Step 1 | loss:0.21454522013664246 lr:4.000000000000001e-06 tokens_per_second_per_gpu:2204.886471951761 Step 2 | loss:0.2192268818616867 lr:8.000000000000001e-06 tokens_per_second_per_gpu:1874.2989836713725 Step 3 | loss:0.12282795459032059 lr:1.2e-05 tokens_per_second_per_gpu:3008.5158935654927 Step 4 | loss:0.1078612208366394 lr:1.6000000000000003e-05 tokens_per_second_per_gpu:7182.33391872045 Step 5 | loss:0.11316835135221481 lr:2e-05 tokens_per_second_per_gpu:3531.969999084538 Step 6 | loss:0.19186416268348694 lr:2.4e-05 tokens_per_second_per_gpu:6728.453057493188 Step 7 | loss:0.21128560602664948 lr:2.8000000000000003e-05 tokens_per_second_per_gpu:2210.4398761036896 Step 8 | loss:0.10171176493167877 lr:3.2000000000000005e-05 tokens_per_second_per_gpu:7237.620268713336 Step 9 | loss:0.1533355861902237 lr:3.6e-05 tokens_per_second_per_gpu:7168.727917212457 Step 10 | loss:0.11144552379846573 lr:4e-05 tokens_per_second_per_gpu:2376.565219104462 Step 11 | loss:0.20093227922916412 lr:4.4000000000000006e-05 tokens_per_second_per_gpu:1306.8151053478143 Step 12 | loss:0.12860259413719177 lr:4.8e-05 tokens_per_second_per_gpu:2197.2884503043597 Step 13 | loss:0.23503157496452332 lr:5.2000000000000004e-05 tokens_per_second_per_gpu:1856.1268896808217 Step 14 | loss:0.1340928077697754 lr:5.6000000000000006e-05 tokens_per_second_per_gpu:6927.611608093336 Step 15 | loss:0.12543116509914398 lr:6e-05 tokens_per_second_per_gpu:6734.467248486393 Step 16 | loss:0.10119607299566269 lr:6.400000000000001e-05 tokens_per_second_per_gpu:6835.519648543333 Step 17 | loss:0.05681230127811432 lr:6.800000000000001e-05 tokens_per_second_per_gpu:3530.438653895445 Step 18 | loss:0.06565061956644058 lr:7.2e-05 tokens_per_second_per_gpu:7167.118850819361 Step 19 | loss:0.24538388848304749 lr:7.6e-05 tokens_per_second_per_gpu:6807.932873567432 Step 20 | loss:0.09544023871421814 lr:8e-05 tokens_per_second_per_gpu:1331.7042731481047 Step 21 | loss:0.12082114815711975 lr:8.4e-05 tokens_per_second_per_gpu:7104.901843029605 Step 22 | loss:0.055162493139505386 lr:8.800000000000001e-05 tokens_per_second_per_gpu:6880.495181009204 Step 23 | loss:0.056379713118076324 lr:9.200000000000001e-05 tokens_per_second_per_gpu:7178.194503820619 Step 24 | loss:0.079165980219841 lr:9.6e-05 tokens_per_second_per_gpu:1440.1568461783522 Step 25 | loss:0.09269428253173828 lr:0.0001 tokens_per_second_per_gpu:7156.190721863311 Step 26 | loss:0.049547187983989716 lr:9.999512620046522e-05 tokens_per_second_per_gpu:6905.502402629844 Step 27 | loss:0.051843784749507904 lr:9.998050575201771e-05 tokens_per_second_per_gpu:5119.147290036451 Step 28 | loss:0.05784168466925621 lr:9.995614150494293e-05 tokens_per_second_per_gpu:6760.960399163626 Step 29 | loss:0.05249595642089844 lr:9.992203820909906e-05 tokens_per_second_per_gpu:1417.2869923768815 Step 30 | loss:0.036574386060237885 lr:9.987820251299122e-05 tokens_per_second_per_gpu:7201.34342556336 Step 31 | loss:0.04362167790532112 lr:9.982464296247522e-05 tokens_per_second_per_gpu:6848.333447182901 Step 32 | loss:0.021947499364614487 lr:9.976136999909156e-05 tokens_per_second_per_gpu:7223.283463904051 Step 33 | loss:0.043542664498090744 lr:9.968839595802982e-05 tokens_per_second_per_gpu:7220.467549519646 Step 34 | loss:0.0430750735104084 