|
Step 1 | loss:0.06546077132225037 lr:4.000000000000001e-06 tokens_per_second_per_gpu:1899.111248745599 |
|
Step 2 | loss:0.048652563244104385 lr:8.000000000000001e-06 tokens_per_second_per_gpu:3187.490127984658 |
|
Step 3 | loss:0.11955612152814865 lr:1.2e-05 tokens_per_second_per_gpu:7239.32459230221 |
|
Step 4 | loss:0.050140414386987686 lr:1.6000000000000003e-05 tokens_per_second_per_gpu:2451.544747581494 |
|
Step 5 | loss:0.08751427382230759 lr:2e-05 tokens_per_second_per_gpu:6947.434828424588 |
|
Step 6 | loss:0.03238687291741371 lr:2.4e-05 tokens_per_second_per_gpu:3180.3518073895607 |
|
Step 7 | loss:0.04688405245542526 lr:2.8000000000000003e-05 tokens_per_second_per_gpu:7229.148749865313 |
|
Step 8 | loss:0.03336497023701668 lr:3.2000000000000005e-05 tokens_per_second_per_gpu:7221.496960389093 |
|
Step 9 | loss:0.03561889007687569 lr:3.6e-05 tokens_per_second_per_gpu:7241.131873683623 |
|
Step 10 | loss:0.07751365751028061 lr:4e-05 tokens_per_second_per_gpu:2009.7336321667988 |
|
Step 11 | loss:0.08949209004640579 lr:4.4000000000000006e-05 tokens_per_second_per_gpu:1293.1198166441525 |
|
Step 12 | loss:0.08842364698648453 lr:4.8e-05 tokens_per_second_per_gpu:7000.464473847161 |
|
Step 13 | loss:0.026776956394314766 lr:5.2000000000000004e-05 tokens_per_second_per_gpu:7154.985064927596 |
|
Step 14 | loss:0.06119929254055023 lr:5.6000000000000006e-05 tokens_per_second_per_gpu:6850.75088979156 |
|
Step 15 | loss:0.029401805251836777 lr:6e-05 tokens_per_second_per_gpu:7231.712696495142 |
|
Step 16 | loss:0.050774332135915756 lr:6.400000000000001e-05 tokens_per_second_per_gpu:6840.9098271139355 |
|
Step 17 | loss:0.033134933561086655 lr:6.800000000000001e-05 tokens_per_second_per_gpu:7277.672017039365 |
|
Step 18 | loss:0.015783770009875298 lr:7.2e-05 tokens_per_second_per_gpu:7265.00308031439 |
|
Step 19 | loss:0.01681678183376789 lr:7.6e-05 tokens_per_second_per_gpu:7161.888582058088 |
|
Step 20 | loss:0.03722219541668892 lr:8e-05 tokens_per_second_per_gpu:1328.8901105825826 |
|
Step 21 | loss:0.009588022716343403 lr:8.4e-05 tokens_per_second_per_gpu:7207.183218529437 |
|
Step 22 | loss:0.012159164063632488 lr:8.800000000000001e-05 tokens_per_second_per_gpu:7114.04999006765 |
|
Step 23 | loss:0.014627138152718544 lr:9.200000000000001e-05 tokens_per_second_per_gpu:7268.0731876084765 |
|
Step 24 | loss:0.08523207157850266 lr:9.6e-05 tokens_per_second_per_gpu:1159.0600949810228 |
|
Step 25 | loss:0.0346188023686409 lr:0.0001 tokens_per_second_per_gpu:1437.5888855340593 |
|
Step 26 | loss:0.012201088480651379 lr:9.999512620046522e-05 tokens_per_second_per_gpu:7225.49627044823 |
|
Step 27 | loss:0.04622826725244522 lr:9.998050575201771e-05 tokens_per_second_per_gpu:3885.29768384515 |
|
Step 28 | loss:0.012623291462659836 lr:9.995614150494293e-05 tokens_per_second_per_gpu:7240.07205797553 |
|
Step 29 | loss:0.021248620003461838 lr:9.992203820909906e-05 tokens_per_second_per_gpu:3045.055583356834 |
|
Step 30 | loss:0.031091202050447464 lr:9.987820251299122e-05 tokens_per_second_per_gpu:6913.630770541244 |
|
Step 31 | loss:0.023271074518561363 lr:9.982464296247522e-05 tokens_per_second_per_gpu:6956.317130097324 |
|
Step 32 | loss:0.01355912908911705 lr:9.976136999909156e-05 tokens_per_second_per_gpu:7201.195313905872 |
|
Step 33 | loss:0.016683122143149376 lr:9.968839595802982e-05 tokens_per_second_per_gpu:6950.168536512465 |
|
