Step 1 | loss:0.05147874355316162 lr:4.000000000000001e-06 tokens_per_second_per_gpu:2209.7250181716795 Step 2 | loss:0.043523360043764114 lr:8.000000000000001e-06 tokens_per_second_per_gpu:7127.020013387663 Step 3 | loss:0.036781810224056244 lr:1.2e-05 tokens_per_second_per_gpu:2175.7971487246537 Step 4 | loss:0.03892979770898819 lr:1.6000000000000003e-05 tokens_per_second_per_gpu:6950.021403874265 Step 5 | loss:0.11738340556621552 lr:2e-05 tokens_per_second_per_gpu:810.3742368360905 Step 6 | loss:0.06756217032670975 lr:2.4e-05 tokens_per_second_per_gpu:1308.4563208582395 Step 7 | loss:0.04701422154903412 lr:2.8000000000000003e-05 tokens_per_second_per_gpu:6945.189935802292 Step 8 | loss:0.04512825235724449 lr:3.2000000000000005e-05 tokens_per_second_per_gpu:7052.137167143608 Step 9 | loss:0.0395982563495636 lr:3.6e-05 tokens_per_second_per_gpu:6906.627032888982 Step 10 | loss:0.08577527105808258 lr:4e-05 tokens_per_second_per_gpu:6755.834162873462 Step 11 | loss:0.12639638781547546 lr:4.4000000000000006e-05 tokens_per_second_per_gpu:581.5025596969126 Step 12 | loss:0.037665992975234985 lr:4.8e-05 tokens_per_second_per_gpu:7105.388134962218 Step 13 | loss:0.0333024337887764 lr:5.2000000000000004e-05 tokens_per_second_per_gpu:7027.2359526335795 Step 14 | loss:0.04286828264594078 lr:5.6000000000000006e-05 tokens_per_second_per_gpu:6973.333399999541 Step 15 | loss:0.05092582106590271 lr:6e-05 tokens_per_second_per_gpu:1327.164789106125 Step 16 | loss:0.08894742280244827 lr:6.400000000000001e-05 tokens_per_second_per_gpu:746.8152528168472 Step 17 | loss:0.06243601813912392 lr:6.800000000000001e-05 tokens_per_second_per_gpu:1044.0996536149723 Step 18 | loss:0.06930171698331833 lr:7.2e-05 tokens_per_second_per_gpu:6502.8282894997665 Step 19 | loss:0.06304563581943512 lr:7.6e-05 tokens_per_second_per_gpu:1017.1599706278467 Step 20 | loss:0.046461645513772964 lr:8e-05 tokens_per_second_per_gpu:6715.843171596227 Step 21 | loss:0.03484892100095749 lr:8.4e-05 tokens_per_second_per_gpu:1790.416064877827 Step 22 | loss:0.03316212445497513 lr:8.800000000000001e-05 tokens_per_second_per_gpu:7013.220936746286 Step 23 | loss:0.055547792464494705 lr:9.200000000000001e-05 tokens_per_second_per_gpu:5503.379742348575 Step 24 | loss:0.09070231020450592 lr:9.6e-05 tokens_per_second_per_gpu:5534.810912032588 Step 25 | loss:0.05724829435348511 lr:0.0001 tokens_per_second_per_gpu:6433.610047147281 Step 26 | loss:0.023668743669986725 lr:9.999512620046522e-05 tokens_per_second_per_gpu:6749.19630467374 Step 27 | loss:0.017250103875994682 lr:9.998050575201771e-05 tokens_per_second_per_gpu:5802.018420537243 Step 28 | loss:0.05390876904129982 lr:9.995614150494293e-05 tokens_per_second_per_gpu:5301.725743375331 Step 29 | loss:0.011932523921132088 lr:9.992203820909906e-05 tokens_per_second_per_gpu:2847.0288571909223 Step 30 | loss:0.017412487417459488 lr:9.987820251299122e-05 tokens_per_second_per_gpu:6745.805633930024 Step 31 | loss:0.017865633592009544 lr:9.982464296247522e-05 tokens_per_second_per_gpu:7071.609523172376 Step 32 | loss:0.021166397258639336 lr:9.976136999909156e-05 tokens_per_second_per_gpu:5473.154008631543 Step 33 | loss:0.08063451945781708 lr:9.968839595802982e-05 tokens_per_second_per_gpu:5514.467244053035 Step 34 | loss:0.016928916797041893 