Step 1 | loss:0.09594444930553436 lr:4.000000000000001e-06 tokens_per_second_per_gpu:1715.6769661527067 
Step 2 | loss:0.032612573355436325 lr:8.000000000000001e-06 tokens_per_second_per_gpu:4257.384016888243 
Step 3 | loss:0.03703868016600609 lr:1.2e-05 tokens_per_second_per_gpu:7118.213139384143 
Step 4 | loss:0.04869644343852997 lr:1.6000000000000003e-05 tokens_per_second_per_gpu:2861.776388430861 
Step 5 | loss:0.04404347762465477 lr:2e-05 tokens_per_second_per_gpu:2890.405749137227 
Step 6 | loss:0.04101202264428139 lr:2.4e-05 tokens_per_second_per_gpu:7102.234102434205 
Step 7 | loss:0.048599839210510254 lr:2.8000000000000003e-05 tokens_per_second_per_gpu:7020.581060628121 
Step 8 | loss:0.024283362552523613 lr:3.2000000000000005e-05 tokens_per_second_per_gpu:6993.611958028155 
Step 9 | loss:0.03192838281393051 lr:3.6e-05 tokens_per_second_per_gpu:7122.84532645759 
Step 10 | loss:0.07498080283403397 lr:4e-05 tokens_per_second_per_gpu:6758.487752244918 
Step 11 | loss:0.05588093400001526 lr:4.4000000000000006e-05 tokens_per_second_per_gpu:2187.1191955052795 
Step 12 | loss:0.06042847782373428 lr:4.8e-05 tokens_per_second_per_gpu:7091.115951473602 
Step 13 | loss:0.07163452357053757 lr:5.2000000000000004e-05 tokens_per_second_per_gpu:6771.857666986925 
Step 14 | loss:0.020770439878106117 lr:5.6000000000000006e-05 tokens_per_second_per_gpu:3408.1900982120937 
Step 15 | loss:0.07795064151287079 lr:6e-05 tokens_per_second_per_gpu:6720.726208902146 
Step 16 | loss:0.049128226935863495 lr:6.400000000000001e-05 tokens_per_second_per_gpu:7154.987550845856 
Step 17 | loss:0.03991858661174774 lr:6.800000000000001e-05 tokens_per_second_per_gpu:7038.071954264581 
Step 18 | loss:0.020218411460518837 lr:7.2e-05 tokens_per_second_per_gpu:7052.16330095677 
Step 19 | loss:0.049349959939718246 lr:7.6e-05 tokens_per_second_per_gpu:7135.243307802797 
Step 20 | loss:0.024519197642803192 lr:8e-05 tokens_per_second_per_gpu:7070.415186103101 
Step 21 | loss:0.06849371641874313 lr:8.4e-05 tokens_per_second_per_gpu:6798.501835862438 
Step 22 | loss:0.03306471183896065 lr:8.800000000000001e-05 tokens_per_second_per_gpu:7143.20493993916 
Step 23 | loss:0.038712278008461 lr:9.200000000000001e-05 tokens_per_second_per_gpu:7062.176042971551 
Step 24 | loss:0.022722184658050537 lr:9.6e-05 tokens_per_second_per_gpu:7093.97275491179 
Step 25 | loss:0.014121896587312222 lr:0.0001 tokens_per_second_per_gpu:7069.144169807532 
Step 26 | loss:0.0176176019012928 lr:9.999512620046522e-05 tokens_per_second_per_gpu:7131.631923799358 
Step 27 | loss:0.00988552626222372 lr:9.998050575201771e-05 tokens_per_second_per_gpu:6891.637589561682 
Step 28 | loss:0.010788653045892715 lr:9.995614150494293e-05 tokens_per_second_per_gpu:7146.763009204502 
Step 29 | loss:0.012993809767067432 lr:9.992203820909906e-05 tokens_per_second_per_gpu:7135.075134041281 
Step 30 | loss:0.011962542310357094 lr:9.987820251299122e-05 tokens_per_second_per_gpu:7080.446021298551 
Step 31 | loss:0.0072456710040569305 lr:9.982464296247522e-05 tokens_per_second_per_gpu:7100.213845627682 
Step 32 | loss:0.036037687212228775 lr:9.976136999909156e-05 tokens_per_second_per_gpu:2155.485116316584 
Step 33 | loss:0.010557749308645725 lr:9.968839595802982e-05 tokens_per_second_per_gpu:6916.82365083494 
