|
Step 1 | loss:0.04215042293071747 lr:4.000000000000001e-06 tokens_per_second_per_gpu:4647.1187254594915 |
|
Step 2 | loss:0.08958189189434052 lr:8.000000000000001e-06 tokens_per_second_per_gpu:3357.3715013315955 |
|
Step 3 | loss:0.04213809594511986 lr:1.2e-05 tokens_per_second_per_gpu:7022.182383758634 |
|
Step 4 | loss:0.07334428280591965 lr:1.6000000000000003e-05 tokens_per_second_per_gpu:2616.05290295991 |
|
Step 5 | loss:0.0572502501308918 lr:2e-05 tokens_per_second_per_gpu:7150.83925797967 |
|
Step 6 | loss:0.048984725028276443 lr:2.4e-05 tokens_per_second_per_gpu:3387.8334084312023 |
|
Step 7 | loss:0.056656613945961 lr:2.8000000000000003e-05 tokens_per_second_per_gpu:7109.908992415555 |
|
Step 8 | loss:0.08737850934267044 lr:3.2000000000000005e-05 tokens_per_second_per_gpu:7121.285388817181 |
|
Step 9 | loss:0.04351073503494263 lr:3.6e-05 tokens_per_second_per_gpu:6972.152874286363 |
|
Step 10 | loss:0.05034875497221947 lr:4e-05 tokens_per_second_per_gpu:7163.673518377882 |
|
Step 11 | loss:0.09638502448797226 lr:4.4000000000000006e-05 tokens_per_second_per_gpu:7020.253349456141 |
|
Step 12 | loss:0.03940489888191223 lr:4.8e-05 tokens_per_second_per_gpu:7007.9560771578135 |
|
Step 13 | loss:0.09778154641389847 lr:5.2000000000000004e-05 tokens_per_second_per_gpu:2119.4360025603924 |
|
Step 14 | loss:0.02709851786494255 lr:5.6000000000000006e-05 tokens_per_second_per_gpu:7029.247882452085 |
|
Step 15 | loss:0.03088054060935974 lr:6e-05 tokens_per_second_per_gpu:6971.645184747378 |
|
Step 16 | loss:0.0712149441242218 lr:6.400000000000001e-05 tokens_per_second_per_gpu:2645.6884956870576 |
|
Step 17 | loss:0.0603531114757061 lr:6.800000000000001e-05 tokens_per_second_per_gpu:1578.9708278566216 |
|
Step 18 | loss:0.04335852339863777 lr:7.2e-05 tokens_per_second_per_gpu:6885.621070120474 |
|
Step 19 | loss:0.053766168653964996 lr:7.6e-05 tokens_per_second_per_gpu:7118.341439474123 |
|
Step 20 | loss:0.04179014638066292 lr:8e-05 tokens_per_second_per_gpu:7141.09410612426 |
|
Step 21 | loss:0.022095046937465668 lr:8.4e-05 tokens_per_second_per_gpu:6934.467494571387 |
|
Step 22 | loss:0.02832031063735485 lr:8.800000000000001e-05 tokens_per_second_per_gpu:7110.540773151844 |
|
Step 23 | loss:0.05593244358897209 lr:9.200000000000001e-05 tokens_per_second_per_gpu:6802.004140614846 |
|
Step 24 | loss:0.01897679828107357 lr:9.6e-05 tokens_per_second_per_gpu:7094.300864940928 |
|
Step 25 | loss:0.07287943363189697 lr:0.0001 tokens_per_second_per_gpu:6883.370893985433 |
|
Step 26 | loss:0.024570493027567863 lr:9.999512620046522e-05 tokens_per_second_per_gpu:7194.150375534295 |
|
Step 27 | loss:0.022486839443445206 lr:9.998050575201771e-05 tokens_per_second_per_gpu:6555.81607290927 |
|
Step 28 | loss:0.022946307435631752 lr:9.995614150494293e-05 tokens_per_second_per_gpu:6921.364209169676 |
|
Step 29 | loss:0.02819202095270157 lr:9.992203820909906e-05 tokens_per_second_per_gpu:3978.4571935308463 |
|
Step 30 | loss:0.016549646854400635 lr:9.987820251299122e-05 tokens_per_second_per_gpu:6933.393320944731 |
|
Step 31 | loss:0.029019009321928024 lr:9.982464296247522e-05 tokens_per_second_per_gpu:7071.6547672469205 |
|
Step 32 | loss:0.024149976670742035 lr:9.976136999909156e-05 tokens_per_second_per_gpu:7093.283001892852 |
|
Step 33 | loss:0.016558295115828514 lr:9.968839595802982e-05 tokens_per_second_per_gpu:7052.780911994404 |
|
