Step 1 | loss:0.04097459092736244 lr:4.000000000000001e-06 tokens_per_second_per_gpu:1929.9336284624296 Step 2 | loss:0.014769749715924263 lr:8.000000000000001e-06 tokens_per_second_per_gpu:3219.3184156904404 Step 3 | loss:0.014718251302838326 lr:1.2e-05 tokens_per_second_per_gpu:7238.737220389479 Step 4 | loss:0.022565631195902824 lr:1.6000000000000003e-05 tokens_per_second_per_gpu:6888.636606495882 Step 5 | loss:0.01763095334172249 lr:2e-05 tokens_per_second_per_gpu:7233.267719183705 Step 6 | loss:0.02161341719329357 lr:2.4e-05 tokens_per_second_per_gpu:7177.137039231461 Step 7 | loss:0.033705923706293106 lr:2.8000000000000003e-05 tokens_per_second_per_gpu:1157.473021785543 Step 8 | loss:0.02932225726544857 lr:3.2000000000000005e-05 tokens_per_second_per_gpu:2020.0306840199773 Step 9 | loss:0.022671489045023918 lr:3.6e-05 tokens_per_second_per_gpu:7263.034466232188 Step 10 | loss:0.027695495635271072 lr:4e-05 tokens_per_second_per_gpu:7027.387047963508 Step 11 | loss:0.029824214056134224 lr:4.4000000000000006e-05 tokens_per_second_per_gpu:6618.9331968860015 Step 12 | loss:0.024500330910086632 lr:4.8e-05 tokens_per_second_per_gpu:7208.947978462374 Step 13 | loss:0.024549439549446106 lr:5.2000000000000004e-05 tokens_per_second_per_gpu:6922.626248193618 Step 14 | loss:0.01854652166366577 lr:5.6000000000000006e-05 tokens_per_second_per_gpu:6643.451748250099 Step 15 | loss:0.019052326679229736 lr:6e-05 tokens_per_second_per_gpu:6537.116676432155 Step 16 | loss:0.009060165844857693 lr:6.400000000000001e-05 tokens_per_second_per_gpu:7149.575141117122 Step 17 | loss:0.014165119268000126 lr:6.800000000000001e-05 tokens_per_second_per_gpu:6561.999201241398 Step 18 | loss:0.011772827245295048 lr:7.2e-05 tokens_per_second_per_gpu:6831.357338725334 Step 19 | loss:0.01952959969639778 lr:7.6e-05 tokens_per_second_per_gpu:6602.805831010314 Step 20 | loss:0.031038831919431686 lr:8e-05 tokens_per_second_per_gpu:6846.190036293804 Step 21 | loss:0.008206038735806942 lr:8.4e-05 tokens_per_second_per_gpu:7229.910865364922 Step 22 | loss:0.014941736124455929 lr:8.800000000000001e-05 tokens_per_second_per_gpu:7237.052033286902 Step 23 | loss:0.00923325028270483 lr:9.200000000000001e-05 tokens_per_second_per_gpu:7230.149810494695 Step 24 | loss:0.0060252901166677475 lr:9.6e-05 tokens_per_second_per_gpu:7066.655925444652 Step 25 | loss:0.012783813290297985 lr:0.0001 tokens_per_second_per_gpu:6893.822955763525 Step 26 | loss:0.019153939560055733 lr:9.999512620046522e-05 tokens_per_second_per_gpu:7069.653624211338 Step 27 | loss:0.014044328592717648 lr:9.998050575201771e-05 tokens_per_second_per_gpu:5361.106282008841 Step 28 | loss:0.0023241667076945305 lr:9.995614150494293e-05 tokens_per_second_per_gpu:7191.254482035383 Step 29 | loss:0.004707769490778446 lr:9.992203820909906e-05 tokens_per_second_per_gpu:6929.241116746872 Step 30 | loss:0.006845809984952211 lr:9.987820251299122e-05 tokens_per_second_per_gpu:7280.8475768821445 Step 31 | loss:0.0069190883077681065 lr:9.982464296247522e-05 tokens_per_second_per_gpu:6801.975389702492 Step 32 | loss:0.0051384251564741135 lr:9.976136999909156e-05 tokens_per_second_per_gpu:7167.057376757111 Step 33 | loss:0.006842658389359713 lr:9.968839595802982e-05 tokens_per_second_per_gpu:7224.149826035738 Step 34 | loss:0.008702367544174194 