|
Step 1 | loss:0.05883090943098068 lr:4.000000000000001e-06 tokens_per_second_per_gpu:2611.2751764532522 |
|
Step 2 | loss:0.1065659150481224 lr:8.000000000000001e-06 tokens_per_second_per_gpu:934.6274612544344 |
|
Step 3 | loss:0.10369853675365448 lr:1.2e-05 tokens_per_second_per_gpu:1633.880920446792 |
|
Step 4 | loss:0.06993220746517181 lr:1.6000000000000003e-05 tokens_per_second_per_gpu:2003.4908633730493 |
|
Step 5 | loss:0.0536116324365139 lr:2e-05 tokens_per_second_per_gpu:7071.469899338988 |
|
Step 6 | loss:0.06969004124403 lr:2.4e-05 tokens_per_second_per_gpu:7059.030951476349 |
|
Step 7 | loss:0.12010835856199265 lr:2.8000000000000003e-05 tokens_per_second_per_gpu:5949.667488090579 |
|
Step 8 | loss:0.051114361733198166 lr:3.2000000000000005e-05 tokens_per_second_per_gpu:7016.083742408133 |
|
Step 9 | loss:0.04927004128694534 lr:3.6e-05 tokens_per_second_per_gpu:6961.956915402864 |
|
Step 10 | loss:0.08280401676893234 lr:4e-05 tokens_per_second_per_gpu:1167.2202124089874 |
|
Step 11 | loss:0.08619477599859238 lr:4.4000000000000006e-05 tokens_per_second_per_gpu:1139.6981710490575 |
|
Step 12 | loss:0.07909607887268066 lr:4.8e-05 tokens_per_second_per_gpu:7098.479896993361 |
|
Step 13 | loss:0.05969027802348137 lr:5.2000000000000004e-05 tokens_per_second_per_gpu:7094.291274042624 |
|
Step 14 | loss:0.06413069367408752 lr:5.6000000000000006e-05 tokens_per_second_per_gpu:6855.497619317191 |
|
Step 15 | loss:0.0635824203491211 lr:6e-05 tokens_per_second_per_gpu:7149.597258818894 |
|
Step 16 | loss:0.07948478311300278 lr:6.400000000000001e-05 tokens_per_second_per_gpu:6649.963046324791 |
|
Step 17 | loss:0.0760459378361702 lr:6.800000000000001e-05 tokens_per_second_per_gpu:6535.773747266753 |
|
Step 18 | loss:0.05200653523206711 lr:7.2e-05 tokens_per_second_per_gpu:6886.203505416455 |
|
Step 19 | loss:0.05042438581585884 lr:7.6e-05 tokens_per_second_per_gpu:7118.639800231809 |
|
Step 20 | loss:0.05962265655398369 lr:8e-05 tokens_per_second_per_gpu:6906.562284368418 |
|
Step 21 | loss:0.06424694508314133 lr:8.4e-05 tokens_per_second_per_gpu:6511.331095251028 |
|
Step 22 | loss:0.0616440623998642 lr:8.800000000000001e-05 tokens_per_second_per_gpu:1586.2845500246515 |
|
Step 23 | loss:0.06509910523891449 lr:9.200000000000001e-05 tokens_per_second_per_gpu:6546.337467431212 |
|
Step 24 | loss:0.06912975758314133 lr:9.6e-05 tokens_per_second_per_gpu:661.4638977396842 |
|
Step 25 | loss:0.04250991344451904 lr:0.0001 tokens_per_second_per_gpu:6657.945357791943 |
|
Step 26 | loss:0.04667964577674866 lr:9.999512620046522e-05 tokens_per_second_per_gpu:5958.279583441191 |
|
Step 27 | loss:0.03431122750043869 lr:9.998050575201771e-05 tokens_per_second_per_gpu:4794.290307232642 |
|
Step 28 | loss:0.07390312105417252 lr:9.995614150494293e-05 tokens_per_second_per_gpu:6607.071950662243 |
|
Step 29 | loss:0.039681028574705124 lr:9.992203820909906e-05 tokens_per_second_per_gpu:6552.995122018929 |
|
Step 30 | loss:0.03120642900466919 lr:9.987820251299122e-05 tokens_per_second_per_gpu:6945.21487409806 |
|
Step 31 | loss:0.03754393011331558 lr:9.982464296247522e-05 tokens_per_second_per_gpu:6547.6040707603825 |
|
Step 32 | loss:0.0607815682888031 lr:9.976136999909156e-05 tokens_per_second_per_gpu:6445.429115622666 |
|
Step 33 | loss:0.022207770496606827 lr:9.968839595802982e-05 tokens_per_second_per_gpu:6928.181601878918 |
|
Step 34 | loss:0.011908555403351784 lr:9.96057350657239e-05 tokens_per_second_per_gpu:7062.763301040281 |