Step 34 | loss:0.015351448208093643 lr:9.96057350657239e-05 tokens_per_second_per_gpu:7069.06570578152 |
|
Step 35 | loss:0.011170708574354649 lr:9.951340343707852e-05 tokens_per_second_per_gpu:6922.7702850765445 |
|
Step 36 | loss:0.027870869264006615 lr:9.941141907232765e-05 tokens_per_second_per_gpu:6817.7337056422575 |
|
Step 37 | loss:0.016473719850182533 lr:9.929980185352526e-05 tokens_per_second_per_gpu:6996.185538363585 |
|
Step 38 | loss:0.01076983567327261 lr:9.917857354066931e-05 tokens_per_second_per_gpu:6933.129604943275 |
|
Step 39 | loss:0.009128141216933727 lr:9.904775776745958e-05 tokens_per_second_per_gpu:6966.67628894575 |
|
Step 40 | loss:0.048571910709142685 lr:9.890738003669029e-05 tokens_per_second_per_gpu:6524.640444330688 |
|
Step 41 | loss:0.017220987007021904 lr:9.875746771527816e-05 tokens_per_second_per_gpu:7108.492213972599 |
|
Step 42 | loss:0.03372334688901901 lr:9.859805002892732e-05 tokens_per_second_per_gpu:2497.911430762369 |
|
Step 43 | loss:0.025175612419843674 lr:9.842915805643155e-05 tokens_per_second_per_gpu:7160.456782609851 |
|
Step 44 | loss:0.00914957094937563 lr:9.825082472361557e-05 tokens_per_second_per_gpu:6929.228399097177 |
|
Step 45 | loss:0.010613073594868183 lr:9.806308479691595e-05 tokens_per_second_per_gpu:6989.342298607297 |
|
Step 46 | loss:0.007543059065937996 lr:9.786597487660337e-05 tokens_per_second_per_gpu:6945.443034806758 |
|
Step 47 | loss:0.030928002670407295 lr:9.765953338964735e-05 tokens_per_second_per_gpu:7012.084765360256 |
|
Step 48 | loss:0.01814030297100544 lr:9.744380058222483e-05 tokens_per_second_per_gpu:6994.302352697613 |
|
Step 49 | loss:0.03378879278898239 lr:9.721881851187406e-05 tokens_per_second_per_gpu:6520.932734624143 |
|
Step 50 | loss:0.03357093036174774 lr:9.698463103929542e-05 tokens_per_second_per_gpu:7192.654561720016 |
|
Step 51 | loss:0.0235911775380373 lr:9.674128381980072e-05 tokens_per_second_per_gpu:7067.638833412 |
|
Step 52 | loss:0.016505662351846695 lr:9.648882429441257e-05 tokens_per_second_per_gpu:7048.371966880589 |
|
Step 53 | loss:0.011654402129352093 lr:9.622730168061567e-05 tokens_per_second_per_gpu:7147.799924288925 |
|
Step 54 | loss:0.019919371232390404 lr:9.595676696276172e-05 tokens_per_second_per_gpu:7088.348031249094 |
|
Step 55 | loss:0.013333844020962715 lr:9.567727288213005e-05 tokens_per_second_per_gpu:7117.961129257003 |
|
Step 56 | loss:0.010824856348335743 lr:9.538887392664544e-05 tokens_per_second_per_gpu:6473.692112138805 |
|
Step 57 | loss:0.008925478905439377 lr:9.50916263202557e-05 tokens_per_second_per_gpu:7089.141917691826 |
|
Step 58 | loss:0.00918285921216011 lr:9.478558801197065e-05 tokens_per_second_per_gpu:6984.624220629644 |
|
Step 59 | loss:0.0076332795433700085 lr:9.447081866456489e-05 tokens_per_second_per_gpu:6954.464286212376 |
|
Step 60 | loss:0.0072117880918085575 lr:9.414737964294636e-05 tokens_per_second_per_gpu:6949.658160478569 |
|
Step 61 | loss:0.012769433669745922 lr:9.381533400219318e-05 tokens_per_second_per_gpu:7023.948119040068 |
|
Step 62 | loss:0.011435179971158504 lr:9.347474647526095e-05 tokens_per_second_per_gpu:7013.126662041556 |
|
Step 63 | loss:0.012945052236318588 lr:9.312568346036288e-05 tokens_per_second_per_gpu:6875.273557870438 |
|
Step 64 | loss:0.027221037074923515 lr:9.276821300802534e-05 tokens_per_second_per_gpu:6547.694598995759 |
|
Step 65 | loss:0.006611868739128113 lr:9.24024048078213e-05 tokens_per_second_per_gpu:6979.584947060188 |
