Step 1 | loss:0.044024672359228134 lr:4.000000000000001e-06 tokens_per_second_per_gpu:2491.6973629520467 Step 2 | loss:0.05892680212855339 lr:8.000000000000001e-06 tokens_per_second_per_gpu:3974.2111776128972 Step 3 | loss:0.04225453361868858 lr:1.2e-05 tokens_per_second_per_gpu:3905.370467421552 Step 4 | loss:0.17764173448085785 lr:1.6000000000000003e-05 tokens_per_second_per_gpu:1551.9643215537606 Step 5 | loss:0.037487227469682693 lr:2e-05 tokens_per_second_per_gpu:7130.939572168644 Step 6 | loss:0.02036396972835064 lr:2.4e-05 tokens_per_second_per_gpu:7011.3341117074515 Step 7 | loss:0.05785895884037018 lr:2.8000000000000003e-05 tokens_per_second_per_gpu:6912.113823343527 Step 8 | loss:0.07742859423160553 lr:3.2000000000000005e-05 tokens_per_second_per_gpu:6956.913493790545 Step 9 | loss:0.03660118579864502 lr:3.6e-05 tokens_per_second_per_gpu:7061.035461267933 Step 10 | loss:0.04339168220758438 lr:4e-05 tokens_per_second_per_gpu:3193.9909894637226 Step 11 | loss:0.03603703901171684 lr:4.4000000000000006e-05 tokens_per_second_per_gpu:7237.857296584382 Step 12 | loss:0.054984547197818756 lr:4.8e-05 tokens_per_second_per_gpu:6993.441059839511 Step 13 | loss:0.013416779227554798 lr:5.2000000000000004e-05 tokens_per_second_per_gpu:7072.765016051136 Step 14 | loss:0.005032726563513279 lr:5.6000000000000006e-05 tokens_per_second_per_gpu:7127.475165099142 Step 15 | loss:0.01390102505683899 lr:6e-05 tokens_per_second_per_gpu:7109.448269370965 Step 16 | loss:0.0136568583548069 lr:6.400000000000001e-05 tokens_per_second_per_gpu:1982.3982249786534 Step 17 | loss:0.0008882262627594173 lr:6.800000000000001e-05 tokens_per_second_per_gpu:7250.524389681674 Step 18 | loss:0.0032167285680770874 lr:7.2e-05 tokens_per_second_per_gpu:7213.540355055951 Step 19 | loss:0.0025759534910321236 lr:7.6e-05 tokens_per_second_per_gpu:7121.0069379952865 Step 20 | loss:0.005988647695630789 lr:8e-05 tokens_per_second_per_gpu:2547.6257517383906 Step 21 | loss:0.0008513733628205955 lr:8.4e-05 tokens_per_second_per_gpu:7191.71777409903 Step 22 | loss:0.002248356817290187 lr:8.800000000000001e-05 tokens_per_second_per_gpu:7035.1764218136495 Step 23 | loss:0.0009723395924083889 lr:9.200000000000001e-05 tokens_per_second_per_gpu:7080.389898625971 Step 24 | loss:0.000236137057072483 lr:9.6e-05 tokens_per_second_per_gpu:7020.606339376537 Step 25 | loss:0.0003219555364921689 lr:0.0001 tokens_per_second_per_gpu:7184.303569325483 Step 26 | loss:0.00020240044977981597 lr:9.999512620046522e-05 tokens_per_second_per_gpu:7203.458892320161 Step 27 | loss:0.0001260352582903579 lr:9.998050575201771e-05 tokens_per_second_per_gpu:6809.96120938708 Step 28 | loss:6.977388693485409e-05 lr:9.995614150494293e-05 tokens_per_second_per_gpu:7104.9650664705705 Step 29 | loss:1.6838406736496836e-05 lr:9.992203820909906e-05 tokens_per_second_per_gpu:7140.525330720113 Step 30 | loss:0.00025073738652281463 lr:9.987820251299122e-05 tokens_per_second_per_gpu:7200.059353063329 Step 31 | loss:1.950736304934253e-06 lr:9.982464296247522e-05 tokens_per_second_per_gpu:2762.464688903786 Step 32 | loss:4.355678811407415e-06 lr:9.976136999909156e-05 tokens_per_second_per_gpu:7077.602903719109 Step 33 | loss:0.0002980708086397499 lr:9.968839595802982e-05 tokens_per_second_per_gpu:7205.392617148052 Step 34 | loss:5.626531219604658e-06 