qa": 5.634863535563151 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.024260803639120546, "math_qa": 0.035175879396984924 } }, { "flos": 2.4045909903178465e+18, "train_loss": 5.577454833984375, "eval_loss": 6.020704578708958, "eval_accuracy": 0.03137340939008337, "eval_loss_by_set": { "aqua_rat": 6.031010627746582, "gsm8k": 6.899076288396662, "math_qa": 5.617258707682292 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.019711902956785442, "math_qa": 0.034170854271356785 } }, { "flos": 2.4105641194479944e+18, "train_loss": 5.57292236328125, "eval_loss": 6.0359397836633635, "eval_accuracy": 0.03268977621763931, "eval_loss_by_set": { "aqua_rat": 6.034896373748779, "gsm8k": 6.924197110262784, "math_qa": 5.628908793131511 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.021986353297952996, "math_qa": 0.035510887772194306 } }, { "flos": 2.4165008750369833e+18, "train_loss": 5.575346069335938, "eval_loss": 6.028091765738822, "eval_accuracy": 0.03312856516015796, "eval_loss_by_set": { "aqua_rat": 6.037535190582275, "gsm8k": 6.901148015802557, "math_qa": 5.627154032389323 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.02122820318423048, "math_qa": 0.035510887772194306 } }, { "flos": 2.422470582688809e+18, "train_loss": 5.575103759765625, "eval_loss": 6.035557746887207, "eval_accuracy": 0.030057042562527423, "eval_loss_by_set": { "aqua_rat": 6.052017688751221, "gsm8k": 6.924274097789418, "math_qa": 5.626857757568359 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.019711902956785442, "math_qa": 0.03249581239530988 } }, { "flos": 2.4284164054906307e+18, "train_loss": 5.571085815429687, "eval_loss": 6.035361805477658, "eval_accuracy": 0.032250987275120664, "eval_loss_by_set": { "aqua_rat": 6.052279949188232, "gsm8k": 6.930494828657671, "math_qa": 5.6236826578776045 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.02122820318423048, "math_qa": 0.035510887772194306 } }, { "flos": 2.4343495549177037e+18, "train_loss": 5.570867309570312, "eval_loss": 6.033549927376412, "eval_accuracy": 0.02917946467749013, "eval_loss_by_set": { "aqua_rat": 6.017707347869873, "gsm8k": 6.920536388050426, "math_qa": 5.628334681193034 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.021986353297952996, "math_qa": 0.031155778894472363 } }, { "flos": 2.4403292370942034e+18, "train_loss": 5.57302734375, "eval_loss": 6.033196939004434, "eval_accuracy": 0.032250987275120664, "eval_loss_by_set": { "aqua_rat": 6.029747009277344, "gsm8k": 6.924846302379262, "math_qa": 5.6248118082682295 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.02577710386656558, "math_qa": 0.03350083752093802 } }, { "flos": 2.4462392022878126e+18, "train_loss": 5.571840209960937, "eval_loss": 6.03832043828191, "eval_accuracy": 0.02632733655111891, "eval_loss_by_set": { "aqua_rat": 6.048821449279785, "gsm8k": 6.919363542036577, "math_qa": 5.633633931477864 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.01819560272934041, "math_qa": 0.0288107202680067 } }, { "flos": 2.4521914965316076e+18, "train_loss": 5.567505493164062, "eval_loss": 6.035290331453891, "eval_accuracy": 0.03422553751645459, "eval_loss_by_set": { "aqua_rat": 6.039166450500488, "gsm8k": 6.925074490633878, "math_qa": 5.62714958190918 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.025018953752843062, "math_qa": 0.03484087102177554 } }, { "flos": 2.4581672423705805e+18, "train_loss": 5.5719384765625, "eval_loss": 6.026173900913548, "eval_accuracy": 0.025888547608600262, "eval_loss_by_set": { "aqua_rat": 6.020655155181885, "gsm8k": 6.907900723544034, "math_qa": 5.622509002685547 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.019711902956785442, "math_qa": 0.026465661641541037 } }, { "flos": 2.464173982841045e+18, "train_loss": 5.5717236328125, "eval_loss": 6.035090111397408, "eval_accuracy": 0.028960070206230804, "eval_loss_by_set": { "aqua_rat": 6.028996467590332, "gsm8k": 6.914044466885653, "math_qa": 5.632743835449219 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.02350265352539803, "math_qa": 0.02948073701842546 } }, { "flos": 2.470084236871205e+18, "train_loss": 5.561227416992187, "eval_loss": 6.0275243037455795, "eval_accuracy": 0.028960070206230804, "eval_loss_by_set": { "aqua_rat": 6.032106876373291, "gsm8k": 6.90463603626598, "math_qa": 5.625132878621419 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.02350265352539803, "math_qa": 0.02847571189279732 } }, { "flos": 2.476057077164802e+18, "train_loss": 5.567742919921875, "eval_loss": 6.0256526276871964, "eval_accuracy": 0.02632733655111891, "eval_loss_by_set": { "aqua_rat": 6.020716190338135, "gsm8k": 6.898112903941762, "math_qa": 5.626186370849609 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.018953752843062926, "math_qa": 0.0288107202680067 } }, { "flos": 2.481957088771703e+18, "train_loss": 5.5685205078125, "eval_loss": 6.046793447958456, "eval_accuracy": 0.02874067573497148, "eval_loss_by_set": { "aqua_rat": 6.050374984741211, "gsm8k": 6.942751104181463, "math_qa": 5.635847727457683 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.024260803639120546, "math_qa": 0.0288107202680067 } }, { "flos": 2.4879485380848517e+18, "train_loss": 5.571201782226563, "eval_loss": 6.037952165345888, "eval_accuracy": 0.030715225976305396, "eval_loss_by_set": { "aqua_rat": 6.040410041809082, "gsm8k": 6.920691750266335, "math_qa": 5.633158365885417 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.025018953752843062, "math_qa": 0.03015075376884422 } }, { "flos": 2.493888157880156e+18, "train_loss": 5.558572387695312, "eval_loss": 6.038757762393436, "eval_accuracy": 0.030495831505046072, "eval_loss_by_set": { "aqua_rat": 6.035477161407471, "gsm8k": 6.906148737127131, "math_qa": 5.641476949055989 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.01819560272934041, "math_qa": 0.03350083752093802 } }, { "flos": 2.4998570618362266e+18, "train_loss": 5.5678948974609375, "eval_loss": 6.0350838223019165, "eval_accuracy": 0.026985519964896884, "eval_loss_by_set": { "aqua_rat": 6.0490827560424805, "gsm8k": 6.923330133611506, "math_qa": 5.626804351806641 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.018953752843062926, "math_qa": 0.02747068676716918 } }, { "flos": 2.505804595645645e+18, "train_loss": 5.57853515625, "eval_loss": 6.036874771118164, "eval_accuracy": 0.030057042562527423, "eval_loss_by_set": { "aqua_rat": 6.041501045227051, "gsm8k": 6.914475180886009, "math_qa": 5.634255727132161 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.02122820318423048, "math_qa": 0.031825795644891124 } }, { "flos": 2.511808842887594e+18, "train_loss": 5.574312133789062, "eval_loss": 6.031306241009687, "eval_accuracy": 0.02413339183852567, "eval_loss_by_set": { "aqua_rat": 6.031672477722168, "gsm8k": 6.914241443980824, "math_qa": 5.626597086588542 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.024260803639120546, "math_qa": 0.021775544388609715 } }, { "flos": 2.517745474459402e+18, "train_loss": 5.57105224609375, "eval_loss": 6.034674206295529, "eval_accuracy": 0.03312856516015796, "eval_loss_by_set": { "aqua_rat": 6.056149482727051, "gsm8k": 6.912044871937145, "math_qa": 5.630756378173828 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.01819560272934041, "math_qa": 0.03584589614740368 } }, { "flos": 2.523748340869366e+18, "train_loss": 5.577871704101563, "eval_loss": 6.0465805466110645, "eval_accuracy": 0.02830188679245283, "eval_loss_by_set": { "aqua_rat": 6.050872802734375, "gsm8k": 6.925778475674716, "math_qa": 5.643257141113281 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.02350265352539803, "math_qa": 0.02780569514237856 } }, { "flos": 2.5297187496746025e+18, "train_loss": 5.569179077148437, "eval_loss": 6.023157789900496, "eval_accuracy": 0.028082492321193506, "eval_loss_by_set": { "aqua_rat": 6.037321090698242, "gsm8k": 6.889586015181108, "math_qa": 5.62486457824707 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.021986353297952996, "math_qa": 0.02747068676716918 } }, { "flos": 2.5356813475449405e+18, "train_loss": 5.56722412109375, "eval_loss": 6.019998498865076, "eval_accuracy": 0.030715225976305396, "eval_loss_by_set": { "aqua_rat": 6.025108337402344, "gsm8k": 6.904306585138494, "math_qa": 5.614264806111653 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.016679302501895376, "math_qa": 0.0338358458961474 } }, { "flos": 2.541613445778768e+18, "train_loss": 5.574127197265625, "eval_loss": 6.043110177323625, "eval_accuracy": 0.031154014918824045, "eval_loss_by_set": { "aqua_rat": 6.056102275848389, "gsm8k": 6.937550631436435, "math_qa": 5.6320756276448565 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.030326004548900682, "math_qa": 0.02981574539363484 } }, { "flos": 2.547619383090348e+18, "train_loss": 5.5723095703125, "eval_loss": 6.029909288561022, "eval_accuracy": 0.030715225976305396, "eval_loss_by_set": { "aqua_rat": 6.029510498046875, "gsm8k": 6.907252918590199, "math_qa": 5.627826690673828 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.026535253980288095, "math_qa": 0.030485762144053602 } }, { "flos": 2.553541362381226e+18, "train_loss": 5.5637255859375, "eval_loss": 6.033506934707229, "eval_accuracy": 0.03290917068889864, "eval_loss_by_set": { "aqua_rat": 6.0325446128845215, "gsm8k": 6.901698719371449, "math_qa": 5.6356658935546875 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.021986353297952996, "math_qa": 0.03484087102177554 } }, { "flos": 2.559487330138194e+18, "train_loss": 5.56212646484375, "eval_loss": 6.04663542154673, "eval_accuracy": 0.0298376480912681, "eval_loss_by_set": { "aqua_rat": 6.039249897003174, "gsm8k": 6.923765009099787, "math_qa": 5.645233154296875 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.02350265352539803, "math_qa": 0.03082077051926298 } }, { "flos": 2.565420376486052e+18, "train_loss": 5.572843017578125, "eval_loss": 6.039938591622017, "eval_accuracy": 0.03268977621763931, "eval_loss_by_set": { "aqua_rat": 6.043730735778809, "gsm8k": 6.910815845836293, "math_qa": 5.640470504760742 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.022744503411675512, "math_qa": 0.03584589614740368 } }, { "flos": 2.5713927636605993e+18, "train_loss": 5.575111083984375, "eval_loss": 6.038646182498416, "eval_accuracy": 0.027643703378674857, "eval_loss_by_set": { "aqua_rat": 6.045650482177734, "gsm8k": 6.926578868519176, "math_qa": 5.631093343098958 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.024260803639120546, "math_qa": 0.02747068676716918 } }, { "flos": 2.577329704470053e+18, "train_loss": 5.557333374023438, "eval_loss": 6.029778867154508, "eval_accuracy": 0.028521281263712155, "eval_loss_by_set": { "aqua_rat": 6.03095817565918, "gsm8k": 6.904706087979403, "math_qa": 5.628672281901042 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.018953752843062926, "math_qa": 0.031155778894472363 } }, { "flos": 2.5833081292948767e+18, "train_loss": 5.560988159179687, "eval_loss": 6.042328190159154, "eval_accuracy": 0.03137340939008337, "eval_loss_by_set": { "aqua_rat": 6.047937393188477, "gsm8k": 6.921850724653765, "math_qa": 5.63874626159668 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.019711902956785442, "math_qa": 0.03484087102177554 } }, { "flos": 2.5892910879945523e+18, "train_loss": 5.576554565429688, "eval_loss": 6.0399395195213526, "eval_accuracy": 0.02830188679245283, "eval_loss_by_set": { "aqua_rat": 6.052460670471191, "gsm8k": 6.925804138183594, "math_qa": 5.632874806722005 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.017437452615617893, "math_qa": 0.031825795644891124 } }, { "flos": 2.595271471324463e+18, "train_loss": 5.568358154296875, "eval_loss": 6.024983122542098, "eval_accuracy": 0.032250987275120664, "eval_loss_by_set": { "aqua_rat": 6.01908016204834, "gsm8k": 6.91162802956321, "math_qa": 5.619096120198567 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.024260803639120546, "math_qa": 0.034170854271356785 } }, { "flos": 2.6012504115453624e+18, "train_loss": 5.57995361328125, "eval_loss": 6.0328546730247705, "eval_accuracy": 0.030715225976305396, "eval_loss_by_set": { "aqua_rat": 6.038986682891846, "gsm8k": 6.9198830344460225, "math_qa": 5.6257890065511065 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.021986353297952996, "math_qa": 0.033165829145728645 } }, { "flos": 2.607196688003105e+18, "train_loss": 5.567796630859375, "eval_loss": 6.0337087012626025, "eval_accuracy": 0.030495831505046072, "eval_loss_by_set": { "aqua_rat": 6.0258097648620605, "gsm8k": 6.908653952858665, "math_qa": 5.633350372314453 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.02350265352539803, "math_qa": 0.033165829145728645 } }, { "flos": 2.6131965039125463e+18, "train_loss": 5.5689892578125, "eval_loss": 6.040209332027951, "eval_accuracy": 0.031592803861342694, "eval_loss_by_set": { "aqua_rat": 6.028834342956543, "gsm8k": 6.928233059969815, "math_qa": 5.634146372477214 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.02047005307050796, "math_qa": 