Step 1 | loss:0.012126867659389973 lr:4.000000000000001e-06 tokens_per_second_per_gpu:4833.300924868494 Step 2 | loss:0.01700320467352867 lr:8.000000000000001e-06 tokens_per_second_per_gpu:4932.880444196351 Step 3 | loss:0.021946880966424942 lr:1.2e-05 tokens_per_second_per_gpu:3640.294727406159 Step 4 | loss:0.013717728666961193 lr:1.6000000000000003e-05 tokens_per_second_per_gpu:6773.375876211844 Step 5 | loss:0.0203966423869133 lr:2e-05 tokens_per_second_per_gpu:4430.56786854172 Step 6 | loss:0.006744523532688618 lr:2.4e-05 tokens_per_second_per_gpu:6787.600986731158 Step 7 | loss:0.00617251405492425 lr:2.8000000000000003e-05 tokens_per_second_per_gpu:6892.911605316321 Step 8 | loss:0.014487615786492825 lr:3.2000000000000005e-05 tokens_per_second_per_gpu:6772.608140720518 Step 9 | loss:0.021100787445902824 lr:3.6e-05 tokens_per_second_per_gpu:6857.449017829765 Step 10 | loss:0.004503477830439806 lr:4e-05 tokens_per_second_per_gpu:4418.204188273966 Step 11 | loss:0.007161840330809355 lr:4.4000000000000006e-05 tokens_per_second_per_gpu:6882.475896833199 Step 12 | loss:0.00430942652747035 lr:4.8e-05 tokens_per_second_per_gpu:6867.294951584685 Step 13 | loss:0.005604463163763285 lr:5.2000000000000004e-05 tokens_per_second_per_gpu:6841.057322396758 Step 14 | loss:0.014212383888661861 lr:5.6000000000000006e-05 tokens_per_second_per_gpu:6985.6677572465915 Step 15 | loss:0.004473082255572081 lr:6e-05 tokens_per_second_per_gpu:6788.760331102294 Step 16 | loss:0.007423576433211565 lr:6.400000000000001e-05 tokens_per_second_per_gpu:6880.1682233994015 Step 17 | loss:0.010623784735798836 lr:6.800000000000001e-05 tokens_per_second_per_gpu:6915.164450146292 Step 18 | loss:0.0050511714071035385 lr:7.2e-05 tokens_per_second_per_gpu:6874.173381862588 Step 19 | loss:0.0032848434057086706 lr:7.6e-05 tokens_per_second_per_gpu:6805.071539165989 Step 20 | loss:0.012150806374847889 lr:8e-05 tokens_per_second_per_gpu:7100.132943815336 Step 21 | loss:0.00669699115678668 lr:8.4e-05 tokens_per_second_per_gpu:3038.338587650967 Step 22 | loss:0.010127614252269268 lr:8.800000000000001e-05 tokens_per_second_per_gpu:6807.187637373558 Step 23 | loss:0.013531161472201347 lr:9.200000000000001e-05 tokens_per_second_per_gpu:6952.433563053499 Step 24 | loss:0.0026388501282781363 lr:9.6e-05 tokens_per_second_per_gpu:6810.9823582615545 Step 25 | loss:0.012501201592385769 lr:0.0001 tokens_per_second_per_gpu:7107.259414071098 Step 26 | loss:0.0067090666852891445 lr:9.999512620046522e-05 tokens_per_second_per_gpu:6957.126090490083 Step 27 | loss:0.010586481541395187 lr:9.998050575201771e-05 tokens_per_second_per_gpu:6825.458527984589 Step 28 | loss:0.0049416739493608475 lr:9.995614150494293e-05 tokens_per_second_per_gpu:6853.583840928845 Step 29 | loss:0.003947166725993156 lr:9.992203820909906e-05 tokens_per_second_per_gpu:7027.559961845077 Step 30 | loss:0.011007261462509632 lr:9.987820251299122e-05 tokens_per_second_per_gpu:7120.954875398477 Step 31 | loss:0.00568861560896039 lr:9.982464296247522e-05 tokens_per_second_per_gpu:7042.030863972232 Step 32 | loss:0.00941373873502016 lr:9.976136999909156e-05 tokens_per_second_per_gpu:6878.572026276843 Step 33 | loss:0.010303176939487457 lr:9.968839595802982e-05 tokens_per_second_per_gpu:6902.249828332477 Step 34 | loss:0.006990714464336634 