[ { "flos": 8344000000000000.0, "train_loss": 6.3768, "eval_loss": 6.3427, "eval_accuracy": 0.0077, "eval_loss_by_set": { "aqua_rat": 6.152424335479736, "gsm8k": 6.583466963334517, "math_qa": 6.248193740844727 }, "eval_accuracy_by_set": { "aqua_rat": 0.0, "gsm8k": 0.016679302501895376, "math_qa": 0.004355108877721943 } }, { "flos": 1.669e+16, "train_loss": 5.674, "eval_loss": 6.2964, "eval_accuracy": 0.0097, "eval_loss_by_set": { "aqua_rat": 6.127630233764648, "gsm8k": 6.501551541415128, "math_qa": 6.216512044270833 }, "eval_accuracy_by_set": { "aqua_rat": 0.011811023622047244, "gsm8k": 0.014404852160727824, "math_qa": 0.007370184254606365 } }, { "flos": 2.501e+16, "train_loss": 5.6202, "eval_loss": 6.3102, "eval_accuracy": 0.0083, "eval_loss_by_set": { "aqua_rat": 6.13031005859375, "gsm8k": 6.501138166947798, "math_qa": 6.237631479899089 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01061410159211524, "math_qa": 0.007370184254606365 } }, { "flos": 3.336e+16, "train_loss": 5.5997, "eval_loss": 6.3176, "eval_accuracy": 0.0088, "eval_loss_by_set": { "aqua_rat": 6.131016731262207, "gsm8k": 6.49481201171875, "math_qa": 6.251903533935547 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01592115238817286, "math_qa": 0.005695142378559464 } }, { "flos": 4.169e+16, "train_loss": 5.5745, "eval_loss": 6.321, "eval_accuracy": 0.0103, "eval_loss_by_set": { "aqua_rat": 6.131950855255127, "gsm8k": 6.524568037553267, "math_qa": 6.2433827718098955 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.017437452615617893, "math_qa": 0.007370184254606365 } }, { "flos": 5.003e+16, "train_loss": 5.5697, "eval_loss": 6.2945, "eval_accuracy": 0.0066, "eval_loss_by_set": { "aqua_rat": 6.129327774047852, "gsm8k": 6.518950722434304, "math_qa": 6.205457051595052 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.01288855193328279, "math_qa": 0.004020100502512563 } }, { "flos": 5.84e+16, "train_loss": 5.5392, "eval_loss": 6.2893, "eval_accuracy": 0.0081, "eval_loss_by_set": { "aqua_rat": 6.108038902282715, "gsm8k": 6.44967304576527, "math_qa": 6.230856577555339 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.012130401819560273, "math_qa": 0.005360134003350084 } }, { "flos": 6.674e+16, "train_loss": 5.5196, "eval_loss": 6.2927, "eval_accuracy": 0.0088, "eval_loss_by_set": { "aqua_rat": 6.111459255218506, "gsm8k": 6.49408652565696, "math_qa": 6.215552012125651 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.017437452615617893, "math_qa": 0.004020100502512563 } }, { "flos": 7.508e+16, "train_loss": 5.5063, "eval_loss": 6.2955, "eval_accuracy": 0.0088, "eval_loss_by_set": { "aqua_rat": 6.1171183586120605, "gsm8k": 6.504412564364347, "math_qa": 6.214557647705078 }, "eval_accuracy_by_set": { "aqua_rat": 0.023622047244094488, "gsm8k": 0.01592115238817286, "math_qa": 0.004355108877721943 } }, { "flos": 8.342e+16, "train_loss": 5.5001, "eval_loss": 6.3067, "eval_accuracy": 0.0081, "eval_loss_by_set": { "aqua_rat": 6.122527122497559, "gsm8k": 6.5119760686701, "math_qa": 6.227949142456055 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.01592115238817286, "math_qa": 0.003015075376884422 } }, { "flos": 9.177e+16, "train_loss": 5.4963, "eval_loss": 6.3068, "eval_accuracy": 0.0081, "eval_loss_by_set": { "aqua_rat": 6.116511344909668, "gsm8k": 6.510828191583807, "math_qa": 6.229176839192708 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.016679302501895376, "math_qa": 0.0033500837520938024 } }, { "flos": 1.001e+17, "train_loss": 5.4989, "eval_loss": 6.3247, "eval_accuracy": 0.0097, "eval_loss_by_set": { "aqua_rat": 6.130397796630859, "gsm8k": 6.525844227183949, "math_qa": 6.248732248942058 }, "eval_accuracy_by_set": { "aqua_rat": 0.027559055118110236, "gsm8k": 0.02350265352539803, "math_qa": 0.0020100502512562816 } }, { "flos": 1.085e+17, "train_loss": 5.4999, "eval_loss": 6.28, "eval_accuracy": 0.007, "eval_loss_by_set": { "aqua_rat": 6.096288681030273, "gsm8k": 6.448364951393821, "math_qa": 6.218065897623698 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.01592115238817286, "math_qa": 0.0020100502512562816 } }, { "flos": 1.168e+17, "train_loss": 5.4914, "eval_loss": 6.3064, "eval_accuracy": 0.0077, "eval_loss_by_set": { "aqua_rat": 6.109436511993408, "gsm8k": 6.501270640980113, "math_qa": 6.233523686726888 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.019711902956785442, "math_qa": 0.001340033500837521 } }, { "flos": 1.251e+17, "train_loss": 5.4765, "eval_loss": 6.2844, "eval_accuracy": 0.0088, "eval_loss_by_set": { "aqua_rat": 6.099407196044922, "gsm8k": 6.468893571333452, "math_qa": 6.215260823567708 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.019711902956785442, "math_qa": 0.003015075376884422 } }, { "flos": 1.335e+17, "train_loss": 5.4683, "eval_loss": 6.2917, "eval_accuracy": 0.0086, "eval_loss_by_set": { "aqua_rat": 6.102294921875, "gsm8k": 6.484849409623579, "math_qa": 6.218924840291341 }, "eval_accuracy_by_set": { "aqua_rat": 0.01968503937007874, "gsm8k": 0.017437452615617893, "math_qa": 0.0036850921273031824 } }, { "flos": 1.418e+17, "train_loss": 5.4793, "eval_loss": 6.3068, "eval_accuracy": 0.007, "eval_loss_by_set": { "aqua_rat": 6.118063926696777, "gsm8k": 6.515262256969105, "math_qa": 6.226924896240234 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.016679302501895376, "math_qa": 0.002680067001675042 } }, { "flos": 1.502e+17, "train_loss": 5.4862, "eval_loss": 6.2929, "eval_accuracy": 0.0059, "eval_loss_by_set": { "aqua_rat": 6.111114501953125, "gsm8k": 6.50272646817294, "math_qa": 6.211840311686198 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.014404852160727824, "math_qa": 0.0020100502512562816 } }, { "flos": 1.585e+17, "train_loss": 5.4685, "eval_loss": 6.2836, "eval_accuracy": 0.0055, "eval_loss_by_set": { "aqua_rat": 6.109811305999756, "gsm8k": 6.498605207963423, "math_qa": 6.199535369873047 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.014404852160727824, "math_qa": 0.001340033500837521 } }, { "flos": 1.669e+17, "train_loss": 5.4715, "eval_loss": 6.2751, "eval_accuracy": 0.0068, "eval_loss_by_set": { "aqua_rat": 6.0966877937316895, "gsm8k": 6.496557755903765, "math_qa": 6.188504536946614 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01819560272934041, "math_qa": 0.0016750418760469012 } }, { "flos": 1.752e+17, "train_loss": 5.4701, "eval_loss": 6.2532, "eval_accuracy": 0.0066, "eval_loss_by_set": { "aqua_rat": 6.08678674697876, "gsm8k": 6.4701621315696025, "math_qa": 6.167672475179036 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.016679302501895376, "math_qa": 0.0023450586264656616 } }, { "flos": 1.835e+17, "train_loss": 5.4678, "eval_loss": 6.2812, "eval_accuracy": 0.0068, "eval_loss_by_set": { "aqua_rat": 6.110876560211182, "gsm8k": 6.50830078125, "math_qa": 6.191378275553386 }, "eval_accuracy_by_set": { "aqua_rat": 0.011811023622047244, "gsm8k": 0.015163002274450341, "math_qa": 0.002680067001675042 } }, { "flos": 1.919e+17, "train_loss": 5.4792, "eval_loss": 6.2891, "eval_accuracy": 0.0079, "eval_loss_by_set": { "aqua_rat": 6.111384391784668, "gsm8k": 6.502713290127841, "math_qa": 6.2059377034505205 }, "eval_accuracy_by_set": { "aqua_rat": 0.011811023622047244, "gsm8k": 0.02122820318423048, "math_qa": 0.0016750418760469012 } }, { "flos": 2.003e+17, "train_loss": 5.4469, "eval_loss": 6.2817, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.099559783935547, "gsm8k": 6.499463168057528, "math_qa": 6.19703992207845 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.015163002274450341, "math_qa": 0.0020100502512562816 } }, { "flos": 2.086e+17, "train_loss": 5.443, "eval_loss": 6.2852, "eval_accuracy": 0.0046, "eval_loss_by_set": { "aqua_rat": 6.115828514099121, "gsm8k": 6.522109291770241, "math_qa": 6.190753936767578 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.012130401819560273, "math_qa": 0.001340033500837521 } }, { "flos": 2.169e+17, "train_loss": 5.4487, "eval_loss": 6.2808, "eval_accuracy": 0.005, "eval_loss_by_set": { "aqua_rat": 6.108249187469482, "gsm8k": 6.504149003462358, "math_qa": 6.192788441975911 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.013646702047005308, "math_qa": 0.001340033500837521 } }, { "flos": 2.253e+17, "train_loss": 5.4457, "eval_loss": 6.2604, "eval_accuracy": 0.007, "eval_loss_by_set": { "aqua_rat": 6.096056938171387, "gsm8k": 6.451825228604403, "math_qa": 6.186429341634114 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.02047005307050796, "math_qa": 0.001340033500837521 } }, { "flos": 2.336e+17, "train_loss": 5.4654, "eval_loss": 6.2667, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.099778652191162, "gsm8k": 6.498971418900923, "math_qa": 6.174201329549153 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.015163002274450341, "math_qa": 0.001340033500837521 } }, { "flos": 2.42e+17, "train_loss": 5.4565, "eval_loss": 6.2472, "eval_accuracy": 0.007, "eval_loss_by_set": { "aqua_rat": 6.091784954071045, "gsm8k": 6.462314952503551, "math_qa": 6.161608378092448 }, "eval_accuracy_by_set": { "aqua_rat": 0.011811023622047244, "gsm8k": 0.01819560272934041, "math_qa": 0.0016750418760469012 } }, { "flos": 2.503e+17, "train_loss": 5.4409, "eval_loss": 6.2463, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.088776588439941, "gsm8k": 6.4782326438210225, "math_qa": 6.153158823649089 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.015163002274450341, "math_qa": 0.001340033500837521 } }, { "flos": 2.586e+17, "train_loss": 5.4267, "eval_loss": 6.2494, "eval_accuracy": 0.0059, "eval_loss_by_set": { "aqua_rat": 6.097511291503906, "gsm8k": 6.480795426802202, "math_qa": 6.155932108561198 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 2.67e+17, "train_loss": 5.4374, "eval_loss": 6.238, "eval_accuracy": 0.0059, "eval_loss_by_set": { "aqua_rat": 6.088752269744873, "gsm8k": 6.471283652565696, "math_qa": 6.143560409545898 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 2.753e+17, "train_loss": 5.4426, "eval_loss": 6.2428, "eval_accuracy": 0.0068, "eval_loss_by_set": { "aqua_rat": 6.090592384338379, "gsm8k": 6.483743840997869, "math_qa": 6.145005544026692 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.019711902956785442, "math_qa": 0.001340033500837521 } }, { "flos": 2.837e+17, "train_loss": 5.4414, "eval_loss": 6.2288, "eval_accuracy": 0.0068, "eval_loss_by_set": { "aqua_rat": 6.086564064025879, "gsm8k": 6.453077836470171, "math_qa": 6.137875874837239 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.019711902956785442, "math_qa": 0.001340033500837521 } }, { "flos": 2.92e+17, "train_loss": 5.4223, "eval_loss": 6.2473, "eval_accuracy": 0.005, "eval_loss_by_set": { "aqua_rat": 6.099801063537598, "gsm8k": 6.482866460626775, "math_qa": 6.151623407999675 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.013646702047005308, "math_qa": 0.001340033500837521 } }, { "flos": 3.004e+17, "train_loss": 5.4387, "eval_loss": 6.2226, "eval_accuracy": 0.005, "eval_loss_by_set": { "aqua_rat": 6.084864616394043, "gsm8k": 6.460751620205966, "math_qa": 6.124874750773112 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.013646702047005308, "math_qa": 0.001340033500837521 } }, { "flos": 3.087e+17, "train_loss": 5.4232, "eval_loss": 6.2259, "eval_accuracy": 0.0064, "eval_loss_by_set": { "aqua_rat": 6.090140342712402, "gsm8k": 6.468562039462003, "math_qa": 6.125944137573242 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.016679302501895376, "math_qa": 0.0016750418760469012 } }, { "flos": 3.17e+17, "train_loss": 5.4171, "eval_loss": 6.2179, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.094843864440918, "gsm8k": 6.465215509588068, "math_qa": 6.114824930826823 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 3.254e+17, "train_loss": 5.4227, "eval_loss": 6.2224, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.102873802185059, "gsm8k": 6.496129816228693, "math_qa": 6.106831868489583 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.015163002274450341, "math_qa": 0.001340033500837521 } }, { "flos": 3.337e+17, "train_loss": 5.4059, "eval_loss": 6.2107, "eval_accuracy": 0.0064, "eval_loss_by_set": { "aqua_rat": 6.07914924621582, "gsm8k": 6.4155495383522725, "math_qa": 6.127744038899739 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.01819560272934041, "math_qa": 0.001340033500837521 } }, { "flos": 3.42e+17, "train_loss": 5.4008, "eval_loss": 6.2303, "eval_accuracy": 0.0068, "eval_loss_by_set": { "aqua_rat": 6.104904651641846, "gsm8k": 6.46920429576527, "math_qa": 6.131325403849284 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.018953752843062926, "math_qa": 0.001340033500837521 } }, { "flos": 3.504e+17, "train_loss": 5.4208, "eval_loss": 6.2121, "eval_accuracy": 0.0066, "eval_loss_by_set": { "aqua_rat": 6.094965934753418, "gsm8k": 6.458857449618253, "math_qa": 6.108826955159505 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01819560272934041, "math_qa": 0.001340033500837521 } }, { "flos": 3.587e+17, "train_loss": 5.4101, "eval_loss": 6.2062, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.092215061187744, "gsm8k": 6.48055683482777, "math_qa": 6.089959462483724 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.015163002274450341, "math_qa": 0.001340033500837521 } }, { "flos": 3.67e+17, "train_loss": 5.4213, "eval_loss": 6.2223, "eval_accuracy": 0.0066, "eval_loss_by_set": { "aqua_rat": 6.099459648132324, "gsm8k": 6.461223949085582, "math_qa": 6.122962951660156 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01819560272934041, "math_qa": 0.001340033500837521 } }, { "flos": 3.754e+17, "train_loss": 5.4025, "eval_loss": 6.2195, "eval_accuracy": 0.0059, "eval_loss_by_set": { "aqua_rat": 6.095149993896484, "gsm8k": 6.4881460016424, "math_qa": 6.1066843668619795 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 3.838e+17, "train_loss": 5.4274, "eval_loss": 6.2216, "eval_accuracy": 0.0064, "eval_loss_by_set": { "aqua_rat": 6.103466987609863, "gsm8k": 6.487240184437145, "math_qa": 6.109713236490886 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.01819560272934041, "math_qa": 0.001340033500837521 } }, { "flos": 3.921e+17, "train_loss": 5.3965, "eval_loss": 6.19, "eval_accuracy": 0.0064, "eval_loss_by_set": { "aqua_rat": 6.0885396003723145, "gsm8k": 6.463203430175781, "math_qa": 6.073259353637695 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.017437452615617893, "math_qa": 0.001340033500837521 } }, { "flos": 4.005e+17, "train_loss": 5.4149, "eval_loss": 6.1891, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.084489822387695, "gsm8k": 6.426495638760653, "math_qa": 6.089049021402995 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.01592115238817286, "math_qa": 0.001340033500837521 } }, { "flos": 4.088e+17, "train_loss": 5.4128, "eval_loss": 6.1848, "eval_accuracy": 0.0059, "eval_loss_by_set": { "aqua_rat": 6.076869964599609, "gsm8k": 6.424213062633168, "math_qa": 6.084053039550781 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01592115238817286, "math_qa": 0.001340033500837521 } }, { "flos": 4.171e+17, "train_loss": 5.4102, "eval_loss": 6.1857, "eval_accuracy": 0.0055, "eval_loss_by_set": { "aqua_rat": 6.073483943939209, "gsm8k": 6.434513438831676, "math_qa": 6.080971399943034 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.014404852160727824, "math_qa": 0.001340033500837521 } }, { "flos": 4.255e+17, "train_loss": 5.3968, "eval_loss": 6.2121, "eval_accuracy": 0.007, "eval_loss_by_set": { "aqua_rat": 6.097209453582764, "gsm8k": 6.468801325017756, "math_qa": 6.1040802001953125 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.02047005307050796, "math_qa": 0.001340033500837521 } }, { "flos": 4.338e+17, "train_loss": 5.3964, "eval_loss": 6.1843, "eval_accuracy": 0.0066, "eval_loss_by_set": { "aqua_rat": 6.082108974456787, "gsm8k": 6.459865223277699, "math_qa": 6.066450754801433 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01819560272934041, "math_qa": 0.001340033500837521 } }, { "flos": 4.422e+17, "train_loss": 5.3938, "eval_loss": 6.1862, "eval_accuracy": 0.0048, "eval_loss_by_set": { "aqua_rat": 6.085331916809082, "gsm8k": 6.441335504705256, "math_qa": 6.0776112874348955 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.012130401819560273, "math_qa": 0.001340033500837521 } }, { "flos": 4.505e+17, "train_loss": 5.4012, "eval_loss": 6.1905, "eval_accuracy": 0.0059, "eval_loss_by_set": { "aqua_rat": 6.087717056274414, "gsm8k": 6.459979664195668, "math_qa": 6.075517654418945 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01592115238817286, "math_qa": 0.001340033500837521 } }, { "flos": 4.588e+17, "train_loss": 5.4047, "eval_loss": 6.1907, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.083394527435303, "gsm8k": 6.451701771129262, "math_qa": 6.080080668131511 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.015163002274450341, "math_qa": 0.001340033500837521 } }, { "flos": 4.672e+17, "train_loss": 5.405, "eval_loss": 6.2044, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.099118232727051, "gsm8k": 6.478655034845525, "math_qa": 6.087471008300781 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 4.755e+17, "train_loss": 5.4161, "eval_loss": 6.1914, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.086254596710205, "gsm8k": 6.451506874778054, "math_qa": 6.080891291300456 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 4.839e+17, "train_loss": 5.4061, "eval_loss": 6.1879, "eval_accuracy": 0.0064, "eval_loss_by_set": { "aqua_rat": 6.085782051086426, "gsm8k": 6.4380340576171875, "math_qa": 6.081692377726237 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.017437452615617893, "math_qa": 0.001340033500837521 } }, { "flos": 4.922e+17, "train_loss": 5.4009, "eval_loss": 6.1873, "eval_accuracy": 0.0048, "eval_loss_by_set": { "aqua_rat": 6.083032608032227, "gsm8k": 6.469100258567116, "math_qa": 6.06687863667806 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.012130401819560273, "math_qa": 0.001340033500837521 } }, { "flos": 5.006e+17, "train_loss": 5.4086, "eval_loss": 6.1855, "eval_accuracy": 0.0079, "eval_loss_by_set": { "aqua_rat": 6.079922199249268, "gsm8k": 6.454909584738991, "math_qa": 6.070873260498047 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.022744503411675512, "math_qa": 0.001340033500837521 } }, { "flos": 5.089e+17, "train_loss": 5.361, "eval_loss": 6.1983, "eval_accuracy": 0.0072, "eval_loss_by_set": { "aqua_rat": 6.083361625671387, "gsm8k": 6.467858748002485, "math_qa": 6.0842634836832685 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.02047005307050796, "math_qa": 0.001340033500837521 } }, { "flos": 5.172e+17, "train_loss": 5.4206, "eval_loss": 6.1885, "eval_accuracy": 0.0066, "eval_loss_by_set": { "aqua_rat": 6.086402893066406, "gsm8k": 6.465852910822088, "math_qa": 6.069862365722656 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01819560272934041, "math_qa": 0.001340033500837521 } }, { "flos": 5.256e+17, "train_loss": 5.4068, "eval_loss": 6.1817, "eval_accuracy": 0.0066, "eval_loss_by_set": { "aqua_rat": 6.086407661437988, "gsm8k": 6.44659423828125, "math_qa": 6.06820551554362 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01819560272934041, "math_qa": 0.001340033500837521 } }, { "flos": 5.339e+17, "train_loss": 5.3948, "eval_loss": 6.2021, "eval_accuracy": 0.0068, "eval_loss_by_set": { "aqua_rat": 6.092379570007324, "gsm8k": 6.481600674715909, "math_qa": 6.083179473876953 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.018953752843062926, "math_qa": 0.001340033500837521 } }, { "flos": 5.423e+17, "train_loss": 5.3958, "eval_loss": 6.1799, "eval_accuracy": 0.0059, "eval_loss_by_set": { "aqua_rat": 6.081972122192383, "gsm8k": 6.453982266512784, "math_qa": 6.0625044504801435 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01592115238817286, "math_qa": 0.001340033500837521 } }, { "flos": 5.506e+17, "train_loss": 5.4235, "eval_loss": 6.1833, "eval_accuracy": 0.0055, "eval_loss_by_set": { "aqua_rat": 6.077853202819824, "gsm8k": 6.457950245250355, "math_qa": 6.066134770711263 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.014404852160727824, "math_qa": 0.001340033500837521 } }, { "flos": 5.59e+17, "train_loss": 5.395, "eval_loss": 6.1737, "eval_accuracy": 0.0072, "eval_loss_by_set": { "aqua_rat": 6.083410739898682, "gsm8k": 6.446344549005682, "math_qa": 6.056332906087239 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.02047005307050796, "math_qa": 0.001340033500837521 } }, { "flos": 5.673e+17, "train_loss": 5.3993, "eval_loss": 6.1686, "eval_accuracy": 0.0068, "eval_loss_by_set": { "aqua_rat": 6.081304550170898, "gsm8k": 6.4429238059303975, "math_qa": 6.05015500386556 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.018953752843062926, "math_qa": 0.001340033500837521 } }, { "flos": 5.756e+17, "train_loss": 5.3859, "eval_loss": 6.1829, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.0696916580200195, "gsm8k": 6.442150462757457, "math_qa": 6.0735626220703125 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.015163002274450341, "math_qa": 0.001340033500837521 } }, { "flos": 5.84e+17, "train_loss": 5.3938, "eval_loss": 6.1788, "eval_accuracy": 0.0066, "eval_loss_by_set": { "aqua_rat": 6.084567070007324, "gsm8k": 6.46202989058061, "math_qa": 6.056814829508464 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01819560272934041, "math_qa": 0.001340033500837521 } }, { "flos": 5.923e+17, "train_loss": 5.374, "eval_loss": 6.1756, "eval_accuracy": 0.007, "eval_loss_by_set": { "aqua_rat": 6.0784759521484375, "gsm8k": 6.461965387517756, "math_qa": 6.052391688028972 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.019711902956785442, "math_qa": 0.001340033500837521 } }, { "flos": 6.007e+17, "train_loss": 5.3833, "eval_loss": 6.1648, "eval_accuracy": 0.0064, "eval_loss_by_set": { "aqua_rat": 6.071146011352539, "gsm8k": 6.434797113591975, "math_qa": 6.048851013183594 }, "eval_accuracy_by_set": { "aqua_rat": 0.011811023622047244, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 6.09e+17, "train_loss": 5.3766, "eval_loss": 6.1591, "eval_accuracy": 0.0068, "eval_loss_by_set": { "aqua_rat": 6.074350357055664, "gsm8k": 6.460832075639204, "math_qa": 6.027873992919922 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.018953752843062926, "math_qa": 0.001340033500837521 } }, { "flos": 6.173e+17, "train_loss": 5.4043, "eval_loss": 6.1531, "eval_accuracy": 0.007, "eval_loss_by_set": { "aqua_rat": 6.069973945617676, "gsm8k": 6.4363625266335225, "math_qa": 6.030171712239583 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.019711902956785442, "math_qa": 0.001340033500837521 } }, { "flos": 6.257e+17, "train_loss": 5.3758, "eval_loss": 6.1772, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.083588123321533, "gsm8k": 6.466828086159446, "math_qa": 6.052293141682942 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 6.34e+17, "train_loss": 5.3889, "eval_loss": 6.1796, "eval_accuracy": 0.0072, "eval_loss_by_set": { "aqua_rat": 6.087658405303955, "gsm8k": 6.479916659268466, "math_qa": 6.049660364786784 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.02047005307050796, "math_qa": 0.001340033500837521 } }, { "flos": 6.424e+17, "train_loss": 5.3771, "eval_loss": 6.1572, "eval_accuracy": 0.0059, "eval_loss_by_set": { "aqua_rat": 6.078010082244873, "gsm8k": 6.436308427290483, "math_qa": 6.035820007324219 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01592115238817286, "math_qa": 0.001340033500837521 } }, { "flos": 6.507e+17, "train_loss": 5.3961, "eval_loss": 6.1787, "eval_accuracy": 0.0048, "eval_loss_by_set": { "aqua_rat": 6.0843987464904785, "gsm8k": 6.46026611328125, "math_qa": 6.057482401529948 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.012130401819560273, "math_qa": 0.001340033500837521 } }, { "flos": 6.59e+17, "train_loss": 5.3984, "eval_loss": 6.1664, "eval_accuracy": 0.0059, "eval_loss_by_set": { "aqua_rat": 6.079687595367432, "gsm8k": 6.451474276455966, "math_qa": 6.042946497599284 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01592115238817286, "math_qa": 0.001340033500837521 } }, { "flos": 6.674e+17, "train_loss": 5.413, "eval_loss": 6.1587, "eval_accuracy": 0.0066, "eval_loss_by_set": { "aqua_rat": 6.069234371185303, "gsm8k": 6.423649181019176, "math_qa": 6.044656117757161 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01819560272934041, "math_qa": 0.001340033500837521 } }, { "flos": 6.757e+17, "train_loss": 5.3671, "eval_loss": 6.1762, "eval_accuracy": 0.0066, "eval_loss_by_set": { "aqua_rat": 6.075897216796875, "gsm8k": 6.459019747647372, "math_qa": 6.054943720499675 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01819560272934041, "math_qa": 0.001340033500837521 } }, { "flos": 6.841e+17, "train_loss": 5.379, "eval_loss": 6.1945, "eval_accuracy": 0.0066, "eval_loss_by_set": { "aqua_rat": 6.08323335647583, "gsm8k": 6.4658966064453125, "math_qa": 6.07937749226888 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01819560272934041, "math_qa": 0.001340033500837521 } }, { "flos": 6.924e+17, "train_loss": 5.3973, "eval_loss": 6.1659, "eval_accuracy": 0.0064, "eval_loss_by_set": { "aqua_rat": 6.081808567047119, "gsm8k": 6.439580050381747, "math_qa": 6.047472635904948 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.017437452615617893, "math_qa": 0.001340033500837521 } }, { "flos": 7.008e+17, "train_loss": 5.3876, "eval_loss": 6.1582, "eval_accuracy": 0.0068, "eval_loss_by_set": { "aqua_rat": 6.073687553405762, "gsm8k": 6.447984175248579, "math_qa": 6.032442092895508 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.018953752843062926, "math_qa": 0.001340033500837521 } }, { "flos": 7.091e+17, "train_loss": 5.395, "eval_loss": 