Step 1 | loss:0.043674495071172714 lr:4.000000000000001e-06 tokens_per_second_per_gpu:4419.359793465856 Step 2 | loss:0.07647235691547394 lr:8.000000000000001e-06 tokens_per_second_per_gpu:2724.2461849571273 Step 3 | loss:0.07056241482496262 lr:1.2e-05 tokens_per_second_per_gpu:6960.814822465255 Step 4 | loss:0.04830174520611763 lr:1.6000000000000003e-05 tokens_per_second_per_gpu:4106.5421600143145 Step 5 | loss:0.10787405073642731 lr:2e-05 tokens_per_second_per_gpu:3393.1521441350837 Step 6 | loss:0.045880936086177826 lr:2.4e-05 tokens_per_second_per_gpu:4506.259376324593 Step 7 | loss:0.11328550428152084 lr:2.8000000000000003e-05 tokens_per_second_per_gpu:6962.979305345885 Step 8 | loss:0.04459526389837265 lr:3.2000000000000005e-05 tokens_per_second_per_gpu:7055.311081238262 Step 9 | loss:0.05426022782921791 lr:3.6e-05 tokens_per_second_per_gpu:7028.283734592704 Step 10 | loss:0.04848957434296608 lr:4e-05 tokens_per_second_per_gpu:7017.3539801029965 Step 11 | loss:0.0881425216794014 lr:4.4000000000000006e-05 tokens_per_second_per_gpu:1943.8477348992296 Step 12 | loss:0.0685952752828598 lr:4.8e-05 tokens_per_second_per_gpu:6952.732802620781 Step 13 | loss:0.049236081540584564 lr:5.2000000000000004e-05 tokens_per_second_per_gpu:7082.1390664539385 Step 14 | loss:0.020731262862682343 lr:5.6000000000000006e-05 tokens_per_second_per_gpu:7056.273474830204 Step 15 | loss:0.04161064699292183 lr:6e-05 tokens_per_second_per_gpu:3112.918555044047 Step 16 | loss:0.02741307206451893 lr:6.400000000000001e-05 tokens_per_second_per_gpu:6983.52845216913 Step 17 | loss:0.03214961662888527 lr:6.800000000000001e-05 tokens_per_second_per_gpu:3154.4844167130377 Step 18 | loss:0.02267203852534294 lr:7.2e-05 tokens_per_second_per_gpu:7054.444364634089 Step 19 | loss:0.07679328322410583 lr:7.6e-05 tokens_per_second_per_gpu:2743.9195229188676 Step 20 | loss:0.04312453791499138 lr:8e-05 tokens_per_second_per_gpu:2174.246562584131 Step 21 | loss:0.1131562814116478 lr:8.4e-05 tokens_per_second_per_gpu:2161.2844179030008 Step 22 | loss:0.009116842411458492 lr:8.800000000000001e-05 tokens_per_second_per_gpu:7113.803469020326 Step 23 | loss:0.026383861899375916 lr:9.200000000000001e-05 tokens_per_second_per_gpu:7077.9805635971015 Step 24 | loss:0.01811072789132595 lr:9.6e-05 tokens_per_second_per_gpu:7123.492174707879 Step 25 | loss:0.009490473195910454 lr:0.0001 tokens_per_second_per_gpu:7053.228618090932 Step 26 | loss:0.0056476048193871975 lr:9.999512620046522e-05 tokens_per_second_per_gpu:7144.3630580616555 Step 27 | loss:0.008903786540031433 lr:9.998050575201771e-05 tokens_per_second_per_gpu:6601.668206482556 Step 28 | loss:0.0114928362891078 lr:9.995614150494293e-05 tokens_per_second_per_gpu:6916.210420494009 Step 29 | loss:0.036354534327983856 lr:9.992203820909906e-05 tokens_per_second_per_gpu:7095.468211925889 Step 30 | loss:0.008947554975748062 lr:9.987820251299122e-05 tokens_per_second_per_gpu:7065.885337048228 Step 31 | loss:0.007534285541623831 lr:9.982464296247522e-05 tokens_per_second_per_gpu:7032.490635569819 Step 32 | loss:0.005298151168972254 lr:9.976136999909156e-05 tokens_per_second_per_gpu:6875.820771405147 Step 33 | loss:0.00544830784201622 lr:9.968839595802982e-05 tokens_per_second_per_gpu:7057.810474959553 Step 34 | loss:0.00439912173897028 lr:9.96057350657239e-05 