Step 1 | loss:0.013372980058193207 lr:4.000000000000001e-06 tokens_per_second_per_gpu:3874.8165404626934 Step 2 | loss:0.008318759500980377 lr:8.000000000000001e-06 tokens_per_second_per_gpu:3994.9100071089683 Step 3 | loss:0.020588943734765053 lr:1.2e-05 tokens_per_second_per_gpu:2622.9347670806737 Step 4 | loss:0.015207692980766296 lr:1.6000000000000003e-05 tokens_per_second_per_gpu:7117.680403972301 Step 5 | loss:0.015772100538015366 lr:2e-05 tokens_per_second_per_gpu:2841.3650484667232 Step 6 | loss:0.014235018752515316 lr:2.4e-05 tokens_per_second_per_gpu:7144.18862882571 Step 7 | loss:0.04776996001601219 lr:2.8000000000000003e-05 tokens_per_second_per_gpu:6944.746126975525 Step 8 | loss:0.01470720861107111 lr:3.2000000000000005e-05 tokens_per_second_per_gpu:7099.559212838606 Step 9 | loss:0.011193573474884033 lr:3.6e-05 tokens_per_second_per_gpu:7085.40196576822 Step 10 | loss:0.010021017864346504 lr:4e-05 tokens_per_second_per_gpu:7123.146230649066 Step 11 | loss:0.01647418551146984 lr:4.4000000000000006e-05 tokens_per_second_per_gpu:7026.652050826819 Step 12 | loss:0.011999926529824734 lr:4.8e-05 tokens_per_second_per_gpu:7097.950716141434 Step 13 | loss:0.022550508379936218 lr:5.2000000000000004e-05 tokens_per_second_per_gpu:5038.530118848792 Step 14 | loss:0.01995103433728218 lr:5.6000000000000006e-05 tokens_per_second_per_gpu:4248.733461591392 Step 15 | loss:0.006620384287089109 lr:6e-05 tokens_per_second_per_gpu:7131.65967860037 Step 16 | loss:0.00740306731313467 lr:6.400000000000001e-05 tokens_per_second_per_gpu:7127.628243449412 Step 17 | loss:0.0060096438974142075 lr:6.800000000000001e-05 tokens_per_second_per_gpu:4974.283310307197 Step 18 | loss:0.006891552358865738 lr:7.2e-05 tokens_per_second_per_gpu:7093.440515229761 Step 19 | loss:0.03327202796936035 lr:7.6e-05 tokens_per_second_per_gpu:3179.4929076391018 Step 20 | loss:0.009643638506531715 lr:8e-05 tokens_per_second_per_gpu:3810.467892928971 Step 21 | loss:0.005601323209702969 lr:8.4e-05 tokens_per_second_per_gpu:3646.923119975776 Step 22 | loss:0.007782038766890764 lr:8.800000000000001e-05 tokens_per_second_per_gpu:7135.31195854449 Step 23 | loss:0.00458392733708024 lr:9.200000000000001e-05 tokens_per_second_per_gpu:7043.86940911673 Step 24 | loss:0.004309103358536959 lr:9.6e-05 tokens_per_second_per_gpu:4565.439191471691 Step 25 | loss:0.01496342197060585 lr:0.0001 tokens_per_second_per_gpu:7025.824794922582 Step 26 | loss:0.004186063073575497 lr:9.999512620046522e-05 tokens_per_second_per_gpu:7152.228127227936 Step 27 | loss:0.0035033023450523615 lr:9.998050575201771e-05 tokens_per_second_per_gpu:6816.616531689177 Step 28 | loss:0.00774459820240736 lr:9.995614150494293e-05 tokens_per_second_per_gpu:6955.943011111193 Step 29 | loss:0.0031369992066174746 lr:9.992203820909906e-05 tokens_per_second_per_gpu:6952.491947617002 Step 30 | loss:0.0030230407137423754 lr:9.987820251299122e-05 tokens_per_second_per_gpu:6775.238885333704 Step 31 | loss:0.003314398694783449 lr:9.982464296247522e-05 tokens_per_second_per_gpu:7106.728739581611 Step 32 | loss:0.001633325358852744 lr:9.976136999909156e-05 tokens_per_second_per_gpu:3764.4525024505992 Step 33 | loss:0.005330185871571302 lr:9.968839595802982e-05 tokens_per_second_per_gpu:3603.47294425594 Step 34 | loss:0.0014852150343358517 