lr:9.96057350657239e-05 tokens_per_second_per_gpu:7090.649003910936 Step 35 | loss:0.017500245943665504 lr:9.951340343707852e-05 tokens_per_second_per_gpu:6754.274346647743 Step 36 | loss:0.025639405474066734 lr:9.941141907232765e-05 tokens_per_second_per_gpu:6766.71454061651 Step 37 | loss:0.013126703910529613 lr:9.929980185352526e-05 tokens_per_second_per_gpu:7021.787422744494 Step 38 | loss:0.01323827262967825 lr:9.917857354066931e-05 tokens_per_second_per_gpu:7009.879461553375 Step 39 | loss:0.009400242008268833 lr:9.904775776745958e-05 tokens_per_second_per_gpu:6954.122187769143 Step 40 | loss:0.008134931325912476 lr:9.890738003669029e-05 tokens_per_second_per_gpu:6901.254911924243 Step 41 | loss:0.02550586499273777 lr:9.875746771527816e-05 tokens_per_second_per_gpu:6928.281351077583 Step 42 | loss:0.012136021628975868 lr:9.859805002892732e-05 tokens_per_second_per_gpu:6963.419309150671 Step 43 | loss:0.028815755620598793 lr:9.842915805643155e-05 tokens_per_second_per_gpu:6354.532003674189 Step 44 | loss:0.007682180497795343 lr:9.825082472361557e-05 tokens_per_second_per_gpu:6965.227328289745 Step 45 | loss:0.033431630581617355 lr:9.806308479691595e-05 tokens_per_second_per_gpu:6996.290878364393 Step 46 | loss:0.03118099458515644 lr:9.786597487660337e-05 tokens_per_second_per_gpu:6778.297970676929 Step 47 | loss:0.008037610910832882 lr:9.765953338964735e-05 tokens_per_second_per_gpu:7028.335214836144 Step 48 | loss:0.027925267815589905 lr:9.744380058222483e-05 tokens_per_second_per_gpu:6772.463942498169 Step 49 | loss:0.031190793961286545 lr:9.721881851187406e-05 tokens_per_second_per_gpu:6474.668018976352 Step 50 | loss:0.004165398422628641 lr:9.698463103929542e-05 tokens_per_second_per_gpu:6707.643316120384 Step 51 | loss:0.012326560914516449 lr:9.674128381980072e-05 tokens_per_second_per_gpu:7036.763442274439 Step 52 | loss:0.010515719652175903 lr:9.648882429441257e-05 tokens_per_second_per_gpu:6691.942337482149 Step 53 | loss:0.005056723952293396 lr:9.622730168061567e-05 tokens_per_second_per_gpu:6929.699050024886 Step 54 | loss:0.012861047871410847 lr:9.595676696276172e-05 tokens_per_second_per_gpu:6923.051432008459 Step 55 | loss:0.016572091728448868 lr:9.567727288213005e-05 tokens_per_second_per_gpu:6913.677940404831 Step 56 | loss:0.03173821419477463 lr:9.538887392664544e-05 tokens_per_second_per_gpu:3055.230091158895 Step 57 | loss:0.012892535887658596 lr:9.50916263202557e-05 tokens_per_second_per_gpu:6784.112862192736 Step 58 | loss:0.005285034421831369 lr:9.478558801197065e-05 tokens_per_second_per_gpu:7029.69910428428 Step 59 | loss:0.004446064122021198 lr:9.447081866456489e-05 tokens_per_second_per_gpu:7049.183126197825 Step 60 | loss:0.03167906031012535 lr:9.414737964294636e-05 tokens_per_second_per_gpu:5900.564681192717 Step 61 | loss:0.021942172199487686 lr:9.381533400219318e-05 tokens_per_second_per_gpu:1858.8753375510216 Step 62 | loss:0.010253912769258022 lr:9.347474647526095e-05 tokens_per_second_per_gpu:7034.719000135198 Step 63 | loss:0.007201052270829678 lr:9.312568346036288e-05 tokens_per_second_per_gpu:6720.448679246894 Step 64 | loss:0.04340610280632973 lr:9.276821300802534e-05 tokens_per_second_per_gpu:632.065486254777 Step 65 | loss:0.023571740835905075 lr:9.24024048078213e-05 