lr:9.96057350657239e-05 tokens_per_second_per_gpu:7161.078762181198 Step 35 | loss:0.004742838907986879 lr:9.951340343707852e-05 tokens_per_second_per_gpu:6488.403887294411 Step 36 | loss:0.019643355160951614 lr:9.941141907232765e-05 tokens_per_second_per_gpu:6524.077379584215 Step 37 | loss:0.018209680914878845 lr:9.929980185352526e-05 tokens_per_second_per_gpu:6861.426506870731 Step 38 | loss:0.0076057990081608295 lr:9.917857354066931e-05 tokens_per_second_per_gpu:6512.712362465692 Step 39 | loss:0.0036715688183903694 lr:9.904775776745958e-05 tokens_per_second_per_gpu:7243.057622047762 Step 40 | loss:0.003805298125371337 lr:9.890738003669029e-05 tokens_per_second_per_gpu:7211.564937003023 Step 41 | loss:0.0017868501599878073 lr:9.875746771527816e-05 tokens_per_second_per_gpu:7243.168315001 Step 42 | loss:0.008847368881106377 lr:9.859805002892732e-05 tokens_per_second_per_gpu:5918.06578670039 Step 43 | loss:0.0030521585140377283 lr:9.842915805643155e-05 tokens_per_second_per_gpu:7250.38614702591 Step 44 | loss:0.0016976961633190513 lr:9.825082472361557e-05 tokens_per_second_per_gpu:7251.043718891135 Step 45 | loss:0.0010969701688736677 lr:9.806308479691595e-05 tokens_per_second_per_gpu:7204.644530019324 Step 46 | loss:0.001503846957348287 lr:9.786597487660337e-05 tokens_per_second_per_gpu:7173.520983237417 Step 47 | loss:0.004120840225368738 lr:9.765953338964735e-05 tokens_per_second_per_gpu:6806.19477925347 Step 48 | loss:0.002081388607621193 lr:9.744380058222483e-05 tokens_per_second_per_gpu:7257.209376767817 Step 49 | loss:0.004583453293889761 lr:9.721881851187406e-05 tokens_per_second_per_gpu:7076.924683862166 Step 50 | loss:0.001161870313808322 lr:9.698463103929542e-05 tokens_per_second_per_gpu:7225.351090462347 Step 51 | loss:0.003230300033465028 lr:9.674128381980072e-05 tokens_per_second_per_gpu:6820.775399736879 Step 52 | loss:0.0018242279766127467 lr:9.648882429441257e-05 tokens_per_second_per_gpu:7175.249285496814 Step 53 | loss:0.0013441737974062562 lr:9.622730168061567e-05 tokens_per_second_per_gpu:7234.903235894888 Step 54 | loss:0.001810164307244122 lr:9.595676696276172e-05 tokens_per_second_per_gpu:6522.547214502252 Step 55 | loss:0.0014648062642663717 lr:9.567727288213005e-05 tokens_per_second_per_gpu:6640.046580235724 Step 56 | loss:0.000436306931078434 lr:9.538887392664544e-05 tokens_per_second_per_gpu:4999.372928681108 Step 57 | loss:0.00746438093483448 lr:9.50916263202557e-05 tokens_per_second_per_gpu:6539.169092230806 Step 58 | loss:0.0005420186789706349 lr:9.478558801197065e-05 tokens_per_second_per_gpu:7234.072067469529 Step 59 | loss:0.0006392847280949354 lr:9.447081866456489e-05 tokens_per_second_per_gpu:7260.927656165604 Step 60 | loss:0.002469714032486081 lr:9.414737964294636e-05 tokens_per_second_per_gpu:7251.862728997451 Step 61 | loss:0.001661772606894374 lr:9.381533400219318e-05 tokens_per_second_per_gpu:7106.691783127853 Step 62 | loss:0.008740504272282124 lr:9.347474647526095e-05 tokens_per_second_per_gpu:6519.812011572131 Step 63 | loss:0.0009972653351724148 lr:9.312568346036288e-05 tokens_per_second_per_gpu:7294.210925748909 Step 64 | loss:0.004283817019313574 lr:9.276821300802534e-05 tokens_per_second_per_gpu:7024.292541193249 Step 65 | loss:0.002201689640060067 lr:9.24024048078213e-05 