tokens_per_second_per_gpu:7042.282482648198 Step 35 | loss:0.008980338461697102 lr:9.951340343707852e-05 tokens_per_second_per_gpu:6959.547550583167 Step 36 | loss:0.04122934862971306 lr:9.941141907232765e-05 tokens_per_second_per_gpu:7069.742350095681 Step 37 | loss:0.0028896064031869173 lr:9.929980185352526e-05 tokens_per_second_per_gpu:6960.10595802011 Step 38 | loss:0.002492100466042757 lr:9.917857354066931e-05 tokens_per_second_per_gpu:2124.606589926057 Step 39 | loss:0.00473462650552392 lr:9.904775776745958e-05 tokens_per_second_per_gpu:6960.974627271292 Step 40 | loss:0.005951483268290758 lr:9.890738003669029e-05 tokens_per_second_per_gpu:6874.069116332843 Step 41 | loss:0.0013595054624602199 lr:9.875746771527816e-05 tokens_per_second_per_gpu:7165.394672400745 Step 42 | loss:0.00032235830440185964 lr:9.859805002892732e-05 tokens_per_second_per_gpu:6923.842699413365 Step 43 | loss:0.006130571942776442 lr:9.842915805643155e-05 tokens_per_second_per_gpu:7139.492779582739 Step 44 | loss:0.0016649358440190554 lr:9.825082472361557e-05 tokens_per_second_per_gpu:7011.731226529311 Step 45 | loss:0.001900543924421072 lr:9.806308479691595e-05 tokens_per_second_per_gpu:6932.374308996605 Step 46 | loss:0.002852720906957984 lr:9.786597487660337e-05 tokens_per_second_per_gpu:7064.616682685165 Step 47 | loss:0.0009402642608620226 lr:9.765953338964735e-05 tokens_per_second_per_gpu:7024.1161996665805 Step 48 | loss:0.06473583728075027 lr:9.744380058222483e-05 tokens_per_second_per_gpu:7080.774087266069 Step 49 | loss:0.0019610037561506033 lr:9.721881851187406e-05 tokens_per_second_per_gpu:7056.525585883424 Step 50 | loss:0.0002276381419505924 lr:9.698463103929542e-05 tokens_per_second_per_gpu:6972.399526065765 Step 51 | loss:0.002553830621764064 lr:9.674128381980072e-05 tokens_per_second_per_gpu:7087.395051350735 Step 52 | loss:0.01724120043218136 lr:9.648882429441257e-05 tokens_per_second_per_gpu:7089.949766557423 Step 53 | loss:0.00531097874045372 lr:9.622730168061567e-05 tokens_per_second_per_gpu:7108.3172227257655 Step 54 | loss:0.0005657114088535309 lr:9.595676696276172e-05 tokens_per_second_per_gpu:7118.738810946048 Step 55 | loss:0.00020866389968432486 lr:9.567727288213005e-05 tokens_per_second_per_gpu:7209.409955624229 Step 56 | loss:0.00033698687911964953 lr:9.538887392664544e-05 tokens_per_second_per_gpu:5985.472444106006 Step 57 | loss:0.001993008190765977 lr:9.50916263202557e-05 tokens_per_second_per_gpu:6877.956612513394 Step 58 | loss:0.001148563576862216 lr:9.478558801197065e-05 tokens_per_second_per_gpu:7143.540787423363 Step 59 | loss:0.0011705976212397218 lr:9.447081866456489e-05 tokens_per_second_per_gpu:6968.184377258604 Step 60 | loss:9.299201337853447e-05 lr:9.414737964294636e-05 tokens_per_second_per_gpu:6940.037661661558 Step 61 | loss:0.0017085925210267305 lr:9.381533400219318e-05 tokens_per_second_per_gpu:6880.377944463396 Step 62 | loss:8.154520037351176e-05 lr:9.347474647526095e-05 tokens_per_second_per_gpu:7087.4646315325035 Step 63 | loss:0.0037816863041371107 lr:9.312568346036288e-05 tokens_per_second_per_gpu:7106.066904279913 Step 64 | loss:0.002388354390859604 lr:9.276821300802534e-05 tokens_per_second_per_gpu:7122.96164326815 Step 65 | loss:0.0006903193425387144 lr:9.24024048078213e-05 tokens_per_second_per_gpu:6890.623177933791 