Step 1 | loss:0.3214961588382721 lr:4.000000000000001e-06 tokens_per_second_per_gpu:3594.3483549137964 Step 2 | loss:0.5330340266227722 lr:8.000000000000001e-06 tokens_per_second_per_gpu:1390.1818049712726 Step 3 | loss:0.29198145866394043 lr:1.2e-05 tokens_per_second_per_gpu:7081.618262844307 Step 4 | loss:0.43005019426345825 lr:1.6000000000000003e-05 tokens_per_second_per_gpu:3661.2699994336945 Step 5 | loss:0.5110501646995544 lr:2e-05 tokens_per_second_per_gpu:7151.551512824823 Step 6 | loss:0.4939457178115845 lr:2.4e-05 tokens_per_second_per_gpu:2378.650657003139 Step 7 | loss:0.40483665466308594 lr:2.8000000000000003e-05 tokens_per_second_per_gpu:6402.289009524379 Step 8 | loss:0.5239858031272888 lr:3.2000000000000005e-05 tokens_per_second_per_gpu:7092.903174817931 Step 9 | loss:0.4325823485851288 lr:3.6e-05 tokens_per_second_per_gpu:7146.975748273666 Step 10 | loss:0.2897239029407501 lr:4e-05 tokens_per_second_per_gpu:7096.272018161872 Step 11 | loss:0.29443660378456116 lr:4.4000000000000006e-05 tokens_per_second_per_gpu:7133.1334966362565 Step 12 | loss:0.370257705450058 lr:4.8e-05 tokens_per_second_per_gpu:7121.480227867628 Step 13 | loss:0.2542576789855957 lr:5.2000000000000004e-05 tokens_per_second_per_gpu:7142.50331526294 Step 14 | loss:0.21866637468338013 lr:5.6000000000000006e-05 tokens_per_second_per_gpu:7095.704452596951 Step 15 | loss:0.19863693416118622 lr:6e-05 tokens_per_second_per_gpu:7124.205863554088 Step 16 | loss:0.1805194467306137 lr:6.400000000000001e-05 tokens_per_second_per_gpu:7141.494500993941 Step 17 | loss:0.127895787358284 lr:6.800000000000001e-05 tokens_per_second_per_gpu:2322.344146078966 Step 18 | loss:0.16514752805233002 lr:7.2e-05 tokens_per_second_per_gpu:7106.778408650539 Step 19 | loss:0.07268558442592621 lr:7.6e-05 tokens_per_second_per_gpu:7107.802476059421 Step 20 | loss:0.0653766319155693 lr:8e-05 tokens_per_second_per_gpu:7136.293470341892 Step 21 | loss:0.06386169046163559 lr:8.4e-05 tokens_per_second_per_gpu:7120.793270821883 Step 22 | loss:0.07126857340335846 lr:8.800000000000001e-05 tokens_per_second_per_gpu:7138.236296802291 Step 23 | loss:0.051759544759988785 lr:9.200000000000001e-05 tokens_per_second_per_gpu:6983.142906286637 Step 24 | loss:0.05076303333044052 lr:9.6e-05 tokens_per_second_per_gpu:7108.128570168865 Step 25 | loss:0.05275893956422806 lr:0.0001 tokens_per_second_per_gpu:3032.977055566302 Step 26 | loss:0.0361633226275444 lr:9.999512620046522e-05 tokens_per_second_per_gpu:7148.676493706225 Step 27 | loss:0.04864358901977539 lr:9.998050575201771e-05 tokens_per_second_per_gpu:5914.75116029403 Step 28 | loss:0.033986952155828476 lr:9.995614150494293e-05 tokens_per_second_per_gpu:7136.591220952046 Step 29 | loss:0.025534963235259056 lr:9.992203820909906e-05 tokens_per_second_per_gpu:7042.223273025534 Step 30 | loss:0.040556397289037704 lr:9.987820251299122e-05 tokens_per_second_per_gpu:7149.011513154317 Step 31 | loss:0.02934034913778305 lr:9.982464296247522e-05 tokens_per_second_per_gpu:7078.938523576819 Step 32 | loss:0.04411907121539116 lr:9.976136999909156e-05 tokens_per_second_per_gpu:7120.191602158542 Step 33 | loss:0.04091024771332741 