tokens_per_second_per_gpu:6817.285425325651 Step 66 | loss:0.002990669570863247 lr:9.202833017478422e-05 tokens_per_second_per_gpu:6920.630358741347 Step 67 | loss:0.0015884492313489318 lr:9.164606203550497e-05 tokens_per_second_per_gpu:7196.1344747772555 Step 68 | loss:0.0012366349110379815 lr:9.125567491391476e-05 tokens_per_second_per_gpu:7266.56836624248 Step 69 | loss:0.0014715156285092235 lr:9.085724491675642e-05 tokens_per_second_per_gpu:7143.154267530744 Step 70 | loss:0.010383970104157925 lr:9.045084971874738e-05 tokens_per_second_per_gpu:6796.642938933161 Step 71 | loss:0.005689555313438177 lr:9.003656854743667e-05 tokens_per_second_per_gpu:6903.228334748435 Step 72 | loss:0.0019345164764672518 lr:8.961448216775954e-05 tokens_per_second_per_gpu:6594.229378805127 Step 73 | loss:0.00325796683318913 lr:8.9184672866292e-05 tokens_per_second_per_gpu:6858.045488723956 Step 74 | loss:0.0005512746283784509 lr:8.874722443520899e-05 tokens_per_second_per_gpu:7134.242517208104 Step 75 | loss:0.0017566350288689137 lr:8.83022221559489e-05 tokens_per_second_per_gpu:7163.784456728544 Step 76 | loss:0.006619305349886417 lr:8.784975278258783e-05 tokens_per_second_per_gpu:6463.9294125116185 Step 77 | loss:0.002156282076612115 lr:8.73899045249266e-05 tokens_per_second_per_gpu:6561.807199309982 Step 78 | loss:0.0029460187070071697 lr:8.692276703129421e-05 tokens_per_second_per_gpu:7276.726388092638 Step 79 | loss:0.000772997154854238 lr:8.644843137107059e-05 tokens_per_second_per_gpu:6797.037110602544 Step 80 | loss:0.0027902317233383656 lr:8.596699001693255e-05 tokens_per_second_per_gpu:7274.191656350864 Step 81 | loss:0.0012049961369484663 lr:8.547853682682604e-05 tokens_per_second_per_gpu:7250.300041425546 Step 82 | loss:0.0047317733988165855 lr:8.498316702566828e-05 tokens_per_second_per_gpu:6502.021727314682 Step 83 | loss:0.0028366215992718935 lr:8.44809771867835e-05 tokens_per_second_per_gpu:6583.573279394692 Step 84 | loss:0.002422972582280636 lr:8.397206521307584e-05 tokens_per_second_per_gpu:6544.601498241148 Step 85 | loss:0.0010934899328276515 lr:8.345653031794292e-05 tokens_per_second_per_gpu:7211.431468699534 Step 86 | loss:0.003059197450056672 lr:8.293447300593402e-05 tokens_per_second_per_gpu:7049.56440550115 Step 87 | loss:0.0037902037147432566 lr:8.240599505315655e-05 tokens_per_second_per_gpu:6555.62500875138 Step 88 | loss:0.00697923032566905 lr:8.18711994874345e-05 tokens_per_second_per_gpu:6845.403748129954 Step 89 | loss:0.0007215198129415512 lr:8.133019056822304e-05 tokens_per_second_per_gpu:7161.721332510466 Step 90 | loss:0.004373953677713871 lr:8.07830737662829e-05 tokens_per_second_per_gpu:6595.270618469162 Step 91 | loss:0.0006784538854844868 lr:8.022995574311876e-05 tokens_per_second_per_gpu:7208.272511707808 Step 92 | loss:0.0005650371313095093 lr:7.967094433018508e-05 tokens_per_second_per_gpu:7214.541542290585 Step 93 | loss:0.0033636679872870445 lr:7.910614850786448e-05 tokens_per_second_per_gpu:6575.787513689174 Step 94 | loss:0.0035964183043688536 lr:7.85356783842216e-05 tokens_per_second_per_gpu:7224.596818879392 Step 95 | loss:0.0012116474099457264 lr:7.795964517353735e-05 tokens_per_second_per_gpu:6799.804031957816 Step 96 | loss:0.0006790937040932477 lr:7.737816117462752e-05 tokens_per_second_per_gpu:7225.533209642582 