|
Step 66 | loss:0.013862483203411102 lr:9.202833017478422e-05 tokens_per_second_per_gpu:7136.522712884573 |
|
Step 67 | loss:0.01116298045963049 lr:9.164606203550497e-05 tokens_per_second_per_gpu:6979.500460125288 |
|
Step 68 | loss:0.007385791279375553 lr:9.125567491391476e-05 tokens_per_second_per_gpu:7050.882595801868 |
|
Step 69 | loss:0.009465196169912815 lr:9.085724491675642e-05 tokens_per_second_per_gpu:6925.193182387022 |
|
Step 70 | loss:0.006853089202195406 lr:9.045084971874738e-05 tokens_per_second_per_gpu:6919.055326047798 |
|
Step 71 | loss:0.008219563402235508 lr:9.003656854743667e-05 tokens_per_second_per_gpu:7017.700993094878 |
|
Step 72 | loss:0.015989139676094055 lr:8.961448216775954e-05 tokens_per_second_per_gpu:7030.337257267225 |
|
Step 73 | loss:0.012423246167600155 lr:8.9184672866292e-05 tokens_per_second_per_gpu:7010.061484849103 |
|
Step 74 | loss:0.021352389827370644 lr:8.874722443520899e-05 tokens_per_second_per_gpu:7036.894106369774 |
|
Step 75 | loss:0.008610804565250874 lr:8.83022221559489e-05 tokens_per_second_per_gpu:6925.648438720128 |
|
Step 76 | loss:0.005319702904671431 lr:8.784975278258783e-05 tokens_per_second_per_gpu:6994.629897487184 |
|
Step 77 | loss:0.016950633376836777 lr:8.73899045249266e-05 tokens_per_second_per_gpu:7164.460428076916 |
|
Step 78 | loss:0.004855715669691563 lr:8.692276703129421e-05 tokens_per_second_per_gpu:7164.2299950368215 |
|
Step 79 | loss:0.005726809147745371 lr:8.644843137107059e-05 tokens_per_second_per_gpu:6916.107405261695 |
|
Step 80 | loss:0.00949916709214449 lr:8.596699001693255e-05 tokens_per_second_per_gpu:7173.491126598326 |
|
Step 81 | loss:0.007938658818602562 lr:8.547853682682604e-05 tokens_per_second_per_gpu:7073.302132941829 |
|
Step 82 | loss:0.004066552501171827 lr:8.498316702566828e-05 tokens_per_second_per_gpu:6952.3303703807405 |
|
Step 83 | loss:0.009648513980209827 lr:8.44809771867835e-05 tokens_per_second_per_gpu:7050.989683566043 |
|
Step 84 | loss:0.005391728598624468 lr:8.397206521307584e-05 tokens_per_second_per_gpu:7054.4676192944025 |
|
Step 85 | loss:0.008159473538398743 lr:8.345653031794292e-05 tokens_per_second_per_gpu:7019.063399749939 |
|
Step 86 | loss:0.00528710475191474 lr:8.293447300593402e-05 tokens_per_second_per_gpu:7167.757792890184 |
|
Step 87 | loss:0.013560117222368717 lr:8.240599505315655e-05 tokens_per_second_per_gpu:7170.484049247675 |
|
Step 88 | loss:0.009445931762456894 lr:8.18711994874345e-05 tokens_per_second_per_gpu:7022.012473739118 |
|
Step 89 | loss:0.006872545462101698 lr:8.133019056822304e-05 tokens_per_second_per_gpu:7123.130050721631 |
|
Step 90 | loss:0.007461061701178551 lr:8.07830737662829e-05 tokens_per_second_per_gpu:6993.289632631602 |
|
Step 91 | loss:0.00945632066577673 lr:8.022995574311876e-05 tokens_per_second_per_gpu:7005.007246162496 |
|
Step 92 | loss:0.007700109854340553 lr:7.967094433018508e-05 tokens_per_second_per_gpu:7121.285748063472 |
|
Step 93 | loss:0.006697500124573708 lr:7.910614850786448e-05 tokens_per_second_per_gpu:6959.65703591489 |
|
Step 94 | loss:0.016305014491081238 lr:7.85356783842216e-05 tokens_per_second_per_gpu:6839.423398817574 |
|
Step 95 | loss:0.00850058812648058 lr:7.795964517353735e-05 tokens_per_second_per_gpu:7146.829753162642 |
|
Step 96 | loss:0.005745197646319866 lr:7.737816117462752e-05 tokens_per_second_per_gpu:2473.6435778711293 |
