Step 1 | loss:0.016397161409258842 lr:7.142857142857143e-06 tokens_per_second_per_gpu:3306.1997536767876 Step 2 | loss:0.03742658346891403 lr:1.4285714285714285e-05 tokens_per_second_per_gpu:7062.19779693317 Step 3 | loss:0.022238673642277718 lr:2.1428571428571428e-05 tokens_per_second_per_gpu:7140.746015335055 Step 4 | loss:0.027638735249638557 lr:2.857142857142857e-05 tokens_per_second_per_gpu:2684.812823776721 Step 5 | loss:0.058235324919223785 lr:3.571428571428572e-05 tokens_per_second_per_gpu:2568.9568262633743 Step 6 | loss:0.024167785421013832 lr:4.2857142857142856e-05 tokens_per_second_per_gpu:2551.201138192373 Step 7 | loss:0.013970529660582542 lr:5e-05 tokens_per_second_per_gpu:7143.620691270135 Step 8 | loss:0.04369419813156128 lr:5.714285714285714e-05 tokens_per_second_per_gpu:2645.6852563203383 Step 9 | loss:0.019096726551651955 lr:6.428571428571429e-05 tokens_per_second_per_gpu:7123.891370692307 Step 10 | loss:0.018623316660523415 lr:7.142857142857143e-05 tokens_per_second_per_gpu:6984.6280518821495 Step 11 | loss:0.008832694962620735 lr:7.857142857142858e-05 tokens_per_second_per_gpu:6979.76761769708 Step 12 | loss:0.009800988249480724 lr:8.571428571428571e-05 tokens_per_second_per_gpu:6957.947040492509 Step 13 | loss:0.007687712553888559 lr:9.285714285714286e-05 tokens_per_second_per_gpu:6984.0270572755035 Step 14 | loss:0.033459775149822235 lr:0.0001 tokens_per_second_per_gpu:7014.791403920163 Step 15 | loss:0.003528009168803692 lr:9.998540070400966e-05 tokens_per_second_per_gpu:6937.203959387754 Step 16 | loss:0.003845039987936616 lr:9.994161134161634e-05 tokens_per_second_per_gpu:6982.2027738669 Step 17 | loss:0.02608061023056507 lr:9.986865748457457e-05 tokens_per_second_per_gpu:6920.612567892091 Step 18 | loss:0.006232541054487228 lr:9.976658173588244e-05 tokens_per_second_per_gpu:7078.1475256570775 Step 19 | loss:0.006578405853360891 lr:9.96354437049027e-05 tokens_per_second_per_gpu:7085.295846317261 Step 20 | loss:0.00022706191521137953 lr:9.947531997255256e-05 tokens_per_second_per_gpu:6959.381407040068 Step 21 | loss:0.00023938719823490828 lr:9.928630404658255e-05 tokens_per_second_per_gpu:6971.344500658577 Step 22 | loss:0.001606603036634624 lr:9.906850630697068e-05 tokens_per_second_per_gpu:6980.482352366198 Step 23 | loss:0.001169066410511732 lr:9.882205394146361e-05 tokens_per_second_per_gpu:7016.986949038028 Step 24 | loss:0.0004242211580276489 lr:9.85470908713026e-05 tokens_per_second_per_gpu:6951.187196216129 Step 25 | loss:0.014282144606113434 lr:9.824377766717759e-05 tokens_per_second_per_gpu:7091.857156718297 Step 26 | loss:0.00679903756827116 lr:9.791229145545831e-05 tokens_per_second_per_gpu:7101.191357385334 Step 27 | loss:0.017791584134101868 lr:9.755282581475769e-05 tokens_per_second_per_gpu:6425.984704590751 Step 28 | loss:0.00011745126539608464 lr:9.716559066288715e-05 tokens_per_second_per_gpu:6891.039867271743 Step 29 | loss:0.0007341586169786751 lr:9.675081213427076e-05 tokens_per_second_per_gpu:6973.205690319995 Step 30 | loss:0.0036232005804777145 