|
Step 1 | loss:0.02746153064072132 lr:4.000000000000001e-06 tokens_per_second_per_gpu:3810.563910527513 |
|
Step 2 | loss:0.012695659883320332 lr:8.000000000000001e-06 tokens_per_second_per_gpu:4451.273241245203 |
|
Step 3 | loss:0.02766001969575882 lr:1.2e-05 tokens_per_second_per_gpu:7049.166726204655 |
|
Step 4 | loss:0.025804588571190834 lr:1.6000000000000003e-05 tokens_per_second_per_gpu:4495.492657700255 |
|
Step 5 | loss:0.03201904147863388 lr:2e-05 tokens_per_second_per_gpu:3109.016764368029 |
|
Step 6 | loss:0.02750915102660656 lr:2.4e-05 tokens_per_second_per_gpu:7041.632259279107 |
|
Step 7 | loss:0.019953470677137375 lr:2.8000000000000003e-05 tokens_per_second_per_gpu:6985.389762201553 |
|
Step 8 | loss:0.03008897602558136 lr:3.2000000000000005e-05 tokens_per_second_per_gpu:7031.603227845363 |
|
Step 9 | loss:0.024956434965133667 lr:3.6e-05 tokens_per_second_per_gpu:6969.649070296816 |
|
Step 10 | loss:0.015605844557285309 lr:4e-05 tokens_per_second_per_gpu:6978.782314648597 |
|
Step 11 | loss:0.025317393243312836 lr:4.4000000000000006e-05 tokens_per_second_per_gpu:3912.514662645861 |
|
Step 12 | loss:0.023303674533963203 lr:4.8e-05 tokens_per_second_per_gpu:6952.359214065986 |
|
Step 13 | loss:0.04082059487700462 lr:5.2000000000000004e-05 tokens_per_second_per_gpu:7062.807389701852 |
|
Step 14 | loss:0.022635383531451225 lr:5.6000000000000006e-05 tokens_per_second_per_gpu:7182.345030649563 |
|
Step 15 | loss:0.013234628364443779 lr:6e-05 tokens_per_second_per_gpu:7032.346083917788 |
|
Step 16 | loss:0.020057788118720055 lr:6.400000000000001e-05 tokens_per_second_per_gpu:6945.262437797177 |
|
Step 17 | loss:0.017696188762784004 lr:6.800000000000001e-05 tokens_per_second_per_gpu:7036.448029271321 |
|
Step 18 | loss:0.01695149391889572 lr:7.2e-05 tokens_per_second_per_gpu:7145.393391713265 |
|
Step 19 | loss:0.013789743185043335 lr:7.6e-05 tokens_per_second_per_gpu:7054.388596746345 |
|
Step 20 | loss:0.011184888891875744 lr:8e-05 tokens_per_second_per_gpu:7122.158977016995 |
|
Step 21 | loss:0.026842668652534485 lr:8.4e-05 tokens_per_second_per_gpu:7099.317465259314 |
|
Step 22 | loss:0.011652654968202114 lr:8.800000000000001e-05 tokens_per_second_per_gpu:7000.915541244278 |
|
Step 23 | loss:0.006112516857683659 lr:9.200000000000001e-05 tokens_per_second_per_gpu:7052.8910069183585 |
|
Step 24 | loss:0.005981456022709608 lr:9.6e-05 tokens_per_second_per_gpu:6983.850857474127 |
|
Step 25 | loss:0.010493079200387001 lr:0.0001 tokens_per_second_per_gpu:7000.069698089665 |
|
Step 26 | loss:0.009683908894658089 lr:9.999512620046522e-05 tokens_per_second_per_gpu:6980.402462036478 |
|
Step 27 | loss:0.014691420830786228 lr:9.998050575201771e-05 tokens_per_second_per_gpu:7009.937438931116 |
|
Step 28 | loss:0.005180081352591515 lr:9.995614150494293e-05 tokens_per_second_per_gpu:6966.166309761949 |
|
Step 29 | loss:0.008658966980874538 lr:9.992203820909906e-05 tokens_per_second_per_gpu:7156.089882332444 |
|
Step 30 | loss:0.01724599301815033 lr:9.987820251299122e-05 tokens_per_second_per_gpu:7118.579765959348 |
|
Step 31 | loss:0.019483113661408424 lr:9.982464296247522e-05 tokens_per_second_per_gpu:2544.1549923843186 |
|
Step 32 | loss:0.004920274019241333 lr:9.976136999909156e-05 tokens_per_second_per_gpu:7092.4482213579 |
|
Step 33 | loss:0.014659096486866474 lr:9.968839595802982e-05 tokens_per_second_per_gpu:6933.290783603298 |
|