lr:9.96057350657239e-05 tokens_per_second_per_gpu:6835.549929644228 Step 35 | loss:0.0025181621313095093 lr:9.951340343707852e-05 tokens_per_second_per_gpu:6800.752998578519 Step 36 | loss:0.004338821396231651 lr:9.941141907232765e-05 tokens_per_second_per_gpu:6851.301232524426 Step 37 | loss:0.006985168904066086 lr:9.929980185352526e-05 tokens_per_second_per_gpu:6760.642753898902 Step 38 | loss:0.00593229616060853 lr:9.917857354066931e-05 tokens_per_second_per_gpu:6984.240084251336 Step 39 | loss:0.007242584601044655 lr:9.904775776745958e-05 tokens_per_second_per_gpu:7091.593336769536 Step 40 | loss:0.0033401234541088343 lr:9.890738003669029e-05 tokens_per_second_per_gpu:7006.254505860222 Step 41 | loss:0.004227368626743555 lr:9.875746771527816e-05 tokens_per_second_per_gpu:6858.381354925646 Step 42 | loss:0.001282719662413001 lr:9.859805002892732e-05 tokens_per_second_per_gpu:7059.5528419620905 Step 43 | loss:0.0043543302454054356 lr:9.842915805643155e-05 tokens_per_second_per_gpu:7117.532154805262 Step 44 | loss:0.006948532070964575 lr:9.825082472361557e-05 tokens_per_second_per_gpu:7081.300274580479 Step 45 | loss:0.004268730524927378 lr:9.806308479691595e-05 tokens_per_second_per_gpu:6848.809257172993 Step 46 | loss:0.0013655956136062741 lr:9.786597487660337e-05 tokens_per_second_per_gpu:6990.513535666626 Step 47 | loss:0.0033806092105805874 lr:9.765953338964735e-05 tokens_per_second_per_gpu:7078.386675609349 Step 48 | loss:0.003592906054109335 lr:9.744380058222483e-05 tokens_per_second_per_gpu:6807.575788298728 Step 49 | loss:0.0012465346371755004 lr:9.721881851187406e-05 tokens_per_second_per_gpu:7050.111093745911 Step 50 | loss:0.002906613517552614 lr:9.698463103929542e-05 tokens_per_second_per_gpu:7095.764677672945 Step 51 | loss:0.004270544275641441 lr:9.674128381980072e-05 tokens_per_second_per_gpu:6847.379473798361 Step 52 | loss:0.0044741458259522915 lr:9.648882429441257e-05 tokens_per_second_per_gpu:7129.030824676643 Step 53 | loss:0.0017880145460367203 lr:9.622730168061567e-05 tokens_per_second_per_gpu:7047.9373639061305 Step 54 | loss:0.0014009695732966065 lr:9.595676696276172e-05 tokens_per_second_per_gpu:6850.643456250875 Step 55 | loss:0.0008995666285045445 lr:9.567727288213005e-05 tokens_per_second_per_gpu:6932.888405744129 Step 56 | loss:0.0008053722558543086 lr:9.538887392664544e-05 tokens_per_second_per_gpu:6439.712221118734 Step 57 | loss:0.002311884192749858 lr:9.50916263202557e-05 tokens_per_second_per_gpu:7095.9443481996195 Step 58 | loss:0.001219618134200573 lr:9.478558801197065e-05 tokens_per_second_per_gpu:7003.198959214072 Step 59 | loss:0.0012370777549222112 lr:9.447081866456489e-05 tokens_per_second_per_gpu:6967.829722788717 Step 60 | loss:0.002615226898342371 lr:9.414737964294636e-05 tokens_per_second_per_gpu:7121.603034903321 Step 61 | loss:0.004097046330571175 lr:9.381533400219318e-05 tokens_per_second_per_gpu:7077.656493703444 Step 62 | loss:0.0010872111888602376 lr:9.347474647526095e-05 tokens_per_second_per_gpu:7137.766177138471 Step 63 | loss:0.0013398496666923165 lr:9.312568346036288e-05 tokens_per_second_per_gpu:7027.160007392011 Step 64 | loss:0.0007282105507329106 lr:9.276821300802534e-05 tokens_per_second_per_gpu:7084.3621470275975 Step 65 | loss:0.002187884645536542 lr:9.24024048078213e-05 