lr:9.630873244788883e-05 tokens_per_second_per_gpu:6977.096249693659 Step 31 | loss:0.012285743840038776 lr:9.583960976582913e-05 tokens_per_second_per_gpu:6960.107163240302 Step 32 | loss:5.590498767560348e-05 lr:9.534371804252728e-05 tokens_per_second_per_gpu:6936.521808573649 Step 33 | loss:0.0005110141355544329 lr:9.482134686478519e-05 tokens_per_second_per_gpu:7117.425782107312 Step 34 | loss:0.016854679211974144 lr:9.42728012826605e-05 tokens_per_second_per_gpu:6950.48990693112 Step 35 | loss:0.002051198622211814 lr:9.36984016313259e-05 tokens_per_second_per_gpu:6942.153408173635 Step 36 | loss:0.000642083992715925 lr:9.309848334400246e-05 tokens_per_second_per_gpu:7095.019705428279 Step 37 | loss:0.0006663668318651617 lr:9.247339675607605e-05 tokens_per_second_per_gpu:7011.89775903554 Step 38 | loss:0.007946617901325226 lr:9.182350690051133e-05 tokens_per_second_per_gpu:6898.5457422087065 Step 39 | loss:0.0001719836873235181 lr:9.114919329468282e-05 tokens_per_second_per_gpu:6991.795596901835 Step 40 | loss:8.117085235426202e-05 lr:9.045084971874738e-05 tokens_per_second_per_gpu:7087.086937025432 Step 41 | loss:0.0014969357289373875 lr:8.972888398568772e-05 tokens_per_second_per_gpu:6925.683524542703 Step 42 | loss:0.0029777847230434418 lr:8.898371770316111e-05 tokens_per_second_per_gpu:7076.295671436614 Step 43 | loss:0.013367896899580956 lr:8.821578602729242e-05 tokens_per_second_per_gpu:7036.867326082149 Step 44 | loss:7.151573663577437e-05 lr:8.742553740855506e-05 tokens_per_second_per_gpu:6994.84196544083 Step 45 | loss:0.0004115064803045243 lr:8.661343332988869e-05 tokens_per_second_per_gpu:6995.895172179661 Step 46 | loss:0.0003813663497567177 lr:8.577994803720606e-05 tokens_per_second_per_gpu:6963.017711088038 Step 47 | loss:0.0002045320434262976 lr:8.492556826244687e-05 tokens_per_second_per_gpu:2478.67199591773 Step 48 | loss:0.009046241641044617 lr:8.405079293933986e-05 tokens_per_second_per_gpu:6965.9047836446 Step 49 | loss:0.002227130811661482 lr:8.315613291203976e-05 tokens_per_second_per_gpu:6973.049480551411 Step 50 | loss:0.00014541299606207758 lr:8.224211063680853e-05 tokens_per_second_per_gpu:7041.276546282364 Step 51 | loss:0.01105420757085085 lr:8.130925987691569e-05 tokens_per_second_per_gpu:6957.613284526947 Step 52 | loss:0.006284783594310284 lr:8.035812539093557e-05 tokens_per_second_per_gpu:7021.436506719234 Step 53 | loss:4.5882301492383704e-05 lr:7.938926261462366e-05 tokens_per_second_per_gpu:6906.783630357554 Step 54 | loss:0.00036842076224274933 lr:7.840323733655778e-05 tokens_per_second_per_gpu:7095.980306492073 Step 55 | loss:0.0001270872598979622 lr:7.740062536773352e-05 tokens_per_second_per_gpu:7003.3383921803415 Step 56 | loss:0.00014381104847416282 lr:7.638201220530665e-05 tokens_per_second_per_gpu:6044.233734683347 Step 57 | loss:0.005274840164929628 lr:7.534799269067953e-05 tokens_per_second_per_gpu:6950.851011351618 Step 58 | loss:5.681148832081817e-05 lr:7.42991706621303e-05 tokens_per_second_per_gpu:7035.497053867417 Step 59 | loss:6.911497621331364e-05 