6.1776, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.088944435119629, "gsm8k": 6.462923916903409, "math_qa": 6.054239908854167 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 7.175e+17, "train_loss": 5.3966, "eval_loss": 6.174, "eval_accuracy": 0.0079, "eval_loss_by_set": { "aqua_rat": 6.084561824798584, "gsm8k": 6.4574432373046875, "math_qa": 6.051617940266927 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.022744503411675512, "math_qa": 0.001340033500837521 } }, { "flos": 7.258e+17, "train_loss": 5.3695, "eval_loss": 6.1586, "eval_accuracy": 0.0068, "eval_loss_by_set": { "aqua_rat": 6.07827091217041, "gsm8k": 6.440763993696733, "math_qa": 6.035910924275716 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.018953752843062926, "math_qa": 0.001340033500837521 } }, { "flos": 7.342e+17, "train_loss": 5.3708, "eval_loss": 6.1697, "eval_accuracy": 0.0059, "eval_loss_by_set": { "aqua_rat": 6.079062461853027, "gsm8k": 6.453514099121094, "math_qa": 6.047183990478516 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01592115238817286, "math_qa": 0.001340033500837521 } }, { "flos": 7.425e+17, "train_loss": 5.3789, "eval_loss": 6.1672, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.080084800720215, "gsm8k": 6.45553935657848, "math_qa": 6.042311350504558 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 7.508e+17, "train_loss": 5.3718, "eval_loss": 6.176, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.090424537658691, "gsm8k": 6.4713217995383525, "math_qa": 6.047728856404622 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 7.592e+17, "train_loss": 5.3728, "eval_loss": 6.1592, "eval_accuracy": 0.0059, "eval_loss_by_set": { "aqua_rat": 6.072979927062988, "gsm8k": 6.4303810813210225, "math_qa": 6.042096455891927 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01592115238817286, "math_qa": 0.001340033500837521 } }, { "flos": 7.675e+17, "train_loss": 5.3837, "eval_loss": 6.1664, "eval_accuracy": 0.0064, "eval_loss_by_set": { "aqua_rat": 6.082969665527344, "gsm8k": 6.452913457697088, "math_qa": 6.0419921875 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.017437452615617893, "math_qa": 0.001340033500837521 } }, { "flos": 7.758e+17, "train_loss": 5.3978, "eval_loss": 6.1614, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.0771484375, "gsm8k": 6.451404918323863, "math_qa": 6.035561879475911 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.015163002274450341, "math_qa": 0.001340033500837521 } }, { "flos": 7.842e+17, "train_loss": 5.3877, "eval_loss": 6.1714, "eval_accuracy": 0.0055, "eval_loss_by_set": { "aqua_rat": 6.0838727951049805, "gsm8k": 6.4619272405451, "math_qa": 6.045560201009114 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.014404852160727824, "math_qa": 0.001340033500837521 } }, { "flos": 7.925e+17, "train_loss": 5.3636, "eval_loss": 6.1684, "eval_accuracy": 0.0066, "eval_loss_by_set": { "aqua_rat": 6.076985836029053, "gsm8k": 6.458904613148082, "math_qa": 6.042924245198567 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01819560272934041, "math_qa": 0.001340033500837521 } }, { "flos": 8.008e+17, "train_loss": 5.3562, "eval_loss": 6.1591, "eval_accuracy": 0.0064, "eval_loss_by_set": { "aqua_rat": 6.073703765869141, "gsm8k": 6.435189680619673, "math_qa": 6.039730707804362 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.017437452615617893, "math_qa": 0.001340033500837521 } }, { "flos": 8.092e+17, "train_loss": 5.382, "eval_loss": 6.1645, "eval_accuracy": 0.0072, "eval_loss_by_set": { "aqua_rat": 6.078795909881592, "gsm8k": 6.447138699618253, "math_qa": 6.042115529378255 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.02047005307050796, "math_qa": 0.001340033500837521 } }, { "flos": 8.175e+17, "train_loss": 5.3785, "eval_loss": 6.1635, "eval_accuracy": 0.0055, "eval_loss_by_set": { "aqua_rat": 6.0737199783325195, "gsm8k": 6.448199185458097, "math_qa": 6.040439605712891 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.014404852160727824, "math_qa": 0.001340033500837521 } }, { "flos": 8.259e+17, "train_loss": 5.3931, "eval_loss": 6.1711, "eval_accuracy": 0.0066, "eval_loss_by_set": { "aqua_rat": 6.0859551429748535, "gsm8k": 6.458102139559659, "math_qa": 6.046674092610677 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01819560272934041, "math_qa": 0.001340033500837521 } }, { "flos": 8.342e+17, "train_loss": 5.3664, "eval_loss": 6.1547, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.079275608062744, "gsm8k": 6.433806679465554, "math_qa": 6.033093770345052 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.015163002274450341, "math_qa": 0.001340033500837521 } }, { "flos": 8.426e+17, "train_loss": 5.3665, "eval_loss": 6.1667, "eval_accuracy": 0.0066, "eval_loss_by_set": { "aqua_rat": 6.084194183349609, "gsm8k": 6.456151095303622, "math_qa": 6.040907541910808 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01819560272934041, "math_qa": 0.001340033500837521 } }, { "flos": 8.509e+17, "train_loss": 5.383, "eval_loss": 6.1604, "eval_accuracy": 0.0059, "eval_loss_by_set": { "aqua_rat": 6.079100608825684, "gsm8k": 6.4447153264826, "math_qa": 6.0368913014729815 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01592115238817286, "math_qa": 0.001340033500837521 } }, { "flos": 8.592e+17, "train_loss": 5.3852, "eval_loss": 6.1678, "eval_accuracy": 0.0064, "eval_loss_by_set": { "aqua_rat": 6.079319477081299, "gsm8k": 6.462890625, "math_qa": 6.039875666300456 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.017437452615617893, "math_qa": 0.001340033500837521 } }, { "flos": 8.676e+17, "train_loss": 5.3799, "eval_loss": 6.1714, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.084506034851074, "gsm8k": 6.45489501953125, "math_qa": 6.048638025919597 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 8.759e+17, "train_loss": 5.3704, "eval_loss": 6.148, "eval_accuracy": 0.005, "eval_loss_by_set": { "aqua_rat": 6.064852237701416, "gsm8k": 6.42432334206321, "math_qa": 6.028344472249349 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01288855193328279, "math_qa": 0.001340033500837521 } }, { "flos": 8.843e+17, "train_loss": 5.3883, "eval_loss": 6.1742, "eval_accuracy": 0.0059, "eval_loss_by_set": { "aqua_rat": 6.091931343078613, "gsm8k": 6.475805109197443, "math_qa": 6.042844136555989 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01592115238817286, "math_qa": 0.001340033500837521 } }, { "flos": 8.926e+17, "train_loss": 5.3945, "eval_loss": 6.1597, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.078987121582031, "gsm8k": 6.447112343528054, "math_qa": 6.034735361735026 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.015163002274450341, "math_qa": 0.001340033500837521 } }, { "flos": 9.01e+17, "train_loss": 5.3703, "eval_loss": 6.1625, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.0849928855896, "gsm8k": 6.473345669833097, "math_qa": 6.026564915974935 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 9.093e+17, "train_loss": 5.3733, "eval_loss": 6.1702, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.085886001586914, "gsm8k": 6.44855360551314, "math_qa": 6.049612681070964 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.01592115238817286, "math_qa": 0.001340033500837521 } }, { "flos": 9.177e+17, "train_loss": 5.3576, "eval_loss": 6.1666, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.084629535675049, "gsm8k": 6.456479159268466, "math_qa": 6.040608088175456 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 9.26e+17, "train_loss": 5.3635, "eval_loss": 6.1739, "eval_accuracy": 0.0064, "eval_loss_by_set": { "aqua_rat": 6.088237762451172, "gsm8k": 6.46553525057706, "math_qa": 6.047390619913737 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.017437452615617893, "math_qa": 0.001340033500837521 } }, { "flos": 9.344e+17, "train_loss": 5.3813, "eval_loss": 6.1671, "eval_accuracy": 0.0064, "eval_loss_by_set": { "aqua_rat": 6.078421592712402, "gsm8k": 6.447659579190341, "math_qa": 6.045846939086914 }, "eval_accuracy_by_set": { "aqua_rat": 0.011811023622047244, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 9.427e+17, "train_loss": 5.3612, "eval_loss": 6.1643, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.078129291534424, "gsm8k": 6.435503179376775, "math_qa": 6.047214508056641 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 9.51e+17, "train_loss": 5.3919, "eval_loss": 6.1497, "eval_accuracy": 0.0059, "eval_loss_by_set": { "aqua_rat": 6.069518089294434, "gsm8k": 6.427023454145952, "math_qa": 6.029343922932942 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 9.594e+17, "train_loss": 5.3647, "eval_loss": 6.1635, "eval_accuracy": 0.0068, "eval_loss_by_set": { "aqua_rat": 6.084902763366699, "gsm8k": 6.431009465997869, "math_qa": 6.047400156656901 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.019711902956785442, "math_qa": 0.001340033500837521 } }, { "flos": 9.677e+17, "train_loss": 5.347, "eval_loss": 6.1422, "eval_accuracy": 0.007, "eval_loss_by_set": { "aqua_rat": 6.0721845626831055, "gsm8k": 6.432535344904119, "math_qa": 6.014944076538086 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.019711902956785442, "math_qa": 0.001340033500837521 } }, { "flos": 9.761e+17, "train_loss": 5.3687, "eval_loss": 6.1631, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.08431339263916, "gsm8k": 6.455214066938921, "math_qa": 6.035758972167969 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.015163002274450341, "math_qa": 0.001340033500837521 } }, { "flos": 9.844e+17, "train_loss": 5.375, "eval_loss": 6.1574, "eval_accuracy": 0.0066, "eval_loss_by_set": { "aqua_rat": 6.079107284545898, "gsm8k": 6.4423911354758525, "math_qa": 6.0333506266276045 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01819560272934041, "math_qa": 0.001340033500837521 } }, { "flos": 9.927e+17, "train_loss": 5.3887, "eval_loss": 6.1632, "eval_accuracy": 0.0046, "eval_loss_by_set": { "aqua_rat": 6.086674213409424, "gsm8k": 6.449316544966265, "math_qa": 6.038408279418945 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.012130401819560273, "math_qa": 0.001340033500837521 } }, { "flos": 1.001e+18, "train_loss": 5.375, "eval_loss": 6.1674, "eval_accuracy": 0.0059, "eval_loss_by_set": { "aqua_rat": 6.08617639541626, "gsm8k": 6.453376770019531, "math_qa": 6.043121337890625 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01592115238817286, "math_qa": 0.001340033500837521 } }, { "flos": 1.009e+18, "train_loss": 5.3618, "eval_loss": 6.1712, "eval_accuracy": 0.0059, "eval_loss_by_set": { "aqua_rat": 6.082624435424805, "gsm8k": 6.449904701926491, "math_qa": 6.050828297932942 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 1.018e+18, "train_loss": 5.3849, "eval_loss": 6.1702, "eval_accuracy": 0.0048, "eval_loss_by_set": { "aqua_rat": 6.092123031616211, "gsm8k": 6.465029629794034, "math_qa": 6.041512807210286 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.01288855193328279, "math_qa": 0.001340033500837521 } }, { "flos": 1.026e+18, "train_loss": 5.368, "eval_loss": 6.1434, "eval_accuracy": 0.0053, "eval_loss_by_set": { "aqua_rat": 6.068844795227051, "gsm8k": 6.428285078568892, "math_qa": 6.018980026245117 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.013646702047005308, "math_qa": 0.001340033500837521 } }, { "flos": 1.034e+18, "train_loss": 5.3625, "eval_loss": 6.1547, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.081298351287842, "gsm8k": 6.448145779696378, "math_qa": 6.026334126790364 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.015163002274450341, "math_qa": 0.001340033500837521 } }, { "flos": 1.043e+18, "train_loss": 5.3754, "eval_loss": 6.1507, "eval_accuracy": 0.0055, "eval_loss_by_set": { "aqua_rat": 6.074888706207275, "gsm8k": 6.437116449529475, "math_qa": 6.02573839823405 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.015163002274450341, "math_qa": 0.001340033500837521 } }, { "flos": 1.051e+18, "train_loss": 5.3651, "eval_loss": 6.1584, "eval_accuracy": 0.0064, "eval_loss_by_set": { "aqua_rat": 6.07520866394043, "gsm8k": 6.452166470614347, "math_qa": 6.0307362874348955 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.017437452615617893, "math_qa": 0.001340033500837521 } }, { "flos": 1.06e+18, "train_loss": 5.3721, "eval_loss": 6.172, "eval_accuracy": 0.0059, "eval_loss_by_set": { "aqua_rat": 6.083588600158691, "gsm8k": 6.4640724875710225, "math_qa": 6.045446395874023 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01592115238817286, "math_qa": 0.001340033500837521 } }, { "flos": 1.068e+18, "train_loss": 5.3702, "eval_loss": 6.1628, "eval_accuracy": 0.0055, "eval_loss_by_set": { "aqua_rat": 6.078520774841309, "gsm8k": 6.439174305308949, "math_qa": 6.043079376220703 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.014404852160727824, "math_qa": 0.001340033500837521 } }, { "flos": 1.076e+18, "train_loss": 5.3966, "eval_loss": 6.1518, "eval_accuracy": 0.0055, "eval_loss_by_set": { "aqua_rat": 6.079293251037598, "gsm8k": 6.449168118563565, "math_qa": 6.021507263183594 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.014404852160727824, "math_qa": 0.001340033500837521 } }, { "flos": 1.085e+18, "train_loss": 5.3705, "eval_loss": 6.1608, "eval_accuracy": 0.0055, "eval_loss_by_set": { "aqua_rat": 6.083435535430908, "gsm8k": 6.455882679332387, "math_qa": 6.032016754150391 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.015163002274450341, "math_qa": 0.001340033500837521 } }, { "flos": 1.093e+18, "train_loss": 5.3956, "eval_loss": 6.1718, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.092315673828125, "gsm8k": 6.468908136541193, "math_qa": 6.042254130045573 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.01592115238817286, "math_qa": 0.001340033500837521 } }, { "flos": 1.101e+18, "train_loss": 5.37, "eval_loss": 6.1504, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.071559429168701, "gsm8k": 6.430761163884943, "math_qa": 6.028474807739258 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 1.11e+18, "train_loss": 5.3669, "eval_loss": 6.1626, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.083080291748047, "gsm8k": 6.436742609197443, "math_qa": 6.043548583984375 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.01592115238817286, "math_qa": 0.001340033500837521 } }, { "flos": 1.118e+18, "train_loss": 5.3675, "eval_loss": 6.1504, "eval_accuracy": 0.0048, "eval_loss_by_set": { "aqua_rat": 6.075137615203857, "gsm8k": 6.420812433416193, "math_qa": 6.032695134480794 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.012130401819560273, "math_qa": 0.001340033500837521 } }, { "flos": 1.126e+18, "train_loss": 5.3778, "eval_loss": 6.1671, "eval_accuracy": 0.0059, "eval_loss_by_set": { "aqua_rat": 6.083521366119385, "gsm8k": 6.446598399769176, "math_qa": 6.045978546142578 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 1.135e+18, "train_loss": 5.3455, "eval_loss": 6.1534, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.077916145324707, "gsm8k": 6.459800720214844, "math_qa": 6.0192515055338545 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.015163002274450341, "math_qa": 0.001340033500837521 } }, { "flos": 1.143e+18, "train_loss": 5.3525, "eval_loss": 6.1414, "eval_accuracy": 0.0068, "eval_loss_by_set": { "aqua_rat": 6.07309627532959, "gsm8k": 6.439678538929332, "math_qa": 6.010400136311849 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.018953752843062926, "math_qa": 0.001340033500837521 } }, { "flos": 1.151e+18, "train_loss": 5.3814, "eval_loss": 6.1389, "eval_accuracy": 0.005, "eval_loss_by_set": { "aqua_rat": 6.070833206176758, "gsm8k": 6.424359408291903, "math_qa": 6.013799667358398 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01288855193328279, "math_qa": 0.001340033500837521 } }, { "flos": 1.16e+18, "train_loss": 5.3701, "eval_loss": 6.148, "eval_accuracy": 0.0059, "eval_loss_by_set": { "aqua_rat": 6.073402404785156, "gsm8k": 6.432354320179332, "math_qa": 6.023821512858073 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 1.168e+18, "train_loss": 5.3618, "eval_loss": 6.1565, "eval_accuracy": 0.0055, "eval_loss_by_set": { "aqua_rat": 6.084665298461914, "gsm8k": 6.451876553622159, "math_qa": 6.027079264322917 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.015163002274450341, "math_qa": 0.001340033500837521 } }, { "flos": 1.176e+18, "train_loss": 5.3595, "eval_loss": 6.1601, "eval_accuracy": 0.0053, "eval_loss_by_set": { "aqua_rat": 6.081357002258301, "gsm8k": 6.458627874200994, "math_qa": 6.029818216959636 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.013646702047005308, "math_qa": 0.001340033500837521 } }, { "flos": 1.185e+18, "train_loss": 5.3665, "eval_loss": 6.1553, "eval_accuracy": 0.0059, "eval_loss_by_set": { "aqua_rat": 6.08267879486084, "gsm8k": 6.4556801535866475, "math_qa": 6.023632049560547 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 1.193e+18, "train_loss": 5.3631, "eval_loss": 6.1693, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.08925199508667, "gsm8k": 6.460882013494318, "math_qa": 6.042287190755208 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 1.201e+18, "train_loss": 5.3749, "eval_loss": 6.1492, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.0720624923706055, "gsm8k": 6.444716713645241, "math_qa": 6.020137786865234 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 1.21e+18, "train_loss": 5.3759, "eval_loss": 6.1502, "eval_accuracy": 0.0055, "eval_loss_by_set": { "aqua_rat": 6.077836513519287, "gsm8k": 6.438594471324574, "math_qa": 6.024007797241211 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.015163002274450341, "math_qa": 0.001340033500837521 } }, { "flos": 1.218e+18, "train_loss": 5.3764, "eval_loss": 6.1514, "eval_accuracy": 0.0055, "eval_loss_by_set": { "aqua_rat": 6.074617385864258, "gsm8k": 6.444173639470881, "math_qa": 6.02366574605306 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.014404852160727824, "math_qa": 0.001340033500837521 } }, { "flos": 1.226e+18, "train_loss": 5.3509, "eval_loss": 6.1592, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.085960388183594, "gsm8k": 6.463744423606179, "math_qa": 6.0257314046223955 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.017437452615617893, "math_qa": 0.001340033500837521 } }, { "flos": 1.235e+18, "train_loss": 5.3657, "eval_loss": 6.1395, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.074496269226074, "gsm8k": 6.421826449307528, "math_qa": 6.015478769938151 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.015163002274450341, "math_qa": 0.001340033500837521 } }, { "flos": 1.243e+18, "train_loss": 5.3614, "eval_loss": 6.1562, "eval_accuracy": 0.0055, "eval_loss_by_set": { "aqua_rat": 6.0811004638671875, "gsm8k": 6.453686107288707, "math_qa": 6.026074727376302 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.014404852160727824, "math_qa": 0.001340033500837521 } }, { "flos": 1.251e+18, "train_loss": 5.3466, "eval_loss": 6.1433, "eval_accuracy": 0.0064, "eval_loss_by_set": { "aqua_rat": 6.070333957672119, "gsm8k": 6.425192399458452, "math_qa": 6.020247141520183 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.016679302501895376, "math_qa": 0.0016750418760469012 } }, { "flos": 1.26e+18, "train_loss": 5.3648, "eval_loss": 6.148, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.071573734283447, "gsm8k": 6.429698597301137, "math_qa": 6.025321324666341 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 1.268e+18, "train_loss": 5.3816, "eval_loss": 6.1489, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.078484535217285, "gsm8k": 6.459440057927912, "math_qa": 6.0124467213948565 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 1.276e+18, "train_loss": 5.3409, "eval_loss": 6.1491, "eval_accuracy": 0.0055, "eval_loss_by_set": { "aqua_rat": 6.067976951599121, "gsm8k": 6.430386629971591, "math_qa": 6.026866277058919 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.015163002274450341, "math_qa": 0.001340033500837521 } }, { "flos": 1.285e+18, "train_loss": 5.3524, "eval_loss": 6.1526, "eval_accuracy": 0.0064, "eval_loss_by_set": { "aqua_rat": 6.075307846069336, "gsm8k": 6.44162334095348, "math_qa": 6.026571909586589 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.01819560272934041, "math_qa": 0.001340033500837521 } }, { "flos": 1.293e+18, "train_loss": 5.369, "eval_loss": 6.1612, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.083963871002197, "gsm8k": 6.446619207208807, "math_qa": 6.036815643310547 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 1.301e+18, "train_loss": 5.3756, "eval_loss": 6.1575, "eval_accuracy": 0.0055, "eval_loss_by_set": { "aqua_rat": 6.083482265472412, "gsm8k": 6.447088068181818, "math_qa": 6.030939102172852 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.014404852160727824, "math_qa": 0.001340033500837521 } }, { "flos": 1.31e+18, "train_loss": 5.363, "eval_loss": 6.1554, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.076425552368164, "gsm8k": 6.450388128107244, "math_qa": 6.026723861694336 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 1.318e+18, "train_loss": 5.3726, "eval_loss": 6.16, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.080287933349609, "gsm8k": 6.450357610529119, "math_qa": 6.033551534016927 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.015163002274450341, "math_qa": 0.001340033500837521 } }, { "flos": 1.327e+18, "train_loss": 5.36, "eval_loss": 6.1462, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.0693254470825195, "gsm8k": 6.428289240056818, "math_qa": 6.023316065470378 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.015163002274450341, "math_qa": 0.001340033500837521 } }, { "flos": 1.335e+18, "train_loss": 5.3469, "eval_loss": 6.1465, "eval_accuracy": 0.0055, "eval_loss_by_set": { "aqua_rat": 6.07256555557251, "gsm8k": 6.4298928000710225, "math_qa": 6.022792816162109 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.014404852160727824, "math_qa": 0.001340033500837521 } }, { "flos": 1.343e+18, "train_loss": 5.3626, "eval_loss": 6.1482, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.077568054199219, "gsm8k": 6.423980019309304, "math_qa": 6.02773920694987 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.015163002274450341, "math_qa": 0.001340033500837521 } }, { "flos": 1.352e+18, "train_loss": 5.3548, "eval_loss": 6.1691, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.089290618896484, "gsm8k": 6.460177334872159, "math_qa": 6.042274475097656 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.015163002274450341, "math_qa": 0.001340033500837521 } }, { "flos": 1.36e+18, "train_loss": 5.3519, "eval_loss": 6.1442, "eval_accuracy": 0.0055, "eval_loss_by_set": { "aqua_rat": 6.070032119750977, "gsm8k": 6.446653192693537, "math_qa": 6.011816660563151 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.013646702047005308, "math_qa": 0.0016750418760469012 } }, { "flos": 1.368e+18, "train_loss": 5.3769, "eval_loss": 6.152, "eval_accuracy": 0.0046, "eval_loss_by_set": { "aqua_rat": 6.073600769042969, "gsm8k": 6.43677382035689, "math_qa": 6.0280717213948565 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.011372251705837756, "math_qa": 0.001340033500837521 } }, { "flos": 1.377e+18, "train_loss": 5.3775, "eval_loss": 6.1376, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.068869113922119, "gsm8k": 6.41132909601385, "math_qa": 6.017881393432617 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 1.385e+18, "train_loss": 5.3626, "eval_loss": 6.1636, "eval_accuracy": 0.0059, "eval_loss_by_set": { "aqua_rat": 6.083983421325684, "gsm8k": 6.455983942205256, "math_qa": 6.036271413167317 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.015163002274450341, "math_qa": 0.0016750418760469012 } }, { "flos": 1.393e+18, "train_loss": 5.3572, "eval_loss": 6.1469, "eval_accuracy": 0.0064, "eval_loss_by_set": { "aqua_rat": 6.075814247131348, "gsm8k": 6.439236727627841, "math_qa": 6.018874486287435 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.017437452615617893, "math_qa": 0.001340033500837521 } }, { "flos": 1.402e+18, "train_loss": 5.3632, "eval_loss": 6.1543, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.082464694976807, "gsm8k": 6.4552154541015625, "math_qa": 6.022292455037435 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.015163002274450341, "math_qa": 0.001340033500837521 } }, { "flos": 1.41e+18, "train_loss": 5.3359, "eval_loss": 6.1531, "eval_accuracy": 0.005, "eval_loss_by_set": { "aqua_rat": 6.087891578674316, "gsm8k": 6.445680791681463, "math_qa": 6.024365107218425 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01288855193328279, "math_qa": 0.001340033500837521 } }, { "flos": 1.418e+18, "train_loss": 5.3424, "eval_loss": 6.1625, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.085758209228516, "gsm8k": 6.472423206676137, "math_qa": 6.026842753092448 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.015163002274450341, "math_qa": 0.001340033500837521 } }, { "flos": 1.427e+18, "train_loss": 5.3769, "eval_loss": 6.1603, "eval_accuracy": 0.005, "eval_loss_by_set": { "aqua_rat": 6.08692741394043, "gsm8k": 6.46733925559304, "math_qa": 6.025636672973633 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01288855193328279, "math_qa": 0.001340033500837521 } }, { "flos": 1.435e+18, "train_loss": 5.3516, "eval_loss": 6.1575, "eval_accuracy": 0.0048, "eval_loss_by_set": { "aqua_rat": 6.080989837646484, "gsm8k": 6.4560463645241475, "math_qa": 6.027099609375 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.01288855193328279, "math_qa": 0.001340033500837521 } }, { "flos": 1.443e+18, "train_loss": 5.376, "eval_loss": 6.1544, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.079292297363281, "gsm8k": 