tokens_per_second_per_gpu:6806.53232927901 Step 66 | loss:0.003463924629613757 lr:9.202833017478422e-05 tokens_per_second_per_gpu:6787.510591927632 Step 67 | loss:0.004247263073921204 lr:9.164606203550497e-05 tokens_per_second_per_gpu:6874.465031449895 Step 68 | loss:0.002274675527587533 lr:9.125567491391476e-05 tokens_per_second_per_gpu:7126.363126195635 Step 69 | loss:0.0025124435778707266 lr:9.085724491675642e-05 tokens_per_second_per_gpu:7067.983222655297 Step 70 | loss:0.0007425479707308114 lr:9.045084971874738e-05 tokens_per_second_per_gpu:7013.3962757821955 Step 71 | loss:0.00046460487646982074 lr:9.003656854743667e-05 tokens_per_second_per_gpu:6850.323872454945 Step 72 | loss:0.0005358102498576045 lr:8.961448216775954e-05 tokens_per_second_per_gpu:7011.9482527864275 Step 73 | loss:0.0008165960316546261 lr:8.9184672866292e-05 tokens_per_second_per_gpu:6874.9466401705795 Step 74 | loss:0.0013159812660887837 lr:8.874722443520899e-05 tokens_per_second_per_gpu:6904.754917327851 Step 75 | loss:0.0011063289130106568 lr:8.83022221559489e-05 tokens_per_second_per_gpu:6900.259317828343 Step 76 | loss:0.0009968270314857364 lr:8.784975278258783e-05 tokens_per_second_per_gpu:7092.875645716278 Step 77 | loss:0.0011400597868487239 lr:8.73899045249266e-05 tokens_per_second_per_gpu:6852.714783493283 Step 78 | loss:0.0006061335443519056 lr:8.692276703129421e-05 tokens_per_second_per_gpu:6799.395047834512 Step 79 | loss:0.0020276436116546392 lr:8.644843137107059e-05 tokens_per_second_per_gpu:6876.4764526644785 Step 80 | loss:0.0005658188019879162 lr:8.596699001693255e-05 tokens_per_second_per_gpu:6854.214558071189 Step 81 | loss:0.0007222832646220922 lr:8.547853682682604e-05 tokens_per_second_per_gpu:7036.772156230615 Step 82 | loss:0.0008630384691059589 lr:8.498316702566828e-05 tokens_per_second_per_gpu:7021.2610884194055 Step 83 | loss:0.0007969830767251551 lr:8.44809771867835e-05 tokens_per_second_per_gpu:6961.947951988879 Step 84 | loss:0.0008431139285676181 lr:8.397206521307584e-05 tokens_per_second_per_gpu:7113.672941534877 Step 85 | loss:0.000588306924328208 lr:8.345653031794292e-05 tokens_per_second_per_gpu:6845.808422971787 Step 86 | loss:0.0008693189593032002 lr:8.293447300593402e-05 tokens_per_second_per_gpu:7008.446727705492 Step 87 | loss:0.0003906263445969671 lr:8.240599505315655e-05 tokens_per_second_per_gpu:6791.030004572347 Step 88 | loss:0.0007734567043371499 lr:8.18711994874345e-05 tokens_per_second_per_gpu:6752.530944669517 Step 89 | loss:0.0016889908583834767 lr:8.133019056822304e-05 tokens_per_second_per_gpu:7041.528941607407 Step 90 | loss:0.000954675255343318 lr:8.07830737662829e-05 tokens_per_second_per_gpu:7050.12225598687 Step 91 | loss:0.004883120767772198 lr:8.022995574311876e-05 tokens_per_second_per_gpu:7095.413816473139 Step 92 | loss:0.0007773354300297797 lr:7.967094433018508e-05 tokens_per_second_per_gpu:7022.382547657683 Step 93 | loss:0.0011948546161875129 lr:7.910614850786448e-05 tokens_per_second_per_gpu:6864.4645758321385 Step 94 | loss:0.0005624517798423767 lr:7.85356783842216e-05 tokens_per_second_per_gpu:6903.856469402347 Step 95 | loss:0.0007071316358633339 lr:7.795964517353735e-05 tokens_per_second_per_gpu:7015.995003713729 Step 96 | loss:0.00034775296808220446 lr:7.737816117462752e-05 tokens_per_second_per_gpu:6917.529669358174 