lr:9.96057350657239e-05 tokens_per_second_per_gpu:7117.485152356746 Step 35 | loss:0.003130739787593484 lr:9.951340343707852e-05 tokens_per_second_per_gpu:6990.789773012925 Step 36 | loss:0.004151569213718176 lr:9.941141907232765e-05 tokens_per_second_per_gpu:7033.465646617793 Step 37 | loss:0.013509933836758137 lr:9.929980185352526e-05 tokens_per_second_per_gpu:7094.785297432972 Step 38 | loss:0.001217296696268022 lr:9.917857354066931e-05 tokens_per_second_per_gpu:6891.074270619146 Step 39 | loss:0.018984084948897362 lr:9.904775776745958e-05 tokens_per_second_per_gpu:6937.616604164713 Step 40 | loss:0.0024438444525003433 lr:9.890738003669029e-05 tokens_per_second_per_gpu:7102.9656227885835 Step 41 | loss:0.004817514214664698 lr:9.875746771527816e-05 tokens_per_second_per_gpu:6932.069229790838 Step 42 | loss:0.00136182748246938 lr:9.859805002892732e-05 tokens_per_second_per_gpu:7147.055721597306 Step 43 | loss:0.001384297152981162 lr:9.842915805643155e-05 tokens_per_second_per_gpu:6985.959203114564 Step 44 | loss:0.002320047002285719 lr:9.825082472361557e-05 tokens_per_second_per_gpu:7128.594394261389 Step 45 | loss:0.0039440966211259365 lr:9.806308479691595e-05 tokens_per_second_per_gpu:7092.24097995752 Step 46 | loss:0.002282568486407399 lr:9.786597487660337e-05 tokens_per_second_per_gpu:7099.248524495624 Step 47 | loss:0.007890361361205578 lr:9.765953338964735e-05 tokens_per_second_per_gpu:7125.180928719208 Step 48 | loss:0.0063784425146877766 lr:9.744380058222483e-05 tokens_per_second_per_gpu:3185.985379749494 Step 49 | loss:0.0014725268119946122 lr:9.721881851187406e-05 tokens_per_second_per_gpu:2882.7688858859356 Step 50 | loss:0.0023472707252949476 lr:9.698463103929542e-05 tokens_per_second_per_gpu:7020.361247128179 Step 51 | loss:0.005551986861974001 lr:9.674128381980072e-05 tokens_per_second_per_gpu:7138.453096495373 Step 52 | loss:0.0020946969743818045 lr:9.648882429441257e-05 tokens_per_second_per_gpu:7095.370745145354 Step 53 | loss:0.0014590605860576034 lr:9.622730168061567e-05 tokens_per_second_per_gpu:6938.182521117374 Step 54 | loss:0.0026314163114875555 lr:9.595676696276172e-05 tokens_per_second_per_gpu:7146.813608067687 Step 55 | loss:0.004251094534993172 lr:9.567727288213005e-05 tokens_per_second_per_gpu:7020.545527205833 Step 56 | loss:0.002550149569287896 lr:9.538887392664544e-05 tokens_per_second_per_gpu:6238.048724097262 Step 57 | loss:0.0020003155805170536 lr:9.50916263202557e-05 tokens_per_second_per_gpu:6745.993080512584 Step 58 | loss:0.010202882811427116 lr:9.478558801197065e-05 tokens_per_second_per_gpu:1990.4750697143486 Step 59 | loss:0.005923750344663858 lr:9.447081866456489e-05 tokens_per_second_per_gpu:6820.061144228702 Step 60 | loss:0.0033114587422460318 lr:9.414737964294636e-05 tokens_per_second_per_gpu:7085.365520634816 Step 61 | loss:0.002277028514072299 lr:9.381533400219318e-05 tokens_per_second_per_gpu:6987.3647924218085 Step 62 | loss:0.0060898070223629475 lr:9.347474647526095e-05 tokens_per_second_per_gpu:6994.6666444410985 Step 63 | loss:0.0019283033907413483 lr:9.312568346036288e-05 tokens_per_second_per_gpu:6814.584929042839 Step 64 | loss:0.0009065241320058703 lr:9.276821300802534e-05 tokens_per_second_per_gpu:7062.157178065032 Step 65 | loss:0.001274686655960977 lr:9.24024048078213e-05 