lr:9.96057350657239e-05 tokens_per_second_per_gpu:6697.823138472947 Step 35 | loss:0.1189943253993988 lr:9.951340343707852e-05 tokens_per_second_per_gpu:6867.26113270018 Step 36 | loss:0.02588760107755661 lr:9.941141907232765e-05 tokens_per_second_per_gpu:7221.17133674717 Step 37 | loss:0.03736526146531105 lr:9.929980185352526e-05 tokens_per_second_per_gpu:6732.894046454971 Step 38 | loss:0.014334405772387981 lr:9.917857354066931e-05 tokens_per_second_per_gpu:7222.791426848653 Step 39 | loss:0.12494668364524841 lr:9.904775776745958e-05 tokens_per_second_per_gpu:6739.218489833239 Step 40 | loss:0.10289347916841507 lr:9.890738003669029e-05 tokens_per_second_per_gpu:6841.899029387429 Step 41 | loss:0.019181478768587112 lr:9.875746771527816e-05 tokens_per_second_per_gpu:7133.6424484187 Step 42 | loss:0.013900469988584518 lr:9.859805002892732e-05 tokens_per_second_per_gpu:7023.0507795153235 Step 43 | loss:0.025148896500468254 lr:9.842915805643155e-05 tokens_per_second_per_gpu:6908.7888546191325 Step 44 | loss:0.009295633062720299 lr:9.825082472361557e-05 tokens_per_second_per_gpu:7157.954873165439 Step 45 | loss:0.028096619993448257 lr:9.806308479691595e-05 tokens_per_second_per_gpu:7026.065495499532 Step 46 | loss:0.0365627147257328 lr:9.786597487660337e-05 tokens_per_second_per_gpu:6587.225263210627 Step 47 | loss:0.019679149612784386 lr:9.765953338964735e-05 tokens_per_second_per_gpu:7080.082548074433 Step 48 | loss:0.01593785174190998 lr:9.744380058222483e-05 tokens_per_second_per_gpu:7186.864108027182 Step 49 | loss:0.0063719493336975574 lr:9.721881851187406e-05 tokens_per_second_per_gpu:7043.572775779108 Step 50 | loss:0.009346225298941135 lr:9.698463103929542e-05 tokens_per_second_per_gpu:7131.891273066765 Step 51 | loss:0.006743339356034994 lr:9.674128381980072e-05 tokens_per_second_per_gpu:6781.385892331163 Step 52 | loss:0.01974179595708847 lr:9.648882429441257e-05 tokens_per_second_per_gpu:6872.449202672026 Step 53 | loss:0.028884118422865868 lr:9.622730168061567e-05 tokens_per_second_per_gpu:7156.445993745408 Step 54 | loss:0.00988077837973833 lr:9.595676696276172e-05 tokens_per_second_per_gpu:6722.493877553382 Step 55 | loss:0.01314352173358202 lr:9.567727288213005e-05 tokens_per_second_per_gpu:7214.729208087308 Step 56 | loss:0.009458537213504314 lr:9.538887392664544e-05 tokens_per_second_per_gpu:6178.28490677864 Step 57 | loss:0.003685786621645093 lr:9.50916263202557e-05 tokens_per_second_per_gpu:6671.514130358334 Step 58 | loss:0.004821490030735731 lr:9.478558801197065e-05 tokens_per_second_per_gpu:7215.557656441985 Step 59 | loss:0.03915349021553993 lr:9.447081866456489e-05 tokens_per_second_per_gpu:6870.6832939515425 Step 60 | loss:0.02035912312567234 lr:9.414737964294636e-05 tokens_per_second_per_gpu:6887.087453120185 Step 61 | loss:0.0886089950799942 lr:9.381533400219318e-05 tokens_per_second_per_gpu:6849.0079914900025 Step 62 | loss:0.0047807227820158005 lr:9.347474647526095e-05 tokens_per_second_per_gpu:7213.785285609079 Step 63 | loss:0.010801953263580799 lr:9.312568346036288e-05 tokens_per_second_per_gpu:6825.669452337699 Step 64 | loss:0.006679396145045757 lr:9.276821300802534e-05 tokens_per_second_per_gpu:7059.6198278937445 Step 65 | loss:0.017594274133443832 lr:9.24024048078213e-05 tokens_per_second_per_gpu:6851.689860301379 