lr:9.96057350657239e-05 tokens_per_second_per_gpu:7055.941632262539 Step 35 | loss:0.0689399391412735 lr:9.951340343707852e-05 tokens_per_second_per_gpu:7005.982858059566 Step 36 | loss:2.136021066689864e-06 lr:9.941141907232765e-05 tokens_per_second_per_gpu:7095.48050132196 Step 37 | loss:0.0004781906900461763 lr:9.929980185352526e-05 tokens_per_second_per_gpu:6924.668370821682 Step 38 | loss:0.0005276959855109453 lr:9.917857354066931e-05 tokens_per_second_per_gpu:7064.710956998861 Step 39 | loss:4.42290365754161e-05 lr:9.904775776745958e-05 tokens_per_second_per_gpu:7088.084264304419 Step 40 | loss:0.002827366581186652 lr:9.890738003669029e-05 tokens_per_second_per_gpu:6966.313383062993 Step 41 | loss:3.2591353829047875e-06 lr:9.875746771527816e-05 tokens_per_second_per_gpu:7104.248864905117 Step 42 | loss:4.0894756239140406e-05 lr:9.859805002892732e-05 tokens_per_second_per_gpu:1164.9711553193358 Step 43 | loss:2.042909954980132e-06 lr:9.842915805643155e-05 tokens_per_second_per_gpu:7025.651422634611 Step 44 | loss:5.1866086323570926e-06 lr:9.825082472361557e-05 tokens_per_second_per_gpu:6935.558790612978 Step 45 | loss:1.643649852667295e-06 lr:9.806308479691595e-05 tokens_per_second_per_gpu:7007.716467709001 Step 46 | loss:4.22128823629464e-06 lr:9.786597487660337e-05 tokens_per_second_per_gpu:7030.722281930516 Step 47 | loss:1.5117912880668882e-05 lr:9.765953338964735e-05 tokens_per_second_per_gpu:6557.16775418851 Step 48 | loss:1.2553706255857833e-05 lr:9.744380058222483e-05 tokens_per_second_per_gpu:6638.369950492554 Step 49 | loss:7.3374003477511e-06 lr:9.721881851187406e-05 tokens_per_second_per_gpu:1663.003343042255 Step 50 | loss:2.4675407985341735e-05 lr:9.698463103929542e-05 tokens_per_second_per_gpu:7089.915264859427 Step 51 | loss:9.96050403045956e-06 lr:9.674128381980072e-05 tokens_per_second_per_gpu:7138.593417947804 Step 52 | loss:0.00020252492686267942 lr:9.648882429441257e-05 tokens_per_second_per_gpu:7093.839654869536 Step 53 | loss:0.09148562699556351 lr:9.622730168061567e-05 tokens_per_second_per_gpu:6875.4494319134465 Step 54 | loss:1.147508191934321e-05 lr:9.595676696276172e-05 tokens_per_second_per_gpu:7093.948313889124 Step 55 | loss:2.533208862587344e-05 lr:9.567727288213005e-05 tokens_per_second_per_gpu:6897.8826465700495 Step 56 | loss:6.397398919943953e-06 lr:9.538887392664544e-05 tokens_per_second_per_gpu:6289.281784075682 Step 57 | loss:4.083194289705716e-05 lr:9.50916263202557e-05 tokens_per_second_per_gpu:6786.677966970842 Step 58 | loss:7.382668172795093e-06 lr:9.478558801197065e-05 tokens_per_second_per_gpu:7149.280927403911 Step 59 | loss:3.2811499295348767e-06 lr:9.447081866456489e-05 tokens_per_second_per_gpu:7141.383111775478 Step 60 | loss:6.9066634750925e-05 lr:9.414737964294636e-05 tokens_per_second_per_gpu:6513.9318694201775 Step 61 | loss:1.410721324646147e-05 lr:9.381533400219318e-05 tokens_per_second_per_gpu:3183.585154764245 Step 62 | loss:1.873036308097653e-05 lr:9.347474647526095e-05 tokens_per_second_per_gpu:7024.102742524136 Step 63 | loss:3.535393625497818e-05 lr:9.312568346036288e-05 tokens_per_second_per_gpu:6920.730649585629 Step 64 | loss:6.71536399750039e-05 lr:9.276821300802534e-05 tokens_per_second_per_gpu:6870.022287696528 Step 65 | loss:2.3371201677946374e-05 lr:9.24024048078213e-05 