lr:9.968839595802982e-05 tokens_per_second_per_gpu:6363.964584880051 Step 34 | loss:0.02435337007045746 lr:9.96057350657239e-05 tokens_per_second_per_gpu:7164.5249903799695 Step 35 | loss:0.024645743891596794 lr:9.951340343707852e-05 tokens_per_second_per_gpu:7172.329178165068 Step 36 | loss:0.02853880636394024 lr:9.941141907232765e-05 tokens_per_second_per_gpu:7161.606671625852 Step 37 | loss:0.01912279799580574 lr:9.929980185352526e-05 tokens_per_second_per_gpu:7169.53402013519 Step 38 | loss:0.02017577737569809 lr:9.917857354066931e-05 tokens_per_second_per_gpu:7053.245364284332 Step 39 | loss:0.04465937241911888 lr:9.904775776745958e-05 tokens_per_second_per_gpu:7175.1999601187035 Step 40 | loss:0.03162321820855141 lr:9.890738003669029e-05 tokens_per_second_per_gpu:7045.837072800119 Step 41 | loss:0.03645043447613716 lr:9.875746771527816e-05 tokens_per_second_per_gpu:7139.16325775111 Step 42 | loss:0.008878340013325214 lr:9.859805002892732e-05 tokens_per_second_per_gpu:7153.401062312513 Step 43 | loss:0.038854774087667465 lr:9.842915805643155e-05 tokens_per_second_per_gpu:7093.995450516707 Step 44 | loss:0.01308248471468687 lr:9.825082472361557e-05 tokens_per_second_per_gpu:7106.861748007991 Step 45 | loss:0.019132737070322037 lr:9.806308479691595e-05 tokens_per_second_per_gpu:7167.178044980943 Step 46 | loss:0.015623858198523521 lr:9.786597487660337e-05 tokens_per_second_per_gpu:7098.629042007513 Step 47 | loss:0.010018376633524895 lr:9.765953338964735e-05 tokens_per_second_per_gpu:6391.17084394225 Step 48 | loss:0.019334087148308754 lr:9.744380058222483e-05 tokens_per_second_per_gpu:7127.277968670331 Step 49 | loss:0.0196536835283041 lr:9.721881851187406e-05 tokens_per_second_per_gpu:3174.1973731552876 Step 50 | loss:0.004388618282973766 lr:9.698463103929542e-05 tokens_per_second_per_gpu:7121.966933641705 Step 51 | loss:0.004834826570004225 lr:9.674128381980072e-05 tokens_per_second_per_gpu:7045.794487493226 Step 52 | loss:0.0013942443765699863 lr:9.648882429441257e-05 tokens_per_second_per_gpu:7110.625181916154 Step 53 | loss:0.010880803689360619 lr:9.622730168061567e-05 tokens_per_second_per_gpu:7112.916208157149 Step 54 | loss:0.23427248001098633 lr:9.595676696276172e-05 tokens_per_second_per_gpu:6368.651324757572 Step 55 | loss:0.0009179513435810804 lr:9.567727288213005e-05 tokens_per_second_per_gpu:7052.93579694605 Step 56 | loss:0.0008739550830796361 lr:9.538887392664544e-05 tokens_per_second_per_gpu:5367.01409725602 Step 57 | loss:0.006889927666634321 lr:9.50916263202557e-05 tokens_per_second_per_gpu:7107.493962138421 Step 58 | loss:0.1630222648382187 lr:9.478558801197065e-05 tokens_per_second_per_gpu:7057.2517525156445 Step 59 | loss:0.0048117078840732574 lr:9.447081866456489e-05 tokens_per_second_per_gpu:7081.437030141605 Step 60 | loss:0.016307005658745766 lr:9.414737964294636e-05 tokens_per_second_per_gpu:7118.300368631394 Step 61 | loss:0.00857655517756939 lr:9.381533400219318e-05 tokens_per_second_per_gpu:7141.977523613875 Step 62 | loss:0.002178497612476349 lr:9.347474647526095e-05 tokens_per_second_per_gpu:7107.245889527357 Step 63 | loss:0.00895470380783081 lr:9.312568346036288e-05 