Step 97 | loss:0.00033728909329511225 lr:7.679133974894983e-05 tokens_per_second_per_gpu:6927.123607887701 Step 98 | loss:0.0009426011820323765 lr:7.619929529850397e-05 tokens_per_second_per_gpu:7096.773202798088 Step 99 | loss:0.00023242016322910786 lr:7.560214324352858e-05 tokens_per_second_per_gpu:6905.949740702393 Step 100 | loss:0.0008040693355724216 lr:7.500000000000001e-05 tokens_per_second_per_gpu:7021.613272270064 Step 101 | loss:0.0006634981255047023 lr:7.439298295693665e-05 tokens_per_second_per_gpu:7118.938429962486 Step 102 | loss:0.0005453706253319979 lr:7.378121045351378e-05 tokens_per_second_per_gpu:6988.862606766333 Step 103 | loss:0.0013171351747587323 lr:7.316480175599309e-05 tokens_per_second_per_gpu:6989.849639083941 Step 104 | loss:0.0006460000877268612 lr:7.254387703447154e-05 tokens_per_second_per_gpu:6868.071580288199 Step 105 | loss:0.0003579905314836651 lr:7.191855733945387e-05 tokens_per_second_per_gpu:7080.707882008111 Step 106 | loss:0.0007657781825400889 lr:7.128896457825364e-05 tokens_per_second_per_gpu:6879.740730972892 Step 107 | loss:0.0010963898384943604 lr:7.06552214912271e-05 tokens_per_second_per_gpu:6905.497306565076 Step 108 | loss:0.00011449164594523609 lr:7.001745162784477e-05 tokens_per_second_per_gpu:6914.401681508231 Step 109 | loss:0.0007816519355401397 lr:6.937577932260515e-05 tokens_per_second_per_gpu:6884.069095494742 Step 110 | loss:0.0009465090115554631 lr:6.873032967079561e-05 tokens_per_second_per_gpu:6846.467791941489 Step 111 | loss:0.0005542872240766883 lr:6.808122850410461e-05 tokens_per_second_per_gpu:6891.795597097536 Step 112 | loss:0.00032626307802274823 lr:6.742860236609077e-05 tokens_per_second_per_gpu:6944.683658020617 Step 113 | loss:0.0018325377022847533 lr:6.677257848751277e-05 tokens_per_second_per_gpu:7069.896486479744 Step 114 | loss:0.0003625378885772079 lr:6.611328476152557e-05 tokens_per_second_per_gpu:6839.802666987416 Step 115 | loss:0.0005067411693744361 lr:6.545084971874738e-05 tokens_per_second_per_gpu:6883.290889716776 Step 116 | loss:0.00026771731791086495 lr:6.478540250220234e-05 tokens_per_second_per_gpu:6937.224577200657 Step 117 | loss:0.0005085628945380449 lr:6.411707284214384e-05 tokens_per_second_per_gpu:6901.000095154726 Step 118 | loss:0.00035051320446655154 lr:6.344599103076329e-05 tokens_per_second_per_gpu:6808.470070414611 Step 119 | loss:0.0005614007241092622 lr:6.277228789678953e-05 tokens_per_second_per_gpu:6868.457771687214 Step 120 | loss:0.0003708350704982877 lr:6.209609477998338e-05 tokens_per_second_per_gpu:6802.771463278319 Step 121 | loss:0.0003196424513589591 lr:6.141754350553279e-05 tokens_per_second_per_gpu:6850.203136563997 Step 122 | loss:0.0004698104748968035 lr:6.073676635835317e-05 tokens_per_second_per_gpu:6903.530390397868 Step 123 | loss:0.0012211567955091596 lr:6.005389605729824e-05 tokens_per_second_per_gpu:6968.305287524247 Step 124 | loss:0.0004674977099057287 lr:5.9369065729286245e-05 tokens_per_second_per_gpu:6904.635158243699 Step 125 | loss:0.0005282903439365327 lr:5.868240888334653e-05 tokens_per_second_per_gpu:7055.893126178938 Step 126 | loss:0.0004448916297405958 lr:5.799405938459175e-05 tokens_per_second_per_gpu:6862.985504972477 Step 127 | loss:0.0004872394201811403 lr:5.730415142812059e-05 tokens_per_second_per_gpu:6875.166186991574 