|
Step 35 | loss:0.013044281862676144 lr:9.951340343707852e-05 tokens_per_second_per_gpu:5892.149529787437 |
|
Step 36 | loss:0.015627676621079445 lr:9.941141907232765e-05 tokens_per_second_per_gpu:7135.602800487149 |
|
Step 37 | loss:0.016328388825058937 lr:9.929980185352526e-05 tokens_per_second_per_gpu:7081.303577017091 |
|
Step 38 | loss:0.005116661079227924 lr:9.917857354066931e-05 tokens_per_second_per_gpu:7032.88413547479 |
|
Step 39 | loss:0.020706845447421074 lr:9.904775776745958e-05 tokens_per_second_per_gpu:7051.139499141364 |
|
Step 40 | loss:0.023872001096606255 lr:9.890738003669029e-05 tokens_per_second_per_gpu:6903.941838072107 |
|
Step 41 | loss:0.013512889854609966 lr:9.875746771527816e-05 tokens_per_second_per_gpu:6883.324140607382 |
|
Step 42 | loss:0.023559028282761574 lr:9.859805002892732e-05 tokens_per_second_per_gpu:5220.333405477438 |
|
Step 43 | loss:0.009499269537627697 lr:9.842915805643155e-05 tokens_per_second_per_gpu:6883.461614545596 |
|
Step 44 | loss:0.006331244483590126 lr:9.825082472361557e-05 tokens_per_second_per_gpu:6617.3389363356155 |
|
Step 45 | loss:0.015614012256264687 lr:9.806308479691595e-05 tokens_per_second_per_gpu:7068.646531980263 |
|
Step 46 | loss:0.04139475151896477 lr:9.786597487660337e-05 tokens_per_second_per_gpu:6651.108418816515 |
|
Step 47 | loss:0.01379504892975092 lr:9.765953338964735e-05 tokens_per_second_per_gpu:7110.698789407686 |
|
Step 48 | loss:0.00873752310872078 lr:9.744380058222483e-05 tokens_per_second_per_gpu:6883.427074840145 |
|
Step 49 | loss:0.0025170650333166122 lr:9.721881851187406e-05 tokens_per_second_per_gpu:6530.497468449956 |
|
Step 50 | loss:0.049308665096759796 lr:9.698463103929542e-05 tokens_per_second_per_gpu:6657.147320144416 |
|
Step 51 | loss:0.013455690816044807 lr:9.674128381980072e-05 tokens_per_second_per_gpu:6629.482383767396 |
|
Step 52 | loss:0.015905072912573814 lr:9.648882429441257e-05 tokens_per_second_per_gpu:6450.48251411474 |
|
Step 53 | loss:0.002275326522067189 lr:9.622730168061567e-05 tokens_per_second_per_gpu:6824.529962920934 |
|
Step 54 | loss:0.01587088219821453 lr:9.595676696276172e-05 tokens_per_second_per_gpu:6521.132932898683 |
|
Step 55 | loss:0.005622063297778368 lr:9.567727288213005e-05 tokens_per_second_per_gpu:6531.4447554583185 |
|
Step 56 | loss:0.004901554435491562 lr:9.538887392664544e-05 tokens_per_second_per_gpu:5633.388308641928 |
|
Step 57 | loss:0.0019407781073823571 lr:9.50916263202557e-05 tokens_per_second_per_gpu:6906.319790444152 |
|
Step 58 | loss:0.0060058278031647205 lr:9.478558801197065e-05 tokens_per_second_per_gpu:6856.7635894640125 |
|
Step 59 | loss:0.005499544087797403 lr:9.447081866456489e-05 tokens_per_second_per_gpu:6642.833062245913 |
|
Step 60 | loss:0.013067233376204967 lr:9.414737964294636e-05 tokens_per_second_per_gpu:6643.617905289443 |
|
Step 61 | loss:0.00852174125611782 lr:9.381533400219318e-05 tokens_per_second_per_gpu:6553.863668850757 |
|
Step 62 | loss:0.007614427246153355 lr:9.347474647526095e-05 tokens_per_second_per_gpu:7052.1698789666825 |
|
Step 63 | loss:0.01105488557368517 lr:9.312568346036288e-05 tokens_per_second_per_gpu:7058.621720464415 |
|
Step 64 | loss:0.013129975646734238 lr:9.276821300802534e-05 tokens_per_second_per_gpu:6528.830458609242 |
|
Step 65 | loss:0.0036676388699561357 lr:9.24024048078213e-05 tokens_per_second_per_gpu:7099.631236412344 |