0.03484087102177554 } }, { "flos": 2.6192171139061514e+18, "train_loss": 5.586649169921875, "eval_loss": 6.024938325624208, "eval_accuracy": 0.02676612549363756, "eval_loss_by_set": { "aqua_rat": 6.034944534301758, "gsm8k": 6.9000937721946025, "math_qa": 5.622991561889648 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.02577710386656558, "math_qa": 0.02613065326633166 } }, { "flos": 2.6252179815457096e+18, "train_loss": 5.566541748046875, "eval_loss": 6.026591996888857, "eval_accuracy": 0.030495831505046072, "eval_loss_by_set": { "aqua_rat": 6.032402992248535, "gsm8k": 6.912539395419034, "math_qa": 5.620048522949219 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.026535253980288095, "math_qa": 0.031155778894472363 } }, { "flos": 2.631186494122885e+18, "train_loss": 5.565408325195312, "eval_loss": 6.035055882221943, "eval_accuracy": 0.030495831505046072, "eval_loss_by_set": { "aqua_rat": 6.038220405578613, "gsm8k": 6.923679698597301, "math_qa": 5.627506256103516 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.02122820318423048, "math_qa": 0.03249581239530988 } }, { "flos": 2.6371822298133955e+18, "train_loss": 5.567106323242188, "eval_loss": 6.038505734624089, "eval_accuracy": 0.027424308907415533, "eval_loss_by_set": { "aqua_rat": 6.039699077606201, "gsm8k": 6.925141074440696, "math_qa": 5.632031758626302 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.01819560272934041, "math_qa": 0.02948073701842546 } }, { "flos": 2.6431942874533724e+18, "train_loss": 5.578947143554688, "eval_loss": 6.0470476150512695, "eval_accuracy": 0.030495831505046072, "eval_loss_by_set": { "aqua_rat": 6.036888599395752, "gsm8k": 6.927284240722656, "math_qa": 5.644452412923177 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.02350265352539803, "math_qa": 0.031825795644891124 } }, { "flos": 2.649125499313324e+18, "train_loss": 5.557513427734375, "eval_loss": 6.04488401155214, "eval_accuracy": 0.032250987275120664, "eval_loss_by_set": { "aqua_rat": 6.0535407066345215, "gsm8k": 6.924097928133878, "math_qa": 5.6411895751953125 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.02350265352539803, "math_qa": 0.032160804020100506 } }, { "flos": 2.655102337684603e+18, "train_loss": 5.56725341796875, "eval_loss": 6.0456475438298405, "eval_accuracy": 0.03532250987275121, "eval_loss_by_set": { "aqua_rat": 6.052609443664551, "gsm8k": 6.927309903231534, "math_qa": 5.640972137451172 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.019711902956785442, "math_qa": 0.03919597989949749 } }, { "flos": 2.6610119109624463e+18, "train_loss": 5.565108642578125, "eval_loss": 6.042930396827492, "eval_accuracy": 0.0379552435278631, "eval_loss_by_set": { "aqua_rat": 6.0579376220703125, "gsm8k": 6.923280195756392, "math_qa": 5.638186136881511 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.021986353297952996, "math_qa": 0.04154103852596315 } }, { "flos": 2.666983535780299e+18, "train_loss": 5.558267822265625, "eval_loss": 6.040726816332018, "eval_accuracy": 0.030715225976305396, "eval_loss_by_set": { "aqua_rat": 6.032811641693115, "gsm8k": 6.916689786044034, "math_qa": 5.639903386433919 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.022744503411675512, "math_qa": 0.03249581239530988 } }, { "flos": 2.672920662347088e+18, "train_loss": 5.5615087890625, "eval_loss": 6.040698077227618, "eval_accuracy": 0.032250987275120664, "eval_loss_by_set": { "aqua_rat": 6.045063018798828, "gsm8k": 6.922649730335582, "math_qa": 5.636106491088867 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.02122820318423048, "math_qa": 0.035510887772194306 } }, { "flos": 2.678815315982287e+18, "train_loss": 5.554144287109375, "eval_loss": 6.040996139113967, "eval_accuracy": 0.02874067573497148, "eval_loss_by_set": { "aqua_rat": 6.045469284057617, "gsm8k": 6.92572715065696, "math_qa": 5.635121663411458 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.021986353297952996, "math_qa": 0.02847571189279732 } }, { "flos": 2.6848101658357924e+18, "train_loss": 5.567095336914062, "eval_loss": 6.029514261194177, "eval_accuracy": 0.029398859148749453, "eval_loss_by_set": { "aqua_rat": 6.036866188049316, "gsm8k": 6.903241244229403, "math_qa": 5.6284434000651045 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.024260803639120546, "math_qa": 0.02847571189279732 } }, { "flos": 2.6907523003344486e+18, "train_loss": 5.557403564453125, "eval_loss": 6.0493991697156755, "eval_accuracy": 0.03203159280386134, "eval_loss_by_set": { "aqua_rat": 6.060723781585693, "gsm8k": 6.929127779873935, "math_qa": 5.645246505737305 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.02350265352539803, "math_qa": 0.032160804020100506 } }, { "flos": 2.696671972154147e+18, "train_loss": 5.561212158203125, "eval_loss": 6.029867378441063, "eval_accuracy": 0.025888547608600262, "eval_loss_by_set": { "aqua_rat": 6.023852348327637, "gsm8k": 6.911747325550426, "math_qa": 5.626173655192058 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.025018953752843062, "math_qa": 0.024120603015075376 } }, { "flos": 2.7026851840665846e+18, "train_loss": 5.5627984619140625, "eval_loss": 6.037264463063833, "eval_accuracy": 0.029398859148749453, "eval_loss_by_set": { "aqua_rat": 6.048386096954346, "gsm8k": 6.921632246537642, "math_qa": 5.631002426147461 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.021986353297952996, "math_qa": 0.02847571189279732 } }, { "flos": 2.7086579416820613e+18, "train_loss": 5.567188720703125, "eval_loss": 6.04782315847036, "eval_accuracy": 0.030715225976305396, "eval_loss_by_set": { "aqua_rat": 6.0439958572387695, "gsm8k": 6.941198869185015, "math_qa": 5.638678232828776 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.024260803639120546, "math_qa": 0.031155778894472363 } }, { "flos": 2.71462045741115e+18, "train_loss": 5.555384521484375, "eval_loss": 6.032190245551032, "eval_accuracy": 0.031812198332602015, "eval_loss_by_set": { "aqua_rat": 6.038421154022217, "gsm8k": 6.9120094992897725, "math_qa": 5.628420511881511 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.024260803639120546, "math_qa": 0.0338358458961474 } }, { "flos": 2.7206275275203543e+18, "train_loss": 5.575490112304688, "eval_loss": 6.029130317069389, "eval_accuracy": 0.030495831505046072, "eval_loss_by_set": { "aqua_rat": 6.038212776184082, "gsm8k": 6.914701288396662, "math_qa": 5.622486750284831 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.019711902956785442, "math_qa": 0.0338358458961474 } }, { "flos": 2.726615123174097e+18, "train_loss": 5.569443359375, "eval_loss": 6.031473726839633, "eval_accuracy": 0.029398859148749453, "eval_loss_by_set": { "aqua_rat": 6.033397674560547, "gsm8k": 6.905381636186079, "math_qa": 5.6307722727457685 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.021986353297952996, "math_qa": 0.030485762144053602 } }, { "flos": 2.7325654599865467e+18, "train_loss": 5.5591192626953125, "eval_loss": 6.039837399044552, "eval_accuracy": 0.03137340939008337, "eval_loss_by_set": { "aqua_rat": 6.049705505371094, "gsm8k": 6.915879683061079, "math_qa": 5.637495676676433 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.02577710386656558, "math_qa": 0.031155778894472363 } }, { "flos": 2.738526286182875e+18, "train_loss": 5.561903076171875, "eval_loss": 6.036366952432169, "eval_accuracy": 0.031154014918824045, "eval_loss_by_set": { "aqua_rat": 6.051942825317383, "gsm8k": 6.913097728382457, "math_qa": 5.633234024047852 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.024260803639120546, "math_qa": 0.031155778894472363 } }, { "flos": 2.744479940857561e+18, "train_loss": 5.573428955078125, "eval_loss": 6.0327555166708455, "eval_accuracy": 0.030715225976305396, "eval_loss_by_set": { "aqua_rat": 6.033860206604004, "gsm8k": 6.914072903719815, "math_qa": 5.628726323445638 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.025018953752843062, "math_qa": 0.031825795644891124 } }, { "flos": 2.750391946160636e+18, "train_loss": 5.552734375, "eval_loss": 6.038226488474253, "eval_accuracy": 0.0298376480912681, "eval_loss_by_set": { "aqua_rat": 6.048254489898682, "gsm8k": 6.922458995472301, "math_qa": 5.632117589314778 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.024260803639120546, "math_qa": 0.03015075376884422 } }, { "flos": 2.756347722549166e+18, "train_loss": 5.5563287353515625, "eval_loss": 6.046098296706741, "eval_accuracy": 0.03444493198771391, "eval_loss_by_set": { "aqua_rat": 6.042553901672363, "gsm8k": 6.9209747314453125, "math_qa": 5.645408630371094 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.026535253980288095, "math_qa": 0.037520938023450585 } }, { "flos": 2.762313494400336e+18, "train_loss": 5.559736328125, "eval_loss": 6.036237484699971, "eval_accuracy": 0.03247038174637999, "eval_loss_by_set": { "aqua_rat": 6.031141757965088, "gsm8k": 6.928622159090909, "math_qa": 5.627652486165364 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.02577710386656558, "math_qa": 0.03450586264656617 } }, { "flos": 2.7682513425216307e+18, "train_loss": 5.570716552734375, "eval_loss": 6.044384466635214, "eval_accuracy": 0.030276437033786747, "eval_loss_by_set": { "aqua_rat": 6.049365043640137, "gsm8k": 6.929621609774503, "math_qa": 5.638235727945964 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.02122820318423048, "math_qa": 0.03149078726968174 } }, { "flos": 2.774246707771212e+18, "train_loss": 5.569277954101563, "eval_loss": 6.040658976580645, "eval_accuracy": 0.03268977621763931, "eval_loss_by_set": { "aqua_rat": 6.056966304779053, "gsm8k": 6.931252913041548, "math_qa": 5.631111145019531 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.021986353297952996, "math_qa": 0.0338358458961474 } }, { "flos": 2.780199640891392e+18, "train_loss": 5.571696166992187, "eval_loss": 6.049110412597656, "eval_accuracy": 0.027863097849934182, "eval_loss_by_set": { "aqua_rat": 6.056987762451172, "gsm8k": 6.922918146306818, "math_qa": 5.647958755493164 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.024260803639120546, "math_qa": 0.02579564489112228 } }, { "flos": 2.786166443534713e+18, "train_loss": 5.568010864257812, "eval_loss": 6.030130154377705, "eval_accuracy": 0.02830188679245283, "eval_loss_by_set": { "aqua_rat": 6.037010669708252, "gsm8k": 6.921198758212003, "math_qa": 5.6211503346761065 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.021986353297952996, "math_qa": 0.03082077051926298 } }, { "flos": 2.7920973874960794e+18, "train_loss": 5.5613818359375, "eval_loss": 6.041914115080962, "eval_accuracy": 0.031592803861342694, "eval_loss_by_set": { "aqua_rat": 6.056504726409912, "gsm8k": 6.93090196089311, "math_qa": 5.633245468139648 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.02122820318423048, "math_qa": 0.03350083752093802 } }, { "flos": 2.7980336282258637e+18, "train_loss": 5.556953125, "eval_loss": 6.0456351718387085, "eval_accuracy": 0.03203159280386134, "eval_loss_by_set": { "aqua_rat": 6.063519477844238, "gsm8k": 6.940962357954546, "math_qa": 5.633786519368489 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.02577710386656558, "math_qa": 0.03350083752093802 } }, { "flos": 2.8039975865270927e+18, "train_loss": 5.562910766601562, "eval_loss": 6.042721464827254, "eval_accuracy": 0.02830188679245283, "eval_loss_by_set": { "aqua_rat": 6.053454399108887, "gsm8k": 6.93017578125, "math_qa": 5.635077158610026 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.02047005307050796, "math_qa": 0.02780569514237856 } }, { "flos": 2.8100013801131213e+18, "train_loss": 5.570511474609375, "eval_loss": 6.0534846589371964, "eval_accuracy": 0.027424308907415533, "eval_loss_by_set": { "aqua_rat": 6.049295902252197, "gsm8k": 6.959625244140625, "math_qa": 5.638519287109375 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.01819560272934041, "math_qa": 0.030485762144053602 } }, { "flos": 2.8159404641112556e+18, "train_loss": 5.552078857421875, "eval_loss": 6.047849603601404, "eval_accuracy": 0.03400614304519526, "eval_loss_by_set": { "aqua_rat": 6.045686721801758, "gsm8k": 6.93138954856179, "math_qa": 5.643074035644531 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.021986353297952996, "math_qa": 0.037520938023450585 } }, { "flos": 2.821896941653197e+18, "train_loss": 5.559752197265625, "eval_loss": 6.0358620720940666, "eval_accuracy": 0.031592803861342694, "eval_loss_by_set": { "aqua_rat": 6.0499420166015625, "gsm8k": 6.925453186035156, "math_qa": 5.626959482828776 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.022744503411675512, "math_qa": 0.03249581239530988 } }, { "flos": 2.8278441662249697e+18, "train_loss": 5.5682568359375, "eval_loss": 6.045363967483108, "eval_accuracy": 0.03137340939008337, "eval_loss_by_set": { "aqua_rat": 6.044380187988281, "gsm8k": 6.938867742365057, "math_qa": 5.635923385620117 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.022744503411675512, "math_qa": 0.03283082077051926 } }, { "flos": 2.8338475684321034e+18, "train_loss": 