tokens_per_second_per_gpu:5941.939179289097 Step 66 | loss:0.005690110847353935 lr:9.202833017478422e-05 tokens_per_second_per_gpu:7087.275438335827 Step 67 | loss:0.012147211469709873 lr:9.164606203550497e-05 tokens_per_second_per_gpu:6940.668507649066 Step 68 | loss:0.00472741574048996 lr:9.125567491391476e-05 tokens_per_second_per_gpu:6934.214417788099 Step 69 | loss:0.00965108908712864 lr:9.085724491675642e-05 tokens_per_second_per_gpu:6933.550746830148 Step 70 | loss:0.01974014937877655 lr:9.045084971874738e-05 tokens_per_second_per_gpu:5486.631518295914 Step 71 | loss:0.03995132073760033 lr:9.003656854743667e-05 tokens_per_second_per_gpu:6752.484822015263 Step 72 | loss:0.007483765482902527 lr:8.961448216775954e-05 tokens_per_second_per_gpu:6862.027843628086 Step 73 | loss:0.022619029507040977 lr:8.9184672866292e-05 tokens_per_second_per_gpu:6701.752694887577 Step 74 | loss:0.0033045297022908926 lr:8.874722443520899e-05 tokens_per_second_per_gpu:7050.588200668822 Step 75 | loss:0.009399507194757462 lr:8.83022221559489e-05 tokens_per_second_per_gpu:7027.504790980146 Step 76 | loss:0.005000630393624306 lr:8.784975278258783e-05 tokens_per_second_per_gpu:6745.116919281494 Step 77 | loss:0.010632808320224285 lr:8.73899045249266e-05 tokens_per_second_per_gpu:6934.9678570535625 Step 78 | loss:0.003816715208813548 lr:8.692276703129421e-05 tokens_per_second_per_gpu:6676.158293809904 Step 79 | loss:0.014692451804876328 lr:8.644843137107059e-05 tokens_per_second_per_gpu:6692.778639610146 Step 80 | loss:0.006270149722695351 lr:8.596699001693255e-05 tokens_per_second_per_gpu:6964.5735052821765 Step 81 | loss:0.004408980254083872 lr:8.547853682682604e-05 tokens_per_second_per_gpu:7017.769295934003 Step 82 | loss:0.008176732808351517 lr:8.498316702566828e-05 tokens_per_second_per_gpu:7048.657420619673 Step 83 | loss:0.004897640086710453 lr:8.44809771867835e-05 tokens_per_second_per_gpu:5659.086788796779 Step 84 | loss:0.01283059362322092 lr:8.397206521307584e-05 tokens_per_second_per_gpu:6701.38823888926 Step 85 | loss:0.010772138833999634 lr:8.345653031794292e-05 tokens_per_second_per_gpu:6679.258146932443 Step 86 | loss:0.0076423995196819305 lr:8.293447300593402e-05 tokens_per_second_per_gpu:6826.650389925164 Step 87 | loss:0.02007436379790306 lr:8.240599505315655e-05 tokens_per_second_per_gpu:6914.458313697555 Step 88 | loss:0.0038772867992520332 lr:8.18711994874345e-05 tokens_per_second_per_gpu:7106.557976968709 Step 89 | loss:0.007673254236578941 lr:8.133019056822304e-05 tokens_per_second_per_gpu:6926.6614487404995 Step 90 | loss:0.014162499457597733 lr:8.07830737662829e-05 tokens_per_second_per_gpu:6382.3219970970185 Step 91 | loss:0.002787807025015354 lr:8.022995574311876e-05 tokens_per_second_per_gpu:7097.851136187626 Step 92 | loss:0.0045578558929264545 lr:7.967094433018508e-05 tokens_per_second_per_gpu:6951.229082221754 Step 93 | loss:0.0061919488944113255 lr:7.910614850786448e-05 tokens_per_second_per_gpu:6447.472836691149 Step 94 | loss:0.008360223844647408 lr:7.85356783842216e-05 tokens_per_second_per_gpu:6958.3205553207 Step 95 | loss:0.003080762457102537 lr:7.795964517353735e-05 tokens_per_second_per_gpu:6693.919063012913 Step 96 | loss:0.010521787218749523 lr:7.737816117462752e-05 tokens_per_second_per_gpu:6931.602027045962 