6.439244357022372, "math_qa": 6.030137379964192 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 1.452e+18, "train_loss": 5.3512, "eval_loss": 6.1527, "eval_accuracy": 0.0055, "eval_loss_by_set": { "aqua_rat": 6.074826240539551, "gsm8k": 6.436852195046165, "math_qa": 6.028977711995442 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.013646702047005308, "math_qa": 0.0016750418760469012 } }, { "flos": 1.46e+18, "train_loss": 5.3632, "eval_loss": 6.158, "eval_accuracy": 0.0064, "eval_loss_by_set": { "aqua_rat": 6.079761981964111, "gsm8k": 6.449956026944247, "math_qa": 6.030742009480794 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.017437452615617893, "math_qa": 0.001340033500837521 } }, { "flos": 1.468e+18, "train_loss": 5.3806, "eval_loss": 6.1664, "eval_accuracy": 0.0055, "eval_loss_by_set": { "aqua_rat": 6.088852405548096, "gsm8k": 6.46076133034446, "math_qa": 6.037961324055989 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.014404852160727824, "math_qa": 0.001340033500837521 } }, { "flos": 1.477e+18, "train_loss": 5.3424, "eval_loss": 6.1454, "eval_accuracy": 0.005, "eval_loss_by_set": { "aqua_rat": 6.0740251541137695, "gsm8k": 6.4325034401633525, "math_qa": 6.019723256429036 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01288855193328279, "math_qa": 0.001340033500837521 } }, { "flos": 1.485e+18, "train_loss": 5.3661, "eval_loss": 6.1573, "eval_accuracy": 0.0064, "eval_loss_by_set": { "aqua_rat": 6.084558010101318, "gsm8k": 6.456825256347656, "math_qa": 6.026081085205078 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.017437452615617893, "math_qa": 0.001340033500837521 } }, { "flos": 1.493e+18, "train_loss": 5.359, "eval_loss": 6.1396, "eval_accuracy": 0.0042, "eval_loss_by_set": { "aqua_rat": 6.068215370178223, "gsm8k": 6.427814136851918, "math_qa": 6.013424555460612 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.009855951478392721, "math_qa": 0.001340033500837521 } }, { "flos": 1.502e+18, "train_loss": 5.3619, "eval_loss": 6.157, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.077211856842041, "gsm8k": 6.432880054820668, "math_qa": 6.037206649780273 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.015163002274450341, "math_qa": 0.001340033500837521 } }, { "flos": 1.51e+18, "train_loss": 5.3628, "eval_loss": 6.1395, "eval_accuracy": 0.0055, "eval_loss_by_set": { "aqua_rat": 6.057583332061768, "gsm8k": 6.413607510653409, "math_qa": 6.020683924357097 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.014404852160727824, "math_qa": 0.001340033500837521 } }, { "flos": 1.518e+18, "train_loss": 5.3601, "eval_loss": 6.1554, "eval_accuracy": 0.0064, "eval_loss_by_set": { "aqua_rat": 6.073965072631836, "gsm8k": 6.434541182084517, "math_qa": 6.03431765238444 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.016679302501895376, "math_qa": 0.0016750418760469012 } }, { "flos": 1.527e+18, "train_loss": 5.346, "eval_loss": 6.1498, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.0737128257751465, "gsm8k": 6.438907970081676, "math_qa": 6.023590723673503 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.015163002274450341, "math_qa": 0.001340033500837521 } }, { "flos": 1.535e+18, "train_loss": 5.3685, "eval_loss": 6.1522, "eval_accuracy": 0.0077, "eval_loss_by_set": { "aqua_rat": 6.07402229309082, "gsm8k": 6.455646168101918, "math_qa": 6.019660949707031 }, "eval_accuracy_by_set": { "aqua_rat": 0.011811023622047244, "gsm8k": 0.02122820318423048, "math_qa": 0.001340033500837521 } }, { "flos": 1.543e+18, "train_loss": 5.3668, "eval_loss": 6.1516, "eval_accuracy": 0.0059, "eval_loss_by_set": { "aqua_rat": 6.068660736083984, "gsm8k": 6.447554154829546, "math_qa": 6.022809346516927 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01592115238817286, "math_qa": 0.001340033500837521 } }, { "flos": 1.552e+18, "train_loss": 5.3524, "eval_loss": 6.1587, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.072835445404053, "gsm8k": 6.437031139026988, "math_qa": 6.03828239440918 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.015163002274450341, "math_qa": 0.001340033500837521 } }, { "flos": 1.56e+18, "train_loss": 5.3551, "eval_loss": 6.1556, "eval_accuracy": 0.0055, "eval_loss_by_set": { "aqua_rat": 6.077116966247559, "gsm8k": 6.444129250266335, "math_qa": 6.029883702596028 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.015163002274450341, "math_qa": 0.001340033500837521 } }, { "flos": 1.569e+18, "train_loss": 5.3342, "eval_loss": 6.1612, "eval_accuracy": 0.0064, "eval_loss_by_set": { "aqua_rat": 6.079534530639648, "gsm8k": 6.450813293457031, "math_qa": 6.035327275594075 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.016679302501895376, "math_qa": 0.0016750418760469012 } }, { "flos": 1.577e+18, "train_loss": 5.3721, "eval_loss": 6.1403, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.074985504150391, "gsm8k": 6.43084023215554, "math_qa": 6.012502670288086 }, "eval_accuracy_by_set": { "aqua_rat": 0.011811023622047244, "gsm8k": 0.015163002274450341, "math_qa": 0.0016750418760469012 } }, { "flos": 1.585e+18, "train_loss": 5.3587, "eval_loss": 6.1467, "eval_accuracy": 0.007, "eval_loss_by_set": { "aqua_rat": 6.0691328048706055, "gsm8k": 6.434525923295454, "math_qa": 6.021308898925781 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.019711902956785442, "math_qa": 0.001340033500837521 } }, { "flos": 1.594e+18, "train_loss": 5.3628, "eval_loss": 6.1455, "eval_accuracy": 0.0072, "eval_loss_by_set": { "aqua_rat": 6.076591491699219, "gsm8k": 6.441010908647017, "math_qa": 6.0158030192057295 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.02047005307050796, "math_qa": 0.001340033500837521 } }, { "flos": 1.602e+18, "train_loss": 5.3574, "eval_loss": 6.142, "eval_accuracy": 0.0066, "eval_loss_by_set": { "aqua_rat": 6.072415351867676, "gsm8k": 6.449636285955256, "math_qa": 6.006825764973958 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.017437452615617893, "math_qa": 0.0016750418760469012 } }, { "flos": 1.61e+18, "train_loss": 5.3503, "eval_loss": 6.1366, "eval_accuracy": 0.0059, "eval_loss_by_set": { "aqua_rat": 6.069148540496826, "gsm8k": 6.433821244673296, "math_qa": 6.006028493245442 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.015163002274450341, "math_qa": 0.0016750418760469012 } }, { "flos": 1.619e+18, "train_loss": 5.3562, "eval_loss": 6.1428, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.072711944580078, "gsm8k": 6.431656577370384, "math_qa": 6.016279220581055 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.015163002274450341, "math_qa": 0.001340033500837521 } }, { "flos": 1.627e+18, "train_loss": 5.3409, "eval_loss": 6.163, "eval_accuracy": 0.007, "eval_loss_by_set": { "aqua_rat": 6.0908894538879395, "gsm8k": 6.465269608931108, "math_qa": 6.030401229858398 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.018953752843062926, "math_qa": 0.0016750418760469012 } }, { "flos": 1.635e+18, "train_loss": 5.3676, "eval_loss": 6.1338, "eval_accuracy": 0.0055, "eval_loss_by_set": { "aqua_rat": 6.067920684814453, "gsm8k": 6.423690102317116, "math_qa": 6.006355285644531 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.013646702047005308, "math_qa": 0.0016750418760469012 } }, { "flos": 1.644e+18, "train_loss": 5.3637, "eval_loss": 6.1506, "eval_accuracy": 0.0066, "eval_loss_by_set": { "aqua_rat": 6.079724311828613, "gsm8k": 6.435499711470171, "math_qa": 6.025922139485677 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.017437452615617893, "math_qa": 0.0016750418760469012 } }, { "flos": 1.652e+18, "train_loss": 5.3538, "eval_loss": 6.1511, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.077124118804932, "gsm8k": 6.439601551402699, "math_qa": 6.025044123331706 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.015163002274450341, "math_qa": 0.0016750418760469012 } }, { "flos": 1.66e+18, "train_loss": 5.3507, "eval_loss": 6.1387, "eval_accuracy": 0.0066, "eval_loss_by_set": { "aqua_rat": 6.07029914855957, "gsm8k": 6.4320456764914775, "math_qa": 6.009922027587891 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.017437452615617893, "math_qa": 0.0016750418760469012 } }, { "flos": 1.669e+18, "train_loss": 5.3599, "eval_loss": 6.1497, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.08086633682251, "gsm8k": 6.438559098677202, "math_qa": 6.023111343383789 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.015163002274450341, "math_qa": 0.001340033500837521 } }, { "flos": 1.677e+18, "train_loss": 5.3634, "eval_loss": 6.1449, "eval_accuracy": 0.005, "eval_loss_by_set": { "aqua_rat": 6.072770595550537, "gsm8k": 6.442627646706321, "math_qa": 6.014506657918294 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01288855193328279, "math_qa": 0.001340033500837521 } }, { "flos": 1.685e+18, "train_loss": 5.347, "eval_loss": 6.1493, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.069969177246094, "gsm8k": 6.435421336780895, "math_qa": 6.024741490681966 }, "eval_accuracy_by_set": { "aqua_rat": 0.011811023622047244, "gsm8k": 0.015163002274450341, "math_qa": 0.0016750418760469012 } }, { "flos": 1.694e+18, "train_loss": 5.3363, "eval_loss": 6.137, "eval_accuracy": 0.0055, "eval_loss_by_set": { "aqua_rat": 6.066619873046875, "gsm8k": 6.42841269753196, "math_qa": 6.009375254313151 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.014404852160727824, "math_qa": 0.0016750418760469012 } }, { "flos": 1.702e+18, "train_loss": 5.3457, "eval_loss": 6.147, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.0722126960754395, "gsm8k": 6.434000188654119, "math_qa": 6.02163823445638 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.015163002274450341, "math_qa": 0.0016750418760469012 } }, { "flos": 1.71e+18, "train_loss": 5.3573, "eval_loss": 6.1449, "eval_accuracy": 0.0053, "eval_loss_by_set": { "aqua_rat": 6.068811416625977, "gsm8k": 6.439558549360796, "math_qa": 6.0162614186604815 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.014404852160727824, "math_qa": 0.001340033500837521 } }, { "flos": 1.719e+18, "train_loss": 5.3638, "eval_loss": 6.1356, "eval_accuracy": 0.0053, "eval_loss_by_set": { "aqua_rat": 6.068318843841553, "gsm8k": 6.415383772416548, "math_qa": 6.01296869913737 }, "eval_accuracy_by_set": { "aqua_rat": 0.011811023622047244, "gsm8k": 0.01288855193328279, "math_qa": 0.001340033500837521 } }, { "flos": 1.727e+18, "train_loss": 5.3526, "eval_loss": 6.1483, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.076712608337402, "gsm8k": 6.461988969282671, "math_qa": 6.010456720987956 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.015163002274450341, "math_qa": 0.001340033500837521 } }, { "flos": 1.735e+18, "train_loss": 5.3411, "eval_loss": 6.1464, "eval_accuracy": 0.0066, "eval_loss_by_set": { "aqua_rat": 6.067948818206787, "gsm8k": 6.433219909667969, "math_qa": 6.021470387776692 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.017437452615617893, "math_qa": 0.0016750418760469012 } }, { "flos": 1.744e+18, "train_loss": 5.3556, "eval_loss": 6.156, "eval_accuracy": 0.0068, "eval_loss_by_set": { "aqua_rat": 6.079143524169922, "gsm8k": 6.448518232865767, "math_qa": 6.028399149576823 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.018953752843062926, "math_qa": 0.001340033500837521 } }, { "flos": 1.752e+18, "train_loss": 5.3524, "eval_loss": 6.1342, "eval_accuracy": 0.0059, "eval_loss_by_set": { "aqua_rat": 6.064161777496338, "gsm8k": 6.433375965465199, "math_qa": 6.002888997395833 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 1.76e+18, "train_loss": 5.3549, "eval_loss": 6.1521, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.0765767097473145, "gsm8k": 6.455070495605469, "math_qa": 6.019542058308919 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.015163002274450341, "math_qa": 0.001340033500837521 } }, { "flos": 1.769e+18, "train_loss": 5.3701, "eval_loss": 6.1426, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.0712199211120605, "gsm8k": 6.431798761541193, "math_qa": 6.016062418619792 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 1.777e+18, "train_loss": 5.3491, "eval_loss": 6.1534, "eval_accuracy": 0.0059, "eval_loss_by_set": { "aqua_rat": 6.08159875869751, "gsm8k": 6.454958829012784, "math_qa": 6.021216074625651 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01592115238817286, "math_qa": 0.001340033500837521 } }, { "flos": 1.785e+18, "train_loss": 5.3587, "eval_loss": 6.132, "eval_accuracy": 0.0064, "eval_loss_by_set": { "aqua_rat": 6.055446624755859, "gsm8k": 6.409071488813921, "math_qa": 6.0114186604817705 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.01819560272934041, "math_qa": 0.001340033500837521 } }, { "flos": 1.794e+18, "train_loss": 5.3567, "eval_loss": 6.1567, "eval_accuracy": 0.0068, "eval_loss_by_set": { "aqua_rat": 6.08056640625, "gsm8k": 6.448164506392046, "math_qa": 6.02940559387207 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.018953752843062926, "math_qa": 0.001340033500837521 } }, { "flos": 1.802e+18, "train_loss": 5.3345, "eval_loss": 6.1527, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.08262825012207, "gsm8k": 6.446475635875355, "math_qa": 6.02383295694987 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.015163002274450341, "math_qa": 0.001340033500837521 } }, { "flos": 1.81e+18, "train_loss": 5.3481, "eval_loss": 6.1601, "eval_accuracy": 0.0068, "eval_loss_by_set": { "aqua_rat": 6.085085868835449, "gsm8k": 6.469014948064631, "math_qa": 6.024699529012044 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.018953752843062926, "math_qa": 0.001340033500837521 } }, { "flos": 1.819e+18, "train_loss": 5.3574, "eval_loss": 6.16, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.083130836486816, "gsm8k": 6.466507651589134, "math_qa": 6.025927861531575 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.015163002274450341, "math_qa": 0.001340033500837521 } }, { "flos": 1.827e+18, "train_loss": 5.3606, "eval_loss": 6.1456, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.07041072845459, "gsm8k": 6.420628634366122, "math_qa": 6.025824228922526 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.015163002274450341, "math_qa": 0.001340033500837521 } }, { "flos": 1.835e+18, "train_loss": 5.3648, "eval_loss": 6.1508, "eval_accuracy": 0.0066, "eval_loss_by_set": { "aqua_rat": 6.070516586303711, "gsm8k": 6.437401511452415, "math_qa": 6.026082992553711 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.017437452615617893, "math_qa": 0.0016750418760469012 } }, { "flos": 1.844e+18, "train_loss": 5.3484, "eval_loss": 6.1497, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.083341598510742, "gsm8k": 6.4559104225852275, "math_qa": 6.014860153198242 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 1.852e+18, "train_loss": 5.3711, "eval_loss": 6.1356, "eval_accuracy": 0.0064, "eval_loss_by_set": { "aqua_rat": 6.056187152862549, "gsm8k": 6.415980945933949, "math_qa": 6.0136667887369795 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.016679302501895376, "math_qa": 0.0016750418760469012 } }, { "flos": 1.86e+18, "train_loss": 5.331, "eval_loss": 6.1425, "eval_accuracy": 0.0075, "eval_loss_by_set": { "aqua_rat": 6.073963165283203, "gsm8k": 6.436175259676847, "math_qa": 6.013682047526042 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.02122820318423048, "math_qa": 0.001340033500837521 } }, { "flos": 1.869e+18, "train_loss": 5.354, "eval_loss": 6.1359, "eval_accuracy": 0.0075, "eval_loss_by_set": { "aqua_rat": 6.065001487731934, "gsm8k": 6.418893987482244, "math_qa": 6.012086868286133 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.02047005307050796, "math_qa": 0.0016750418760469012 } }, { "flos": 1.877e+18, "train_loss": 5.3354, "eval_loss": 6.1456, "eval_accuracy": 0.007, "eval_loss_by_set": { "aqua_rat": 6.075804233551025, "gsm8k": 6.440628745339134, "math_qa": 6.016129811604817 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.018953752843062926, "math_qa": 0.0016750418760469012 } }, { "flos": 1.885e+18, "train_loss": 5.3304, "eval_loss": 6.1403, "eval_accuracy": 0.0059, "eval_loss_by_set": { "aqua_rat": 6.063568115234375, "gsm8k": 6.432843988591975, "math_qa": 6.012545903523763 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.015163002274450341, "math_qa": 0.0016750418760469012 } }, { "flos": 1.894e+18, "train_loss": 5.3483, "eval_loss": 6.1434, "eval_accuracy": 0.007, "eval_loss_by_set": { "aqua_rat": 6.075047016143799, "gsm8k": 6.448862942782315, "math_qa": 6.009158452351888 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01819560272934041, "math_qa": 0.0020100502512562816 } }, { "flos": 1.902e+18, "train_loss": 5.3578, "eval_loss": 6.1476, "eval_accuracy": 0.007, "eval_loss_by_set": { "aqua_rat": 6.0719404220581055, "gsm8k": 6.441083041104403, "math_qa": 6.01944096883138 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01819560272934041, "math_qa": 0.0020100502512562816 } }, { "flos": 1.91e+18, "train_loss": 5.3616, "eval_loss": 6.1577, "eval_accuracy": 0.0064, "eval_loss_by_set": { "aqua_rat": 6.075067043304443, "gsm8k": 6.45440673828125, "math_qa": 6.028561274210612 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.01819560272934041, "math_qa": 0.001340033500837521 } }, { "flos": 1.919e+18, "train_loss": 5.368, "eval_loss": 6.1254, "eval_accuracy": 0.0066, "eval_loss_by_set": { "aqua_rat": 6.055496692657471, "gsm8k": 6.397986672141335, "math_qa": 6.006315231323242 }, "eval_accuracy_by_set": { "aqua_rat": 0.011811023622047244, "gsm8k": 0.016679302501895376, "math_qa": 0.0016750418760469012 } }, { "flos": 1.927e+18, "train_loss": 5.3462, "eval_loss": 6.1479, "eval_accuracy": 0.0053, "eval_loss_by_set": { "aqua_rat": 6.077619552612305, "gsm8k": 6.442380038174716, "math_qa": 6.018735249837239 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.014404852160727824, "math_qa": 0.001340033500837521 } }, { "flos": 1.935e+18, "train_loss": 5.3298, "eval_loss": 6.1431, "eval_accuracy": 0.0066, "eval_loss_by_set": { "aqua_rat": 6.068150520324707, "gsm8k": 6.437403592196378, "math_qa": 6.014495213826497 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.01819560272934041, "math_qa": 0.0016750418760469012 } }, { "flos": 1.944e+18, "train_loss": 5.3395, "eval_loss": 6.1287, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.063396453857422, "gsm8k": 6.423402959650213, "math_qa": 5.999011357625325 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.01592115238817286, "math_qa": 0.001340033500837521 } }, { "flos": 1.952e+18, "train_loss": 5.3692, "eval_loss": 6.138, "eval_accuracy": 0.0059, "eval_loss_by_set": { "aqua_rat": 6.071093559265137, "gsm8k": 6.445939497514204, "math_qa": 6.002445220947266 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 1.961e+18, "train_loss": 5.3628, "eval_loss": 6.1482, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.079810619354248, "gsm8k": 6.442142833362926, "math_qa": 6.019161224365234 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.016679302501895376, "math_qa": 0.0016750418760469012 } }, { "flos": 1.969e+18, "train_loss": 5.3563, "eval_loss": 6.1524, "eval_accuracy": 0.0055, "eval_loss_by_set": { "aqua_rat": 6.086348533630371, "gsm8k": 6.45732948996804, "math_qa": 6.018072764078776 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.013646702047005308, "math_qa": 0.0016750418760469012 } }, { "flos": 1.977e+18, "train_loss": 5.3594, "eval_loss": 6.1588, "eval_accuracy": 0.007, "eval_loss_by_set": { "aqua_rat": 6.085717678070068, "gsm8k": 6.454693880948153, "math_qa": 6.029197692871094 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01819560272934041, "math_qa": 0.0020100502512562816 } }, { "flos": 1.986e+18, "train_loss": 5.347, "eval_loss": 6.1483, "eval_accuracy": 0.0072, "eval_loss_by_set": { "aqua_rat": 6.078394889831543, "gsm8k": 6.455042058771307, "math_qa": 6.013578414916992 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.02047005307050796, "math_qa": 0.001340033500837521 } }, { "flos": 1.994e+18, "train_loss": 5.3517, "eval_loss": 6.1412, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.066160202026367, "gsm8k": 6.416182084517046, "math_qa": 6.021382013956706 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.015163002274450341, "math_qa": 0.0020100502512562816 } }, { "flos": 2.002e+18, "train_loss": 5.3475, "eval_loss": 6.1569, "eval_accuracy": 0.0068, "eval_loss_by_set": { "aqua_rat": 6.084001541137695, "gsm8k": 6.4583518288352275, "math_qa": 6.024847030639648 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01819560272934041, "math_qa": 0.0016750418760469012 } }, { "flos": 2.011e+18, "train_loss": 5.3505, "eval_loss": 6.1491, "eval_accuracy": 0.0059, "eval_loss_by_set": { "aqua_rat": 6.078339576721191, "gsm8k": 6.442309986461293, "math_qa": 6.020566304524739 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01592115238817286, "math_qa": 0.001340033500837521 } }, { "flos": 2.019e+18, "train_loss": 5.3349, "eval_loss": 6.1323, "eval_accuracy": 0.0064, "eval_loss_by_set": { "aqua_rat": 6.062560081481934, "gsm8k": 6.411548961292613, "math_qa": 6.010158538818359 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.017437452615617893, "math_qa": 0.0016750418760469012 } }, { "flos": 2.027e+18, "train_loss": 5.3612, "eval_loss": 6.1424, "eval_accuracy": 0.0064, "eval_loss_by_set": { "aqua_rat": 6.069005012512207, "gsm8k": 6.435365850275213, "math_qa": 6.014229456583659 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.017437452615617893, "math_qa": 0.0016750418760469012 } }, { "flos": 2.036e+18, "train_loss": 5.3501, "eval_loss": 6.153, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.075499534606934, "gsm8k": 6.4573891379616475, "math_qa": 6.020020167032878 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 2.044e+18, "train_loss": 5.3498, "eval_loss": 6.1498, "eval_accuracy": 0.005, "eval_loss_by_set": { "aqua_rat": 6.079788684844971, "gsm8k": 6.454716769131747, "math_qa": 6.015870412190755 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.013646702047005308, "math_qa": 0.001340033500837521 } }, { "flos": 2.052e+18, "train_loss": 5.3344, "eval_loss": 6.1503, "eval_accuracy": 0.0059, "eval_loss_by_set": { "aqua_rat": 6.083023548126221, "gsm8k": 6.457128351384943, "math_qa": 6.015323003133138 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 2.061e+18, "train_loss": 5.3401, "eval_loss": 6.139, "eval_accuracy": 0.0066, "eval_loss_by_set": { "aqua_rat": 6.071455955505371, "gsm8k": 6.437273892489347, "math_qa": 6.007967631022136 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.018953752843062926, "math_qa": 0.001340033500837521 } }, { "flos": 2.069e+18, "train_loss": 5.3525, "eval_loss": 6.151, "eval_accuracy": 0.0053, "eval_loss_by_set": { "aqua_rat": 6.077144145965576, "gsm8k": 6.455119739879262, "math_qa": 6.017766952514648 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.013646702047005308, "math_qa": 0.001340033500837521 } }, { "flos": 2.077e+18, "train_loss": 5.3398, "eval_loss": 6.1425, "eval_accuracy": 0.0064, "eval_loss_by_set": { "aqua_rat": 6.069194793701172, "gsm8k": 6.434398304332387, "math_qa": 6.01475715637207 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01592115238817286, "math_qa": 0.0020100502512562816 } }, { "flos": 2.086e+18, "train_loss": 5.3493, "eval_loss": 6.1458, "eval_accuracy": 0.0059, "eval_loss_by_set": { "aqua_rat": 6.077215194702148, "gsm8k": 6.446357727050781, "math_qa": 6.013806660970052 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.01592115238817286, "math_qa": 0.0016750418760469012 } }, { "flos": 2.094e+18, "train_loss": 5.3523, "eval_loss": 6.145, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.06728982925415, "gsm8k": 6.42859510941939, "math_qa": 6.021465301513672 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.01592115238817286, "math_qa": 0.001340033500837521 } }, { "flos": 2.102e+18, "train_loss": 5.3408, "eval_loss": 6.1501, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.078736305236816, "gsm8k": 6.459717490456321, "math_qa": 6.014194488525391 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.01592115238817286, "math_qa": 0.001340033500837521 } }, { "flos": 2.111e+18, "train_loss": 5.334, "eval_loss": 6.1484, "eval_accuracy": 0.0055, "eval_loss_by_set": { "aqua_rat": 6.0737714767456055, "gsm8k": 6.440345070578835, "math_qa": 6.020744323730469 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.014404852160727824, "math_qa": 0.001340033500837521 } }, { "flos": 2.119e+18, "train_loss": 5.3315, "eval_loss": 6.1439, "eval_accuracy": 0.0059, "eval_loss_by_set": { "aqua_rat": 6.075357913970947, "gsm8k": 6.445459539240057, "math_qa": 6.011428197224935 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.015163002274450341, "math_qa": 0.0020100502512562816 } }, { "flos": 2.127e+18, "train_loss": 5.3509, "eval_loss": 6.1488, "eval_accuracy": 0.0059, "eval_loss_by_set": { "aqua_rat": 6.073482990264893, "gsm8k": 6.43572304465554, "math_qa": 6.023612976074219 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.01592115238817286, "math_qa": 0.0016750418760469012 } }, { "flos": 2.136e+18, "train_loss": 5.3744, "eval_loss": 6.1372, "eval_accuracy": 0.005, "eval_loss_by_set": { "aqua_rat": 6.063905715942383, "gsm8k": 6.431650335138494, "math_qa": 6.0083160400390625 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.013646702047005308, "math_qa": 0.001340033500837521 } }, { "flos": 2.144e+18, "train_loss": 5.3498, "eval_loss": 6.1512, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.068212509155273, "gsm8k": 6.446079600941051, "math_qa": 6.02299435933431 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.016679302501895376, "math_qa": 0.0016750418760469012 } }, { "flos": 2.152e+18, "train_loss": 5.34, "eval_loss": 6.148, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.065868854522705, "gsm8k": 6.441741943359375, "math_qa": 6.020246505737305 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.01592115238817286, "math_qa": 0.001340033500837521 } }, { "flos": 2.161e+18, "train_loss": 5.3621, "eval_loss": 6.1572, "eval_accuracy": 0.0066, "eval_loss_by_set": { "aqua_rat": 6.078779697418213, "gsm8k": 6.458294261585582, "math_qa": 6.025702794392903 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.01819560272934041, "math_qa": 0.0016750418760469012 } }, { "flos": 2.169e+18, "train_loss": 5.3541, "eval_loss": 6.137, "eval_accuracy": 0.0066, "eval_loss_by_set": { "aqua_rat": 6.064920425415039, "gsm8k": 6.420195146040483, "math_qa": 6.013170878092448 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01592115238817286, "math_qa": 0.0023450586264656616 } }, { "flos": 2.177e+18, "train_loss": 5.3422, "eval_loss": 6.1527, "eval_accuracy": 0.0066, "eval_loss_by_set": { "aqua_rat": 6.08025598526001, "gsm8k": 6.437312039462003, "math_qa": 6.028347015380859 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01592115238817286, "math_qa": 0.0023450586264656616 } }, { "flos": 2.186e+18, "train_loss": 5.3512, "eval_loss": 6.138, "eval_accuracy": 0.0068, "eval_loss_by_set": { "aqua_rat": 6.0690107345581055, "gsm8k": 6.42951757257635, "math_qa": 6.010064442952474 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.016679302501895376, "math_qa": 0.0023450586264656616 } }, { "flos": 2.194e+18, "train_loss": 5.3688, "eval_loss": 6.1589, "eval_accuracy": 0.0075, "eval_loss_by_set": { "aqua_rat": 6.076730728149414, "gsm8k": 6.453974637118253, "math_qa": 6.030550003051758 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.019711902956785442, "math_qa": 0.0023450586264656616 } }, { "flos": 2.202e+18, "train_loss": 5.3531, "eval_loss": 6.1343, "eval_accuracy": 0.007, "eval_loss_by_set": { "aqua_rat": 6.065770149230957, "gsm8k": 6.424163818359375, "math_qa": 6.007158279418945 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.02047005307050796, "math_qa": 0.001340033500837521 } }, { "flos": 2.211e+18, "train_loss": 5.3334, "eval_loss": 6.142, "eval_accuracy": 0.0066, "eval_loss_by_set": { "aqua_rat": 6.067741870880127, "gsm8k": 6.455144708806818, "math_qa": 6.0047251383463545 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.018953752843062926, "math_qa": 0.001340033500837521 } }, { "flos": 2.219e+18, "train_loss": 5.3376, "eval_loss": 6.1475, "eval_accuracy": 0.0064, "eval_loss_by_set": { "aqua_rat": 6.070160388946533, "gsm8k": 6.4288857199928975, "math_qa": 6.025034586588542 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.016679302501895376, "math_qa": 0.0020100502512562816 } }, { "flos": 2.228e+18, "train_loss": 5.337, "eval_loss": 6.1375, "eval_accuracy": 0.0077, "eval_loss_by_set": { "aqua_rat": 6.0651750564575195, "gsm8k": 6.441540804776278, "math_qa": 6.004156748453776 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.02047005307050796, "math_qa": 0.0023450586264656616 } }, { "flos": 2.236e+18, "train_loss": 5.3312, "eval_loss": 6.1495, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.084222793579102, "gsm8k": 6.46234824440696, "math_qa": 6.011616388956706 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.015163002274450341, "math_qa": 0.0016750418760469012 } }, { "flos": 2.244e+18, "train_loss": 5.341, "eval_loss": 6.1409, "eval_accuracy": 0.0053, "eval_loss_by_set": { "aqua_rat": 6.069973945617676, "gsm8k": 6.441241871226918, "math_qa": 6.009182612101237 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.012130401819560273, "math_qa": 0.0023450586264656616 } }, { "flos": 2.253e+18, "train_loss": 5.356, "eval_loss": 6.1469, "eval_accuracy": 0.0066, "eval_loss_by_set": { "aqua_rat": 6.0699920654296875, "gsm8k": 6.436524131081321, "math_qa": 6.020585378011067 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.016679302501895376, "math_qa": 0.0023450586264656616 } }, { "flos": 2.261e+18, "train_loss": 5.3425, "eval_loss": 6.1392, "eval_accuracy": 0.0075, "eval_loss_by_set": { "aqua_rat": 6.073261737823486, "gsm8k": 6.442094282670454, "math_qa": 6.005818684895833 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.018953752843062926, "math_qa": 0.0023450586264656616 } }, { "flos": 2.269e+18, "train_loss": 5.3596, "eval_loss": 6.1462, "eval_accuracy": 0.0075, "eval_loss_by_set": { "aqua_rat": 6.079766750335693, "gsm8k": 6.443323308771307, "math_qa": 6.0155378977457685 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.019711902956785442, "math_qa": 0.0023450586264656616 } }, { "flos": 2.278e+18, "train_loss": 5.3435, "eval_loss": 6.1521, "eval_accuracy": 0.0053, "eval_loss_by_set": { "aqua_rat": 6.081230163574219, "gsm8k": 6.466338417746804, "math_qa": 6.013909022013347 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.013646702047005308, "math_qa": 0.0016750418760469012 } }, { "flos": 2.286e+18, "train_loss": 5.3598, "eval_loss": 6.1364, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.067131996154785, "gsm8k": 6.435832630504262, "math_qa": 6.004929860432942 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.014404852160727824, "math_qa": 0.0023450586264656616 } }, { "flos": 2.294e+18, "train_loss": 5.3511, "eval_loss": 6.1483, "eval_accuracy": 0.0066, "eval_loss_by_set": { "aqua_rat": 6.070858001708984, "gsm8k": 6.458089655095881, "math_qa": 6.0127614339192705 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.017437452615617893, "math_qa": 0.0020100502512562816 } }, { "flos": 2.303e+18, "train_loss": 5.3564, "eval_loss": 6.1427, "eval_accuracy": 0.0068, "eval_loss_by_set": { "aqua_rat": 6.076345920562744, "gsm8k": 6.465571316805753, "math_qa": 6.000224431355794 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.018953752843062926, "math_qa": 0.0016750418760469012 } }, { "flos": 2.311e+18, "train_loss": 5.356, "eval_loss": 6.1437, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.075289249420166, "gsm8k": 6.447291981090199, "math_qa": 6.010236740112305 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.017437452615617893, "math_qa": 0.001340033500837521 } }, { "flos": 2.319e+18, "train_loss": 5.3309, "eval_loss": 6.1508, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.081694602966309, "gsm8k": 6.461597095836293, "math_qa": 6.0140736897786455 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01592115238817286, "math_qa": 0.0016750418760469012 } }, { "flos": 2.328e+18, "train_loss": 5.3544, "eval_loss": 6.1306, "eval_accuracy": 0.007, "eval_loss_by_set": { "aqua_rat": 6.0645952224731445, "gsm8k": 6.432643543590199, "math_qa": 5.997703552246094 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.018953752843062926, "math_qa": 0.0016750418760469012 } }, { "flos": 2.336e+18, "train_loss": 5.3389, "eval_loss": 6.1342, "eval_accuracy": 0.0059, "eval_loss_by_set": { "aqua_rat": 6.071507930755615, "gsm8k": 6.434043884277344, "math_qa": 6.001930872599284 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.01592115238817286, "math_qa": 0.0016750418760469012 } }, { "flos": 2.344e+18, "train_loss": 5.3164, "eval_loss": 6.1364, "eval_accuracy": 0.0066, "eval_loss_by_set": { "aqua_rat": 6.066437721252441, "gsm8k": 6.42196308482777, "math_qa": 6.011376063028972 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.01819560272934041, "math_qa": 0.0016750418760469012 } }, { "flos": 2.353e+18, "train_loss": 5.3356, "eval_loss": 6.1484, "eval_accuracy": 0.007, "eval_loss_by_set": { "aqua_rat": 6.077330112457275, "gsm8k": 6.447696339000355, "math_qa": 6.017157872517903 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.018953752843062926, "math_qa": 0.0016750418760469012 } }, { "flos": 2.361e+18, "train_loss": 5.3434, "eval_loss": 6.1369, "eval_accuracy": 0.0068, "eval_loss_by_set": { "aqua_rat": 6.066393852233887, "gsm8k": 6.436666315252131, "math_qa": 6.0053361256917315 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.019711902956785442, "math_qa": 0.001340033500837521 } }, { "flos": 2.369e+18, "train_loss": 5.3349, "eval_loss": 6.1474, "eval_accuracy": 0.0059, "eval_loss_by_set": { "aqua_rat": 6.070897102355957, "gsm8k": 6.449372031471946, "math_qa": 6.015303293863933 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.01592115238817286, "math_qa": 0.0016750418760469012 } }, { "flos": 2.378e+18, "train_loss": 5.329, "eval_loss": 6.1479, "eval_accuracy": 0.0064, "eval_loss_by_set": { "aqua_rat": 6.0700507164001465, "gsm8k": 6.459670326926491, "math_qa": 6.01144282023112 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.017437452615617893, "math_qa": 0.0016750418760469012 } }, { "flos": 2.386e+18, "train_loss": 5.3665, "eval_loss": 6.1451, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.0753631591796875, "gsm8k": 6.458975358442827, "math_qa": 6.007057825724284 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.01592115238817286, "math_qa": 0.001340033500837521 } }, { "flos": 2.394e+18, "train_loss": 5.3376, "eval_loss": 6.1386, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.065056800842285, "gsm8k": 6.436676718971946, "math_qa": 6.008165995279948 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.015163002274450341, "math_qa": 0.0016750418760469012 } }, { "flos": 2.403e+18, "train_loss": 5.3561, "eval_loss": 6.1471, "eval_accuracy": 0.005, "eval_loss_by_set": { "aqua_rat": 6.077376842498779, "gsm8k": 6.450193925337358, "math_qa": 6.014069239298503 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.01288855193328279, "math_qa": 0.0016750418760469012 } }, { "flos": 2.411e+18, "train_loss": 5.334, "eval_loss": 6.1338, "eval_accuracy": 0.0068, "eval_loss_by_set": { "aqua_rat": 6.070457458496094, "gsm8k": 6.4387969970703125, "math_qa": 5.999267578125 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.01819560272934041, "math_qa": 0.0020100502512562816 } }, { "flos": 2.42e+18, "train_loss": 5.3397, "eval_loss": 6.1429, "eval_accuracy": 0.0068, "eval_loss_by_set": { "aqua_rat": 6.070038795471191, "gsm8k": 6.445971402254972, "math_qa": 6.010133743286133 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.018953752843062926, "math_qa": 0.0016750418760469012 } }, { "flos": 2.428e+18, "train_loss": 5.3287, "eval_loss": 6.1405, "eval_accuracy": 0.0077, "eval_loss_by_set": { "aqua_rat": 6.070577621459961, "gsm8k": 6.442782315340909, "math_qa": 6.007827123006185 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.02047005307050796, "math_qa": 0.0023450586264656616 } }, { "flos": 2.436e+18, "train_loss": 5.3238, "eval_loss": 6.1573, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.080885887145996, "gsm8k": 6.451315446333452, "math_qa": 6.02896245320638 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.01592115238817286, "math_qa": 0.001340033500837521 } }, { "flos": 2.445e+18, "train_loss": 5.3631, "eval_loss": 6.1465, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.06906795501709, "gsm8k": 6.438959295099432, "math_qa": 6.018836975097656 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.016679302501895376, "math_qa": 0.0016750418760469012 } }, { "flos": 2.453e+18, "train_loss": 5.338, "eval_loss": 6.149, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.069755554199219, "gsm8k": 6.4391000921076, "math_qa": 6.022717157999675 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.01592115238817286, "math_qa": 0.001340033500837521 } }, { "flos": 2.461e+18, "train_loss": 5.3714, "eval_loss": 6.1445, "eval_accuracy": 0.0072, "eval_loss_by_set": { "aqua_rat": 6.072763919830322, "gsm8k": 6.452898892489347, "math_qa": 6.009161631266276 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01819560272934041, "math_qa": 0.0023450586264656616 } }, { "flos": 2.47e+18, "train_loss": 5.3545, "eval_loss": 6.1466, "eval_accuracy": 0.0068, "eval_loss_by_set": { "aqua_rat": 6.070586204528809, "gsm8k": 6.4505088112571025, "math_qa": 6.013715108235677 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.017437452615617893, "math_qa": 0.0023450586264656616 } }, { "flos": 2.478e+18, "train_loss": 5.3412, "eval_loss": 6.1442, "eval_accuracy": 0.0068, "eval_loss_by_set": { "aqua_rat": 6.066789150238037, "gsm8k": 6.44510234485973, "math_qa": 6.012699127197266 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.018953752843062926, "math_qa": 0.0016750418760469012 } }, { "flos": 2.486e+18, "train_loss": 5.3225, "eval_loss": 6.1566, "eval_accuracy": 0.0072, "eval_loss_by_set": { "aqua_rat": 6.077278137207031, "gsm8k": 6.4624245383522725, "math_qa": 6.023047129313151 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.02122820318423048, "math_qa": 0.001340033500837521 } }, { "flos": 2.495e+18, "train_loss": 5.3473, "eval_loss": 6.1393, "eval_accuracy": 0.0055, "eval_loss_by_set": { "aqua_rat": 6.0623459815979, "gsm8k": 6.4345571344549, "math_qa": 6.010430018107097 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.014404852160727824, "math_qa": 0.0016750418760469012 } }, { "flos": 2.503e+18, "train_loss": 5.3329, "eval_loss": 6.1529, "eval_accuracy": 0.0064, "eval_loss_by_set": { "aqua_rat": 6.079031944274902, "gsm8k": 6.457304521040483, "math_qa": 6.019509633382161 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.016679302501895376, "math_qa": 0.0016750418760469012 } }, { "flos": 2.511e+18, "train_loss": 5.3283, "eval_loss": 6.1399, "eval_accuracy": 0.0064, "eval_loss_by_set": { "aqua_rat": 6.065117835998535, "gsm8k": 6.434241554953835, "math_qa": 6.011285781860352 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.01819560272934041, "math_qa": 0.001340033500837521 } }, { "flos": 2.52e+18, "train_loss": 5.335, "eval_loss": 6.1389, "eval_accuracy": 0.0064, "eval_loss_by_set": { "aqua_rat": 6.067636013031006, "gsm8k": 6.431884072043679, "math_qa": 6.010581970214844 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.01819560272934041, "math_qa": 0.001340033500837521 } }, { "flos": 2.528e+18, "train_loss": 5.3356, "eval_loss": 6.1295, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.062850475311279, "gsm8k": 6.425211126154119, "math_qa": 5.999576568603516 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.016679302501895376, "math_qa": 0.0016750418760469012 } }, { "flos": 2.536e+18, "train_loss": 5.3298, "eval_loss": 6.1477, "eval_accuracy": 0.0072, "eval_loss_by_set": { "aqua_rat": 6.075683116912842, "gsm8k": 6.449147311123935, "math_qa": 6.01551628112793 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.02047005307050796, "math_qa": 0.0016750418760469012 } }, { "flos": 2.545e+18, "train_loss": 5.3447, "eval_loss": 6.1344, "eval_accuracy": 0.0077, "eval_loss_by_set": { "aqua_rat": 6.068378448486328, "gsm8k": 6.430485118519176, "math_qa": 6.004230499267578 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.02047005307050796, "math_qa": 0.0023450586264656616 } }, { "flos": 2.553e+18, "train_loss": 5.3499, "eval_loss": 6.1332, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.065188407897949, "gsm8k": 6.436176646839488, "math_qa": 5.999926884969075 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.017437452615617893, "math_qa": 0.001340033500837521 } }, { "flos": 2.561e+18, "train_loss": 5.3491, "eval_loss": 6.1483, "eval_accuracy": 0.005, "eval_loss_by_set": { "aqua_rat": 6.073981761932373, "gsm8k": 6.465749567205256, "math_qa": 6.0089874267578125 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.013646702047005308, "math_qa": 0.001340033500837521 } }, { "flos": 2.57e+18, "train_loss": 5.3705, "eval_loss": 6.139, "eval_accuracy": 0.0064, "eval_loss_by_set": { "aqua_rat": 6.068730354309082, "gsm8k": 6.435703624378551, "math_qa": 6.008894602457683 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.017437452615617893, "math_qa": 0.001340033500837521 } }, { "flos": 2.578e+18, "train_loss": 5.3461, "eval_loss": 6.1486, "eval_accuracy": 0.0068, "eval_loss_by_set": { "aqua_rat": 6.068136215209961, "gsm8k": 6.450028852982954, "math_qa": 6.017139434814453 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.018953752843062926, "math_qa": 0.001340033500837521 } }, { "flos": 2.586e+18, "train_loss": 5.3414, "eval_loss": 6.1353, "eval_accuracy": 0.0064, "eval_loss_by_set": { "aqua_rat": 6.058961868286133, "gsm8k": 6.4194252707741475, "math_qa": 6.011454900105794 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.01819560272934041, "math_qa": 0.001340033500837521 } }, { "flos": 2.595e+18, "train_loss": 5.3525, "eval_loss": 6.1456, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.066134929656982, "gsm8k": 6.446101795543324, "math_qa": 6.014568328857422 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.01592115238817286, "math_qa": 0.001340033500837521 } }, { "flos": 2.603e+18, "train_loss": 5.3597, "eval_loss": 6.1426, "eval_accuracy": 0.0077, "eval_loss_by_set": { "aqua_rat": 6.061967372894287, "gsm8k": 6.419606989080256, "math_qa": 6.022396087646484 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.02047005307050796, "math_qa": 0.0020100502512562816 } }, { "flos": 2.611e+18, "train_loss": 5.335, "eval_loss": 6.1436, "eval_accuracy": 0.0077, "eval_loss_by_set": { "aqua_rat": 6.067106246948242, "gsm8k": 6.4411232688210225, "math_qa": 6.013682683308919 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.02047005307050796, "math_qa": 0.0023450586264656616 } }, { "flos": 2.62e+18, "train_loss": 5.3344, "eval_loss": 6.1456, "eval_accuracy": 0.007, "eval_loss_by_set": { "aqua_rat": 6.07343864440918, "gsm8k": 6.442337729714134, "math_qa": 6.015622456868489 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.019711902956785442, "math_qa": 0.001340033500837521 } }, { "flos": 2.628e+18, "train_loss": 5.3477, "eval_loss": 6.1405, "eval_accuracy": 0.0068, "eval_loss_by_set": { "aqua_rat": 6.074522018432617, "gsm8k": 6.445039922540838, "math_qa": 6.006415685017903 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.019711902956785442, "math_qa": 0.001340033500837521 } }, { "flos": 2.636e+18, "train_loss": 5.349, "eval_loss": 6.1417, "eval_accuracy": 0.0066, "eval_loss_by_set": { "aqua_rat": 6.0697832107543945, "gsm8k": 6.4362099387428975, "math_qa": 6.0126527150472 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.018953752843062926, "math_qa": 0.001340033500837521 } }, { "flos": 2.645e+18, "train_loss": 5.3586, "eval_loss": 6.1466, "eval_accuracy": 0.0059, "eval_loss_by_set": { "aqua_rat": 6.071943283081055, "gsm8k": 6.452848954634233, "math_qa": 6.012488047281901 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.01592115238817286, "math_qa": 0.0016750418760469012 } }, { "flos": 2.653e+18, "train_loss": 5.325, "eval_loss": 6.1593, "eval_accuracy": 0.0059, "eval_loss_by_set": { "aqua_rat": 6.07432746887207, "gsm8k": 6.4572622125799, "math_qa": 6.029788335164388 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.01592115238817286, "math_qa": 0.0016750418760469012 } }, { "flos": 2.661e+18, "train_loss": 5.3476, "eval_loss": 6.1427, "eval_accuracy": 0.0046, "eval_loss_by_set": { "aqua_rat": 6.066959857940674, "gsm8k": 6.446429165926847, "math_qa": 6.009792327880859 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.012130401819560273, "math_qa": 0.001340033500837521 } }, { "flos": 2.67e+18, "train_loss": 5.3439, "eval_loss": 6.1496, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.077167987823486, "gsm8k": 6.453546697443182, "math_qa": 6.016356786092122 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.016679302501895376, "math_qa": 0.0016750418760469012 } }, { "flos": 2.678e+18, "train_loss": 5.3312, "eval_loss": 6.1462, "eval_accuracy": 0.007, "eval_loss_by_set": { "aqua_rat": 6.070766448974609, "gsm8k": 6.450277155095881, "math_qa": 6.013191223144531 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.019711902956785442, "math_qa": 0.0016750418760469012 } }, { "flos": 2.686e+18, "train_loss": 5.3376, "eval_loss": 6.1501, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.073497772216797, "gsm8k": 6.462434248490767, "math_qa": 6.01336669921875 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.015163002274450341, "math_qa": 0.0016750418760469012 } }, { "flos": 2.695e+18, "train_loss": 5.3461, "eval_loss": 6.1537, "eval_accuracy": 0.0064, "eval_loss_by_set": { "aqua_rat": 6.074988842010498, "gsm8k": 6.457964810458097, "math_qa": 6.020865122477214 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.01819560272934041, "math_qa": 0.001340033500837521 } }, { "flos": 2.703e+18, "train_loss": 5.3506, "eval_loss": 6.1555, "eval_accuracy": 0.0055, "eval_loss_by_set": { "aqua_rat": 6.07314395904541, "gsm8k": 6.455169677734375, "math_qa": 6.025047302246094 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.015163002274450341, "math_qa": 0.001340033500837521 } }, { "flos": 2.711e+18, "train_loss": 5.3232, "eval_loss": 6.1412, "eval_accuracy": 0.007, "eval_loss_by_set": { "aqua_rat": 6.063539981842041, "gsm8k": 6.431141246448863, "math_qa": 6.014738082885742 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.02047005307050796, "math_qa": 0.001340033500837521 } }, { "flos": 2.72e+18, "train_loss": 5.3382, "eval_loss": 6.1389, "eval_accuracy": 0.0081, "eval_loss_by_set": { "aqua_rat": 6.0637335777282715, "gsm8k": 6.422162836248225, "math_qa": 6.0152587890625 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.024260803639120546, "math_qa": 0.001340033500837521 } }, { "flos": 2.728e+18, "train_loss": 5.3212, "eval_loss": 6.1477, "eval_accuracy": 0.0059, "eval_loss_by_set": { "aqua_rat": 6.066989898681641, "gsm8k": 6.450800115411932, "math_qa": 6.015557607014974 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.015163002274450341, "math_qa": 0.0016750418760469012 } }, { "flos": 2.736e+18, "train_loss": 5.3363, "eval_loss": 6.1398, "eval_accuracy": 0.007, "eval_loss_by_set": { "aqua_rat": 6.06794548034668, "gsm8k": 6.432148326526988, "math_qa": 6.011757532755534 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.02047005307050796, "math_qa": 0.001340033500837521 } }, { "flos": 2.745e+18, "train_loss": 5.3451, "eval_loss": 6.1535, "eval_accuracy": 0.0059, "eval_loss_by_set": { "aqua_rat": 6.071935653686523, "gsm8k": 6.4438088156960225, "math_qa": 6.0271860758463545 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.01592115238817286, "math_qa": 0.0016750418760469012 } }, { "flos": 2.753e+18, "train_loss": 5.3483, "eval_loss": 6.1496, "eval_accuracy": 0.0066, "eval_loss_by_set": { "aqua_rat": 6.070157051086426, "gsm8k": 6.441100380637429, "math_qa": 6.02261225382487 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.01819560272934041, "math_qa": 0.0016750418760469012 } }, { "flos": 2.762e+18, "train_loss": 5.349, "eval_loss": 6.1448, "eval_accuracy": 0.0066, "eval_loss_by_set": { "aqua_rat": 6.068930625915527, "gsm8k": 6.434688914905895, "math_qa": 6.018314361572266 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.018953752843062926, "math_qa": 0.001340033500837521 } }, { "flos": 2.77e+18, "train_loss": 5.3603, "eval_loss": 6.144, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.0638837814331055, "gsm8k": 6.431893782182173, "math_qa": 6.0187028249104815 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.01592115238817286, "math_qa": 0.001340033500837521 } }, { "flos": 2.778e+18, "train_loss": 5.3575, "eval_loss": 6.1417, "eval_accuracy": 0.0075, "eval_loss_by_set": { "aqua_rat": 6.062434196472168, "gsm8k": 6.427057439630682, "math_qa": 6.017534891764323 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.02047005307050796, "math_qa": 0.0016750418760469012 } }, { "flos": 2.787e+18, "train_loss": 5.3352, "eval_loss": 6.1506, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.078388214111328, "gsm8k": 6.445493524724787, "math_qa": 6.021443684895833 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 2.795e+18, "train_loss": 5.3372, "eval_loss": 6.1452, "eval_accuracy": 0.0068, "eval_loss_by_set": { "aqua_rat": 6.066365718841553, "gsm8k": 6.436424255371094, "math_qa": 6.018368403116862 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.018953752843062926, "math_qa": 0.001340033500837521 } }, { "flos": 2.803e+18, "train_loss": 5.3433, "eval_loss": 6.1382, "eval_accuracy": 0.0055, "eval_loss_by_set": { "aqua_rat": 6.066489219665527, "gsm8k": 6.430213234641335, "math_qa": 6.01034673055013 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.015163002274450341, "math_qa": 0.001340033500837521 } }, { "flos": 2.812e+18, "train_loss": 5.3418, "eval_loss": 6.1322, "eval_accuracy": 0.0066, "eval_loss_by_set": { "aqua_rat": 6.073009967803955, "gsm8k": 6.443943370472301, "math_qa": 5.994211832682292 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01819560272934041, "math_qa": 0.001340033500837521 } }, { "flos": 2.82e+18, "train_loss": 5.3464, "eval_loss": 6.1441, "eval_accuracy": 0.0064, "eval_loss_by_set": { "aqua_rat": 6.069725036621094, "gsm8k": 6.449211120605469, "math_qa": 6.010388056437175 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.01819560272934041, "math_qa": 0.001340033500837521 } }, { "flos": 2.828e+18, "train_loss": 5.3533, "eval_loss": 6.1247, "eval_accuracy": 0.0077, "eval_loss_by_set": { "aqua_rat": 6.055631637573242, "gsm8k": 6.4105446555397725, "math_qa": 5.999504725138347 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.021986353297952996, "math_qa": 0.001340033500837521 } }, { "flos": 2.837e+18, "train_loss": 5.3083, "eval_loss": 6.1396, "eval_accuracy": 0.0068, "eval_loss_by_set": { "aqua_rat": 6.066208839416504, "gsm8k": 6.442386973987926, "math_qa": 6.006984710693359 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.019711902956785442, "math_qa": 0.001340033500837521 } }, { "flos": 2.845e+18, "train_loss": 5.3501, "eval_loss": 6.1436, "eval_accuracy": 0.0053, "eval_loss_by_set": { "aqua_rat": 