Step 97 | loss:0.0013626653235405684 lr:7.679133974894983e-05 tokens_per_second_per_gpu:7264.918931504713 Step 98 | loss:0.0025007606018334627 lr:7.619929529850397e-05 tokens_per_second_per_gpu:7220.198167351506 Step 99 | loss:0.0015476488042622805 lr:7.560214324352858e-05 tokens_per_second_per_gpu:7230.415947614678 Step 100 | loss:0.0031118157785385847 lr:7.500000000000001e-05 tokens_per_second_per_gpu:6793.105640133401 Step 101 | loss:0.0006266957498155534 lr:7.439298295693665e-05 tokens_per_second_per_gpu:7151.780788679229 Step 102 | loss:0.0012741275131702423 lr:7.378121045351378e-05 tokens_per_second_per_gpu:6893.078997278256 Step 103 | loss:0.0006419572164304554 lr:7.316480175599309e-05 tokens_per_second_per_gpu:7070.596929761773 Step 104 | loss:0.0006927671493031085 lr:7.254387703447154e-05 tokens_per_second_per_gpu:6846.961405634795 Step 105 | loss:0.002119016367942095 lr:7.191855733945387e-05 tokens_per_second_per_gpu:6887.51865687184 Step 106 | loss:0.0017365614185109735 lr:7.128896457825364e-05 tokens_per_second_per_gpu:6536.15132288285 Step 107 | loss:0.001290334272198379 lr:7.06552214912271e-05 tokens_per_second_per_gpu:7085.04337260806 Step 108 | loss:0.0016466735396534204 lr:7.001745162784477e-05 tokens_per_second_per_gpu:7224.168881224529 Step 109 | loss:0.0005937103414908051 lr:6.937577932260515e-05 tokens_per_second_per_gpu:6798.889324885552 Step 110 | loss:0.0005489122704602778 lr:6.873032967079561e-05 tokens_per_second_per_gpu:6805.663409177833 Step 111 | loss:0.001645527663640678 lr:6.808122850410461e-05 tokens_per_second_per_gpu:6571.836348819957 Step 112 | loss:0.0023427929263561964 lr:6.742860236609077e-05 tokens_per_second_per_gpu:6635.114597556468 Step 113 | loss:0.0021976488642394543 lr:6.677257848751277e-05 tokens_per_second_per_gpu:6930.643425590084 Step 114 | loss:0.004333576187491417 lr:6.611328476152557e-05 tokens_per_second_per_gpu:7137.7199765154155 Step 115 | loss:0.0005143475718796253 lr:6.545084971874738e-05 tokens_per_second_per_gpu:7239.883584102567 Step 116 | loss:0.00018481251026969403 lr:6.478540250220234e-05 tokens_per_second_per_gpu:7147.372635964062 Step 117 | loss:0.0035171585623174906 lr:6.411707284214384e-05 tokens_per_second_per_gpu:6741.65244401723 Step 118 | loss:0.0017174758249893785 lr:6.344599103076329e-05 tokens_per_second_per_gpu:6618.453183019406 Step 119 | loss:0.0007142869872041047 lr:6.277228789678953e-05 tokens_per_second_per_gpu:7249.748753418584 Step 120 | loss:0.00041562062688171864 lr:6.209609477998338e-05 tokens_per_second_per_gpu:6765.568218809548 Step 121 | loss:0.0023718439042568207 lr:6.141754350553279e-05 tokens_per_second_per_gpu:7241.637041740242 Step 122 | loss:0.003506784327328205 lr:6.073676635835317e-05 tokens_per_second_per_gpu:7067.507963504398 Step 123 | loss:0.0009584081708453596 lr:6.005389605729824e-05 tokens_per_second_per_gpu:7300.350329468501 Step 124 | loss:0.0014651136007159948 lr:5.9369065729286245e-05 tokens_per_second_per_gpu:6865.81767377466 Step 125 | loss:0.005649914965033531 lr:5.868240888334653e-05 tokens_per_second_per_gpu:6913.447417309613 Step 126 | loss:0.0005537703982554376 lr:5.799405938459175e-05 tokens_per_second_per_gpu:7192.05972399213 Step 127 | loss:0.00029012461891397834 lr:5.730415142812059e-05 tokens_per_second_per_gpu:7129.579407255549 