|
Step 97 | loss:0.0037460874300450087 lr:7.679133974894983e-05 tokens_per_second_per_gpu:6896.376463262212 |
|
Step 98 | loss:0.028708690777420998 lr:7.619929529850397e-05 tokens_per_second_per_gpu:6825.205294617742 |
|
Step 99 | loss:0.00859098881483078 lr:7.560214324352858e-05 tokens_per_second_per_gpu:7130.383506799234 |
|
Step 100 | loss:0.01707088202238083 lr:7.500000000000001e-05 tokens_per_second_per_gpu:6567.103403252111 |
|
Step 101 | loss:0.006430222187191248 lr:7.439298295693665e-05 tokens_per_second_per_gpu:7040.384735543964 |
|
Step 102 | loss:0.023264506831765175 lr:7.378121045351378e-05 tokens_per_second_per_gpu:6976.3491918263835 |
|
Step 103 | loss:0.014383533969521523 lr:7.316480175599309e-05 tokens_per_second_per_gpu:6838.746881199135 |
|
Step 104 | loss:0.004162967205047607 lr:7.254387703447154e-05 tokens_per_second_per_gpu:6989.027065906691 |
|
Step 105 | loss:0.005258842837065458 lr:7.191855733945387e-05 tokens_per_second_per_gpu:7130.299870671076 |
|
Step 106 | loss:0.019391141831874847 lr:7.128896457825364e-05 tokens_per_second_per_gpu:6819.229023220395 |
|
Step 107 | loss:0.006506034638732672 lr:7.06552214912271e-05 tokens_per_second_per_gpu:7123.370013312798 |
|
Step 108 | loss:0.008356930688023567 lr:7.001745162784477e-05 tokens_per_second_per_gpu:7089.035088996434 |
|
Step 109 | loss:0.009794753044843674 lr:6.937577932260515e-05 tokens_per_second_per_gpu:6996.633905019013 |
|
Step 110 | loss:0.00666762376204133 lr:6.873032967079561e-05 tokens_per_second_per_gpu:7148.394320245328 |
|
Step 111 | loss:0.005746235139667988 lr:6.808122850410461e-05 tokens_per_second_per_gpu:6991.618286544351 |
|
Step 112 | loss:0.004946377594023943 lr:6.742860236609077e-05 tokens_per_second_per_gpu:6983.967393265605 |
|
Step 113 | loss:0.013146648183465004 lr:6.677257848751277e-05 tokens_per_second_per_gpu:7089.004669790884 |
|
Step 114 | loss:0.003838649485260248 lr:6.611328476152557e-05 tokens_per_second_per_gpu:7098.553406915029 |
|
Step 115 | loss:0.0031974734738469124 lr:6.545084971874738e-05 tokens_per_second_per_gpu:7050.3830640087 |
|
Step 116 | loss:0.009875626303255558 lr:6.478540250220234e-05 tokens_per_second_per_gpu:6522.160668615052 |
|
Step 117 | loss:0.013462849892675877 lr:6.411707284214384e-05 tokens_per_second_per_gpu:6874.585612383489 |
|
Step 118 | loss:0.007681750226765871 lr:6.344599103076329e-05 tokens_per_second_per_gpu:6838.088648903154 |
|
Step 119 | loss:0.0025514615699648857 lr:6.277228789678953e-05 tokens_per_second_per_gpu:7130.490631877365 |
|
Step 120 | loss:0.004866372793912888 lr:6.209609477998338e-05 tokens_per_second_per_gpu:7124.773789050104 |
|
Step 121 | loss:0.009351493790745735 lr:6.141754350553279e-05 tokens_per_second_per_gpu:7008.246450764246 |
|
Step 122 | loss:0.00558257382363081 lr:6.073676635835317e-05 tokens_per_second_per_gpu:6996.862189059404 |
|
Step 123 | loss:0.009923309087753296 lr:6.005389605729824e-05 tokens_per_second_per_gpu:7021.641698193046 |
|
Step 124 | loss:0.0021765155252069235 lr:5.9369065729286245e-05 tokens_per_second_per_gpu:7059.5006541145785 |
|
Step 125 | loss:0.004107597749680281 lr:5.868240888334653e-05 tokens_per_second_per_gpu:7036.467724110549 |
|
Step 126 | loss:0.002224874682724476 lr:5.799405938459175e-05 tokens_per_second_per_gpu:6995.75140257784 |
|
Step 127 | loss:0.007369120605289936 lr:5.730415142812059e-05 tokens_per_second_per_gpu:6813.496973729987 |
|