|
Step 66 | loss:0.0017698833253234625 lr:9.202833017478422e-05 tokens_per_second_per_gpu:7080.763740321347 |
|
Step 67 | loss:0.0006935734418220818 lr:9.164606203550497e-05 tokens_per_second_per_gpu:6518.712752628263 |
|
Step 68 | loss:0.006906419526785612 lr:9.125567491391476e-05 tokens_per_second_per_gpu:6591.018648894371 |
|
Step 69 | loss:0.002882704371586442 lr:9.085724491675642e-05 tokens_per_second_per_gpu:7116.528546515005 |
|
Step 70 | loss:0.00394488824531436 lr:9.045084971874738e-05 tokens_per_second_per_gpu:6827.659097483362 |
|
Step 71 | loss:0.0019539296627044678 lr:9.003656854743667e-05 tokens_per_second_per_gpu:6636.826259591227 |
|
Step 72 | loss:0.0005638383445329964 lr:8.961448216775954e-05 tokens_per_second_per_gpu:6894.328447107831 |
|
Step 73 | loss:0.0041533648036420345 lr:8.9184672866292e-05 tokens_per_second_per_gpu:6878.894826933022 |
|
Step 74 | loss:0.0009008919005282223 lr:8.874722443520899e-05 tokens_per_second_per_gpu:7076.127400677781 |
|
Step 75 | loss:0.002822647336870432 lr:8.83022221559489e-05 tokens_per_second_per_gpu:6604.422504566621 |
|
Step 76 | loss:0.0012791752815246582 lr:8.784975278258783e-05 tokens_per_second_per_gpu:6662.954752142708 |
|
Step 77 | loss:0.0034571527503430843 lr:8.73899045249266e-05 tokens_per_second_per_gpu:6878.229928630995 |
|
Step 78 | loss:0.0003115411091130227 lr:8.692276703129421e-05 tokens_per_second_per_gpu:6621.282027338098 |
|
Step 79 | loss:0.004982416983693838 lr:8.644843137107059e-05 tokens_per_second_per_gpu:7065.362582716634 |
|
Step 80 | loss:0.005641724448651075 lr:8.596699001693255e-05 tokens_per_second_per_gpu:6818.3028179613775 |
|
Step 81 | loss:0.007741517852991819 lr:8.547853682682604e-05 tokens_per_second_per_gpu:7068.3698595558735 |
|
Step 82 | loss:0.004250807221978903 lr:8.498316702566828e-05 tokens_per_second_per_gpu:6417.045004042305 |
|
Step 83 | loss:0.0003256700874771923 lr:8.44809771867835e-05 tokens_per_second_per_gpu:5288.4226300841865 |
|
Step 84 | loss:0.002000636188313365 lr:8.397206521307584e-05 tokens_per_second_per_gpu:6634.974566286588 |
|
Step 85 | loss:0.000544965558219701 lr:8.345653031794292e-05 tokens_per_second_per_gpu:6634.014989792351 |
|
Step 86 | loss:0.001567141618579626 lr:8.293447300593402e-05 tokens_per_second_per_gpu:6860.262958802247 |
|
Step 87 | loss:0.0006420569843612611 lr:8.240599505315655e-05 tokens_per_second_per_gpu:6905.004579443605 |
|
Step 88 | loss:0.007808868307620287 lr:8.18711994874345e-05 tokens_per_second_per_gpu:6632.698013944389 |
|
Step 89 | loss:0.00021798825764562935 lr:8.133019056822304e-05 tokens_per_second_per_gpu:6439.540558933112 |
|
Step 90 | loss:0.00026628863997757435 lr:8.07830737662829e-05 tokens_per_second_per_gpu:6905.334910011535 |
|
Step 91 | loss:0.009381849318742752 lr:8.022995574311876e-05 tokens_per_second_per_gpu:6520.647037620224 |
|
Step 92 | loss:0.0001644226722419262 lr:7.967094433018508e-05 tokens_per_second_per_gpu:6899.679949135617 |
|
Step 93 | loss:0.00557605130597949 lr:7.910614850786448e-05 tokens_per_second_per_gpu:6619.658986620156 |
|
Step 94 | loss:0.0020753894932568073 lr:7.85356783842216e-05 tokens_per_second_per_gpu:6527.52192209492 |
|
Step 95 | loss:0.0009785438887774944 lr:7.795964517353735e-05 tokens_per_second_per_gpu:6851.988618005506 |
|
Step 96 | loss:0.00023535460059065372 lr:7.737816117462752e-05 tokens_per_second_per_gpu:6892.176184929317 |
|