tokens_per_second_per_gpu:7102.3208098111545 Step 66 | loss:4.80350126963458e-06 lr:9.202833017478422e-05 tokens_per_second_per_gpu:7149.835815077596 Step 67 | loss:8.619115760666318e-06 lr:9.164606203550497e-05 tokens_per_second_per_gpu:7067.735036527763 Step 68 | loss:0.001971589867025614 lr:9.125567491391476e-05 tokens_per_second_per_gpu:7170.884678860327 Step 69 | loss:2.3260561647475697e-05 lr:9.085724491675642e-05 tokens_per_second_per_gpu:7088.57508957724 Step 70 | loss:0.07770252227783203 lr:9.045084971874738e-05 tokens_per_second_per_gpu:6995.339749223063 Step 71 | loss:3.7465426430571824e-05 lr:9.003656854743667e-05 tokens_per_second_per_gpu:6961.616681131454 Step 72 | loss:5.002773832529783e-05 lr:8.961448216775954e-05 tokens_per_second_per_gpu:6752.329964849588 Step 73 | loss:1.054703079717001e-05 lr:8.9184672866292e-05 tokens_per_second_per_gpu:7141.04100419206 Step 74 | loss:0.06129450723528862 lr:8.874722443520899e-05 tokens_per_second_per_gpu:6972.27620878167 Step 75 | loss:4.6133030991768464e-05 lr:8.83022221559489e-05 tokens_per_second_per_gpu:7008.612537455016 Step 76 | loss:4.6424112952081487e-05 lr:8.784975278258783e-05 tokens_per_second_per_gpu:7025.140425388787 Step 77 | loss:0.0019122450612485409 lr:8.73899045249266e-05 tokens_per_second_per_gpu:6539.73691951206 Step 78 | loss:1.744095243338961e-05 lr:8.692276703129421e-05 tokens_per_second_per_gpu:7112.092177721466 Step 79 | loss:4.13628549722489e-05 lr:8.644843137107059e-05 tokens_per_second_per_gpu:6536.868072506976 Step 80 | loss:6.11851064604707e-05 lr:8.596699001693255e-05 tokens_per_second_per_gpu:6961.497704848605 Step 81 | loss:1.2528754268714692e-05 lr:8.547853682682604e-05 tokens_per_second_per_gpu:7086.960101134971 Step 82 | loss:1.1446889402577654e-05 lr:8.498316702566828e-05 tokens_per_second_per_gpu:6691.280208245457 Step 83 | loss:4.815257852897048e-06 lr:8.44809771867835e-05 tokens_per_second_per_gpu:6658.248403221658 Step 84 | loss:3.0488231459457893e-06 lr:8.397206521307584e-05 tokens_per_second_per_gpu:6978.3308970377675 Step 85 | loss:1.2022415830870159e-05 lr:8.345653031794292e-05 tokens_per_second_per_gpu:7024.04356118677 Step 86 | loss:9.813477845455054e-06 lr:8.293447300593402e-05 tokens_per_second_per_gpu:6766.809768733323 Step 87 | loss:2.6369045372121036e-05 lr:8.240599505315655e-05 tokens_per_second_per_gpu:6978.200935022428 Step 88 | loss:8.541922397853341e-06 lr:8.18711994874345e-05 tokens_per_second_per_gpu:7098.156734459604 Step 89 | loss:3.103864855802385e-06 lr:8.133019056822304e-05 tokens_per_second_per_gpu:7219.056551161025 Step 90 | loss:3.5655316423799377e-06 lr:8.07830737662829e-05 tokens_per_second_per_gpu:7019.067698524688 Step 91 | loss:1.0854146239580587e-06 lr:8.022995574311876e-05 tokens_per_second_per_gpu:7153.69747754744 Step 92 | loss:4.263146365701687e-06 lr:7.967094433018508e-05 tokens_per_second_per_gpu:6957.553828013221 Step 93 | loss:7.060260486468906e-06 lr:7.910614850786448e-05 tokens_per_second_per_gpu:6853.263305103832 Step 94 | loss:1.1903109225386288e-05 lr:7.85356783842216e-05 tokens_per_second_per_gpu:6589.575326434221 Step 95 | loss:0.00016185850836336613 lr:7.795964517353735e-05 tokens_per_second_per_gpu:6944.601303606873 Step 96 | loss:8.044984861044213e-05 lr:7.737816117462752e-05 