tokens_per_second_per_gpu:7123.374265454482 Step 66 | loss:0.002168378559872508 lr:9.202833017478422e-05 tokens_per_second_per_gpu:7069.50761988174 Step 67 | loss:0.0021304618567228317 lr:9.164606203550497e-05 tokens_per_second_per_gpu:7052.259079224 Step 68 | loss:0.002201642142608762 lr:9.125567491391476e-05 tokens_per_second_per_gpu:7136.391561456483 Step 69 | loss:0.0009723631665110588 lr:9.085724491675642e-05 tokens_per_second_per_gpu:7064.5492701151925 Step 70 | loss:0.003060169517993927 lr:9.045084971874738e-05 tokens_per_second_per_gpu:6941.652866473926 Step 71 | loss:0.0032122512347996235 lr:9.003656854743667e-05 tokens_per_second_per_gpu:7022.946844400017 Step 72 | loss:0.0020385109819471836 lr:8.961448216775954e-05 tokens_per_second_per_gpu:6927.626839447722 Step 73 | loss:0.001373852021060884 lr:8.9184672866292e-05 tokens_per_second_per_gpu:7065.016192215358 Step 74 | loss:0.004395594820380211 lr:8.874722443520899e-05 tokens_per_second_per_gpu:7113.838441720636 Step 75 | loss:0.0020413161255419254 lr:8.83022221559489e-05 tokens_per_second_per_gpu:7119.761473963676 Step 76 | loss:0.003172144526615739 lr:8.784975278258783e-05 tokens_per_second_per_gpu:7129.411685133083 Step 77 | loss:0.0022230115719139576 lr:8.73899045249266e-05 tokens_per_second_per_gpu:7063.9619534628155 Step 78 | loss:0.0008520846022292972 lr:8.692276703129421e-05 tokens_per_second_per_gpu:7034.131822093049 Step 79 | loss:0.001710437354631722 lr:8.644843137107059e-05 tokens_per_second_per_gpu:7058.615724528316 Step 80 | loss:0.0006989283137954772 lr:8.596699001693255e-05 tokens_per_second_per_gpu:6876.49493969523 Step 81 | loss:0.0011765643721446395 lr:8.547853682682604e-05 tokens_per_second_per_gpu:6893.020499058587 Step 82 | loss:0.002165679819881916 lr:8.498316702566828e-05 tokens_per_second_per_gpu:7026.9744119362285 Step 83 | loss:0.001775385346263647 lr:8.44809771867835e-05 tokens_per_second_per_gpu:6819.755051209656 Step 84 | loss:0.002057864563539624 lr:8.397206521307584e-05 tokens_per_second_per_gpu:7161.343267645968 Step 85 | loss:0.0026688796933740377 lr:8.345653031794292e-05 tokens_per_second_per_gpu:7056.729456010942 Step 86 | loss:0.0009387475438416004 lr:8.293447300593402e-05 tokens_per_second_per_gpu:7046.82909670213 Step 87 | loss:0.0029537666123360395 lr:8.240599505315655e-05 tokens_per_second_per_gpu:7163.705186401793 Step 88 | loss:0.001403899397701025 lr:8.18711994874345e-05 tokens_per_second_per_gpu:7086.841256326294 Step 89 | loss:0.0009538537124171853 lr:8.133019056822304e-05 tokens_per_second_per_gpu:6745.587328039051 Step 90 | loss:0.0026184518355876207 lr:8.07830737662829e-05 tokens_per_second_per_gpu:7151.122838997032 Step 91 | loss:0.0038881609216332436 lr:8.022995574311876e-05 tokens_per_second_per_gpu:7109.856026332342 Step 92 | loss:0.0007222425774671137 lr:7.967094433018508e-05 tokens_per_second_per_gpu:7084.979094367599 Step 93 | loss:0.00215703877620399 lr:7.910614850786448e-05 tokens_per_second_per_gpu:7127.295756871386 Step 94 | loss:0.00035772137925960124 lr:7.85356783842216e-05 tokens_per_second_per_gpu:6902.882920407662 Step 95 | loss:0.00417992053553462 lr:7.795964517353735e-05 tokens_per_second_per_gpu:6972.93791991583 Step 96 | loss:0.001009405474178493 lr:7.737816117462752e-05 tokens_per_second_per_gpu:7052.199205708232 