Step 34 | loss:0.015682470053434372 lr:9.96057350657239e-05 tokens_per_second_per_gpu:6944.731992130036 |
|
Step 35 | loss:0.009485973976552486 lr:9.951340343707852e-05 tokens_per_second_per_gpu:7190.446153830537 |
|
Step 36 | loss:0.04073016718029976 lr:9.941141907232765e-05 tokens_per_second_per_gpu:6511.226063836032 |
|
Step 37 | loss:0.022151978686451912 lr:9.929980185352526e-05 tokens_per_second_per_gpu:7249.635289397723 |
|
Step 38 | loss:0.008496436290442944 lr:9.917857354066931e-05 tokens_per_second_per_gpu:7207.757438234654 |
|
Step 39 | loss:0.019105421379208565 lr:9.904775776745958e-05 tokens_per_second_per_gpu:6503.726244066047 |
|
Step 40 | loss:0.006263361778110266 lr:9.890738003669029e-05 tokens_per_second_per_gpu:6952.169813368149 |
|
Step 41 | loss:0.014868299476802349 lr:9.875746771527816e-05 tokens_per_second_per_gpu:7273.272915760774 |
|
Step 42 | loss:0.010259944945573807 lr:9.859805002892732e-05 tokens_per_second_per_gpu:6641.4157264828145 |
|
Step 43 | loss:0.008029812015593052 lr:9.842915805643155e-05 tokens_per_second_per_gpu:7239.810586396663 |
|
Step 44 | loss:0.007884396240115166 lr:9.825082472361557e-05 tokens_per_second_per_gpu:6850.916181816909 |
|
Step 45 | loss:0.0075033679604530334 lr:9.806308479691595e-05 tokens_per_second_per_gpu:6909.056977352708 |
|
Step 46 | loss:0.008111163042485714 lr:9.786597487660337e-05 tokens_per_second_per_gpu:6958.735458684212 |
|
Step 47 | loss:0.18889857828617096 lr:9.765953338964735e-05 tokens_per_second_per_gpu:6971.607205699985 |
|
Step 48 | loss:0.0054248315282166 lr:9.744380058222483e-05 tokens_per_second_per_gpu:7278.026295304224 |
|
Step 49 | loss:0.008706084452569485 lr:9.721881851187406e-05 tokens_per_second_per_gpu:6947.3160260517025 |
|
Step 50 | loss:0.0091332932934165 lr:9.698463103929542e-05 tokens_per_second_per_gpu:6977.633204958479 |
|
Step 51 | loss:0.0064770374447107315 lr:9.674128381980072e-05 tokens_per_second_per_gpu:6529.267758367089 |
|
Step 52 | loss:0.0017953087808564305 lr:9.648882429441257e-05 tokens_per_second_per_gpu:7233.926471496849 |
|
Step 53 | loss:0.0024088872596621513 lr:9.622730168061567e-05 tokens_per_second_per_gpu:7171.506922000218 |
|
Step 54 | loss:0.011489334516227245 lr:9.595676696276172e-05 tokens_per_second_per_gpu:6499.969970180441 |
|
Step 55 | loss:0.007883118465542793 lr:9.567727288213005e-05 tokens_per_second_per_gpu:7217.742285699045 |
|
Step 56 | loss:0.0021584825590252876 lr:9.538887392664544e-05 tokens_per_second_per_gpu:4960.9349161533455 |
|
Step 57 | loss:0.01261111255735159 lr:9.50916263202557e-05 tokens_per_second_per_gpu:1144.4630326836811 |
|
Step 58 | loss:0.0038552277255803347 lr:9.478558801197065e-05 tokens_per_second_per_gpu:6499.102929312511 |
|
Step 59 | loss:0.002756482921540737 lr:9.447081866456489e-05 tokens_per_second_per_gpu:7238.019943352679 |
|
Step 60 | loss:0.003040582872927189 lr:9.414737964294636e-05 tokens_per_second_per_gpu:6839.643059614835 |
|
Step 61 | loss:0.0063329278491437435 lr:9.381533400219318e-05 tokens_per_second_per_gpu:2199.2090671915153 |
|
Step 62 | loss:0.001776869990862906 lr:9.347474647526095e-05 tokens_per_second_per_gpu:7201.860631790156 |
|
Step 63 | loss:0.005619619973003864 lr:9.312568346036288e-05 tokens_per_second_per_gpu:6955.594484365451 |
|
Step 64 | loss:0.002909269416704774 lr:9.276821300802534e-05 tokens_per_second_per_gpu:7194.8050028778225 |
|
Step 65 | loss:0.008338110521435738 lr:9.24024048078213e-05 tokens_per_second_per_gpu:6809.080419869152 |