tokens_per_second_per_gpu:7009.911236723735 Step 64 | loss:0.000926482432987541 lr:9.276821300802534e-05 tokens_per_second_per_gpu:7093.5172020402515 Step 65 | loss:0.001013862551189959 lr:9.24024048078213e-05 tokens_per_second_per_gpu:7044.884483644873 Step 66 | loss:0.002607440808787942 lr:9.202833017478422e-05 tokens_per_second_per_gpu:7052.039437576213 Step 67 | loss:0.005312749184668064 lr:9.164606203550497e-05 tokens_per_second_per_gpu:7138.983018210351 Step 68 | loss:0.0014834870817139745 lr:9.125567491391476e-05 tokens_per_second_per_gpu:7020.362529854587 Step 69 | loss:0.01221237052232027 lr:9.085724491675642e-05 tokens_per_second_per_gpu:7148.509738105196 Step 70 | loss:0.0030341483652591705 lr:9.045084971874738e-05 tokens_per_second_per_gpu:7153.779081769032 Step 71 | loss:0.00042202547774650156 lr:9.003656854743667e-05 tokens_per_second_per_gpu:7109.287154976311 Step 72 | loss:0.18808768689632416 lr:8.961448216775954e-05 tokens_per_second_per_gpu:1834.292400146575 Step 73 | loss:0.009801657870411873 lr:8.9184672866292e-05 tokens_per_second_per_gpu:7167.170219786018 Step 74 | loss:0.012009918689727783 lr:8.874722443520899e-05 tokens_per_second_per_gpu:7115.338567521795 Step 75 | loss:0.015348431654274464 lr:8.83022221559489e-05 tokens_per_second_per_gpu:7083.921975259006 Step 76 | loss:0.006224790122359991 lr:8.784975278258783e-05 tokens_per_second_per_gpu:7082.596962688719 Step 77 | loss:0.011981501244008541 lr:8.73899045249266e-05 tokens_per_second_per_gpu:1383.8875278254338 Step 78 | loss:0.04659278690814972 lr:8.692276703129421e-05 tokens_per_second_per_gpu:7103.068335408726 Step 79 | loss:0.005729911848902702 lr:8.644843137107059e-05 tokens_per_second_per_gpu:7106.968283652876 Step 80 | loss:0.00460313493385911 lr:8.596699001693255e-05 tokens_per_second_per_gpu:7167.780197725977 Step 81 | loss:0.0029054705519229174 lr:8.547853682682604e-05 tokens_per_second_per_gpu:7145.196870441238 Step 82 | loss:0.01506748516112566 lr:8.498316702566828e-05 tokens_per_second_per_gpu:7096.019600802657 Step 83 | loss:0.0170370414853096 lr:8.44809771867835e-05 tokens_per_second_per_gpu:5864.96769644322 Step 84 | loss:0.0036904411390423775 lr:8.397206521307584e-05 tokens_per_second_per_gpu:7100.436561373847 Step 85 | loss:0.0031084788497537374 lr:8.345653031794292e-05 tokens_per_second_per_gpu:7129.709955090517 Step 86 | loss:0.06680218130350113 lr:8.293447300593402e-05 tokens_per_second_per_gpu:6350.5297673369 Step 87 | loss:0.0025754400994628668 lr:8.240599505315655e-05 tokens_per_second_per_gpu:7113.979064504963 Step 88 | loss:0.003147409064695239 lr:8.18711994874345e-05 tokens_per_second_per_gpu:7097.372434226334 Step 89 | loss:0.0037036645226180553 lr:8.133019056822304e-05 tokens_per_second_per_gpu:7136.547395665124 Step 90 | loss:0.008090498857200146 lr:8.07830737662829e-05 tokens_per_second_per_gpu:6359.786584735908 Step 91 | loss:0.0036573840770870447 lr:8.022995574311876e-05 tokens_per_second_per_gpu:7166.353281930487 Step 92 | loss:0.0025515365414321423 lr:7.967094433018508e-05 tokens_per_second_per_gpu:7033.525638247291 Step 93 | loss:0.0034233182668685913 lr:7.910614850786448e-05 tokens_per_second_per_gpu:7020.415310339935 