6.068141937255859, "gsm8k": 6.440127979625355, "math_qa": 6.014040629069011 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.014404852160727824, "math_qa": 0.001340033500837521 } }, { "flos": 2.853e+18, "train_loss": 5.3566, "eval_loss": 6.1551, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.067192077636719, "gsm8k": 6.451057434082031, "math_qa": 6.026831309000651 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01592115238817286, "math_qa": 0.0016750418760469012 } }, { "flos": 2.862e+18, "train_loss": 5.3347, "eval_loss": 6.1548, "eval_accuracy": 0.007, "eval_loss_by_set": { "aqua_rat": 6.072941303253174, "gsm8k": 6.458430203524503, "math_qa": 6.0224609375 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.02047005307050796, "math_qa": 0.001340033500837521 } }, { "flos": 2.87e+18, "train_loss": 5.3563, "eval_loss": 6.1473, "eval_accuracy": 0.0055, "eval_loss_by_set": { "aqua_rat": 6.068387985229492, "gsm8k": 6.446275190873579, "math_qa": 6.016918818155925 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.015163002274450341, "math_qa": 0.001340033500837521 } }, { "flos": 2.878e+18, "train_loss": 5.3507, "eval_loss": 6.139, "eval_accuracy": 0.0066, "eval_loss_by_set": { "aqua_rat": 6.068937301635742, "gsm8k": 6.435365156693892, "math_qa": 6.0090484619140625 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.01819560272934041, "math_qa": 0.0016750418760469012 } }, { "flos": 2.887e+18, "train_loss": 5.3387, "eval_loss": 6.1429, "eval_accuracy": 0.0059, "eval_loss_by_set": { "aqua_rat": 6.063875198364258, "gsm8k": 6.434946233575994, "math_qa": 6.0156911214192705 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.01592115238817286, "math_qa": 0.0016750418760469012 } }, { "flos": 2.895e+18, "train_loss": 5.3433, "eval_loss": 6.1566, "eval_accuracy": 0.0066, "eval_loss_by_set": { "aqua_rat": 6.073780059814453, "gsm8k": 6.460766878995028, "math_qa": 6.024141947428386 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.01819560272934041, "math_qa": 0.0016750418760469012 } }, { "flos": 2.903e+18, "train_loss": 5.3508, "eval_loss": 6.1484, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.072027683258057, "gsm8k": 6.450854214754972, "math_qa": 6.016099294026692 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.016679302501895376, "math_qa": 0.0016750418760469012 } }, { "flos": 2.912e+18, "train_loss": 5.3515, "eval_loss": 6.1516, "eval_accuracy": 0.0053, "eval_loss_by_set": { "aqua_rat": 6.070567607879639, "gsm8k": 6.448279640891335, "math_qa": 6.022427876790364 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.014404852160727824, "math_qa": 0.001340033500837521 } }, { "flos": 2.92e+18, "train_loss": 5.3495, "eval_loss": 6.1491, "eval_accuracy": 0.007, "eval_loss_by_set": { "aqua_rat": 6.073242664337158, "gsm8k": 6.443037553267046, "math_qa": 6.020635604858398 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.018953752843062926, "math_qa": 0.0020100502512562816 } }, { "flos": 2.928e+18, "train_loss": 5.356, "eval_loss": 6.1369, "eval_accuracy": 0.0064, "eval_loss_by_set": { "aqua_rat": 6.06146240234375, "gsm8k": 6.435162630948153, "math_qa": 6.00651486714681 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.01819560272934041, "math_qa": 0.001340033500837521 } }, { "flos": 2.937e+18, "train_loss": 5.3459, "eval_loss": 6.1236, "eval_accuracy": 0.0053, "eval_loss_by_set": { "aqua_rat": 6.057173728942871, "gsm8k": 6.413667158647017, "math_qa": 5.9961732228597 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.013646702047005308, "math_qa": 0.0016750418760469012 } }, { "flos": 2.945e+18, "train_loss": 5.3277, "eval_loss": 6.1511, "eval_accuracy": 0.0068, "eval_loss_by_set": { "aqua_rat": 6.067284107208252, "gsm8k": 6.457749106667259, "math_qa": 6.017611185709636 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.01819560272934041, "math_qa": 0.0020100502512562816 } }, { "flos": 2.953e+18, "train_loss": 5.3407, "eval_loss": 6.1478, "eval_accuracy": 0.0066, "eval_loss_by_set": { "aqua_rat": 6.066556930541992, "gsm8k": 6.455981167879972, "math_qa": 6.0133310953776045 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.016679302501895376, "math_qa": 0.0020100502512562816 } }, { "flos": 2.962e+18, "train_loss": 5.3205, "eval_loss": 6.1431, "eval_accuracy": 0.007, "eval_loss_by_set": { "aqua_rat": 6.063905715942383, "gsm8k": 6.4357452392578125, "math_qa": 6.015581766764323 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.019711902956785442, "math_qa": 0.001340033500837521 } }, { "flos": 2.97e+18, "train_loss": 5.3433, "eval_loss": 6.1475, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.068298816680908, "gsm8k": 6.433543118563565, "math_qa": 6.022924423217773 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.017437452615617893, "math_qa": 0.001340033500837521 } }, { "flos": 2.978e+18, "train_loss": 5.3375, "eval_loss": 6.1431, "eval_accuracy": 0.0068, "eval_loss_by_set": { "aqua_rat": 6.0618367195129395, "gsm8k": 6.432572104714134, "math_qa": 6.017152150472005 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.019711902956785442, "math_qa": 0.001340033500837521 } }, { "flos": 2.987e+18, "train_loss": 5.3419, "eval_loss": 6.1474, "eval_accuracy": 0.0068, "eval_loss_by_set": { "aqua_rat": 6.06303596496582, "gsm8k": 6.435739690607244, "math_qa": 6.022338231404622 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.019711902956785442, "math_qa": 0.001340033500837521 } }, { "flos": 2.995e+18, "train_loss": 5.3351, "eval_loss": 6.1428, "eval_accuracy": 0.0044, "eval_loss_by_set": { "aqua_rat": 6.068631172180176, "gsm8k": 6.450392289595171, "math_qa": 6.008066813151042 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.011372251705837756, "math_qa": 0.001340033500837521 } }, { "flos": 3.003e+18, "train_loss": 5.317, "eval_loss": 6.1367, "eval_accuracy": 0.0064, "eval_loss_by_set": { "aqua_rat": 6.06280517578125, "gsm8k": 6.434741627086293, "math_qa": 6.006267547607422 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.01819560272934041, "math_qa": 0.001340033500837521 } }, { "flos": 3.012e+18, "train_loss": 5.3504, "eval_loss": 6.1484, "eval_accuracy": 0.0053, "eval_loss_by_set": { "aqua_rat": 6.0744309425354, "gsm8k": 6.466357144442472, "math_qa": 6.008766174316406 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.014404852160727824, "math_qa": 0.001340033500837521 } }, { "flos": 3.02e+18, "train_loss": 5.34, "eval_loss": 6.1516, "eval_accuracy": 0.0064, "eval_loss_by_set": { "aqua_rat": 6.072611331939697, "gsm8k": 6.451472889293324, "math_qa": 6.020776112874349 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.017437452615617893, "math_qa": 0.0016750418760469012 } }, { "flos": 3.028e+18, "train_loss": 5.3283, "eval_loss": 6.1412, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.069194316864014, "gsm8k": 6.441864013671875, "math_qa": 6.009436925252278 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.01592115238817286, "math_qa": 0.001340033500837521 } }, { "flos": 3.037e+18, "train_loss": 5.3216, "eval_loss": 6.1454, "eval_accuracy": 0.0059, "eval_loss_by_set": { "aqua_rat": 6.068107604980469, "gsm8k": 6.440568403764204, "math_qa": 6.016518910725911 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 3.045e+18, "train_loss": 5.3377, "eval_loss": 6.1507, "eval_accuracy": 0.0055, "eval_loss_by_set": { "aqua_rat": 6.072761535644531, "gsm8k": 6.447614496404475, "math_qa": 6.02113660176595 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.015163002274450341, "math_qa": 0.001340033500837521 } }, { "flos": 3.053e+18, "train_loss": 5.3432, "eval_loss": 6.1525, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.075194835662842, "gsm8k": 6.4525840065696025, "math_qa": 6.021408716837565 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.01592115238817286, "math_qa": 0.001340033500837521 } }, { "flos": 3.062e+18, "train_loss": 5.3344, "eval_loss": 6.1443, "eval_accuracy": 0.0064, "eval_loss_by_set": { "aqua_rat": 6.072860240936279, "gsm8k": 6.4502646706321025, "math_qa": 6.010060628255208 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.01819560272934041, "math_qa": 0.001340033500837521 } }, { "flos": 3.07e+18, "train_loss": 5.3371, "eval_loss": 6.1334, "eval_accuracy": 0.0077, "eval_loss_by_set": { "aqua_rat": 6.062057018280029, "gsm8k": 6.423054088245738, "math_qa": 6.0065561930338545 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.022744503411675512, "math_qa": 0.001340033500837521 } }, { "flos": 3.078e+18, "train_loss": 5.3469, "eval_loss": 6.1379, "eval_accuracy": 0.0068, "eval_loss_by_set": { "aqua_rat": 6.068545341491699, "gsm8k": 6.432826649058949, "math_qa": 6.00843620300293 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.018953752843062926, "math_qa": 0.001340033500837521 } }, { "flos": 3.087e+18, "train_loss": 5.3078, "eval_loss": 6.1477, "eval_accuracy": 0.007, "eval_loss_by_set": { "aqua_rat": 6.066555500030518, "gsm8k": 6.453790838068182, "math_qa": 6.014148712158203 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.019711902956785442, "math_qa": 0.001340033500837521 } }, { "flos": 3.095e+18, "train_loss": 5.3432, "eval_loss": 6.1351, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.064269542694092, "gsm8k": 6.436175259676847, "math_qa": 6.003037770589192 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 3.104e+18, "train_loss": 5.3503, "eval_loss": 6.1562, "eval_accuracy": 0.0064, "eval_loss_by_set": { "aqua_rat": 6.072056770324707, "gsm8k": 6.453541148792613, "math_qa": 6.026926676432292 }, "eval_accuracy_by_set": { "aqua_rat": 0.011811023622047244, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 3.112e+18, "train_loss": 5.3417, "eval_loss": 6.151, "eval_accuracy": 0.0055, "eval_loss_by_set": { "aqua_rat": 6.072028636932373, "gsm8k": 6.4574806906960225, "math_qa": 6.017157236735026 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.015163002274450341, "math_qa": 0.001340033500837521 } }, { "flos": 3.12e+18, "train_loss": 5.3599, "eval_loss": 6.1405, "eval_accuracy": 0.0068, "eval_loss_by_set": { "aqua_rat": 6.066774845123291, "gsm8k": 6.437833612615412, "math_qa": 6.010412216186523 }, "eval_accuracy_by_set": { "aqua_rat": 0.011811023622047244, "gsm8k": 0.01819560272934041, "math_qa": 0.001340033500837521 } }, { "flos": 3.129e+18, "train_loss": 5.3338, "eval_loss": 6.138, "eval_accuracy": 0.0068, "eval_loss_by_set": { "aqua_rat": 6.0693206787109375, "gsm8k": 6.4453208229758525, "math_qa": 6.002819061279297 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.019711902956785442, "math_qa": 0.001340033500837521 } }, { "flos": 3.137e+18, "train_loss": 5.3538, "eval_loss": 6.1522, "eval_accuracy": 0.0072, "eval_loss_by_set": { "aqua_rat": 6.071402072906494, "gsm8k": 6.455531727183949, "math_qa": 6.019906997680664 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.02122820318423048, "math_qa": 0.001340033500837521 } }, { "flos": 3.145e+18, "train_loss": 5.3519, "eval_loss": 6.1478, "eval_accuracy": 0.0066, "eval_loss_by_set": { "aqua_rat": 6.074611663818359, "gsm8k": 6.444340792569247, "math_qa": 6.017954508463542 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.018953752843062926, "math_qa": 0.001340033500837521 } }, { "flos": 3.154e+18, "train_loss": 5.3314, "eval_loss": 6.1471, "eval_accuracy": 0.0066, "eval_loss_by_set": { "aqua_rat": 6.069217681884766, "gsm8k": 6.449727838689631, "math_qa": 6.014902750651042 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.01819560272934041, "math_qa": 0.0016750418760469012 } }, { "flos": 3.162e+18, "train_loss": 5.328, "eval_loss": 6.1503, "eval_accuracy": 0.0066, "eval_loss_by_set": { "aqua_rat": 6.0723700523376465, "gsm8k": 6.462554931640625, "math_qa": 6.013718922932942 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.018953752843062926, "math_qa": 0.001340033500837521 } }, { "flos": 3.17e+18, "train_loss": 5.3337, "eval_loss": 6.1509, "eval_accuracy": 0.0064, "eval_loss_by_set": { "aqua_rat": 6.068110942840576, "gsm8k": 6.447114424272017, "math_qa": 6.021975199381511 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.01819560272934041, "math_qa": 0.001340033500837521 } }, { "flos": 3.179e+18, "train_loss": 5.319, "eval_loss": 6.1472, "eval_accuracy": 0.0072, "eval_loss_by_set": { "aqua_rat": 6.073777198791504, "gsm8k": 6.457462657581676, "math_qa": 6.011088053385417 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.02122820318423048, "math_qa": 0.001340033500837521 } }, { "flos": 3.187e+18, "train_loss": 5.3274, "eval_loss": 6.1549, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.079101085662842, "gsm8k": 6.467333706942472, "math_qa": 6.017977396647136 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.01592115238817286, "math_qa": 0.001340033500837521 } }, { "flos": 3.195e+18, "train_loss": 5.3465, "eval_loss": 6.152, "eval_accuracy": 0.005, "eval_loss_by_set": { "aqua_rat": 6.072585582733154, "gsm8k": 6.4518585205078125, "math_qa": 6.021132151285808 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.01288855193328279, "math_qa": 0.0016750418760469012 } }, { "flos": 3.204e+18, "train_loss": 5.3314, "eval_loss": 6.1434, "eval_accuracy": 0.0055, "eval_loss_by_set": { "aqua_rat": 6.067710876464844, "gsm8k": 6.441530401056463, "math_qa": 6.013072967529297 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.014404852160727824, "math_qa": 0.001340033500837521 } }, { "flos": 3.212e+18, "train_loss": 5.3493, "eval_loss": 6.1591, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.080972671508789, "gsm8k": 6.462033358487216, "math_qa": 6.026758193969727 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.01592115238817286, "math_qa": 0.001340033500837521 } }, { "flos": 3.22e+18, "train_loss": 5.3541, "eval_loss": 6.1558, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.077005863189697, "gsm8k": 6.456579034978693, "math_qa": 6.024548848470052 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.017437452615617893, "math_qa": 0.001340033500837521 } }, { "flos": 3.229e+18, "train_loss": 5.3423, "eval_loss": 6.1526, "eval_accuracy": 0.0066, "eval_loss_by_set": { "aqua_rat": 6.074342727661133, "gsm8k": 6.458364313299006, "math_qa": 6.018992106119792 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.016679302501895376, "math_qa": 0.0020100502512562816 } }, { "flos": 3.237e+18, "train_loss": 5.32, "eval_loss": 6.1427, "eval_accuracy": 0.0075, "eval_loss_by_set": { "aqua_rat": 6.062560558319092, "gsm8k": 6.440723765980113, "math_qa": 6.012796401977539 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.021986353297952996, "math_qa": 0.001340033500837521 } }, { "flos": 3.245e+18, "train_loss": 5.3289, "eval_loss": 6.1566, "eval_accuracy": 0.0059, "eval_loss_by_set": { "aqua_rat": 6.0775370597839355, "gsm8k": 6.468324141068892, "math_qa": 6.020385106404622 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 3.254e+18, "train_loss": 5.3404, "eval_loss": 6.1389, "eval_accuracy": 0.0053, "eval_loss_by_set": { "aqua_rat": 6.064739227294922, "gsm8k": 6.432545748623935, "math_qa": 6.010428110758464 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.014404852160727824, "math_qa": 0.001340033500837521 } }, { "flos": 3.262e+18, "train_loss": 5.3377, "eval_loss": 6.149, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.069781303405762, "gsm8k": 6.447013854980469, "math_qa": 6.019008636474609 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.01592115238817286, "math_qa": 0.001340033500837521 } }, { "flos": 3.27e+18, "train_loss": 5.337, "eval_loss": 6.1391, "eval_accuracy": 0.0059, "eval_loss_by_set": { "aqua_rat": 6.063379287719727, "gsm8k": 6.43254921653054, "math_qa": 6.010927836100261 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 3.279e+18, "train_loss": 5.3254, "eval_loss": 6.1489, "eval_accuracy": 0.0066, "eval_loss_by_set": { "aqua_rat": 6.069933891296387, "gsm8k": 6.462148492986506, "math_qa": 6.011848449707031 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.018953752843062926, "math_qa": 0.001340033500837521 } }, { "flos": 3.287e+18, "train_loss": 5.3257, "eval_loss": 6.1569, "eval_accuracy": 0.0059, "eval_loss_by_set": { "aqua_rat": 6.076312065124512, "gsm8k": 6.463206898082387, "math_qa": 6.023248036702474 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 3.295e+18, "train_loss": 5.3336, "eval_loss": 6.1486, "eval_accuracy": 0.0072, "eval_loss_by_set": { "aqua_rat": 6.064736366271973, "gsm8k": 6.4325644753196025, "math_qa": 6.025374094645183 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.019711902956785442, "math_qa": 0.0020100502512562816 } }, { "flos": 3.304e+18, "train_loss": 5.3319, "eval_loss": 6.1495, "eval_accuracy": 0.0066, "eval_loss_by_set": { "aqua_rat": 6.072162628173828, "gsm8k": 6.454175082120028, "math_qa": 6.0162353515625 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.018953752843062926, "math_qa": 0.001340033500837521 } }, { "flos": 3.312e+18, "train_loss": 5.3464, "eval_loss": 6.1437, "eval_accuracy": 0.007, "eval_loss_by_set": { "aqua_rat": 6.067646503448486, "gsm8k": 6.462765780362216, "math_qa": 6.0037689208984375 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.02047005307050796, "math_qa": 0.001340033500837521 } }, { "flos": 3.32e+18, "train_loss": 5.3243, "eval_loss": 6.1446, "eval_accuracy": 0.0072, "eval_loss_by_set": { "aqua_rat": 6.0690598487854, "gsm8k": 6.463951804421165, "math_qa": 6.004472732543945 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.02047005307050796, "math_qa": 0.001340033500837521 } }, { "flos": 3.329e+18, "train_loss": 5.325, "eval_loss": 6.1478, "eval_accuracy": 0.0066, "eval_loss_by_set": { "aqua_rat": 6.066192626953125, "gsm8k": 6.441099687056108, "math_qa": 6.020184834798177 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.018953752843062926, "math_qa": 0.001340033500837521 } }, { "flos": 3.337e+18, "train_loss": 5.3391, "eval_loss": 6.1523, "eval_accuracy": 0.0059, "eval_loss_by_set": { "aqua_rat": 6.0682854652404785, "gsm8k": 6.4492409446022725, "math_qa": 6.02314821879069 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 3.346e+18, "train_loss": 5.3342, "eval_loss": 6.1462, "eval_accuracy": 0.0066, "eval_loss_by_set": { "aqua_rat": 6.068414211273193, "gsm8k": 6.448304609818892, "math_qa": 6.014232635498047 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.018953752843062926, "math_qa": 0.001340033500837521 } }, { "flos": 3.354e+18, "train_loss": 5.3457, "eval_loss": 6.1496, "eval_accuracy": 0.0064, "eval_loss_by_set": { "aqua_rat": 6.070217132568359, "gsm8k": 6.445734891024503, "math_qa": 6.020530700683594 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.01819560272934041, "math_qa": 0.001340033500837521 } }, { "flos": 3.362e+18, "train_loss": 5.3478, "eval_loss": 6.1406, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.065244674682617, "gsm8k": 6.4404380104758525, "math_qa": 6.00947634379069 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.01592115238817286, "math_qa": 0.0020100502512562816 } }, { "flos": 3.371e+18, "train_loss": 5.3557, "eval_loss": 6.145, "eval_accuracy": 0.0053, "eval_loss_by_set": { "aqua_rat": 6.070929050445557, "gsm8k": 6.448634060946378, "math_qa": 6.011983235677083 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.014404852160727824, "math_qa": 0.001340033500837521 } }, { "flos": 3.379e+18, "train_loss": 5.3452, "eval_loss": 6.1441, "eval_accuracy": 0.0055, "eval_loss_by_set": { "aqua_rat": 6.0651397705078125, "gsm8k": 6.435589183460582, "math_qa": 6.017068862915039 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.015163002274450341, "math_qa": 0.001340033500837521 } }, { "flos": 3.387e+18, "train_loss": 5.3381, "eval_loss": 6.1547, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.074188232421875, "gsm8k": 6.459327004172585, "math_qa": 6.021823883056641 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.017437452615617893, "math_qa": 0.001340033500837521 } }, { "flos": 3.396e+18, "train_loss": 5.35, "eval_loss": 6.1483, "eval_accuracy": 0.0066, "eval_loss_by_set": { "aqua_rat": 6.069810390472412, "gsm8k": 6.446061567826704, "math_qa": 6.018311818440755 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.018953752843062926, "math_qa": 0.001340033500837521 } }, { "flos": 3.404e+18, "train_loss": 5.3268, "eval_loss": 6.1438, "eval_accuracy": 0.0064, "eval_loss_by_set": { "aqua_rat": 6.071338653564453, "gsm8k": 6.448846990411932, "math_qa": 6.009986877441406 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.01819560272934041, "math_qa": 0.001340033500837521 } }, { "flos": 3.412e+18, "train_loss": 5.3288, "eval_loss": 6.1457, "eval_accuracy": 0.0066, "eval_loss_by_set": { "aqua_rat": 6.07059383392334, "gsm8k": 6.442027698863637, "math_qa": 6.016139984130859 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.018953752843062926, "math_qa": 0.001340033500837521 } }, { "flos": 3.421e+18, "train_loss": 5.3373, "eval_loss": 6.1435, "eval_accuracy": 0.0064, "eval_loss_by_set": { "aqua_rat": 6.070277214050293, "gsm8k": 6.450361078435725, "math_qa": 6.008883158365886 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.01819560272934041, "math_qa": 0.001340033500837521 } }, { "flos": 3.429e+18, "train_loss": 5.3359, "eval_loss": 6.1438, "eval_accuracy": 0.005, "eval_loss_by_set": { "aqua_rat": 6.069149494171143, "gsm8k": 6.4468772194602275, "math_qa": 6.011128743489583 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.013646702047005308, "math_qa": 0.001340033500837521 } }, { "flos": 3.437e+18, "train_loss": 5.338, "eval_loss": 6.1482, "eval_accuracy": 0.0064, "eval_loss_by_set": { "aqua_rat": 6.070199012756348, "gsm8k": 6.448410727761009, "math_qa": 6.017075220743815 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.01819560272934041, "math_qa": 0.001340033500837521 } }, { "flos": 3.446e+18, "train_loss": 5.3279, "eval_loss": 6.1483, "eval_accuracy": 0.0068, "eval_loss_by_set": { "aqua_rat": 6.068012237548828, "gsm8k": 6.44136532870206, "math_qa": 6.020652135213216 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.019711902956785442, "math_qa": 0.001340033500837521 } }, { "flos": 3.454e+18, "train_loss": 5.3002, "eval_loss": 6.1484, "eval_accuracy": 0.005, "eval_loss_by_set": { "aqua_rat": 6.069093704223633, "gsm8k": 6.460402055220171, "math_qa": 6.011995951334636 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.013646702047005308, "math_qa": 0.001340033500837521 } }, { "flos": 3.462e+18, "train_loss": 5.3334, "eval_loss": 6.1545, "eval_accuracy": 0.0072, "eval_loss_by_set": { "aqua_rat": 6.06968355178833, "gsm8k": 6.454051624644887, "math_qa": 6.024294535319011 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.02122820318423048, "math_qa": 0.001340033500837521 } }, { "flos": 3.471e+18, "train_loss": 5.345, "eval_loss": 6.1459, "eval_accuracy": 0.0066, "eval_loss_by_set": { "aqua_rat": 6.0745391845703125, "gsm8k": 6.452557650479403, "math_qa": 6.011363983154297 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.018953752843062926, "math_qa": 0.001340033500837521 } }, { "flos": 3.479e+18, "train_loss": 5.3348, "eval_loss": 6.1414, "eval_accuracy": 0.0066, "eval_loss_by_set": { "aqua_rat": 6.069282531738281, "gsm8k": 6.441402782093395, "math_qa": 6.009946823120117 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.018953752843062926, "math_qa": 0.001340033500837521 } }, { "flos": 3.487e+18, "train_loss": 5.3568, "eval_loss": 6.1488, "eval_accuracy": 0.0059, "eval_loss_by_set": { "aqua_rat": 6.066270351409912, "gsm8k": 6.45256874778054, "math_qa": 6.016520818074544 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 3.496e+18, "train_loss": 5.3386, "eval_loss": 6.1503, "eval_accuracy": 0.0059, "eval_loss_by_set": { "aqua_rat": 6.072019577026367, "gsm8k": 6.451474276455966, "math_qa": 6.018791198730469 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 3.504e+18, "train_loss": 5.3408, "eval_loss": 6.147, "eval_accuracy": 0.0064, "eval_loss_by_set": { "aqua_rat": 6.069178104400635, "gsm8k": 6.455843145197088, "math_qa": 6.011894226074219 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.01819560272934041, "math_qa": 0.001340033500837521 } }, { "flos": 3.512e+18, "train_loss": 5.3231, "eval_loss": 6.1311, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.060822486877441, "gsm8k": 6.442671342329546, "math_qa": 5.994165420532227 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.017437452615617893, "math_qa": 0.001340033500837521 } }, { "flos": 3.521e+18, "train_loss": 5.3321, "eval_loss": 6.1488, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.071310043334961, "gsm8k": 6.451829390092329, "math_qa": 6.016320546468099 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.017437452615617893, "math_qa": 0.001340033500837521 } }, { "flos": 3.529e+18, "train_loss": 5.3284, "eval_loss": 6.1392, "eval_accuracy": 0.0068, "eval_loss_by_set": { "aqua_rat": 6.065729141235352, "gsm8k": 6.446941722523082, "math_qa": 6.004210789998372 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.018953752843062926, "math_qa": 0.0016750418760469012 } }, { "flos": 3.537e+18, "train_loss": 5.3414, "eval_loss": 6.1514, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.068408966064453, "gsm8k": 6.449812455610796, "math_qa": 6.021507263183594 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.015163002274450341, "math_qa": 0.001340033500837521 } }, { "flos": 3.546e+18, "train_loss": 5.3496, "eval_loss": 6.1449, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.066247940063477, "gsm8k": 6.434940684925426, "math_qa": 6.018520355224609 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.01592115238817286, "math_qa": 0.001340033500837521 } }, { "flos": 3.554e+18, "train_loss": 5.3401, "eval_loss": 6.1573, "eval_accuracy": 0.0068, "eval_loss_by_set": { "aqua_rat": 