Step 66 | loss:0.00011760497000068426 lr:9.202833017478422e-05 tokens_per_second_per_gpu:7173.5540245383345 Step 67 | loss:0.00016076462634373456 lr:9.164606203550497e-05 tokens_per_second_per_gpu:7154.7000891931375 Step 68 | loss:0.0017489870078861713 lr:9.125567491391476e-05 tokens_per_second_per_gpu:7109.003480755876 Step 69 | loss:0.0031393219251185656 lr:9.085724491675642e-05 tokens_per_second_per_gpu:7124.823709321188 Step 70 | loss:8.688953676028177e-05 lr:9.045084971874738e-05 tokens_per_second_per_gpu:7086.39946413596 Step 71 | loss:0.044045958667993546 lr:9.003656854743667e-05 tokens_per_second_per_gpu:6965.385365643236 Step 72 | loss:0.0010130113223567605 lr:8.961448216775954e-05 tokens_per_second_per_gpu:7087.704532918209 Step 73 | loss:5.404852709034458e-05 lr:8.9184672866292e-05 tokens_per_second_per_gpu:7214.507917902828 Step 74 | loss:6.700110679958016e-05 lr:8.874722443520899e-05 tokens_per_second_per_gpu:7088.500765974267 Step 75 | loss:5.5710228480165824e-05 lr:8.83022221559489e-05 tokens_per_second_per_gpu:7065.8653049557915 Step 76 | loss:0.04833333566784859 lr:8.784975278258783e-05 tokens_per_second_per_gpu:6954.82236744377 Step 77 | loss:0.0007975705666467547 lr:8.73899045249266e-05 tokens_per_second_per_gpu:6958.417600542274 Step 78 | loss:0.0008155775140039623 lr:8.692276703129421e-05 tokens_per_second_per_gpu:6969.169615787584 Step 79 | loss:0.014820348471403122 lr:8.644843137107059e-05 tokens_per_second_per_gpu:7047.096155841846 Step 80 | loss:9.19706144486554e-05 lr:8.596699001693255e-05 tokens_per_second_per_gpu:6965.522090543687 Step 81 | loss:3.2131534680956975e-05 lr:8.547853682682604e-05 tokens_per_second_per_gpu:7196.617738487695 Step 82 | loss:0.033360835164785385 lr:8.498316702566828e-05 tokens_per_second_per_gpu:7115.1209197775 Step 83 | loss:0.00046541576739400625 lr:8.44809771867835e-05 tokens_per_second_per_gpu:6631.541868433463 Step 84 | loss:0.00021498779824469239 lr:8.397206521307584e-05 tokens_per_second_per_gpu:6972.893470773807 Step 85 | loss:0.0006872712401673198 lr:8.345653031794292e-05 tokens_per_second_per_gpu:7188.938009979623 Step 86 | loss:0.012367724440991879 lr:8.293447300593402e-05 tokens_per_second_per_gpu:7041.928108969203 Step 87 | loss:0.0005004698759876192 lr:8.240599505315655e-05 tokens_per_second_per_gpu:7030.473092528077 Step 88 | loss:0.0008002397953532636 lr:8.18711994874345e-05 tokens_per_second_per_gpu:6965.978650678287 Step 89 | loss:0.006468301638960838 lr:8.133019056822304e-05 tokens_per_second_per_gpu:6955.002332314134 Step 90 | loss:0.0010322853922843933 lr:8.07830737662829e-05 tokens_per_second_per_gpu:7026.689649723494 Step 91 | loss:0.0021917782723903656 lr:8.022995574311876e-05 tokens_per_second_per_gpu:7049.689129678624 Step 92 | loss:5.479810351971537e-05 lr:7.967094433018508e-05 tokens_per_second_per_gpu:7145.14126940615 Step 93 | loss:0.00032177611137740314 lr:7.910614850786448e-05 tokens_per_second_per_gpu:7127.902009014699 Step 94 | loss:4.1998268898169044e-06 lr:7.85356783842216e-05 tokens_per_second_per_gpu:7126.891602122338 Step 95 | loss:0.00015233409067150205 lr:7.795964517353735e-05 tokens_per_second_per_gpu:6936.906564574708 Step 96 | loss:0.014088990166783333 lr:7.737816117462752e-05 tokens_per_second_per_gpu:7134.781179376626 Step 97 | loss:0.0003012325905729085 lr:7.679133974894983e-05 tokens_per_second_per_gpu:6937.110386019028 Step 98 | loss:0.000511819904204458 lr:7.619929529850397e-05 tokens_per_second_per_gpu:7025.3070893772565 Step 99 | loss:0.00026057279319502413 lr:7.560214324352858e-05 tokens_per_second_per_gpu:1940.8048042439789 Step 100 | loss:0.00033775632618926466 lr:7.500000000000001e-05 tokens_per_second_per_gpu:7153.295985121105 Step 101 | loss:0.0009956208523362875 lr:7.439298295693665e-05 tokens_per_second_per_gpu:7079.402870998616 Step 102 | loss:0.0003387658216524869 lr:7.378121045351378e-05 tokens_per_second_per_gpu:6942.659062734311 Step 103 | loss:5.418209912022576e-05 lr:7.316480175599309e-05 tokens_per_second_per_gpu:7015.82466383622 Step 104 | loss:0.0034662270918488503 lr:7.254387703447154e-05 tokens_per_second_per_gpu:7069.526354777707 Step 105 | loss:0.010241003707051277 lr:7.191855733945387e-05 tokens_per_second_per_gpu:7086.718452922028 Step 106 | loss:0.00022722584253642708 lr:7.128896457825364e-05 tokens_per_second_per_gpu:6920.852588322986 Step 107 | loss:0.005534096155315638 lr:7.06552214912271e-05 tokens_per_second_per_gpu:7094.725335418691 Step 108 | loss:0.00011627697676885873 lr:7.001745162784477e-05 tokens_per_second_per_gpu:7096.53105188645 Step 109 | loss:0.0012711388990283012 lr:6.937577932260515e-05 tokens_per_second_per_gpu:7054.047008100872 Step 110 | loss:0.007834851741790771 lr:6.873032967079561e-05 tokens_per_second_per_gpu:7031.898632174864 Step 111 | loss:0.00027020229026675224 lr:6.808122850410461e-05 tokens_per_second_per_gpu:6064.586963128856 Step 112 | loss:1.5623674698872492e-05 lr:6.742860236609077e-05 tokens_per_second_per_gpu:7204.287682463826 Step 113 | loss:1.6284971934510395e-05 lr:6.677257848751277e-05 tokens_per_second_per_gpu:7219.798954983771 Step 114 | loss:3.738223676919006e-05 lr:6.611328476152557e-05 tokens_per_second_per_gpu:7137.086495245911 Step 115 | loss:4.672707291319966e-05 lr:6.545084971874738e-05 tokens_per_second_per_gpu:7142.653265351455 Step 116 | loss:0.005011536180973053 lr:6.478540250220234e-05 tokens_per_second_per_gpu:7119.441070671983 Step 117 | loss:1.556543429614976e-05 lr:6.411707284214384e-05 tokens_per_second_per_gpu:7187.637024609732 Step 118 | loss:5.800935468869284e-06 lr:6.344599103076329e-05 tokens_per_second_per_gpu:7021.288505082598 Step 119 | loss:2.245832365588285e-05 lr:6.277228789678953e-05 tokens_per_second_per_gpu:6917.976780708287 Step 120 | loss:4.2964809836121276e-05 lr:6.209609477998338e-05 tokens_per_second_per_gpu:7012.121082275777 Step 121 | loss:0.0009158899774774909 lr:6.141754350553279e-05 tokens_per_second_per_gpu:7068.72713273128 Step 122 | loss:0.0033361720852553844 lr:6.073676635835317e-05 tokens_per_second_per_gpu:6983.597705574198 Step 123 | loss:3.5905526601709425e-05 lr:6.005389605729824e-05 tokens_per_second_per_gpu:6996.101222636149 Step 124 | loss:8.054270438151434e-05 lr:5.9369065729286245e-05 tokens_per_second_per_gpu:7042.470540631015 Step 125 | loss:2.2346790501615033e-05 lr:5.868240888334653e-05 tokens_per_second_per_gpu:6883.991749671246 Step 126 | loss:0.00010228392784483731 lr:5.799405938459175e-05 tokens_per_second_per_gpu:6851.880926520395 Step 127 | loss:0.009216566570103168 lr:5.730415142812059e-05 tokens_per_second_per_gpu:6944.35436383415 Step 