tokens_per_second_per_gpu:6884.864612321647 Step 97 | loss:7.145414656406501e-06 lr:7.679133974894983e-05 tokens_per_second_per_gpu:6651.570890606297 Step 98 | loss:9.237920494342688e-06 lr:7.619929529850397e-05 tokens_per_second_per_gpu:6981.50227936076 Step 99 | loss:1.2111839168937877e-05 lr:7.560214324352858e-05 tokens_per_second_per_gpu:7168.252572265034 Step 100 | loss:0.026117179542779922 lr:7.500000000000001e-05 tokens_per_second_per_gpu:7081.326389342591 Step 101 | loss:0.0802021324634552 lr:7.439298295693665e-05 tokens_per_second_per_gpu:6970.406976143403 Step 102 | loss:1.909429329316481e-06 lr:7.378121045351378e-05 tokens_per_second_per_gpu:6981.964998585159 Step 103 | loss:3.795558086494566e-06 lr:7.316480175599309e-05 tokens_per_second_per_gpu:7068.4476399981295 Step 104 | loss:2.2362472009263e-05 lr:7.254387703447154e-05 tokens_per_second_per_gpu:6983.714695167926 Step 105 | loss:7.627813465660438e-05 lr:7.191855733945387e-05 tokens_per_second_per_gpu:6743.04177836767 Step 106 | loss:1.7890037270262837e-05 lr:7.128896457825364e-05 tokens_per_second_per_gpu:7010.008610179187 Step 107 | loss:7.333755092986394e-06 lr:7.06552214912271e-05 tokens_per_second_per_gpu:7180.622708674705 Step 108 | loss:7.34656787244603e-05 lr:7.001745162784477e-05 tokens_per_second_per_gpu:6715.895583278378 Step 109 | loss:0.04645148292183876 lr:6.937577932260515e-05 tokens_per_second_per_gpu:6988.207653074747 Step 110 | loss:2.43443064391613e-05 lr:6.873032967079561e-05 tokens_per_second_per_gpu:6956.44202161727 Step 111 | loss:6.660214239673223e-06 lr:6.808122850410461e-05 tokens_per_second_per_gpu:6822.459221804685 Step 112 | loss:0.012756402604281902 lr:6.742860236609077e-05 tokens_per_second_per_gpu:7100.676232373181 Step 113 | loss:1.7311773262917995e-05 lr:6.677257848751277e-05 tokens_per_second_per_gpu:7156.757410833997 Step 114 | loss:3.133984137093648e-05 lr:6.611328476152557e-05 tokens_per_second_per_gpu:7024.579430239129 Step 115 | loss:1.045593398885103e-05 lr:6.545084971874738e-05 tokens_per_second_per_gpu:7132.709611658199 Step 116 | loss:2.3038093786453828e-05 lr:6.478540250220234e-05 tokens_per_second_per_gpu:6551.364179401075 Step 117 | loss:4.244555384502746e-05 lr:6.411707284214384e-05 tokens_per_second_per_gpu:6972.92108119478 Step 118 | loss:4.624223493010504e-06 lr:6.344599103076329e-05 tokens_per_second_per_gpu:7040.4981318665305 Step 119 | loss:1.8302846001461148e-05 lr:6.277228789678953e-05 tokens_per_second_per_gpu:7035.868734705393 Step 120 | loss:1.2434774134817417e-06 lr:6.209609477998338e-05 tokens_per_second_per_gpu:6995.260130722958 Step 121 | loss:0.059504956007003784 lr:6.141754350553279e-05 tokens_per_second_per_gpu:6470.644661102764 Step 122 | loss:0.06491203606128693 lr:6.073676635835317e-05 tokens_per_second_per_gpu:6572.499955115313 Step 123 | loss:0.0078155267983675 lr:6.005389605729824e-05 tokens_per_second_per_gpu:7122.328916332964 Step 124 | loss:3.2552068205404794e-06 lr:5.9369065729286245e-05 tokens_per_second_per_gpu:6979.690909126259 Step 125 | loss:2.347284316783771e-05 lr:5.868240888334653e-05 tokens_per_second_per_gpu:1226.3605470349123 Step 126 | loss:6.7143696469429415e-06 lr:5.799405938459175e-05 tokens_per_second_per_gpu:7054.351458698333 Step 127 | loss:8.008167242223863e-06 lr:5.730415142812059e-05 tokens_per_second_per_gpu:7079.00426628037 