lr:7.323615860218843e-05 tokens_per_second_per_gpu:7113.884518000181 Step 60 | loss:2.6198255000053905e-05 lr:7.215957727996207e-05 tokens_per_second_per_gpu:6879.370313638725 Step 61 | loss:0.00015070693916641176 lr:7.107005538862646e-05 tokens_per_second_per_gpu:7103.8580625828345 Step 62 | loss:0.01125973928719759 lr:6.996822917828477e-05 tokens_per_second_per_gpu:7095.491308072574 Step 63 | loss:0.007858753204345703 lr:6.885474208441603e-05 tokens_per_second_per_gpu:6989.252988570978 Step 64 | loss:0.000505140982568264 lr:6.773024435212678e-05 tokens_per_second_per_gpu:7105.115889066369 Step 65 | loss:6.4155888139794115e-06 lr:6.659539265642643e-05 tokens_per_second_per_gpu:6962.443406365357 Step 66 | loss:1.3621217476611491e-05 lr:6.545084971874738e-05 tokens_per_second_per_gpu:7097.328465018962 Step 67 | loss:0.0022206397261470556 lr:6.429728391993446e-05 tokens_per_second_per_gpu:7003.442742070719 Step 68 | loss:5.029049498261884e-05 lr:6.313536890992935e-05 tokens_per_second_per_gpu:7088.189675959633 Step 69 | loss:0.0003365690936334431 lr:6.19657832143779e-05 tokens_per_second_per_gpu:6983.942182196126 Step 70 | loss:7.271781214512885e-05 lr:6.078920983839031e-05 tokens_per_second_per_gpu:7142.871361089922 Step 71 | loss:8.283425268018618e-05 lr:5.960633586768543e-05 tokens_per_second_per_gpu:7005.234325960676 Step 72 | loss:3.1005798518890515e-05 lr:5.841785206735192e-05 tokens_per_second_per_gpu:7156.012246041024 Step 73 | loss:3.0176004202076e-06 lr:5.7224452478461064e-05 tokens_per_second_per_gpu:6998.183393768826 Step 74 | loss:1.3262722859508358e-05 lr:5.602683401276615e-05 tokens_per_second_per_gpu:6968.999223233301 Step 75 | loss:5.582269295700826e-06 lr:5.482569604572576e-05 tokens_per_second_per_gpu:7021.95424136323 Step 76 | loss:4.424786675372161e-05 lr:5.3621740008088126e-05 tokens_per_second_per_gpu:7089.600565422166 Step 77 | loss:0.0009114808053709567 lr:5.2415668976275355e-05 tokens_per_second_per_gpu:7096.835923374081 Step 78 | loss:2.8360396754578687e-05 lr:5.1208187261806615e-05 tokens_per_second_per_gpu:7086.1552287995155 Step 79 | loss:6.1444370658136904e-06 lr:5e-05 tokens_per_second_per_gpu:7126.369194583206 Step 80 | loss:0.0019692040514200926 lr:4.87918127381934e-05 tokens_per_second_per_gpu:7026.4061426743265 Step 81 | loss:0.002585497684776783 lr:4.758433102372466e-05 tokens_per_second_per_gpu:7109.172357608716 Step 82 | loss:1.7788398736229283e-06 lr:4.6378259991911886e-05 tokens_per_second_per_gpu:6929.278707033571 Step 83 | loss:2.5151928184641292e-06 lr:4.5174303954274244e-05 tokens_per_second_per_gpu:5937.026864668412 Step 84 | loss:1.8295755580766127e-05 lr:4.397316598723385e-05 tokens_per_second_per_gpu:6970.797413838669 Step 85 | loss:0.003329699393361807 lr:4.277554752153895e-05 tokens_per_second_per_gpu:7051.750274158542 Step 86 | loss:1.3597697943623643e-05 lr:4.1582147932648074e-05 tokens_per_second_per_gpu:7028.710651823076 Step 87 | loss:4.406199150253087e-05 lr:4.039366413231458e-05 tokens_per_second_per_gpu:6898.993508061195 Step 