Step 34 | loss:0.022763660177588463 lr:9.96057350657239e-05 tokens_per_second_per_gpu:6963.677786918989 
Step 35 | loss:0.05381365120410919 lr:9.951340343707852e-05 tokens_per_second_per_gpu:6749.30636485485 
Step 36 | loss:0.033899154514074326 lr:9.941141907232765e-05 tokens_per_second_per_gpu:7095.564843066931 
Step 37 | loss:0.004967940039932728 lr:9.929980185352526e-05 tokens_per_second_per_gpu:6990.531549510169 
Step 38 | loss:0.01169795822352171 lr:9.917857354066931e-05 tokens_per_second_per_gpu:7128.511183238077 
Step 39 | loss:0.012766576372087002 lr:9.904775776745958e-05 tokens_per_second_per_gpu:7079.308564480445 
Step 40 | loss:0.01314773503690958 lr:9.890738003669029e-05 tokens_per_second_per_gpu:7046.018317224989 
Step 41 | loss:0.0301198773086071 lr:9.875746771527816e-05 tokens_per_second_per_gpu:6641.960318371145 
Step 42 | loss:0.02045576646924019 lr:9.859805002892732e-05 tokens_per_second_per_gpu:7143.374203812877 
Step 43 | loss:0.009153805673122406 lr:9.842915805643155e-05 tokens_per_second_per_gpu:7057.907999612955 
Step 44 | loss:0.014376576989889145 lr:9.825082472361557e-05 tokens_per_second_per_gpu:7106.24093855879 
Step 45 | loss:0.006419774144887924 lr:9.806308479691595e-05 tokens_per_second_per_gpu:6975.467572936728 
Step 46 | loss:0.010145753622055054 lr:9.786597487660337e-05 tokens_per_second_per_gpu:7086.584362075627 
Step 47 | loss:0.01086120679974556 lr:9.765953338964735e-05 tokens_per_second_per_gpu:7082.111393455114 
Step 48 | loss:0.013914630748331547 lr:9.744380058222483e-05 tokens_per_second_per_gpu:7071.756851147732 
Step 49 | loss:0.006967062130570412 lr:9.721881851187406e-05 tokens_per_second_per_gpu:7096.142942882559 
Step 50 | loss:0.004446886479854584 lr:9.698463103929542e-05 tokens_per_second_per_gpu:7079.807724349228 
Step 51 | loss:0.011698620393872261 lr:9.674128381980072e-05 tokens_per_second_per_gpu:6734.770564917194 
Step 52 | loss:0.0073717557825148106 lr:9.648882429441257e-05 tokens_per_second_per_gpu:7099.255240592363 
Step 53 | loss:0.04363773763179779 lr:9.622730168061567e-05 tokens_per_second_per_gpu:1271.1740731348273 
Step 54 | loss:0.0032293389085680246 lr:9.595676696276172e-05 tokens_per_second_per_gpu:7009.180949621221 
Step 55 | loss:0.014490296132862568 lr:9.567727288213005e-05 tokens_per_second_per_gpu:7143.885987070321 
Step 56 | loss:0.02843150869011879 lr:9.538887392664544e-05 tokens_per_second_per_gpu:4646.515178976232 
Step 57 | loss:0.011716767214238644 lr:9.50916263202557e-05 tokens_per_second_per_gpu:6930.332067235958 
Step 58 | loss:0.011800938285887241 lr:9.478558801197065e-05 tokens_per_second_per_gpu:6956.873287159913 
Step 59 | loss:0.019172390922904015 lr:9.447081866456489e-05 tokens_per_second_per_gpu:7094.0306617429105 
Step 60 | loss:0.0029313103295862675 lr:9.414737964294636e-05 tokens_per_second_per_gpu:7074.439718451712 
Step 61 | loss:0.01510224211961031 lr:9.381533400219318e-05 tokens_per_second_per_gpu:7057.053816060703 
Step 62 | loss:0.012170720845460892 lr:9.347474647526095e-05 tokens_per_second_per_gpu:7054.9581135919825 
Step 63 | loss:0.002090180292725563 lr:9.312568346036288e-05 tokens_per_second_per_gpu:7041.351263053978 
Step 64 | loss:0.008515679277479649 lr:9.276821300802534e-05 tokens_per_second_per_gpu:7107.134029255465 
Step 65 | loss:0.005716190207749605 lr:9.24024048078213e-05 tokens_per_second_per_gpu:7033.337463035152 