Step 128 | loss:1.265558512386633e-05 lr:5.661281951285613e-05 tokens_per_second_per_gpu:6978.817305625372 Step 129 | loss:5.403888280852698e-06 lr:5.5920198415325064e-05 tokens_per_second_per_gpu:7116.884844031205 Step 130 | loss:3.3160192742798245e-06 lr:5.522642316338268e-05 tokens_per_second_per_gpu:7170.247458165003 Step 131 | loss:0.03811214491724968 lr:5.453162900988902e-05 tokens_per_second_per_gpu:6532.210400971212 Step 132 | loss:9.247117304767016e-06 lr:5.383595140634093e-05 tokens_per_second_per_gpu:7168.145254774769 Step 133 | loss:2.4717032829357777e-06 lr:5.313952597646568e-05 tokens_per_second_per_gpu:7091.0692874879815 Step 134 | loss:7.369029481196776e-05 lr:5.244248848978067e-05 tokens_per_second_per_gpu:7004.214080065665 Step 135 | loss:3.1085594400792615e-06 lr:5.174497483512506e-05 tokens_per_second_per_gpu:6990.065421926794 Step 136 | loss:9.577012178851874e-07 lr:5.104712099416785e-05 tokens_per_second_per_gpu:7008.389750168799 Step 137 | loss:1.0971440133289434e-05 lr:5.034906301489808e-05 tokens_per_second_per_gpu:6928.087081095463 Step 138 | loss:4.204719516565092e-06 lr:4.965093698510193e-05 tokens_per_second_per_gpu:6909.812329064061 Step 139 | loss:1.0095306606672239e-05 lr:4.895287900583216e-05 tokens_per_second_per_gpu:7073.22815454305 Step 140 | loss:3.268487853347324e-05 lr:4.825502516487497e-05 tokens_per_second_per_gpu:5531.814526502013 Step 141 | loss:0.04684333875775337 lr:4.755751151021934e-05 tokens_per_second_per_gpu:1222.5209777558305 Step 142 | loss:0.007246284279972315 lr:4.6860474023534335e-05 tokens_per_second_per_gpu:7069.36560305965 Step 143 | loss:0.0004771423991769552 lr:4.616404859365907e-05 tokens_per_second_per_gpu:6842.861539922387 Step 144 | loss:1.924601019709371e-05 lr:4.5468370990111006e-05 tokens_per_second_per_gpu:6604.936550883388 Step 145 | loss:0.0027290782891213894 lr:4.477357683661734e-05 tokens_per_second_per_gpu:7107.98693950717 Step 146 | loss:1.3675327181772445e-06 lr:4.407980158467495e-05 tokens_per_second_per_gpu:7070.146281288021 Step 147 | loss:1.4125947700449615e-06 lr:4.3387180487143876e-05 tokens_per_second_per_gpu:7067.684661770268 Step 148 | loss:4.665956112148706e-06 lr:4.269584857187943e-05 tokens_per_second_per_gpu:6923.578320260167 Step 149 | loss:1.6779952147771837e-06 lr:4.2005940615408264e-05 tokens_per_second_per_gpu:7082.018376457293 Step 150 | loss:0.0056058503687381744 lr:4.131759111665349e-05 tokens_per_second_per_gpu:7219.916012532959 Step 151 | loss:5.618292561848648e-06 lr:4.063093427071376e-05 tokens_per_second_per_gpu:7145.512686855166 Step 152 | loss:1.7041573983078706e-06 lr:3.9946103942701777e-05 tokens_per_second_per_gpu:7097.425317714264 Step 153 | loss:5.979360139463097e-06 lr:3.926323364164684e-05 tokens_per_second_per_gpu:6643.699919698053 Step 154 | loss:2.7793234949058387e-06 lr:3.858245649446721e-05 tokens_per_second_per_gpu:7055.825278983358 Step 155 | loss:5.22729760632501e-06 lr:3.790390522001662e-05 tokens_per_second_per_gpu:7009.005737334563 Step 156 | loss:2.1051121166237863e-06 lr:3.7227712103210486e-05 tokens_per_second_per_gpu:7026.554489305066 Step 157 | loss:6.214169161466998e-07 lr:3.655400896923672e-05 tokens_per_second_per_gpu:7142.538870029408 Step 158 | loss:1.981428567887633e-06 lr:3.588292715785617e-05 