Step 97 | loss:0.0009588804095983505 lr:7.679133974894983e-05 tokens_per_second_per_gpu:7000.472939006606 Step 98 | loss:0.0018452832009643316 lr:7.619929529850397e-05 tokens_per_second_per_gpu:7084.619581608012 Step 99 | loss:0.0035648574121296406 lr:7.560214324352858e-05 tokens_per_second_per_gpu:7087.564819676298 Step 100 | loss:0.0012323096161708236 lr:7.500000000000001e-05 tokens_per_second_per_gpu:6959.057675476407 Step 101 | loss:0.0014938520034775138 lr:7.439298295693665e-05 tokens_per_second_per_gpu:7144.913116406752 Step 102 | loss:0.001955854007974267 lr:7.378121045351378e-05 tokens_per_second_per_gpu:7067.2556906500395 Step 103 | loss:0.0031611681915819645 lr:7.316480175599309e-05 tokens_per_second_per_gpu:6974.208066732836 Step 104 | loss:0.00555458152666688 lr:7.254387703447154e-05 tokens_per_second_per_gpu:6906.162536864967 Step 105 | loss:0.001002943841740489 lr:7.191855733945387e-05 tokens_per_second_per_gpu:6972.908661671081 Step 106 | loss:0.0017082667909562588 lr:7.128896457825364e-05 tokens_per_second_per_gpu:7005.0246815049695 Step 107 | loss:0.0013688785256817937 lr:7.06552214912271e-05 tokens_per_second_per_gpu:7103.879138546548 Step 108 | loss:0.0005387114943005145 lr:7.001745162784477e-05 tokens_per_second_per_gpu:6982.492730096482 Step 109 | loss:0.0016628771554678679 lr:6.937577932260515e-05 tokens_per_second_per_gpu:7014.960024636566 Step 110 | loss:0.004161191172897816 lr:6.873032967079561e-05 tokens_per_second_per_gpu:6953.228299164842 Step 111 | loss:0.0009758872911334038 lr:6.808122850410461e-05 tokens_per_second_per_gpu:6855.019034410367 Step 112 | loss:0.0013757736887782812 lr:6.742860236609077e-05 tokens_per_second_per_gpu:6921.972251687803 Step 113 | loss:0.0019739512354135513 lr:6.677257848751277e-05 tokens_per_second_per_gpu:7069.092554140731 Step 114 | loss:0.0011348786065354943 lr:6.611328476152557e-05 tokens_per_second_per_gpu:7158.150929958733 Step 115 | loss:0.003932917956262827 lr:6.545084971874738e-05 tokens_per_second_per_gpu:6947.480109452886 Step 116 | loss:0.0009977880399674177 lr:6.478540250220234e-05 tokens_per_second_per_gpu:7127.033721864732 Step 117 | loss:0.00743027264252305 lr:6.411707284214384e-05 tokens_per_second_per_gpu:7096.241446538374 Step 118 | loss:0.002439243718981743 lr:6.344599103076329e-05 tokens_per_second_per_gpu:6935.2267354820715 Step 119 | loss:0.0004214672080706805 lr:6.277228789678953e-05 tokens_per_second_per_gpu:7091.56909795498 Step 120 | loss:0.0007211238844320178 lr:6.209609477998338e-05 tokens_per_second_per_gpu:6898.000938353513 Step 121 | loss:0.0007646355079486966 lr:6.141754350553279e-05 tokens_per_second_per_gpu:7099.772787485942 Step 122 | loss:0.0011237451108172536 lr:6.073676635835317e-05 tokens_per_second_per_gpu:6775.0731863648925 Step 123 | loss:0.0006198790506459773 lr:6.005389605729824e-05 tokens_per_second_per_gpu:7153.354180313162 Step 124 | loss:0.00046897237189114094 lr:5.9369065729286245e-05 tokens_per_second_per_gpu:6944.312583773988 Step 125 | loss:0.0015241801738739014 lr:5.868240888334653e-05 tokens_per_second_per_gpu:7065.43870966363 Step 126 | loss:0.00150835991371423 lr:5.799405938459175e-05 tokens_per_second_per_gpu:6991.128441325819 Step 127 | loss:0.0031010867096483707 lr:5.730415142812059e-05 tokens_per_second_per_gpu:7042.518093887544 