Step 97 | loss:0.003265009494498372 lr:7.679133974894983e-05 tokens_per_second_per_gpu:6843.570445836782 Step 98 | loss:0.009578531607985497 lr:7.619929529850397e-05 tokens_per_second_per_gpu:6987.611009084642 Step 99 | loss:0.006371459923684597 lr:7.560214324352858e-05 tokens_per_second_per_gpu:6340.3626998653335 Step 100 | loss:0.0290974173694849 lr:7.500000000000001e-05 tokens_per_second_per_gpu:6475.392050088676 Step 101 | loss:0.017059288918972015 lr:7.439298295693665e-05 tokens_per_second_per_gpu:6774.846045539627 Step 102 | loss:0.004905846901237965 lr:7.378121045351378e-05 tokens_per_second_per_gpu:6988.351578826188 Step 103 | loss:0.009384077042341232 lr:7.316480175599309e-05 tokens_per_second_per_gpu:7035.175257078579 Step 104 | loss:0.008222030475735664 lr:7.254387703447154e-05 tokens_per_second_per_gpu:6947.672408189551 Step 105 | loss:0.00886679720133543 lr:7.191855733945387e-05 tokens_per_second_per_gpu:6926.876997864973 Step 106 | loss:0.010427959263324738 lr:7.128896457825364e-05 tokens_per_second_per_gpu:7068.867460029357 Step 107 | loss:0.002204813761636615 lr:7.06552214912271e-05 tokens_per_second_per_gpu:6917.127845556736 Step 108 | loss:0.004603002220392227 lr:7.001745162784477e-05 tokens_per_second_per_gpu:6933.362787742441 Step 109 | loss:0.0014567406615242362 lr:6.937577932260515e-05 tokens_per_second_per_gpu:6944.957528797474 Step 110 | loss:0.011430821381509304 lr:6.873032967079561e-05 tokens_per_second_per_gpu:6721.159338484312 Step 111 | loss:0.013794478960335255 lr:6.808122850410461e-05 tokens_per_second_per_gpu:4327.031590128899 Step 112 | loss:0.005076818633824587 lr:6.742860236609077e-05 tokens_per_second_per_gpu:6952.513121016411 Step 113 | loss:0.036225080490112305 lr:6.677257848751277e-05 tokens_per_second_per_gpu:5919.771385382679 Step 114 | loss:0.012992974370718002 lr:6.611328476152557e-05 tokens_per_second_per_gpu:6891.0200598193815 Step 115 | loss:0.016333892941474915 lr:6.545084971874738e-05 tokens_per_second_per_gpu:6752.285755468467 Step 116 | loss:0.0013113553868606687 lr:6.478540250220234e-05 tokens_per_second_per_gpu:6678.764671534915 Step 117 | loss:0.0018955350387841463 lr:6.411707284214384e-05 tokens_per_second_per_gpu:6683.371848986411 Step 118 | loss:0.00597984716296196 lr:6.344599103076329e-05 tokens_per_second_per_gpu:6755.915001767642 Step 119 | loss:0.007629127241671085 lr:6.277228789678953e-05 tokens_per_second_per_gpu:6356.243860576967 Step 120 | loss:0.010765857063233852 lr:6.209609477998338e-05 tokens_per_second_per_gpu:6918.751100458293 Step 121 | loss:0.003509789239615202 lr:6.141754350553279e-05 tokens_per_second_per_gpu:6960.079785471238 Step 122 | loss:0.018370801582932472 lr:6.073676635835317e-05 tokens_per_second_per_gpu:6762.442767986698 Step 123 | loss:0.012954381294548512 lr:6.005389605729824e-05 tokens_per_second_per_gpu:7004.548670576017 Step 124 | loss:0.026485862210392952 lr:5.9369065729286245e-05 tokens_per_second_per_gpu:5908.519393639382 Step 125 | loss:0.0054400828666985035 lr:5.868240888334653e-05 tokens_per_second_per_gpu:6949.320257559778 Step 126 | loss:0.013101345859467983 lr:5.799405938459175e-05 tokens_per_second_per_gpu:6703.816727952213 Step 127 | loss:0.00421176990494132 lr:5.730415142812059e-05 tokens_per_second_per_gpu:6660.239855240987 