5.575614624023437, "eval_loss": 6.053261086747453, "eval_accuracy": 0.03488372093023256, "eval_loss_by_set": { "aqua_rat": 6.06909704208374, "gsm8k": 6.945467168634588, "math_qa": 5.643013636271159 }, "eval_accuracy_by_set": { "aqua_rat": 0.08267716535433071, "gsm8k": 0.02350265352539803, "math_qa": 0.03584589614740368 } }, { "flos": 2.8398288580001137e+18, "train_loss": 5.567645874023437, "eval_loss": 6.037151826394571, "eval_accuracy": 0.02874067573497148, "eval_loss_by_set": { "aqua_rat": 6.046355724334717, "gsm8k": 6.926456798206676, "math_qa": 5.628786722819011 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.019711902956785442, "math_qa": 0.02914572864321608 } }, { "flos": 2.8457775664830874e+18, "train_loss": 5.566644897460938, "eval_loss": 6.040236086458774, "eval_accuracy": 0.030276437033786747, "eval_loss_by_set": { "aqua_rat": 6.046125411987305, "gsm8k": 6.924437089399858, "math_qa": 5.6344865163167315 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.02047005307050796, "math_qa": 0.030485762144053602 } }, { "flos": 2.851789046986834e+18, "train_loss": 5.575859375, "eval_loss": 6.037639721019848, "eval_accuracy": 0.028960070206230804, "eval_loss_by_set": { "aqua_rat": 6.0398712158203125, "gsm8k": 6.9354775168678975, "math_qa": 5.62594477335612 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.021986353297952996, "math_qa": 0.02981574539363484 } }, { "flos": 2.857811305174139e+18, "train_loss": 5.563358154296875, "eval_loss": 6.036736307917415, "eval_accuracy": 0.03356735410267661, "eval_loss_by_set": { "aqua_rat": 6.048758506774902, "gsm8k": 6.920358137650923, "math_qa": 5.630741119384766 }, "eval_accuracy_by_set": { "aqua_rat": 0.08267716535433071, "gsm8k": 0.024260803639120546, "math_qa": 0.03350083752093802 } }, { "flos": 2.863782290578735e+18, "train_loss": 5.563098754882812, "eval_loss": 6.049227327913852, "eval_accuracy": 0.03268977621763931, "eval_loss_by_set": { "aqua_rat": 6.050151824951172, "gsm8k": 6.935891584916548, "math_qa": 5.642762502034505 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.02350265352539803, "math_qa": 0.033165829145728645 } }, { "flos": 2.8697136876591514e+18, "train_loss": 5.5627587890625, "eval_loss": 6.048704044238941, "eval_accuracy": 0.027863097849934182, "eval_loss_by_set": { "aqua_rat": 6.063584327697754, "gsm8k": 6.945581609552557, "math_qa": 5.6363951365153 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.021986353297952996, "math_qa": 0.02847571189279732 } }, { "flos": 2.87570394189765e+18, "train_loss": 5.571358642578125, "eval_loss": 6.035402297973633, "eval_accuracy": 0.031154014918824045, "eval_loss_by_set": { "aqua_rat": 6.048527717590332, "gsm8k": 6.919795643199574, "math_qa": 5.628961563110352 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.027293404094010616, "math_qa": 0.03015075376884422 } }, { "flos": 2.881620789776351e+18, "train_loss": 5.565479125976562, "eval_loss": 6.049792186633961, "eval_accuracy": 0.03532250987275121, "eval_loss_by_set": { "aqua_rat": 6.051114559173584, "gsm8k": 6.935667558149858, "math_qa": 5.643655776977539 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.026535253980288095, "math_qa": 0.036515912897822446 } }, { "flos": 2.887604923686453e+18, "train_loss": 5.573349609375, "eval_loss": 6.041641441551414, "eval_accuracy": 0.032250987275120664, "eval_loss_by_set": { "aqua_rat": 6.050296783447266, "gsm8k": 6.919648603959517, "math_qa": 5.638500213623047 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.029567854435178165, "math_qa": 0.030485762144053602 } }, { "flos": 2.8935870174870897e+18, "train_loss": 5.564193115234375, "eval_loss": 6.041892386771537, "eval_accuracy": 0.03268977621763931, "eval_loss_by_set": { "aqua_rat": 6.052375793457031, "gsm8k": 6.92963340065696, "math_qa": 5.634137471516927 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.024260803639120546, "math_qa": 0.034170854271356785 } }, { "flos": 2.8994855038437294e+18, "train_loss": 5.55638671875, "eval_loss": 6.053055814794592, "eval_accuracy": 0.03137340939008337, "eval_loss_by_set": { "aqua_rat": 6.062655925750732, "gsm8k": 6.94451210715554, "math_qa": 5.6436716715494795 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.028051554207733132, "math_qa": 0.03149078726968174 } }, { "flos": 2.9054558299708457e+18, "train_loss": 5.564776611328125, "eval_loss": 6.030373470203297, "eval_accuracy": 0.02830188679245283, "eval_loss_by_set": { "aqua_rat": 6.031383991241455, "gsm8k": 6.910264448686079, "math_qa": 5.627005894978841 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.024260803639120546, "math_qa": 0.02814070351758794 } }, { "flos": 2.9113980879498117e+18, "train_loss": 5.5601708984375, "eval_loss": 6.05408712335535, "eval_accuracy": 0.03247038174637999, "eval_loss_by_set": { "aqua_rat": 6.068406581878662, "gsm8k": 6.931529651988637, "math_qa": 5.650732676188151 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.024260803639120546, "math_qa": 0.033165829145728645 } }, { "flos": 2.9173753176999854e+18, "train_loss": 5.56893310546875, "eval_loss": 6.047197032619167, "eval_accuracy": 0.031154014918824045, "eval_loss_by_set": { "aqua_rat": 6.057642936706543, "gsm8k": 6.927397988059304, "math_qa": 5.642901102701823 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.024260803639120546, "math_qa": 0.031825795644891124 } }, { "flos": 2.9233125473459896e+18, "train_loss": 5.562703857421875, "eval_loss": 6.049789763785697, "eval_accuracy": 0.03137340939008337, "eval_loss_by_set": { "aqua_rat": 6.055983066558838, "gsm8k": 6.915761774236506, "math_qa": 5.6523698170979815 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.027293404094010616, "math_qa": 0.030485762144053602 } }, { "flos": 2.9292943523100754e+18, "train_loss": 5.559013671875, "eval_loss": 6.049412392281197, "eval_accuracy": 0.03203159280386134, "eval_loss_by_set": { "aqua_rat": 6.050924301147461, "gsm8k": 6.9358132102272725, "math_qa": 5.643019358317058 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.022744503411675512, "math_qa": 0.033165829145728645 } }, { "flos": 2.93526014456234e+18, "train_loss": 5.5696142578125, "eval_loss": 6.052404661436339, "eval_accuracy": 0.030495831505046072, "eval_loss_by_set": { "aqua_rat": 6.058082580566406, "gsm8k": 6.924914966930043, "math_qa": 5.652030944824219 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.022744503411675512, "math_qa": 0.03149078726968174 } }, { "flos": 2.9411981161639444e+18, "train_loss": 5.556864013671875, "eval_loss": 6.040902936780775, "eval_accuracy": 0.03532250987275121, "eval_loss_by_set": { "aqua_rat": 6.053041458129883, "gsm8k": 6.922354264692827, "math_qa": 5.635892868041992 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.026535253980288095, "math_qa": 0.03584589614740368 } }, { "flos": 2.947225856340132e+18, "train_loss": 5.56885986328125, "eval_loss": 6.0405558766545475, "eval_accuracy": 0.02874067573497148, "eval_loss_by_set": { "aqua_rat": 6.049523830413818, "gsm8k": 6.9306113503196025, "math_qa": 5.631866455078125 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.022744503411675512, "math_qa": 0.02914572864321608 } }, { "flos": 2.9532136581523046e+18, "train_loss": 5.569835815429688, "eval_loss": 6.057394388559702, "eval_accuracy": 0.03203159280386134, "eval_loss_by_set": { "aqua_rat": 6.068498611450195, "gsm8k": 6.940637068314985, "math_qa": 5.651649475097656 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.02350265352539803, "math_qa": 0.03283082077051926 } }, { "flos": 2.9591432626207457e+18, "train_loss": 5.563304443359375, "eval_loss": 6.050152933275378, "eval_accuracy": 0.027424308907415533, "eval_loss_by_set": { "aqua_rat": 6.057918071746826, "gsm8k": 6.944416392933238, "math_qa": 5.63963508605957 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.017437452615617893, "math_qa": 0.02914572864321608 } }, { "flos": 2.9651482518182953e+18, "train_loss": 5.567506103515625, "eval_loss": 6.052986660519162, "eval_accuracy": 0.030276437033786747, "eval_loss_by_set": { "aqua_rat": 6.05162239074707, "gsm8k": 6.931725935502485, "math_qa": 5.6503448486328125 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.02350265352539803, "math_qa": 0.031155778894472363 } }, { "flos": 2.971058237412999e+18, "train_loss": 5.554093627929688, "eval_loss": 6.05231439745104, "eval_accuracy": 0.028960070206230804, "eval_loss_by_set": { "aqua_rat": 6.057007789611816, "gsm8k": 6.936336864124645, "math_qa": 5.646746317545573 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.022744503411675512, "math_qa": 0.02814070351758794 } }, { "flos": 2.977042226904826e+18, "train_loss": 5.565379638671875, "eval_loss": 6.041840630608636, "eval_accuracy": 0.02632733655111891, "eval_loss_by_set": { "aqua_rat": 6.046302795410156, "gsm8k": 6.930818731134588, "math_qa": 5.634020487467448 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.017437452615617893, "math_qa": 0.027135678391959798 } }, { "flos": 2.9830447636760494e+18, "train_loss": 5.568486328125, "eval_loss": 6.055727417404587, "eval_accuracy": 0.030057042562527423, "eval_loss_by_set": { "aqua_rat": 6.0630388259887695, "gsm8k": 6.947092229669744, "math_qa": 5.646575927734375 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.02350265352539803, "math_qa": 0.030485762144053602 } }, { "flos": 2.9890049504591217e+18, "train_loss": 5.56609619140625, "eval_loss": 6.058716696661872, "eval_accuracy": 0.032250987275120664, "eval_loss_by_set": { "aqua_rat": 6.065526008605957, "gsm8k": 6.956482627175071, "math_qa": 5.646673202514648 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.018953752843062926, "math_qa": 0.03484087102177554 } }, { "flos": 2.994910113879294e+18, "train_loss": 5.566434936523438, "eval_loss": 6.045622696747651, "eval_accuracy": 0.030715225976305396, "eval_loss_by_set": { "aqua_rat": 6.074278831481934, "gsm8k": 6.934752724387429, "math_qa": 5.6357167561848955 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.019711902956785442, "math_qa": 0.03249581239530988 } }, { "flos": 3.000929033803268e+18, "train_loss": 5.564778442382813, "eval_loss": 6.051119108457823, "eval_accuracy": 0.031154014918824045, "eval_loss_by_set": { "aqua_rat": 6.057008743286133, "gsm8k": 6.931800148703835, "math_qa": 5.646982828776042 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.025018953752843062, "math_qa": 0.032160804020100506 } }, { "flos": 3.0068120437821276e+18, "train_loss": 5.558419799804687, "eval_loss": 6.047580358144399, "eval_accuracy": 0.03356735410267661, "eval_loss_by_set": { "aqua_rat": 6.059100151062012, "gsm8k": 6.927881414240057, "math_qa": 5.643149058024089 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.027293404094010616, "math_qa": 0.035175879396984924 } }, { "flos": 3.0127930863895183e+18, "train_loss": 5.568631591796875, "eval_loss": 6.055422525148134, "eval_accuracy": 0.031812198332602015, "eval_loss_by_set": { "aqua_rat": 6.053877353668213, "gsm8k": 6.9462758844549, "math_qa": 5.647243499755859 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.024260803639120546, "math_qa": 0.0338358458961474 } }, { "flos": 3.0187814653379215e+18, "train_loss": 5.5609912109375, "eval_loss": 6.052990552541372, "eval_accuracy": 0.026985519964896884, "eval_loss_by_set": { "aqua_rat": 6.054688930511475, "gsm8k": 6.942614468661222, "math_qa": 5.645104726155599 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.018953752843062926, "math_qa": 0.02780569514237856 } }, { "flos": 3.0247718226556355e+18, "train_loss": 5.554647216796875, "eval_loss": 6.060636752360576, "eval_accuracy": 0.029618253620008774, "eval_loss_by_set": { "aqua_rat": 6.075538158416748, "gsm8k": 6.959561434659091, "math_qa": 5.647387822469075 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.02122820318423048, "math_qa": 0.031155778894472363 } }, { "flos": 3.030753359721136e+18, "train_loss": 5.5612548828125, "eval_loss": 6.052864280906883, "eval_accuracy": 0.031154014918824045, "eval_loss_by_set": { "aqua_rat": 6.063438415527344, "gsm8k": 6.927094893022017, "math_qa": 5.651294072469075 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.019711902956785442, "math_qa": 0.03283082077051926 } }, { "flos": 3.0367660970396877e+18, "train_loss": 5.559215698242188, "eval_loss": 6.0369291563291805, "eval_accuracy": 0.029398859148749453, "eval_loss_by_set": { "aqua_rat": 6.0450439453125, "gsm8k": 6.924864335493608, "math_qa": 5.629282633463542 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.02047005307050796, "math_qa": 0.031825795644891124 } }, { "flos": 3.042709035234099e+18, "train_loss": 5.561949462890625, "eval_loss": 6.055293237840807, "eval_accuracy": 0.03247038174637999, "eval_loss_by_set": { "aqua_rat": 6.062735080718994, "gsm8k": 6.937056107954546, "math_qa": 5.650531768798828 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.022744503411675512, "math_qa": 0.03484087102177554 } }, { "flos": 3.0486826384212623e+18, "train_loss": 5.563551635742187, "eval_loss": 