128 | loss:4.989889930584468e-05 lr:5.661281951285613e-05 tokens_per_second_per_gpu:7066.202458617094 Step 129 | loss:2.9771052140858956e-05 lr:5.5920198415325064e-05 tokens_per_second_per_gpu:7114.01033634083 Step 130 | loss:2.9351815101108514e-05 lr:5.522642316338268e-05 tokens_per_second_per_gpu:7113.925123845522 Step 131 | loss:0.00022129551507532597 lr:5.453162900988902e-05 tokens_per_second_per_gpu:7070.752511766455 Step 132 | loss:0.00013191800098866224 lr:5.383595140634093e-05 tokens_per_second_per_gpu:6826.735868298663 Step 133 | loss:1.8393444406683557e-05 lr:5.313952597646568e-05 tokens_per_second_per_gpu:7073.793007285818 Step 134 | loss:0.001314793829806149 lr:5.244248848978067e-05 tokens_per_second_per_gpu:6942.121006398592 Step 135 | loss:0.0002268955431645736 lr:5.174497483512506e-05 tokens_per_second_per_gpu:6917.970008026615 Step 136 | loss:3.624207238317467e-05 lr:5.104712099416785e-05 tokens_per_second_per_gpu:6861.682979369597 Step 137 | loss:1.2716344826912973e-05 lr:5.034906301489808e-05 tokens_per_second_per_gpu:7180.87626329326 Step 138 | loss:0.003315841546282172 lr:4.965093698510193e-05 tokens_per_second_per_gpu:7071.001067992811 Step 139 | loss:4.6946879592724144e-06 lr:4.895287900583216e-05 tokens_per_second_per_gpu:7065.080228852681 Step 140 | loss:1.2532163054856937e-05 lr:4.825502516487497e-05 tokens_per_second_per_gpu:6645.867475251714 Step 141 | loss:0.00017276468861382455 lr:4.755751151021934e-05 tokens_per_second_per_gpu:7037.315989508988 Step 142 | loss:0.0005283844657242298 lr:4.6860474023534335e-05 tokens_per_second_per_gpu:7159.727517797382 Step 143 | loss:0.0021685995161533356 lr:4.616404859365907e-05 tokens_per_second_per_gpu:7040.884364854597 Step 144 | loss:9.090670687328384e-07 lr:4.5468370990111006e-05 tokens_per_second_per_gpu:7194.2115223844685 Step 145 | loss:0.00012133843847550452 lr:4.477357683661734e-05 tokens_per_second_per_gpu:7058.616578033227 Step 146 | loss:4.2023657442769036e-06 lr:4.407980158467495e-05 tokens_per_second_per_gpu:7095.438879745784 Step 147 | loss:0.0003925826749764383 lr:4.3387180487143876e-05 tokens_per_second_per_gpu:6949.434608089511 Step 148 | loss:3.3766911656130105e-05 lr:4.269584857187943e-05 tokens_per_second_per_gpu:7043.1552897764295 Step 149 | loss:3.4904051062767394e-06 lr:4.2005940615408264e-05 tokens_per_second_per_gpu:7013.4776285254575 Step 150 | loss:8.137324766721576e-05 lr:4.131759111665349e-05 tokens_per_second_per_gpu:6958.869901130744 Step 151 | loss:0.00016065464296843857 lr:4.063093427071376e-05 tokens_per_second_per_gpu:7087.424345053378 Step 152 | loss:0.00010077508341055363 lr:3.9946103942701777e-05 tokens_per_second_per_gpu:7045.051444080234 Step 153 | loss:7.43091368349269e-05 lr:3.926323364164684e-05 tokens_per_second_per_gpu:7070.901724247428 Step 154 | loss:0.00017325948283541948 lr:3.858245649446721e-05 tokens_per_second_per_gpu:6963.354807953419 Step 155 | loss:7.979149813763797e-06 lr:3.790390522001662e-05 tokens_per_second_per_gpu:7025.162341872974 Step 156 | loss:2.0571420463966206e-05 lr:3.7227712103210486e-05 tokens_per_second_per_gpu:7060.836154768928 Step 157 | loss:0.003111779922619462 lr:3.655400896923672e-05 tokens_per_second_per_gpu:7122.354062524588 Step 158 | loss:2.3453589165001176e-05 lr:3.588292715785617e-05 