Step 128 | loss:0.0016380972228944302 lr:5.661281951285613e-05 tokens_per_second_per_gpu:6978.117094807362 |
|
Step 129 | loss:0.0013927873224020004 lr:5.5920198415325064e-05 tokens_per_second_per_gpu:7161.84178922261 |
|
Step 130 | loss:0.0016175087075680494 lr:5.522642316338268e-05 tokens_per_second_per_gpu:7031.693616871232 |
|
Step 131 | loss:0.007058033719658852 lr:5.453162900988902e-05 tokens_per_second_per_gpu:7154.383780593954 |
|
Step 132 | loss:0.014386061578989029 lr:5.383595140634093e-05 tokens_per_second_per_gpu:7141.5645950399785 |
|
Step 133 | loss:0.004207151476293802 lr:5.313952597646568e-05 tokens_per_second_per_gpu:6983.599399337058 |
|
Step 134 | loss:0.004966855514794588 lr:5.244248848978067e-05 tokens_per_second_per_gpu:7022.113170034169 |
|
Step 135 | loss:0.0005020507960580289 lr:5.174497483512506e-05 tokens_per_second_per_gpu:7081.595631646572 |
|
Step 136 | loss:0.0024716693442314863 lr:5.104712099416785e-05 tokens_per_second_per_gpu:7021.689111673453 |
|
Step 137 | loss:0.0028216049540787935 lr:5.034906301489808e-05 tokens_per_second_per_gpu:6944.568252868344 |
|
Step 138 | loss:0.0016597588546574116 lr:4.965093698510193e-05 tokens_per_second_per_gpu:7091.175972317294 |
|
Step 139 | loss:0.0011911126784980297 lr:4.895287900583216e-05 tokens_per_second_per_gpu:6951.5013836139315 |
|
Step 140 | loss:0.006537472829222679 lr:4.825502516487497e-05 tokens_per_second_per_gpu:5451.811592881016 |
|
Step 141 | loss:0.0005307656829245389 lr:4.755751151021934e-05 tokens_per_second_per_gpu:7044.906143464728 |
|
Step 142 | loss:0.014001252129673958 lr:4.6860474023534335e-05 tokens_per_second_per_gpu:6995.696220628538 |
|
Step 143 | loss:0.0006640875362791121 lr:4.616404859365907e-05 tokens_per_second_per_gpu:6549.887801094139 |
|
Step 144 | loss:0.0023395728785544634 lr:4.5468370990111006e-05 tokens_per_second_per_gpu:6849.639307576006 |
|
Step 145 | loss:0.0016866429941728711 lr:4.477357683661734e-05 tokens_per_second_per_gpu:7061.3373069868485 |
|
Step 146 | loss:0.006960507016628981 lr:4.407980158467495e-05 tokens_per_second_per_gpu:7111.980218167057 |
|
Step 147 | loss:0.0030706170946359634 lr:4.3387180487143876e-05 tokens_per_second_per_gpu:6981.926067344113 |
|
Step 148 | loss:0.0015286823036149144 lr:4.269584857187943e-05 tokens_per_second_per_gpu:6914.699684063005 |
|
Step 149 | loss:0.002848327625542879 lr:4.2005940615408264e-05 tokens_per_second_per_gpu:7125.92184777077 |
|
Step 150 | loss:0.002262271009385586 lr:4.131759111665349e-05 tokens_per_second_per_gpu:6967.0122997997205 |
|
Step 151 | loss:0.004250329919159412 lr:4.063093427071376e-05 tokens_per_second_per_gpu:6579.43975374904 |
|
Step 152 | loss:0.006092091090977192 lr:3.9946103942701777e-05 tokens_per_second_per_gpu:7043.639160920609 |
|
Step 153 | loss:0.007418781518936157 lr:3.926323364164684e-05 tokens_per_second_per_gpu:6885.235670982188 |
|
Step 154 | loss:0.0034225641284137964 lr:3.858245649446721e-05 tokens_per_second_per_gpu:6993.671956478971 |
|
Step 155 | loss:0.0022845198400318623 lr:3.790390522001662e-05 tokens_per_second_per_gpu:7026.352612513473 |
|
Step 156 | loss:0.0019335101824253798 lr:3.7227712103210486e-05 tokens_per_second_per_gpu:7051.727758396438 |
|
Step 157 | loss:0.0018237214535474777 lr:3.655400896923672e-05 tokens_per_second_per_gpu:7165.814551383084 |
|
Step 158 | loss:0.00340351858176291 lr:3.588292715785617e-05 tokens_per_second_per_gpu:7007.795805651924 |