Step 128 | loss:0.0016071032732725143 lr:5.661281951285613e-05 tokens_per_second_per_gpu:6596.937317414032 Step 129 | loss:0.0007958397036418319 lr:5.5920198415325064e-05 tokens_per_second_per_gpu:7073.275829334385 Step 130 | loss:0.0022363944444805384 lr:5.522642316338268e-05 tokens_per_second_per_gpu:6498.64208710475 Step 131 | loss:0.002599939238280058 lr:5.453162900988902e-05 tokens_per_second_per_gpu:6542.051810296333 Step 132 | loss:0.0017267565708607435 lr:5.383595140634093e-05 tokens_per_second_per_gpu:6667.16470070388 Step 133 | loss:0.0013555341865867376 lr:5.313952597646568e-05 tokens_per_second_per_gpu:7208.055666203118 Step 134 | loss:0.00019527475524228066 lr:5.244248848978067e-05 tokens_per_second_per_gpu:7156.214162069381 Step 135 | loss:0.0008878572843968868 lr:5.174497483512506e-05 tokens_per_second_per_gpu:7126.11681690913 Step 136 | loss:0.001495590666308999 lr:5.104712099416785e-05 tokens_per_second_per_gpu:7122.411333753985 Step 137 | loss:0.000273075420409441 lr:5.034906301489808e-05 tokens_per_second_per_gpu:7221.362055735714 Step 138 | loss:0.0014533718349412084 lr:4.965093698510193e-05 tokens_per_second_per_gpu:7195.307507482834 Step 139 | loss:0.0014078562380746007 lr:4.895287900583216e-05 tokens_per_second_per_gpu:6474.009117832569 Step 140 | loss:0.0006170913693495095 lr:4.825502516487497e-05 tokens_per_second_per_gpu:6656.3975287649555 Step 141 | loss:0.0019269072217866778 lr:4.755751151021934e-05 tokens_per_second_per_gpu:6550.281178548433 Step 142 | loss:0.0011296696029603481 lr:4.6860474023534335e-05 tokens_per_second_per_gpu:6806.817189183881 Step 143 | loss:0.0009911612141877413 lr:4.616404859365907e-05 tokens_per_second_per_gpu:7110.399792457167 Step 144 | loss:0.0009444269235245883 lr:4.5468370990111006e-05 tokens_per_second_per_gpu:6925.340177641164 Step 145 | loss:0.0006295506609603763 lr:4.477357683661734e-05 tokens_per_second_per_gpu:6517.118041502331 Step 146 | loss:0.0003473514807410538 lr:4.407980158467495e-05 tokens_per_second_per_gpu:6857.706238450775 Step 147 | loss:0.00033395804348401725 lr:4.3387180487143876e-05 tokens_per_second_per_gpu:6797.584853351243 Step 148 | loss:0.0005998439737595618 lr:4.269584857187943e-05 tokens_per_second_per_gpu:7210.268758227153 Step 149 | loss:0.001365359523333609 lr:4.2005940615408264e-05 tokens_per_second_per_gpu:7212.00797799857 Step 150 | loss:0.0017841528169810772 lr:4.131759111665349e-05 tokens_per_second_per_gpu:6872.316876927345 Step 151 | loss:0.000666565727442503 lr:4.063093427071376e-05 tokens_per_second_per_gpu:7248.669915195027 Step 152 | loss:0.0013103943783789873 lr:3.9946103942701777e-05 tokens_per_second_per_gpu:6739.249778698113 Step 153 | loss:0.002656620694324374 lr:3.926323364164684e-05 tokens_per_second_per_gpu:6553.565604970934 Step 154 | loss:0.0004526124685071409 lr:3.858245649446721e-05 tokens_per_second_per_gpu:7205.36925737935 Step 155 | loss:0.0009877069387584925 lr:3.790390522001662e-05 tokens_per_second_per_gpu:6847.804197330822 Step 156 | loss:0.0011117910034954548 lr:3.7227712103210486e-05 tokens_per_second_per_gpu:6854.064761024538 Step 157 | loss:0.0021748177241533995 lr:3.655400896923672e-05 tokens_per_second_per_gpu:6557.990892010329 Step 158 | loss:0.00019791505474131554 lr:3.588292715785617e-05 