Step 34 | loss:0.008841688744723797 lr:9.96057350657239e-05 tokens_per_second_per_gpu:6988.980099526232 |
|
Step 35 | loss:0.005231147166341543 lr:9.951340343707852e-05 tokens_per_second_per_gpu:6990.737998676945 |
|
Step 36 | loss:0.046613603830337524 lr:9.941141907232765e-05 tokens_per_second_per_gpu:7086.891496346473 |
|
Step 37 | loss:0.011419838294386864 lr:9.929980185352526e-05 tokens_per_second_per_gpu:7090.892549711032 |
|
Step 38 | loss:0.02710597775876522 lr:9.917857354066931e-05 tokens_per_second_per_gpu:7128.282089988408 |
|
Step 39 | loss:0.008800565265119076 lr:9.904775776745958e-05 tokens_per_second_per_gpu:7033.301905403689 |
|
Step 40 | loss:0.023295264691114426 lr:9.890738003669029e-05 tokens_per_second_per_gpu:6917.685146717141 |
|
Step 41 | loss:0.001863287528976798 lr:9.875746771527816e-05 tokens_per_second_per_gpu:6967.693380195547 |
|
Step 42 | loss:0.00248198420740664 lr:9.859805002892732e-05 tokens_per_second_per_gpu:7068.858756638031 |
|
Step 43 | loss:0.005183618050068617 lr:9.842915805643155e-05 tokens_per_second_per_gpu:7109.37945148348 |
|
Step 44 | loss:0.0023477256763726473 lr:9.825082472361557e-05 tokens_per_second_per_gpu:6911.212709377753 |
|
Step 45 | loss:0.009867859072983265 lr:9.806308479691595e-05 tokens_per_second_per_gpu:7118.869828033984 |
|
Step 46 | loss:0.0017542128916829824 lr:9.786597487660337e-05 tokens_per_second_per_gpu:7131.8433869124765 |
|
Step 47 | loss:0.006347876973450184 lr:9.765953338964735e-05 tokens_per_second_per_gpu:7078.0691702608865 |
|
Step 48 | loss:0.0025910832919180393 lr:9.744380058222483e-05 tokens_per_second_per_gpu:7033.673326652825 |
|
Step 49 | loss:0.00811317190527916 lr:9.721881851187406e-05 tokens_per_second_per_gpu:6899.814641158904 |
|
Step 50 | loss:0.003559301607310772 lr:9.698463103929542e-05 tokens_per_second_per_gpu:7028.745769769606 |
|
Step 51 | loss:0.006895318161696196 lr:9.674128381980072e-05 tokens_per_second_per_gpu:6913.508470031172 |
|
Step 52 | loss:0.004837665241211653 lr:9.648882429441257e-05 tokens_per_second_per_gpu:7116.479966625115 |
|
Step 53 | loss:0.023339372128248215 lr:9.622730168061567e-05 tokens_per_second_per_gpu:6932.1058200457155 |
|
Step 54 | loss:0.0022509577684104443 lr:9.595676696276172e-05 tokens_per_second_per_gpu:6988.41905663823 |
|
Step 55 | loss:0.004808652214705944 lr:9.567727288213005e-05 tokens_per_second_per_gpu:7145.214253057703 |
|
Step 56 | loss:0.0020097948145121336 lr:9.538887392664544e-05 tokens_per_second_per_gpu:6412.212433895577 |
|
Step 57 | loss:0.0038399628829210997 lr:9.50916263202557e-05 tokens_per_second_per_gpu:7015.980321190468 |
|
Step 58 | loss:0.011330761015415192 lr:9.478558801197065e-05 tokens_per_second_per_gpu:6895.417894930393 |
|
Step 59 | loss:0.0018599978648126125 lr:9.447081866456489e-05 tokens_per_second_per_gpu:6990.92783500862 |
|
Step 60 | loss:0.0014608117053285241 lr:9.414737964294636e-05 tokens_per_second_per_gpu:6988.897245903753 |
|
Step 61 | loss:0.001823238912038505 lr:9.381533400219318e-05 tokens_per_second_per_gpu:7019.940007692442 |
|
Step 62 | loss:0.0018076816340908408 lr:9.347474647526095e-05 tokens_per_second_per_gpu:7106.287742491246 |
|
Step 63 | loss:0.0011915063951164484 lr:9.312568346036288e-05 tokens_per_second_per_gpu:6992.840316129503 |
|
Step 64 | loss:0.0010787455830723047 lr:9.276821300802534e-05 tokens_per_second_per_gpu:7021.278052540677 |
|
Step 65 | loss:0.022880682721734047 lr:9.24024048078213e-05 tokens_per_second_per_gpu:7104.804051497557 |