6.044202546815614, "eval_accuracy": 0.03290917068889864, "eval_loss_by_set": { "aqua_rat": 6.052694320678711, "gsm8k": 6.930761163884943, "math_qa": 5.637155532836914 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.024260803639120546, "math_qa": 0.03484087102177554 } }, { "flos": 3.054633159917306e+18, "train_loss": 5.56603515625, "eval_loss": 6.044793360942119, "eval_accuracy": 0.02874067573497148, "eval_loss_by_set": { "aqua_rat": 6.05502986907959, "gsm8k": 6.921093333851207, "math_qa": 5.642302831013997 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.02350265352539803, "math_qa": 0.0288107202680067 } }, { "flos": 3.0606561396591165e+18, "train_loss": 5.561398315429687, "eval_loss": 6.044399570774388, "eval_accuracy": 0.0298376480912681, "eval_loss_by_set": { "aqua_rat": 6.047199249267578, "gsm8k": 6.924234563654119, "math_qa": 5.640908559163411 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.02047005307050796, "math_qa": 0.03149078726968174 } }, { "flos": 3.0665756670605394e+18, "train_loss": 5.562489013671875, "eval_loss": 6.046347927402806, "eval_accuracy": 0.0298376480912681, "eval_loss_by_set": { "aqua_rat": 6.039924144744873, "gsm8k": 6.934491244229403, "math_qa": 5.639817555745442 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.019711902956785442, "math_qa": 0.031825795644891124 } }, { "flos": 3.072570393433735e+18, "train_loss": 5.571422729492188, "eval_loss": 6.048935013848382, "eval_accuracy": 0.030276437033786747, "eval_loss_by_set": { "aqua_rat": 6.051633358001709, "gsm8k": 6.949401161887429, "math_qa": 5.635996500651042 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.018953752843062926, "math_qa": 0.03350083752093802 } }, { "flos": 3.078487900589916e+18, "train_loss": 5.555867919921875, "eval_loss": 6.044412148965372, "eval_accuracy": 0.030057042562527423, "eval_loss_by_set": { "aqua_rat": 6.0481109619140625, "gsm8k": 6.929677789861506, "math_qa": 5.638357162475586 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.02350265352539803, "math_qa": 0.03015075376884422 } }, { "flos": 3.084447181134889e+18, "train_loss": 5.564863891601562, "eval_loss": 6.046090538437302, "eval_accuracy": 0.025449758666081616, "eval_loss_by_set": { "aqua_rat": 6.038904666900635, "gsm8k": 6.938683943314985, "math_qa": 5.637584050496419 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.022744503411675512, "math_qa": 0.025460636515912898 } }, { "flos": 3.0904047925481964e+18, "train_loss": 5.563429565429687, "eval_loss": 6.047865841839765, "eval_accuracy": 0.029618253620008774, "eval_loss_by_set": { "aqua_rat": 6.0600175857543945, "gsm8k": 6.923936323686079, "math_qa": 5.645320892333984 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.02122820318423048, "math_qa": 0.031155778894472363 } }, { "flos": 3.096377221061804e+18, "train_loss": 5.56996826171875, "eval_loss": 6.041785936097841, "eval_accuracy": 0.03312856516015796, "eval_loss_by_set": { "aqua_rat": 6.055846214294434, "gsm8k": 6.930812488902699, "math_qa": 5.6331437428792315 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.02350265352539803, "math_qa": 0.03584589614740368 } }, { "flos": 3.1023288968303084e+18, "train_loss": 5.556396484375, "eval_loss": 6.054422842489706, "eval_accuracy": 0.029398859148749453, "eval_loss_by_set": { "aqua_rat": 6.052797317504883, "gsm8k": 6.939555775035512, "math_qa": 5.648872375488281 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.02350265352539803, "math_qa": 0.02981574539363484 } }, { "flos": 3.1082931224932516e+18, "train_loss": 5.563140869140625, "eval_loss": 6.043003597775021, "eval_accuracy": 0.031592803861342694, "eval_loss_by_set": { "aqua_rat": 6.043964385986328, "gsm8k": 6.933618718927557, "math_qa": 5.634724934895833 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.026535253980288095, "math_qa": 0.030485762144053602 } }, { "flos": 3.114214957902725e+18, "train_loss": 5.552532348632813, "eval_loss": 6.057039054664406, "eval_accuracy": 0.03334795963141729, "eval_loss_by_set": { "aqua_rat": 6.066658973693848, "gsm8k": 6.946071277965199, "math_qa": 5.648764292399089 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.019711902956785442, "math_qa": 0.03584589614740368 } }, { "flos": 3.1202217606502154e+18, "train_loss": 5.5624169921875, "eval_loss": 6.052208616926864, "eval_accuracy": 0.03093462044756472, "eval_loss_by_set": { "aqua_rat": 6.062085151672363, "gsm8k": 6.94701524214311, "math_qa": 5.641265869140625 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.017437452615617893, "math_qa": 0.03350083752093802 } }, { "flos": 3.1261540237034127e+18, "train_loss": 5.55888916015625, "eval_loss": 6.0538454313535945, "eval_accuracy": 0.02874067573497148, "eval_loss_by_set": { "aqua_rat": 6.059212684631348, "gsm8k": 6.939177079634233, "math_qa": 5.647621154785156 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.02047005307050796, "math_qa": 0.02948073701842546 } }, { "flos": 3.132116333274071e+18, "train_loss": 5.561558837890625, "eval_loss": 6.055437113787677, "eval_accuracy": 0.0298376480912681, "eval_loss_by_set": { "aqua_rat": 6.069932460784912, "gsm8k": 6.94314921985973, "math_qa": 5.647361119588216 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.02047005307050796, "math_qa": 0.032160804020100506 } }, { "flos": 3.138058364693512e+18, "train_loss": 5.559783935546875, "eval_loss": 6.049985834070154, "eval_accuracy": 0.030057042562527423, "eval_loss_by_set": { "aqua_rat": 6.049646377563477, "gsm8k": 6.933599298650568, "math_qa": 5.6450246175130205 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.021986353297952996, "math_qa": 0.03149078726968174 } }, { "flos": 3.1440025801038234e+18, "train_loss": 5.559340209960937, "eval_loss": 6.035843307907517, "eval_accuracy": 0.030057042562527423, "eval_loss_by_set": { "aqua_rat": 6.042713165283203, "gsm8k": 6.917452031915838, "math_qa": 5.6312001546223955 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.02047005307050796, "math_qa": 0.03283082077051926 } }, { "flos": 3.1499724729761137e+18, "train_loss": 5.560810546875, "eval_loss": 6.056332201571078, "eval_accuracy": 0.031812198332602015, "eval_loss_by_set": { "aqua_rat": 6.061169624328613, "gsm8k": 6.942368247292259, "math_qa": 5.649829228719075 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.02047005307050796, "math_qa": 0.034170854271356785 } }, { "flos": 3.155903149038895e+18, "train_loss": 5.556427001953125, "eval_loss": 6.047882569802774, "eval_accuracy": 0.031154014918824045, "eval_loss_by_set": { "aqua_rat": 6.0564093589782715, "gsm8k": 6.9433725530451, "math_qa": 5.636739095052083 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.02122820318423048, "math_qa": 0.03450586264656617 } }, { "flos": 3.161870775242195e+18, "train_loss": 5.561845092773438, "eval_loss": 6.05901135625066, "eval_accuracy": 0.030495831505046072, "eval_loss_by_set": { "aqua_rat": 6.067334175109863, "gsm8k": 6.944322065873579, "math_qa": 5.652550379435222 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.019711902956785442, "math_qa": 0.03350083752093802 } }, { "flos": 3.167813898657071e+18, "train_loss": 5.566221923828125, "eval_loss": 6.04776820620975, "eval_accuracy": 0.03203159280386134, "eval_loss_by_set": { "aqua_rat": 6.048712730407715, "gsm8k": 6.925503817471591, "math_qa": 5.645394007364909 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.018953752843062926, "math_qa": 0.03484087102177554 } }, { "flos": 3.1737774038392504e+18, "train_loss": 5.557081298828125, "eval_loss": 6.052757933333114, "eval_accuracy": 0.03554190434401053, "eval_loss_by_set": { "aqua_rat": 6.06746768951416, "gsm8k": 6.935849276455966, "math_qa": 5.646781921386719 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.028051554207733132, "math_qa": 0.037520938023450585 } }, { "flos": 3.1797171476517356e+18, "train_loss": 5.552625732421875, "eval_loss": 6.05412921390018, "eval_accuracy": 0.029398859148749453, "eval_loss_by_set": { "aqua_rat": 6.059350967407227, "gsm8k": 6.950479680841619, "math_qa": 5.642866770426433 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.02122820318423048, "math_qa": 0.02981574539363484 } }, { "flos": 3.185707092652589e+18, "train_loss": 5.556126708984375, "eval_loss": 6.044002842258763, "eval_accuracy": 0.029398859148749453, "eval_loss_by_set": { "aqua_rat": 6.048099517822266, "gsm8k": 6.927423650568182, "math_qa": 5.638760248819987 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.02047005307050796, "math_qa": 0.030485762144053602 } }, { "flos": 3.1916642708110705e+18, "train_loss": 5.557313842773437, "eval_loss": 6.0505616729323926, "eval_accuracy": 0.03312856516015796, "eval_loss_by_set": { "aqua_rat": 6.060661792755127, "gsm8k": 6.936777981844815, "math_qa": 5.643537521362305 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.025018953752843062, "math_qa": 0.035175879396984924 } }, { "flos": 3.1975713095213384e+18, "train_loss": 5.55338623046875, "eval_loss": 6.055518073004645, "eval_accuracy": 0.03203159280386134, "eval_loss_by_set": { "aqua_rat": 6.065578460693359, "gsm8k": 6.932678916237571, "math_qa": 5.652647654215495 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.022744503411675512, "math_qa": 0.0338358458961474 } }, { "flos": 3.2035615428218716e+18, "train_loss": 5.564739990234375, "eval_loss": 6.055416390702531, "eval_accuracy": 0.032250987275120664, "eval_loss_by_set": { "aqua_rat": 6.066161632537842, "gsm8k": 6.940187627618963, "math_qa": 5.649000803629558 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.019711902956785442, "math_qa": 0.034170854271356785 } }, { "flos": 3.20948393442961e+18, "train_loss": 5.564984130859375, "eval_loss": 6.051086657756084, "eval_accuracy": 0.03334795963141729, "eval_loss_by_set": { "aqua_rat": 6.053398609161377, "gsm8k": 6.935711253773082, "math_qa": 5.645441055297852 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.028051554207733132, "math_qa": 0.03484087102177554 } }, { "flos": 3.2155349415173816e+18, "train_loss": 5.5718115234375, "eval_loss": 6.046636968045621, "eval_accuracy": 0.03247038174637999, "eval_loss_by_set": { "aqua_rat": 6.06118631362915, "gsm8k": 6.942101218483665, "math_qa": 5.635003407796224 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.022744503411675512, "math_qa": 0.03450586264656617 } }, { "flos": 3.2214886573953516e+18, "train_loss": 5.558699951171875, "eval_loss": 6.049391411446236, "eval_accuracy": 0.02830188679245283, "eval_loss_by_set": { "aqua_rat": 6.0559186935424805, "gsm8k": 6.939614729447798, "math_qa": 5.640828450520833 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.019711902956785442, "math_qa": 0.03015075376884422 } }, { "flos": 3.2274611272480195e+18, "train_loss": 5.5544482421875, "eval_loss": 6.045121631106815, "eval_accuracy": 0.029398859148749453, "eval_loss_by_set": { "aqua_rat": 6.046504020690918, "gsm8k": 6.924879594282671, "math_qa": 5.641784032185872 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.02122820318423048, "math_qa": 0.030485762144053602 } }, { "flos": 3.233464055398138e+18, "train_loss": 5.5761376953125, "eval_loss": 6.0542462323163, "eval_accuracy": 0.029618253620008774, "eval_loss_by_set": { "aqua_rat": 6.062141418457031, "gsm8k": 6.947169910777699, "math_qa": 5.644331614176433 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.022744503411675512, "math_qa": 0.03082077051926298 } }, { "flos": 3.239446210938929e+18, "train_loss": 5.55146728515625, "eval_loss": 6.051746394183184, "eval_accuracy": 0.03312856516015796, "eval_loss_by_set": { "aqua_rat": 6.068933963775635, "gsm8k": 6.935451160777699, "math_qa": 5.645282745361328 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.02047005307050796, "math_qa": 0.037520938023450585 } }, { "flos": 3.245404934748766e+18, "train_loss": 5.5577783203125, "eval_loss": 6.044481792965451, "eval_accuracy": 0.029398859148749453, "eval_loss_by_set": { "aqua_rat": 6.049319267272949, "gsm8k": 6.935342268510298, "math_qa": 5.6357676188151045 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.021986353297952996, "math_qa": 0.030485762144053602 } }, { "flos": 3.2513539315314196e+18, "train_loss": 5.554295654296875, "eval_loss": 6.047050037899533, "eval_accuracy": 0.02830188679245283, "eval_loss_by_set": { "aqua_rat": 6.051257610321045, "gsm8k": 6.92877890846946, "math_qa": 5.6425736745198565 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.024260803639120546, "math_qa": 0.02914572864321608 } }, { "flos": 3.257299342553252e+18, "train_loss": 5.559605712890625, "eval_loss": 6.059336224117795, "eval_accuracy": 0.031812198332602015, "eval_loss_by_set": { "aqua_rat": 6.068480491638184, "gsm8k": 6.94647841020064, "math_qa": 5.651967366536458 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.02350265352539803, "math_qa": 0.032160804020100506 } }, { "flos": 3.2632789216505364e+18, "train_loss": 5.562420043945313, "eval_loss": 6.045549392700195, "eval_accuracy": 0.032250987275120664, "eval_loss_by_set": { "aqua_rat": 6.053708076477051, "gsm8k": 