|
Step 66 | loss:0.0012672255979850888 lr:9.202833017478422e-05 tokens_per_second_per_gpu:7242.701863477383 |
|
Step 67 | loss:0.0018992478726431727 lr:9.164606203550497e-05 tokens_per_second_per_gpu:7245.3406135187015 |
|
Step 68 | loss:0.006870816927403212 lr:9.125567491391476e-05 tokens_per_second_per_gpu:7233.22945243056 |
|
Step 69 | loss:0.0013532611774280667 lr:9.085724491675642e-05 tokens_per_second_per_gpu:6898.220613211783 |
|
Step 70 | loss:0.13891181349754333 lr:9.045084971874738e-05 tokens_per_second_per_gpu:6909.920211729971 |
|
Step 71 | loss:0.005052177235484123 lr:9.003656854743667e-05 tokens_per_second_per_gpu:7236.488915338989 |
|
Step 72 | loss:0.010721510276198387 lr:8.961448216775954e-05 tokens_per_second_per_gpu:2208.8392340532278 |
|
Step 73 | loss:0.005147602874785662 lr:8.9184672866292e-05 tokens_per_second_per_gpu:6879.302251551932 |
|
Step 74 | loss:0.0006254129111766815 lr:8.874722443520899e-05 tokens_per_second_per_gpu:7196.194087622638 |
|
Step 75 | loss:0.0012219698401167989 lr:8.83022221559489e-05 tokens_per_second_per_gpu:6927.112252802871 |
|
Step 76 | loss:0.0064183385111391544 lr:8.784975278258783e-05 tokens_per_second_per_gpu:7239.470882495577 |
|
Step 77 | loss:0.005643194075673819 lr:8.73899045249266e-05 tokens_per_second_per_gpu:7267.334039578599 |
|
Step 78 | loss:0.003780151717364788 lr:8.692276703129421e-05 tokens_per_second_per_gpu:7216.762603610822 |
|
Step 79 | loss:0.002893806202337146 lr:8.644843137107059e-05 tokens_per_second_per_gpu:7221.018945121883 |
|
Step 80 | loss:0.0012355687795206904 lr:8.596699001693255e-05 tokens_per_second_per_gpu:6935.224808818595 |
|
Step 81 | loss:0.005067302379757166 lr:8.547853682682604e-05 tokens_per_second_per_gpu:7203.485439997014 |
|
Step 82 | loss:0.17590466141700745 lr:8.498316702566828e-05 tokens_per_second_per_gpu:6507.361599211361 |
|
Step 83 | loss:0.0014302482595667243 lr:8.44809771867835e-05 tokens_per_second_per_gpu:6489.720392361714 |
|
Step 84 | loss:0.4223830997943878 lr:8.397206521307584e-05 tokens_per_second_per_gpu:6514.146223049989 |
|
Step 85 | loss:0.0022069416008889675 lr:8.345653031794292e-05 tokens_per_second_per_gpu:7232.01808480851 |
|
Step 86 | loss:0.0031973652075976133 lr:8.293447300593402e-05 tokens_per_second_per_gpu:7168.72250394572 |
|
Step 87 | loss:0.005546098574995995 lr:8.240599505315655e-05 tokens_per_second_per_gpu:6914.22081505654 |
|
Step 88 | loss:0.0006724463892169297 lr:8.18711994874345e-05 tokens_per_second_per_gpu:7236.696352954054 |
|
Step 89 | loss:0.0034629914443939924 lr:8.133019056822304e-05 tokens_per_second_per_gpu:7197.539840420435 |
|
Step 90 | loss:0.006134921219199896 lr:8.07830737662829e-05 tokens_per_second_per_gpu:2626.1779241802246 |
|
Step 91 | loss:0.010058923624455929 lr:8.022995574311876e-05 tokens_per_second_per_gpu:7237.397622507109 |
|
Step 92 | loss:0.0018223989754915237 lr:7.967094433018508e-05 tokens_per_second_per_gpu:6834.351323117253 |
|
Step 93 | loss:0.004867095500230789 lr:7.910614850786448e-05 tokens_per_second_per_gpu:2402.4591628674443 |
|
Step 94 | loss:0.11734828352928162 lr:7.85356783842216e-05 tokens_per_second_per_gpu:6485.126361360171 |
|
Step 95 | loss:0.0020852547604590654 lr:7.795964517353735e-05 tokens_per_second_per_gpu:7234.330383033677 |
|
Step 96 | loss:0.003236407646909356 lr:7.737816117462752e-05 tokens_per_second_per_gpu:6938.487513247408 |