Step 128 | loss:0.000658935634419322 lr:5.661281951285613e-05 tokens_per_second_per_gpu:6984.4888204604495 Step 129 | loss:0.0019208983285352588 lr:5.5920198415325064e-05 tokens_per_second_per_gpu:7114.971657321872 Step 130 | loss:0.010894868522882462 lr:5.522642316338268e-05 tokens_per_second_per_gpu:6949.150946368696 Step 131 | loss:0.0006857437547296286 lr:5.453162900988902e-05 tokens_per_second_per_gpu:7138.962920295958 Step 132 | loss:0.0025876301806420088 lr:5.383595140634093e-05 tokens_per_second_per_gpu:6911.379588236837 Step 133 | loss:0.0007797284051775932 lr:5.313952597646568e-05 tokens_per_second_per_gpu:7010.2993322206075 Step 134 | loss:0.0006535501452162862 lr:5.244248848978067e-05 tokens_per_second_per_gpu:7117.641226887859 Step 135 | loss:0.0011649364605545998 lr:5.174497483512506e-05 tokens_per_second_per_gpu:7042.7284180611705 Step 136 | loss:0.00197750236839056 lr:5.104712099416785e-05 tokens_per_second_per_gpu:6937.186163094593 Step 137 | loss:0.0006281325477175415 lr:5.034906301489808e-05 tokens_per_second_per_gpu:6890.483427881456 Step 138 | loss:0.0004475094028748572 lr:4.965093698510193e-05 tokens_per_second_per_gpu:7061.311318509494 Step 139 | loss:0.001448856433853507 lr:4.895287900583216e-05 tokens_per_second_per_gpu:6794.672713275055 Step 140 | loss:0.0017595699755474925 lr:4.825502516487497e-05 tokens_per_second_per_gpu:6787.3119728029815 Step 141 | loss:0.0038012624718248844 lr:4.755751151021934e-05 tokens_per_second_per_gpu:7027.214726395109 Step 142 | loss:0.0019520800560712814 lr:4.6860474023534335e-05 tokens_per_second_per_gpu:7069.12945612731 Step 143 | loss:0.001292936853133142 lr:4.616404859365907e-05 tokens_per_second_per_gpu:6698.106579498869 Step 144 | loss:0.0011428159195929766 lr:4.5468370990111006e-05 tokens_per_second_per_gpu:6902.521683648508 Step 145 | loss:0.004733377136290073 lr:4.477357683661734e-05 tokens_per_second_per_gpu:7006.496317744093 Step 146 | loss:0.00043399244896136224 lr:4.407980158467495e-05 tokens_per_second_per_gpu:7114.975104224623 Step 147 | loss:0.0014300920302048326 lr:4.3387180487143876e-05 tokens_per_second_per_gpu:7081.525811614731 Step 148 | loss:0.000798733439296484 lr:4.269584857187943e-05 tokens_per_second_per_gpu:7045.750572126043 Step 149 | loss:0.002541664056479931 lr:4.2005940615408264e-05 tokens_per_second_per_gpu:6900.663567071848 Step 150 | loss:0.0009505233610980213 lr:4.131759111665349e-05 tokens_per_second_per_gpu:6986.384852225816 Step 151 | loss:0.001285750069655478 lr:4.063093427071376e-05 tokens_per_second_per_gpu:7168.225778742038 Step 152 | loss:0.0008513851789757609 lr:3.9946103942701777e-05 tokens_per_second_per_gpu:7039.891508284199 Step 153 | loss:0.0036429339088499546 lr:3.926323364164684e-05 tokens_per_second_per_gpu:7007.155142247289 Step 154 | loss:0.001225275918841362 lr:3.858245649446721e-05 tokens_per_second_per_gpu:7075.071287563538 Step 155 | loss:0.0014096405357122421 lr:3.790390522001662e-05 tokens_per_second_per_gpu:6981.197578253649 Step 156 | loss:0.0010392990661785007 lr:3.7227712103210486e-05 tokens_per_second_per_gpu:7098.612489109119 Step 157 | loss:0.0027088394854217768 lr:3.655400896923672e-05 tokens_per_second_per_gpu:7156.940597865128 Step 158 | loss:0.003336328314617276 lr:3.588292715785617e-05 