Step 66 | loss:0.003724724519997835 lr:9.202833017478422e-05 tokens_per_second_per_gpu:6753.27843297091 
Step 67 | loss:0.0013471748679876328 lr:9.164606203550497e-05 tokens_per_second_per_gpu:7069.459297300209 
Step 68 | loss:0.028791621327400208 lr:9.125567491391476e-05 tokens_per_second_per_gpu:6762.340892360801 
Step 69 | loss:0.034610774368047714 lr:9.085724491675642e-05 tokens_per_second_per_gpu:6740.150911219675 
Step 70 | loss:0.008526662364602089 lr:9.045084971874738e-05 tokens_per_second_per_gpu:7074.943892812442 
Step 71 | loss:0.007055385038256645 lr:9.003656854743667e-05 tokens_per_second_per_gpu:7093.802250036825 
Step 72 | loss:0.004274093080312014 lr:8.961448216775954e-05 tokens_per_second_per_gpu:7177.604704465473 
Step 73 | loss:0.01708085462450981 lr:8.9184672866292e-05 tokens_per_second_per_gpu:7097.049507784967 
Step 74 | loss:0.004166878294199705 lr:8.874722443520899e-05 tokens_per_second_per_gpu:7110.845091689312 
Step 75 | loss:0.004323659930378199 lr:8.83022221559489e-05 tokens_per_second_per_gpu:7087.7417758858555 
Step 76 | loss:0.0018252398585900664 lr:8.784975278258783e-05 tokens_per_second_per_gpu:7066.170856740396 
Step 77 | loss:0.030012302100658417 lr:8.73899045249266e-05 tokens_per_second_per_gpu:6788.34487321683 
Step 78 | loss:0.0072570620104670525 lr:8.692276703129421e-05 tokens_per_second_per_gpu:7055.591958327719 
Step 79 | loss:0.01024627685546875 lr:8.644843137107059e-05 tokens_per_second_per_gpu:7099.121611303732 
Step 80 | loss:0.023203443735837936 lr:8.596699001693255e-05 tokens_per_second_per_gpu:6928.721677860912 
Step 81 | loss:0.025124238803982735 lr:8.547853682682604e-05 tokens_per_second_per_gpu:7085.958076572892 
Step 82 | loss:0.0048821973614394665 lr:8.498316702566828e-05 tokens_per_second_per_gpu:7065.727309648535 
Step 83 | loss:0.023713823407888412 lr:8.44809771867835e-05 tokens_per_second_per_gpu:5447.8865534438755 
Step 84 | loss:0.010438942350447178 lr:8.397206521307584e-05 tokens_per_second_per_gpu:7054.727469347494 
Step 85 | loss:0.012677349150180817 lr:8.345653031794292e-05 tokens_per_second_per_gpu:7059.575956676728 
Step 86 | loss:0.004624150227755308 lr:8.293447300593402e-05 tokens_per_second_per_gpu:7050.472275899744 
Step 87 | loss:0.0012963004410266876 lr:8.240599505315655e-05 tokens_per_second_per_gpu:7097.777791176698 
Step 88 | loss:0.004414051305502653 lr:8.18711994874345e-05 tokens_per_second_per_gpu:6981.526522990102 
Step 89 | loss:0.023303508758544922 lr:8.133019056822304e-05 tokens_per_second_per_gpu:6472.518825923673 
Step 90 | loss:0.0030153817497193813 lr:8.07830737662829e-05 tokens_per_second_per_gpu:7017.439179194748 
Step 91 | loss:0.00913572683930397 lr:8.022995574311876e-05 tokens_per_second_per_gpu:6943.81647207651 
Step 92 | loss:0.0011044674320146441 lr:7.967094433018508e-05 tokens_per_second_per_gpu:7048.682661139392 
Step 93 | loss:0.004775516223162413 lr:7.910614850786448e-05 tokens_per_second_per_gpu:6905.493230117229 
Step 94 | loss:0.008886449970304966 lr:7.85356783842216e-05 tokens_per_second_per_gpu:7115.512181418436 
Step 95 | loss:0.0027299695648252964 lr:7.795964517353735e-05 tokens_per_second_per_gpu:7081.430962658991 
Step 96 | loss:0.00905381515622139 lr:7.737816117462752e-05 tokens_per_second_per_gpu:7077.885327106005 