|
Step 97 | loss:0.0033761102240532637 lr:7.679133974894983e-05 tokens_per_second_per_gpu:7244.335868708892 |
|
Step 98 | loss:0.003140476532280445 lr:7.619929529850397e-05 tokens_per_second_per_gpu:7180.800590615507 |
|
Step 99 | loss:0.003371448954567313 lr:7.560214324352858e-05 tokens_per_second_per_gpu:1602.4515087604007 |
|
Step 100 | loss:0.004087939392775297 lr:7.500000000000001e-05 tokens_per_second_per_gpu:7230.553459396093 |
|
Step 101 | loss:0.003066370962187648 lr:7.439298295693665e-05 tokens_per_second_per_gpu:7205.996317606415 |
|
Step 102 | loss:0.0016833605477586389 lr:7.378121045351378e-05 tokens_per_second_per_gpu:6937.969386769377 |
|
Step 103 | loss:0.04205913841724396 lr:7.316480175599309e-05 tokens_per_second_per_gpu:7173.264501881493 |
|
Step 104 | loss:0.009091147221624851 lr:7.254387703447154e-05 tokens_per_second_per_gpu:6469.162161385801 |
|
Step 105 | loss:0.0014217837015166879 lr:7.191855733945387e-05 tokens_per_second_per_gpu:7238.394830749191 |
|
Step 106 | loss:0.003368057543411851 lr:7.128896457825364e-05 tokens_per_second_per_gpu:7180.08440337413 |
|
Step 107 | loss:0.0011393044842407107 lr:7.06552214912271e-05 tokens_per_second_per_gpu:7082.626571878067 |
|
Step 108 | loss:0.0017756723100319505 lr:7.001745162784477e-05 tokens_per_second_per_gpu:6848.752417804069 |
|
Step 109 | loss:0.003360250499099493 lr:6.937577932260515e-05 tokens_per_second_per_gpu:7190.6000598087985 |
|
Step 110 | loss:0.004788301885128021 lr:6.873032967079561e-05 tokens_per_second_per_gpu:7231.242196703568 |
|
Step 111 | loss:0.004177471622824669 lr:6.808122850410461e-05 tokens_per_second_per_gpu:3887.969074699589 |
|
Step 112 | loss:0.002845532726496458 lr:6.742860236609077e-05 tokens_per_second_per_gpu:6988.647596822497 |
|
Step 113 | loss:0.00595108512789011 lr:6.677257848751277e-05 tokens_per_second_per_gpu:6485.160276798583 |
|
Step 114 | loss:0.010461295023560524 lr:6.611328476152557e-05 tokens_per_second_per_gpu:6511.086990227759 |
|
Step 115 | loss:0.0006954252021387219 lr:6.545084971874738e-05 tokens_per_second_per_gpu:7206.724950326596 |
|
Step 116 | loss:0.000555613252799958 lr:6.478540250220234e-05 tokens_per_second_per_gpu:7133.109884470054 |
|
Step 117 | loss:0.003257938427850604 lr:6.411707284214384e-05 tokens_per_second_per_gpu:7132.092291586698 |
|
Step 118 | loss:0.0034849802032113075 lr:6.344599103076329e-05 tokens_per_second_per_gpu:6459.208217783255 |
|
Step 119 | loss:0.034471265971660614 lr:6.277228789678953e-05 tokens_per_second_per_gpu:6997.730428449021 |
|
Step 120 | loss:0.0037143463268876076 lr:6.209609477998338e-05 tokens_per_second_per_gpu:7216.055344332053 |
|
Step 121 | loss:0.00044111546594649553 lr:6.141754350553279e-05 tokens_per_second_per_gpu:7191.517036261166 |
|
Step 122 | loss:0.0019836947321891785 lr:6.073676635835317e-05 tokens_per_second_per_gpu:3046.867631720553 |
|
Step 123 | loss:0.002268873155117035 lr:6.005389605729824e-05 tokens_per_second_per_gpu:7091.936730301142 |
|
Step 124 | loss:0.0018307192949578166 lr:5.9369065729286245e-05 tokens_per_second_per_gpu:6884.548509389471 |
|
Step 125 | loss:0.004751366097480059 lr:5.868240888334653e-05 tokens_per_second_per_gpu:6487.567696956562 |
|
Step 126 | loss:0.0027368832379579544 lr:5.799405938459175e-05 tokens_per_second_per_gpu:7258.228715551712 |
|
Step 127 | loss:0.0008390247821807861 lr:5.730415142812059e-05 tokens_per_second_per_gpu:7242.887008262235 |