tokens_per_second_per_gpu:7074.938218893302 Step 159 | loss:4.341255043982528e-05 lr:3.5214597497797684e-05 tokens_per_second_per_gpu:6773.6664543150055 Step 160 | loss:1.4852120330033358e-05 lr:3.4549150281252636e-05 tokens_per_second_per_gpu:6960.888432183912 Step 161 | loss:0.0031983666121959686 lr:3.388671523847445e-05 tokens_per_second_per_gpu:7092.048945582944 Step 162 | loss:6.343660061247647e-06 lr:3.322742151248725e-05 tokens_per_second_per_gpu:7015.240720682864 Step 163 | loss:6.975037194933975e-06 lr:3.257139763390925e-05 tokens_per_second_per_gpu:7024.166830863724 Step 164 | loss:0.0017867812421172857 lr:3.1918771495895396e-05 tokens_per_second_per_gpu:7080.242762993974 Step 165 | loss:0.00021020961867179722 lr:3.12696703292044e-05 tokens_per_second_per_gpu:7021.6692198998235 Step 166 | loss:2.382525281063863e-06 lr:3.062422067739485e-05 tokens_per_second_per_gpu:7182.20458088362 Step 167 | loss:2.1856312741874717e-05 lr:2.9982548372155263e-05 tokens_per_second_per_gpu:7054.295858459668 Step 168 | loss:5.99730083195027e-06 lr:2.934477850877292e-05 tokens_per_second_per_gpu:7069.725214225424 Step 169 | loss:1.3508506526704878e-06 lr:2.8711035421746367e-05 tokens_per_second_per_gpu:7019.005262048196 Step 170 | loss:3.7983310903655365e-05 lr:2.8081442660546125e-05 tokens_per_second_per_gpu:7048.394828341541 Step 171 | loss:7.725130672042724e-06 lr:2.7456122965528475e-05 tokens_per_second_per_gpu:6909.961744303842 Step 172 | loss:4.822511618840508e-05 lr:2.6835198244006927e-05 tokens_per_second_per_gpu:7064.967066786179 Step 173 | loss:7.0207643148023635e-06 lr:2.6218789546486234e-05 tokens_per_second_per_gpu:7020.184879478688 Step 174 | loss:2.5988554170908174e-06 lr:2.560701704306336e-05 tokens_per_second_per_gpu:6855.290472577 Step 175 | loss:2.0116198356845416e-05 lr:2.500000000000001e-05 tokens_per_second_per_gpu:7121.674912212804 Step 176 | loss:0.0018564763013273478 lr:2.4397856756471432e-05 tokens_per_second_per_gpu:7050.494984704086 Step 177 | loss:5.568914730247343e-06 lr:2.3800704701496053e-05 tokens_per_second_per_gpu:6854.952748054827 Step 178 | loss:0.00016175849305000156 lr:2.3208660251050158e-05 tokens_per_second_per_gpu:2125.856458896523 Step 179 | loss:8.769461601332296e-06 lr:2.2621838825372493e-05 tokens_per_second_per_gpu:7132.1774306403395 Step 180 | loss:7.612565241288394e-06 lr:2.2040354826462668e-05 tokens_per_second_per_gpu:6947.727733226439 Step 181 | loss:1.152878121501999e-05 lr:2.1464321615778422e-05 tokens_per_second_per_gpu:6889.739737498116 Step 182 | loss:5.863937531103147e-06 lr:2.0893851492135537e-05 tokens_per_second_per_gpu:6921.491948079155 Step 183 | loss:0.0007172836922109127 lr:2.0329055669814934e-05 tokens_per_second_per_gpu:7153.60628639992 Step 184 | loss:4.729838838102296e-05 lr:1.977004425688126e-05 tokens_per_second_per_gpu:6965.524897994451 Step 185 | loss:9.562207196722738e-06 lr:1.9216926233717085e-05 tokens_per_second_per_gpu:6911.7910910205455 Step 186 | loss:2.5079818897211226e-06 lr:1.866980943177699e-05 tokens_per_second_per_gpu:7017.92557317039 Step 187 | loss:0.0016225886065512896 lr:1.8128800512565513e-05 tokens_per_second_per_gpu:7061.541576329739 Step 188 | loss:2.6910747692454606e-05 lr:1.7594004946843456e-05 tokens_per_second_per_gpu:6920.2433528593565 Step 189 | loss:5.382075869420078e-06 