Step 97 | loss:0.0003037667484022677 lr:7.679133974894983e-05 tokens_per_second_per_gpu:7058.211221380861 
Step 98 | loss:0.0015372553607448936 lr:7.619929529850397e-05 tokens_per_second_per_gpu:7059.540422425649 
Step 99 | loss:0.00771813839673996 lr:7.560214324352858e-05 tokens_per_second_per_gpu:7163.497036762075 
Step 100 | loss:0.0002618357539176941 lr:7.500000000000001e-05 tokens_per_second_per_gpu:7129.741724390563 
Step 101 | loss:0.002139240736141801 lr:7.439298295693665e-05 tokens_per_second_per_gpu:7063.026386610476 
Step 102 | loss:0.000588633178267628 lr:7.378121045351378e-05 tokens_per_second_per_gpu:7085.274584805542 
Step 103 | loss:0.0009644604288041592 lr:7.316480175599309e-05 tokens_per_second_per_gpu:7079.005873332365 
Step 104 | loss:0.0014253875706344843 lr:7.254387703447154e-05 tokens_per_second_per_gpu:7110.536329650884 
Step 105 | loss:0.008904769085347652 lr:7.191855733945387e-05 tokens_per_second_per_gpu:7165.9044236089685 
Step 106 | loss:0.01313498429954052 lr:7.128896457825364e-05 tokens_per_second_per_gpu:7044.567480443534 
Step 107 | loss:0.009586299769580364 lr:7.06552214912271e-05 tokens_per_second_per_gpu:7065.759004065457 
Step 108 | loss:0.004150373861193657 lr:7.001745162784477e-05 tokens_per_second_per_gpu:7144.795253698613 
Step 109 | loss:0.0025894774589687586 lr:6.937577932260515e-05 tokens_per_second_per_gpu:7092.035088440755 
Step 110 | loss:0.009777382016181946 lr:6.873032967079561e-05 tokens_per_second_per_gpu:7093.150806060385 
Step 111 | loss:0.0069180880673229694 lr:6.808122850410461e-05 tokens_per_second_per_gpu:6953.824523940086 
Step 112 | loss:0.004603222478181124 lr:6.742860236609077e-05 tokens_per_second_per_gpu:7045.455581600914 
Step 113 | loss:0.0011307838140055537 lr:6.677257848751277e-05 tokens_per_second_per_gpu:7113.028856346813 
Step 114 | loss:0.00957533810287714 lr:6.611328476152557e-05 tokens_per_second_per_gpu:6866.532520421302 
Step 115 | loss:0.0010501754004508257 lr:6.545084971874738e-05 tokens_per_second_per_gpu:7045.1286895041985 
Step 116 | loss:0.0003030570223927498 lr:6.478540250220234e-05 tokens_per_second_per_gpu:6919.206378095726 
Step 117 | loss:0.012309281155467033 lr:6.411707284214384e-05 tokens_per_second_per_gpu:6959.89602153374 
Step 118 | loss:0.0011735755251720548 lr:6.344599103076329e-05 tokens_per_second_per_gpu:6998.818230826136 
Step 119 | loss:0.006594390608370304 lr:6.277228789678953e-05 tokens_per_second_per_gpu:7027.889308059036 
Step 120 | loss:0.004384372849017382 lr:6.209609477998338e-05 tokens_per_second_per_gpu:7043.651450873184 
Step 121 | loss:0.004672420211136341 lr:6.141754350553279e-05 tokens_per_second_per_gpu:7101.4110384159385 
Step 122 | loss:0.005256533622741699 lr:6.073676635835317e-05 tokens_per_second_per_gpu:7102.926567716092 
Step 123 | loss:0.006718686316162348 lr:6.005389605729824e-05 tokens_per_second_per_gpu:7031.4624230505915 
Step 124 | loss:0.007981338538229465 lr:5.9369065729286245e-05 tokens_per_second_per_gpu:7118.1753882686 
Step 125 | loss:0.004765128251165152 lr:5.868240888334653e-05 tokens_per_second_per_gpu:6946.728970297603 
Step 126 | loss:0.006511871702969074 lr:5.799405938459175e-05 tokens_per_second_per_gpu:7068.353681650787 
Step 127 | loss:0.006299371365457773 lr:5.730415142812059e-05 tokens_per_second_per_gpu:7125.328240536463 