|
Step 66 | loss:0.003861143486574292 lr:9.202833017478422e-05 tokens_per_second_per_gpu:7118.831070663273 |
|
Step 67 | loss:0.016442544758319855 lr:9.164606203550497e-05 tokens_per_second_per_gpu:7063.082674346704 |
|
Step 68 | loss:0.00486761936917901 lr:9.125567491391476e-05 tokens_per_second_per_gpu:7125.405452614787 |
|
Step 69 | loss:0.0015136034926399589 lr:9.085724491675642e-05 tokens_per_second_per_gpu:7029.652824839256 |
|
Step 70 | loss:0.0009690000442788005 lr:9.045084971874738e-05 tokens_per_second_per_gpu:7135.415617103636 |
|
Step 71 | loss:0.004229606129229069 lr:9.003656854743667e-05 tokens_per_second_per_gpu:7040.127753302347 |
|
Step 72 | loss:0.010976462624967098 lr:8.961448216775954e-05 tokens_per_second_per_gpu:7074.461602454236 |
|
Step 73 | loss:0.0018723574467003345 lr:8.9184672866292e-05 tokens_per_second_per_gpu:7042.3416609674 |
|
Step 74 | loss:0.0016246505547314882 lr:8.874722443520899e-05 tokens_per_second_per_gpu:6997.87070694717 |
|
Step 75 | loss:0.002152395201846957 lr:8.83022221559489e-05 tokens_per_second_per_gpu:6906.177355283252 |
|
Step 76 | loss:0.0014226296916604042 lr:8.784975278258783e-05 tokens_per_second_per_gpu:6921.679084517957 |
|
Step 77 | loss:0.0015887536574155092 lr:8.73899045249266e-05 tokens_per_second_per_gpu:7014.130262707656 |
|
Step 78 | loss:0.01619776524603367 lr:8.692276703129421e-05 tokens_per_second_per_gpu:7120.418673109272 |
|
Step 79 | loss:0.0014319289475679398 lr:8.644843137107059e-05 tokens_per_second_per_gpu:6984.699334598674 |
|
Step 80 | loss:0.007120057940483093 lr:8.596699001693255e-05 tokens_per_second_per_gpu:7116.871071955083 |
|
Step 81 | loss:0.0009436402469873428 lr:8.547853682682604e-05 tokens_per_second_per_gpu:6988.951497761178 |
|
Step 82 | loss:0.0015558796003460884 lr:8.498316702566828e-05 tokens_per_second_per_gpu:7082.372741980646 |
|
Step 83 | loss:0.000648799876216799 lr:8.44809771867835e-05 tokens_per_second_per_gpu:6948.460083718124 |
|
Step 84 | loss:0.009158353321254253 lr:8.397206521307584e-05 tokens_per_second_per_gpu:7039.877119008431 |
|
Step 85 | loss:0.008706255815923214 lr:8.345653031794292e-05 tokens_per_second_per_gpu:7025.180327666526 |
|
Step 86 | loss:0.00923173874616623 lr:8.293447300593402e-05 tokens_per_second_per_gpu:7077.716005758276 |
|
Step 87 | loss:0.003416030667722225 lr:8.240599505315655e-05 tokens_per_second_per_gpu:7127.374109310799 |
|
Step 88 | loss:0.001143158646300435 lr:8.18711994874345e-05 tokens_per_second_per_gpu:6936.582556028229 |
|
Step 89 | loss:0.0015417742542922497 lr:8.133019056822304e-05 tokens_per_second_per_gpu:6900.05216642832 |
|
Step 90 | loss:0.0018219465855509043 lr:8.07830737662829e-05 tokens_per_second_per_gpu:7080.4146388686695 |
|
Step 91 | loss:0.0016905806260183454 lr:8.022995574311876e-05 tokens_per_second_per_gpu:7071.64783387549 |
|
Step 92 | loss:0.0005747248651459813 lr:7.967094433018508e-05 tokens_per_second_per_gpu:6953.482612749782 |
|
Step 93 | loss:0.0011646777857095003 lr:7.910614850786448e-05 tokens_per_second_per_gpu:6980.555197455416 |
|
Step 94 | loss:0.0018550357781350613 lr:7.85356783842216e-05 tokens_per_second_per_gpu:7045.548869670144 |
|
Step 95 | loss:0.00562914926558733 lr:7.795964517353735e-05 tokens_per_second_per_gpu:7035.790802895999 |
|
Step 96 | loss:0.0007901251083239913 lr:7.737816117462752e-05 tokens_per_second_per_gpu:7084.417608533555 |