|
Step 159 | loss:0.003507403191179037 lr:3.5214597497797684e-05 tokens_per_second_per_gpu:7209.777315395053 |
|
Step 160 | loss:0.007351553067564964 lr:3.4549150281252636e-05 tokens_per_second_per_gpu:7182.8277986080375 |
|
Step 161 | loss:0.0007474210578948259 lr:3.388671523847445e-05 tokens_per_second_per_gpu:6918.682500948646 |
|
Step 162 | loss:0.002348431386053562 lr:3.322742151248725e-05 tokens_per_second_per_gpu:7074.314747811755 |
|
Step 163 | loss:0.0012364622671157122 lr:3.257139763390925e-05 tokens_per_second_per_gpu:6965.379251055672 |
|
Step 164 | loss:0.0022965287789702415 lr:3.1918771495895396e-05 tokens_per_second_per_gpu:7172.274604260389 |
|
Step 165 | loss:0.0026479933876544237 lr:3.12696703292044e-05 tokens_per_second_per_gpu:7105.55790968854 |
|
Step 166 | loss:0.0016279935371130705 lr:3.062422067739485e-05 tokens_per_second_per_gpu:6967.78903508017 |
|
Step 167 | loss:0.001954744104295969 lr:2.9982548372155263e-05 tokens_per_second_per_gpu:6967.720059881217 |
|
Step 168 | loss:0.010959520936012268 lr:2.934477850877292e-05 tokens_per_second_per_gpu:7017.625884897816 |
|
Step 169 | loss:0.0046213106252253056 lr:2.8711035421746367e-05 tokens_per_second_per_gpu:6568.585195372882 |
|
Step 170 | loss:0.0010504021774977446 lr:2.8081442660546125e-05 tokens_per_second_per_gpu:7088.0016850809125 |
|
Step 171 | loss:0.0008090205956250429 lr:2.7456122965528475e-05 tokens_per_second_per_gpu:6919.812086505417 |
|
Step 172 | loss:0.0027049824129790068 lr:2.6835198244006927e-05 tokens_per_second_per_gpu:7156.859705598196 |
|
Step 173 | loss:0.001630611252039671 lr:2.6218789546486234e-05 tokens_per_second_per_gpu:7026.460816725105 |
|
Step 174 | loss:0.0019743561279028654 lr:2.560701704306336e-05 tokens_per_second_per_gpu:7004.629146681552 |
|
Step 175 | loss:0.002281033433973789 lr:2.500000000000001e-05 tokens_per_second_per_gpu:7024.6174927584125 |
|
Step 176 | loss:0.005290736444294453 lr:2.4397856756471432e-05 tokens_per_second_per_gpu:6861.041267484 |
|
Step 177 | loss:0.006532042752951384 lr:2.3800704701496053e-05 tokens_per_second_per_gpu:7201.974739224035 |
|
Step 178 | loss:0.001225695596076548 lr:2.3208660251050158e-05 tokens_per_second_per_gpu:7053.886338134641 |
|
Step 179 | loss:6.363681313814595e-05 lr:2.2621838825372493e-05 tokens_per_second_per_gpu:7011.607656678879 |
|
Step 180 | loss:0.0028563456144183874 lr:2.2040354826462668e-05 tokens_per_second_per_gpu:7041.055500430913 |
|
Step 181 | loss:0.018733564764261246 lr:2.1464321615778422e-05 tokens_per_second_per_gpu:6863.709192515457 |
|
Step 182 | loss:0.0004367312940303236 lr:2.0893851492135537e-05 tokens_per_second_per_gpu:7083.112498391501 |
|
Step 183 | loss:0.002563081681728363 lr:2.0329055669814934e-05 tokens_per_second_per_gpu:7006.717362476327 |
|
Step 184 | loss:0.002250371500849724 lr:1.977004425688126e-05 tokens_per_second_per_gpu:7019.994008206745 |
|
Step 185 | loss:0.00207173521630466 lr:1.9216926233717085e-05 tokens_per_second_per_gpu:7046.292538138158 |
|
Step 186 | loss:0.00216984492726624 lr:1.866980943177699e-05 tokens_per_second_per_gpu:6806.659346608232 |
|
Step 187 | loss:0.012741277925670147 lr:1.8128800512565513e-05 tokens_per_second_per_gpu:6986.556727574333 |
|
Step 188 | loss:0.0008626581984572113 lr:1.7594004946843456e-05 tokens_per_second_per_gpu:7223.729823509615 |
|