6.943463412198153, "math_qa": 5.633325576782227 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.02122820318423048, "math_qa": 0.03484087102177554 } }, { "flos": 3.2692752758163374e+18, "train_loss": 5.564578857421875, "eval_loss": 6.054991799431878, "eval_accuracy": 0.0298376480912681, "eval_loss_by_set": { "aqua_rat": 6.072833061218262, "gsm8k": 6.944296403364702, "math_qa": 5.645907084147136 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.022744503411675512, "math_qa": 0.031155778894472363 } }, { "flos": 3.275211392528941e+18, "train_loss": 5.552900390625, "eval_loss": 6.044279794435243, "eval_accuracy": 0.030276437033786747, "eval_loss_by_set": { "aqua_rat": 6.055172443389893, "gsm8k": 6.933330882679332, "math_qa": 5.6358903249104815 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.02350265352539803, "math_qa": 0.031155778894472363 } }, { "flos": 3.281163191777755e+18, "train_loss": 5.566780395507813, "eval_loss": 6.050023620193069, "eval_accuracy": 0.027863097849934182, "eval_loss_by_set": { "aqua_rat": 6.069117546081543, "gsm8k": 6.940283341841265, "math_qa": 5.64039675394694 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.019711902956785442, "math_qa": 0.02814070351758794 } }, { "flos": 3.2871429566323753e+18, "train_loss": 5.56725341796875, "eval_loss": 6.047872208260201, "eval_accuracy": 0.030715225976305396, "eval_loss_by_set": { "aqua_rat": 6.05509614944458, "gsm8k": 6.935836098410866, "math_qa": 5.640286763509114 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.016679302501895376, "math_qa": 0.03450586264656617 } }, { "flos": 3.293111510548611e+18, "train_loss": 5.557484130859375, "eval_loss": 6.043597556449272, "eval_accuracy": 0.03422553751645459, "eval_loss_by_set": { "aqua_rat": 6.054868698120117, "gsm8k": 6.918147693980824, "math_qa": 5.641822814941406 }, "eval_accuracy_by_set": { "aqua_rat": 0.07874015748031496, "gsm8k": 0.02880970432145565, "math_qa": 0.03283082077051926 } }, { "flos": 3.2990306873733284e+18, "train_loss": 5.55577392578125, "eval_loss": 6.049311509003511, "eval_accuracy": 0.03268977621763931, "eval_loss_by_set": { "aqua_rat": 6.061936378479004, "gsm8k": 6.942737926136363, "math_qa": 5.638772328694661 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.025018953752843062, "math_qa": 0.03350083752093802 } }, { "flos": 3.3049819921640325e+18, "train_loss": 5.5542138671875, "eval_loss": 6.045821318755278, "eval_accuracy": 0.03532250987275121, "eval_loss_by_set": { "aqua_rat": 6.058750152587891, "gsm8k": 6.925605773925781, "math_qa": 5.641509373982747 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.028051554207733132, "math_qa": 0.0371859296482412 } }, { "flos": 3.3109505256791736e+18, "train_loss": 5.563279418945313, "eval_loss": 6.044648763295767, "eval_accuracy": 0.02720491443615621, "eval_loss_by_set": { "aqua_rat": 6.061410903930664, "gsm8k": 6.932929992675781, "math_qa": 5.636123021443685 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.02047005307050796, "math_qa": 0.02814070351758794 } }, { "flos": 3.31697476277266e+18, "train_loss": 5.554556884765625, "eval_loss": 6.051885862608214, "eval_accuracy": 0.03400614304519526, "eval_loss_by_set": { "aqua_rat": 6.069278717041016, "gsm8k": 6.941583806818182, "math_qa": 5.642658233642578 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.026535253980288095, "math_qa": 0.036180904522613064 } }, { "flos": 3.3229111677849436e+18, "train_loss": 5.5600390625, "eval_loss": 6.051869443944983, "eval_accuracy": 0.030276437033786747, "eval_loss_by_set": { "aqua_rat": 6.067422389984131, "gsm8k": 6.934436451305043, "math_qa": 5.646063486735026 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.024260803639120546, "math_qa": 0.030485762144053602 } }, { "flos": 3.328865399058989e+18, "train_loss": 5.55937744140625, "eval_loss": 6.059133400788179, "eval_accuracy": 0.03312856516015796, "eval_loss_by_set": { "aqua_rat": 6.074245929718018, "gsm8k": 6.941624034534801, "math_qa": 5.653399149576823 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.024260803639120546, "math_qa": 0.03450586264656617 } }, { "flos": 3.334842773227438e+18, "train_loss": 5.563673095703125, "eval_loss": 6.047912958505991, "eval_accuracy": 0.031592803861342694, "eval_loss_by_set": { "aqua_rat": 6.058722496032715, "gsm8k": 6.9314797141335225, "math_qa": 5.6420440673828125 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.021986353297952996, "math_qa": 0.03484087102177554 } }, { "flos": 3.3408215899680276e+18, "train_loss": 5.554681396484375, "eval_loss": 6.055064072480073, "eval_accuracy": 0.02830188679245283, "eval_loss_by_set": { "aqua_rat": 6.068665504455566, "gsm8k": 6.952972412109375, "math_qa": 5.642389297485352 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.016679302501895376, "math_qa": 0.031825795644891124 } }, { "flos": 3.346729370633896e+18, "train_loss": 5.556343994140625, "eval_loss": 6.06145276250066, "eval_accuracy": 0.028082492321193506, "eval_loss_by_set": { "aqua_rat": 6.065915107727051, "gsm8k": 6.949605768377131, "math_qa": 5.654010772705078 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.02047005307050796, "math_qa": 0.02914572864321608 } }, { "flos": 3.3527146174773985e+18, "train_loss": 5.557593994140625, "eval_loss": 6.062459662153914, "eval_accuracy": 0.028082492321193506, "eval_loss_by_set": { "aqua_rat": 6.064691066741943, "gsm8k": 6.949550281871449, "math_qa": 5.655690511067708 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.018953752843062926, "math_qa": 0.02914572864321608 } }, { "flos": 3.3586612445118464e+18, "train_loss": 5.551328125, "eval_loss": 6.058768349724847, "eval_accuracy": 0.03268977621763931, "eval_loss_by_set": { "aqua_rat": 6.075774192810059, "gsm8k": 6.943999550559304, "math_qa": 5.651620229085286 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.02122820318423048, "math_qa": 0.03685092127303183 } }, { "flos": 3.364644863025873e+18, "train_loss": 5.551657104492188, "eval_loss": 6.052962535136455, "eval_accuracy": 0.031154014918824045, "eval_loss_by_set": { "aqua_rat": 6.066316604614258, "gsm8k": 6.941470059481534, "math_qa": 5.644617080688477 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.018953752843062926, "math_qa": 0.035510887772194306 } }, { "flos": 3.370617765596496e+18, "train_loss": 5.5642022705078125, "eval_loss": 6.0624425217912, "eval_accuracy": 0.03093462044756472, "eval_loss_by_set": { "aqua_rat": 6.0681352615356445, "gsm8k": 6.953244295987216, "math_qa": 5.653683980305989 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.016679302501895376, "math_qa": 0.034170854271356785 } }, { "flos": 3.37655586067841e+18, "train_loss": 5.557647094726563, "eval_loss": 6.054827019974992, "eval_accuracy": 0.030495831505046072, "eval_loss_by_set": { "aqua_rat": 6.062265872955322, "gsm8k": 6.9392478249289775, "math_qa": 5.648847579956055 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.025018953752843062, "math_qa": 0.03015075376884422 } }, { "flos": 3.3825515346287657e+18, "train_loss": 5.567315673828125, "eval_loss": 6.051072197991449, "eval_accuracy": 0.029398859148749453, "eval_loss_by_set": { "aqua_rat": 6.0620574951171875, "gsm8k": 6.941967357288707, "math_qa": 5.64182980855306 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.02047005307050796, "math_qa": 0.031155778894472363 } }, { "flos": 3.3884991505794335e+18, "train_loss": 5.550678100585937, "eval_loss": 6.052019737862252, "eval_accuracy": 0.030495831505046072, "eval_loss_by_set": { "aqua_rat": 6.062657356262207, "gsm8k": 6.941895224831321, "math_qa": 5.643273671468099 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.018953752843062926, "math_qa": 0.0338358458961474 } }, { "flos": 3.394441388157305e+18, "train_loss": 5.550819091796875, "eval_loss": 6.05986399263949, "eval_accuracy": 0.029618253620008774, "eval_loss_by_set": { "aqua_rat": 6.068161964416504, "gsm8k": 6.947892622514204, "math_qa": 5.652159372965495 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.024260803639120546, "math_qa": 0.02948073701842546 } }, { "flos": 3.400391394257273e+18, "train_loss": 5.55003173828125, "eval_loss": 6.058040464246595, "eval_accuracy": 0.02720491443615621, "eval_loss_by_set": { "aqua_rat": 6.065432548522949, "gsm8k": 6.938765092329546, "math_qa": 5.653759002685547 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.015163002274450341, "math_qa": 0.03015075376884422 } }, { "flos": 3.4063712412531425e+18, "train_loss": 5.558304443359375, "eval_loss": 6.056028211438978, "eval_accuracy": 0.030495831505046072, "eval_loss_by_set": { "aqua_rat": 6.066356658935547, "gsm8k": 6.952845486727628, "math_qa": 5.644126256306966 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.02047005307050796, "math_qa": 0.032160804020100506 } }, { "flos": 3.4123657410668134e+18, "train_loss": 5.569844970703125, "eval_loss": 6.05775498055123, "eval_accuracy": 0.029398859148749453, "eval_loss_by_set": { "aqua_rat": 6.061326026916504, "gsm8k": 6.948995416814631, "math_qa": 5.648972193400065 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.01592115238817286, "math_qa": 0.03450586264656617 } }, { "flos": 3.4183018368414515e+18, "train_loss": 5.5512017822265625, "eval_loss": 6.0492726661063525, "eval_accuracy": 0.03137340939008337, "eval_loss_by_set": { "aqua_rat": 6.0558085441589355, "gsm8k": 6.929913607510653, "math_qa": 5.645100911458333 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.026535253980288095, "math_qa": 0.031825795644891124 } }, { "flos": 3.424218376019378e+18, "train_loss": 5.555042724609375, "eval_loss": 6.048127818751979, "eval_accuracy": 0.02917946467749013, "eval_loss_by_set": { "aqua_rat": 6.06485652923584, "gsm8k": 6.93915488503196, "math_qa": 5.638346354166667 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.019711902956785442, "math_qa": 0.031155778894472363 } }, { "flos": 3.4301737615658844e+18, "train_loss": 5.552029418945312, "eval_loss": 6.054664354066591, "eval_accuracy": 0.0298376480912681, "eval_loss_by_set": { "aqua_rat": 6.076354026794434, "gsm8k": 6.94537353515625, "math_qa": 5.644615173339844 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.022744503411675512, "math_qa": 0.031155778894472363 } }, { "flos": 3.4361504759199826e+18, "train_loss": 5.56545166015625, "eval_loss": 6.06063023129025, "eval_accuracy": 0.02917946467749013, "eval_loss_by_set": { "aqua_rat": 6.067288398742676, "gsm8k": 6.954084222966975, "math_qa": 5.650575637817383 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.019711902956785442, "math_qa": 0.032160804020100506 } }, { "flos": 3.4420929604584735e+18, "train_loss": 5.564771728515625, "eval_loss": 6.057365881430136, "eval_accuracy": 0.028960070206230804, "eval_loss_by_set": { "aqua_rat": 6.058304786682129, "gsm8k": 6.95479306307706, "math_qa": 5.64596684773763 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.017437452615617893, "math_qa": 0.031825795644891124 } }, { "flos": 3.448080020315046e+18, "train_loss": 5.556994018554687, "eval_loss": 6.048482070098052, "eval_accuracy": 0.02720491443615621, "eval_loss_by_set": { "aqua_rat": 6.055983543395996, "gsm8k": 6.936968716708097, "math_qa": 5.640633900960286 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.015163002274450341, "math_qa": 0.03015075376884422 } }, { "flos": 3.454072397341131e+18, "train_loss": 5.567552490234375, "eval_loss": 6.052637357969542, "eval_accuracy": 0.031592803861342694, "eval_loss_by_set": { "aqua_rat": 6.058576583862305, "gsm8k": 6.948390613902699, "math_qa": 5.641588846842448 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.019711902956785442, "math_qa": 0.035175879396984924 } }, { "flos": 3.460027184813441e+18, "train_loss": 5.5424072265625, "eval_loss": 6.05532878154033, "eval_accuracy": 0.031154014918824045, "eval_loss_by_set": { "aqua_rat": 6.0577392578125, "gsm8k": 6.941198175603693, "math_qa": 5.6491044362386065 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.026535253980288095, "math_qa": 0.03082077051926298 } }, { "flos": 3.4660384596956283e+18, "train_loss": 5.561431274414063, "eval_loss": 6.052422368848646, "eval_accuracy": 0.028960070206230804, "eval_loss_by_set": { "aqua_rat": 6.056041240692139, "gsm8k": 6.943812977183949, "math_qa": 5.643566767374675 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.017437452615617893, "math_qa": 0.032160804020100506 } }, { "flos": 3.471989126146818e+18, "train_loss": 5.5623291015625, "eval_loss": 6.0606435827306795, "eval_accuracy": 0.03444493198771391, "eval_loss_by_set": { "aqua_rat": 6.068561553955078, "gsm8k": 6.953144420276988, "math_qa": 5.650920867919922 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.025018953752843062, "math_qa": 0.036180904522613064 } }, { "flos": 3.4779529609677373e+18, "train_loss": 5.556593017578125, "eval_loss": 6.055036235500026, "eval_accuracy": 0.03312856516015796, "eval_loss_by_set": { "aqua_rat": 6.070736885070801, "gsm8k": 6.9456259987571025, "math_qa": 5.645540873209636 