|
Step 97 | loss:0.0030633523128926754 lr:7.679133974894983e-05 tokens_per_second_per_gpu:7147.459942884517 |
|
Step 98 | loss:0.0037855948321521282 lr:7.619929529850397e-05 tokens_per_second_per_gpu:7067.728652316575 |
|
Step 99 | loss:0.006067368201911449 lr:7.560214324352858e-05 tokens_per_second_per_gpu:7140.1441528522055 |
|
Step 100 | loss:0.0013416701694950461 lr:7.500000000000001e-05 tokens_per_second_per_gpu:6994.104421847807 |
|
Step 101 | loss:0.0007225268636830151 lr:7.439298295693665e-05 tokens_per_second_per_gpu:6945.514192300232 |
|
Step 102 | loss:0.0022766063921153545 lr:7.378121045351378e-05 tokens_per_second_per_gpu:7111.714240713364 |
|
Step 103 | loss:0.0017433242173865438 lr:7.316480175599309e-05 tokens_per_second_per_gpu:7105.047032557444 |
|
Step 104 | loss:0.001276876893825829 lr:7.254387703447154e-05 tokens_per_second_per_gpu:7139.60565481186 |
|
Step 105 | loss:0.0008742883801460266 lr:7.191855733945387e-05 tokens_per_second_per_gpu:7064.512973625912 |
|
Step 106 | loss:0.004383294843137264 lr:7.128896457825364e-05 tokens_per_second_per_gpu:7009.914961246837 |
|
Step 107 | loss:0.003905724734067917 lr:7.06552214912271e-05 tokens_per_second_per_gpu:7108.881238582078 |
|
Step 108 | loss:0.004067558329552412 lr:7.001745162784477e-05 tokens_per_second_per_gpu:7072.668814670594 |
|
Step 109 | loss:0.0007550563313998282 lr:6.937577932260515e-05 tokens_per_second_per_gpu:6917.831149012028 |
|
Step 110 | loss:0.0017923268023878336 lr:6.873032967079561e-05 tokens_per_second_per_gpu:6955.323379756017 |
|
Step 111 | loss:0.0007057379116304219 lr:6.808122850410461e-05 tokens_per_second_per_gpu:6904.948376368929 |
|
Step 112 | loss:0.0007379968883469701 lr:6.742860236609077e-05 tokens_per_second_per_gpu:7153.398547283699 |
|
Step 113 | loss:0.0018347478471696377 lr:6.677257848751277e-05 tokens_per_second_per_gpu:7188.034361670168 |
|
Step 114 | loss:0.007473267614841461 lr:6.611328476152557e-05 tokens_per_second_per_gpu:7126.322488015339 |
|
Step 115 | loss:0.0018762246472761035 lr:6.545084971874738e-05 tokens_per_second_per_gpu:6955.728395223383 |
|
Step 116 | loss:0.0016810846282169223 lr:6.478540250220234e-05 tokens_per_second_per_gpu:7127.168276028668 |
|
Step 117 | loss:0.001141136628575623 lr:6.411707284214384e-05 tokens_per_second_per_gpu:7021.080865826398 |
|
Step 118 | loss:0.0010234861401841044 lr:6.344599103076329e-05 tokens_per_second_per_gpu:7060.332693507492 |
|
Step 119 | loss:0.00130595697555691 lr:6.277228789678953e-05 tokens_per_second_per_gpu:7142.475629382465 |
|
Step 120 | loss:0.004872153513133526 lr:6.209609477998338e-05 tokens_per_second_per_gpu:7092.480263189864 |
|
Step 121 | loss:0.001116426195949316 lr:6.141754350553279e-05 tokens_per_second_per_gpu:7121.562264475883 |
|
Step 122 | loss:0.0046634073369205 lr:6.073676635835317e-05 tokens_per_second_per_gpu:7150.269690216827 |
|
Step 123 | loss:0.001187909278087318 lr:6.005389605729824e-05 tokens_per_second_per_gpu:6951.717196495926 |
|
Step 124 | loss:0.0008000991656444967 lr:5.9369065729286245e-05 tokens_per_second_per_gpu:6989.895599432251 |
|
Step 125 | loss:0.00087369215907529 lr:5.868240888334653e-05 tokens_per_second_per_gpu:6996.036151890579 |
|
Step 126 | loss:0.00484832376241684 lr:5.799405938459175e-05 tokens_per_second_per_gpu:7045.847468191668 |
|
Step 127 | loss:0.0006868625059723854 lr:5.730415142812059e-05 tokens_per_second_per_gpu:7098.86436928685 |
|