tokens_per_second_per_gpu:6945.79586399277 Step 159 | loss:0.0022836641874164343 lr:3.5214597497797684e-05 tokens_per_second_per_gpu:6948.45775123944 Step 160 | loss:0.00043441716115921736 lr:3.4549150281252636e-05 tokens_per_second_per_gpu:7117.049542009377 Step 161 | loss:0.0015876208199188113 lr:3.388671523847445e-05 tokens_per_second_per_gpu:6917.912796460095 Step 162 | loss:0.0003647822595667094 lr:3.322742151248725e-05 tokens_per_second_per_gpu:7135.103724169449 Step 163 | loss:0.0021626269444823265 lr:3.257139763390925e-05 tokens_per_second_per_gpu:6914.728402143451 Step 164 | loss:0.002703474136069417 lr:3.1918771495895396e-05 tokens_per_second_per_gpu:6896.78496264613 Step 165 | loss:0.0022170422598719597 lr:3.12696703292044e-05 tokens_per_second_per_gpu:7088.043016537944 Step 166 | loss:0.0008771849097684026 lr:3.062422067739485e-05 tokens_per_second_per_gpu:6884.6708126055555 Step 167 | loss:0.0016094500897452235 lr:2.9982548372155263e-05 tokens_per_second_per_gpu:6842.5530033440355 Step 168 | loss:0.0004359333252068609 lr:2.934477850877292e-05 tokens_per_second_per_gpu:7025.009382698733 Step 169 | loss:0.00035868945997208357 lr:2.8711035421746367e-05 tokens_per_second_per_gpu:6818.46959405271 Step 170 | loss:0.0010377708822488785 lr:2.8081442660546125e-05 tokens_per_second_per_gpu:6963.642834178167 Step 171 | loss:0.004563743248581886 lr:2.7456122965528475e-05 tokens_per_second_per_gpu:7009.664219092231 Step 172 | loss:0.002375879557803273 lr:2.6835198244006927e-05 tokens_per_second_per_gpu:7145.9721486139315 Step 173 | loss:0.0013227115850895643 lr:2.6218789546486234e-05 tokens_per_second_per_gpu:7027.731133241178 Step 174 | loss:0.001065325690433383 lr:2.560701704306336e-05 tokens_per_second_per_gpu:7145.854333408454 Step 175 | loss:0.00026451688609085977 lr:2.500000000000001e-05 tokens_per_second_per_gpu:6977.66593747055 Step 176 | loss:0.0007138861110433936 lr:2.4397856756471432e-05 tokens_per_second_per_gpu:7035.885887306675 Step 177 | loss:0.000287461094558239 lr:2.3800704701496053e-05 tokens_per_second_per_gpu:6875.0926933782675 Step 178 | loss:0.0005073968786746264 lr:2.3208660251050158e-05 tokens_per_second_per_gpu:7110.455798158638 Step 179 | loss:0.0009222722728736699 lr:2.2621838825372493e-05 tokens_per_second_per_gpu:7084.7714553618725 Step 180 | loss:0.0010540970833972096 lr:2.2040354826462668e-05 tokens_per_second_per_gpu:6988.182011407202 Step 181 | loss:0.00043954243301413953 lr:2.1464321615778422e-05 tokens_per_second_per_gpu:7011.86383701614 Step 182 | loss:0.0011906925356015563 lr:2.0893851492135537e-05 tokens_per_second_per_gpu:6885.3141883194785 Step 183 | loss:0.002102498197928071 lr:2.0329055669814934e-05 tokens_per_second_per_gpu:7080.036222220117 Step 184 | loss:0.0005148081108927727 lr:1.977004425688126e-05 tokens_per_second_per_gpu:7076.435828090621 Step 185 | loss:0.0012309339363127947 lr:1.9216926233717085e-05 tokens_per_second_per_gpu:7017.950566668733 Step 186 | loss:0.0015539468731731176 lr:1.866980943177699e-05 tokens_per_second_per_gpu:7132.538506473828 Step 187 | loss:0.001363910036161542 lr:1.8128800512565513e-05 tokens_per_second_per_gpu:6969.457191706217 Step 188 | loss:0.0008457832736894488 lr:1.7594004946843456e-05 tokens_per_second_per_gpu:7114.060352573214 Step 189 | loss:0.0006026898045092821 