Step 66 | loss:0.0016389205120503902 lr:9.202833017478422e-05 tokens_per_second_per_gpu:6868.109593259859 Step 67 | loss:0.013542493805289268 lr:9.164606203550497e-05 tokens_per_second_per_gpu:6864.392835940598 Step 68 | loss:0.005851435009390116 lr:9.125567491391476e-05 tokens_per_second_per_gpu:6709.500157596116 Step 69 | loss:0.00034265598515048623 lr:9.085724491675642e-05 tokens_per_second_per_gpu:6832.669825454431 Step 70 | loss:0.01172163151204586 lr:9.045084971874738e-05 tokens_per_second_per_gpu:6866.885023191393 Step 71 | loss:0.03239409625530243 lr:9.003656854743667e-05 tokens_per_second_per_gpu:7136.646186123374 Step 72 | loss:0.0023614217061549425 lr:8.961448216775954e-05 tokens_per_second_per_gpu:6829.780968731167 Step 73 | loss:0.051009178161621094 lr:8.9184672866292e-05 tokens_per_second_per_gpu:6676.785580418302 Step 74 | loss:0.0036364442203193903 lr:8.874722443520899e-05 tokens_per_second_per_gpu:7196.170654247331 Step 75 | loss:0.01017762441188097 lr:8.83022221559489e-05 tokens_per_second_per_gpu:7192.59424533737 Step 76 | loss:0.005098192021250725 lr:8.784975278258783e-05 tokens_per_second_per_gpu:6727.1905182225555 Step 77 | loss:0.004959724843502045 lr:8.73899045249266e-05 tokens_per_second_per_gpu:7137.561266386104 Step 78 | loss:0.006274321582168341 lr:8.692276703129421e-05 tokens_per_second_per_gpu:7085.901071158827 Step 79 | loss:0.013396183028817177 lr:8.644843137107059e-05 tokens_per_second_per_gpu:7160.663616175761 Step 80 | loss:0.0051046330481767654 lr:8.596699001693255e-05 tokens_per_second_per_gpu:7156.519878161912 Step 81 | loss:0.0010839422466233373 lr:8.547853682682604e-05 tokens_per_second_per_gpu:6671.416727650906 Step 82 | loss:0.0037536185700446367 lr:8.498316702566828e-05 tokens_per_second_per_gpu:7186.741462598087 Step 83 | loss:0.003516328288242221 lr:8.44809771867835e-05 tokens_per_second_per_gpu:6710.2107957683575 Step 84 | loss:0.002433683490380645 lr:8.397206521307584e-05 tokens_per_second_per_gpu:7140.425548304953 Step 85 | loss:7.5109965109732e-05 lr:8.345653031794292e-05 tokens_per_second_per_gpu:1312.6654163674975 Step 86 | loss:0.10559462010860443 lr:8.293447300593402e-05 tokens_per_second_per_gpu:7058.510524108618 Step 87 | loss:0.012298772111535072 lr:8.240599505315655e-05 tokens_per_second_per_gpu:7210.344186803624 Step 88 | loss:0.002052792813628912 lr:8.18711994874345e-05 tokens_per_second_per_gpu:6701.398716988629 Step 89 | loss:0.05832357332110405 lr:8.133019056822304e-05 tokens_per_second_per_gpu:7231.848312118448 Step 90 | loss:0.013411249034106731 lr:8.07830737662829e-05 tokens_per_second_per_gpu:7245.303222202199 Step 91 | loss:0.003465564688667655 lr:8.022995574311876e-05 tokens_per_second_per_gpu:6747.304921900364 Step 92 | loss:0.057763900607824326 lr:7.967094433018508e-05 tokens_per_second_per_gpu:6875.581623145613 Step 93 | loss:0.0011183329625055194 lr:7.910614850786448e-05 tokens_per_second_per_gpu:7197.89329811353 Step 94 | loss:0.0015590006951242685 lr:7.85356783842216e-05 tokens_per_second_per_gpu:7286.717675154484 Step 95 | loss:0.036075200885534286 lr:7.795964517353735e-05 tokens_per_second_per_gpu:7032.083338680449 Step 96 | loss:0.01859893649816513 lr:7.737816117462752e-05 tokens_per_second_per_gpu:6701.352524314828 Step 97 | loss:0.007013784255832434 