Step 128 | loss:0.002500183880329132 lr:5.661281951285613e-05 tokens_per_second_per_gpu:6762.9994900944475 
Step 129 | loss:0.0003447072522249073 lr:5.5920198415325064e-05 tokens_per_second_per_gpu:7116.810989279679 
Step 130 | loss:0.0038090553134679794 lr:5.522642316338268e-05 tokens_per_second_per_gpu:7068.002336185429 
Step 131 | loss:0.0015808121534064412 lr:5.453162900988902e-05 tokens_per_second_per_gpu:7067.758646043467 
Step 132 | loss:0.005941121373325586 lr:5.383595140634093e-05 tokens_per_second_per_gpu:7091.837221774894 
Step 133 | loss:0.0010753199458122253 lr:5.313952597646568e-05 tokens_per_second_per_gpu:7068.938359991409 
Step 134 | loss:0.0007225701119750738 lr:5.244248848978067e-05 tokens_per_second_per_gpu:6743.037281274063 
Step 135 | loss:0.008606262505054474 lr:5.174497483512506e-05 tokens_per_second_per_gpu:7060.966363726559 
Step 136 | loss:0.004445431753993034 lr:5.104712099416785e-05 tokens_per_second_per_gpu:7051.867724934648 
Step 137 | loss:0.0019743351731449366 lr:5.034906301489808e-05 tokens_per_second_per_gpu:6682.908717884122 
Step 138 | loss:0.009234325028955936 lr:4.965093698510193e-05 tokens_per_second_per_gpu:7139.389343634964 
Step 139 | loss:0.005030487664043903 lr:4.895287900583216e-05 tokens_per_second_per_gpu:7080.114364087144 
Step 140 | loss:0.0006191696156747639 lr:4.825502516487497e-05 tokens_per_second_per_gpu:6177.17880138713 
Step 141 | loss:0.003408745164051652 lr:4.755751151021934e-05 tokens_per_second_per_gpu:6959.878964928582 
Step 142 | loss:0.0030980852898210287 lr:4.6860474023534335e-05 tokens_per_second_per_gpu:7048.244691756786 
Step 143 | loss:0.0019596803467720747 lr:4.616404859365907e-05 tokens_per_second_per_gpu:6965.323695321251 
Step 144 | loss:0.009168603457510471 lr:4.5468370990111006e-05 tokens_per_second_per_gpu:6709.272693327204 
Step 145 | loss:0.00331300450488925 lr:4.477357683661734e-05 tokens_per_second_per_gpu:7122.655300155168 
Step 146 | loss:0.0020876226481050253 lr:4.407980158467495e-05 tokens_per_second_per_gpu:7059.668810962822 
Step 147 | loss:0.0013308243360370398 lr:4.3387180487143876e-05 tokens_per_second_per_gpu:6982.222854743132 
Step 148 | loss:0.0034321194980293512 lr:4.269584857187943e-05 tokens_per_second_per_gpu:6684.743597530625 
Step 149 | loss:0.0019766073673963547 lr:4.2005940615408264e-05 tokens_per_second_per_gpu:7067.469060841531 
Step 150 | loss:0.0008945669396780431 lr:4.131759111665349e-05 tokens_per_second_per_gpu:7066.655473123749 
Step 151 | loss:0.0008740133489482105 lr:4.063093427071376e-05 tokens_per_second_per_gpu:7175.781860123878 
Step 152 | loss:0.0032591235358268023 lr:3.9946103942701777e-05 tokens_per_second_per_gpu:7008.007102721075 
Step 153 | loss:0.0033099993597716093 lr:3.926323364164684e-05 tokens_per_second_per_gpu:7084.441039783992 
Step 154 | loss:0.0014826861442998052 lr:3.858245649446721e-05 tokens_per_second_per_gpu:6662.47060324718 
Step 155 | loss:0.0008808820857666433 lr:3.790390522001662e-05 tokens_per_second_per_gpu:7067.196327829486 
Step 156 | loss:0.0009888733038678765 lr:3.7227712103210486e-05 tokens_per_second_per_gpu:6989.206805860369 
Step 157 | loss:0.0038229695055633783 lr:3.655400896923672e-05 tokens_per_second_per_gpu:6902.019722464749 
Step 158 | loss:7.960521907079965e-05 lr:3.588292715785617e-05 tokens_per_second_per_gpu:6887.668597374931 