|
Step 128 | loss:0.004580748733133078 lr:5.661281951285613e-05 tokens_per_second_per_gpu:6721.123055506177 |
|
Step 129 | loss:0.005211775191128254 lr:5.5920198415325064e-05 tokens_per_second_per_gpu:7001.21537588965 |
|
Step 130 | loss:0.09115011245012283 lr:5.522642316338268e-05 tokens_per_second_per_gpu:6548.096326680435 |
|
Step 131 | loss:0.0009327076259069145 lr:5.453162900988902e-05 tokens_per_second_per_gpu:7268.565411833865 |
|
Step 132 | loss:0.0012624373193830252 lr:5.383595140634093e-05 tokens_per_second_per_gpu:7238.868965529443 |
|
Step 133 | loss:0.0012063749600201845 lr:5.313952597646568e-05 tokens_per_second_per_gpu:6983.078258361508 |
|
Step 134 | loss:0.001517970347777009 lr:5.244248848978067e-05 tokens_per_second_per_gpu:7158.8296938898475 |
|
Step 135 | loss:0.012263035401701927 lr:5.174497483512506e-05 tokens_per_second_per_gpu:7253.752638158302 |
|
Step 136 | loss:0.0020020061638206244 lr:5.104712099416785e-05 tokens_per_second_per_gpu:6448.758825261569 |
|
Step 137 | loss:0.001614861306734383 lr:5.034906301489808e-05 tokens_per_second_per_gpu:6951.366879066016 |
|
Step 138 | loss:0.0017596834804862738 lr:4.965093698510193e-05 tokens_per_second_per_gpu:6931.1820205463555 |
|
Step 139 | loss:0.0010472075082361698 lr:4.895287900583216e-05 tokens_per_second_per_gpu:6994.221224891913 |
|
Step 140 | loss:0.0008883971022441983 lr:4.825502516487497e-05 tokens_per_second_per_gpu:6497.098739389554 |
|
Step 141 | loss:0.0018283214885741472 lr:4.755751151021934e-05 tokens_per_second_per_gpu:7183.062142831603 |
|
Step 142 | loss:0.0014343843795359135 lr:4.6860474023534335e-05 tokens_per_second_per_gpu:7187.789855231951 |
|
Step 143 | loss:0.0015963813057169318 lr:4.616404859365907e-05 tokens_per_second_per_gpu:6869.182244186862 |
|
Step 144 | loss:0.017620472237467766 lr:4.5468370990111006e-05 tokens_per_second_per_gpu:6975.191175615885 |
|
Step 145 | loss:0.000757466594222933 lr:4.477357683661734e-05 tokens_per_second_per_gpu:7234.339122296307 |
|
Step 146 | loss:0.005827900487929583 lr:4.407980158467495e-05 tokens_per_second_per_gpu:6520.743242767228 |
|
Step 147 | loss:0.0017527113668620586 lr:4.3387180487143876e-05 tokens_per_second_per_gpu:6955.709292265261 |
|
Step 148 | loss:0.0006355632795020938 lr:4.269584857187943e-05 tokens_per_second_per_gpu:6876.200091796233 |
|
Step 149 | loss:0.0007113250903785229 lr:4.2005940615408264e-05 tokens_per_second_per_gpu:7242.004206478676 |
|
Step 150 | loss:0.004731751047074795 lr:4.131759111665349e-05 tokens_per_second_per_gpu:6890.033530755856 |
|
Step 151 | loss:0.003411336336284876 lr:4.063093427071376e-05 tokens_per_second_per_gpu:6516.994937307178 |
|
Step 152 | loss:0.010047228075563908 lr:3.9946103942701777e-05 tokens_per_second_per_gpu:7252.550259728189 |
|
Step 153 | loss:0.001580787356942892 lr:3.926323364164684e-05 tokens_per_second_per_gpu:7252.2957974993415 |
|
Step 154 | loss:0.0005627106875181198 lr:3.858245649446721e-05 tokens_per_second_per_gpu:6912.560390432837 |
|
Step 155 | loss:0.0012077429564669728 lr:3.790390522001662e-05 tokens_per_second_per_gpu:7210.048847641519 |
|
Step 156 | loss:0.0019266967428848147 lr:3.7227712103210486e-05 tokens_per_second_per_gpu:7109.797857647483 |
|
Step 157 | loss:0.0026629699859768152 lr:3.655400896923672e-05 tokens_per_second_per_gpu:6525.483462573243 |
|
Step 158 | loss:0.0005116283427923918 lr:3.588292715785617e-05 tokens_per_second_per_gpu:7251.261825655518 |