lr:7.679133974894983e-05 tokens_per_second_per_gpu:7246.091112119367 Step 98 | loss:0.005453180056065321 lr:7.619929529850397e-05 tokens_per_second_per_gpu:7213.152971501417 Step 99 | loss:0.01213571336120367 lr:7.560214324352858e-05 tokens_per_second_per_gpu:7215.703751177921 Step 100 | loss:0.0007280568825080991 lr:7.500000000000001e-05 tokens_per_second_per_gpu:6713.174913884814 Step 101 | loss:0.008527942933142185 lr:7.439298295693665e-05 tokens_per_second_per_gpu:7195.631844891046 Step 102 | loss:0.028709452599287033 lr:7.378121045351378e-05 tokens_per_second_per_gpu:6745.97101482126 Step 103 | loss:0.005169436801224947 lr:7.316480175599309e-05 tokens_per_second_per_gpu:7230.934373176921 Step 104 | loss:0.04041149839758873 lr:7.254387703447154e-05 tokens_per_second_per_gpu:7027.674430800321 Step 105 | loss:0.009436164051294327 lr:7.191855733945387e-05 tokens_per_second_per_gpu:6927.145100676699 Step 106 | loss:0.0018053905805572867 lr:7.128896457825364e-05 tokens_per_second_per_gpu:7165.635694717159 Step 107 | loss:0.002695614704862237 lr:7.06552214912271e-05 tokens_per_second_per_gpu:7166.8471974265285 Step 108 | loss:0.015116673894226551 lr:7.001745162784477e-05 tokens_per_second_per_gpu:6905.68778058486 Step 109 | loss:0.0022071264684200287 lr:6.937577932260515e-05 tokens_per_second_per_gpu:6755.146966728061 Step 110 | loss:0.0013368356740102172 lr:6.873032967079561e-05 tokens_per_second_per_gpu:7112.036254053348 Step 111 | loss:0.005866238847374916 lr:6.808122850410461e-05 tokens_per_second_per_gpu:5642.1029374653135 Step 112 | loss:0.0007922259974293411 lr:6.742860236609077e-05 tokens_per_second_per_gpu:6705.328267283878 Step 113 | loss:0.0020623011514544487 lr:6.677257848751277e-05 tokens_per_second_per_gpu:6992.892877145843 Step 114 | loss:0.02311033383011818 lr:6.611328476152557e-05 tokens_per_second_per_gpu:6974.87166699355 Step 115 | loss:0.04651001840829849 lr:6.545084971874738e-05 tokens_per_second_per_gpu:6712.790027902941 Step 116 | loss:0.0011063816491514444 lr:6.478540250220234e-05 tokens_per_second_per_gpu:6954.408906812058 Step 117 | loss:0.0004514830943662673 lr:6.411707284214384e-05 tokens_per_second_per_gpu:7015.178895368217 Step 118 | loss:0.0007309417123906314 lr:6.344599103076329e-05 tokens_per_second_per_gpu:6730.353240249519 Step 119 | loss:0.0018614016007632017 lr:6.277228789678953e-05 tokens_per_second_per_gpu:7124.619609571141 Step 120 | loss:0.01511246059089899 lr:6.209609477998338e-05 tokens_per_second_per_gpu:6693.8705710472805 Step 121 | loss:0.04765196144580841 lr:6.141754350553279e-05 tokens_per_second_per_gpu:6751.604919111893 Step 122 | loss:0.0002860105305444449 lr:6.073676635835317e-05 tokens_per_second_per_gpu:6748.728051826743 Step 123 | loss:0.00021126835781615227 lr:6.005389605729824e-05 tokens_per_second_per_gpu:7043.679848148311 Step 124 | loss:0.007544124964624643 lr:5.9369065729286245e-05 tokens_per_second_per_gpu:7090.756401875122 Step 125 | loss:0.010680953040719032 lr:5.868240888334653e-05 tokens_per_second_per_gpu:7201.845165519939 Step 126 | loss:0.0011367222759872675 lr:5.799405938459175e-05 tokens_per_second_per_gpu:6674.787294043434 Step 127 | loss:0.000524386006873101 lr:5.730415142812059e-05 tokens_per_second_per_gpu:7049.524563165695 Step 128 | loss:0.000252923637162894 