Step 159 | loss:0.0016212619375437498 lr:3.5214597497797684e-05 tokens_per_second_per_gpu:6971.546283451361 
Step 160 | loss:9.730933379614726e-05 lr:3.4549150281252636e-05 tokens_per_second_per_gpu:7001.316944454005 
Step 161 | loss:0.0019280611304566264 lr:3.388671523847445e-05 tokens_per_second_per_gpu:7058.511728463046 
Step 162 | loss:0.0032107133883982897 lr:3.322742151248725e-05 tokens_per_second_per_gpu:7074.473400661386 
Step 163 | loss:0.0020377160981297493 lr:3.257139763390925e-05 tokens_per_second_per_gpu:7079.718647038059 
Step 164 | loss:0.0058026742190122604 lr:3.1918771495895396e-05 tokens_per_second_per_gpu:6904.0378816734565 
Step 165 | loss:0.0010289129568263888 lr:3.12696703292044e-05 tokens_per_second_per_gpu:7115.230322496159 
Step 166 | loss:0.0020757780876010656 lr:3.062422067739485e-05 tokens_per_second_per_gpu:7143.786317408253 
Step 167 | loss:0.005250038579106331 lr:2.9982548372155263e-05 tokens_per_second_per_gpu:6904.71251059718 
Step 168 | loss:0.0008269779500551522 lr:2.934477850877292e-05 tokens_per_second_per_gpu:7127.128386332989 
Step 169 | loss:0.007161479443311691 lr:2.8711035421746367e-05 tokens_per_second_per_gpu:6973.786818409613 
Step 170 | loss:0.0016270504565909505 lr:2.8081442660546125e-05 tokens_per_second_per_gpu:6944.131316659634 
Step 171 | loss:0.0005630644736811519 lr:2.7456122965528475e-05 tokens_per_second_per_gpu:6968.731351596765 
Step 172 | loss:0.000764863274525851 lr:2.6835198244006927e-05 tokens_per_second_per_gpu:6751.367808378523 
Step 173 | loss:0.005358004476875067 lr:2.6218789546486234e-05 tokens_per_second_per_gpu:7121.830729623779 
Step 174 | loss:4.0301574699697085e-06 lr:2.560701704306336e-05 tokens_per_second_per_gpu:6938.362346146086 
Step 175 | loss:0.0015505176270380616 lr:2.500000000000001e-05 tokens_per_second_per_gpu:6982.030611321107 
Step 176 | loss:0.004141073673963547 lr:2.4397856756471432e-05 tokens_per_second_per_gpu:7141.479902718891 
Step 177 | loss:0.006702089682221413 lr:2.3800704701496053e-05 tokens_per_second_per_gpu:7087.489435882164 
Step 178 | loss:0.004516590852290392 lr:2.3208660251050158e-05 tokens_per_second_per_gpu:7110.237668215957 
Step 179 | loss:0.0002626439672894776 lr:2.2621838825372493e-05 tokens_per_second_per_gpu:7056.144125914929 
Step 180 | loss:0.002430600579828024 lr:2.2040354826462668e-05 tokens_per_second_per_gpu:6759.34132815909 
Step 181 | loss:4.081410588696599e-05 lr:2.1464321615778422e-05 tokens_per_second_per_gpu:7053.257854517555 
Step 182 | loss:0.00031062396010383964 lr:2.0893851492135537e-05 tokens_per_second_per_gpu:6915.0048024862435 
Step 183 | loss:1.496891854912974e-05 lr:2.0329055669814934e-05 tokens_per_second_per_gpu:7029.941830363428 
Step 184 | loss:0.0008824768592603505 lr:1.977004425688126e-05 tokens_per_second_per_gpu:7049.465102859838 
Step 185 | loss:0.0025399732403457165 lr:1.9216926233717085e-05 tokens_per_second_per_gpu:7065.522537463739 
Step 186 | loss:0.0011831234442070127 lr:1.866980943177699e-05 tokens_per_second_per_gpu:7057.038829715127 
Step 187 | loss:8.935239748097956e-05 lr:1.8128800512565513e-05 tokens_per_second_per_gpu:7045.273026663626 
Step 188 | loss:0.00030020231497474015 lr:1.7594004946843456e-05 tokens_per_second_per_gpu:7101.548701998664 
Step 189 | loss:0.002447166247293353 lr:1.7065526994065973e-05 tokens_per_second_per_gpu:7132.322499430969 