Step 128 | loss:0.00047956101479940116 lr:5.661281951285613e-05 tokens_per_second_per_gpu:6940.012332908143 |
|
Step 129 | loss:0.0004669419431593269 lr:5.5920198415325064e-05 tokens_per_second_per_gpu:6972.946487214679 |
|
Step 130 | loss:0.0004756593843922019 lr:5.522642316338268e-05 tokens_per_second_per_gpu:6968.344154931831 |
|
Step 131 | loss:0.0011142973089590669 lr:5.453162900988902e-05 tokens_per_second_per_gpu:7121.680284615958 |
|
Step 132 | loss:0.004303267225623131 lr:5.383595140634093e-05 tokens_per_second_per_gpu:6915.749573456138 |
|
Step 133 | loss:0.0009837456746026874 lr:5.313952597646568e-05 tokens_per_second_per_gpu:6963.5640457391155 |
|
Step 134 | loss:0.0007821984472684562 lr:5.244248848978067e-05 tokens_per_second_per_gpu:7138.879899535869 |
|
Step 135 | loss:0.0006728306761942804 lr:5.174497483512506e-05 tokens_per_second_per_gpu:7011.110557891249 |
|
Step 136 | loss:0.0004501852672547102 lr:5.104712099416785e-05 tokens_per_second_per_gpu:7018.34305051074 |
|
Step 137 | loss:0.0012011223006993532 lr:5.034906301489808e-05 tokens_per_second_per_gpu:7123.661720842122 |
|
Step 138 | loss:0.0005516944802366197 lr:4.965093698510193e-05 tokens_per_second_per_gpu:7022.055921962106 |
|
Step 139 | loss:0.0005424295668490231 lr:4.895287900583216e-05 tokens_per_second_per_gpu:7145.3342400065285 |
|
Step 140 | loss:0.0013666569720953703 lr:4.825502516487497e-05 tokens_per_second_per_gpu:7030.732414159867 |
|
Step 141 | loss:0.0017626546323299408 lr:4.755751151021934e-05 tokens_per_second_per_gpu:7108.107377261014 |
|
Step 142 | loss:0.001241979654878378 lr:4.6860474023534335e-05 tokens_per_second_per_gpu:7153.268644133736 |
|
Step 143 | loss:0.0006725737475790083 lr:4.616404859365907e-05 tokens_per_second_per_gpu:7101.217530317505 |
|
Step 144 | loss:0.0007120270165614784 lr:4.5468370990111006e-05 tokens_per_second_per_gpu:7082.544184263966 |
|
Step 145 | loss:0.00043776549864560366 lr:4.477357683661734e-05 tokens_per_second_per_gpu:6955.9781654954595 |
|
Step 146 | loss:0.0031522451899945736 lr:4.407980158467495e-05 tokens_per_second_per_gpu:7097.638512378798 |
|
Step 147 | loss:0.001153664430603385 lr:4.3387180487143876e-05 tokens_per_second_per_gpu:7070.57866441772 |
|
Step 148 | loss:0.0021554091945290565 lr:4.269584857187943e-05 tokens_per_second_per_gpu:7003.975358441163 |
|
Step 149 | loss:0.0009045489132404327 lr:4.2005940615408264e-05 tokens_per_second_per_gpu:7100.238244021048 |
|
Step 150 | loss:0.002245988929644227 lr:4.131759111665349e-05 tokens_per_second_per_gpu:7142.71458244575 |
|
Step 151 | loss:0.0010295120300725102 lr:4.063093427071376e-05 tokens_per_second_per_gpu:6956.780398258748 |
|
Step 152 | loss:0.0005752541474066675 lr:3.9946103942701777e-05 tokens_per_second_per_gpu:6989.410579757051 |
|
Step 153 | loss:0.0009264898835681379 lr:3.926323364164684e-05 tokens_per_second_per_gpu:7127.296761001994 |
|
Step 154 | loss:0.003229705849662423 lr:3.858245649446721e-05 tokens_per_second_per_gpu:7106.645426344949 |
|
Step 155 | loss:0.0008876493666321039 lr:3.790390522001662e-05 tokens_per_second_per_gpu:7080.0082234765805 |
|
Step 156 | loss:0.00046552784624509513 lr:3.7227712103210486e-05 tokens_per_second_per_gpu:6959.818097074865 |
|
Step 157 | loss:0.002298208186402917 lr:3.655400896923672e-05 tokens_per_second_per_gpu:7129.613433958085 |
|
Step 158 | loss:0.0004902664804831147 lr:3.588292715785617e-05 tokens_per_second_per_gpu:6978.609449926726 |