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.024260803639120546, "math_qa": 0.03484087102177554 } }, { "flos": 3.483930417277436e+18, "train_loss": 5.556591186523438, "eval_loss": 6.059316093857224, "eval_accuracy": 0.03137340939008337, "eval_loss_by_set": { "aqua_rat": 6.074284076690674, "gsm8k": 6.948594526811079, "math_qa": 5.650482813517253 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.022744503411675512, "math_qa": 0.034170854271356785 } }, { "flos": 3.4898871009778074e+18, "train_loss": 5.560100708007813, "eval_loss": 6.055434768264358, "eval_accuracy": 0.031592803861342694, "eval_loss_by_set": { "aqua_rat": 6.0669403076171875, "gsm8k": 6.946605335582387, "math_qa": 5.646022796630859 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.024260803639120546, "math_qa": 0.03149078726968174 } }, { "flos": 3.4958618374994657e+18, "train_loss": 5.554712524414063, "eval_loss": 6.06132460929252, "eval_accuracy": 0.03268977621763931, "eval_loss_by_set": { "aqua_rat": 6.066695213317871, "gsm8k": 6.946719082919034, "math_qa": 5.655071258544922 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.022744503411675512, "math_qa": 0.03584589614740368 } }, { "flos": 3.5018898251731436e+18, "train_loss": 5.569210815429687, "eval_loss": 6.05261163453798, "eval_accuracy": 0.03203159280386134, "eval_loss_by_set": { "aqua_rat": 6.052340507507324, "gsm8k": 6.9388885498046875, "math_qa": 5.646423975626628 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.018953752843062926, "math_qa": 0.035175879396984924 } }, { "flos": 3.507806549571535e+18, "train_loss": 5.55548095703125, "eval_loss": 6.056573661598, "eval_accuracy": 0.030495831505046072, "eval_loss_by_set": { "aqua_rat": 6.072598457336426, "gsm8k": 6.945829911665483, "math_qa": 5.6476624806722 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.02122820318423048, "math_qa": 0.033165829145728645 } }, { "flos": 3.5137938778635633e+18, "train_loss": 5.545706787109375, "eval_loss": 6.057673686259502, "eval_accuracy": 0.035980693286529176, "eval_loss_by_set": { "aqua_rat": 6.069282531738281, "gsm8k": 6.9458840110085225, "math_qa": 5.649609883626302 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.02577710386656558, "math_qa": 0.03919597989949749 } }, { "flos": 3.519684739579511e+18, "train_loss": 5.550069580078125, "eval_loss": 6.061764820201977, "eval_accuracy": 0.03444493198771391, "eval_loss_by_set": { "aqua_rat": 6.073038578033447, "gsm8k": 6.9507904052734375, "math_qa": 5.6533552805582685 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.02047005307050796, "math_qa": 0.03886097152428811 } }, { "flos": 3.5257165605115003e+18, "train_loss": 5.562824096679687, "eval_loss": 6.054642136032517, "eval_accuracy": 0.03422553751645459, "eval_loss_by_set": { "aqua_rat": 6.0714569091796875, "gsm8k": 6.942585338245738, "math_qa": 5.646266937255859 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.02880970432145565, "math_qa": 0.03450586264656617 } }, { "flos": 3.5316843311330755e+18, "train_loss": 5.561094970703125, "eval_loss": 6.05605378022065, "eval_accuracy": 0.03137340939008337, "eval_loss_by_set": { "aqua_rat": 6.0652313232421875, "gsm8k": 6.950906926935369, "math_qa": 5.645147959391276 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.02577710386656558, "math_qa": 0.03082077051926298 } }, { "flos": 3.537645095589249e+18, "train_loss": 5.552965087890625, "eval_loss": 6.062238229287638, "eval_accuracy": 0.02874067573497148, "eval_loss_by_set": { "aqua_rat": 6.070882797241211, "gsm8k": 6.947410583496094, "math_qa": 5.655813852945964 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.022744503411675512, "math_qa": 0.02914572864321608 } }, { "flos": 3.543595432401699e+18, "train_loss": 5.554370727539062, "eval_loss": 6.0539161063529345, "eval_accuracy": 0.03137340939008337, "eval_loss_by_set": { "aqua_rat": 6.059490203857422, "gsm8k": 6.943345503373579, "math_qa": 5.645796457926433 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.028051554207733132, "math_qa": 0.031825795644891124 } }, { "flos": 3.5495757121155236e+18, "train_loss": 5.560413818359375, "eval_loss": 6.047149503553236, "eval_accuracy": 0.0298376480912681, "eval_loss_by_set": { "aqua_rat": 6.05483341217041, "gsm8k": 6.933414112437855, "math_qa": 5.6403045654296875 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.027293404094010616, "math_qa": 0.02814070351758794 } }, { "flos": 3.5555294902705193e+18, "train_loss": 5.564462890625, "eval_loss": 6.052312567427352, "eval_accuracy": 0.03312856516015796, "eval_loss_by_set": { "aqua_rat": 6.0649542808532715, "gsm8k": 6.941404169256037, "math_qa": 5.643758773803711 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.028051554207733132, "math_qa": 0.033165829145728645 } }, { "flos": 3.561483268425515e+18, "train_loss": 5.543060302734375, "eval_loss": 6.041766347111882, "eval_accuracy": 0.030715225976305396, "eval_loss_by_set": { "aqua_rat": 6.063239097595215, "gsm8k": 6.927847428755327, "math_qa": 5.633856455485026 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.02350265352539803, "math_qa": 0.031825795644891124 } }, { "flos": 3.567412398836941e+18, "train_loss": 5.552120971679687, "eval_loss": 6.0502836124317065, "eval_accuracy": 0.03247038174637999, "eval_loss_by_set": { "aqua_rat": 6.058054447174072, "gsm8k": 6.936559503728693, "math_qa": 5.643426259358724 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.02350265352539803, "math_qa": 0.034170854271356785 } }, { "flos": 3.5733852187294433e+18, "train_loss": 5.555675048828125, "eval_loss": 6.060484138694969, "eval_accuracy": 0.03554190434401053, "eval_loss_by_set": { "aqua_rat": 6.079939842224121, "gsm8k": 6.945237593217329, "math_qa": 5.653350830078125 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.02577710386656558, "math_qa": 0.03819095477386935 } }, { "flos": 3.579329393337565e+18, "train_loss": 5.557530517578125, "eval_loss": 6.055624111278637, "eval_accuracy": 0.03268977621763931, "eval_loss_by_set": { "aqua_rat": 6.0732316970825195, "gsm8k": 6.942591580477628, "math_qa": 5.647630055745442 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.025018953752843062, "math_qa": 0.03350083752093802 } }, { "flos": 3.5852480139640177e+18, "train_loss": 5.550302734375, "eval_loss": 6.0589204221158415, "eval_accuracy": 0.031812198332602015, "eval_loss_by_set": { "aqua_rat": 6.063874244689941, "gsm8k": 6.948772083629262, "math_qa": 5.650658925374349 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.021986353297952996, "math_qa": 0.03450586264656617 } }, { "flos": 3.5912618851539354e+18, "train_loss": 5.567915649414062, "eval_loss": 6.055322131595096, "eval_accuracy": 0.03334795963141729, "eval_loss_by_set": { "aqua_rat": 6.061362266540527, "gsm8k": 6.951707319779829, "math_qa": 5.643975575764974 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.021986353297952996, "math_qa": 0.035510887772194306 } }, { "flos": 3.5972552306951455e+18, "train_loss": 5.55826171875, "eval_loss": 6.060773076237859, "eval_accuracy": 0.035103115401491886, "eval_loss_by_set": { "aqua_rat": 6.069515228271484, "gsm8k": 6.945974176580256, "math_qa": 5.654327392578125 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.02577710386656558, "math_qa": 0.0371859296482412 } }, { "flos": 3.6032063706664796e+18, "train_loss": 5.553410034179688, "eval_loss": 6.054708738584776, "eval_accuracy": 0.03466432645897324, "eval_loss_by_set": { "aqua_rat": 6.067806243896484, "gsm8k": 6.944745150479403, "math_qa": 5.645683924357097 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.022744503411675512, "math_qa": 0.03886097152428811 } }, { "flos": 3.609132636334719e+18, "train_loss": 5.55615966796875, "eval_loss": 6.060365032505345, "eval_accuracy": 0.03247038174637999, "eval_loss_by_set": { "aqua_rat": 6.081573963165283, "gsm8k": 6.948387839577415, "math_qa": 5.651587168375651 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.02122820318423048, "math_qa": 0.035175879396984924 } }, { "flos": 3.6151008810133094e+18, "train_loss": 5.562438354492188, "eval_loss": 6.057905016718684, "eval_accuracy": 0.03268977621763931, "eval_loss_by_set": { "aqua_rat": 6.069465160369873, "gsm8k": 6.942614468661222, "math_qa": 5.651449839274089 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.026535253980288095, "math_qa": 0.033165829145728645 } }, { "flos": 3.6210812439421256e+18, "train_loss": 5.567066650390625, "eval_loss": 6.056510512893264, "eval_accuracy": 0.03247038174637999, "eval_loss_by_set": { "aqua_rat": 6.064609527587891, "gsm8k": 6.942889126864347, "math_qa": 5.6495787302653 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.02350265352539803, "math_qa": 0.034170854271356785 } }, { "flos": 3.6270663667684475e+18, "train_loss": 5.560771484375, "eval_loss": 6.060370831876187, "eval_accuracy": 0.03532250987275121, "eval_loss_by_set": { "aqua_rat": 6.070412635803223, "gsm8k": 6.9514853737571025, "math_qa": 5.651106516520183 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.028051554207733132, "math_qa": 0.037520938023450585 } }, { "flos": 3.632971674070024e+18, "train_loss": 5.546552124023438, "eval_loss": 6.057069829992346, "eval_accuracy": 0.031812198332602015, "eval_loss_by_set": { "aqua_rat": 6.07136344909668, "gsm8k": 6.943310824307528, "math_qa": 5.649684906005859 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.021986353297952996, "math_qa": 0.034170854271356785 } }, { "flos": 3.6389694912090604e+18, "train_loss": 5.55107177734375, "eval_loss": 6.0574618159113705, "eval_accuracy": 0.030276437033786747, "eval_loss_by_set": { "aqua_rat": 6.068559646606445, "gsm8k": 6.952029141512784, "math_qa": 5.6465269724528 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.02122820318423048, "math_qa": 0.03082077051926298 } }, { "flos": 3.644909853496836e+18, "train_loss": 5.549193115234375, "eval_loss": 6.0655828939901815, "eval_accuracy": 0.03268977621763931, "eval_loss_by_set": { "aqua_rat": 6.072761535644531, "gsm8k": 6.954025962136009, "math_qa": 5.657781600952148 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.021986353297952996, "math_qa": 0.03584589614740368 } }, { "flos": 3.650877686395437e+18, "train_loss": 5.5512060546875, "eval_loss": 6.055723396507469, "eval_accuracy": 0.031592803861342694, "eval_loss_by_set": { "aqua_rat": 6.0691328048706055, "gsm8k": 6.940778558904475, "math_qa": 5.648955663045247 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.02047005307050796, "math_qa": 0.035175879396984924 } }, { "flos": 3.656880696686805e+18, "train_loss": 5.548779296875, "eval_loss": 6.059584153665079, "eval_accuracy": 0.03444493198771391, "eval_loss_by_set": { "aqua_rat": 6.077259540557861, "gsm8k": 6.948018854314631, "math_qa": 5.650911966959636 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.025018953752843062, "math_qa": 0.03819095477386935 } }, { "flos": 3.6628799773359473e+18, "train_loss": 5.55883544921875, "eval_loss": 6.05896300238532, "eval_accuracy": 0.031592803861342694, "eval_loss_by_set": { "aqua_rat": 6.074835777282715, "gsm8k": 6.947617270729759, "math_qa": 5.650340398152669 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.02122820318423048, "math_qa": 0.035510887772194306 } }, { "flos": 3.6688681291879547e+18, "train_loss": 5.556146240234375, "eval_loss": 6.061601844993797, "eval_accuracy": 0.035761298815269855, "eval_loss_by_set": { "aqua_rat": 6.074501991271973, "gsm8k": 6.951169100674716, "math_qa": 5.652808507283528 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.025018953752843062, "math_qa": 0.03819095477386935 } }, { "flos": 3.674836992341836e+18, "train_loss": 5.553027954101562, "eval_loss": 6.0590311514364705, "eval_accuracy": 0.030276437033786747, "eval_loss_by_set": { "aqua_rat": 6.072281837463379, "gsm8k": 6.948007063432173, "math_qa": 5.650479634602864 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.02122820318423048, "math_qa": 0.03249581239530988 } }, { "flos": 3.680837262444069e+18, "train_loss": 5.557493896484375, "eval_loss": 6.063885998081517, "eval_accuracy": 0.03488372093023256, "eval_loss_by_set": { "aqua_rat": 6.078211307525635, "gsm8k": 6.951180891557173, "math_qa": 5.656015396118164 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.02880970432145565, "math_qa": 0.036180904522613064 } }, { "flos": 3.68679406962475e+18, "train_loss": 5.5527685546875, "eval_loss": 6.053513861991264, "eval_accuracy": 0.03334795963141729, "eval_loss_by_set": { "aqua_rat": 6.071709632873535, "gsm8k": 6.943241466175426, "math_qa": 5.644205729166667 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.027293404094010616, "math_qa": 0.034170854271356785 } }, { "flos": 3.69280025389695e+18, "train_loss": 5.55413818359375, "eval_loss": 6.059189100523253, "eval_accuracy": 0.03093462044756472, "eval_loss_by_set": { "aqua_rat": 6.0743608474731445, "gsm8k": 6.948468295010653, "math_qa": 5.650338490804036 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.022744503411675512, "math_qa": 0.03350083752093802 } }, { "flos": 