Step 189 | loss:0.002413097769021988 lr:1.7065526994065973e-05 tokens_per_second_per_gpu:6973.601269201493 |
|
Step 190 | loss:0.0021829043980687857 lr:1.6543469682057106e-05 tokens_per_second_per_gpu:7153.348489785394 |
|
Step 191 | loss:0.002612983575090766 lr:1.602793478692419e-05 tokens_per_second_per_gpu:6902.310298651488 |
|
Step 192 | loss:0.0019071849528700113 lr:1.551902281321651e-05 tokens_per_second_per_gpu:7017.082077501308 |
|
Step 193 | loss:0.0011209172662347555 lr:1.5016832974331724e-05 tokens_per_second_per_gpu:7210.369828169043 |
|
Step 194 | loss:0.0003583554644137621 lr:1.4521463173173965e-05 tokens_per_second_per_gpu:6997.1057399320725 |
|
Step 195 | loss:0.0011847264831885695 lr:1.4033009983067452e-05 tokens_per_second_per_gpu:6825.88002827092 |
|
Step 196 | loss:0.0017767081735655665 lr:1.3551568628929434e-05 tokens_per_second_per_gpu:7107.240433466439 |
|
Step 197 | loss:0.00286451680585742 lr:1.3077232968705805e-05 tokens_per_second_per_gpu:7008.771046295556 |
|
Step 198 | loss:0.0035536375362426043 lr:1.2610095475073414e-05 tokens_per_second_per_gpu:6748.574544873667 |
|
Step 199 | loss:0.0015341676771640778 lr:1.2150247217412186e-05 tokens_per_second_per_gpu:6940.976372167806 |
|
Step 200 | loss:0.0011653564870357513 lr:1.1697777844051105e-05 tokens_per_second_per_gpu:7205.262196741465 |
|
Step 201 | loss:0.0020588436163961887 lr:1.1252775564791024e-05 tokens_per_second_per_gpu:7076.158922240114 |
|
Step 202 | loss:0.0005898997187614441 lr:1.0815327133708015e-05 tokens_per_second_per_gpu:7172.111654500394 |
|
Step 203 | loss:0.00038664767635054886 lr:1.0385517832240471e-05 tokens_per_second_per_gpu:7027.572099104698 |
|
Step 204 | loss:0.002056462224572897 lr:9.963431452563332e-06 tokens_per_second_per_gpu:6985.348721017726 |
|
Step 205 | loss:0.0010346496710553765 lr:9.549150281252633e-06 tokens_per_second_per_gpu:6989.876515555202 |
|
Step 206 | loss:0.0008006116258911788 lr:9.142755083243576e-06 tokens_per_second_per_gpu:7151.686706558325 |
|
Step 207 | loss:0.002810983220115304 lr:8.744325086085248e-06 tokens_per_second_per_gpu:7148.638719432468 |
|
Step 208 | loss:0.002492031781002879 lr:8.353937964495029e-06 tokens_per_second_per_gpu:7022.656506727871 |
|
Step 209 | loss:0.001024445053189993 lr:7.971669825215788e-06 tokens_per_second_per_gpu:6966.839328078706 |
|
Step 210 | loss:0.0014267779188230634 lr:7.597595192178702e-06 tokens_per_second_per_gpu:6903.07916682007 |
|
Step 211 | loss:0.0020388916600495577 lr:7.2317869919746705e-06 tokens_per_second_per_gpu:7176.003488446711 |
|
Step 212 | loss:0.0021616120357066393 lr:6.874316539637127e-06 tokens_per_second_per_gpu:6991.555096002299 |
|
Step 213 | loss:0.0002891359617933631 lr:6.52525352473905e-06 tokens_per_second_per_gpu:7210.447005197424 |
|
Step 214 | loss:0.0003259213117416948 lr:6.184665997806832e-06 tokens_per_second_per_gpu:7112.505734036785 |
|
Step 215 | loss:0.0008648609509691596 lr:5.852620357053651e-06 tokens_per_second_per_gpu:7067.725138117656 |
|
Step 216 | loss:0.0005746301612816751 lr:5.529181335435124e-06 tokens_per_second_per_gpu:7057.425819091941 |
|
Step 217 | loss:0.0016254200600087643 lr:5.214411988029355e-06 tokens_per_second_per_gpu:7174.492537789315 |
|
Step 218 | loss:0.0021314863115549088 lr:4.908373679744316e-06 tokens_per_second_per_gpu:7158.522123554691 |
|
Step 219 | loss:0.002594989025965333 lr:4.611126073354571e-06 tokens_per_second_per_gpu:6965.26896275426 |
|