tokens_per_second_per_gpu:7138.991147850895 Step 159 | loss:0.00023612374207004905 lr:3.5214597497797684e-05 tokens_per_second_per_gpu:7268.447373810991 Step 160 | loss:0.0005414762999862432 lr:3.4549150281252636e-05 tokens_per_second_per_gpu:7267.866066163293 Step 161 | loss:0.0004933732561767101 lr:3.388671523847445e-05 tokens_per_second_per_gpu:6870.044567872678 Step 162 | loss:0.0018356043146923184 lr:3.322742151248725e-05 tokens_per_second_per_gpu:6519.37654221993 Step 163 | loss:0.00035462703090161085 lr:3.257139763390925e-05 tokens_per_second_per_gpu:7207.367385637251 Step 164 | loss:0.000855001388117671 lr:3.1918771495895396e-05 tokens_per_second_per_gpu:7067.597134971686 Step 165 | loss:0.0007439227192662656 lr:3.12696703292044e-05 tokens_per_second_per_gpu:6895.273812811788 Step 166 | loss:0.0003836042887996882 lr:3.062422067739485e-05 tokens_per_second_per_gpu:6860.803065563865 Step 167 | loss:0.0006375150405801833 lr:2.9982548372155263e-05 tokens_per_second_per_gpu:6855.635145197796 Step 168 | loss:0.0010679884580895305 lr:2.934477850877292e-05 tokens_per_second_per_gpu:6806.132570351503 Step 169 | loss:0.00030187994707375765 lr:2.8711035421746367e-05 tokens_per_second_per_gpu:6591.395532667738 Step 170 | loss:0.0014069299213588238 lr:2.8081442660546125e-05 tokens_per_second_per_gpu:6611.600880540396 Step 171 | loss:0.0003865704347845167 lr:2.7456122965528475e-05 tokens_per_second_per_gpu:6875.933808519128 Step 172 | loss:0.00046160249621607363 lr:2.6835198244006927e-05 tokens_per_second_per_gpu:6856.641084271552 Step 173 | loss:0.00022469396935775876 lr:2.6218789546486234e-05 tokens_per_second_per_gpu:7233.114896257279 Step 174 | loss:0.0002716211602091789 lr:2.560701704306336e-05 tokens_per_second_per_gpu:7236.478340785872 Step 175 | loss:0.0004086577973794192 lr:2.500000000000001e-05 tokens_per_second_per_gpu:6905.308811129988 Step 176 | loss:0.0005348652484826744 lr:2.4397856756471432e-05 tokens_per_second_per_gpu:6847.505971347445 Step 177 | loss:0.000541216169949621 lr:2.3800704701496053e-05 tokens_per_second_per_gpu:6521.636608842507 Step 178 | loss:0.0005779328057542443 lr:2.3208660251050158e-05 tokens_per_second_per_gpu:7185.774722540906 Step 179 | loss:0.0002126227627741173 lr:2.2621838825372493e-05 tokens_per_second_per_gpu:7212.482604647085 Step 180 | loss:0.0014459057711064816 lr:2.2040354826462668e-05 tokens_per_second_per_gpu:6940.793528443122 Step 181 | loss:0.0007859404431656003 lr:2.1464321615778422e-05 tokens_per_second_per_gpu:7257.990425268565 Step 182 | loss:0.0025287482421845198 lr:2.0893851492135537e-05 tokens_per_second_per_gpu:7271.376513866403 Step 183 | loss:0.00036082378937862813 lr:2.0329055669814934e-05 tokens_per_second_per_gpu:6825.521890599478 Step 184 | loss:0.00020927691366523504 lr:1.977004425688126e-05 tokens_per_second_per_gpu:7238.902734288074 Step 185 | loss:0.0012729590525850654 lr:1.9216926233717085e-05 tokens_per_second_per_gpu:7071.500534832078 Step 186 | loss:0.00022643858392257243 lr:1.866980943177699e-05 tokens_per_second_per_gpu:7215.806613694495 Step 187 | loss:0.0007641566335223615 lr:1.8128800512565513e-05 tokens_per_second_per_gpu:7063.2272524668815 Step 188 | loss:0.0021792433690279722 lr:1.7594004946843456e-05 tokens_per_second_per_gpu:6541.8888214409135 Step 189 | loss:0.0011961536947637796 