tokens_per_second_per_gpu:7035.408645586714 Step 159 | loss:1.229327267537883e-06 lr:3.5214597497797684e-05 tokens_per_second_per_gpu:7116.95198366537 Step 160 | loss:0.00840386375784874 lr:3.4549150281252636e-05 tokens_per_second_per_gpu:7011.8687130323815 Step 161 | loss:4.690188688982744e-06 lr:3.388671523847445e-05 tokens_per_second_per_gpu:6973.663980687629 Step 162 | loss:1.0637126024448662e-06 lr:3.322742151248725e-05 tokens_per_second_per_gpu:7037.310787111708 Step 163 | loss:2.723348643485224e-06 lr:3.257139763390925e-05 tokens_per_second_per_gpu:6965.671214397283 Step 164 | loss:3.37466713062895e-06 lr:3.1918771495895396e-05 tokens_per_second_per_gpu:7002.487856209016 Step 165 | loss:1.709984417175292e-06 lr:3.12696703292044e-05 tokens_per_second_per_gpu:6973.210713786478 Step 166 | loss:4.1995344872702844e-06 lr:3.062422067739485e-05 tokens_per_second_per_gpu:7116.373478596367 Step 167 | loss:2.869960189855192e-05 lr:2.9982548372155263e-05 tokens_per_second_per_gpu:7169.540838190056 Step 168 | loss:5.113638962939149e-06 lr:2.934477850877292e-05 tokens_per_second_per_gpu:7109.270070429179 Step 169 | loss:1.845184783633158e-06 lr:2.8711035421746367e-05 tokens_per_second_per_gpu:6897.6678713681085 Step 170 | loss:7.516128789575305e-06 lr:2.8081442660546125e-05 tokens_per_second_per_gpu:6839.149029652966 Step 171 | loss:2.8925494461873313e-06 lr:2.7456122965528475e-05 tokens_per_second_per_gpu:7031.877241122064 Step 172 | loss:7.430535333696753e-07 lr:2.6835198244006927e-05 tokens_per_second_per_gpu:7065.385613955569 Step 173 | loss:2.773562755464809e-06 lr:2.6218789546486234e-05 tokens_per_second_per_gpu:7121.649218064128 Step 174 | loss:1.5943980997690232e-06 lr:2.560701704306336e-05 tokens_per_second_per_gpu:7043.376839781155 Step 175 | loss:2.5899310003296705e-06 lr:2.500000000000001e-05 tokens_per_second_per_gpu:6978.686237887583 Step 176 | loss:3.070770162594272e-06 lr:2.4397856756471432e-05 tokens_per_second_per_gpu:7021.193638604272 Step 177 | loss:2.501697053958196e-06 lr:2.3800704701496053e-05 tokens_per_second_per_gpu:6935.321589001509 Step 178 | loss:9.196894552587764e-07 lr:2.3208660251050158e-05 tokens_per_second_per_gpu:7113.116177287278 Step 179 | loss:1.4915924566594185e-06 lr:2.2621838825372493e-05 tokens_per_second_per_gpu:7080.012930507778 Step 180 | loss:7.816337529220618e-06 lr:2.2040354826462668e-05 tokens_per_second_per_gpu:6730.247387924899 Step 181 | loss:4.5060451157041825e-06 lr:2.1464321615778422e-05 tokens_per_second_per_gpu:6633.126456234147 Step 182 | loss:9.429815008843434e-07 lr:2.0893851492135537e-05 tokens_per_second_per_gpu:6876.042804461826 Step 183 | loss:1.7461517245465075e-06 lr:2.0329055669814934e-05 tokens_per_second_per_gpu:7088.35117352931 Step 184 | loss:8.307407028951275e-07 lr:1.977004425688126e-05 tokens_per_second_per_gpu:7043.547922215887 Step 185 | loss:4.707547304860782e-06 lr:1.9216926233717085e-05 tokens_per_second_per_gpu:6643.8900988303285 Step 186 | loss:1.0972149539156817e-05 lr:1.866980943177699e-05 tokens_per_second_per_gpu:6694.705107240203 Step 187 | loss:4.4071919546695426e-05 lr:1.8128800512565513e-05 tokens_per_second_per_gpu:7240.146015342119 Step 188 | loss:8.381610427932173e-07 lr:1.7594004946843456e-05 tokens_per_second_per_gpu:7096.8964979719885 Step 189 | loss:7.407321049868187e-07 