lr:5.661281951285613e-05 tokens_per_second_per_gpu:7170.667645098482 Step 129 | loss:0.0003102787595707923 lr:5.5920198415325064e-05 tokens_per_second_per_gpu:7027.8755641874295 Step 130 | loss:0.00015616213204339147 lr:5.522642316338268e-05 tokens_per_second_per_gpu:6967.28060445015 Step 131 | loss:0.0011364052770659328 lr:5.453162900988902e-05 tokens_per_second_per_gpu:6724.794350293351 Step 132 | loss:0.0015487158671021461 lr:5.383595140634093e-05 tokens_per_second_per_gpu:6877.221599931812 Step 133 | loss:0.0019609443843364716 lr:5.313952597646568e-05 tokens_per_second_per_gpu:7241.615521717516 Step 134 | loss:0.0003139186301268637 lr:5.244248848978067e-05 tokens_per_second_per_gpu:6737.525116992511 Step 135 | loss:0.00040980218909680843 lr:5.174497483512506e-05 tokens_per_second_per_gpu:7139.69558515326 Step 136 | loss:0.0010918889893218875 lr:5.104712099416785e-05 tokens_per_second_per_gpu:6665.288129303459 Step 137 | loss:0.00046571268467232585 lr:5.034906301489808e-05 tokens_per_second_per_gpu:6723.607684717743 Step 138 | loss:0.00018371768237557262 lr:4.965093698510193e-05 tokens_per_second_per_gpu:6890.604166702296 Step 139 | loss:4.508267738856375e-05 lr:4.895287900583216e-05 tokens_per_second_per_gpu:6756.40339484982 Step 140 | loss:0.00038852368015795946 lr:4.825502516487497e-05 tokens_per_second_per_gpu:5641.7686501145245 Step 141 | loss:0.011766304261982441 lr:4.755751151021934e-05 tokens_per_second_per_gpu:7206.919635840261 Step 142 | loss:0.002816063119098544 lr:4.6860474023534335e-05 tokens_per_second_per_gpu:7277.287282195006 Step 143 | loss:0.0024972371757030487 lr:4.616404859365907e-05 tokens_per_second_per_gpu:6904.9799525133885 Step 144 | loss:2.5079951228690334e-05 lr:4.5468370990111006e-05 tokens_per_second_per_gpu:6869.733579935104 Step 145 | loss:0.005149812437593937 lr:4.477357683661734e-05 tokens_per_second_per_gpu:6700.716769944385 Step 146 | loss:0.0003222393279429525 lr:4.407980158467495e-05 tokens_per_second_per_gpu:1319.9440908319277 Step 147 | loss:0.00020474102348089218 lr:4.3387180487143876e-05 tokens_per_second_per_gpu:7044.718401344008 Step 148 | loss:6.389812187990174e-05 lr:4.269584857187943e-05 tokens_per_second_per_gpu:7125.192079409829 Step 149 | loss:0.00022454356076195836 lr:4.2005940615408264e-05 tokens_per_second_per_gpu:6899.7020106373975 Step 150 | loss:0.00020254458650015295 lr:4.131759111665349e-05 tokens_per_second_per_gpu:6926.646027061933 Step 151 | loss:4.565511699183844e-05 lr:4.063093427071376e-05 tokens_per_second_per_gpu:6832.485727412436 Step 152 | loss:0.00018762053514365107 lr:3.9946103942701777e-05 tokens_per_second_per_gpu:7180.819541957924 Step 153 | loss:2.6780402549775317e-05 lr:3.926323364164684e-05 tokens_per_second_per_gpu:6656.041290312809 Step 154 | loss:0.020499125123023987 lr:3.858245649446721e-05 tokens_per_second_per_gpu:6917.950375438419 Step 155 | loss:3.116218067589216e-05 lr:3.790390522001662e-05 tokens_per_second_per_gpu:7123.958958670115 Step 156 | loss:0.0001650269841775298 lr:3.7227712103210486e-05 tokens_per_second_per_gpu:6927.14354031202 Step 157 | loss:0.0007947291596792638 lr:3.655400896923672e-05 tokens_per_second_per_gpu:7240.6871722814885 Step 158 | loss:9.410783968633041e-05 lr:3.588292715785617e-05 tokens_per_second_per_gpu:6857.693066373381 