3.6987426353562255e+18, "train_loss": 5.54634033203125, "eval_loss": 6.05936388067297, "eval_accuracy": 0.030057042562527423, "eval_loss_by_set": { "aqua_rat": 6.068507671356201, "gsm8k": 6.949931751598012, "math_qa": 5.650424957275391 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.021986353297952996, "math_qa": 0.03249581239530988 } }, { "flos": 3.7046800507595653e+18, "train_loss": 5.559100341796875, "eval_loss": 6.054580379176784, "eval_accuracy": 0.028521281263712155, "eval_loss_by_set": { "aqua_rat": 6.063756942749023, "gsm8k": 6.945220253684304, "math_qa": 5.645605723063151 }, "eval_accuracy_by_set": { "aqua_rat": 0.031496062992125984, "gsm8k": 0.018953752843062926, "math_qa": 0.03249581239530988 } }, { "flos": 3.710655961954779e+18, "train_loss": 5.5576611328125, "eval_loss": 6.058184185543576, "eval_accuracy": 0.02830188679245283, "eval_loss_by_set": { "aqua_rat": 6.0727033615112305, "gsm8k": 6.947493813254616, "math_qa": 5.649374008178711 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.02047005307050796, "math_qa": 0.031155778894472363 } }, { "flos": 3.716639003332575e+18, "train_loss": 5.555716552734375, "eval_loss": 6.053595207832955, "eval_accuracy": 0.032250987275120664, "eval_loss_by_set": { "aqua_rat": 6.06796932220459, "gsm8k": 6.941612243652344, "math_qa": 5.645389556884766 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.02047005307050796, "math_qa": 0.036180904522613064 } }, { "flos": 3.7226381809025024e+18, "train_loss": 5.554948120117188, "eval_loss": 6.053452156685494, "eval_accuracy": 0.03466432645897324, "eval_loss_by_set": { "aqua_rat": 6.0667572021484375, "gsm8k": 6.943078474564985, "math_qa": 5.644598007202148 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.025018953752843062, "math_qa": 0.03819095477386935 } }, { "flos": 3.728592020797653e+18, "train_loss": 5.558704223632812, "eval_loss": 6.059399579022382, "eval_accuracy": 0.03422553751645459, "eval_loss_by_set": { "aqua_rat": 6.069427490234375, "gsm8k": 6.950464422052557, "math_qa": 5.650159200032552 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.027293404094010616, "math_qa": 0.035175879396984924 } }, { "flos": 3.73452300609808e+18, "train_loss": 5.55464111328125, "eval_loss": 6.051964270102011, "eval_accuracy": 0.03312856516015796, "eval_loss_by_set": { "aqua_rat": 6.065739631652832, "gsm8k": 6.939356023615057, "math_qa": 5.644095102945964 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.018953752843062926, "math_qa": 0.0371859296482412 } }, { "flos": 3.740484449695957e+18, "train_loss": 5.553890380859375, "eval_loss": 6.052166552157016, "eval_accuracy": 0.0298376480912681, "eval_loss_by_set": { "aqua_rat": 6.070710182189941, "gsm8k": 6.942037409002131, "math_qa": 5.642763773600261 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.016679302501895376, "math_qa": 0.03350083752093802 } }, { "flos": 3.746468707086369e+18, "train_loss": 5.555827026367187, "eval_loss": 6.059778110401051, "eval_accuracy": 0.031154014918824045, "eval_loss_by_set": { "aqua_rat": 6.071372032165527, "gsm8k": 6.945234818892046, "math_qa": 5.652977625528972 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.019711902956785442, "math_qa": 0.035510887772194306 } }, { "flos": 3.752435530130784e+18, "train_loss": 5.555598754882812, "eval_loss": 6.064367732486209, "eval_accuracy": 0.03290917068889864, "eval_loss_by_set": { "aqua_rat": 6.077910900115967, "gsm8k": 6.962120749733665, "math_qa": 5.6517690022786455 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.025018953752843062, "math_qa": 0.03484087102177554 } }, { "flos": 3.758405671037436e+18, "train_loss": 5.55022705078125, "eval_loss": 6.055769043999749, "eval_accuracy": 0.028960070206230804, "eval_loss_by_set": { "aqua_rat": 6.067127704620361, "gsm8k": 6.952152598987926, "math_qa": 5.643980026245117 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.019711902956785442, "math_qa": 0.030485762144053602 } }, { "flos": 3.764377542815908e+18, "train_loss": 5.554290161132813, "eval_loss": 6.0509920893488705, "eval_accuracy": 0.03290917068889864, "eval_loss_by_set": { "aqua_rat": 6.05650520324707, "gsm8k": 6.942029086026278, "math_qa": 5.642140706380208 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.019711902956785442, "math_qa": 0.0371859296482412 } }, { "flos": 3.7702877141679473e+18, "train_loss": 5.545007934570313, "eval_loss": 6.0553012023100985, "eval_accuracy": 0.031154014918824045, "eval_loss_by_set": { "aqua_rat": 6.065285682678223, "gsm8k": 6.943668712269176, "math_qa": 5.647300720214844 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.021986353297952996, "math_qa": 0.033165829145728645 } }, { "flos": 3.776252991561007e+18, "train_loss": 5.55803955078125, "eval_loss": 6.057851482082057, "eval_accuracy": 0.03137340939008337, "eval_loss_by_set": { "aqua_rat": 6.06783390045166, "gsm8k": 6.943757490678267, "math_qa": 5.650979359944661 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.022744503411675512, "math_qa": 0.03283082077051926 } }, { "flos": 3.7821943637029683e+18, "train_loss": 5.5468359375, "eval_loss": 6.058991535289867, "eval_accuracy": 0.03378674857393594, "eval_loss_by_set": { "aqua_rat": 6.0747761726379395, "gsm8k": 6.951112920587713, "math_qa": 5.648787180582683 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.021986353297952996, "math_qa": 0.037520938023450585 } }, { "flos": 3.7881986109449175e+18, "train_loss": 5.5516729736328125, "eval_loss": 6.0579607680037215, "eval_accuracy": 0.03203159280386134, "eval_loss_by_set": { "aqua_rat": 6.069573402404785, "gsm8k": 6.945431795987216, "math_qa": 5.650235493977864 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.019711902956785442, "math_qa": 0.03450586264656617 } }, { "flos": 3.794139591171113e+18, "train_loss": 5.54901611328125, "eval_loss": 6.0491678392564925, "eval_accuracy": 0.03422553751645459, "eval_loss_by_set": { "aqua_rat": 6.060819625854492, "gsm8k": 6.936092029918324, "math_qa": 5.641689936319987 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.02350265352539803, "math_qa": 0.0371859296482412 } }, { "flos": 3.80019362728457e+18, "train_loss": 5.572955932617187, "eval_loss": 6.059243227984454, "eval_accuracy": 0.031592803861342694, "eval_loss_by_set": { "aqua_rat": 6.076651573181152, "gsm8k": 6.9455649636008525, "math_qa": 5.651561737060547 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.022744503411675512, "math_qa": 0.03350083752093802 } }, { "flos": 3.806137245694427e+18, "train_loss": 5.5576318359375, "eval_loss": 6.058323782843512, "eval_accuracy": 0.030276437033786747, "eval_loss_by_set": { "aqua_rat": 6.069140434265137, "gsm8k": 6.946870283647017, "math_qa": 5.6501719156901045 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.015163002274450341, "math_qa": 0.035175879396984924 } }, { "flos": 3.812110539107074e+18, "train_loss": 5.56074951171875, "eval_loss": 6.057844857911806, "eval_accuracy": 0.03137340939008337, "eval_loss_by_set": { "aqua_rat": 6.069668292999268, "gsm8k": 6.947147022594105, "math_qa": 5.64926274617513 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.017437452615617893, "math_qa": 0.03584589614740368 } }, { "flos": 3.818077670852264e+18, "train_loss": 5.558587646484375, "eval_loss": 6.056871826584275, "eval_accuracy": 0.028960070206230804, "eval_loss_by_set": { "aqua_rat": 6.071476936340332, "gsm8k": 6.949156327681108, "math_qa": 5.646691004435222 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.014404852160727824, "math_qa": 0.034170854271356785 } }, { "flos": 3.8240915624432763e+18, "train_loss": 5.566087646484375, "eval_loss": 6.063228916477513, "eval_accuracy": 0.03137340939008337, "eval_loss_by_set": { "aqua_rat": 6.0814361572265625, "gsm8k": 6.957541032270952, "math_qa": 5.651818593343099 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.018953752843062926, "math_qa": 0.03450586264656617 } }, { "flos": 3.830027411257295e+18, "train_loss": 5.5458056640625, "eval_loss": 6.0581613489099455, "eval_accuracy": 0.0298376480912681, "eval_loss_by_set": { "aqua_rat": 6.075431823730469, "gsm8k": 6.947586753151634, "math_qa": 5.649068832397461 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.017437452615617893, "math_qa": 0.0338358458961474 } }, { "flos": 3.835996645388976e+18, "train_loss": 5.549791870117187, "eval_loss": 6.054193213179305, "eval_accuracy": 0.03093462044756472, "eval_loss_by_set": { "aqua_rat": 6.068690776824951, "gsm8k": 6.944108442826704, "math_qa": 5.645107269287109 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.02122820318423048, "math_qa": 0.03283082077051926 } }, { "flos": 3.8420195429895373e+18, "train_loss": 5.564708862304688, "eval_loss": 6.057072201290646, "eval_accuracy": 0.03268977621763931, "eval_loss_by_set": { "aqua_rat": 6.073184967041016, "gsm8k": 6.945741133256392, "math_qa": 5.648422876993815 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.022744503411675512, "math_qa": 0.03484087102177554 } }, { "flos": 3.847952485721309e+18, "train_loss": 5.550535888671875, "eval_loss": 6.060747352806297, "eval_accuracy": 0.03334795963141729, "eval_loss_by_set": { "aqua_rat": 6.070847511291504, "gsm8k": 6.949992786754262, "math_qa": 5.652334849039714 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.022744503411675512, "math_qa": 0.036515912897822446 } }, { "flos": 3.8538793908028047e+18, "train_loss": 5.551788940429687, "eval_loss": 6.066188477181099, "eval_accuracy": 0.03137340939008337, "eval_loss_by_set": { "aqua_rat": 6.080810070037842, "gsm8k": 6.9599609375, "math_qa": 5.655324300130208 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.021986353297952996, "math_qa": 0.03450586264656617 } }, { "flos": 3.859814064943268e+18, "train_loss": 5.5485992431640625, "eval_loss": 6.05789413967648, "eval_accuracy": 0.03093462044756472, "eval_loss_by_set": { "aqua_rat": 6.069202899932861, "gsm8k": 6.954008622602983, "math_qa": 5.646232604980469 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.027293404094010616, "math_qa": 0.030485762144053602 } }, { "flos": 3.865778682521977e+18, "train_loss": 5.556934814453125, "eval_loss": 6.060999225925755, "eval_accuracy": 0.029618253620008774, "eval_loss_by_set": { "aqua_rat": 6.070433616638184, "gsm8k": 6.953410755504262, "math_qa": 5.651191075642903 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.02122820318423048, "math_qa": 0.03149078726968174 } }, { "flos": 3.8717290391986504e+18, "train_loss": 5.5462158203125, "eval_loss": 6.063700160464725, "eval_accuracy": 0.030715225976305396, "eval_loss_by_set": { "aqua_rat": 6.076745510101318, "gsm8k": 6.958303278142756, "math_qa": 5.652586619059245 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.02122820318423048, "math_qa": 0.03283082077051926 } }, { "flos": 3.8777237446338806e+18, "train_loss": 5.55636962890625, "eval_loss": 6.058135805903254, "eval_accuracy": 0.03093462044756472, "eval_loss_by_set": { "aqua_rat": 6.067413806915283, "gsm8k": 6.94938867742365, "math_qa": 5.648871739705403 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.024260803639120546, "math_qa": 0.032160804020100506 } }, { "flos": 3.883625672869937e+18, "train_loss": 5.545186157226563, "eval_loss": 6.054517977946514, "eval_accuracy": 0.03268977621763931, "eval_loss_by_set": { "aqua_rat": 6.0655436515808105, "gsm8k": 6.943835171786222, "math_qa": 5.645995457967122 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.027293404094010616, "math_qa": 0.03283082077051926 } }, { "flos": 3.8896236967042744e+18, "train_loss": 5.54569091796875, "eval_loss": 6.057452330718169, "eval_accuracy": 0.03356735410267661, "eval_loss_by_set": { "aqua_rat": 6.069074630737305, "gsm8k": 6.953458612615412, "math_qa": 5.645814259847005 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.02122820318423048, "math_qa": 0.037520938023450585 } }, { "flos": 3.895571931130233e+18, "train_loss": 5.545509643554688, "eval_loss": 6.063668096387708, "eval_accuracy": 0.03203159280386134, "eval_loss_by_set": { "aqua_rat": 6.080001354217529, "gsm8k": 6.955421447753906, "math_qa": 5.653586705525716 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.022744503411675512, "math_qa": 0.03283082077051926 } }, { "flos": 3.901532715987501e+18, "train_loss": 5.542611694335937, "eval_loss": 6.061884106816472, "eval_accuracy": 0.03137340939008337, "eval_loss_by_set": { "aqua_rat": 6.073883533477783, "gsm8k": 6.953562649813565, "math_qa": 5.652198155721028 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.019711902956785442, "math_qa": 0.035175879396984924 } }, { "flos": 3.907471202985181e+18, "train_loss": 5.55003662109375, "eval_loss": 6.062499123650628, "eval_accuracy": 0.03378674857393594, "eval_loss_by_set": { "aqua_rat": 6.080031394958496, "gsm8k": 6.95330810546875, "math_qa": 5.652750651041667 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.02577710386656558, "math_qa": 0.035510887772194306 } }, { "flos": 3.913449833968435e+18, "train_loss": 5.557523193359375, "eval_loss": 