Step 128 | loss:0.00048035828513093293 lr:5.661281951285613e-05 tokens_per_second_per_gpu:6992.471976837858 Step 129 | loss:0.000463725533336401 lr:5.5920198415325064e-05 tokens_per_second_per_gpu:6901.979689462905 Step 130 | loss:0.0006561948102898896 lr:5.522642316338268e-05 tokens_per_second_per_gpu:7135.026365459946 Step 131 | loss:0.00037814470124430954 lr:5.453162900988902e-05 tokens_per_second_per_gpu:7021.098708428236 Step 132 | loss:0.0004345242050476372 lr:5.383595140634093e-05 tokens_per_second_per_gpu:6907.315934736296 Step 133 | loss:0.0003118895983789116 lr:5.313952597646568e-05 tokens_per_second_per_gpu:6778.1254017278725 Step 134 | loss:0.000464145588921383 lr:5.244248848978067e-05 tokens_per_second_per_gpu:6973.722700062042 Step 135 | loss:0.00036559876753017306 lr:5.174497483512506e-05 tokens_per_second_per_gpu:6837.60181112429 Step 136 | loss:0.0006815510569140315 lr:5.104712099416785e-05 tokens_per_second_per_gpu:6977.708387016327 Step 137 | loss:0.0019014901481568813 lr:5.034906301489808e-05 tokens_per_second_per_gpu:6830.4771870152645 Step 138 | loss:0.0017304376233369112 lr:4.965093698510193e-05 tokens_per_second_per_gpu:7081.32224915058 Step 139 | loss:0.0009343961137346923 lr:4.895287900583216e-05 tokens_per_second_per_gpu:7111.019085209936 Step 140 | loss:0.00039526732871308923 lr:4.825502516487497e-05 tokens_per_second_per_gpu:6987.182332353864 Step 141 | loss:0.0003155454178340733 lr:4.755751151021934e-05 tokens_per_second_per_gpu:6930.302116809142 Step 142 | loss:0.0004248145269230008 lr:4.6860474023534335e-05 tokens_per_second_per_gpu:6978.093741169269 Step 143 | loss:0.0005807343986816704 lr:4.616404859365907e-05 tokens_per_second_per_gpu:7040.77394967062 Step 144 | loss:0.0004226055752951652 lr:4.5468370990111006e-05 tokens_per_second_per_gpu:7040.038675577352 Step 145 | loss:0.0003462506865616888 lr:4.477357683661734e-05 tokens_per_second_per_gpu:6859.201369470284 Step 146 | loss:0.0005459514795802534 lr:4.407980158467495e-05 tokens_per_second_per_gpu:6873.064585021703 Step 147 | loss:0.00042545361793600023 lr:4.3387180487143876e-05 tokens_per_second_per_gpu:6763.888688916748 Step 148 | loss:0.0009329136810265481 lr:4.269584857187943e-05 tokens_per_second_per_gpu:6892.7893426032715 Step 149 | loss:0.0005262850318104029 lr:4.2005940615408264e-05 tokens_per_second_per_gpu:6845.078542273576 Step 150 | loss:0.000379923585569486 lr:4.131759111665349e-05 tokens_per_second_per_gpu:6852.206124726934 Step 151 | loss:0.0005463198176585138 lr:4.063093427071376e-05 tokens_per_second_per_gpu:7042.271656808378 Step 152 | loss:0.0005022517871111631 lr:3.9946103942701777e-05 tokens_per_second_per_gpu:6856.786881754081 Step 153 | loss:0.0007131119491532445 lr:3.926323364164684e-05 tokens_per_second_per_gpu:7030.896321034875 Step 154 | loss:0.0005893012857995927 lr:3.858245649446721e-05 tokens_per_second_per_gpu:6769.511734404627 Step 155 | loss:0.0003959594469051808 lr:3.790390522001662e-05 tokens_per_second_per_gpu:6745.937970641678 Step 156 | loss:0.0004363474145065993 lr:3.7227712103210486e-05 tokens_per_second_per_gpu:6887.956487701875 Step 157 | loss:0.0004094526811968535 lr:3.655400896923672e-05 tokens_per_second_per_gpu:7005.08336596915 Step 158 | loss:0.00059685786254704 lr:3.588292715785617e-05 