Step 159 | loss:4.4820859329774976e-05 lr:3.5214597497797684e-05 tokens_per_second_per_gpu:7240.532411435879 Step 160 | loss:3.969995668740012e-05 lr:3.4549150281252636e-05 tokens_per_second_per_gpu:6809.314346176168 Step 161 | loss:0.001787496032193303 lr:3.388671523847445e-05 tokens_per_second_per_gpu:7233.074179115523 Step 162 | loss:5.837308708578348e-05 lr:3.322742151248725e-05 tokens_per_second_per_gpu:7154.958497849225 Step 163 | loss:4.34636531281285e-05 lr:3.257139763390925e-05 tokens_per_second_per_gpu:7157.025158795719 Step 164 | loss:0.0001924792304635048 lr:3.1918771495895396e-05 tokens_per_second_per_gpu:7188.738452995817 Step 165 | loss:0.0010299683781340718 lr:3.12696703292044e-05 tokens_per_second_per_gpu:6803.975530244364 Step 166 | loss:0.00015102078032214195 lr:3.062422067739485e-05 tokens_per_second_per_gpu:7275.2337259845735 Step 167 | loss:0.013041829690337181 lr:2.9982548372155263e-05 tokens_per_second_per_gpu:7196.174589765266 Step 168 | loss:3.924150951206684e-05 lr:2.934477850877292e-05 tokens_per_second_per_gpu:7029.281023027497 Step 169 | loss:1.3280385246616788e-05 lr:2.8711035421746367e-05 tokens_per_second_per_gpu:4271.599842498729 Step 170 | loss:0.00014277368609327823 lr:2.8081442660546125e-05 tokens_per_second_per_gpu:6925.0481418184545 Step 171 | loss:0.004575395490974188 lr:2.7456122965528475e-05 tokens_per_second_per_gpu:6825.357349094899 Step 172 | loss:0.00036650101537816226 lr:2.6835198244006927e-05 tokens_per_second_per_gpu:7219.033124023539 Step 173 | loss:9.771480108611286e-05 lr:2.6218789546486234e-05 tokens_per_second_per_gpu:7132.653328249004 Step 174 | loss:0.004404139705002308 lr:2.560701704306336e-05 tokens_per_second_per_gpu:7123.760726587094 Step 175 | loss:6.910594674991444e-05 lr:2.500000000000001e-05 tokens_per_second_per_gpu:6731.891450654538 Step 176 | loss:5.778518971055746e-05 lr:2.4397856756471432e-05 tokens_per_second_per_gpu:7263.171119483078 Step 177 | loss:1.1581289072637446e-05 lr:2.3800704701496053e-05 tokens_per_second_per_gpu:6937.856086142961 Step 178 | loss:2.099542871292215e-05 lr:2.3208660251050158e-05 tokens_per_second_per_gpu:7081.433372890857 Step 179 | loss:0.00012874671665485948 lr:2.2621838825372493e-05 tokens_per_second_per_gpu:7203.083230416578 Step 180 | loss:3.4759726986521855e-05 lr:2.2040354826462668e-05 tokens_per_second_per_gpu:6743.642845257739 Step 181 | loss:8.574708044761792e-05 lr:2.1464321615778422e-05 tokens_per_second_per_gpu:7166.931675924236 Step 182 | loss:0.00013232270430307835 lr:2.0893851492135537e-05 tokens_per_second_per_gpu:7030.175750895704 Step 183 | loss:2.5258697860408574e-05 lr:2.0329055669814934e-05 tokens_per_second_per_gpu:6930.59174719172 Step 184 | loss:5.778928971267305e-05 lr:1.977004425688126e-05 tokens_per_second_per_gpu:6709.958741130997 Step 185 | loss:0.0024249653797596693 lr:1.9216926233717085e-05 tokens_per_second_per_gpu:7196.562518251089 Step 186 | loss:3.324362478451803e-05 lr:1.866980943177699e-05 tokens_per_second_per_gpu:6983.622221138546 Step 187 | loss:8.629039803054184e-05 lr:1.8128800512565513e-05 tokens_per_second_per_gpu:7063.586359335986 Step 188 | loss:0.0025053436402231455 lr:1.7594004946843456e-05 tokens_per_second_per_gpu:7193.417449202519 Step 189 | loss:0.0006006701732985675 