Step 97 | loss:0.00012474882532842457 lr:7.679133974894983e-05 tokens_per_second_per_gpu:6853.329438980445 |
|
Step 98 | loss:0.003538035321980715 lr:7.619929529850397e-05 tokens_per_second_per_gpu:6631.218921573058 |
|
Step 99 | loss:0.00324582913890481 lr:7.560214324352858e-05 tokens_per_second_per_gpu:5222.440706457179 |
|
Step 100 | loss:6.167021638248116e-05 lr:7.500000000000001e-05 tokens_per_second_per_gpu:6919.006783887625 |
|
Step 101 | loss:0.0016939690103754401 lr:7.439298295693665e-05 tokens_per_second_per_gpu:6406.025615551767 |
|
Step 102 | loss:0.0006084628403186798 lr:7.378121045351378e-05 tokens_per_second_per_gpu:6877.084720206567 |
|
Step 103 | loss:0.00017363041115459055 lr:7.316480175599309e-05 tokens_per_second_per_gpu:5929.288778810249 |
|
Step 104 | loss:0.0005308957188390195 lr:7.254387703447154e-05 tokens_per_second_per_gpu:7095.644998839233 |
|
Step 105 | loss:0.0019598398357629776 lr:7.191855733945387e-05 tokens_per_second_per_gpu:6873.67040419656 |
|
Step 106 | loss:0.0008263597846962512 lr:7.128896457825364e-05 tokens_per_second_per_gpu:6628.67102415756 |
|
Step 107 | loss:0.0006074818084016442 lr:7.06552214912271e-05 tokens_per_second_per_gpu:6630.428254088887 |
|
Step 108 | loss:0.0003068344376515597 lr:7.001745162784477e-05 tokens_per_second_per_gpu:6420.439101038877 |
|
Step 109 | loss:0.0009827185422182083 lr:6.937577932260515e-05 tokens_per_second_per_gpu:6656.780873474644 |
|
Step 110 | loss:0.0019185517448931932 lr:6.873032967079561e-05 tokens_per_second_per_gpu:6634.594462348685 |
|
Step 111 | loss:0.0037080980837345123 lr:6.808122850410461e-05 tokens_per_second_per_gpu:5337.909562507922 |
|
Step 112 | loss:1.8280934455106035e-05 lr:6.742860236609077e-05 tokens_per_second_per_gpu:6890.276452233108 |
|
Step 113 | loss:6.343572022160515e-05 lr:6.677257848751277e-05 tokens_per_second_per_gpu:6916.200469048678 |
|
Step 114 | loss:8.518458344042301e-05 lr:6.611328476152557e-05 tokens_per_second_per_gpu:6642.759167552707 |
|
Step 115 | loss:0.0010669255862012506 lr:6.545084971874738e-05 tokens_per_second_per_gpu:7106.338781109161 |
|
Step 116 | loss:7.879980694269761e-05 lr:6.478540250220234e-05 tokens_per_second_per_gpu:6450.590534138903 |
|
Step 117 | loss:1.610443359822966e-05 lr:6.411707284214384e-05 tokens_per_second_per_gpu:6948.888592453719 |
|
Step 118 | loss:7.019325130386278e-05 lr:6.344599103076329e-05 tokens_per_second_per_gpu:6843.619329003747 |
|
Step 119 | loss:0.00010053990263259038 lr:6.277228789678953e-05 tokens_per_second_per_gpu:6470.339743921217 |
|
Step 120 | loss:0.0006487674545496702 lr:6.209609477998338e-05 tokens_per_second_per_gpu:6632.729896144266 |
|
Step 121 | loss:5.3303869208320975e-05 lr:6.141754350553279e-05 tokens_per_second_per_gpu:6661.920876119739 |
|
Step 122 | loss:0.0001957487256731838 lr:6.073676635835317e-05 tokens_per_second_per_gpu:7117.271578375329 |
|
Step 123 | loss:0.00020888530707452446 lr:6.005389605729824e-05 tokens_per_second_per_gpu:6532.323786611221 |
|
Step 124 | loss:0.00016734490054659545 lr:5.9369065729286245e-05 tokens_per_second_per_gpu:6470.860378475325 |
|
Step 125 | loss:0.0001500799844507128 lr:5.868240888334653e-05 tokens_per_second_per_gpu:6887.746656319498 |
|
Step 126 | loss:3.6837009247392416e-05 lr:5.799405938459175e-05 tokens_per_second_per_gpu:6652.201306620712 |
|
Step 127 | loss:0.0021684449166059494 lr:5.730415142812059e-05 tokens_per_second_per_gpu:6880.78207607067 |
|