Step 128 | loss:0.0026094967033714056 lr:5.661281951285613e-05 tokens_per_second_per_gpu:6955.534200763428 Step 129 | loss:0.009470321238040924 lr:5.5920198415325064e-05 tokens_per_second_per_gpu:6747.904374431035 Step 130 | loss:0.008754801005125046 lr:5.522642316338268e-05 tokens_per_second_per_gpu:6698.846480767512 Step 131 | loss:0.005730781704187393 lr:5.453162900988902e-05 tokens_per_second_per_gpu:6978.049440110429 Step 132 | loss:0.010698440484702587 lr:5.383595140634093e-05 tokens_per_second_per_gpu:6750.184289806843 Step 133 | loss:0.007397581823170185 lr:5.313952597646568e-05 tokens_per_second_per_gpu:7035.7086540191785 Step 134 | loss:0.0070086317136883736 lr:5.244248848978067e-05 tokens_per_second_per_gpu:6662.974407497913 Step 135 | loss:0.002189722377806902 lr:5.174497483512506e-05 tokens_per_second_per_gpu:6949.868620120697 Step 136 | loss:0.008925589732825756 lr:5.104712099416785e-05 tokens_per_second_per_gpu:6968.128419730209 Step 137 | loss:0.0026622051373124123 lr:5.034906301489808e-05 tokens_per_second_per_gpu:6921.258374547391 Step 138 | loss:0.010600435547530651 lr:4.965093698510193e-05 tokens_per_second_per_gpu:6301.987142290314 Step 139 | loss:0.0021846245508641005 lr:4.895287900583216e-05 tokens_per_second_per_gpu:7070.390085635233 Step 140 | loss:0.005960069131106138 lr:4.825502516487497e-05 tokens_per_second_per_gpu:5752.226916533092 Step 141 | loss:0.027469905093312263 lr:4.755751151021934e-05 tokens_per_second_per_gpu:6704.958607049676 Step 142 | loss:0.007926453836262226 lr:4.6860474023534335e-05 tokens_per_second_per_gpu:6924.557449388856 Step 143 | loss:0.003907023463398218 lr:4.616404859365907e-05 tokens_per_second_per_gpu:6887.427605434061 Step 144 | loss:0.008207329548895359 lr:4.5468370990111006e-05 tokens_per_second_per_gpu:6973.566014423558 Step 145 | loss:0.052640728652477264 lr:4.477357683661734e-05 tokens_per_second_per_gpu:5903.077083379559 Step 146 | loss:0.0033343143295496702 lr:4.407980158467495e-05 tokens_per_second_per_gpu:6925.508345150243 Step 147 | loss:0.009512447752058506 lr:4.3387180487143876e-05 tokens_per_second_per_gpu:7079.588584934116 Step 148 | loss:0.001313482061959803 lr:4.269584857187943e-05 tokens_per_second_per_gpu:6985.102278504007 Step 149 | loss:0.0035433853045105934 lr:4.2005940615408264e-05 tokens_per_second_per_gpu:6952.799262959906 Step 150 | loss:0.024211272597312927 lr:4.131759111665349e-05 tokens_per_second_per_gpu:6771.596443276175 Step 151 | loss:0.013524808920919895 lr:4.063093427071376e-05 tokens_per_second_per_gpu:6839.443835534106 Step 152 | loss:0.0020400506909936666 lr:3.9946103942701777e-05 tokens_per_second_per_gpu:7043.335263941309 Step 153 | loss:0.006887585856020451 lr:3.926323364164684e-05 tokens_per_second_per_gpu:6948.367086104009 Step 154 | loss:0.0007622658740729094 lr:3.858245649446721e-05 tokens_per_second_per_gpu:6876.779326366299 Step 155 | loss:0.004148123785853386 lr:3.790390522001662e-05 tokens_per_second_per_gpu:6932.678884531136 Step 156 | loss:0.006994878873229027 lr:3.7227712103210486e-05 tokens_per_second_per_gpu:6733.89746737431 Step 157 | loss:0.005628213286399841 lr:3.655400896923672e-05 tokens_per_second_per_gpu:6919.475062339656 Step 158 | loss:0.0012905232142657042 lr:3.588292715785617e-05 