6.078315258026123, "gsm8k": 6.46842471036044, "math_qa": 6.021327972412109 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.019711902956785442, "math_qa": 0.001340033500837521 } }, { "flos": 3.562e+18, "train_loss": 5.3385, "eval_loss": 6.1508, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.070828437805176, "gsm8k": 6.4630959250710225, "math_qa": 6.014392852783203 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.017437452615617893, "math_qa": 0.001340033500837521 } }, { "flos": 3.571e+18, "train_loss": 5.3427, "eval_loss": 6.1446, "eval_accuracy": 0.0068, "eval_loss_by_set": { "aqua_rat": 6.0680437088012695, "gsm8k": 6.453566117720171, "math_qa": 6.009382247924805 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.019711902956785442, "math_qa": 0.001340033500837521 } }, { "flos": 3.579e+18, "train_loss": 5.3448, "eval_loss": 6.1508, "eval_accuracy": 0.007, "eval_loss_by_set": { "aqua_rat": 6.07547664642334, "gsm8k": 6.464601690118963, "math_qa": 6.01327641805013 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.02047005307050796, "math_qa": 0.001340033500837521 } }, { "flos": 3.587e+18, "train_loss": 5.3493, "eval_loss": 6.1596, "eval_accuracy": 0.0064, "eval_loss_by_set": { "aqua_rat": 6.078639030456543, "gsm8k": 6.458486383611506, "math_qa": 6.029304504394531 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.01819560272934041, "math_qa": 0.001340033500837521 } }, { "flos": 3.596e+18, "train_loss": 5.3239, "eval_loss": 6.1494, "eval_accuracy": 0.0064, "eval_loss_by_set": { "aqua_rat": 6.068138599395752, "gsm8k": 6.457141529430043, "math_qa": 6.015163421630859 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.01819560272934041, "math_qa": 0.001340033500837521 } }, { "flos": 3.604e+18, "train_loss": 5.3287, "eval_loss": 6.148, "eval_accuracy": 0.0053, "eval_loss_by_set": { "aqua_rat": 6.069642066955566, "gsm8k": 6.447671370072798, "math_qa": 6.017232259114583 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.014404852160727824, "math_qa": 0.001340033500837521 } }, { "flos": 3.612e+18, "train_loss": 5.3303, "eval_loss": 6.1461, "eval_accuracy": 0.0068, "eval_loss_by_set": { "aqua_rat": 6.070550918579102, "gsm8k": 6.452966863458807, "math_qa": 6.011779149373372 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.019711902956785442, "math_qa": 0.001340033500837521 } }, { "flos": 3.621e+18, "train_loss": 5.3386, "eval_loss": 6.1509, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.072902202606201, "gsm8k": 6.461327986283735, "math_qa": 6.0150801340738935 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.017437452615617893, "math_qa": 0.001340033500837521 } }, { "flos": 3.629e+18, "train_loss": 5.3518, "eval_loss": 6.1478, "eval_accuracy": 0.005, "eval_loss_by_set": { "aqua_rat": 6.070950508117676, "gsm8k": 6.448577187278054, "math_qa": 6.016354878743489 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.013646702047005308, "math_qa": 0.001340033500837521 } }, { "flos": 3.638e+18, "train_loss": 5.3526, "eval_loss": 6.1491, "eval_accuracy": 0.0068, "eval_loss_by_set": { "aqua_rat": 6.064167022705078, "gsm8k": 6.449918573552912, "math_qa": 6.0182679494222 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.018953752843062926, "math_qa": 0.0016750418760469012 } }, { "flos": 3.646e+18, "train_loss": 5.3391, "eval_loss": 6.1459, "eval_accuracy": 0.0059, "eval_loss_by_set": { "aqua_rat": 6.066690444946289, "gsm8k": 6.4513633034446025, "math_qa": 6.012517929077148 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 3.654e+18, "train_loss": 5.3364, "eval_loss": 6.141, "eval_accuracy": 0.0066, "eval_loss_by_set": { "aqua_rat": 6.06346321105957, "gsm8k": 6.433475147594105, "math_qa": 6.013419469197591 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.018953752843062926, "math_qa": 0.001340033500837521 } }, { "flos": 3.663e+18, "train_loss": 5.3135, "eval_loss": 6.1518, "eval_accuracy": 0.0059, "eval_loss_by_set": { "aqua_rat": 6.067758560180664, "gsm8k": 6.46451846036044, "math_qa": 6.015474319458008 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 3.671e+18, "train_loss": 5.3276, "eval_loss": 6.1484, "eval_accuracy": 0.0046, "eval_loss_by_set": { "aqua_rat": 6.076416969299316, "gsm8k": 6.45828593860973, "math_qa": 6.012337366739909 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.012130401819560273, "math_qa": 0.001340033500837521 } }, { "flos": 3.679e+18, "train_loss": 5.3343, "eval_loss": 6.1638, "eval_accuracy": 0.0053, "eval_loss_by_set": { "aqua_rat": 6.075188636779785, "gsm8k": 6.464134909889915, "math_qa": 6.033575693766276 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.014404852160727824, "math_qa": 0.001340033500837521 } }, { "flos": 3.688e+18, "train_loss": 5.3579, "eval_loss": 6.142, "eval_accuracy": 0.005, "eval_loss_by_set": { "aqua_rat": 6.065446853637695, "gsm8k": 6.443812977183949, "math_qa": 6.010088602701823 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.013646702047005308, "math_qa": 0.001340033500837521 } }, { "flos": 3.696e+18, "train_loss": 5.3219, "eval_loss": 6.1357, "eval_accuracy": 0.0068, "eval_loss_by_set": { "aqua_rat": 6.06483268737793, "gsm8k": 6.441488786177202, "math_qa": 6.001462300618489 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.019711902956785442, "math_qa": 0.001340033500837521 } }, { "flos": 3.704e+18, "train_loss": 5.33, "eval_loss": 6.1448, "eval_accuracy": 0.0059, "eval_loss_by_set": { "aqua_rat": 6.071198463439941, "gsm8k": 6.455204356800426, "math_qa": 6.008726755777995 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 3.713e+18, "train_loss": 5.3274, "eval_loss": 6.1504, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.070489883422852, "gsm8k": 6.456385525790128, "math_qa": 6.016881942749023 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.01592115238817286, "math_qa": 0.001340033500837521 } }, { "flos": 3.721e+18, "train_loss": 5.3219, "eval_loss": 6.1406, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.064599514007568, "gsm8k": 6.443308049982244, "math_qa": 6.008251190185547 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 3.729e+18, "train_loss": 5.3266, "eval_loss": 6.1441, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.068447113037109, "gsm8k": 6.452839244495738, "math_qa": 6.008841832478841 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.01592115238817286, "math_qa": 0.001340033500837521 } }, { "flos": 3.738e+18, "train_loss": 5.3428, "eval_loss": 6.1502, "eval_accuracy": 0.0053, "eval_loss_by_set": { "aqua_rat": 6.070888996124268, "gsm8k": 6.451612992720171, "math_qa": 6.018660227457683 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.013646702047005308, "math_qa": 0.001340033500837521 } }, { "flos": 3.746e+18, "train_loss": 5.3319, "eval_loss": 6.1511, "eval_accuracy": 0.0064, "eval_loss_by_set": { "aqua_rat": 6.075139999389648, "gsm8k": 6.47420224276456, "math_qa": 6.009267807006836 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.01819560272934041, "math_qa": 0.001340033500837521 } }, { "flos": 3.754e+18, "train_loss": 5.3512, "eval_loss": 6.1426, "eval_accuracy": 0.0059, "eval_loss_by_set": { "aqua_rat": 6.067625999450684, "gsm8k": 6.439317183061079, "math_qa": 6.012863794962565 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 3.763e+18, "train_loss": 5.3253, "eval_loss": 6.1503, "eval_accuracy": 0.0066, "eval_loss_by_set": { "aqua_rat": 6.072997570037842, "gsm8k": 6.450399918989702, "math_qa": 6.019203186035156 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.018953752843062926, "math_qa": 0.001340033500837521 } }, { "flos": 3.771e+18, "train_loss": 5.3393, "eval_loss": 6.1381, "eval_accuracy": 0.0066, "eval_loss_by_set": { "aqua_rat": 6.06302547454834, "gsm8k": 6.44156230579723, "math_qa": 6.005327224731445 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.018953752843062926, "math_qa": 0.001340033500837521 } }, { "flos": 3.779e+18, "train_loss": 5.342, "eval_loss": 6.1445, "eval_accuracy": 0.0048, "eval_loss_by_set": { "aqua_rat": 6.066464424133301, "gsm8k": 6.442589499733665, "math_qa": 6.014369964599609 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.01288855193328279, "math_qa": 0.001340033500837521 } }, { "flos": 3.788e+18, "train_loss": 5.3363, "eval_loss": 6.1461, "eval_accuracy": 0.0066, "eval_loss_by_set": { "aqua_rat": 6.067447185516357, "gsm8k": 6.462101329456676, "math_qa": 6.007752100626628 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.018953752843062926, "math_qa": 0.001340033500837521 } }, { "flos": 3.796e+18, "train_loss": 5.3407, "eval_loss": 6.1478, "eval_accuracy": 0.0053, "eval_loss_by_set": { "aqua_rat": 6.0686140060424805, "gsm8k": 6.454776417125355, "math_qa": 6.013706207275391 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.013646702047005308, "math_qa": 0.001340033500837521 } }, { "flos": 3.804e+18, "train_loss": 5.3126, "eval_loss": 6.1449, "eval_accuracy": 0.0053, "eval_loss_by_set": { "aqua_rat": 6.06585168838501, "gsm8k": 6.441667730158025, "math_qa": 6.015405019124349 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.014404852160727824, "math_qa": 0.001340033500837521 } }, { "flos": 3.813e+18, "train_loss": 5.3291, "eval_loss": 6.1397, "eval_accuracy": 0.0053, "eval_loss_by_set": { "aqua_rat": 6.060029029846191, "gsm8k": 6.427946610884233, "math_qa": 6.014253616333008 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.013646702047005308, "math_qa": 0.001340033500837521 } }, { "flos": 3.821e+18, "train_loss": 5.3443, "eval_loss": 6.1394, "eval_accuracy": 0.0064, "eval_loss_by_set": { "aqua_rat": 6.055566310882568, "gsm8k": 6.427007501775568, "math_qa": 6.014545440673828 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.017437452615617893, "math_qa": 0.001340033500837521 } }, { "flos": 3.829e+18, "train_loss": 5.3336, "eval_loss": 6.1424, "eval_accuracy": 0.0053, "eval_loss_by_set": { "aqua_rat": 6.064447402954102, "gsm8k": 6.450543490323153, "math_qa": 6.007714589436849 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.014404852160727824, "math_qa": 0.001340033500837521 } }, { "flos": 3.838e+18, "train_loss": 5.3336, "eval_loss": 6.1487, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.069109916687012, "gsm8k": 6.454227100719105, "math_qa": 6.015261332194011 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 3.846e+18, "train_loss": 5.3429, "eval_loss": 6.1476, "eval_accuracy": 0.0059, "eval_loss_by_set": { "aqua_rat": 6.066751480102539, "gsm8k": 6.44693339954723, "math_qa": 6.0171324412028 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01592115238817286, "math_qa": 0.001340033500837521 } }, { "flos": 3.854e+18, "train_loss": 5.3359, "eval_loss": 6.152, "eval_accuracy": 0.0059, "eval_loss_by_set": { "aqua_rat": 6.070639610290527, "gsm8k": 6.462338534268466, "math_qa": 6.016593933105469 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 3.863e+18, "train_loss": 5.3518, "eval_loss": 6.1519, "eval_accuracy": 0.0064, "eval_loss_by_set": { "aqua_rat": 6.065835952758789, "gsm8k": 6.450889587402344, "math_qa": 6.022102355957031 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.01819560272934041, "math_qa": 0.001340033500837521 } }, { "flos": 3.871e+18, "train_loss": 5.3415, "eval_loss": 6.1434, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.065364360809326, "gsm8k": 6.451699690385298, "math_qa": 6.008584340413411 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.015163002274450341, "math_qa": 0.001340033500837521 } }, { "flos": 3.879e+18, "train_loss": 5.3337, "eval_loss": 6.1427, "eval_accuracy": 0.0055, "eval_loss_by_set": { "aqua_rat": 6.064255714416504, "gsm8k": 6.44107402454723, "math_qa": 6.0124460856119795 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.014404852160727824, "math_qa": 0.001340033500837521 } }, { "flos": 3.888e+18, "train_loss": 5.3387, "eval_loss": 6.1451, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.0677490234375, "gsm8k": 6.461261402476918, "math_qa": 6.006676355997722 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.017437452615617893, "math_qa": 0.001340033500837521 } }, { "flos": 3.896e+18, "train_loss": 5.3374, "eval_loss": 6.1574, "eval_accuracy": 0.0048, "eval_loss_by_set": { "aqua_rat": 6.077689170837402, "gsm8k": 6.471033269708807, "math_qa": 6.020315806070964 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.01288855193328279, "math_qa": 0.001340033500837521 } }, { "flos": 3.904e+18, "train_loss": 5.3295, "eval_loss": 6.1454, "eval_accuracy": 0.0055, "eval_loss_by_set": { "aqua_rat": 6.068569183349609, "gsm8k": 6.4491799094460225, "math_qa": 6.012587229410808 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.014404852160727824, "math_qa": 0.001340033500837521 } }, { "flos": 3.913e+18, "train_loss": 5.3377, "eval_loss": 6.1539, "eval_accuracy": 0.0059, "eval_loss_by_set": { "aqua_rat": 6.072157382965088, "gsm8k": 6.46439639004794, "math_qa": 6.018359502156575 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01592115238817286, "math_qa": 0.001340033500837521 } }, { "flos": 3.921e+18, "train_loss": 5.3399, "eval_loss": 6.1319, "eval_accuracy": 0.0059, "eval_loss_by_set": { "aqua_rat": 6.059302806854248, "gsm8k": 6.436267505992543, "math_qa": 5.998513539632161 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 3.93e+18, "train_loss": 5.3302, "eval_loss": 6.1522, "eval_accuracy": 0.005, "eval_loss_by_set": { "aqua_rat": 6.0690765380859375, "gsm8k": 6.461057489568537, "math_qa": 6.017597198486328 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.013646702047005308, "math_qa": 0.001340033500837521 } }, { "flos": 3.938e+18, "train_loss": 5.3284, "eval_loss": 6.1367, "eval_accuracy": 0.0046, "eval_loss_by_set": { "aqua_rat": 6.062234878540039, "gsm8k": 6.436476967551491, "math_qa": 6.005573272705078 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.012130401819560273, "math_qa": 0.001340033500837521 } }, { "flos": 3.946e+18, "train_loss": 5.3409, "eval_loss": 6.1589, "eval_accuracy": 0.0059, "eval_loss_by_set": { "aqua_rat": 6.072988510131836, "gsm8k": 6.461279435591265, "math_qa": 6.027405420939128 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 3.955e+18, "train_loss": 5.323, "eval_loss": 6.1513, "eval_accuracy": 0.0053, "eval_loss_by_set": { "aqua_rat": 6.070372104644775, "gsm8k": 6.452428644353693, "math_qa": 6.019960403442383 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.014404852160727824, "math_qa": 0.001340033500837521 } }, { "flos": 3.963e+18, "train_loss": 5.3421, "eval_loss": 6.1493, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.0710859298706055, "gsm8k": 6.46509413285689, "math_qa": 6.011124928792317 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.017437452615617893, "math_qa": 0.001340033500837521 } }, { "flos": 3.971e+18, "train_loss": 5.3287, "eval_loss": 6.1584, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.074357032775879, "gsm8k": 6.468369223854759, "math_qa": 6.023349126180013 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.017437452615617893, "math_qa": 0.001340033500837521 } }, { "flos": 3.98e+18, "train_loss": 5.3186, "eval_loss": 6.1427, "eval_accuracy": 0.0066, "eval_loss_by_set": { "aqua_rat": 6.059846878051758, "gsm8k": 6.440701571377841, "math_qa": 6.012948354085286 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01819560272934041, "math_qa": 0.001340033500837521 } }, { "flos": 3.988e+18, "train_loss": 5.33, "eval_loss": 6.1564, "eval_accuracy": 0.007, "eval_loss_by_set": { "aqua_rat": 6.073156833648682, "gsm8k": 6.466608220880682, "math_qa": 6.021109263102214 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.019711902956785442, "math_qa": 0.001340033500837521 } }, { "flos": 3.996e+18, "train_loss": 5.3392, "eval_loss": 6.143, "eval_accuracy": 0.0072, "eval_loss_by_set": { "aqua_rat": 6.062018871307373, "gsm8k": 6.439802689985796, "math_qa": 6.013662338256836 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.02047005307050796, "math_qa": 0.001340033500837521 } }, { "flos": 4.005e+18, "train_loss": 5.3386, "eval_loss": 6.1612, "eval_accuracy": 0.005, "eval_loss_by_set": { "aqua_rat": 6.076070308685303, "gsm8k": 6.47564697265625, "math_qa": 6.024112701416016 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01288855193328279, "math_qa": 0.001340033500837521 } }, { "flos": 4.013e+18, "train_loss": 5.3357, "eval_loss": 6.1571, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.073575019836426, "gsm8k": 6.466798955743963, "math_qa": 6.022172927856445 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.01592115238817286, "math_qa": 0.001340033500837521 } }, { "flos": 4.021e+18, "train_loss": 5.3194, "eval_loss": 6.1427, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.0667524337768555, "gsm8k": 6.447789972478693, "math_qa": 6.009263356526692 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.015163002274450341, "math_qa": 0.001340033500837521 } }, { "flos": 4.03e+18, "train_loss": 5.3412, "eval_loss": 6.1524, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.074774742126465, "gsm8k": 6.45660400390625, "math_qa": 6.019491195678711 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.015163002274450341, "math_qa": 0.001340033500837521 } }, { "flos": 4.038e+18, "train_loss": 5.3233, "eval_loss": 6.1391, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.0590643882751465, "gsm8k": 6.4330527565696025, "math_qa": 6.011075337727864 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.017437452615617893, "math_qa": 0.001340033500837521 } }, { "flos": 4.046e+18, "train_loss": 5.3132, "eval_loss": 6.1542, "eval_accuracy": 0.0059, "eval_loss_by_set": { "aqua_rat": 6.072114944458008, "gsm8k": 6.45746473832564, "math_qa": 6.022061030069987 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01592115238817286, "math_qa": 0.001340033500837521 } }, { "flos": 4.055e+18, "train_loss": 5.3171, "eval_loss": 6.1512, "eval_accuracy": 0.0046, "eval_loss_by_set": { "aqua_rat": 6.071040153503418, "gsm8k": 6.463301225142046, "math_qa": 6.014842351277669 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.012130401819560273, "math_qa": 0.001340033500837521 } }, { "flos": 4.063e+18, "train_loss": 5.3335, "eval_loss": 6.1436, "eval_accuracy": 0.0064, "eval_loss_by_set": { "aqua_rat": 6.067935943603516, "gsm8k": 6.451785694469105, "math_qa": 6.0086669921875 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.01819560272934041, "math_qa": 0.001340033500837521 } }, { "flos": 4.072e+18, "train_loss": 5.3462, "eval_loss": 6.151, "eval_accuracy": 0.0064, "eval_loss_by_set": { "aqua_rat": 6.073394775390625, "gsm8k": 6.466874556107954, "math_qa": 6.012641270955403 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.01819560272934041, "math_qa": 0.001340033500837521 } }, { "flos": 4.08e+18, "train_loss": 5.3466, "eval_loss": 6.1526, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.070376873016357, "gsm8k": 6.455516468394887, "math_qa": 6.020620346069336 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 4.088e+18, "train_loss": 5.3583, "eval_loss": 6.1549, "eval_accuracy": 0.0059, "eval_loss_by_set": { "aqua_rat": 6.068315029144287, "gsm8k": 6.457716508345171, "math_qa": 6.023386637369792 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01592115238817286, "math_qa": 0.001340033500837521 } }, { "flos": 4.097e+18, "train_loss": 5.3369, "eval_loss": 6.1585, "eval_accuracy": 0.0059, "eval_loss_by_set": { "aqua_rat": 6.073589324951172, "gsm8k": 6.467647205699574, "math_qa": 6.023853302001953 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01592115238817286, "math_qa": 0.001340033500837521 } }, { "flos": 4.105e+18, "train_loss": 5.3237, "eval_loss": 6.1462, "eval_accuracy": 0.0059, "eval_loss_by_set": { "aqua_rat": 6.071120262145996, "gsm8k": 6.457803899591619, "math_qa": 6.009649276733398 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 4.113e+18, "train_loss": 5.315, "eval_loss": 6.1568, "eval_accuracy": 0.0066, "eval_loss_by_set": { "aqua_rat": 6.075899124145508, "gsm8k": 6.470271023837003, "math_qa": 6.019910176595052 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.018953752843062926, "math_qa": 0.001340033500837521 } }, { "flos": 4.122e+18, "train_loss": 5.341, "eval_loss": 6.1451, "eval_accuracy": 0.0053, "eval_loss_by_set": { "aqua_rat": 6.067100524902344, "gsm8k": 6.453334461558949, "math_qa": 6.010358174641927 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.013646702047005308, "math_qa": 0.001340033500837521 } }, { "flos": 4.13e+18, "train_loss": 5.321, "eval_loss": 6.1562, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.069789886474609, "gsm8k": 6.467416936700994, "math_qa": 6.020707448323567 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.015163002274450341, "math_qa": 0.001340033500837521 } }, { "flos": 4.138e+18, "train_loss": 5.3479, "eval_loss": 6.1479, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.068290710449219, "gsm8k": 6.456085898659446, "math_qa": 6.013245900472005 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01592115238817286, "math_qa": 0.0016750418760469012 } }, { "flos": 4.147e+18, "train_loss": 5.3555, "eval_loss": 6.1496, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.066771030426025, "gsm8k": 6.4593422629616475, "math_qa": 6.01447868347168 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.01592115238817286, "math_qa": 0.001340033500837521 } }, { "flos": 4.155e+18, "train_loss": 5.3468, "eval_loss": 6.1443, "eval_accuracy": 0.0064, "eval_loss_by_set": { "aqua_rat": 6.064062118530273, "gsm8k": 6.444888721812855, "math_qa": 6.013159434000651 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.01819560272934041, "math_qa": 0.001340033500837521 } }, { "flos": 4.163e+18, "train_loss": 5.3224, "eval_loss": 6.1497, "eval_accuracy": 0.0059, "eval_loss_by_set": { "aqua_rat": 6.06428337097168, "gsm8k": 6.447837829589844, "math_qa": 6.020219167073567 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 4.172e+18, "train_loss": 5.3319, "eval_loss": 6.1576, "eval_accuracy": 0.0064, "eval_loss_by_set": { "aqua_rat": 6.072480201721191, "gsm8k": 6.468068903142756, "math_qa": 6.022403717041016 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.017437452615617893, "math_qa": 0.001340033500837521 } }, { "flos": 4.18e+18, "train_loss": 5.3241, "eval_loss": 6.146, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.067570686340332, "gsm8k": 6.453002236106179, "math_qa": 6.011756896972656 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.01592115238817286, "math_qa": 0.001340033500837521 } }, { "flos": 4.188e+18, "train_loss": 5.3266, "eval_loss": 6.1443, "eval_accuracy": 0.0055, "eval_loss_by_set": { "aqua_rat": 6.065454006195068, "gsm8k": 6.439917824485085, "math_qa": 6.015387852986653 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.014404852160727824, "math_qa": 0.001340033500837521 } }, { "flos": 4.197e+18, "train_loss": 5.35, "eval_loss": 6.1548, "eval_accuracy": 0.0053, "eval_loss_by_set": { "aqua_rat": 6.070487976074219, "gsm8k": 6.457004893909801, "math_qa": 6.023267110188802 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.013646702047005308, "math_qa": 0.001340033500837521 } }, { "flos": 4.205e+18, "train_loss": 5.3433, "eval_loss": 6.1569, "eval_accuracy": 0.0066, "eval_loss_by_set": { "aqua_rat": 6.068900108337402, "gsm8k": 6.468143116344105, "math_qa": 6.021570205688477 }, "eval_accuracy_by_set": { "aqua_rat": 0.011811023622047244, "gsm8k": 0.017437452615617893, "math_qa": 0.001340033500837521 } }, { "flos": 4.213e+18, "train_loss": 5.3302, "eval_loss": 6.1507, "eval_accuracy": 0.0055, "eval_loss_by_set": { "aqua_rat": 6.06568717956543, "gsm8k": 6.4546286843039775, "math_qa": 6.018533070882161 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.014404852160727824, "math_qa": 0.001340033500837521 } }, { "flos": 4.222e+18, "train_loss": 5.3248, "eval_loss": 6.1585, "eval_accuracy": 0.0066, "eval_loss_by_set": { "aqua_rat": 6.073417663574219, "gsm8k": 6.468333851207387, "math_qa": 6.023649215698242 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01819560272934041, "math_qa": 0.001340033500837521 } }, { "flos": 4.23e+18, "train_loss": 5.2877, "eval_loss": 6.1452, "eval_accuracy": 0.0066, "eval_loss_by_set": { "aqua_rat": 6.063404083251953, "gsm8k": 6.44799111106179, "math_qa": 6.013225555419922 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01819560272934041, "math_qa": 0.001340033500837521 } }, { "flos": 4.238e+18, "train_loss": 5.3386, "eval_loss": 6.1472, "eval_accuracy": 0.0059, "eval_loss_by_set": { "aqua_rat": 6.0649309158325195, "gsm8k": 6.453213778409091, "math_qa": 6.013805389404297 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01592115238817286, "math_qa": 0.001340033500837521 } }, { "flos": 4.247e+18, "train_loss": 5.34, "eval_loss": 6.1464, "eval_accuracy": 0.0055, "eval_loss_by_set": { "aqua_rat": 6.067928314208984, "gsm8k": 6.447289206764915, "math_qa": 6.014963785807292 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.015163002274450341, "math_qa": 0.001340033500837521 } }, { "flos": 4.255e+18, "train_loss": 5.3403, "eval_loss": 6.1361, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.064609527587891, "gsm8k": 6.442751104181463, "math_qa": 6.001518885294597 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.017437452615617893, "math_qa": 0.001340033500837521 } }, { "flos": 4.263e+18, "train_loss": 5.3381, "eval_loss": 6.1504, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.071317672729492, "gsm8k": 6.462064569646662, "math_qa": 6.014136632283528 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 4.272e+18, "train_loss": 5.3308, "eval_loss": 6.1541, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.070178985595703, "gsm8k": 6.459073153409091, "math_qa": 