Step 94 | loss:0.005082640331238508 lr:7.85356783842216e-05 tokens_per_second_per_gpu:7124.956126166894 Step 95 | loss:0.0026254013646394014 lr:7.795964517353735e-05 tokens_per_second_per_gpu:7100.6255681551975 Step 96 | loss:0.0018859135452657938 lr:7.737816117462752e-05 tokens_per_second_per_gpu:7085.395463478941 Step 97 | loss:0.002288545249029994 lr:7.679133974894983e-05 tokens_per_second_per_gpu:7117.890983602216 Step 98 | loss:0.0042329891584813595 lr:7.619929529850397e-05 tokens_per_second_per_gpu:6389.461964224197 Step 99 | loss:0.0006981268525123596 lr:7.560214324352858e-05 tokens_per_second_per_gpu:7041.3082909367295 Step 100 | loss:0.0288221538066864 lr:7.500000000000001e-05 tokens_per_second_per_gpu:7050.499142850432 Step 101 | loss:0.002242885297164321 lr:7.439298295693665e-05 tokens_per_second_per_gpu:7031.450183260521 Step 102 | loss:0.003164506983011961 lr:7.378121045351378e-05 tokens_per_second_per_gpu:6380.216842693459 Step 103 | loss:0.003226869972422719 lr:7.316480175599309e-05 tokens_per_second_per_gpu:7090.019173706589 Step 104 | loss:0.000611752737313509 lr:7.254387703447154e-05 tokens_per_second_per_gpu:7013.571003369912 Step 105 | loss:0.0009656067122705281 lr:7.191855733945387e-05 tokens_per_second_per_gpu:7102.776691515193 Step 106 | loss:0.002983871614560485 lr:7.128896457825364e-05 tokens_per_second_per_gpu:6395.562840518743 Step 107 | loss:0.06724581122398376 lr:7.06552214912271e-05 tokens_per_second_per_gpu:3161.453541188698 Step 108 | loss:0.03883284702897072 lr:7.001745162784477e-05 tokens_per_second_per_gpu:7138.591605463388 Step 109 | loss:0.0015467897756025195 lr:6.937577932260515e-05 tokens_per_second_per_gpu:7117.323709893626 Step 110 | loss:0.00496696075424552 lr:6.873032967079561e-05 tokens_per_second_per_gpu:7121.645278970816 Step 111 | loss:0.0024042653385549784 lr:6.808122850410461e-05 tokens_per_second_per_gpu:6785.559646409428 Step 112 | loss:0.0017714961431920528 lr:6.742860236609077e-05 tokens_per_second_per_gpu:7011.9641469322 Step 113 | loss:0.0036493330262601376 lr:6.677257848751277e-05 tokens_per_second_per_gpu:7140.710215104429 Step 114 | loss:0.028641490265727043 lr:6.611328476152557e-05 tokens_per_second_per_gpu:7184.8935004454925 Step 115 | loss:0.002954833209514618 lr:6.545084971874738e-05 tokens_per_second_per_gpu:7115.1855057108805 Step 116 | loss:0.03693821653723717 lr:6.478540250220234e-05 tokens_per_second_per_gpu:7143.928330275201 Step 117 | loss:0.004886779468506575 lr:6.411707284214384e-05 tokens_per_second_per_gpu:7103.785094222471 Step 118 | loss:0.003835114650428295 lr:6.344599103076329e-05 tokens_per_second_per_gpu:7104.15863260821 Step 119 | loss:0.002009354764595628 lr:6.277228789678953e-05 tokens_per_second_per_gpu:7089.290380472889 Step 120 | loss:0.003304028883576393 lr:6.209609477998338e-05 tokens_per_second_per_gpu:7060.243801414819 Step 121 | loss:0.001922119758091867 lr:6.141754350553279e-05 tokens_per_second_per_gpu:7163.345391499457 Step 122 | loss:0.0035920387599617243 lr:6.073676635835317e-05 tokens_per_second_per_gpu:7103.333535084545 Step 123 | loss:0.0019547122064977884 lr:6.005389605729824e-05 