|
Step 159 | loss:0.0005792560987174511 lr:3.5214597497797684e-05 tokens_per_second_per_gpu:6997.766216766654 |
|
Step 160 | loss:0.0006528786034323275 lr:3.4549150281252636e-05 tokens_per_second_per_gpu:6991.4232154695455 |
|
Step 161 | loss:0.00048036337830126286 lr:3.388671523847445e-05 tokens_per_second_per_gpu:6945.076606008601 |
|
Step 162 | loss:0.0011659618467092514 lr:3.322742151248725e-05 tokens_per_second_per_gpu:7071.719431199827 |
|
Step 163 | loss:0.00043439690489321947 lr:3.257139763390925e-05 tokens_per_second_per_gpu:6943.699937265891 |
|
Step 164 | loss:0.000437648210208863 lr:3.1918771495895396e-05 tokens_per_second_per_gpu:6991.309806930395 |
|
Step 165 | loss:0.0018092856043949723 lr:3.12696703292044e-05 tokens_per_second_per_gpu:7119.289527867441 |
|
Step 166 | loss:0.0005309141124598682 lr:3.062422067739485e-05 tokens_per_second_per_gpu:6995.726446456126 |
|
Step 167 | loss:0.0016090822173282504 lr:2.9982548372155263e-05 tokens_per_second_per_gpu:7069.169459989144 |
|
Step 168 | loss:0.0008133113151416183 lr:2.934477850877292e-05 tokens_per_second_per_gpu:7133.314904147402 |
|
Step 169 | loss:0.0004484521341510117 lr:2.8711035421746367e-05 tokens_per_second_per_gpu:6970.984479843337 |
|
Step 170 | loss:0.0007173720514401793 lr:2.8081442660546125e-05 tokens_per_second_per_gpu:7097.282608320479 |
|
Step 171 | loss:0.000959720928221941 lr:2.7456122965528475e-05 tokens_per_second_per_gpu:7139.6154456797985 |
|
Step 172 | loss:0.0008743423386476934 lr:2.6835198244006927e-05 tokens_per_second_per_gpu:7047.963660428627 |
|
Step 173 | loss:0.0003595231974031776 lr:2.6218789546486234e-05 tokens_per_second_per_gpu:6943.0272467350715 |
|
Step 174 | loss:0.0012123918859288096 lr:2.560701704306336e-05 tokens_per_second_per_gpu:7145.54271902521 |
|
Step 175 | loss:0.0005709865945391357 lr:2.500000000000001e-05 tokens_per_second_per_gpu:7055.571249683241 |
|
Step 176 | loss:0.0007623767014592886 lr:2.4397856756471432e-05 tokens_per_second_per_gpu:7064.703892124262 |
|
Step 177 | loss:0.0007825460634194314 lr:2.3800704701496053e-05 tokens_per_second_per_gpu:7068.897197028465 |
|
Step 178 | loss:0.0005891617038287222 lr:2.3208660251050158e-05 tokens_per_second_per_gpu:7069.646887090852 |
|
Step 179 | loss:0.0025518257170915604 lr:2.2621838825372493e-05 tokens_per_second_per_gpu:7003.098277303123 |
|
Step 180 | loss:0.0004264521994628012 lr:2.2040354826462668e-05 tokens_per_second_per_gpu:6957.853738042179 |
|
Step 181 | loss:0.000505225732922554 lr:2.1464321615778422e-05 tokens_per_second_per_gpu:7026.185321014853 |
|
Step 182 | loss:0.0008991779177449644 lr:2.0893851492135537e-05 tokens_per_second_per_gpu:7158.764772507499 |
|
Step 183 | loss:0.0007549175643362105 lr:2.0329055669814934e-05 tokens_per_second_per_gpu:7082.381343388264 |
|
Step 184 | loss:0.0004400451434776187 lr:1.977004425688126e-05 tokens_per_second_per_gpu:6981.625247487258 |
|
Step 185 | loss:0.0007796370191499591 lr:1.9216926233717085e-05 tokens_per_second_per_gpu:7055.3425013012065 |
|
Step 186 | loss:0.00043590678251348436 lr:1.866980943177699e-05 tokens_per_second_per_gpu:6935.587584510185 |
|
Step 187 | loss:0.0004538899229373783 lr:1.8128800512565513e-05 tokens_per_second_per_gpu:7030.828664997653 |
|
Step 188 | loss:0.0004330903757363558 lr:1.7594004946843456e-05 tokens_per_second_per_gpu:6976.247465295093 |
|