6.021291097005208 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 4.28e+18, "train_loss": 5.3219, "eval_loss": 6.1471, "eval_accuracy": 0.007, "eval_loss_by_set": { "aqua_rat": 6.062989234924316, "gsm8k": 6.434575167569247, "math_qa": 6.022331237792969 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.019711902956785442, "math_qa": 0.001340033500837521 } }, { "flos": 4.288e+18, "train_loss": 5.3188, "eval_loss": 6.1594, "eval_accuracy": 0.007, "eval_loss_by_set": { "aqua_rat": 6.070740222930908, "gsm8k": 6.468873457475142, "math_qa": 6.025022506713867 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.019711902956785442, "math_qa": 0.001340033500837521 } }, { "flos": 4.297e+18, "train_loss": 5.3514, "eval_loss": 6.1429, "eval_accuracy": 0.007, "eval_loss_by_set": { "aqua_rat": 6.066365718841553, "gsm8k": 6.4380971735174, "math_qa": 6.01402219136556 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.019711902956785442, "math_qa": 0.001340033500837521 } }, { "flos": 4.305e+18, "train_loss": 5.3405, "eval_loss": 6.1372, "eval_accuracy": 0.0064, "eval_loss_by_set": { "aqua_rat": 6.059900760650635, "gsm8k": 6.439348394220525, "math_qa": 6.005178451538086 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.017437452615617893, "math_qa": 0.001340033500837521 } }, { "flos": 4.313e+18, "train_loss": 5.3126, "eval_loss": 6.1547, "eval_accuracy": 0.0064, "eval_loss_by_set": { "aqua_rat": 6.07240629196167, "gsm8k": 6.459937355735085, "math_qa": 6.021605173746745 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.017437452615617893, "math_qa": 0.001340033500837521 } }, { "flos": 4.322e+18, "train_loss": 5.3388, "eval_loss": 6.1509, "eval_accuracy": 0.0064, "eval_loss_by_set": { "aqua_rat": 6.071881294250488, "gsm8k": 6.454218084161932, "math_qa": 6.01841672261556 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.017437452615617893, "math_qa": 0.001340033500837521 } }, { "flos": 4.33e+18, "train_loss": 5.3244, "eval_loss": 6.1459, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.070586204528809, "gsm8k": 6.456777399236506, "math_qa": 6.00967534383138 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 4.338e+18, "train_loss": 5.3498, "eval_loss": 6.1443, "eval_accuracy": 0.0066, "eval_loss_by_set": { "aqua_rat": 6.067965030670166, "gsm8k": 6.451647671786222, "math_qa": 6.009767532348633 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01819560272934041, "math_qa": 0.001340033500837521 } }, { "flos": 4.347e+18, "train_loss": 5.3237, "eval_loss": 6.144, "eval_accuracy": 0.0064, "eval_loss_by_set": { "aqua_rat": 6.06923770904541, "gsm8k": 6.452218489213423, "math_qa": 6.008989334106445 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.017437452615617893, "math_qa": 0.001340033500837521 } }, { "flos": 4.355e+18, "train_loss": 5.3258, "eval_loss": 6.1477, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.071674346923828, "gsm8k": 6.468074451793324, "math_qa": 6.007245381673177 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.015163002274450341, "math_qa": 0.001340033500837521 } }, { "flos": 4.363e+18, "train_loss": 5.3439, "eval_loss": 6.1568, "eval_accuracy": 0.005, "eval_loss_by_set": { "aqua_rat": 6.07080078125, "gsm8k": 6.46276161887429, "math_qa": 6.023722330729167 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01288855193328279, "math_qa": 0.001340033500837521 } }, { "flos": 4.372e+18, "train_loss": 5.322, "eval_loss": 6.151, "eval_accuracy": 0.0064, "eval_loss_by_set": { "aqua_rat": 6.070469856262207, "gsm8k": 6.464114796031605, "math_qa": 6.014258066813151 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.01819560272934041, "math_qa": 0.001340033500837521 } }, { "flos": 4.38e+18, "train_loss": 5.332, "eval_loss": 6.1498, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.066102027893066, "gsm8k": 6.454735495827415, "math_qa": 6.0169728597005205 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.015163002274450341, "math_qa": 0.001340033500837521 } }, { "flos": 4.388e+18, "train_loss": 5.3268, "eval_loss": 6.1473, "eval_accuracy": 0.0064, "eval_loss_by_set": { "aqua_rat": 6.067249298095703, "gsm8k": 6.4492575905539775, "math_qa": 6.015641530354817 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.017437452615617893, "math_qa": 0.001340033500837521 } }, { "flos": 4.397e+18, "train_loss": 5.3262, "eval_loss": 6.1512, "eval_accuracy": 0.0072, "eval_loss_by_set": { "aqua_rat": 6.070882797241211, "gsm8k": 6.458368474786932, "math_qa": 6.017056783040364 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.02047005307050796, "math_qa": 0.001340033500837521 } }, { "flos": 4.405e+18, "train_loss": 5.3437, "eval_loss": 6.1587, "eval_accuracy": 0.0055, "eval_loss_by_set": { "aqua_rat": 6.075079441070557, "gsm8k": 6.4657676003196025, "math_qa": 6.024860382080078 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.014404852160727824, "math_qa": 0.001340033500837521 } }, { "flos": 4.414e+18, "train_loss": 5.3209, "eval_loss": 6.1479, "eval_accuracy": 0.0066, "eval_loss_by_set": { "aqua_rat": 6.069289207458496, "gsm8k": 6.463647322221235, "math_qa": 6.009698867797852 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01819560272934041, "math_qa": 0.001340033500837521 } }, { "flos": 4.422e+18, "train_loss": 5.3366, "eval_loss": 6.1493, "eval_accuracy": 0.0055, "eval_loss_by_set": { "aqua_rat": 6.068902969360352, "gsm8k": 6.459625244140625, "math_qa": 6.01370112101237 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.014404852160727824, "math_qa": 0.001340033500837521 } }, { "flos": 4.43e+18, "train_loss": 5.3371, "eval_loss": 6.1497, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.065614223480225, "gsm8k": 6.457300359552557, "math_qa": 6.0156606038411455 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.015163002274450341, "math_qa": 0.001340033500837521 } }, { "flos": 4.439e+18, "train_loss": 5.336, "eval_loss": 6.1364, "eval_accuracy": 0.0064, "eval_loss_by_set": { "aqua_rat": 6.060659408569336, "gsm8k": 6.435395674272017, "math_qa": 6.005743026733398 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.017437452615617893, "math_qa": 0.001340033500837521 } }, { "flos": 4.447e+18, "train_loss": 5.3051, "eval_loss": 6.1473, "eval_accuracy": 0.007, "eval_loss_by_set": { "aqua_rat": 6.0714945793151855, "gsm8k": 6.457603454589844, "math_qa": 6.011460622151692 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.019711902956785442, "math_qa": 0.001340033500837521 } }, { "flos": 4.455e+18, "train_loss": 5.3273, "eval_loss": 6.152, "eval_accuracy": 0.0068, "eval_loss_by_set": { "aqua_rat": 6.070483684539795, "gsm8k": 6.4648354270241475, "math_qa": 6.015430450439453 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.018953752843062926, "math_qa": 0.001340033500837521 } }, { "flos": 4.464e+18, "train_loss": 5.3245, "eval_loss": 6.1455, "eval_accuracy": 0.0066, "eval_loss_by_set": { "aqua_rat": 6.066381931304932, "gsm8k": 6.4475250244140625, "math_qa": 6.013729731241862 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01819560272934041, "math_qa": 0.001340033500837521 } }, { "flos": 4.472e+18, "train_loss": 5.3305, "eval_loss": 6.1534, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.071381568908691, "gsm8k": 6.452880165793679, "math_qa": 6.023046493530273 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.017437452615617893, "math_qa": 0.001340033500837521 } }, { "flos": 4.48e+18, "train_loss": 5.3314, "eval_loss": 6.1579, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.0745158195495605, "gsm8k": 6.473401156338778, "math_qa": 6.020177841186523 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.01592115238817286, "math_qa": 0.001340033500837521 } }, { "flos": 4.489e+18, "train_loss": 5.3526, "eval_loss": 6.142, "eval_accuracy": 0.0066, "eval_loss_by_set": { "aqua_rat": 6.065897464752197, "gsm8k": 6.447645707563921, "math_qa": 6.008281071980794 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01819560272934041, "math_qa": 0.001340033500837521 } }, { "flos": 4.497e+18, "train_loss": 5.3401, "eval_loss": 6.1413, "eval_accuracy": 0.0072, "eval_loss_by_set": { "aqua_rat": 6.063652038574219, "gsm8k": 6.44666220925071, "math_qa": 6.007864634195964 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.02047005307050796, "math_qa": 0.001340033500837521 } }, { "flos": 4.505e+18, "train_loss": 5.3309, "eval_loss": 6.1469, "eval_accuracy": 0.0064, "eval_loss_by_set": { "aqua_rat": 6.067932605743408, "gsm8k": 6.452002091841265, "math_qa": 6.013695398966472 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.017437452615617893, "math_qa": 0.001340033500837521 } }, { "flos": 4.514e+18, "train_loss": 5.3505, "eval_loss": 6.148, "eval_accuracy": 0.0068, "eval_loss_by_set": { "aqua_rat": 6.068291664123535, "gsm8k": 6.451581087979403, "math_qa": 6.015540440877278 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.018953752843062926, "math_qa": 0.001340033500837521 } }, { "flos": 4.522e+18, "train_loss": 5.3303, "eval_loss": 6.1508, "eval_accuracy": 0.0055, "eval_loss_by_set": { "aqua_rat": 6.070361614227295, "gsm8k": 6.45810283314098, "math_qa": 6.016593297322591 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.014404852160727824, "math_qa": 0.001340033500837521 } }, { "flos": 4.53e+18, "train_loss": 5.3241, "eval_loss": 6.158, "eval_accuracy": 0.0059, "eval_loss_by_set": { "aqua_rat": 6.077075481414795, "gsm8k": 6.469287525523793, "math_qa": 6.0219987233479815 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01592115238817286, "math_qa": 0.001340033500837521 } }, { "flos": 4.539e+18, "train_loss": 5.323, "eval_loss": 6.1489, "eval_accuracy": 0.007, "eval_loss_by_set": { "aqua_rat": 6.067693710327148, "gsm8k": 6.45555947043679, "math_qa": 6.015173594156901 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.019711902956785442, "math_qa": 0.001340033500837521 } }, { "flos": 4.547e+18, "train_loss": 5.3468, "eval_loss": 6.1402, "eval_accuracy": 0.0059, "eval_loss_by_set": { "aqua_rat": 6.064180374145508, "gsm8k": 6.442004117098722, "math_qa": 6.008131663004558 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01592115238817286, "math_qa": 0.001340033500837521 } }, { "flos": 4.555e+18, "train_loss": 5.3255, "eval_loss": 6.1519, "eval_accuracy": 0.0059, "eval_loss_by_set": { "aqua_rat": 6.069766521453857, "gsm8k": 6.463992032137784, "math_qa": 6.0157470703125 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01592115238817286, "math_qa": 0.001340033500837521 } }, { "flos": 4.564e+18, "train_loss": 5.3189, "eval_loss": 6.1444, "eval_accuracy": 0.005, "eval_loss_by_set": { "aqua_rat": 6.069153785705566, "gsm8k": 6.453914989124645, "math_qa": 6.008860905965169 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01288855193328279, "math_qa": 0.001340033500837521 } }, { "flos": 4.572e+18, "train_loss": 5.3564, "eval_loss": 6.1469, "eval_accuracy": 0.007, "eval_loss_by_set": { "aqua_rat": 6.065298080444336, "gsm8k": 6.45263671875, "math_qa": 6.013548533121745 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.019711902956785442, "math_qa": 0.001340033500837521 } }, { "flos": 4.58e+18, "train_loss": 5.3382, "eval_loss": 6.1472, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.071038246154785, "gsm8k": 6.454692493785512, "math_qa": 6.0126698811848955 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.015163002274450341, "math_qa": 0.001340033500837521 } }, { "flos": 4.589e+18, "train_loss": 5.3261, "eval_loss": 6.1436, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.06484317779541, "gsm8k": 6.452393271706321, "math_qa": 6.008598963419597 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.015163002274450341, "math_qa": 0.001340033500837521 } }, { "flos": 4.597e+18, "train_loss": 5.3171, "eval_loss": 6.1452, "eval_accuracy": 0.0055, "eval_loss_by_set": { "aqua_rat": 6.066115379333496, "gsm8k": 6.442638744007457, "math_qa": 6.015492757161458 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.014404852160727824, "math_qa": 0.001340033500837521 } }, { "flos": 4.605e+18, "train_loss": 5.336, "eval_loss": 6.1461, "eval_accuracy": 0.0066, "eval_loss_by_set": { "aqua_rat": 6.068220138549805, "gsm8k": 6.451830777254972, "math_qa": 6.012524922688802 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01819560272934041, "math_qa": 0.001340033500837521 } }, { "flos": 4.614e+18, "train_loss": 5.3234, "eval_loss": 6.1476, "eval_accuracy": 0.0059, "eval_loss_by_set": { "aqua_rat": 6.066596031188965, "gsm8k": 6.45484092018821, "math_qa": 6.013460159301758 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01592115238817286, "math_qa": 0.001340033500837521 } }, { "flos": 4.622e+18, "train_loss": 5.3183, "eval_loss": 6.1437, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.063368797302246, "gsm8k": 6.453034834428267, "math_qa": 6.008555094401042 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 4.63e+18, "train_loss": 5.3273, "eval_loss": 6.1416, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.06684684753418, "gsm8k": 6.447463295676491, "math_qa": 6.007625579833984 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.01592115238817286, "math_qa": 0.001340033500837521 } }, { "flos": 4.639e+18, "train_loss": 5.3285, "eval_loss": 6.151, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.069363594055176, "gsm8k": 6.456407026811079, "math_qa": 6.017855326334636 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.015163002274450341, "math_qa": 0.001340033500837521 } }, { "flos": 4.647e+18, "train_loss": 5.3464, "eval_loss": 6.1494, "eval_accuracy": 0.0048, "eval_loss_by_set": { "aqua_rat": 6.069015979766846, "gsm8k": 6.4593048095703125, "math_qa": 6.014035542805989 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.012130401819560273, "math_qa": 0.001340033500837521 } }, { "flos": 4.655e+18, "train_loss": 5.3183, "eval_loss": 6.1411, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.063562393188477, "gsm8k": 6.43314639004794, "math_qa": 6.013683319091797 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.015163002274450341, "math_qa": 0.001340033500837521 } }, { "flos": 4.664e+18, "train_loss": 5.3289, "eval_loss": 6.146, "eval_accuracy": 0.0053, "eval_loss_by_set": { "aqua_rat": 6.063716888427734, "gsm8k": 6.448358709161932, "math_qa": 6.014296213785808 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.013646702047005308, "math_qa": 0.001340033500837521 } }, { "flos": 4.672e+18, "train_loss": 5.3201, "eval_loss": 6.1443, "eval_accuracy": 0.0055, "eval_loss_by_set": { "aqua_rat": 6.064281463623047, "gsm8k": 6.453822742808949, "math_qa": 6.009103139241536 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.014404852160727824, "math_qa": 0.001340033500837521 } }, { "flos": 4.681e+18, "train_loss": 5.3132, "eval_loss": 6.1511, "eval_accuracy": 0.0059, "eval_loss_by_set": { "aqua_rat": 6.0733795166015625, "gsm8k": 6.463284579190341, "math_qa": 6.014416376749675 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01592115238817286, "math_qa": 0.001340033500837521 } }, { "flos": 4.689e+18, "train_loss": 5.3429, "eval_loss": 6.1443, "eval_accuracy": 0.0059, "eval_loss_by_set": { "aqua_rat": 6.063777923583984, "gsm8k": 6.448414195667613, "math_qa": 6.011661529541016 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01592115238817286, "math_qa": 0.001340033500837521 } }, { "flos": 4.697e+18, "train_loss": 5.3275, "eval_loss": 6.1491, "eval_accuracy": 0.005, "eval_loss_by_set": { "aqua_rat": 6.068020820617676, "gsm8k": 6.459485140713778, "math_qa": 6.013600031534831 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01288855193328279, "math_qa": 0.001340033500837521 } }, { "flos": 4.706e+18, "train_loss": 5.3212, "eval_loss": 6.1483, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.068480491638184, "gsm8k": 6.462818492542613, "math_qa": 6.010791778564453 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.015163002274450341, "math_qa": 0.001340033500837521 } }, { "flos": 4.714e+18, "train_loss": 5.3255, "eval_loss": 6.151, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.071415901184082, "gsm8k": 6.4653778076171875, "math_qa": 6.013569513956706 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 4.722e+18, "train_loss": 5.3293, "eval_loss": 6.144, "eval_accuracy": 0.0064, "eval_loss_by_set": { "aqua_rat": 6.066679000854492, "gsm8k": 6.447726162997159, "math_qa": 6.011192321777344 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.017437452615617893, "math_qa": 0.001340033500837521 } }, { "flos": 4.731e+18, "train_loss": 5.3346, "eval_loss": 6.1449, "eval_accuracy": 0.0064, "eval_loss_by_set": { "aqua_rat": 6.068304538726807, "gsm8k": 6.450887506658381, "math_qa": 6.011047999064128 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.017437452615617893, "math_qa": 0.001340033500837521 } }, { "flos": 4.739e+18, "train_loss": 5.3386, "eval_loss": 6.1437, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.068427562713623, "gsm8k": 6.452542391690341, "math_qa": 6.008434295654297 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.015163002274450341, "math_qa": 0.001340033500837521 } }, { "flos": 4.747e+18, "train_loss": 5.3404, "eval_loss": 6.1406, "eval_accuracy": 0.0066, "eval_loss_by_set": { "aqua_rat": 6.065507888793945, "gsm8k": 6.450829245827415, "math_qa": 6.0047149658203125 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.018953752843062926, "math_qa": 0.001340033500837521 } }, { "flos": 4.756e+18, "train_loss": 5.3409, "eval_loss": 6.1503, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.068762302398682, "gsm8k": 6.457040960138494, "math_qa": 6.016550699869792 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 4.764e+18, "train_loss": 5.3021, "eval_loss": 6.1533, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.070003032684326, "gsm8k": 6.465284867720171, "math_qa": 6.017181396484375 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.017437452615617893, "math_qa": 0.001340033500837521 } }, { "flos": 4.772e+18, "train_loss": 5.334, "eval_loss": 6.1451, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.066530227661133, "gsm8k": 6.460513028231534, "math_qa": 6.00705083211263 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.01592115238817286, "math_qa": 0.001340033500837521 } }, { "flos": 4.781e+18, "train_loss": 5.3163, "eval_loss": 6.1419, "eval_accuracy": 0.0048, "eval_loss_by_set": { "aqua_rat": 6.061250686645508, "gsm8k": 6.445214705033735, "math_qa": 6.00965944925944 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.012130401819560273, "math_qa": 0.001340033500837521 } }, { "flos": 4.789e+18, "train_loss": 5.3394, "eval_loss": 6.1456, "eval_accuracy": 0.0059, "eval_loss_by_set": { "aqua_rat": 6.065016269683838, "gsm8k": 6.461589466441762, "math_qa": 6.0075327555338545 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 4.797e+18, "train_loss": 5.3393, "eval_loss": 6.1441, "eval_accuracy": 0.0066, "eval_loss_by_set": { "aqua_rat": 6.0625762939453125, "gsm8k": 6.453730496493253, "math_qa": 6.009024937947591 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.018953752843062926, "math_qa": 0.001340033500837521 } }, { "flos": 4.806e+18, "train_loss": 5.3255, "eval_loss": 6.1525, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.071036338806152, "gsm8k": 6.4597251198508525, "math_qa": 6.01852289835612 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.017437452615617893, "math_qa": 0.001340033500837521 } }, { "flos": 4.814e+18, "train_loss": 5.331, "eval_loss": 6.1474, "eval_accuracy": 0.0053, "eval_loss_by_set": { "aqua_rat": 6.06730842590332, "gsm8k": 6.460036537863991, "math_qa": 6.010770161946614 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.014404852160727824, "math_qa": 0.001340033500837521 } }, { "flos": 4.822e+18, "train_loss": 5.3282, "eval_loss": 6.1491, "eval_accuracy": 0.0059, "eval_loss_by_set": { "aqua_rat": 6.065456867218018, "gsm8k": 6.455644087357954, "math_qa": 6.015544255574544 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 4.831e+18, "train_loss": 5.3162, "eval_loss": 6.1448, "eval_accuracy": 0.005, "eval_loss_by_set": { "aqua_rat": 6.065251350402832, "gsm8k": 6.450789018110796, "math_qa": 6.011147816975911 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01288855193328279, "math_qa": 0.001340033500837521 } }, { "flos": 4.839e+18, "train_loss": 5.3348, "eval_loss": 6.1399, "eval_accuracy": 0.0048, "eval_loss_by_set": { "aqua_rat": 6.060246467590332, "gsm8k": 6.440245194868608, "math_qa": 6.008827845255534 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.012130401819560273, "math_qa": 0.001340033500837521 } }, { "flos": 4.847e+18, "train_loss": 5.3449, "eval_loss": 6.1477, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.0689616203308105, "gsm8k": 6.453051480379972, "math_qa": 6.014271418253581 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 4.856e+18, "train_loss": 5.3508, "eval_loss": 6.1409, "eval_accuracy": 0.0066, "eval_loss_by_set": { "aqua_rat": 6.065110206604004, "gsm8k": 6.449953252618963, "math_qa": 6.005558013916016 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01819560272934041, "math_qa": 0.001340033500837521 } }, { "flos": 4.864e+18, "train_loss": 5.3196, "eval_loss": 6.1411, "eval_accuracy": 0.0068, "eval_loss_by_set": { "aqua_rat": 6.062549591064453, "gsm8k": 6.443659695712003, "math_qa": 6.00900395711263 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.018953752843062926, "math_qa": 0.001340033500837521 } }, { "flos": 4.872e+18, "train_loss": 5.3454, "eval_loss": 6.1475, "eval_accuracy": 0.005, "eval_loss_by_set": { "aqua_rat": 6.0678534507751465, "gsm8k": 6.452435580166903, "math_qa": 6.014360427856445 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01288855193328279, "math_qa": 0.001340033500837521 } }, { "flos": 4.881e+18, "train_loss": 5.3028, "eval_loss": 6.1501, "eval_accuracy": 0.0055, "eval_loss_by_set": { "aqua_rat": 6.070362567901611, "gsm8k": 6.458643132990057, "math_qa": 6.0153350830078125 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.014404852160727824, "math_qa": 0.001340033500837521 } }, { "flos": 4.889e+18, "train_loss": 5.3275, "eval_loss": 6.1481, "eval_accuracy": 0.0053, "eval_loss_by_set": { "aqua_rat": 6.065053939819336, "gsm8k": 6.457638133655895, "math_qa": 6.013202667236328 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.013646702047005308, "math_qa": 0.001340033500837521 } }, { "flos": 4.897e+18, "train_loss": 5.3288, "eval_loss": 6.1443, "eval_accuracy": 0.0059, "eval_loss_by_set": { "aqua_rat": 6.06313419342041, "gsm8k": 6.448665272105824, "math_qa": 6.0115915934244795 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01592115238817286, "math_qa": 0.001340033500837521 } }, { "flos": 4.906e+18, "train_loss": 5.3296, "eval_loss": 6.1428, "eval_accuracy": 0.0059, "eval_loss_by_set": { "aqua_rat": 6.063846588134766, "gsm8k": 6.446129538796165, "math_qa": 6.010368982950847 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01592115238817286, "math_qa": 0.001340033500837521 } }, { "flos": 4.914e+18, "train_loss": 5.3414, "eval_loss": 6.1384, "eval_accuracy": 0.0053, "eval_loss_by_set": { "aqua_rat": 6.060239791870117, "gsm8k": 6.434694463556463, "math_qa": 6.009092330932617 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.013646702047005308, "math_qa": 0.001340033500837521 } }, { "flos": 4.922e+18, "train_loss": 5.3348, "eval_loss": 6.1507, "eval_accuracy": 0.005, "eval_loss_by_set": { "aqua_rat": 6.068966865539551, "gsm8k": 6.457291342995384, "math_qa": 6.017051696777344 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.013646702047005308, "math_qa": 0.001340033500837521 } }, { "flos": 4.931e+18, "train_loss": 5.3436, "eval_loss": 6.1437, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.064688682556152, "gsm8k": 6.448355241255327, "math_qa": 6.0106557210286455 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 4.939e+18, "train_loss": 5.3423, "eval_loss": 6.151, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.071009635925293, "gsm8k": 6.45482704856179, "math_qa": 6.018470764160156 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.015163002274450341, "math_qa": 0.001340033500837521 } }, { "flos": 4.948e+18, "train_loss": 5.315, "eval_loss": 6.1443, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.064350128173828, "gsm8k": 6.448805375532671, "math_qa": 6.011360168457031 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 4.956e+18, "train_loss": 5.3201, "eval_loss": 6.1455, "eval_accuracy": 0.0055, "eval_loss_by_set": { "aqua_rat": 6.066158771514893, "gsm8k": 6.445526816628196, "math_qa": 6.014588673909505 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.015163002274450341, "math_qa": 0.001340033500837521 } }, { "flos": 4.964e+18, "train_loss": 5.3058, "eval_loss": 6.1478, "eval_accuracy": 0.0059, "eval_loss_by_set": { "aqua_rat": 6.069091320037842, "gsm8k": 6.453641024502841, "math_qa": 6.014198939005534 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01592115238817286, "math_qa": 0.001340033500837521 } }, { "flos": 4.973e+18, "train_loss": 5.3413, "eval_loss": 6.1491, "eval_accuracy": 0.0072, "eval_loss_by_set": { "aqua_rat": 6.066067695617676, "gsm8k": 6.454202825372869, "math_qa": 6.016237894694011 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.02122820318423048, "math_qa": 0.001340033500837521 } }, { "flos": 4.981e+18, "train_loss": 5.3372, "eval_loss": 6.1507, "eval_accuracy": 0.0055, "eval_loss_by_set": { "aqua_rat": 6.068736553192139, "gsm8k": 6.453081304376775, "math_qa": 6.018929799397786 }, "eval_accuracy_by_set": { "aqua_rat": 0.003937007874015748, "gsm8k": 0.015163002274450341, "math_qa": 0.001340033500837521 } }, { "flos": 4.989e+18, "train_loss": 5.3251, "eval_loss": 