tokens_per_second_per_gpu:7091.30090776062 Step 124 | loss:0.002472941530868411 lr:5.9369065729286245e-05 tokens_per_second_per_gpu:7146.755771018813 Step 125 | loss:0.0009650253341533244 lr:5.868240888334653e-05 tokens_per_second_per_gpu:7054.133006971595 Step 126 | loss:0.0031777757685631514 lr:5.799405938459175e-05 tokens_per_second_per_gpu:7125.715494782513 Step 127 | loss:0.0006818406982347369 lr:5.730415142812059e-05 tokens_per_second_per_gpu:7035.937367918513 Step 128 | loss:0.002223866991698742 lr:5.661281951285613e-05 tokens_per_second_per_gpu:7108.648772616149 Step 129 | loss:0.0007463679648935795 lr:5.5920198415325064e-05 tokens_per_second_per_gpu:7044.602437460188 Step 130 | loss:0.003160986816510558 lr:5.522642316338268e-05 tokens_per_second_per_gpu:6361.248064954927 Step 131 | loss:0.009143450297415257 lr:5.453162900988902e-05 tokens_per_second_per_gpu:6426.089420646215 Step 132 | loss:0.0018711427692323923 lr:5.383595140634093e-05 tokens_per_second_per_gpu:7143.675638727226 Step 133 | loss:0.0013067458057776093 lr:5.313952597646568e-05 tokens_per_second_per_gpu:7066.66555765819 Step 134 | loss:0.0008423748076893389 lr:5.244248848978067e-05 tokens_per_second_per_gpu:7022.689851609807 Step 135 | loss:0.0009916579583659768 lr:5.174497483512506e-05 tokens_per_second_per_gpu:7107.4389907978275 Step 136 | loss:0.0007614760543219745 lr:5.104712099416785e-05 tokens_per_second_per_gpu:7120.670252009496 Step 137 | loss:0.001821639365516603 lr:5.034906301489808e-05 tokens_per_second_per_gpu:7083.806710024462 Step 138 | loss:0.000887828238774091 lr:4.965093698510193e-05 tokens_per_second_per_gpu:7026.233051285368 Step 139 | loss:0.0008487945306114852 lr:4.895287900583216e-05 tokens_per_second_per_gpu:7003.075808573581 Step 140 | loss:0.0009150058613158762 lr:4.825502516487497e-05 tokens_per_second_per_gpu:5808.88343656243 Step 141 | loss:0.000990029308013618 lr:4.755751151021934e-05 tokens_per_second_per_gpu:7080.895065996811 Step 142 | loss:0.0009489059448242188 lr:4.6860474023534335e-05 tokens_per_second_per_gpu:7138.431100641158 Step 143 | loss:0.0007239338592626154 lr:4.616404859365907e-05 tokens_per_second_per_gpu:7021.512535478398 Step 144 | loss:0.0017398326890543103 lr:4.5468370990111006e-05 tokens_per_second_per_gpu:7085.514302493882 Step 145 | loss:0.0014178932178765535 lr:4.477357683661734e-05 tokens_per_second_per_gpu:7075.455883335338 Step 146 | loss:0.0010728067718446255 lr:4.407980158467495e-05 tokens_per_second_per_gpu:7106.048382097006 Step 147 | loss:0.0012608059914782643 lr:4.3387180487143876e-05 tokens_per_second_per_gpu:7087.369621431439 Step 148 | loss:0.000860698230098933 lr:4.269584857187943e-05 tokens_per_second_per_gpu:7063.349471708702 Step 149 | loss:0.0007498382474295795 lr:4.2005940615408264e-05 tokens_per_second_per_gpu:7151.591862799349 Step 150 | loss:0.0006709772278554738 lr:4.131759111665349e-05 tokens_per_second_per_gpu:7044.222507523036 Step 151 | loss:0.0009396231034770608 lr:4.063093427071376e-05 tokens_per_second_per_gpu:7046.613044160984 Step 152 | loss:0.0005544096929952502 lr:3.9946103942701777e-05 tokens_per_second_per_gpu:7167.591966119606 Step 153 | loss:0.032708778977394104 