lr:1.7065526994065973e-05 tokens_per_second_per_gpu:7121.173756895708 Step 190 | loss:3.3338999401166802e-06 lr:1.6543469682057106e-05 tokens_per_second_per_gpu:7100.223662186301 Step 191 | loss:0.0035902601666748524 lr:1.602793478692419e-05 tokens_per_second_per_gpu:6515.473321335062 Step 192 | loss:2.5614795049477834e-06 lr:1.551902281321651e-05 tokens_per_second_per_gpu:7003.541912899192 Step 193 | loss:8.393068924306135e-07 lr:1.5016832974331724e-05 tokens_per_second_per_gpu:7014.491032799716 Step 194 | loss:2.447998213028768e-06 lr:1.4521463173173965e-05 tokens_per_second_per_gpu:6708.696099311401 Step 195 | loss:5.267979759082664e-06 lr:1.4033009983067452e-05 tokens_per_second_per_gpu:7116.479522540485 Step 196 | loss:2.3782727112120483e-06 lr:1.3551568628929434e-05 tokens_per_second_per_gpu:7062.6359533488985 Step 197 | loss:2.5765357349882834e-06 lr:1.3077232968705805e-05 tokens_per_second_per_gpu:6958.638851056429 Step 198 | loss:1.9566266473702854e-06 lr:1.2610095475073414e-05 tokens_per_second_per_gpu:6180.3336310184695 Step 199 | loss:1.4055506198928924e-06 lr:1.2150247217412186e-05 tokens_per_second_per_gpu:7024.581093181509 Step 200 | loss:0.00019912575953640044 lr:1.1697777844051105e-05 tokens_per_second_per_gpu:7168.688028092893 Step 201 | loss:1.6661166455378407e-06 lr:1.1252775564791024e-05 tokens_per_second_per_gpu:6929.813512350013 Step 202 | loss:1.5410813603011775e-06 lr:1.0815327133708015e-05 tokens_per_second_per_gpu:6987.44783037789 Step 203 | loss:4.979927325621247e-06 lr:1.0385517832240471e-05 tokens_per_second_per_gpu:6979.381617208856 Step 204 | loss:1.2297186913201585e-06 lr:9.963431452563332e-06 tokens_per_second_per_gpu:7176.665234411136 Step 205 | loss:1.3492949619831052e-05 lr:9.549150281252633e-06 tokens_per_second_per_gpu:7127.822007721629 Step 206 | loss:8.906470156944124e-07 lr:9.142755083243576e-06 tokens_per_second_per_gpu:7210.724540147423 Step 207 | loss:8.889155083124933e-07 lr:8.744325086085248e-06 tokens_per_second_per_gpu:6972.105740048867 Step 208 | loss:8.329041634169698e-07 lr:8.353937964495029e-06 tokens_per_second_per_gpu:7106.554468682579 Step 209 | loss:3.670160140245571e-06 lr:7.971669825215788e-06 tokens_per_second_per_gpu:7220.885235213336 Step 210 | loss:5.802224222861696e-06 lr:7.597595192178702e-06 tokens_per_second_per_gpu:6605.317312538336 Step 211 | loss:7.749559358671831e-07 lr:7.2317869919746705e-06 tokens_per_second_per_gpu:7032.812938997669 Step 212 | loss:7.33648221284966e-06 lr:6.874316539637127e-06 tokens_per_second_per_gpu:7166.742192161262 Step 213 | loss:6.916959591762861e-06 lr:6.52525352473905e-06 tokens_per_second_per_gpu:7222.582898447143 Step 214 | loss:1.3800332681057625e-06 lr:6.184665997806832e-06 tokens_per_second_per_gpu:7143.656007254907 Step 215 | loss:2.8561623821588e-06 lr:5.852620357053651e-06 tokens_per_second_per_gpu:7218.261854220109 Step 216 | loss:2.382758566454868e-06 lr:5.529181335435124e-06 tokens_per_second_per_gpu:7259.21964949639 Step 217 | loss:2.0544837298075436e-06 lr:5.214411988029355e-06 tokens_per_second_per_gpu:6678.5120598161 Step 218 | loss:7.685586751904339e-06 lr:4.908373679744316e-06 tokens_per_second_per_gpu:6626.349056250582 Step 219 | loss:6.007870524626924e-06 lr:4.611126073354571e-06 tokens_per_second_per_gpu:7077.564345481776 Step 