|
Step 159 | loss:0.00034223138936795294 lr:3.5214597497797684e-05 tokens_per_second_per_gpu:7165.846662949642 |
|
Step 160 | loss:0.0009767187293618917 lr:3.4549150281252636e-05 tokens_per_second_per_gpu:6479.901200787538 |
|
Step 161 | loss:0.0002495758526492864 lr:3.388671523847445e-05 tokens_per_second_per_gpu:7138.721732388497 |
|
Step 162 | loss:0.005948242265731096 lr:3.322742151248725e-05 tokens_per_second_per_gpu:7214.973756126934 |
|
Step 163 | loss:0.0011346392566338181 lr:3.257139763390925e-05 tokens_per_second_per_gpu:6896.368466432513 |
|
Step 164 | loss:0.0008426314452663064 lr:3.1918771495895396e-05 tokens_per_second_per_gpu:7157.627729303329 |
|
Step 165 | loss:0.0006407969631254673 lr:3.12696703292044e-05 tokens_per_second_per_gpu:6914.763440392399 |
|
Step 166 | loss:0.0005656238063238561 lr:3.062422067739485e-05 tokens_per_second_per_gpu:6944.917092813639 |
|
Step 167 | loss:0.0008091846248134971 lr:2.9982548372155263e-05 tokens_per_second_per_gpu:6907.338893817747 |
|
Step 168 | loss:0.0016065367963165045 lr:2.934477850877292e-05 tokens_per_second_per_gpu:6988.948187150392 |
|
Step 169 | loss:0.0004634346696548164 lr:2.8711035421746367e-05 tokens_per_second_per_gpu:6483.635045557717 |
|
Step 170 | loss:0.0017387190600857139 lr:2.8081442660546125e-05 tokens_per_second_per_gpu:7177.055841947692 |
|
Step 171 | loss:0.0072456179186701775 lr:2.7456122965528475e-05 tokens_per_second_per_gpu:6486.742074595044 |
|
Step 172 | loss:0.0007275919779203832 lr:2.6835198244006927e-05 tokens_per_second_per_gpu:6502.6720328160045 |
|
Step 173 | loss:0.0003031610103789717 lr:2.6218789546486234e-05 tokens_per_second_per_gpu:7115.466725312442 |
|
Step 174 | loss:0.00044266003533266485 lr:2.560701704306336e-05 tokens_per_second_per_gpu:6826.519793067474 |
|
Step 175 | loss:0.00028436805587261915 lr:2.500000000000001e-05 tokens_per_second_per_gpu:7212.805104560866 |
|
Step 176 | loss:0.0010739279678091407 lr:2.4397856756471432e-05 tokens_per_second_per_gpu:7213.078013315937 |
|
Step 177 | loss:0.0004694955132436007 lr:2.3800704701496053e-05 tokens_per_second_per_gpu:6882.4557180719885 |
|
Step 178 | loss:0.002619611332193017 lr:2.3208660251050158e-05 tokens_per_second_per_gpu:6980.7097359786285 |
|
Step 179 | loss:0.0004050467105116695 lr:2.2621838825372493e-05 tokens_per_second_per_gpu:6892.592684149777 |
|
Step 180 | loss:0.0029296749271452427 lr:2.2040354826462668e-05 tokens_per_second_per_gpu:1902.983866835148 |
|
Step 181 | loss:0.0005268901586532593 lr:2.1464321615778422e-05 tokens_per_second_per_gpu:6965.626994280906 |
|
Step 182 | loss:0.0018398710526525974 lr:2.0893851492135537e-05 tokens_per_second_per_gpu:7241.056798882297 |
|
Step 183 | loss:0.003998288419097662 lr:2.0329055669814934e-05 tokens_per_second_per_gpu:6926.534315763652 |
|
Step 184 | loss:0.0005994075327180326 lr:1.977004425688126e-05 tokens_per_second_per_gpu:6949.658403433735 |
|
Step 185 | loss:0.0015798507956787944 lr:1.9216926233717085e-05 tokens_per_second_per_gpu:6817.151211237511 |
|
Step 186 | loss:0.0003413461963646114 lr:1.866980943177699e-05 tokens_per_second_per_gpu:7171.843907114876 |
|
Step 187 | loss:0.002889839932322502 lr:1.8128800512565513e-05 tokens_per_second_per_gpu:6921.9678623845875 |
|
Step 188 | loss:0.002838453743606806 lr:1.7594004946843456e-05 tokens_per_second_per_gpu:6700.748792056513 |
|