Step 190 | loss:0.00178128806874156 lr:1.6543469682057106e-05 tokens_per_second_per_gpu:7079.7816493973 
Step 191 | loss:0.0005427153082564473 lr:1.602793478692419e-05 tokens_per_second_per_gpu:7049.6550887142785 
Step 192 | loss:0.0004498407943174243 lr:1.551902281321651e-05 tokens_per_second_per_gpu:7151.590671504066 
Step 193 | loss:0.0021533083636313677 lr:1.5016832974331724e-05 tokens_per_second_per_gpu:7073.773690899949 
Step 194 | loss:4.6476934585371055e-06 lr:1.4521463173173965e-05 tokens_per_second_per_gpu:6513.352836122793 
Step 195 | loss:0.0017906646244227886 lr:1.4033009983067452e-05 tokens_per_second_per_gpu:7078.314068986232 
Step 196 | loss:0.00018793635535985231 lr:1.3551568628929434e-05 tokens_per_second_per_gpu:7114.828339260472 
Step 197 | loss:0.0031530391424894333 lr:1.3077232968705805e-05 tokens_per_second_per_gpu:7111.472157868944 
Step 198 | loss:0.00028054098947905004 lr:1.2610095475073414e-05 tokens_per_second_per_gpu:6189.90796946071 
Step 199 | loss:0.0005241130711510777 lr:1.2150247217412186e-05 tokens_per_second_per_gpu:7043.012850462871 
Step 200 | loss:0.004094945732504129 lr:1.1697777844051105e-05 tokens_per_second_per_gpu:7028.667699320902 
Step 201 | loss:0.002229253528639674 lr:1.1252775564791024e-05 tokens_per_second_per_gpu:7107.463195987544 
Step 202 | loss:0.00019255683582741767 lr:1.0815327133708015e-05 tokens_per_second_per_gpu:7068.113178903538 
Step 203 | loss:6.1030459619360045e-06 lr:1.0385517832240471e-05 tokens_per_second_per_gpu:6902.548601670786 
Step 204 | loss:5.9569669247139245e-05 lr:9.963431452563332e-06 tokens_per_second_per_gpu:7057.201818382818 
Step 205 | loss:0.005544851999729872 lr:9.549150281252633e-06 tokens_per_second_per_gpu:7088.885520114002 
Step 206 | loss:0.0030818574596196413 lr:9.142755083243576e-06 tokens_per_second_per_gpu:7127.871132256084 
Step 207 | loss:0.00011336655006743968 lr:8.744325086085248e-06 tokens_per_second_per_gpu:6866.277677188948 
Step 208 | loss:0.00016025043441914022 lr:8.353937964495029e-06 tokens_per_second_per_gpu:7129.579521478313 
Step 209 | loss:1.730686199152842e-05 lr:7.971669825215788e-06 tokens_per_second_per_gpu:7113.120857257116 
Step 210 | loss:0.00028120417846366763 lr:7.597595192178702e-06 tokens_per_second_per_gpu:7073.1185268988165 
Step 211 | loss:0.002427683211863041 lr:7.2317869919746705e-06 tokens_per_second_per_gpu:7114.428420333685 
Step 212 | loss:0.0007908017141744494 lr:6.874316539637127e-06 tokens_per_second_per_gpu:7088.792782859684 
Step 213 | loss:0.00452659884467721 lr:6.52525352473905e-06 tokens_per_second_per_gpu:6896.324693599925 
Step 214 | loss:0.0025756561663001776 lr:6.184665997806832e-06 tokens_per_second_per_gpu:7069.378359232183 
Step 215 | loss:0.00045055814553052187 lr:5.852620357053651e-06 tokens_per_second_per_gpu:7099.053127386129 
Step 216 | loss:0.004190291278064251 lr:5.529181335435124e-06 tokens_per_second_per_gpu:6755.487017523827 
Step 217 | loss:0.002386178122833371 lr:5.214411988029355e-06 tokens_per_second_per_gpu:7142.102004793783 
Step 218 | loss:0.00011885088315466419 lr:4.908373679744316e-06 tokens_per_second_per_gpu:6976.9724357603955 
Step 219 | loss:0.000391733949072659 lr:4.611126073354571e-06 tokens_per_second_per_gpu:7070.465521832886 