lr:1.7065526994065973e-05 tokens_per_second_per_gpu:7100.238133807311 Step 190 | loss:0.002620010171085596 lr:1.6543469682057106e-05 tokens_per_second_per_gpu:6917.934596811246 Step 191 | loss:0.0005382331437431276 lr:1.602793478692419e-05 tokens_per_second_per_gpu:7129.193352348408 Step 192 | loss:0.0011343047954142094 lr:1.551902281321651e-05 tokens_per_second_per_gpu:7089.743379925699 Step 193 | loss:0.0001948566932696849 lr:1.5016832974331724e-05 tokens_per_second_per_gpu:6958.511568194661 Step 194 | loss:0.0032963843550533056 lr:1.4521463173173965e-05 tokens_per_second_per_gpu:7153.5391956230305 Step 195 | loss:0.0013983447570353746 lr:1.4033009983067452e-05 tokens_per_second_per_gpu:7092.817204790224 Step 196 | loss:0.0004038666083943099 lr:1.3551568628929434e-05 tokens_per_second_per_gpu:7034.465560501549 Step 197 | loss:0.0005019771633669734 lr:1.3077232968705805e-05 tokens_per_second_per_gpu:7133.788517058802 Step 198 | loss:0.002158497227355838 lr:1.2610095475073414e-05 tokens_per_second_per_gpu:6935.653682473058 Step 199 | loss:0.0004485348763410002 lr:1.2150247217412186e-05 tokens_per_second_per_gpu:7035.408824162851 Step 200 | loss:0.0010387710062786937 lr:1.1697777844051105e-05 tokens_per_second_per_gpu:6995.588587661693 Step 201 | loss:0.0014105384470894933 lr:1.1252775564791024e-05 tokens_per_second_per_gpu:7165.8917280504775 Step 202 | loss:0.0008372652227990329 lr:1.0815327133708015e-05 tokens_per_second_per_gpu:6824.845028945261 Step 203 | loss:0.0016373236430808902 lr:1.0385517832240471e-05 tokens_per_second_per_gpu:6983.390434038561 Step 204 | loss:0.0010298008564859629 lr:9.963431452563332e-06 tokens_per_second_per_gpu:7092.856782372603 Step 205 | loss:0.0005104406154714525 lr:9.549150281252633e-06 tokens_per_second_per_gpu:6979.889176254553 Step 206 | loss:0.00044149774475954473 lr:9.142755083243576e-06 tokens_per_second_per_gpu:6729.542240077146 Step 207 | loss:0.0016503415536135435 lr:8.744325086085248e-06 tokens_per_second_per_gpu:7045.859341655128 Step 208 | loss:0.0021091720554977655 lr:8.353937964495029e-06 tokens_per_second_per_gpu:6960.631753252208 Step 209 | loss:0.0014547959435731173 lr:7.971669825215788e-06 tokens_per_second_per_gpu:7140.638028664293 Step 210 | loss:0.0011278915917500854 lr:7.597595192178702e-06 tokens_per_second_per_gpu:7112.024889474323 Step 211 | loss:0.0008361373329535127 lr:7.2317869919746705e-06 tokens_per_second_per_gpu:6825.989889307472 Step 212 | loss:0.0011150042992085218 lr:6.874316539637127e-06 tokens_per_second_per_gpu:6953.677938236041 Step 213 | loss:0.00025254415231756866 lr:6.52525352473905e-06 tokens_per_second_per_gpu:6989.570204640159 Step 214 | loss:0.0016249557957053185 lr:6.184665997806832e-06 tokens_per_second_per_gpu:7133.165202912919 Step 215 | loss:0.001143998233601451 lr:5.852620357053651e-06 tokens_per_second_per_gpu:7051.853256206377 Step 216 | loss:0.000365725951269269 lr:5.529181335435124e-06 tokens_per_second_per_gpu:7109.042950385973 Step 217 | loss:0.0015886126784607768 lr:5.214411988029355e-06 tokens_per_second_per_gpu:7028.875248251393 Step 218 | loss:0.0013761294540017843 lr:4.908373679744316e-06 tokens_per_second_per_gpu:7108.213051111388 Step 219 | loss:0.0018573033157736063 lr:4.611126073354571e-06 tokens_per_second_per_gpu:7125.91419319748 Step 220 | loss:0.0019727428443729877 lr:4.322727117869951e-06 tokens_per_second_per_gpu:6949.702618624644 Step 221 | loss:0.00046489882515743375 lr:4.043233037238281e-06 tokens_per_second_per_gpu:7082.179158830416 Step 222 | loss:0.001256947172805667 lr:3.772698319384349e-06 tokens_per_second_per_gpu:7154.753459188333 Step 223 | loss:0.0007704919553361833 lr:3.511175705587433e-06 tokens_per_second_per_gpu:7084.612916916432 Step 224 | loss:0.00048463058192282915 lr:3.258716180199278e-06 tokens_per_second_per_gpu:7100.661102645909 Step 225 | loss:0.0015112065011635423 lr:3.0153689607045845e-06 tokens_per_second_per_gpu:6986.426070544913 Step 226 | loss:0.0014505032449960709 lr:2.7811814881259503e-06 tokens_per_second_per_gpu:7057.156034274591 Step 227 | loss:0.0017806094838306308 lr:2.5561994177751737e-06 tokens_per_second_per_gpu:6967.176853458735 Step 228 | loss:0.0016619979869574308 lr:2.340466610352654e-06 tokens_per_second_per_gpu:6959.813413974034 Step 229 | loss:0.0012311894679442048 lr:2.134025123396638e-06 tokens_per_second_per_gpu:7026.055783363448 Step 230 | loss:0.0019572905730456114 lr:1.9369152030840556e-06 tokens_per_second_per_gpu:7062.787034722274 Step 231 | loss:0.0016982824308797717 lr:1.7491752763844293e-06 tokens_per_second_per_gpu:6831.063215360656 Step 232 | loss:0.0021078097634017467 lr:1.5708419435684462e-06 tokens_per_second_per_gpu:7086.32389932558 Step 233 | loss:0.0013445017393678427 lr:1.4019499710726913e-06 tokens_per_second_per_gpu:6977.155383959046 Step 234 | loss:0.00036836747312918305 lr:1.2425322847218368e-06 tokens_per_second_per_gpu:7094.678174910597 Step 235 | loss:0.0005533919320441782 lr:1.0926199633097157e-06 tokens_per_second_per_gpu:7031.788985841722 Step 236 | loss:0.0016440795734524727 lr:9.522422325404235e-07 tokens_per_second_per_gpu:7046.472693651047 Step 237 | loss:0.0013803904876112938 lr:8.214264593307098e-07 tokens_per_second_per_gpu:6975.3985161252995 Step 238 | loss:0.0009708477882668376 lr:7.001981464747565e-07 tokens_per_second_per_gpu:7049.375475406457 Step 239 | loss:0.00199791113846004 lr:5.885809276723608e-07 tokens_per_second_per_gpu:7017.553232092998 Step 240 | loss:0.0015766591532155871 lr:4.865965629214819e-07 tokens_per_second_per_gpu:6955.9168267022715 Step 241 | loss:0.0014465312706306577 lr:3.9426493427611177e-07 tokens_per_second_per_gpu:6931.547567024191 Step 242 | loss:0.0013422713382169604 lr:3.1160404197018154e-07 tokens_per_second_per_gpu:7060.875940299212 Step 243 | loss:0.0006091100513003767 lr:2.386300009084408e-07 tokens_per_second_per_gpu:7146.698945228412 Step 244 | loss:0.0005727412644773722 lr:1.753570375247815e-07 tokens_per_second_per_gpu:7135.779924518519 Step 245 | loss:0.0005283570499159396 lr:1.2179748700879012e-07 tokens_per_second_per_gpu:7015.242118553269 Step 246 | loss:0.00038219685666263103 lr:7.796179090094891e-08 tokens_per_second_per_gpu:7149.8793604615785 Step 247 | loss:0.0014308899408206344 lr:4.385849505708084e-08 tokens_per_second_per_gpu:7180.676959868798 Step 248 | loss:0.00210582185536623 lr:1.949424798228239e-08 tokens_per_second_per_gpu:7132.91353743717 Step 249 | loss:0.0010692310752347112 lr:4.873799534788059e-09 tokens_per_second_per_gpu:7011.347544756431 Step 250 | loss:0.002054369542747736 lr:0.0 tokens_per_second_per_gpu:7147.0550602441635