Step 189 | loss:0.005105117801576853 lr:1.7065526994065973e-05 tokens_per_second_per_gpu:6655.1305866294015 |
|
Step 190 | loss:0.0003114079008810222 lr:1.6543469682057106e-05 tokens_per_second_per_gpu:7193.6662420155335 |
|
Step 191 | loss:0.000402803038014099 lr:1.602793478692419e-05 tokens_per_second_per_gpu:6864.422103746657 |
|
Step 192 | loss:0.0005131018115207553 lr:1.551902281321651e-05 tokens_per_second_per_gpu:6917.490785702836 |
|
Step 193 | loss:0.0019279043190181255 lr:1.5016832974331724e-05 tokens_per_second_per_gpu:6873.585075616898 |
|
Step 194 | loss:0.0027476451359689236 lr:1.4521463173173965e-05 tokens_per_second_per_gpu:7115.301186919628 |
|
Step 195 | loss:0.0003623691154643893 lr:1.4033009983067452e-05 tokens_per_second_per_gpu:7205.114476478124 |
|
Step 196 | loss:0.000258775515248999 lr:1.3551568628929434e-05 tokens_per_second_per_gpu:7191.851775496317 |
|
Step 197 | loss:0.0014169721398502588 lr:1.3077232968705805e-05 tokens_per_second_per_gpu:7176.352176475379 |
|
Step 198 | loss:0.0005479215178638697 lr:1.2610095475073414e-05 tokens_per_second_per_gpu:5333.232628985052 |
|
Step 199 | loss:0.0009446265175938606 lr:1.2150247217412186e-05 tokens_per_second_per_gpu:7151.87911668633 |
|
Step 200 | loss:0.000713130459189415 lr:1.1697777844051105e-05 tokens_per_second_per_gpu:7111.41922783891 |
|
Step 201 | loss:0.00036724552046507597 lr:1.1252775564791024e-05 tokens_per_second_per_gpu:7193.986799381708 |
|
Step 202 | loss:0.000987916486337781 lr:1.0815327133708015e-05 tokens_per_second_per_gpu:7113.522144588866 |
|
Step 203 | loss:0.0002968055196106434 lr:1.0385517832240471e-05 tokens_per_second_per_gpu:7135.336840172691 |
|
Step 204 | loss:0.000353662675479427 lr:9.963431452563332e-06 tokens_per_second_per_gpu:7205.409066547487 |
|
Step 205 | loss:0.002150371205061674 lr:9.549150281252633e-06 tokens_per_second_per_gpu:6881.95971770437 |
|
Step 206 | loss:0.0013912443537265062 lr:9.142755083243576e-06 tokens_per_second_per_gpu:7208.351728190035 |
|
Step 207 | loss:0.0036943850573152304 lr:8.744325086085248e-06 tokens_per_second_per_gpu:7172.283981256872 |
|
Step 208 | loss:0.011616194620728493 lr:8.353937964495029e-06 tokens_per_second_per_gpu:6874.586149579653 |
|
Step 209 | loss:0.0011006630957126617 lr:7.971669825215788e-06 tokens_per_second_per_gpu:7212.797209944242 |
|
Step 210 | loss:0.0006784137221984565 lr:7.597595192178702e-06 tokens_per_second_per_gpu:6937.992445723651 |
|
Step 211 | loss:0.0015658115735277534 lr:7.2317869919746705e-06 tokens_per_second_per_gpu:7171.1877449052145 |
|
Step 212 | loss:0.0005506619927473366 lr:6.874316539637127e-06 tokens_per_second_per_gpu:6884.112401589749 |
|
Step 213 | loss:0.010955791920423508 lr:6.52525352473905e-06 tokens_per_second_per_gpu:918.4238131616011 |
|
Step 214 | loss:0.0005963208968751132 lr:6.184665997806832e-06 tokens_per_second_per_gpu:6961.058534565415 |
|
Step 215 | loss:0.00029130972689017653 lr:5.852620357053651e-06 tokens_per_second_per_gpu:7119.576302758679 |
|
Step 216 | loss:0.0015587095404043794 lr:5.529181335435124e-06 tokens_per_second_per_gpu:6800.261879261288 |
|
Step 217 | loss:0.0012207169784232974 lr:5.214411988029355e-06 tokens_per_second_per_gpu:7241.2061696603905 |
|
Step 218 | loss:0.0005632808315567672 lr:4.908373679744316e-06 tokens_per_second_per_gpu:6891.1526778601265 |
|
Step 219 | loss:0.0007431649719364941 lr:4.611126073354571e-06 tokens_per_second_per_gpu:6523.819634585338 |
|