6.148, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.067342758178711, "gsm8k": 6.4574737548828125, "math_qa": 6.012809117635091 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 4.998e+18, "train_loss": 5.345, "eval_loss": 6.1452, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.062881946563721, "gsm8k": 6.450354836203835, "math_qa": 6.012251536051433 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.015163002274450341, "math_qa": 0.001340033500837521 } }, { "flos": 5.006e+18, "train_loss": 5.3281, "eval_loss": 6.1501, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.063932418823242, "gsm8k": 6.45440673828125, "math_qa": 6.017773946126302 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 5.014e+18, "train_loss": 5.3274, "eval_loss": 6.1513, "eval_accuracy": 0.0059, "eval_loss_by_set": { "aqua_rat": 6.070356369018555, "gsm8k": 6.466581864790483, "math_qa": 6.013617197672526 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01592115238817286, "math_qa": 0.001340033500837521 } }, { "flos": 5.023e+18, "train_loss": 5.3272, "eval_loss": 6.1449, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.066842555999756, "gsm8k": 6.45415635542436, "math_qa": 6.009637832641602 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 5.031e+18, "train_loss": 5.3334, "eval_loss": 6.1436, "eval_accuracy": 0.0053, "eval_loss_by_set": { "aqua_rat": 6.062616348266602, "gsm8k": 6.455543518066406, "math_qa": 6.007439931233724 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.013646702047005308, "math_qa": 0.001340033500837521 } }, { "flos": 5.039e+18, "train_loss": 5.3271, "eval_loss": 6.1471, "eval_accuracy": 0.0064, "eval_loss_by_set": { "aqua_rat": 6.067492485046387, "gsm8k": 6.450435291637074, "math_qa": 6.014736811319987 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.017437452615617893, "math_qa": 0.001340033500837521 } }, { "flos": 5.048e+18, "train_loss": 5.3154, "eval_loss": 6.1471, "eval_accuracy": 0.0055, "eval_loss_by_set": { "aqua_rat": 6.063624382019043, "gsm8k": 6.453409368341619, "math_qa": 6.0136152903238935 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.014404852160727824, "math_qa": 0.001340033500837521 } }, { "flos": 5.056e+18, "train_loss": 5.3219, "eval_loss": 6.1509, "eval_accuracy": 0.0055, "eval_loss_by_set": { "aqua_rat": 6.071991920471191, "gsm8k": 6.466189297762784, "math_qa": 6.012964248657227 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.014404852160727824, "math_qa": 0.001340033500837521 } }, { "flos": 5.064e+18, "train_loss": 5.3237, "eval_loss": 6.1457, "eval_accuracy": 0.0059, "eval_loss_by_set": { "aqua_rat": 6.063508987426758, "gsm8k": 6.44502050226385, "math_qa": 6.015380223592122 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01592115238817286, "math_qa": 0.001340033500837521 } }, { "flos": 5.073e+18, "train_loss": 5.3334, "eval_loss": 6.146, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.0657854080200195, "gsm8k": 6.448748501864347, "math_qa": 6.013993581136067 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 5.081e+18, "train_loss": 5.345, "eval_loss": 6.1507, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.06894063949585, "gsm8k": 6.460309115323153, "math_qa": 6.015685399373372 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.015163002274450341, "math_qa": 0.001340033500837521 } }, { "flos": 5.089e+18, "train_loss": 5.3181, "eval_loss": 6.1508, "eval_accuracy": 0.0059, "eval_loss_by_set": { "aqua_rat": 6.067317962646484, "gsm8k": 6.455514387650923, "math_qa": 6.018022537231445 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01592115238817286, "math_qa": 0.001340033500837521 } }, { "flos": 5.098e+18, "train_loss": 5.3096, "eval_loss": 6.1513, "eval_accuracy": 0.0064, "eval_loss_by_set": { "aqua_rat": 6.068422794342041, "gsm8k": 6.460486672141335, "math_qa": 6.016466776529948 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.017437452615617893, "math_qa": 0.001340033500837521 } }, { "flos": 5.106e+18, "train_loss": 5.3483, "eval_loss": 6.1477, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.064969062805176, "gsm8k": 6.4471352317116475, "math_qa": 6.0173695882161455 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 5.114e+18, "train_loss": 5.3543, "eval_loss": 6.1443, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.063138961791992, "gsm8k": 6.450646140358665, "math_qa": 6.010592778523763 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 5.123e+18, "train_loss": 5.3279, "eval_loss": 6.1464, "eval_accuracy": 0.0066, "eval_loss_by_set": { "aqua_rat": 6.064918041229248, "gsm8k": 6.455519242720171, "math_qa": 6.011454264322917 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01819560272934041, "math_qa": 0.001340033500837521 } }, { "flos": 5.131e+18, "train_loss": 5.3262, "eval_loss": 6.1462, "eval_accuracy": 0.0066, "eval_loss_by_set": { "aqua_rat": 6.067980766296387, "gsm8k": 6.457224759188565, "math_qa": 6.010098139444987 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01819560272934041, "math_qa": 0.001340033500837521 } }, { "flos": 5.139e+18, "train_loss": 5.3227, "eval_loss": 6.1487, "eval_accuracy": 0.0066, "eval_loss_by_set": { "aqua_rat": 6.071608543395996, "gsm8k": 6.455530340021307, "math_qa": 6.014553705851237 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01819560272934041, "math_qa": 0.001340033500837521 } }, { "flos": 5.148e+18, "train_loss": 5.3307, "eval_loss": 6.1462, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.066352844238281, "gsm8k": 6.447880831631747, "math_qa": 6.0145219167073565 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.015163002274450341, "math_qa": 0.001340033500837521 } }, { "flos": 5.156e+18, "train_loss": 5.3165, "eval_loss": 6.1441, "eval_accuracy": 0.0064, "eval_loss_by_set": { "aqua_rat": 6.062046527862549, "gsm8k": 6.44628212668679, "math_qa": 6.01243273417155 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.017437452615617893, "math_qa": 0.001340033500837521 } }, { "flos": 5.164e+18, "train_loss": 5.3383, "eval_loss": 6.1477, "eval_accuracy": 0.0059, "eval_loss_by_set": { "aqua_rat": 6.067670822143555, "gsm8k": 6.454532276500355, "math_qa": 6.013699849446614 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01592115238817286, "math_qa": 0.001340033500837521 } }, { "flos": 5.173e+18, "train_loss": 5.3328, "eval_loss": 6.149, "eval_accuracy": 0.0059, "eval_loss_by_set": { "aqua_rat": 6.066588878631592, "gsm8k": 6.458005731756037, "math_qa": 6.014265060424805 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01592115238817286, "math_qa": 0.001340033500837521 } }, { "flos": 5.181e+18, "train_loss": 5.3231, "eval_loss": 6.1486, "eval_accuracy": 0.0072, "eval_loss_by_set": { "aqua_rat": 6.069684982299805, "gsm8k": 6.455305619673296, "math_qa": 6.014551162719727 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.02047005307050796, "math_qa": 0.001340033500837521 } }, { "flos": 5.189e+18, "train_loss": 5.3244, "eval_loss": 6.1489, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.067392349243164, "gsm8k": 6.458783236416903, "math_qa": 6.01365343729655 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 5.198e+18, "train_loss": 5.3109, "eval_loss": 6.1506, "eval_accuracy": 0.0064, "eval_loss_by_set": { "aqua_rat": 6.068216800689697, "gsm8k": 6.45345028963956, "math_qa": 6.01858647664388 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.017437452615617893, "math_qa": 0.001340033500837521 } }, { "flos": 5.206e+18, "train_loss": 5.3151, "eval_loss": 6.1533, "eval_accuracy": 0.0066, "eval_loss_by_set": { "aqua_rat": 6.070041656494141, "gsm8k": 6.454880454323509, "math_qa": 6.0219682057698565 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01819560272934041, "math_qa": 0.001340033500837521 } }, { "flos": 5.215e+18, "train_loss": 5.35, "eval_loss": 6.1446, "eval_accuracy": 0.0055, "eval_loss_by_set": { "aqua_rat": 6.063610553741455, "gsm8k": 6.45185643976385, "math_qa": 6.010541280110677 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.014404852160727824, "math_qa": 0.001340033500837521 } }, { "flos": 5.223e+18, "train_loss": 5.3244, "eval_loss": 6.1438, "eval_accuracy": 0.0068, "eval_loss_by_set": { "aqua_rat": 6.060816764831543, "gsm8k": 6.445996371182528, "math_qa": 6.012157440185547 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.018953752843062926, "math_qa": 0.001340033500837521 } }, { "flos": 5.231e+18, "train_loss": 5.351, "eval_loss": 6.1464, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.063226699829102, "gsm8k": 6.452368302778765, "math_qa": 6.013146082560222 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.015163002274450341, "math_qa": 0.001340033500837521 } }, { "flos": 5.24e+18, "train_loss": 5.3212, "eval_loss": 6.1543, "eval_accuracy": 0.0066, "eval_loss_by_set": { "aqua_rat": 6.068268299102783, "gsm8k": 6.464062777432528, "math_qa": 6.019459406534831 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01819560272934041, "math_qa": 0.001340033500837521 } }, { "flos": 5.248e+18, "train_loss": 5.3401, "eval_loss": 6.1528, "eval_accuracy": 0.0059, "eval_loss_by_set": { "aqua_rat": 6.070108413696289, "gsm8k": 6.460705150257457, "math_qa": 6.018615086873372 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01592115238817286, "math_qa": 0.001340033500837521 } }, { "flos": 5.256e+18, "train_loss": 5.3038, "eval_loss": 6.1451, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.063937187194824, "gsm8k": 6.454980330033735, "math_qa": 6.009845733642578 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 5.265e+18, "train_loss": 5.3339, "eval_loss": 6.1423, "eval_accuracy": 0.0055, "eval_loss_by_set": { "aqua_rat": 6.062196731567383, "gsm8k": 6.446054632013494, "math_qa": 6.009738922119141 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.014404852160727824, "math_qa": 0.001340033500837521 } }, { "flos": 5.273e+18, "train_loss": 5.334, "eval_loss": 6.1448, "eval_accuracy": 0.0059, "eval_loss_by_set": { "aqua_rat": 6.0664238929748535, "gsm8k": 6.4540627219460225, "math_qa": 6.009525299072266 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01592115238817286, "math_qa": 0.001340033500837521 } }, { "flos": 5.281e+18, "train_loss": 5.3347, "eval_loss": 6.1449, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.0628132820129395, "gsm8k": 6.452417547052557, "math_qa": 6.010870615641276 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 5.29e+18, "train_loss": 5.3225, "eval_loss": 6.1507, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.067213535308838, "gsm8k": 6.458946228027344, "math_qa": 6.016315460205078 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 5.298e+18, "train_loss": 5.3166, "eval_loss": 6.1466, "eval_accuracy": 0.0064, "eval_loss_by_set": { "aqua_rat": 6.068186283111572, "gsm8k": 6.459505254572088, "math_qa": 6.009787877400716 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.017437452615617893, "math_qa": 0.001340033500837521 } }, { "flos": 5.306e+18, "train_loss": 5.3284, "eval_loss": 6.1442, "eval_accuracy": 0.0068, "eval_loss_by_set": { "aqua_rat": 6.062498092651367, "gsm8k": 6.452151211825284, "math_qa": 6.009808858235677 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.018953752843062926, "math_qa": 0.001340033500837521 } }, { "flos": 5.315e+18, "train_loss": 5.3388, "eval_loss": 6.1431, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.062628746032715, "gsm8k": 6.446257851340554, "math_qa": 6.010822931925456 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 5.323e+18, "train_loss": 5.3373, "eval_loss": 6.1461, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.067298889160156, "gsm8k": 6.451141357421875, "math_qa": 6.0128428141276045 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.015163002274450341, "math_qa": 0.001340033500837521 } }, { "flos": 5.331e+18, "train_loss": 5.3279, "eval_loss": 6.1452, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.063243389129639, "gsm8k": 6.449949091131037, "math_qa": 6.012371063232422 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.015163002274450341, "math_qa": 0.001340033500837521 } }, { "flos": 5.34e+18, "train_loss": 5.3277, "eval_loss": 6.1497, "eval_accuracy": 0.0059, "eval_loss_by_set": { "aqua_rat": 6.069476127624512, "gsm8k": 6.462889237837358, "math_qa": 6.01284917195638 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01592115238817286, "math_qa": 0.001340033500837521 } }, { "flos": 5.348e+18, "train_loss": 5.3155, "eval_loss": 6.1495, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.070512771606445, "gsm8k": 6.461973710493608, "math_qa": 6.012889862060547 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 5.356e+18, "train_loss": 5.3427, "eval_loss": 6.1487, "eval_accuracy": 0.0055, "eval_loss_by_set": { "aqua_rat": 6.065755367279053, "gsm8k": 6.4600677490234375, "math_qa": 6.01291020711263 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.014404852160727824, "math_qa": 0.001340033500837521 } }, { "flos": 5.365e+18, "train_loss": 5.3425, "eval_loss": 6.1437, "eval_accuracy": 0.0064, "eval_loss_by_set": { "aqua_rat": 6.063138961791992, "gsm8k": 6.450336803089488, "math_qa": 6.009817123413086 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.017437452615617893, "math_qa": 0.001340033500837521 } }, { "flos": 5.373e+18, "train_loss": 5.3302, "eval_loss": 6.1499, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.06795597076416, "gsm8k": 6.463048761541193, "math_qa": 6.013219833374023 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.015163002274450341, "math_qa": 0.001340033500837521 } }, { "flos": 5.381e+18, "train_loss": 5.3391, "eval_loss": 6.1477, "eval_accuracy": 0.0055, "eval_loss_by_set": { "aqua_rat": 6.067109107971191, "gsm8k": 6.456577647816051, "math_qa": 6.012850443522136 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.014404852160727824, "math_qa": 0.001340033500837521 } }, { "flos": 5.39e+18, "train_loss": 5.3286, "eval_loss": 6.1457, "eval_accuracy": 0.0059, "eval_loss_by_set": { "aqua_rat": 6.067263603210449, "gsm8k": 6.456873807040128, "math_qa": 6.0096588134765625 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01592115238817286, "math_qa": 0.001340033500837521 } }, { "flos": 5.398e+18, "train_loss": 5.3381, "eval_loss": 6.144, "eval_accuracy": 0.0068, "eval_loss_by_set": { "aqua_rat": 6.065362930297852, "gsm8k": 6.452823985706676, "math_qa": 6.00905164082845 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.018953752843062926, "math_qa": 0.001340033500837521 } }, { "flos": 5.406e+18, "train_loss": 5.3268, "eval_loss": 6.1477, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.067514419555664, "gsm8k": 6.453187422318892, "math_qa": 6.014336903889974 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.015163002274450341, "math_qa": 0.001340033500837521 } }, { "flos": 5.415e+18, "train_loss": 5.3219, "eval_loss": 6.1492, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.068843364715576, "gsm8k": 6.45731631192294, "math_qa": 6.014659245808919 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 5.423e+18, "train_loss": 5.3205, "eval_loss": 6.1455, "eval_accuracy": 0.0068, "eval_loss_by_set": { "aqua_rat": 6.068620204925537, "gsm8k": 6.461221868341619, "math_qa": 6.00717290242513 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.018953752843062926, "math_qa": 0.001340033500837521 } }, { "flos": 5.431e+18, "train_loss": 5.3217, "eval_loss": 6.1474, "eval_accuracy": 0.0055, "eval_loss_by_set": { "aqua_rat": 6.068742275238037, "gsm8k": 6.455683621493253, "math_qa": 6.0126902262369795 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.014404852160727824, "math_qa": 0.001340033500837521 } }, { "flos": 5.44e+18, "train_loss": 5.3387, "eval_loss": 6.1468, "eval_accuracy": 0.0064, "eval_loss_by_set": { "aqua_rat": 6.067287921905518, "gsm8k": 6.456014459783381, "math_qa": 6.011691411336263 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.017437452615617893, "math_qa": 0.001340033500837521 } }, { "flos": 5.448e+18, "train_loss": 5.3244, "eval_loss": 6.1467, "eval_accuracy": 0.0066, "eval_loss_by_set": { "aqua_rat": 6.0670366287231445, "gsm8k": 6.458470431241122, "math_qa": 6.010514577229817 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01819560272934041, "math_qa": 0.001340033500837521 } }, { "flos": 5.456e+18, "train_loss": 5.321, "eval_loss": 6.1431, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.067193508148193, "gsm8k": 6.452287153764204, "math_qa": 6.0076548258463545 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.015163002274450341, "math_qa": 0.001340033500837521 } }, { "flos": 5.465e+18, "train_loss": 5.3224, "eval_loss": 6.1445, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.067204475402832, "gsm8k": 6.454614119096235, "math_qa": 6.008823394775391 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 5.473e+18, "train_loss": 5.3317, "eval_loss": 6.1456, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.070583343505859, "gsm8k": 6.456602616743608, "math_qa": 6.009317398071289 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.015163002274450341, "math_qa": 0.001340033500837521 } }, { "flos": 5.481e+18, "train_loss": 5.3273, "eval_loss": 6.1445, "eval_accuracy": 0.007, "eval_loss_by_set": { "aqua_rat": 6.0679216384887695, "gsm8k": 6.451647671786222, "math_qa": 6.010155995686849 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.019711902956785442, "math_qa": 0.001340033500837521 } }, { "flos": 5.49e+18, "train_loss": 5.3274, "eval_loss": 6.1437, "eval_accuracy": 0.0059, "eval_loss_by_set": { "aqua_rat": 6.0652265548706055, "gsm8k": 6.447025645862926, "math_qa": 6.01123046875 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01592115238817286, "math_qa": 0.001340033500837521 } }, { "flos": 5.498e+18, "train_loss": 5.3356, "eval_loss": 6.1432, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.064269542694092, "gsm8k": 6.451340415261009, "math_qa": 6.008609135945638 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.015163002274450341, "math_qa": 0.001340033500837521 } }, { "flos": 5.506e+18, "train_loss": 5.3148, "eval_loss": 6.143, "eval_accuracy": 0.0066, "eval_loss_by_set": { "aqua_rat": 6.067128658294678, "gsm8k": 6.451953541148793, "math_qa": 6.007680257161458 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01819560272934041, "math_qa": 0.001340033500837521 } }, { "flos": 5.515e+18, "train_loss": 5.3309, "eval_loss": 6.1508, "eval_accuracy": 0.0059, "eval_loss_by_set": { "aqua_rat": 6.070311069488525, "gsm8k": 6.462235190651634, "math_qa": 6.014767964680989 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01592115238817286, "math_qa": 0.001340033500837521 } }, { "flos": 5.523e+18, "train_loss": 5.3179, "eval_loss": 6.1461, "eval_accuracy": 0.0053, "eval_loss_by_set": { "aqua_rat": 6.067505836486816, "gsm8k": 6.45452187278054, "math_qa": 6.0112654368082685 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.013646702047005308, "math_qa": 0.001340033500837521 } }, { "flos": 5.532e+18, "train_loss": 5.3181, "eval_loss": 6.1455, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.069428443908691, "gsm8k": 6.4553985595703125, "math_qa": 6.009774525960286 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 5.54e+18, "train_loss": 5.3332, "eval_loss": 6.1452, "eval_accuracy": 0.0064, "eval_loss_by_set": { "aqua_rat": 6.065830230712891, "gsm8k": 6.453527277166193, "math_qa": 6.010549545288086 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.017437452615617893, "math_qa": 0.001340033500837521 } }, { "flos": 5.548e+18, "train_loss": 5.336, "eval_loss": 6.1481, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.069329738616943, "gsm8k": 6.456470836292613, "math_qa": 6.0133717854817705 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 5.557e+18, "train_loss": 5.346, "eval_loss": 6.144, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.0667195320129395, "gsm8k": 6.454508001154119, "math_qa": 6.008177439371745 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 5.565e+18, "train_loss": 5.312, "eval_loss": 6.1447, "eval_accuracy": 0.0064, "eval_loss_by_set": { "aqua_rat": 6.066997528076172, "gsm8k": 6.455519936301491, "math_qa": 6.008787790934245 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.017437452615617893, "math_qa": 0.001340033500837521 } }, { "flos": 5.573e+18, "train_loss": 5.3533, "eval_loss": 6.144, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.066286087036133, "gsm8k": 6.447267705743963, "math_qa": 6.011539459228516 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 5.582e+18, "train_loss": 5.3217, "eval_loss": 6.1456, "eval_accuracy": 0.0064, "eval_loss_by_set": { "aqua_rat": 6.065615177154541, "gsm8k": 6.456240567294034, "math_qa": 6.00993537902832 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.017437452615617893, "math_qa": 0.001340033500837521 } }, { "flos": 5.59e+18, "train_loss": 5.3204, "eval_loss": 6.1449, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.064128875732422, "gsm8k": 6.449560685591265, "math_qa": 6.01200803120931 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.015163002274450341, "math_qa": 0.001340033500837521 } }, { "flos": 5.598e+18, "train_loss": 5.321, "eval_loss": 6.146, "eval_accuracy": 0.005, "eval_loss_by_set": { "aqua_rat": 6.0664143562316895, "gsm8k": 6.451803034002131, "math_qa": 6.012449264526367 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01288855193328279, "math_qa": 0.001340033500837521 } }, { "flos": 5.607e+18, "train_loss": 5.3418, "eval_loss": 6.1444, "eval_accuracy": 0.0055, "eval_loss_by_set": { "aqua_rat": 6.0655317306518555, "gsm8k": 6.45237246426669, "math_qa": 6.0098876953125 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.014404852160727824, "math_qa": 0.001340033500837521 } }, { "flos": 5.615e+18, "train_loss": 5.3211, "eval_loss": 6.1455, "eval_accuracy": 0.0064, "eval_loss_by_set": { "aqua_rat": 6.064358711242676, "gsm8k": 6.455326427112926, "math_qa": 6.010189692179362 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.017437452615617893, "math_qa": 0.001340033500837521 } }, { "flos": 5.623e+18, "train_loss": 5.3247, "eval_loss": 6.1454, "eval_accuracy": 0.0059, "eval_loss_by_set": { "aqua_rat": 6.065371990203857, "gsm8k": 6.449981689453125, "math_qa": 6.012458801269531 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01592115238817286, "math_qa": 0.001340033500837521 } }, { "flos": 5.632e+18, "train_loss": 5.3344, "eval_loss": 6.1462, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.064958572387695, "gsm8k": 6.454723704944957, "math_qa": 6.011486689249675 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 5.64e+18, "train_loss": 5.3195, "eval_loss": 6.1459, "eval_accuracy": 0.0066, "eval_loss_by_set": { "aqua_rat": 6.0658769607543945, "gsm8k": 6.454029430042613, "math_qa": 6.011351267496745 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01819560272934041, "math_qa": 0.001340033500837521 } }, { "flos": 5.648e+18, "train_loss": 5.3331, "eval_loss": 6.146, "eval_accuracy": 0.0055, "eval_loss_by_set": { "aqua_rat": 6.065297603607178, "gsm8k": 6.456554066051137, "math_qa": 6.010358174641927 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.014404852160727824, "math_qa": 0.001340033500837521 } }, { "flos": 5.657e+18, "train_loss": 5.328, "eval_loss": 6.1467, "eval_accuracy": 0.007, "eval_loss_by_set": { "aqua_rat": 6.067323684692383, "gsm8k": 6.455652410333807, "math_qa": 6.011707305908203 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.019711902956785442, "math_qa": 0.001340033500837521 } }, { "flos": 5.665e+18, "train_loss": 5.337, "eval_loss": 6.1458, "eval_accuracy": 0.0057, "eval_loss_by_set": { "aqua_rat": 6.065846920013428, "gsm8k": 6.454544760964134, "math_qa": 6.011022567749023 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.015163002274450341, "math_qa": 0.001340033500837521 } }, { "flos": 5.673e+18, "train_loss": 5.331, "eval_loss": 6.1448, "eval_accuracy": 0.0059, "eval_loss_by_set": { "aqua_rat": 6.0660247802734375, "gsm8k": 6.454866582697088, "math_qa": 6.009265263875325 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01592115238817286, "math_qa": 0.001340033500837521 } }, { "flos": 5.682e+18, "train_loss": 5.3175, "eval_loss": 6.1471, "eval_accuracy": 0.0064, "eval_loss_by_set": { "aqua_rat": 6.066063404083252, "gsm8k": 6.455804998224432, "math_qa": 6.0123647054036455 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.017437452615617893, "math_qa": 0.001340033500837521 } }, { "flos": 5.69e+18, "train_loss": 5.324, "eval_loss": 6.1458, "eval_accuracy": 0.0053, "eval_loss_by_set": { "aqua_rat": 6.066056728363037, "gsm8k": 6.4546661376953125, "math_qa": 6.010883331298828 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.013646702047005308, "math_qa": 0.001340033500837521 } }, { "flos": 5.698e+18, "train_loss": 5.3271, "eval_loss": 6.1451, "eval_accuracy": 0.0061, "eval_loss_by_set": { "aqua_rat": 6.065712928771973, "gsm8k": 6.4530251242897725, "math_qa": 6.010557810465495 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.016679302501895376, "math_qa": 0.001340033500837521 } }, { "flos": 5.707e+18, "train_loss": 5.3314, "eval_loss": 6.1469, "eval_accuracy": 0.0053, "eval_loss_by_set": { "aqua_rat": 6.068132400512695, "gsm8k": 6.453596635298296, "math_qa": 6.012851079305013 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.013646702047005308, "math_qa": 0.001340033500837521 } }, { "flos": 5.709e+18, "train_loss": 5.3314, "eval_loss": 6.1467, "eval_accuracy": 0.005, "eval_loss_by_set": { "aqua_rat": 6.066442012786865, "gsm8k": 6.452135953036222, "math_qa": 6.01335080464681 }, "eval_accuracy_by_set": { "aqua_rat": 0.007874015748031496, "gsm8k": 0.01288855193328279, "math_qa": 0.001340033500837521 } } ]