88 | loss:4.540777354122838e-06 lr:3.92107901616097e-05 tokens_per_second_per_gpu:7083.998762004015 Step 89 | loss:3.9542524064017925e-06 lr:3.803421678562213e-05 tokens_per_second_per_gpu:6939.512985181514 Step 90 | loss:0.000938387936912477 lr:3.6864631090070655e-05 tokens_per_second_per_gpu:6939.644286642485 Step 91 | loss:9.617162504582666e-06 lr:3.570271608006555e-05 tokens_per_second_per_gpu:6945.365068400767 Step 92 | loss:6.362492058542557e-06 lr:3.4549150281252636e-05 tokens_per_second_per_gpu:7123.88203572789 Step 93 | loss:2.3637352569494396e-05 lr:3.340460734357359e-05 tokens_per_second_per_gpu:6968.307103909072 Step 94 | loss:0.00017570874479133636 lr:3.226975564787322e-05 tokens_per_second_per_gpu:6966.350255169864 Step 95 | loss:0.0005778181948699057 lr:3.114525791558398e-05 tokens_per_second_per_gpu:7054.413300589564 Step 96 | loss:3.5754917462327285e-06 lr:3.003177082171523e-05 tokens_per_second_per_gpu:6967.898086188647 Step 97 | loss:2.407625743217068e-06 lr:2.8929944611373554e-05 tokens_per_second_per_gpu:6937.750773019949 Step 98 | loss:0.0009274276089854538 lr:2.784042272003794e-05 tokens_per_second_per_gpu:7065.157898252117 Step 99 | loss:1.2426003195287194e-06 lr:2.6763841397811573e-05 tokens_per_second_per_gpu:6931.292171563914 Step 100 | loss:2.4075849069049582e-05 lr:2.57008293378697e-05 tokens_per_second_per_gpu:7053.156820582436 Step 101 | loss:5.903457804379286e-06 lr:2.4652007309320498e-05 tokens_per_second_per_gpu:7019.592758254624 Step 102 | loss:7.690755410294514e-06 lr:2.361798779469336e-05 tokens_per_second_per_gpu:6953.825437634371 Step 103 | loss:9.90509079201729e-07 lr:2.259937463226651e-05 tokens_per_second_per_gpu:6944.09213337864 Step 104 | loss:1.6671621096975286e-06 lr:2.1596762663442218e-05 tokens_per_second_per_gpu:6918.677627745505 Step 105 | loss:0.0020772404968738556 lr:2.061073738537635e-05 tokens_per_second_per_gpu:7040.527108571102 Step 106 | loss:6.554265837621642e-06 lr:1.9641874609064443e-05 tokens_per_second_per_gpu:7103.269604760098 Step 107 | loss:3.1814004614716396e-05 lr:1.8690740123084316e-05 tokens_per_second_per_gpu:7019.241174905156 Step 108 | loss:1.132090255850926e-05 lr:1.7757889363191483e-05 tokens_per_second_per_gpu:7008.670338315658 Step 109 | loss:0.0008296921150758862 lr:1.684386708796025e-05 tokens_per_second_per_gpu:7004.1742957507495 Step 110 | loss:3.3144181088573532e-06 lr:1.5949207060660138e-05 tokens_per_second_per_gpu:6995.3825385647715 Step 111 | loss:1.047514615493128e-05 lr:1.5074431737553157e-05 tokens_per_second_per_gpu:6035.782369457874 Step 112 | loss:9.742560905579012e-06 lr:1.422005196279395e-05 tokens_per_second_per_gpu:7095.667767005955 Step 113 | loss:1.152164031736902e-06 lr:1.338656667011134e-05 tokens_per_second_per_gpu:6983.1914040621605 Step 114 | loss:5.981667982268846e-06 lr:1.257446259144494e-05 tokens_per_second_per_gpu:6986.800570169732 Step 115 | loss:1.1920205906790216e-05 lr:1.178421397270758e-05 tokens_per_second_per_gpu:7162.559365300599 Step 116 | loss:1.2543061529868282e-05 