lr:3.926323364164684e-05 tokens_per_second_per_gpu:7045.028589414886 Step 154 | loss:0.0009358657407574356 lr:3.858245649446721e-05 tokens_per_second_per_gpu:7104.680033040125 Step 155 | loss:0.000718667812179774 lr:3.790390522001662e-05 tokens_per_second_per_gpu:7141.112781418297 Step 156 | loss:0.0013625934952870011 lr:3.7227712103210486e-05 tokens_per_second_per_gpu:6376.334152716879 Step 157 | loss:0.0007285962346941233 lr:3.655400896923672e-05 tokens_per_second_per_gpu:7054.39512646273 Step 158 | loss:0.0010063850786536932 lr:3.588292715785617e-05 tokens_per_second_per_gpu:7115.05654521711 Step 159 | loss:0.0008395436452701688 lr:3.5214597497797684e-05 tokens_per_second_per_gpu:7128.016381903246 Step 160 | loss:0.0006124123465269804 lr:3.4549150281252636e-05 tokens_per_second_per_gpu:7102.32049930989 Step 161 | loss:0.0014889788581058383 lr:3.388671523847445e-05 tokens_per_second_per_gpu:7060.253347021968 Step 162 | loss:0.0009626236860640347 lr:3.322742151248725e-05 tokens_per_second_per_gpu:7052.643288064196 Step 163 | loss:0.0007306714542210102 lr:3.257139763390925e-05 tokens_per_second_per_gpu:7169.614137106872 Step 164 | loss:0.001040013856254518 lr:3.1918771495895396e-05 tokens_per_second_per_gpu:7095.579518619618 Step 165 | loss:0.0008000527741387486 lr:3.12696703292044e-05 tokens_per_second_per_gpu:7161.41872833238 Step 166 | loss:0.0004885185044258833 lr:3.062422067739485e-05 tokens_per_second_per_gpu:7113.030092902556 Step 167 | loss:0.0009236372425220907 lr:2.9982548372155263e-05 tokens_per_second_per_gpu:7068.134736902577 Step 168 | loss:0.00048550148494541645 lr:2.934477850877292e-05 tokens_per_second_per_gpu:7060.998096441715 Step 169 | loss:0.0007330997032113373 lr:2.8711035421746367e-05 tokens_per_second_per_gpu:5902.825726111604 Step 170 | loss:0.0006374756922014058 lr:2.8081442660546125e-05 tokens_per_second_per_gpu:7108.530716662601 Step 171 | loss:0.0011957907117903233 lr:2.7456122965528475e-05 tokens_per_second_per_gpu:6387.01199103303 Step 172 | loss:0.0007582813850603998 lr:2.6835198244006927e-05 tokens_per_second_per_gpu:7038.401235537533 Step 173 | loss:0.0013418789021670818 lr:2.6218789546486234e-05 tokens_per_second_per_gpu:7115.496201048929 Step 174 | loss:0.000586264650337398 lr:2.560701704306336e-05 tokens_per_second_per_gpu:7121.520413812484 Step 175 | loss:0.0005392826278693974 lr:2.500000000000001e-05 tokens_per_second_per_gpu:7163.258290458326 Step 176 | loss:0.0012629322009161115 lr:2.4397856756471432e-05 tokens_per_second_per_gpu:7128.360910588774 Step 177 | loss:0.0009241409716196358 lr:2.3800704701496053e-05 tokens_per_second_per_gpu:7161.029650630834 Step 178 | loss:0.0019173137843608856 lr:2.3208660251050158e-05 tokens_per_second_per_gpu:6379.805241620532 Step 179 | loss:0.0007358559523709118 lr:2.2621838825372493e-05 tokens_per_second_per_gpu:7130.9912255234085 Step 180 | loss:0.04418123885989189 lr:2.2040354826462668e-05 tokens_per_second_per_gpu:7177.214648510552 Step 181 | loss:0.0004942835657857358 lr:2.1464321615778422e-05 tokens_per_second_per_gpu:7167.847844933443 Step 182 | loss:0.0012286418350413442 lr:2.0893851492135537e-05 