Step 189 | loss:0.0011968042235821486 lr:1.7065526994065973e-05 tokens_per_second_per_gpu:6931.96609846674 |
|
Step 190 | loss:0.00047548883594572544 lr:1.6543469682057106e-05 tokens_per_second_per_gpu:7050.796475919805 |
|
Step 191 | loss:0.0006672032759524882 lr:1.602793478692419e-05 tokens_per_second_per_gpu:7014.628074331912 |
|
Step 192 | loss:0.00042430919711478055 lr:1.551902281321651e-05 tokens_per_second_per_gpu:6936.297107186702 |
|
Step 193 | loss:0.000518566055689007 lr:1.5016832974331724e-05 tokens_per_second_per_gpu:7133.665460935306 |
|
Step 194 | loss:0.00041731898090802133 lr:1.4521463173173965e-05 tokens_per_second_per_gpu:6992.126666142328 |
|
Step 195 | loss:0.0006135033909231424 lr:1.4033009983067452e-05 tokens_per_second_per_gpu:7034.93375731155 |
|
Step 196 | loss:0.00041678230627439916 lr:1.3551568628929434e-05 tokens_per_second_per_gpu:6996.24987636046 |
|
Step 197 | loss:0.0008842310635372996 lr:1.3077232968705805e-05 tokens_per_second_per_gpu:7099.332839742743 |
|
Step 198 | loss:0.0014190628426149487 lr:1.2610095475073414e-05 tokens_per_second_per_gpu:7004.903938364148 |
|
Step 199 | loss:0.0006429760251194239 lr:1.2150247217412186e-05 tokens_per_second_per_gpu:7069.508314904658 |
|
Step 200 | loss:0.0005709484103135765 lr:1.1697777844051105e-05 tokens_per_second_per_gpu:7054.728498009769 |
|
Step 201 | loss:0.0006574671715497971 lr:1.1252775564791024e-05 tokens_per_second_per_gpu:7063.252101325385 |
|
Step 202 | loss:0.00046187403495423496 lr:1.0815327133708015e-05 tokens_per_second_per_gpu:7047.761559932023 |
|
Step 203 | loss:0.00046730577014386654 lr:1.0385517832240471e-05 tokens_per_second_per_gpu:7007.912124557264 |
|
Step 204 | loss:0.00042251235572621226 lr:9.963431452563332e-06 tokens_per_second_per_gpu:7000.4046814119865 |
|
Step 205 | loss:0.0008081925916485488 lr:9.549150281252633e-06 tokens_per_second_per_gpu:7026.77561165733 |
|
Step 206 | loss:0.00041264371247962117 lr:9.142755083243576e-06 tokens_per_second_per_gpu:7040.357453873263 |
|
Step 207 | loss:0.0008483533165417612 lr:8.744325086085248e-06 tokens_per_second_per_gpu:7147.754060961543 |
|
Step 208 | loss:0.0016957520274445415 lr:8.353937964495029e-06 tokens_per_second_per_gpu:7064.119182752957 |
|
Step 209 | loss:0.0008601445006206632 lr:7.971669825215788e-06 tokens_per_second_per_gpu:7151.071781684289 |
|
Step 210 | loss:0.0006466899649240077 lr:7.597595192178702e-06 tokens_per_second_per_gpu:7046.883227494138 |
|
Step 211 | loss:0.0006277145002968609 lr:7.2317869919746705e-06 tokens_per_second_per_gpu:7087.731898402442 |
|
Step 212 | loss:0.0009709634468890727 lr:6.874316539637127e-06 tokens_per_second_per_gpu:7040.425742568532 |
|
Step 213 | loss:0.0004221511771902442 lr:6.52525352473905e-06 tokens_per_second_per_gpu:7069.030373751735 |
|
Step 214 | loss:0.00041409535333514214 lr:6.184665997806832e-06 tokens_per_second_per_gpu:6963.447651186713 |
|
Step 215 | loss:0.0005849138251505792 lr:5.852620357053651e-06 tokens_per_second_per_gpu:7056.332662297273 |
|
Step 216 | loss:0.00109096709638834 lr:5.529181335435124e-06 tokens_per_second_per_gpu:7064.623409572992 |
|
Step 217 | loss:0.0006437082774937153 lr:5.214411988029355e-06 tokens_per_second_per_gpu:7093.952966518385 |
|
Step 218 | loss:0.0005631728563457727 lr:4.908373679744316e-06 tokens_per_second_per_gpu:7056.5388120404305 |
|
Step 219 | loss:0.0005406254203990102 lr:4.611126073354571e-06 tokens_per_second_per_gpu:6993.811944604283 |
|