Step 128 | loss:1.8878876289818436e-05 lr:5.661281951285613e-05 tokens_per_second_per_gpu:6631.064782221875 |
|
Step 129 | loss:3.306664075353183e-05 lr:5.5920198415325064e-05 tokens_per_second_per_gpu:7111.88461098746 |
|
Step 130 | loss:0.00012198043259559199 lr:5.522642316338268e-05 tokens_per_second_per_gpu:6466.124990035078 |
|
Step 131 | loss:0.000832759658806026 lr:5.453162900988902e-05 tokens_per_second_per_gpu:6581.671788023008 |
|
Step 132 | loss:0.007134541869163513 lr:5.383595140634093e-05 tokens_per_second_per_gpu:6967.797162172086 |
|
Step 133 | loss:2.075553493341431e-05 lr:5.313952597646568e-05 tokens_per_second_per_gpu:6549.833573793661 |
|
Step 134 | loss:2.6473575417185202e-05 lr:5.244248848978067e-05 tokens_per_second_per_gpu:7127.917559570654 |
|
Step 135 | loss:2.2700472982251085e-05 lr:5.174497483512506e-05 tokens_per_second_per_gpu:6574.015968536689 |
|
Step 136 | loss:6.514487904496491e-05 lr:5.104712099416785e-05 tokens_per_second_per_gpu:6429.155021212451 |
|
Step 137 | loss:1.191654064314207e-05 lr:5.034906301489808e-05 tokens_per_second_per_gpu:7140.5249904908105 |
|
Step 138 | loss:0.0005834389012306929 lr:4.965093698510193e-05 tokens_per_second_per_gpu:6452.364510347203 |
|
Step 139 | loss:8.847516437526792e-05 lr:4.895287900583216e-05 tokens_per_second_per_gpu:7117.959177378009 |
|
Step 140 | loss:0.004411947913467884 lr:4.825502516487497e-05 tokens_per_second_per_gpu:3948.052493511066 |
|
Step 141 | loss:5.6236054660985246e-05 lr:4.755751151021934e-05 tokens_per_second_per_gpu:6942.522635416498 |
|
Step 142 | loss:0.00029896333580836654 lr:4.6860474023534335e-05 tokens_per_second_per_gpu:6867.760612053949 |
|
Step 143 | loss:0.010003290139138699 lr:4.616404859365907e-05 tokens_per_second_per_gpu:6446.631164919947 |
|
Step 144 | loss:7.106986595317721e-05 lr:4.5468370990111006e-05 tokens_per_second_per_gpu:6926.631459505046 |
|
Step 145 | loss:0.0005215980345383286 lr:4.477357683661734e-05 tokens_per_second_per_gpu:5213.824134304672 |
|
Step 146 | loss:9.424990275874734e-05 lr:4.407980158467495e-05 tokens_per_second_per_gpu:6651.622279874753 |
|
Step 147 | loss:0.00032575210207141936 lr:4.3387180487143876e-05 tokens_per_second_per_gpu:7009.78129432356 |
|
Step 148 | loss:5.463398338179104e-05 lr:4.269584857187943e-05 tokens_per_second_per_gpu:7021.721905466142 |
|
Step 149 | loss:0.00023407567641697824 lr:4.2005940615408264e-05 tokens_per_second_per_gpu:6632.982085085049 |
|
Step 150 | loss:4.2366555135231465e-05 lr:4.131759111665349e-05 tokens_per_second_per_gpu:7113.6613049929965 |
|
Step 151 | loss:1.727652306726668e-05 lr:4.063093427071376e-05 tokens_per_second_per_gpu:6929.620848245407 |
|
Step 152 | loss:0.0006041711894795299 lr:3.9946103942701777e-05 tokens_per_second_per_gpu:6591.247445364165 |
|
Step 153 | loss:6.702107202727348e-05 lr:3.926323364164684e-05 tokens_per_second_per_gpu:6542.112709633285 |
|
Step 154 | loss:0.00010898215259658173 lr:3.858245649446721e-05 tokens_per_second_per_gpu:6617.720480843186 |
|
Step 155 | loss:0.0005894604837521911 lr:3.790390522001662e-05 tokens_per_second_per_gpu:7121.269133178284 |
|
Step 156 | loss:0.00046646883129142225 lr:3.7227712103210486e-05 tokens_per_second_per_gpu:6810.810132136087 |
|
Step 157 | loss:0.0008714331779628992 lr:3.655400896923672e-05 tokens_per_second_per_gpu:6559.711084234603 |
|
Step 158 | loss:0.0009323527337983251 lr:3.588292715785617e-05 tokens_per_second_per_gpu:6659.847774845367 |