Step 220 | loss:2.282398236275185e-05 lr:4.322727117869951e-06 tokens_per_second_per_gpu:7067.273556888841 
Step 221 | loss:0.00013819478044752032 lr:4.043233037238281e-06 tokens_per_second_per_gpu:7124.199888989333 
Step 222 | loss:6.782953278161585e-05 lr:3.772698319384349e-06 tokens_per_second_per_gpu:7049.3117894643665 
Step 223 | loss:0.000757302506826818 lr:3.511175705587433e-06 tokens_per_second_per_gpu:7097.271216873272 
Step 224 | loss:0.0013424844946712255 lr:3.258716180199278e-06 tokens_per_second_per_gpu:7039.021132485852 
Step 225 | loss:0.00032940192613750696 lr:3.0153689607045845e-06 tokens_per_second_per_gpu:7037.537330538644 
Step 226 | loss:0.0014422229724004865 lr:2.7811814881259503e-06 tokens_per_second_per_gpu:7091.09106833669 
Step 227 | loss:0.0010956695768982172 lr:2.5561994177751737e-06 tokens_per_second_per_gpu:6604.557403083021 
Step 228 | loss:0.0011385928373783827 lr:2.340466610352654e-06 tokens_per_second_per_gpu:6979.094215726923 
Step 229 | loss:0.0018219526391476393 lr:2.134025123396638e-06 tokens_per_second_per_gpu:6895.723399935125 
Step 230 | loss:0.008147644810378551 lr:1.9369152030840556e-06 tokens_per_second_per_gpu:6753.505543554295 
Step 231 | loss:0.0006599955377168953 lr:1.7491752763844293e-06 tokens_per_second_per_gpu:7076.2268471422185 
Step 232 | loss:0.0014754146104678512 lr:1.5708419435684462e-06 tokens_per_second_per_gpu:6802.986797947515 
Step 233 | loss:0.0003230568836443126 lr:1.4019499710726913e-06 tokens_per_second_per_gpu:6944.848647833805 
Step 234 | loss:0.0002109357010340318 lr:1.2425322847218368e-06 tokens_per_second_per_gpu:7087.99972871592 
Step 235 | loss:0.0013953811721876264 lr:1.0926199633097157e-06 tokens_per_second_per_gpu:7110.8439529001935 
Step 236 | loss:4.525236727204174e-05 lr:9.522422325404235e-07 tokens_per_second_per_gpu:7099.461659197926 
Step 237 | loss:0.0006170326378196478 lr:8.214264593307098e-07 tokens_per_second_per_gpu:7072.285288625411 
Step 238 | loss:0.0010877117747440934 lr:7.001981464747565e-07 tokens_per_second_per_gpu:7062.581629530725 
Step 239 | loss:0.000273244600975886 lr:5.885809276723608e-07 tokens_per_second_per_gpu:6751.770199818327 
Step 240 | loss:0.0007284900639206171 lr:4.865965629214819e-07 tokens_per_second_per_gpu:7044.183969309484 
Step 241 | loss:4.254740633768961e-05 lr:3.9426493427611177e-07 tokens_per_second_per_gpu:7088.501677999479 
Step 242 | loss:0.0011083302088081837 lr:3.1160404197018154e-07 tokens_per_second_per_gpu:6983.718705962598 
Step 243 | loss:0.00521168252453208 lr:2.386300009084408e-07 tokens_per_second_per_gpu:7067.875052697799 
Step 244 | loss:0.0009710222948342562 lr:1.753570375247815e-07 tokens_per_second_per_gpu:6997.507768003162 
Step 245 | loss:0.0012455569813027978 lr:1.2179748700879012e-07 tokens_per_second_per_gpu:7113.441984033089 
Step 246 | loss:0.0002956873213406652 lr:7.796179090094891e-08 tokens_per_second_per_gpu:7098.860712192067 
Step 247 | loss:0.0043370844796299934 lr:4.385849505708084e-08 tokens_per_second_per_gpu:7060.336069246184 
Step 248 | loss:0.0003348605241626501 lr:1.949424798228239e-08 tokens_per_second_per_gpu:7053.891355799027 
Step 249 | loss:7.63071802794002e-05 lr:4.873799534788059e-09 tokens_per_second_per_gpu:6912.572067251458 
Step 250 | loss:0.00046650483272969723 lr:0.0 tokens_per_second_per_gpu:7091.354368744028