lr:1.1016282296838887e-05 tokens_per_second_per_gpu:6965.258435399587 Step 117 | loss:1.1269878996245097e-05 lr:1.0271116014312293e-05 tokens_per_second_per_gpu:7165.862396198681 Step 118 | loss:7.680927410547156e-06 lr:9.549150281252633e-06 tokens_per_second_per_gpu:7121.76890668545 Step 119 | loss:3.3339672427246114e-06 lr:8.850806705317183e-06 tokens_per_second_per_gpu:7059.042553467796 Step 120 | loss:1.3305968423082959e-05 lr:8.176493099488663e-06 tokens_per_second_per_gpu:7020.315293062309 Step 121 | loss:0.0003516983997542411 lr:7.526603243923957e-06 tokens_per_second_per_gpu:7137.045674180836 Step 122 | loss:4.048734808748122e-06 lr:6.901516655997536e-06 tokens_per_second_per_gpu:7110.036032049479 Step 123 | loss:7.515820016124053e-06 lr:6.301598368674105e-06 tokens_per_second_per_gpu:7094.092494727734 Step 124 | loss:3.946192464354681e-06 lr:5.727198717339511e-06 tokens_per_second_per_gpu:7067.528935401275 Step 125 | loss:0.00047290927614085376 lr:5.178653135214812e-06 tokens_per_second_per_gpu:6966.355621648842 Step 126 | loss:5.803041403851239e-06 lr:4.65628195747273e-06 tokens_per_second_per_gpu:7117.863728891831 Step 127 | loss:5.158909516467247e-06 lr:4.16039023417088e-06 tokens_per_second_per_gpu:6929.668068180212 Step 128 | loss:4.4963906020711875e-07 lr:3.691267552111183e-06 tokens_per_second_per_gpu:6976.329594904463 Step 129 | loss:4.627099770004861e-06 lr:3.249187865729264e-06 tokens_per_second_per_gpu:7074.737259949742 Step 130 | loss:0.0003387303149793297 lr:2.8344093371128424e-06 tokens_per_second_per_gpu:7102.4063803253175 Step 131 | loss:0.002187069272622466 lr:2.4471741852423237e-06 tokens_per_second_per_gpu:6918.268171741537 Step 132 | loss:1.4217651369108353e-05 lr:2.087708544541689e-06 tokens_per_second_per_gpu:6938.249084897394 Step 133 | loss:0.0022914146538823843 lr:1.7562223328224325e-06 tokens_per_second_per_gpu:6928.297145598233 Step 134 | loss:5.813252300868044e-06 lr:1.4529091286973995e-06 tokens_per_second_per_gpu:7101.972516911091 Step 135 | loss:7.496130820072722e-06 lr:1.1779460585363944e-06 tokens_per_second_per_gpu:7010.62090838566 Step 136 | loss:0.0011146125616505742 lr:9.314936930293283e-07 tokens_per_second_per_gpu:7143.689144652495 Step 137 | loss:4.729995907837292e-06 lr:7.136959534174592e-07 tokens_per_second_per_gpu:7124.514264620032 Step 138 | loss:1.971294977920479e-06 lr:5.246800274474439e-07 tokens_per_second_per_gpu:6944.31167447411 Step 139 | loss:1.4823802302998956e-05 lr:3.6455629509730136e-07 tokens_per_second_per_gpu:6916.382939156954 Step 140 | loss:0.0009491464006714523 lr:2.334182641175686e-07 tokens_per_second_per_gpu:5660.3778382541195 Step 141 | loss:1.1483265552669764e-05 lr:1.3134251542544774e-07 tokens_per_second_per_gpu:7136.094967423619 Step 142 | loss:0.0006993878050707281 lr:5.838865838366792e-08 tokens_per_second_per_gpu:6972.272301564398 Step 143 | loss:5.160792170499917e-06 lr:1.4599295990352924e-08 tokens_per_second_per_gpu:6941.524273848123 Step 144 | loss:1.98136535800586e-06 lr:0.0 tokens_per_second_per_gpu:6892.504281533115