|
Step 159 | loss:9.004903404274955e-05 lr:3.5214597497797684e-05 tokens_per_second_per_gpu:6905.063456852771 |
|
Step 160 | loss:0.00015947382780723274 lr:3.4549150281252636e-05 tokens_per_second_per_gpu:6655.478787142777 |
|
Step 161 | loss:0.0004274751408956945 lr:3.388671523847445e-05 tokens_per_second_per_gpu:6942.9743567778205 |
|
Step 162 | loss:0.00037595766480080783 lr:3.322742151248725e-05 tokens_per_second_per_gpu:6677.666313251598 |
|
Step 163 | loss:3.244326580897905e-05 lr:3.257139763390925e-05 tokens_per_second_per_gpu:6653.075937390707 |
|
Step 164 | loss:0.00030996996792964637 lr:3.1918771495895396e-05 tokens_per_second_per_gpu:6644.397243135655 |
|
Step 165 | loss:5.752700235461816e-05 lr:3.12696703292044e-05 tokens_per_second_per_gpu:6960.209716963056 |
|
Step 166 | loss:7.959095091791824e-05 lr:3.062422067739485e-05 tokens_per_second_per_gpu:6912.57406313066 |
|
Step 167 | loss:0.00031512955320067704 lr:2.9982548372155263e-05 tokens_per_second_per_gpu:6889.145567809192 |
|
Step 168 | loss:0.0016873697750270367 lr:2.934477850877292e-05 tokens_per_second_per_gpu:6455.525014033346 |
|
Step 169 | loss:6.595908780582249e-05 lr:2.8711035421746367e-05 tokens_per_second_per_gpu:3940.9819865040454 |
|
Step 170 | loss:0.0001208314424729906 lr:2.8081442660546125e-05 tokens_per_second_per_gpu:6533.838468920102 |
|
Step 171 | loss:2.291880446136929e-05 lr:2.7456122965528475e-05 tokens_per_second_per_gpu:7036.136911717446 |
|
Step 172 | loss:3.8961392419878393e-05 lr:2.6835198244006927e-05 tokens_per_second_per_gpu:6419.633418996145 |
|
Step 173 | loss:0.0002535284438636154 lr:2.6218789546486234e-05 tokens_per_second_per_gpu:6614.819622468586 |
|
Step 174 | loss:4.4378077291185036e-05 lr:2.560701704306336e-05 tokens_per_second_per_gpu:7058.27307364323 |
|
Step 175 | loss:0.0015160999028012156 lr:2.500000000000001e-05 tokens_per_second_per_gpu:5946.335424162427 |
|
Step 176 | loss:4.20267679146491e-05 lr:2.4397856756471432e-05 tokens_per_second_per_gpu:7076.1643700977365 |
|
Step 177 | loss:0.0009513521217741072 lr:2.3800704701496053e-05 tokens_per_second_per_gpu:6827.403499245773 |
|
Step 178 | loss:2.0644696633098647e-05 lr:2.3208660251050158e-05 tokens_per_second_per_gpu:7118.0654958975465 |
|
Step 179 | loss:5.462503031594679e-05 lr:2.2621838825372493e-05 tokens_per_second_per_gpu:7067.663128977011 |
|
Step 180 | loss:0.00020294466230552644 lr:2.2040354826462668e-05 tokens_per_second_per_gpu:6596.390810214846 |
|
Step 181 | loss:0.00020127856987528503 lr:2.1464321615778422e-05 tokens_per_second_per_gpu:7013.25305818966 |
|
Step 182 | loss:2.1506995835807174e-05 lr:2.0893851492135537e-05 tokens_per_second_per_gpu:6878.958473899288 |
|
Step 183 | loss:0.0016845290083438158 lr:2.0329055669814934e-05 tokens_per_second_per_gpu:6876.458445904233 |
|
Step 184 | loss:0.0001503072853665799 lr:1.977004425688126e-05 tokens_per_second_per_gpu:6608.593972229724 |
|
Step 185 | loss:7.932235166663304e-05 lr:1.9216926233717085e-05 tokens_per_second_per_gpu:6596.182449041913 |
|
Step 186 | loss:7.315298717003316e-05 lr:1.866980943177699e-05 tokens_per_second_per_gpu:6651.494518162662 |
|
Step 187 | loss:2.1691537767765112e-05 lr:1.8128800512565513e-05 tokens_per_second_per_gpu:6906.556298073519 |
|
Step 188 | loss:0.00034803853486664593 lr:1.7594004946843456e-05 tokens_per_second_per_gpu:6855.023616501254 |
|
Step 189 | loss:0.0003062945615965873 lr:1.7065526994065973e-05 tokens_per_second_per_gpu:6494.110561964963 |