220 | loss:3.490607195999473e-05 lr:4.322727117869951e-06 tokens_per_second_per_gpu:7105.257936437791 Step 221 | loss:6.473839675891213e-06 lr:4.043233037238281e-06 tokens_per_second_per_gpu:6574.786620635736 Step 222 | loss:9.190073910758656e-07 lr:3.772698319384349e-06 tokens_per_second_per_gpu:7110.835667763218 Step 223 | loss:3.068495061597787e-05 lr:3.511175705587433e-06 tokens_per_second_per_gpu:7237.129676743387 Step 224 | loss:0.0015145567012950778 lr:3.258716180199278e-06 tokens_per_second_per_gpu:7148.635382871293 Step 225 | loss:1.0374400289947516e-06 lr:3.0153689607045845e-06 tokens_per_second_per_gpu:6931.239539572596 Step 226 | loss:1.3044374099990819e-05 lr:2.7811814881259503e-06 tokens_per_second_per_gpu:7222.589120266079 Step 227 | loss:3.997599196736701e-05 lr:2.5561994177751737e-06 tokens_per_second_per_gpu:6805.225223179514 Step 228 | loss:2.5553501927788602e-06 lr:2.340466610352654e-06 tokens_per_second_per_gpu:7050.79917922558 Step 229 | loss:2.0318548195064068e-06 lr:2.134025123396638e-06 tokens_per_second_per_gpu:7133.6810033473275 Step 230 | loss:3.323497367091477e-06 lr:1.9369152030840556e-06 tokens_per_second_per_gpu:6806.544235688607 Step 231 | loss:3.3078231354011223e-06 lr:1.7491752763844293e-06 tokens_per_second_per_gpu:6575.355492388719 Step 232 | loss:1.2345973345873062e-06 lr:1.5708419435684462e-06 tokens_per_second_per_gpu:7055.031265155706 Step 233 | loss:7.690464940424135e-07 lr:1.4019499710726913e-06 tokens_per_second_per_gpu:7078.248774510847 Step 234 | loss:2.586485607025679e-06 lr:1.2425322847218368e-06 tokens_per_second_per_gpu:7032.57973473013 Step 235 | loss:4.3849086068803445e-06 lr:1.0926199633097157e-06 tokens_per_second_per_gpu:7029.305177581747 Step 236 | loss:8.413181831201655e-07 lr:9.522422325404235e-07 tokens_per_second_per_gpu:7154.23857710486 Step 237 | loss:1.4026572898728773e-06 lr:8.214264593307098e-07 tokens_per_second_per_gpu:7110.085257093312 Step 238 | loss:7.505981557187624e-06 lr:7.001981464747565e-07 tokens_per_second_per_gpu:6492.374810946618 Step 239 | loss:1.034242700370669e-06 lr:5.885809276723608e-07 tokens_per_second_per_gpu:7155.08391999291 Step 240 | loss:7.5563552854873706e-06 lr:4.865965629214819e-07 tokens_per_second_per_gpu:7234.350878362913 Step 241 | loss:0.011282374151051044 lr:3.9426493427611177e-07 tokens_per_second_per_gpu:7003.134545628831 Step 242 | loss:2.187658310504048e-06 lr:3.1160404197018154e-07 tokens_per_second_per_gpu:7034.06735918719 Step 243 | loss:1.2806139011445339e-06 lr:2.386300009084408e-07 tokens_per_second_per_gpu:7085.225395108095 Step 244 | loss:6.366369120769377e-07 lr:1.753570375247815e-07 tokens_per_second_per_gpu:6865.731239141299 Step 245 | loss:2.370304173382465e-06 lr:1.2179748700879012e-07 tokens_per_second_per_gpu:6986.651892281518 Step 246 | loss:1.0725663059929502e-06 lr:7.796179090094891e-08 tokens_per_second_per_gpu:7068.680235913791 Step 247 | loss:1.5921763178994297e-06 lr:4.385849505708084e-08 tokens_per_second_per_gpu:7031.133175520725 Step 248 | loss:0.0008751447894610465 lr:1.949424798228239e-08 tokens_per_second_per_gpu:7130.958260467186 Step 249 | loss:0.010600603185594082 lr:4.873799534788059e-09 tokens_per_second_per_gpu:6802.101333548679 Step 250 | loss:2.739674073382048e-06 lr:0.0 tokens_per_second_per_gpu:6964.726939557889