Step 220 | loss:0.0006842242437414825 lr:4.322727117869951e-06 tokens_per_second_per_gpu:7089.956528397737 |
|
Step 221 | loss:0.0010190687607973814 lr:4.043233037238281e-06 tokens_per_second_per_gpu:6994.372358564081 |
|
Step 222 | loss:0.0012112787226215005 lr:3.772698319384349e-06 tokens_per_second_per_gpu:7124.531182156507 |
|
Step 223 | loss:0.002517084125429392 lr:3.511175705587433e-06 tokens_per_second_per_gpu:6918.0543446720685 |
|
Step 224 | loss:0.0005589801003225148 lr:3.258716180199278e-06 tokens_per_second_per_gpu:7023.829994539822 |
|
Step 225 | loss:0.0017649466171860695 lr:3.0153689607045845e-06 tokens_per_second_per_gpu:7047.696763117713 |
|
Step 226 | loss:0.0005779994535259902 lr:2.7811814881259503e-06 tokens_per_second_per_gpu:7115.241067914687 |
|
Step 227 | loss:0.002819615416228771 lr:2.5561994177751737e-06 tokens_per_second_per_gpu:6396.3266785761125 |
|
Step 228 | loss:0.000707148399669677 lr:2.340466610352654e-06 tokens_per_second_per_gpu:7061.186731356613 |
|
Step 229 | loss:0.00045056085218675435 lr:2.134025123396638e-06 tokens_per_second_per_gpu:7010.929619975376 |
|
Step 230 | loss:0.00041339790914207697 lr:1.9369152030840556e-06 tokens_per_second_per_gpu:7005.465727086567 |
|
Step 231 | loss:0.0006742652622051537 lr:1.7491752763844293e-06 tokens_per_second_per_gpu:7148.12920952124 |
|
Step 232 | loss:0.0014700341271236539 lr:1.5708419435684462e-06 tokens_per_second_per_gpu:6892.28837028219 |
|
Step 233 | loss:0.0007649718318134546 lr:1.4019499710726913e-06 tokens_per_second_per_gpu:7103.177275214076 |
|
Step 234 | loss:0.0005914740031585097 lr:1.2425322847218368e-06 tokens_per_second_per_gpu:7044.154794297553 |
|
Step 235 | loss:0.0004285259637981653 lr:1.0926199633097157e-06 tokens_per_second_per_gpu:6988.588311349487 |
|
Step 236 | loss:0.0006066249334253371 lr:9.522422325404235e-07 tokens_per_second_per_gpu:7015.093578410308 |
|
Step 237 | loss:0.0005865789717063308 lr:8.214264593307098e-07 tokens_per_second_per_gpu:7011.931210086256 |
|
Step 238 | loss:0.0004117491189390421 lr:7.001981464747565e-07 tokens_per_second_per_gpu:6933.225985834734 |
|
Step 239 | loss:0.0011568713234737515 lr:5.885809276723608e-07 tokens_per_second_per_gpu:7057.2877735840575 |
|
Step 240 | loss:0.0004361141473054886 lr:4.865965629214819e-07 tokens_per_second_per_gpu:6973.410298974162 |
|
Step 241 | loss:0.0006616075406782329 lr:3.9426493427611177e-07 tokens_per_second_per_gpu:7082.926011712191 |
|
Step 242 | loss:0.0025170850567519665 lr:3.1160404197018154e-07 tokens_per_second_per_gpu:7105.696262400482 |
|
Step 243 | loss:0.0010358932195231318 lr:2.386300009084408e-07 tokens_per_second_per_gpu:7042.329143139679 |
|
Step 244 | loss:0.000709235668182373 lr:1.753570375247815e-07 tokens_per_second_per_gpu:7150.839813174746 |
|
Step 245 | loss:0.00041517047793604434 lr:1.2179748700879012e-07 tokens_per_second_per_gpu:6961.233781487478 |
|
Step 246 | loss:0.0005878652445971966 lr:7.796179090094891e-08 tokens_per_second_per_gpu:7042.633897002825 |
|
Step 247 | loss:0.0003984997747465968 lr:4.385849505708084e-08 tokens_per_second_per_gpu:7012.575831630716 |
|
Step 248 | loss:0.0005327527760528028 lr:1.949424798228239e-08 tokens_per_second_per_gpu:7041.7383802691475 |
|
Step 249 | loss:0.0005802221712656319 lr:4.873799534788059e-09 tokens_per_second_per_gpu:7019.500158830062 |
|
Step 250 | loss:0.0008447980508208275 lr:0.0 tokens_per_second_per_gpu:7118.770256418007 |
|
|