tokens_per_second_per_gpu:7111.5588582891205 Step 159 | loss:0.00043432306847535074 lr:3.5214597497797684e-05 tokens_per_second_per_gpu:6906.640956123418 Step 160 | loss:0.0004919036873616278 lr:3.4549150281252636e-05 tokens_per_second_per_gpu:7074.263273256111 Step 161 | loss:0.0023742204066365957 lr:3.388671523847445e-05 tokens_per_second_per_gpu:7100.786438311576 Step 162 | loss:0.00034248692099936306 lr:3.322742151248725e-05 tokens_per_second_per_gpu:6882.851995536166 Step 163 | loss:0.000596148893237114 lr:3.257139763390925e-05 tokens_per_second_per_gpu:6887.264633892879 Step 164 | loss:0.00042822863906621933 lr:3.1918771495895396e-05 tokens_per_second_per_gpu:6954.541766030573 Step 165 | loss:0.0003311867476440966 lr:3.12696703292044e-05 tokens_per_second_per_gpu:6807.594028157807 Step 166 | loss:0.0006024214089848101 lr:3.062422067739485e-05 tokens_per_second_per_gpu:7015.439742692234 Step 167 | loss:0.0006596090970560908 lr:2.9982548372155263e-05 tokens_per_second_per_gpu:7126.494541827477 Step 168 | loss:0.0006894031539559364 lr:2.934477850877292e-05 tokens_per_second_per_gpu:7112.682929237526 Step 169 | loss:0.00038004168891347945 lr:2.8711035421746367e-05 tokens_per_second_per_gpu:6801.082790642841 Step 170 | loss:0.0006471855449490249 lr:2.8081442660546125e-05 tokens_per_second_per_gpu:7014.499422548263 Step 171 | loss:0.0004595274804159999 lr:2.7456122965528475e-05 tokens_per_second_per_gpu:7007.604674932902 Step 172 | loss:0.001023106393404305 lr:2.6835198244006927e-05 tokens_per_second_per_gpu:7093.92881865244 Step 173 | loss:0.0005725087248720229 lr:2.6218789546486234e-05 tokens_per_second_per_gpu:6843.884330915251 Step 174 | loss:0.0004387150111142546 lr:2.560701704306336e-05 tokens_per_second_per_gpu:6980.315109706098 Step 175 | loss:0.0006329233874566853 lr:2.500000000000001e-05 tokens_per_second_per_gpu:7116.311879107516 Step 176 | loss:0.00044436732423491776 lr:2.4397856756471432e-05 tokens_per_second_per_gpu:6880.628316758587 Step 177 | loss:0.0005801497609354556 lr:2.3800704701496053e-05 tokens_per_second_per_gpu:7000.4969834579715 Step 178 | loss:0.0006437235861085355 lr:2.3208660251050158e-05 tokens_per_second_per_gpu:7107.315843745441 Step 179 | loss:0.00044405984226614237 lr:2.2621838825372493e-05 tokens_per_second_per_gpu:7063.24412351279 Step 180 | loss:0.0003296049835626036 lr:2.2040354826462668e-05 tokens_per_second_per_gpu:6802.433180682313 Step 181 | loss:0.00032003154046833515 lr:2.1464321615778422e-05 tokens_per_second_per_gpu:6882.385343246859 Step 182 | loss:0.0005389759899117053 lr:2.0893851492135537e-05 tokens_per_second_per_gpu:7041.8536898010825 Step 183 | loss:0.0005675922730006278 lr:2.0329055669814934e-05 tokens_per_second_per_gpu:7022.94067212219 Step 184 | loss:0.00033082920708693564 lr:1.977004425688126e-05 tokens_per_second_per_gpu:6834.94091911023 Step 185 | loss:0.00029504625126719475 lr:1.9216926233717085e-05 tokens_per_second_per_gpu:6838.87937602258 Step 186 | loss:0.0004192401538603008 lr:1.866980943177699e-05 tokens_per_second_per_gpu:6874.068356536863 Step 187 | loss:0.0005113469087518752 lr:1.8128800512565513e-05 tokens_per_second_per_gpu:7018.458444450405 Step 188 | loss:0.0003360128030180931 lr:1.7594004946843456e-05 tokens_per_second_per_gpu:6803.00800482916 Step 189 | loss:0.0010256447130814195 