Step 220 | loss:0.0011671471875160933 lr:4.322727117869951e-06 tokens_per_second_per_gpu:7199.721201195594 |
|
Step 221 | loss:0.0013126779813319445 lr:4.043233037238281e-06 tokens_per_second_per_gpu:7171.5241892113 |
|
Step 222 | loss:0.0025824217591434717 lr:3.772698319384349e-06 tokens_per_second_per_gpu:6845.232897055784 |
|
Step 223 | loss:0.00033475374220870435 lr:3.511175705587433e-06 tokens_per_second_per_gpu:7030.329129301789 |
|
Step 224 | loss:0.00190994911827147 lr:3.258716180199278e-06 tokens_per_second_per_gpu:7138.812730634471 |
|
Step 225 | loss:0.0037967993412166834 lr:3.0153689607045845e-06 tokens_per_second_per_gpu:6816.051879705315 |
|
Step 226 | loss:0.00660149147734046 lr:2.7811814881259503e-06 tokens_per_second_per_gpu:6863.979334427709 |
|
Step 227 | loss:0.0033147600479424 lr:2.5561994177751737e-06 tokens_per_second_per_gpu:6783.886149679305 |
|
Step 228 | loss:0.00022474229626823217 lr:2.340466610352654e-06 tokens_per_second_per_gpu:7070.773182180901 |
|
Step 229 | loss:0.004507806152105331 lr:2.134025123396638e-06 tokens_per_second_per_gpu:7104.700919615501 |
|
Step 230 | loss:0.0013289419002830982 lr:1.9369152030840556e-06 tokens_per_second_per_gpu:7014.310020011136 |
|
Step 231 | loss:0.0032899717334657907 lr:1.7491752763844293e-06 tokens_per_second_per_gpu:6991.076114402474 |
|
Step 232 | loss:0.0004993012989871204 lr:1.5708419435684462e-06 tokens_per_second_per_gpu:7189.286925869835 |
|
Step 233 | loss:0.0020970909390598536 lr:1.4019499710726913e-06 tokens_per_second_per_gpu:6888.402749236451 |
|
Step 234 | loss:0.0014885186683386564 lr:1.2425322847218368e-06 tokens_per_second_per_gpu:6956.358526521228 |
|
Step 235 | loss:0.00104332878254354 lr:1.0926199633097157e-06 tokens_per_second_per_gpu:7100.872465448825 |
|
Step 236 | loss:0.0008983807056210935 lr:9.522422325404235e-07 tokens_per_second_per_gpu:7023.664187868816 |
|
Step 237 | loss:0.0011888393200933933 lr:8.214264593307098e-07 tokens_per_second_per_gpu:7034.798027950856 |
|
Step 238 | loss:0.00167737843003124 lr:7.001981464747565e-07 tokens_per_second_per_gpu:6982.072235712599 |
|
Step 239 | loss:0.00019670512119773775 lr:5.885809276723608e-07 tokens_per_second_per_gpu:7175.871526883832 |
|
Step 240 | loss:0.0010421463521197438 lr:4.865965629214819e-07 tokens_per_second_per_gpu:7039.6844555426815 |
|
Step 241 | loss:0.005810691975057125 lr:3.9426493427611177e-07 tokens_per_second_per_gpu:6783.626062846247 |
|
Step 242 | loss:0.0034142923541367054 lr:3.1160404197018154e-07 tokens_per_second_per_gpu:7110.323284975751 |
|
Step 243 | loss:0.0014499416574835777 lr:2.386300009084408e-07 tokens_per_second_per_gpu:7000.14660359381 |
|
Step 244 | loss:0.00019655893265735358 lr:1.753570375247815e-07 tokens_per_second_per_gpu:6575.534709719152 |
|
Step 245 | loss:0.002633883384987712 lr:1.2179748700879012e-07 tokens_per_second_per_gpu:7021.560578598462 |
|
Step 246 | loss:0.0017441033851355314 lr:7.796179090094891e-08 tokens_per_second_per_gpu:6882.988013140854 |
|
Step 247 | loss:0.0008157814736478031 lr:4.385849505708084e-08 tokens_per_second_per_gpu:7104.733451205545 |
|
Step 248 | loss:0.0009828050388023257 lr:1.949424798228239e-08 tokens_per_second_per_gpu:6885.441108260393 |
|
Step 249 | loss:0.003748729359358549 lr:4.873799534788059e-09 tokens_per_second_per_gpu:7046.4417155623505 |
|
Step 250 | loss:0.002358163706958294 lr:0.0 tokens_per_second_per_gpu:7025.502189517289 |
|
|