tokens_per_second_per_gpu:7053.132014990728 Step 159 | loss:0.006507265847176313 lr:3.5214597497797684e-05 tokens_per_second_per_gpu:6945.005032645729 Step 160 | loss:0.013897155411541462 lr:3.4549150281252636e-05 tokens_per_second_per_gpu:5893.745999019981 Step 161 | loss:0.0009851098293438554 lr:3.388671523847445e-05 tokens_per_second_per_gpu:6961.698540897415 Step 162 | loss:0.0010926288086920977 lr:3.322742151248725e-05 tokens_per_second_per_gpu:6673.138647807616 Step 163 | loss:0.003954046871513128 lr:3.257139763390925e-05 tokens_per_second_per_gpu:5918.993315683383 Step 164 | loss:0.007818661630153656 lr:3.1918771495895396e-05 tokens_per_second_per_gpu:6900.937293006765 Step 165 | loss:0.039015788584947586 lr:3.12696703292044e-05 tokens_per_second_per_gpu:5490.9101656462335 Step 166 | loss:0.0005865814746357501 lr:3.062422067739485e-05 tokens_per_second_per_gpu:6911.407730145985 Step 167 | loss:0.0049000694416463375 lr:2.9982548372155263e-05 tokens_per_second_per_gpu:7016.518956934702 Step 168 | loss:0.0033031702041625977 lr:2.934477850877292e-05 tokens_per_second_per_gpu:6698.291653177231 Step 169 | loss:0.003308843355625868 lr:2.8711035421746367e-05 tokens_per_second_per_gpu:4297.100016481688 Step 170 | loss:0.00299502769485116 lr:2.8081442660546125e-05 tokens_per_second_per_gpu:6944.841721087205 Step 171 | loss:0.00714130001142621 lr:2.7456122965528475e-05 tokens_per_second_per_gpu:6748.406258010629 Step 172 | loss:0.0017500595422461629 lr:2.6835198244006927e-05 tokens_per_second_per_gpu:7072.076895985526 Step 173 | loss:0.0023317839950323105 lr:2.6218789546486234e-05 tokens_per_second_per_gpu:6900.463338502707 Step 174 | loss:0.002073240466415882 lr:2.560701704306336e-05 tokens_per_second_per_gpu:7045.867074480613 Step 175 | loss:0.004037422593683004 lr:2.500000000000001e-05 tokens_per_second_per_gpu:7071.103810684478 Step 176 | loss:0.0012931041419506073 lr:2.4397856756471432e-05 tokens_per_second_per_gpu:6689.330732079918 Step 177 | loss:0.0077163223177194595 lr:2.3800704701496053e-05 tokens_per_second_per_gpu:5933.0086087456575 Step 178 | loss:0.005151920486241579 lr:2.3208660251050158e-05 tokens_per_second_per_gpu:6769.197186021789 Step 179 | loss:0.0024170612450689077 lr:2.2621838825372493e-05 tokens_per_second_per_gpu:6987.089793833158 Step 180 | loss:0.004182575736194849 lr:2.2040354826462668e-05 tokens_per_second_per_gpu:7009.429311496081 Step 181 | loss:0.0075821653008461 lr:2.1464321615778422e-05 tokens_per_second_per_gpu:6959.7537332896245 Step 182 | loss:0.0026343408972024918 lr:2.0893851492135537e-05 tokens_per_second_per_gpu:6969.922145437969 Step 183 | loss:0.002794520230963826 lr:2.0329055669814934e-05 tokens_per_second_per_gpu:7016.6278859416825 Step 184 | loss:0.0009787664748728275 lr:1.977004425688126e-05 tokens_per_second_per_gpu:6711.214801525334 Step 185 | loss:0.014552795328199863 lr:1.9216926233717085e-05 tokens_per_second_per_gpu:6753.259834906264 Step 186 | loss:0.0011452625039964914 lr:1.866980943177699e-05 tokens_per_second_per_gpu:6724.423337307199 Step 187 | loss:0.002244836650788784 lr:1.8128800512565513e-05 tokens_per_second_per_gpu:6903.935880878762 Step 188 | loss:0.005818013101816177 lr:1.7594004946843456e-05 tokens_per_second_per_gpu:6925.250594696032 Step 189 | loss:0.0037504544015973806 