lr:1.7065526994065973e-05 tokens_per_second_per_gpu:7068.999353386659 Step 190 | loss:5.059693194198189e-06 lr:1.6543469682057106e-05 tokens_per_second_per_gpu:7036.202154351747 Step 191 | loss:6.322688932414167e-06 lr:1.602793478692419e-05 tokens_per_second_per_gpu:7019.570816682339 Step 192 | loss:1.3762522030447144e-05 lr:1.551902281321651e-05 tokens_per_second_per_gpu:7186.960747630098 Step 193 | loss:1.6130499716382474e-05 lr:1.5016832974331724e-05 tokens_per_second_per_gpu:6931.377889348733 Step 194 | loss:0.0012891488149762154 lr:1.4521463173173965e-05 tokens_per_second_per_gpu:6923.94432724115 Step 195 | loss:1.1514081052155234e-05 lr:1.4033009983067452e-05 tokens_per_second_per_gpu:7219.701037608233 Step 196 | loss:4.614694717020029e-06 lr:1.3551568628929434e-05 tokens_per_second_per_gpu:6849.9204527778265 Step 197 | loss:6.589160875591915e-06 lr:1.3077232968705805e-05 tokens_per_second_per_gpu:7167.977132160766 Step 198 | loss:4.994192568119615e-05 lr:1.2610095475073414e-05 tokens_per_second_per_gpu:6981.219336717138 Step 199 | loss:0.002434401074424386 lr:1.2150247217412186e-05 tokens_per_second_per_gpu:7142.988021132232 Step 200 | loss:3.514826676109806e-05 lr:1.1697777844051105e-05 tokens_per_second_per_gpu:7043.691517058615 Step 201 | loss:0.002575391437858343 lr:1.1252775564791024e-05 tokens_per_second_per_gpu:6933.347204999327 Step 202 | loss:4.996413554181345e-05 lr:1.0815327133708015e-05 tokens_per_second_per_gpu:7096.318449803076 Step 203 | loss:2.5075056328205392e-05 lr:1.0385517832240471e-05 tokens_per_second_per_gpu:7078.475243762443 Step 204 | loss:0.00038772160769440234 lr:9.963431452563332e-06 tokens_per_second_per_gpu:7122.161162176795 Step 205 | loss:2.0274069356673863e-06 lr:9.549150281252633e-06 tokens_per_second_per_gpu:6869.011105083088 Step 206 | loss:2.971089634229429e-05 lr:9.142755083243576e-06 tokens_per_second_per_gpu:7065.033567386976 Step 207 | loss:0.0002002189285121858 lr:8.744325086085248e-06 tokens_per_second_per_gpu:7206.5467259067755 Step 208 | loss:1.5768082448630594e-05 lr:8.353937964495029e-06 tokens_per_second_per_gpu:7036.026473041153 Step 209 | loss:8.778577466728166e-05 lr:7.971669825215788e-06 tokens_per_second_per_gpu:7049.985605203123 Step 210 | loss:1.851968227128964e-05 lr:7.597595192178702e-06 tokens_per_second_per_gpu:6956.833419646107 Step 211 | loss:7.031407676549861e-06 lr:7.2317869919746705e-06 tokens_per_second_per_gpu:6952.707981294269 Step 212 | loss:1.2874485946667846e-05 lr:6.874316539637127e-06 tokens_per_second_per_gpu:6893.534198130221 Step 213 | loss:9.367141501570586e-06 lr:6.52525352473905e-06 tokens_per_second_per_gpu:6857.354639793877 Step 214 | loss:0.002237878739833832 lr:6.184665997806832e-06 tokens_per_second_per_gpu:7195.5866373952485 Step 215 | loss:0.00048373171011917293 lr:5.852620357053651e-06 tokens_per_second_per_gpu:7002.773188401259 Step 216 | loss:0.0032627710606902838 lr:5.529181335435124e-06 tokens_per_second_per_gpu:7061.696276091508 Step 217 | loss:5.069312464911491e-05 lr:5.214411988029355e-06 tokens_per_second_per_gpu:6890.415881542752 Step 218 | loss:4.757709575642366e-06 lr:4.908373679744316e-06 tokens_per_second_per_gpu:7060.582136958122 Step 219 | loss:1.0104783541464712e-05 lr:4.611126073354571e-06 tokens_per_second_per_gpu:6935.073111293265 Step 220 | loss:1.7441529053030536e-05 lr:4.322727117869951e-06 tokens_per_second_per_gpu:7162.159857597445 Step 221 | loss:7.991015991137829e-06 lr:4.043233037238281e-06 tokens_per_second_per_gpu:7120.473597395198 Step 222 | loss:0.0016436312580481172 lr:3.772698319384349e-06 tokens_per_second_per_gpu:7065.371799685919 Step 223 | loss:0.0001338210713583976 lr:3.511175705587433e-06 tokens_per_second_per_gpu:7066.181303252901 Step 224 | loss:9.547553418087773e-06 lr:3.258716180199278e-06 tokens_per_second_per_gpu:7053.877871748493 Step 225 | loss:1.3877786841476336e-05 lr:3.0153689607045845e-06 tokens_per_second_per_gpu:6936.131143481461 Step 226 | loss:7.166168870753609e-06 lr:2.7811814881259503e-06 tokens_per_second_per_gpu:7011.560953069312 Step 227 | loss:2.667139369805227e-06 lr:2.5561994177751737e-06 tokens_per_second_per_gpu:6960.7849351433215 Step 228 | loss:3.3916057873284444e-05 lr:2.340466610352654e-06 tokens_per_second_per_gpu:7041.290850103043 Step 229 | loss:0.0002864692360162735 lr:2.134025123396638e-06 tokens_per_second_per_gpu:7058.741030555026 Step 230 | loss:0.0033281990326941013 lr:1.9369152030840556e-06 tokens_per_second_per_gpu:6872.165408538311 Step 231 | loss:4.109196743229404e-05 lr:1.7491752763844293e-06 tokens_per_second_per_gpu:7135.676777217044 Step 232 | loss:1.5727893014627625e-06 lr:1.5708419435684462e-06 tokens_per_second_per_gpu:7026.898368111261 Step 233 | loss:3.718547986863996e-06 lr:1.4019499710726913e-06 tokens_per_second_per_gpu:7023.464829798449 Step 234 | loss:1.0648089300957508e-05 lr:1.2425322847218368e-06 tokens_per_second_per_gpu:7136.5639024348875 Step 235 | loss:3.5123148336424492e-06 lr:1.0926199633097157e-06 tokens_per_second_per_gpu:6794.690877645096 Step 236 | loss:8.667976544529665e-06 lr:9.522422325404235e-07 tokens_per_second_per_gpu:6940.512272756377 Step 237 | loss:0.0004719682619906962 lr:8.214264593307098e-07 tokens_per_second_per_gpu:6875.884476947481 Step 238 | loss:0.0027058066334575415 lr:7.001981464747565e-07 tokens_per_second_per_gpu:7084.282113501637 Step 239 | loss:7.863612154324073e-06 lr:5.885809276723608e-07 tokens_per_second_per_gpu:7071.499989090434 Step 240 | loss:0.004036718979477882 lr:4.865965629214819e-07 tokens_per_second_per_gpu:6945.969658776998 Step 241 | loss:7.3063915806415025e-06 lr:3.9426493427611177e-07 tokens_per_second_per_gpu:6972.921059533873 Step 242 | loss:9.349812899017707e-06 lr:3.1160404197018154e-07 tokens_per_second_per_gpu:7096.089393727951 Step 243 | loss:2.7819935439765686e-06 lr:2.386300009084408e-07 tokens_per_second_per_gpu:7202.7611894553265 Step 244 | loss:8.86179714143509e-06 lr:1.753570375247815e-07 tokens_per_second_per_gpu:6876.744283710465 Step 245 | loss:1.3657549970957916e-05 lr:1.2179748700879012e-07 tokens_per_second_per_gpu:6968.336074572096 Step 246 | loss:0.0005366122350096703 lr:7.796179090094891e-08 tokens_per_second_per_gpu:7074.417372015085 Step 247 | loss:6.625515379710123e-05 lr:4.385849505708084e-08 tokens_per_second_per_gpu:7076.23792273582 Step 248 | loss:7.85504380473867e-06 lr:1.949424798228239e-08 tokens_per_second_per_gpu:7117.863134099135 Step 249 | loss:2.1800748072564602e-05 lr:4.873799534788059e-09 tokens_per_second_per_gpu:7073.3416108299 Step 250 | loss:0.0018682614900171757 lr:0.0 tokens_per_second_per_gpu:7068.4513755459375