tokens_per_second_per_gpu:7038.2985496060255 Step 183 | loss:0.0016230872133746743 lr:2.0329055669814934e-05 tokens_per_second_per_gpu:6402.763150593665 Step 184 | loss:0.0011519602267071605 lr:1.977004425688126e-05 tokens_per_second_per_gpu:7148.8540585480105 Step 185 | loss:0.000812906539067626 lr:1.9216926233717085e-05 tokens_per_second_per_gpu:7173.455045949587 Step 186 | loss:0.001370549900457263 lr:1.866980943177699e-05 tokens_per_second_per_gpu:6375.763183135106 Step 187 | loss:0.0005061246338300407 lr:1.8128800512565513e-05 tokens_per_second_per_gpu:7167.316722045516 Step 188 | loss:0.0009212581207975745 lr:1.7594004946843456e-05 tokens_per_second_per_gpu:7157.246148008922 Step 189 | loss:0.00047937125782482326 lr:1.7065526994065973e-05 tokens_per_second_per_gpu:7156.500643033193 Step 190 | loss:0.000992301502265036 lr:1.6543469682057106e-05 tokens_per_second_per_gpu:7042.225068322519 Step 191 | loss:0.0005489535396918654 lr:1.602793478692419e-05 tokens_per_second_per_gpu:7054.242285875433 Step 192 | loss:0.0008266863296739757 lr:1.551902281321651e-05 tokens_per_second_per_gpu:6358.321847811751 Step 193 | loss:0.03574501723051071 lr:1.5016832974331724e-05 tokens_per_second_per_gpu:7229.444675457767 Step 194 | loss:0.0008455842034891248 lr:1.4521463173173965e-05 tokens_per_second_per_gpu:7049.420318946458 Step 195 | loss:0.0007342249737121165 lr:1.4033009983067452e-05 tokens_per_second_per_gpu:7166.247511911766 Step 196 | loss:0.0013816548744216561 lr:1.3551568628929434e-05 tokens_per_second_per_gpu:6404.409102594694 Step 197 | loss:0.0006986480439081788 lr:1.3077232968705805e-05 tokens_per_second_per_gpu:7080.604629928312 Step 198 | loss:0.000581794127356261 lr:1.2610095475073414e-05 tokens_per_second_per_gpu:6766.7840184448 Step 199 | loss:0.0007675242959521711 lr:1.2150247217412186e-05 tokens_per_second_per_gpu:7110.640831372472 Step 200 | loss:0.001319938455708325 lr:1.1697777844051105e-05 tokens_per_second_per_gpu:7088.811529613536 Step 201 | loss:0.0011387454578652978 lr:1.1252775564791024e-05 tokens_per_second_per_gpu:6418.050600616415 Step 202 | loss:0.0008899842505343258 lr:1.0815327133708015e-05 tokens_per_second_per_gpu:7138.637338743455 Step 203 | loss:0.0007275626994669437 lr:1.0385517832240471e-05 tokens_per_second_per_gpu:7111.838069485369 Step 204 | loss:0.0011579848360270262 lr:9.963431452563332e-06 tokens_per_second_per_gpu:7145.518764521527 Step 205 | loss:0.0008033339981921017 lr:9.549150281252633e-06 tokens_per_second_per_gpu:6379.691993814925 Step 206 | loss:0.0008275994914583862 lr:9.142755083243576e-06 tokens_per_second_per_gpu:7128.0776229452285 Step 207 | loss:0.0009921449236571789 lr:8.744325086085248e-06 tokens_per_second_per_gpu:7118.1047892220495 Step 208 | loss:0.031808458268642426 lr:8.353937964495029e-06 tokens_per_second_per_gpu:7139.575851431101 Step 209 | loss:0.001241054618731141 lr:7.971669825215788e-06 tokens_per_second_per_gpu:7139.140406590769 Step 210 | loss:0.0012293203035369515 lr:7.597595192178702e-06 tokens_per_second_per_gpu:7036.760814049174 Step 211 | loss:0.04787912964820862 lr:7.2317869919746705e-06 tokens_per_second_per_gpu:7133.271635439511 Step 212 | loss:0.0003539244644343853 