lr:1.7065526994065973e-05 tokens_per_second_per_gpu:7080.173208831139 Step 190 | loss:0.044447578489780426 lr:1.6543469682057106e-05 tokens_per_second_per_gpu:5916.229506731723 Step 191 | loss:0.0014237151481211185 lr:1.602793478692419e-05 tokens_per_second_per_gpu:6784.332661875743 Step 192 | loss:0.007794543169438839 lr:1.551902281321651e-05 tokens_per_second_per_gpu:6725.665582102402 Step 193 | loss:0.007534835487604141 lr:1.5016832974331724e-05 tokens_per_second_per_gpu:6713.24923744228 Step 194 | loss:0.008911740966141224 lr:1.4521463173173965e-05 tokens_per_second_per_gpu:6936.330644995231 Step 195 | loss:0.002162901684641838 lr:1.4033009983067452e-05 tokens_per_second_per_gpu:6684.5008010833035 Step 196 | loss:0.007540018763393164 lr:1.3551568628929434e-05 tokens_per_second_per_gpu:5507.737310242461 Step 197 | loss:0.003533255076035857 lr:1.3077232968705805e-05 tokens_per_second_per_gpu:6995.567234196738 Step 198 | loss:0.00563846668228507 lr:1.2610095475073414e-05 tokens_per_second_per_gpu:5750.56203123053 Step 199 | loss:0.007794528733938932 lr:1.2150247217412186e-05 tokens_per_second_per_gpu:6871.690207412787 Step 200 | loss:0.020519722253084183 lr:1.1697777844051105e-05 tokens_per_second_per_gpu:6780.506044563265 Step 201 | loss:0.0019027342787012458 lr:1.1252775564791024e-05 tokens_per_second_per_gpu:6904.095467687605 Step 202 | loss:0.007119531277567148 lr:1.0815327133708015e-05 tokens_per_second_per_gpu:6753.190609047638 Step 203 | loss:0.0036339687649160624 lr:1.0385517832240471e-05 tokens_per_second_per_gpu:7056.973969677455 Step 204 | loss:0.0030110671650618315 lr:9.963431452563332e-06 tokens_per_second_per_gpu:7057.171350249303 Step 205 | loss:0.007239978760480881 lr:9.549150281252633e-06 tokens_per_second_per_gpu:6694.407937927384 Step 206 | loss:0.004791794344782829 lr:9.142755083243576e-06 tokens_per_second_per_gpu:6769.5609045893925 Step 207 | loss:0.005512226838618517 lr:8.744325086085248e-06 tokens_per_second_per_gpu:6753.101771645693 Step 208 | loss:0.008155069313943386 lr:8.353937964495029e-06 tokens_per_second_per_gpu:6908.756690503168 Step 209 | loss:0.008876900188624859 lr:7.971669825215788e-06 tokens_per_second_per_gpu:6731.829075558569 Step 210 | loss:0.0006161606288515031 lr:7.597595192178702e-06 tokens_per_second_per_gpu:7039.577285688376 Step 211 | loss:0.0023972175549715757 lr:7.2317869919746705e-06 tokens_per_second_per_gpu:6941.436035767349 Step 212 | loss:0.015587147325277328 lr:6.874316539637127e-06 tokens_per_second_per_gpu:6722.920917725789 Step 213 | loss:0.018419289961457253 lr:6.52525352473905e-06 tokens_per_second_per_gpu:4560.175257149757 Step 214 | loss:0.007582169957458973 lr:6.184665997806832e-06 tokens_per_second_per_gpu:6987.021717898772 Step 215 | loss:0.008330561220645905 lr:5.852620357053651e-06 tokens_per_second_per_gpu:5487.563636500798 Step 216 | loss:0.002304473891854286 lr:5.529181335435124e-06 tokens_per_second_per_gpu:6922.919405639436 Step 217 | loss:0.007012868765741587 lr:5.214411988029355e-06 tokens_per_second_per_gpu:6883.2461759269245 Step 218 | loss:0.004475523252040148 lr:4.908373679744316e-06 tokens_per_second_per_gpu:6695.862131873393 Step 219 | loss:0.004779299255460501 lr:4.611126073354571e-06 tokens_per_second_per_gpu:6942.683624986472 