lr:1.7065526994065973e-05 tokens_per_second_per_gpu:7091.385821470455 Step 190 | loss:0.00032388814724981785 lr:1.6543469682057106e-05 tokens_per_second_per_gpu:6759.067830238384 Step 191 | loss:0.0003387324104551226 lr:1.602793478692419e-05 tokens_per_second_per_gpu:6884.299108603993 Step 192 | loss:0.0006309376331046224 lr:1.551902281321651e-05 tokens_per_second_per_gpu:7141.149678228337 Step 193 | loss:0.00031780378776602447 lr:1.5016832974331724e-05 tokens_per_second_per_gpu:6813.331909196952 Step 194 | loss:0.000532129721250385 lr:1.4521463173173965e-05 tokens_per_second_per_gpu:7013.211817792161 Step 195 | loss:0.00038889056304469705 lr:1.4033009983067452e-05 tokens_per_second_per_gpu:6966.465322304186 Step 196 | loss:0.00032125646248459816 lr:1.3551568628929434e-05 tokens_per_second_per_gpu:6806.83249874059 Step 197 | loss:0.0003870419750455767 lr:1.3077232968705805e-05 tokens_per_second_per_gpu:7015.194301158357 Step 198 | loss:0.0004650031914934516 lr:1.2610095475073414e-05 tokens_per_second_per_gpu:6848.398928690775 Step 199 | loss:0.00048101667198352516 lr:1.2150247217412186e-05 tokens_per_second_per_gpu:7066.199614109938 Step 200 | loss:0.00030778913060203195 lr:1.1697777844051105e-05 tokens_per_second_per_gpu:6842.039758300298 Step 201 | loss:0.00030698918271809816 lr:1.1252775564791024e-05 tokens_per_second_per_gpu:6788.841986942981 Step 202 | loss:0.0004638749815057963 lr:1.0815327133708015e-05 tokens_per_second_per_gpu:7037.795870440856 Step 203 | loss:0.0005949691403657198 lr:1.0385517832240471e-05 tokens_per_second_per_gpu:7033.600937883294 Step 204 | loss:0.0003844074090011418 lr:9.963431452563332e-06 tokens_per_second_per_gpu:6960.097679366252 Step 205 | loss:0.0004969084984622896 lr:9.549150281252633e-06 tokens_per_second_per_gpu:6885.755653404925 Step 206 | loss:0.00047460675705224276 lr:9.142755083243576e-06 tokens_per_second_per_gpu:7032.813594108056 Step 207 | loss:0.00043056943104602396 lr:8.744325086085248e-06 tokens_per_second_per_gpu:7048.187212430326 Step 208 | loss:0.00040919118328019977 lr:8.353937964495029e-06 tokens_per_second_per_gpu:6983.872329466474 Step 209 | loss:0.000647729029878974 lr:7.971669825215788e-06 tokens_per_second_per_gpu:7113.318098152748 Step 210 | loss:0.00041743789915926754 lr:7.597595192178702e-06 tokens_per_second_per_gpu:6852.380821475242 Step 211 | loss:0.0003965847718063742 lr:7.2317869919746705e-06 tokens_per_second_per_gpu:7020.892923841839 Step 212 | loss:0.0005029928288422525 lr:6.874316539637127e-06 tokens_per_second_per_gpu:6850.738597273943 Step 213 | loss:0.0003993400896433741 lr:6.52525352473905e-06 tokens_per_second_per_gpu:7041.427692536272 Step 214 | loss:0.0003851807559840381 lr:6.184665997806832e-06 tokens_per_second_per_gpu:6958.332004980412 Step 215 | loss:0.00037679722299799323 lr:5.852620357053651e-06 tokens_per_second_per_gpu:7008.987106883156 Step 216 | loss:0.0005560445133596659 lr:5.529181335435124e-06 tokens_per_second_per_gpu:7108.996529505505 Step 217 | loss:0.0004068257112521678 lr:5.214411988029355e-06 tokens_per_second_per_gpu:7048.72678327007 Step 218 | loss:0.00042948880582116544 lr:4.908373679744316e-06 tokens_per_second_per_gpu:6875.453704878561 Step 219 | loss:0.0003860412980429828 lr:4.611126073354571e-06 tokens_per_second_per_gpu:6756.730279411705 Step 220 | loss:0.0005670911632478237 lr:4.322727117869951e-06 tokens_per_second_per_gpu:7077.653593406888 Step 221 | loss:0.00043550351983867586 lr:4.043233037238281e-06 tokens_per_second_per_gpu:6827.472452496718 Step 222 | loss:0.0003552791604306549 lr:3.772698319384349e-06 tokens_per_second_per_gpu:7015.860821952089 Step 223 | loss:0.00038456759648397565 lr:3.511175705587433e-06 tokens_per_second_per_gpu:7013.1239168864195 Step 224 | loss:0.00037552512367255986 lr:3.258716180199278e-06 tokens_per_second_per_gpu:7021.0342816795655 Step 225 | loss:0.0006939746090210974 lr:3.0153689607045845e-06 tokens_per_second_per_gpu:7147.37207277239 Step 226 | loss:0.0003304218698758632 lr:2.7811814881259503e-06 tokens_per_second_per_gpu:6840.861592413589 Step 227 | loss:0.00037822945159859955 lr:2.5561994177751737e-06 tokens_per_second_per_gpu:6983.657701999954 Step 228 | loss:0.0003973064012825489 lr:2.340466610352654e-06 tokens_per_second_per_gpu:6759.560344444695 Step 229 | loss:0.0006851706421002746 lr:2.134025123396638e-06 tokens_per_second_per_gpu:7087.96371090323 Step 230 | loss:0.0006889940123073757 lr:1.9369152030840556e-06 tokens_per_second_per_gpu:7088.355448479747 Step 231 | loss:0.00023711643007118255 lr:1.7491752763844293e-06 tokens_per_second_per_gpu:6955.698618409718 Step 232 | loss:0.00024236827448476106 lr:1.5708419435684462e-06 tokens_per_second_per_gpu:6917.742048533692 Step 233 | loss:0.0015999224269762635 lr:1.4019499710726913e-06 tokens_per_second_per_gpu:6854.405218357296 Step 234 | loss:0.00032681747688911855 lr:1.2425322847218368e-06 tokens_per_second_per_gpu:6847.109564255254 Step 235 | loss:0.0003257356001995504 lr:1.0926199633097157e-06 tokens_per_second_per_gpu:6847.462844660527 Step 236 | loss:0.0006124958745203912 lr:9.522422325404235e-07 tokens_per_second_per_gpu:7118.025119623459 Step 237 | loss:0.00037676264764741063 lr:8.214264593307098e-07 tokens_per_second_per_gpu:7010.914469704608 Step 238 | loss:0.00044978337245993316 lr:7.001981464747565e-07 tokens_per_second_per_gpu:6871.220798712625 Step 239 | loss:0.0003326755540911108 lr:5.885809276723608e-07 tokens_per_second_per_gpu:6838.001452060776 Step 240 | loss:0.0003103285562247038 lr:4.865965629214819e-07 tokens_per_second_per_gpu:6842.614784776035 Step 241 | loss:0.00035935320192947984 lr:3.9426493427611177e-07 tokens_per_second_per_gpu:6769.250996839279 Step 242 | loss:0.00030887313187122345 lr:3.1160404197018154e-07 tokens_per_second_per_gpu:6807.417877463088 Step 243 | loss:0.0007364892517216504 lr:2.386300009084408e-07 tokens_per_second_per_gpu:7117.941506656053 Step 244 | loss:0.0004641440464183688 lr:1.753570375247815e-07 tokens_per_second_per_gpu:7043.65477190892 Step 245 | loss:0.0006210881401784718 lr:1.2179748700879012e-07 tokens_per_second_per_gpu:6852.384934124357 Step 246 | loss:0.0004356220888439566 lr:7.796179090094891e-08 tokens_per_second_per_gpu:6768.038382589803 Step 247 | loss:0.0004791610990650952 lr:4.385849505708084e-08 tokens_per_second_per_gpu:6993.109859457661 Step 248 | loss:0.0006747626466676593 lr:1.949424798228239e-08 tokens_per_second_per_gpu:7104.7645717317455 Step 249 | loss:0.00037710845936089754 lr:4.873799534788059e-09 tokens_per_second_per_gpu:6993.003046132695 Step 250 | loss:0.0005932179046794772 lr:0.0 tokens_per_second_per_gpu:7115.818485350633