lr:1.7065526994065973e-05 tokens_per_second_per_gpu:6833.164830044736 Step 190 | loss:0.004268196877092123 lr:1.6543469682057106e-05 tokens_per_second_per_gpu:7148.211892504355 Step 191 | loss:6.555038271471858e-05 lr:1.602793478692419e-05 tokens_per_second_per_gpu:6698.547270972454 Step 192 | loss:0.0005891823675483465 lr:1.551902281321651e-05 tokens_per_second_per_gpu:7260.92974867431 Step 193 | loss:2.2608248400501907e-05 lr:1.5016832974331724e-05 tokens_per_second_per_gpu:7193.886474182759 Step 194 | loss:3.1743580620968714e-05 lr:1.4521463173173965e-05 tokens_per_second_per_gpu:6832.78744376087 Step 195 | loss:4.575397542794235e-05 lr:1.4033009983067452e-05 tokens_per_second_per_gpu:6832.957395738443 Step 196 | loss:0.0003616629110183567 lr:1.3551568628929434e-05 tokens_per_second_per_gpu:7274.633719358859 Step 197 | loss:0.0005494419601745903 lr:1.3077232968705805e-05 tokens_per_second_per_gpu:7193.718198087689 Step 198 | loss:5.0519851356511936e-05 lr:1.2610095475073414e-05 tokens_per_second_per_gpu:6365.04120834734 Step 199 | loss:8.28617557999678e-05 lr:1.2150247217412186e-05 tokens_per_second_per_gpu:6706.968054663239 Step 200 | loss:1.4162425031827297e-05 lr:1.1697777844051105e-05 tokens_per_second_per_gpu:7037.583354093272 Step 201 | loss:4.326807538745925e-05 lr:1.1252775564791024e-05 tokens_per_second_per_gpu:7111.983927392603 Step 202 | loss:2.199582195316907e-05 lr:1.0815327133708015e-05 tokens_per_second_per_gpu:7036.212574642636 Step 203 | loss:0.0011806624243035913 lr:1.0385517832240471e-05 tokens_per_second_per_gpu:7256.835379915137 Step 204 | loss:0.0005066726007498801 lr:9.963431452563332e-06 tokens_per_second_per_gpu:6873.1457740127735 Step 205 | loss:0.002072325674816966 lr:9.549150281252633e-06 tokens_per_second_per_gpu:6694.632430068727 Step 206 | loss:0.0001005070298560895 lr:9.142755083243576e-06 tokens_per_second_per_gpu:7027.013479126797 Step 207 | loss:0.002538858214393258 lr:8.744325086085248e-06 tokens_per_second_per_gpu:7183.746366423666 Step 208 | loss:4.389452442410402e-05 lr:8.353937964495029e-06 tokens_per_second_per_gpu:7183.192814406624 Step 209 | loss:0.00013639482494909316 lr:7.971669825215788e-06 tokens_per_second_per_gpu:7021.408022932253 Step 210 | loss:0.00021397421369329095 lr:7.597595192178702e-06 tokens_per_second_per_gpu:6687.415855488458 Step 211 | loss:0.002936732489615679 lr:7.2317869919746705e-06 tokens_per_second_per_gpu:6740.007373559991 Step 212 | loss:0.0001679590786807239 lr:6.874316539637127e-06 tokens_per_second_per_gpu:6731.600227447955 Step 213 | loss:8.228163642343134e-05 lr:6.52525352473905e-06 tokens_per_second_per_gpu:6852.312799542461 Step 214 | loss:1.3861046681995504e-05 lr:6.184665997806832e-06 tokens_per_second_per_gpu:6833.929874124915 Step 215 | loss:0.0032442801166325808 lr:5.852620357053651e-06 tokens_per_second_per_gpu:7248.546889752173 Step 216 | loss:0.012600164860486984 lr:5.529181335435124e-06 tokens_per_second_per_gpu:6864.4789917479975 Step 217 | loss:0.0008134163799695671 lr:5.214411988029355e-06 tokens_per_second_per_gpu:7178.274120114243 Step 218 | loss:9.964768833015114e-05 lr:4.908373679744316e-06 tokens_per_second_per_gpu:7168.8077070834215 Step 219 | loss:0.001711769262328744 lr:4.611126073354571e-06 tokens_per_second_per_gpu:7144.156669489154 Step 220 | loss:4.248377445037477e-05 lr:4.322727117869951e-06 tokens_per_second_per_gpu:6820.586081373148 Step 221 | loss:2.670160938578192e-05 lr:4.043233037238281e-06 tokens_per_second_per_gpu:6724.551256408319 Step 222 | loss:0.0008727608365006745 lr:3.772698319384349e-06 tokens_per_second_per_gpu:6945.147114413102 Step 223 | loss:0.005545626860111952 lr:3.511175705587433e-06 tokens_per_second_per_gpu:6834.552504166148 Step 224 | loss:2.4884549929993227e-05 lr:3.258716180199278e-06 tokens_per_second_per_gpu:6743.173608305691 Step 225 | loss:5.4829091823194176e-05 lr:3.0153689607045845e-06 tokens_per_second_per_gpu:7144.305402726673 Step 226 | loss:1.8733930119196884e-05 lr:2.7811814881259503e-06 tokens_per_second_per_gpu:7122.762601594169 Step 227 | loss:3.8289570511551574e-05 lr:2.5561994177751737e-06 tokens_per_second_per_gpu:5122.632097586742 Step 228 | loss:0.002775560598820448 lr:2.340466610352654e-06 tokens_per_second_per_gpu:6914.033811574124 Step 229 | loss:0.000505216303281486 lr:2.134025123396638e-06 tokens_per_second_per_gpu:7190.22177616515 Step 230 | loss:3.474711047601886e-05 lr:1.9369152030840556e-06 tokens_per_second_per_gpu:7035.406763807516 Step 231 | loss:0.00017693248810246587 lr:1.7491752763844293e-06 tokens_per_second_per_gpu:6983.550278821847 Step 232 | loss:0.002663969062268734 lr:1.5708419435684462e-06 tokens_per_second_per_gpu:7267.874435093934 Step 233 | loss:1.5446434190380387e-05 lr:1.4019499710726913e-06 tokens_per_second_per_gpu:6810.64968830166 Step 234 | loss:2.35830284509575e-05 lr:1.2425322847218368e-06 tokens_per_second_per_gpu:6985.37212617877 Step 235 | loss:0.000643425970338285 lr:1.0926199633097157e-06 tokens_per_second_per_gpu:7215.846398886284 Step 236 | loss:0.00011912920308532193 lr:9.522422325404235e-07 tokens_per_second_per_gpu:6738.871778992383 Step 237 | loss:0.0037657576613128185 lr:8.214264593307098e-07 tokens_per_second_per_gpu:7212.334403448279 Step 238 | loss:0.0001818757300497964 lr:7.001981464747565e-07 tokens_per_second_per_gpu:7197.828512644593 Step 239 | loss:0.001993682002648711 lr:5.885809276723608e-07 tokens_per_second_per_gpu:6990.298216995204 Step 240 | loss:1.60270938067697e-05 lr:4.865965629214819e-07 tokens_per_second_per_gpu:6923.199150762333 Step 241 | loss:9.389531624037772e-05 lr:3.9426493427611177e-07 tokens_per_second_per_gpu:7163.623510828052 Step 242 | loss:0.0014812041772529483 lr:3.1160404197018154e-07 tokens_per_second_per_gpu:7238.336173159997 Step 243 | loss:1.1227739378227852e-05 lr:2.386300009084408e-07 tokens_per_second_per_gpu:6716.437146109614 Step 244 | loss:6.508493243018165e-05 lr:1.753570375247815e-07 tokens_per_second_per_gpu:7054.218825598797 Step 245 | loss:0.004166287370026112 lr:1.2179748700879012e-07 tokens_per_second_per_gpu:7158.492777321371 Step 246 | loss:2.341901017643977e-05 lr:7.796179090094891e-08 tokens_per_second_per_gpu:6850.401171019304 Step 247 | loss:0.004711752757430077 lr:4.385849505708084e-08 tokens_per_second_per_gpu:7227.439869805944 Step 248 | loss:1.3522277185984422e-05 lr:1.949424798228239e-08 tokens_per_second_per_gpu:7147.485469076724 Step 249 | loss:0.01091584749519825 lr:4.873799534788059e-09 tokens_per_second_per_gpu:6680.285221236753 Step 250 | loss:3.16968908009585e-05 lr:0.0 tokens_per_second_per_gpu:7021.675622598816