|
Step 190 | loss:2.6088669983437285e-05 lr:1.6543469682057106e-05 tokens_per_second_per_gpu:7103.355385947416 |
|
Step 191 | loss:3.2427298719994724e-05 lr:1.602793478692419e-05 tokens_per_second_per_gpu:7049.27116226414 |
|
Step 192 | loss:1.9283334040665068e-05 lr:1.551902281321651e-05 tokens_per_second_per_gpu:6621.940479831454 |
|
Step 193 | loss:1.4837847629678436e-05 lr:1.5016832974331724e-05 tokens_per_second_per_gpu:6632.270038448392 |
|
Step 194 | loss:4.618912498699501e-05 lr:1.4521463173173965e-05 tokens_per_second_per_gpu:6450.603211542761 |
|
Step 195 | loss:8.731346315471455e-05 lr:1.4033009983067452e-05 tokens_per_second_per_gpu:6874.2009861572205 |
|
Step 196 | loss:0.0007837693556211889 lr:1.3551568628929434e-05 tokens_per_second_per_gpu:6438.693332145625 |
|
Step 197 | loss:7.728889613645151e-05 lr:1.3077232968705805e-05 tokens_per_second_per_gpu:6603.994857786765 |
|
Step 198 | loss:2.348179441469256e-05 lr:1.2610095475073414e-05 tokens_per_second_per_gpu:4789.884799591809 |
|
Step 199 | loss:0.00016038610192481428 lr:1.2150247217412186e-05 tokens_per_second_per_gpu:6558.0853059261235 |
|
Step 200 | loss:3.3631153200985864e-05 lr:1.1697777844051105e-05 tokens_per_second_per_gpu:7087.831642948178 |
|
Step 201 | loss:0.00014618111890740693 lr:1.1252775564791024e-05 tokens_per_second_per_gpu:6565.384879539554 |
|
Step 202 | loss:2.701554330997169e-05 lr:1.0815327133708015e-05 tokens_per_second_per_gpu:6893.453313682802 |
|
Step 203 | loss:0.0008529752376489341 lr:1.0385517832240471e-05 tokens_per_second_per_gpu:6517.5355654338255 |
|
Step 204 | loss:1.588598024682142e-05 lr:9.963431452563332e-06 tokens_per_second_per_gpu:7059.871188934064 |
|
Step 205 | loss:0.0008057854720391333 lr:9.549150281252633e-06 tokens_per_second_per_gpu:6548.372620521682 |
|
Step 206 | loss:0.00015476223779842257 lr:9.142755083243576e-06 tokens_per_second_per_gpu:6431.588636343005 |
|
Step 207 | loss:8.664749475428835e-05 lr:8.744325086085248e-06 tokens_per_second_per_gpu:6502.919716342713 |
|
Step 208 | loss:1.2338457963778637e-05 lr:8.353937964495029e-06 tokens_per_second_per_gpu:6861.501104968888 |
|
Step 209 | loss:0.00013570269220508635 lr:7.971669825215788e-06 tokens_per_second_per_gpu:6863.267024088076 |
|
Step 210 | loss:0.002080573933199048 lr:7.597595192178702e-06 tokens_per_second_per_gpu:5904.508517994963 |
|
Step 211 | loss:0.0004988689906895161 lr:7.2317869919746705e-06 tokens_per_second_per_gpu:6622.7369112184415 |
|
Step 212 | loss:0.00018352782353758812 lr:6.874316539637127e-06 tokens_per_second_per_gpu:7081.97858016051 |
|
Step 213 | loss:0.00037246820284053683 lr:6.52525352473905e-06 tokens_per_second_per_gpu:5181.607671540491 |
|
Step 214 | loss:1.9034436263609678e-05 lr:6.184665997806832e-06 tokens_per_second_per_gpu:6877.447332775893 |
|
Step 215 | loss:0.00025970637216232717 lr:5.852620357053651e-06 tokens_per_second_per_gpu:6619.443237103561 |
|
Step 216 | loss:9.822969877859578e-05 lr:5.529181335435124e-06 tokens_per_second_per_gpu:6551.990720176112 |
|
Step 217 | loss:4.414553040987812e-05 lr:5.214411988029355e-06 tokens_per_second_per_gpu:6911.87462585134 |
|
Step 218 | loss:0.0006779417162761092 lr:4.908373679744316e-06 tokens_per_second_per_gpu:6631.687627177202 |
|
Step 219 | loss:1.7940288671525195e-05 lr:4.611126073354571e-06 tokens_per_second_per_gpu:7020.880700776409 |
|