lr:1.7065526994065973e-05 tokens_per_second_per_gpu:6868.248776721679 Step 190 | loss:0.0003689381410367787 lr:1.6543469682057106e-05 tokens_per_second_per_gpu:6904.273726105801 Step 191 | loss:0.0006264817784540355 lr:1.602793478692419e-05 tokens_per_second_per_gpu:6902.09090870066 Step 192 | loss:0.0002761622308753431 lr:1.551902281321651e-05 tokens_per_second_per_gpu:7217.5033154976045 Step 193 | loss:0.0010080195497721434 lr:1.5016832974331724e-05 tokens_per_second_per_gpu:7214.676264778741 Step 194 | loss:0.0022333762608468533 lr:1.4521463173173965e-05 tokens_per_second_per_gpu:6563.721552000728 Step 195 | loss:0.00026827046531252563 lr:1.4033009983067452e-05 tokens_per_second_per_gpu:7248.636941119909 Step 196 | loss:0.00022822435130365193 lr:1.3551568628929434e-05 tokens_per_second_per_gpu:7120.3320818832035 Step 197 | loss:0.002357832621783018 lr:1.3077232968705805e-05 tokens_per_second_per_gpu:6490.701309515714 Step 198 | loss:0.00042384781409054995 lr:1.2610095475073414e-05 tokens_per_second_per_gpu:5261.559665242218 Step 199 | loss:0.0008428985602222383 lr:1.2150247217412186e-05 tokens_per_second_per_gpu:7261.984967652193 Step 200 | loss:0.0014672616962343454 lr:1.1697777844051105e-05 tokens_per_second_per_gpu:6940.547403335431 Step 201 | loss:0.0002568376949056983 lr:1.1252775564791024e-05 tokens_per_second_per_gpu:7255.070156881685 Step 202 | loss:0.0007359752780757844 lr:1.0815327133708015e-05 tokens_per_second_per_gpu:7059.312045607327 Step 203 | loss:0.000589964387472719 lr:1.0385517832240471e-05 tokens_per_second_per_gpu:7252.825424272584 Step 204 | loss:0.0005478272214531898 lr:9.963431452563332e-06 tokens_per_second_per_gpu:7244.846287883003 Step 205 | loss:0.0012679924257099628 lr:9.549150281252633e-06 tokens_per_second_per_gpu:6911.062462583241 Step 206 | loss:0.0020379372872412205 lr:9.142755083243576e-06 tokens_per_second_per_gpu:6542.437010847029 Step 207 | loss:0.001116395927965641 lr:8.744325086085248e-06 tokens_per_second_per_gpu:6877.823222384296 Step 208 | loss:0.0008609795477241278 lr:8.353937964495029e-06 tokens_per_second_per_gpu:7233.180842785249 Step 209 | loss:0.0012457803823053837 lr:7.971669825215788e-06 tokens_per_second_per_gpu:6929.84933405184 Step 210 | loss:0.00019902923668269068 lr:7.597595192178702e-06 tokens_per_second_per_gpu:7233.394646863605 Step 211 | loss:0.0007209706236608326 lr:7.2317869919746705e-06 tokens_per_second_per_gpu:7263.38434228604 Step 212 | loss:0.00022702575370203704 lr:6.874316539637127e-06 tokens_per_second_per_gpu:7184.017084708315 Step 213 | loss:0.0017991185886785388 lr:6.52525352473905e-06 tokens_per_second_per_gpu:7105.007161528755 Step 214 | loss:0.00017719795869197696 lr:6.184665997806832e-06 tokens_per_second_per_gpu:7141.6183127952145 Step 215 | loss:0.0001612526539247483 lr:5.852620357053651e-06 tokens_per_second_per_gpu:7130.5913629349325 Step 216 | loss:0.001316193025559187 lr:5.529181335435124e-06 tokens_per_second_per_gpu:6844.353171237 Step 217 | loss:0.002092335605993867 lr:5.214411988029355e-06 tokens_per_second_per_gpu:6527.915856885188 Step 218 | loss:0.000180719856871292 lr:4.908373679744316e-06 tokens_per_second_per_gpu:7151.045492059814 Step 219 | loss:0.0010880992049351335 lr:4.611126073354571e-06 tokens_per_second_per_gpu:6792.09470996906 Step 220 | loss:0.00046239123912528157 lr:4.322727117869951e-06 tokens_per_second_per_gpu:6779.08951709905 Step 221 | loss:0.00037844982580281794 lr:4.043233037238281e-06 tokens_per_second_per_gpu:6806.416221743766 Step 222 | loss:0.00018761404498945922 lr:3.772698319384349e-06 tokens_per_second_per_gpu:7108.794151594603 Step 223 | loss:0.0018128042574971914 lr:3.511175705587433e-06 tokens_per_second_per_gpu:7084.0108220471075 Step 224 | loss:0.0012525536585599184 lr:3.258716180199278e-06 tokens_per_second_per_gpu:6811.186054138005 Step 225 | loss:0.0004694873932749033 lr:3.0153689607045845e-06 tokens_per_second_per_gpu:6829.286898306396 Step 226 | loss:0.0002738080220296979 lr:2.7811814881259503e-06 tokens_per_second_per_gpu:7193.513077656843 Step 227 | loss:0.0002255330909974873 lr:2.5561994177751737e-06 tokens_per_second_per_gpu:6506.523321958697 Step 228 | loss:0.0005278878379613161 lr:2.340466610352654e-06 tokens_per_second_per_gpu:6775.532503758884 Step 229 | loss:0.0015068536158651114 lr:2.134025123396638e-06 tokens_per_second_per_gpu:7055.198667871743 Step 230 | loss:0.0002130332140950486 lr:1.9369152030840556e-06 tokens_per_second_per_gpu:7222.105826498038 Step 231 | loss:0.0008820161456242204 lr:1.7491752763844293e-06 tokens_per_second_per_gpu:7279.268927804213 Step 232 | loss:0.0004630690673366189 lr:1.5708419435684462e-06 tokens_per_second_per_gpu:7261.765911417392 Step 233 | loss:0.0010652008932083845 lr:1.4019499710726913e-06 tokens_per_second_per_gpu:6877.176542621275 Step 234 | loss:0.0007960734074003994 lr:1.2425322847218368e-06 tokens_per_second_per_gpu:7079.256672853601 Step 235 | loss:0.0009424385498277843 lr:1.0926199633097157e-06 tokens_per_second_per_gpu:6736.652467207448 Step 236 | loss:0.0006260488298721611 lr:9.522422325404235e-07 tokens_per_second_per_gpu:7255.970369421284 Step 237 | loss:0.002719552256166935 lr:8.214264593307098e-07 tokens_per_second_per_gpu:6503.509395086374 Step 238 | loss:0.0007250621565617621 lr:7.001981464747565e-07 tokens_per_second_per_gpu:6908.912779309659 Step 239 | loss:0.0013547075213864446 lr:5.885809276723608e-07 tokens_per_second_per_gpu:7096.380307028733 Step 240 | loss:0.0010835705325007439 lr:4.865965629214819e-07 tokens_per_second_per_gpu:7127.676168174007 Step 241 | loss:0.00021956254204269499 lr:3.9426493427611177e-07 tokens_per_second_per_gpu:7274.116822316814 Step 242 | loss:0.0020217241253703833 lr:3.1160404197018154e-07 tokens_per_second_per_gpu:6605.699153302372 Step 243 | loss:0.0006995209841988981 lr:2.386300009084408e-07 tokens_per_second_per_gpu:7215.44225702703 Step 244 | loss:0.0015042799059301615 lr:1.753570375247815e-07 tokens_per_second_per_gpu:6612.210151184028 Step 245 | loss:0.002229914302006364 lr:1.2179748700879012e-07 tokens_per_second_per_gpu:6553.941622597413 Step 246 | loss:0.00036404465208761394 lr:7.796179090094891e-08 tokens_per_second_per_gpu:6934.620194335123 Step 247 | loss:0.0006328472518362105 lr:4.385849505708084e-08 tokens_per_second_per_gpu:6540.294183617425 Step 248 | loss:0.00026066755526699126 lr:1.949424798228239e-08 tokens_per_second_per_gpu:7233.4023012583375 Step 249 | loss:0.00023298674204852432 lr:4.873799534788059e-09 tokens_per_second_per_gpu:7261.086747602384 Step 250 | loss:0.0004272110527381301 lr:0.0 tokens_per_second_per_gpu:7264.130641877529