Step 220 | loss:0.01103260088711977 lr:4.322727117869951e-06 tokens_per_second_per_gpu:6507.007375305747 |
|
Step 221 | loss:0.0004383371851872653 lr:4.043233037238281e-06 tokens_per_second_per_gpu:6948.637539503261 |
|
Step 222 | loss:0.00047084828838706017 lr:3.772698319384349e-06 tokens_per_second_per_gpu:6845.933134625405 |
|
Step 223 | loss:0.002382498001679778 lr:3.511175705587433e-06 tokens_per_second_per_gpu:7130.207740824223 |
|
Step 224 | loss:0.0033739416394382715 lr:3.258716180199278e-06 tokens_per_second_per_gpu:7002.276745009314 |
|
Step 225 | loss:0.0005694949650205672 lr:3.0153689607045845e-06 tokens_per_second_per_gpu:6989.877796582834 |
|
Step 226 | loss:0.00031773539376445115 lr:2.7811814881259503e-06 tokens_per_second_per_gpu:7118.2328134439 |
|
Step 227 | loss:0.00048105407040566206 lr:2.5561994177751737e-06 tokens_per_second_per_gpu:6548.823617209464 |
|
Step 228 | loss:0.0005287568783387542 lr:2.340466610352654e-06 tokens_per_second_per_gpu:7130.5151797636045 |
|
Step 229 | loss:0.0030859278049319983 lr:2.134025123396638e-06 tokens_per_second_per_gpu:7163.775995755493 |
|
Step 230 | loss:0.0004144504200667143 lr:1.9369152030840556e-06 tokens_per_second_per_gpu:7253.075710892904 |
|
Step 231 | loss:0.0011980643030256033 lr:1.7491752763844293e-06 tokens_per_second_per_gpu:7225.471903602016 |
|
Step 232 | loss:0.0006823253352195024 lr:1.5708419435684462e-06 tokens_per_second_per_gpu:6486.65855455509 |
|
Step 233 | loss:0.0018634963780641556 lr:1.4019499710726913e-06 tokens_per_second_per_gpu:7278.072226096169 |
|
Step 234 | loss:0.0031143079977482557 lr:1.2425322847218368e-06 tokens_per_second_per_gpu:6957.95479374049 |
|
Step 235 | loss:0.0011264184722676873 lr:1.0926199633097157e-06 tokens_per_second_per_gpu:7216.515466506608 |
|
Step 236 | loss:0.005288551561534405 lr:9.522422325404235e-07 tokens_per_second_per_gpu:6428.192128174768 |
|
Step 237 | loss:0.0037977343890815973 lr:8.214264593307098e-07 tokens_per_second_per_gpu:6521.203830214014 |
|
Step 238 | loss:0.0003499909653328359 lr:7.001981464747565e-07 tokens_per_second_per_gpu:7241.208443274206 |
|
Step 239 | loss:0.0043595293536782265 lr:5.885809276723608e-07 tokens_per_second_per_gpu:6492.906947946128 |
|
Step 240 | loss:0.0011807921109721065 lr:4.865965629214819e-07 tokens_per_second_per_gpu:7069.790075453518 |
|
Step 241 | loss:0.00025632345932535827 lr:3.9426493427611177e-07 tokens_per_second_per_gpu:7144.6617239354355 |
|
Step 242 | loss:0.0027939260471612215 lr:3.1160404197018154e-07 tokens_per_second_per_gpu:1592.0295641084367 |
|
Step 243 | loss:0.001873334520496428 lr:2.386300009084408e-07 tokens_per_second_per_gpu:6940.034241696873 |
|
Step 244 | loss:0.0008832565508782864 lr:1.753570375247815e-07 tokens_per_second_per_gpu:7163.385015511229 |
|
Step 245 | loss:0.0017294981516897678 lr:1.2179748700879012e-07 tokens_per_second_per_gpu:6821.565172963375 |
|
Step 246 | loss:0.0005943347350694239 lr:7.796179090094891e-08 tokens_per_second_per_gpu:6909.70146320807 |
|
Step 247 | loss:0.0007064866367727518 lr:4.385849505708084e-08 tokens_per_second_per_gpu:6958.6679885338135 |
|
Step 248 | loss:0.0003860986034851521 lr:1.949424798228239e-08 tokens_per_second_per_gpu:7255.372580433174 |
|
Step 249 | loss:0.0011743954382836819 lr:4.873799534788059e-09 tokens_per_second_per_gpu:7264.828966990349 |
|
Step 250 | loss:0.0004887557588517666 lr:0.0 tokens_per_second_per_gpu:6878.743492292974 |
|
|