Step 220 | loss:0.00406808964908123 lr:4.322727117869951e-06 tokens_per_second_per_gpu:6997.576987061082 Step 221 | loss:0.003888849401846528 lr:4.043233037238281e-06 tokens_per_second_per_gpu:6700.691053019122 Step 222 | loss:0.00902603566646576 lr:3.772698319384349e-06 tokens_per_second_per_gpu:5923.625170839221 Step 223 | loss:0.006663593929260969 lr:3.511175705587433e-06 tokens_per_second_per_gpu:6948.266260388629 Step 224 | loss:0.00816346425563097 lr:3.258716180199278e-06 tokens_per_second_per_gpu:7096.598092270735 Step 225 | loss:0.0035016373731195927 lr:3.0153689607045845e-06 tokens_per_second_per_gpu:6942.4673265236315 Step 226 | loss:0.00954430177807808 lr:2.7811814881259503e-06 tokens_per_second_per_gpu:5929.197453240231 Step 227 | loss:0.00228720810264349 lr:2.5561994177751737e-06 tokens_per_second_per_gpu:4328.227634202687 Step 228 | loss:0.0069065759889781475 lr:2.340466610352654e-06 tokens_per_second_per_gpu:5940.49169306585 Step 229 | loss:0.011968896724283695 lr:2.134025123396638e-06 tokens_per_second_per_gpu:6432.108337071448 Step 230 | loss:0.007078529801219702 lr:1.9369152030840556e-06 tokens_per_second_per_gpu:6775.431967324532 Step 231 | loss:0.002257893793284893 lr:1.7491752763844293e-06 tokens_per_second_per_gpu:6912.350252962254 Step 232 | loss:0.0070510730147361755 lr:1.5708419435684462e-06 tokens_per_second_per_gpu:6722.1797607021 Step 233 | loss:0.010475601069629192 lr:1.4019499710726913e-06 tokens_per_second_per_gpu:7079.859241059848 Step 234 | loss:0.0023329653777182102 lr:1.2425322847218368e-06 tokens_per_second_per_gpu:6917.243915604057 Step 235 | loss:0.005569015629589558 lr:1.0926199633097157e-06 tokens_per_second_per_gpu:6734.3276779321195 Step 236 | loss:0.004110108129680157 lr:9.522422325404235e-07 tokens_per_second_per_gpu:7091.851742198494 Step 237 | loss:0.0031299733091145754 lr:8.214264593307098e-07 tokens_per_second_per_gpu:6732.903567491262 Step 238 | loss:0.004234972409904003 lr:7.001981464747565e-07 tokens_per_second_per_gpu:6779.485565301759 Step 239 | loss:0.039819780737161636 lr:5.885809276723608e-07 tokens_per_second_per_gpu:6739.331183411753 Step 240 | loss:0.010342773050069809 lr:4.865965629214819e-07 tokens_per_second_per_gpu:6492.10023835261 Step 241 | loss:0.011507350951433182 lr:3.9426493427611177e-07 tokens_per_second_per_gpu:6718.34623480546 Step 242 | loss:0.012840881943702698 lr:3.1160404197018154e-07 tokens_per_second_per_gpu:6779.305587749928 Step 243 | loss:0.00423215888440609 lr:2.386300009084408e-07 tokens_per_second_per_gpu:6955.1827357474385 Step 244 | loss:0.0075535341165959835 lr:1.753570375247815e-07 tokens_per_second_per_gpu:6721.9475956424685 Step 245 | loss:0.006801807787269354 lr:1.2179748700879012e-07 tokens_per_second_per_gpu:6883.022162946916 Step 246 | loss:0.007994530722498894 lr:7.796179090094891e-08 tokens_per_second_per_gpu:6773.734285901796 Step 247 | loss:0.0026732247788459063 lr:4.385849505708084e-08 tokens_per_second_per_gpu:5508.2631793805185 Step 248 | loss:0.004023219458758831 lr:1.949424798228239e-08 tokens_per_second_per_gpu:5951.84516290067 Step 249 | loss:0.0005410840385593474 lr:4.873799534788059e-09 tokens_per_second_per_gpu:6965.453101254294 Step 250 | loss:0.0005745271337218583 lr:0.0 tokens_per_second_per_gpu:6891.5934429268555