Step 220 | loss:6.450503133237362e-05 lr:4.322727117869951e-06 tokens_per_second_per_gpu:6897.571010537485 |
|
Step 221 | loss:0.0009318335796706378 lr:4.043233037238281e-06 tokens_per_second_per_gpu:6619.221030435229 |
|
Step 222 | loss:0.00016723918088246137 lr:3.772698319384349e-06 tokens_per_second_per_gpu:7075.477545011553 |
|
Step 223 | loss:8.360719948541373e-05 lr:3.511175705587433e-06 tokens_per_second_per_gpu:6512.199896253443 |
|
Step 224 | loss:1.4453452422458213e-05 lr:3.258716180199278e-06 tokens_per_second_per_gpu:6842.419957161844 |
|
Step 225 | loss:0.0017041980754584074 lr:3.0153689607045845e-06 tokens_per_second_per_gpu:6609.6983750661375 |
|
Step 226 | loss:5.68675714021083e-05 lr:2.7811814881259503e-06 tokens_per_second_per_gpu:6838.0884856370085 |
|
Step 227 | loss:0.002710741711780429 lr:2.5561994177751737e-06 tokens_per_second_per_gpu:3278.290224999214 |
|
Step 228 | loss:0.0017590811476111412 lr:2.340466610352654e-06 tokens_per_second_per_gpu:5959.538228032885 |
|
Step 229 | loss:0.00035566239967010915 lr:2.134025123396638e-06 tokens_per_second_per_gpu:6550.852848790178 |
|
Step 230 | loss:4.236725089867832e-06 lr:1.9369152030840556e-06 tokens_per_second_per_gpu:6560.816553955841 |
|
Step 231 | loss:0.0016642542323097587 lr:1.7491752763844293e-06 tokens_per_second_per_gpu:5188.038830459843 |
|
Step 232 | loss:3.7601857911795378e-06 lr:1.5708419435684462e-06 tokens_per_second_per_gpu:6876.047844526483 |
|
Step 233 | loss:3.0354982300195843e-05 lr:1.4019499710726913e-06 tokens_per_second_per_gpu:7048.910112085713 |
|
Step 234 | loss:9.097172733163461e-05 lr:1.2425322847218368e-06 tokens_per_second_per_gpu:6620.95106717429 |
|
Step 235 | loss:0.0004588098672684282 lr:1.0926199633097157e-06 tokens_per_second_per_gpu:6866.427218408531 |
|
Step 236 | loss:2.3615913960384205e-05 lr:9.522422325404235e-07 tokens_per_second_per_gpu:6807.550934929809 |
|
Step 237 | loss:8.894444908946753e-05 lr:8.214264593307098e-07 tokens_per_second_per_gpu:6632.915847438242 |
|
Step 238 | loss:1.4141115570964757e-05 lr:7.001981464747565e-07 tokens_per_second_per_gpu:7098.742085761691 |
|
Step 239 | loss:2.696912815736141e-05 lr:5.885809276723608e-07 tokens_per_second_per_gpu:6597.974030159197 |
|
Step 240 | loss:0.0008145094616338611 lr:4.865965629214819e-07 tokens_per_second_per_gpu:6674.75699821072 |
|
Step 241 | loss:7.957598427310586e-05 lr:3.9426493427611177e-07 tokens_per_second_per_gpu:6595.459145926985 |
|
Step 242 | loss:3.828562330454588e-05 lr:3.1160404197018154e-07 tokens_per_second_per_gpu:7101.7020777281305 |
|
Step 243 | loss:8.814628927211743e-06 lr:2.386300009084408e-07 tokens_per_second_per_gpu:7011.342644886534 |
|
Step 244 | loss:0.0004267446347512305 lr:1.753570375247815e-07 tokens_per_second_per_gpu:6545.467889161499 |
|
Step 245 | loss:0.0005327242542989552 lr:1.2179748700879012e-07 tokens_per_second_per_gpu:6635.642602121437 |
|
Step 246 | loss:3.4723900171229616e-05 lr:7.796179090094891e-08 tokens_per_second_per_gpu:7081.141397797378 |
|
Step 247 | loss:3.564795770216733e-05 lr:4.385849505708084e-08 tokens_per_second_per_gpu:6877.282976617243 |
|
Step 248 | loss:0.0013675112277269363 lr:1.949424798228239e-08 tokens_per_second_per_gpu:6899.428748658248 |
|
Step 249 | loss:4.7962246753741056e-05 lr:4.873799534788059e-09 tokens_per_second_per_gpu:6932.006787788585 |
|
Step 250 | loss:9.682981908554211e-05 lr:0.0 tokens_per_second_per_gpu:5238.0422309469095 |
|
|