6.061466062391126, "eval_accuracy": 0.03247038174637999, "eval_loss_by_set": { "aqua_rat": 6.079237937927246, "gsm8k": 6.951954234730113, "math_qa": 5.651844660441081 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.02047005307050796, "math_qa": 0.035510887772194306 } }, { "flos": 3.9194083929589023e+18, "train_loss": 5.553679809570313, "eval_loss": 6.060902569745038, "eval_accuracy": 0.031812198332602015, "eval_loss_by_set": { "aqua_rat": 6.072612762451172, "gsm8k": 6.952288540926847, "math_qa": 5.651374816894531 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.019711902956785442, "math_qa": 0.035175879396984924 } }, { "flos": 3.925382078287315e+18, "train_loss": 5.55341796875, "eval_loss": 6.06226160719588, "eval_accuracy": 0.02874067573497148, "eval_loss_by_set": { "aqua_rat": 6.074672222137451, "gsm8k": 6.954376914284446, "math_qa": 5.652341206868489 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.016679302501895376, "math_qa": 0.03249581239530988 } }, { "flos": 3.9313717967286436e+18, "train_loss": 5.551539306640625, "eval_loss": 6.066299850876267, "eval_accuracy": 0.028960070206230804, "eval_loss_by_set": { "aqua_rat": 6.076904296875, "gsm8k": 6.960008101029829, "math_qa": 5.655799865722656 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.01819560272934041, "math_qa": 0.031825795644891124 } }, { "flos": 3.9372952599307223e+18, "train_loss": 5.544481201171875, "eval_loss": 6.06320453334499, "eval_accuracy": 0.03290917068889864, "eval_loss_by_set": { "aqua_rat": 6.081164360046387, "gsm8k": 6.9583823464133525, "math_qa": 5.651418050130208 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.02577710386656558, "math_qa": 0.0338358458961474 } }, { "flos": 3.943254375656325e+18, "train_loss": 5.552538452148437, "eval_loss": 6.064169007378656, "eval_accuracy": 0.03444493198771391, "eval_loss_by_set": { "aqua_rat": 6.073166370391846, "gsm8k": 6.95714638449929, "math_qa": 5.654137929280599 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.02047005307050796, "math_qa": 0.037520938023450585 } }, { "flos": 3.9492399107995075e+18, "train_loss": 5.563353881835938, "eval_loss": 6.061493229221654, "eval_accuracy": 0.03203159280386134, "eval_loss_by_set": { "aqua_rat": 6.076757431030273, "gsm8k": 6.954685557972301, "math_qa": 5.650841395060222 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.02047005307050796, "math_qa": 0.03484087102177554 } }, { "flos": 3.955165888168067e+18, "train_loss": 5.551650390625, "eval_loss": 6.05678754239469, "eval_accuracy": 0.03247038174637999, "eval_loss_by_set": { "aqua_rat": 6.071588516235352, "gsm8k": 6.946870283647017, "math_qa": 5.647599538167317 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.021986353297952996, "math_qa": 0.03450586264656617 } }, { "flos": 3.961096111111799e+18, "train_loss": 5.546860961914063, "eval_loss": 6.058716052287334, "eval_accuracy": 0.03378674857393594, "eval_loss_by_set": { "aqua_rat": 6.071064472198486, "gsm8k": 6.950228604403409, "math_qa": 5.64907709757487 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.02350265352539803, "math_qa": 0.035510887772194306 } }, { "flos": 3.967103078678659e+18, "train_loss": 5.5534765625, "eval_loss": 6.06149959564209, "eval_accuracy": 0.03137340939008337, "eval_loss_by_set": { "aqua_rat": 6.075570583343506, "gsm8k": 6.957118641246449, "math_qa": 5.649834950764974 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.02047005307050796, "math_qa": 0.034170854271356785 } }, { "flos": 3.9730740023431004e+18, "train_loss": 5.550245361328125, "eval_loss": 6.060792974523596, "eval_accuracy": 0.03356735410267661, "eval_loss_by_set": { "aqua_rat": 6.075174331665039, "gsm8k": 6.955390930175781, "math_qa": 5.649570465087891 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.02350265352539803, "math_qa": 0.036180904522613064 } }, { "flos": 3.9790476055302636e+18, "train_loss": 5.5592236328125, "eval_loss": 6.057280153841586, "eval_accuracy": 0.030495831505046072, "eval_loss_by_set": { "aqua_rat": 6.072832107543945, "gsm8k": 6.950537248091265, "math_qa": 5.64657465616862 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.022744503411675512, "math_qa": 0.031155778894472363 } }, { "flos": 3.9850124915444285e+18, "train_loss": 5.5503759765625, "eval_loss": 6.061550527005582, "eval_accuracy": 0.0298376480912681, "eval_loss_by_set": { "aqua_rat": 6.076627254486084, "gsm8k": 6.956867564808238, "math_qa": 5.649940490722656 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.016679302501895376, "math_qa": 0.033165829145728645 } }, { "flos": 3.990974780713992e+18, "train_loss": 5.545946655273437, "eval_loss": 6.060897878698401, "eval_accuracy": 0.03290917068889864, "eval_loss_by_set": { "aqua_rat": 6.0801897048950195, "gsm8k": 6.954754222523082, "math_qa": 5.649606068929036 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.02122820318423048, "math_qa": 0.03484087102177554 } }, { "flos": 3.9969477240868045e+18, "train_loss": 5.5579595947265625, "eval_loss": 6.060131536947714, "eval_accuracy": 0.030715225976305396, "eval_loss_by_set": { "aqua_rat": 6.076994895935059, "gsm8k": 6.953595248135653, "math_qa": 5.649222056070964 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.018953752843062926, "math_qa": 0.03350083752093802 } }, { "flos": 4.0029140730742047e+18, "train_loss": 5.548076171875, "eval_loss": 6.062031874785552, "eval_accuracy": 0.03554190434401053, "eval_loss_by_set": { "aqua_rat": 6.074110984802246, "gsm8k": 6.952498002485796, "math_qa": 5.652894973754883 }, "eval_accuracy_by_set": { "aqua_rat": 0.05511811023622047, "gsm8k": 0.022744503411675512, "math_qa": 0.039530988274706864 } }, { "flos": 4.0088846466988114e+18, "train_loss": 5.557817993164062, "eval_loss": 6.06333876944877, "eval_accuracy": 0.03290917068889864, "eval_loss_by_set": { "aqua_rat": 6.0795087814331055, "gsm8k": 6.956916809082031, "math_qa": 5.652434666951497 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.017437452615617893, "math_qa": 0.03685092127303183 } }, { "flos": 4.014857095076643e+18, "train_loss": 5.54479736328125, "eval_loss": 6.061308113304344, "eval_accuracy": 0.027643703378674857, "eval_loss_by_set": { "aqua_rat": 6.079184532165527, "gsm8k": 6.954068270596591, "math_qa": 5.650636672973633 }, "eval_accuracy_by_set": { "aqua_rat": 0.03543307086614173, "gsm8k": 0.017437452615617893, "math_qa": 0.03149078726968174 } }, { "flos": 4.020837622287958e+18, "train_loss": 5.554400634765625, "eval_loss": 6.057465785258525, "eval_accuracy": 0.029618253620008774, "eval_loss_by_set": { "aqua_rat": 6.072085380554199, "gsm8k": 6.946418762207031, "math_qa": 5.648810704549153 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.018953752843062926, "math_qa": 0.031825795644891124 } }, { "flos": 4.0267991077617664e+18, "train_loss": 5.552013549804688, "eval_loss": 6.0591792029303475, "eval_accuracy": 0.03203159280386134, "eval_loss_by_set": { "aqua_rat": 6.070160865783691, "gsm8k": 6.9498422796076, "math_qa": 5.650043487548828 }, "eval_accuracy_by_set": { "aqua_rat": 0.04330708661417323, "gsm8k": 0.02122820318423048, "math_qa": 0.03584589614740368 } }, { "flos": 4.0327730400507986e+18, "train_loss": 5.552098388671875, "eval_loss": 6.058662285675874, "eval_accuracy": 0.03290917068889864, "eval_loss_by_set": { "aqua_rat": 6.075887203216553, "gsm8k": 6.953575134277344, "math_qa": 5.647058486938477 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.017437452615617893, "math_qa": 0.03919597989949749 } }, { "flos": 4.038746313062351e+18, "train_loss": 5.545939331054687, "eval_loss": 6.063377792770798, "eval_accuracy": 0.03532250987275121, "eval_loss_by_set": { "aqua_rat": 6.079364776611328, "gsm8k": 6.9574363014914775, "math_qa": 5.652268727620442 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.025018953752843062, "math_qa": 0.038525963149078725 } }, { "flos": 4.044717072444293e+18, "train_loss": 5.54518310546875, "eval_loss": 6.058388039872453, "eval_accuracy": 0.035761298815269855, "eval_loss_by_set": { "aqua_rat": 6.070504665374756, "gsm8k": 6.950793179598722, "math_qa": 5.648359298706055 }, "eval_accuracy_by_set": { "aqua_rat": 0.047244094488188976, "gsm8k": 0.026535253980288095, "math_qa": 0.03886097152428811 } }, { "flos": 4.050730490515161e+18, "train_loss": 5.558506469726563, "eval_loss": 6.063336655900285, "eval_accuracy": 0.03378674857393594, "eval_loss_by_set": { "aqua_rat": 6.075582504272461, "gsm8k": 6.955712058327415, "math_qa": 5.653310775756836 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.022744503411675512, "math_qa": 0.0371859296482412 } }, { "flos": 4.05669345990017e+18, "train_loss": 5.546886596679688, "eval_loss": 6.061374973606419, "eval_accuracy": 0.03378674857393594, "eval_loss_by_set": { "aqua_rat": 6.078819274902344, "gsm8k": 6.954997669566762, "math_qa": 5.650344212849935 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.028051554207733132, "math_qa": 0.03484087102177554 } }, { "flos": 4.062677840770892e+18, "train_loss": 5.557406005859375, "eval_loss": 6.0613968823407145, "eval_accuracy": 0.03137340939008337, "eval_loss_by_set": { "aqua_rat": 6.076699256896973, "gsm8k": 6.953303943980824, "math_qa": 5.651330947875977 }, "eval_accuracy_by_set": { "aqua_rat": 0.05905511811023622, "gsm8k": 0.016679302501895376, "math_qa": 0.035510887772194306 } }, { "flos": 4.0686293726579917e+18, "train_loss": 5.552130126953125, "eval_loss": 6.061850753990379, "eval_accuracy": 0.03422553751645459, "eval_loss_by_set": { "aqua_rat": 6.077382564544678, "gsm8k": 6.954890858043324, "math_qa": 5.651246388753255 }, "eval_accuracy_by_set": { "aqua_rat": 0.07480314960629922, "gsm8k": 0.01819560272934041, "math_qa": 0.03785594639865997 } }, { "flos": 4.074601924115038e+18, "train_loss": 5.55271240234375, "eval_loss": 6.059916341626966, "eval_accuracy": 0.03247038174637999, "eval_loss_by_set": { "aqua_rat": 6.07383394241333, "gsm8k": 6.950516440651634, "math_qa": 5.650564829508464 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.018953752843062926, "math_qa": 0.03685092127303183 } }, { "flos": 4.080566500891558e+18, "train_loss": 5.552592163085937, "eval_loss": 6.061814617466283, "eval_accuracy": 0.03400614304519526, "eval_loss_by_set": { "aqua_rat": 6.075897693634033, "gsm8k": 6.953087546608665, "math_qa": 5.652140935262044 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.026535253980288095, "math_qa": 0.03484087102177554 } }, { "flos": 4.0865367448774246e+18, "train_loss": 5.555369262695312, "eval_loss": 6.062513763840134, "eval_accuracy": 0.03554190434401053, "eval_loss_by_set": { "aqua_rat": 6.079131126403809, "gsm8k": 6.957170659845525, "math_qa": 5.65107790629069 }, "eval_accuracy_by_set": { "aqua_rat": 0.07086614173228346, "gsm8k": 0.01819560272934041, "math_qa": 0.04020100502512563 } }, { "flos": 4.0925145104247685e+18, "train_loss": 5.550018920898437, "eval_loss": 6.059633512754698, "eval_accuracy": 0.031154014918824045, "eval_loss_by_set": { "aqua_rat": 6.07435417175293, "gsm8k": 6.95174824107777, "math_qa": 5.6495208740234375 }, "eval_accuracy_by_set": { "aqua_rat": 0.03937007874015748, "gsm8k": 0.022744503411675512, "math_qa": 0.034170854271356785 } }, { "flos": 4.098423197865607e+18, "train_loss": 5.5460009765625, "eval_loss": 6.059536315299369, "eval_accuracy": 0.03137340939008337, "eval_loss_by_set": { "aqua_rat": 6.075134754180908, "gsm8k": 6.953587618741122, "math_qa": 5.6484629313151045 }, "eval_accuracy_by_set": { "aqua_rat": 0.051181102362204724, "gsm8k": 0.019711902956785442, "math_qa": 0.03484087102177554 } }, { "flos": 4.104401438006837e+18, "train_loss": 5.560446166992188, "eval_loss": 6.060932004773939, "eval_accuracy": 0.03203159280386134, "eval_loss_by_set": { "aqua_rat": 6.076857566833496, "gsm8k": 6.956175370649858, "math_qa": 5.649284998575847 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.02047005307050796, "math_qa": 0.03450586264656617 } }, { "flos": 4.1103865404320645e+18, "train_loss": 5.5475390625, "eval_loss": 6.06105562158533, "eval_accuracy": 0.03466432645897324, "eval_loss_by_set": { "aqua_rat": 6.075383186340332, "gsm8k": 6.955395785245028, "math_qa": 5.649955749511719 }, "eval_accuracy_by_set": { "aqua_rat": 0.06299212598425197, "gsm8k": 0.025018953752843062, "math_qa": 0.036515912897822446 } }, { "flos": 4.116385759341052e+18, "train_loss": 5.555821533203125, "eval_loss": 6.061504518663561, "eval_accuracy": 0.03247038174637999, "eval_loss_by_set": { "aqua_rat": 6.075879096984863, "gsm8k": 6.954417142001065, "math_qa": 5.651055018107097 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.017437452615617893, "math_qa": 0.036180904522613064 } }, { "flos": 4.116385759341052e+18, "train_loss": 5.555821533203125, "eval_loss": 6.061504518663561, "eval_accuracy": 0.03247038174637999, "eval_loss_by_set": { "aqua_rat": 6.075879096984863, "gsm8k": 6.954417142001065, "math_qa": 5.651055018107097 }, "eval_accuracy_by_set": { "aqua_rat": 0.06692913385826772, "gsm8k": 0.017437452615617893, "math_qa": 0.036180904522613064 } } ]