lr:6.874316539637127e-06 tokens_per_second_per_gpu:7051.374495372112 Step 213 | loss:0.0015474612591788173 lr:6.52525352473905e-06 tokens_per_second_per_gpu:6424.759916547957 Step 214 | loss:0.0011304545914754272 lr:6.184665997806832e-06 tokens_per_second_per_gpu:7141.972956798824 Step 215 | loss:0.0013133561005815864 lr:5.852620357053651e-06 tokens_per_second_per_gpu:6396.757766884379 Step 216 | loss:0.0016908994875848293 lr:5.529181335435124e-06 tokens_per_second_per_gpu:7138.620629694516 Step 217 | loss:0.0010772993555292487 lr:5.214411988029355e-06 tokens_per_second_per_gpu:6386.239679899351 Step 218 | loss:0.0010760911973193288 lr:4.908373679744316e-06 tokens_per_second_per_gpu:7142.111254192655 Step 219 | loss:0.0005634138360619545 lr:4.611126073354571e-06 tokens_per_second_per_gpu:7173.746053967821 Step 220 | loss:0.0008623565663583577 lr:4.322727117869951e-06 tokens_per_second_per_gpu:6384.20363087924 Step 221 | loss:0.000619406986515969 lr:4.043233037238281e-06 tokens_per_second_per_gpu:7132.222624831104 Step 222 | loss:0.0009301500977016985 lr:3.772698319384349e-06 tokens_per_second_per_gpu:7145.0294336973975 Step 223 | loss:0.07212650030851364 lr:3.511175705587433e-06 tokens_per_second_per_gpu:7087.949096855153 Step 224 | loss:0.0005748933763243258 lr:3.258716180199278e-06 tokens_per_second_per_gpu:7100.436563906037 Step 225 | loss:0.0007549470756202936 lr:3.0153689607045845e-06 tokens_per_second_per_gpu:7088.442318753626 Step 226 | loss:0.0012309304438531399 lr:2.7811814881259503e-06 tokens_per_second_per_gpu:7048.577821577578 Step 227 | loss:0.0005027973675169051 lr:2.5561994177751737e-06 tokens_per_second_per_gpu:6785.809675747135 Step 228 | loss:0.0013977212365716696 lr:2.340466610352654e-06 tokens_per_second_per_gpu:7107.073849790829 Step 229 | loss:0.09466876834630966 lr:2.134025123396638e-06 tokens_per_second_per_gpu:7132.553644791337 Step 230 | loss:0.000421493430621922 lr:1.9369152030840556e-06 tokens_per_second_per_gpu:7121.945994940145 Step 231 | loss:0.0007958764908835292 lr:1.7491752763844293e-06 tokens_per_second_per_gpu:7160.592810859998 Step 232 | loss:0.0007874317234382033 lr:1.5708419435684462e-06 tokens_per_second_per_gpu:7150.2828809349585 Step 233 | loss:0.0016460687620565295 lr:1.4019499710726913e-06 tokens_per_second_per_gpu:7117.548448176717 Step 234 | loss:0.028731944039463997 lr:1.2425322847218368e-06 tokens_per_second_per_gpu:7076.875746264372 Step 235 | loss:0.000897458172403276 lr:1.0926199633097157e-06 tokens_per_second_per_gpu:7034.054921660219 Step 236 | loss:0.0012975538847967982 lr:9.522422325404235e-07 tokens_per_second_per_gpu:7117.188512091801 Step 237 | loss:0.0008466275176033378 lr:8.214264593307098e-07 tokens_per_second_per_gpu:7078.068988432411 Step 238 | loss:0.0007988933939486742 lr:7.001981464747565e-07 tokens_per_second_per_gpu:7164.710486455696 Step 239 | loss:0.0007170048193074763 lr:5.885809276723608e-07 tokens_per_second_per_gpu:7086.796647097288 Step 240 | loss:0.0007392283878289163 lr:4.865965629214819e-07 tokens_per_second_per_gpu:7036.426995819439 Step 241 | loss:0.0013649614993482828 lr:3.9426493427611177e-07 tokens_per_second_per_gpu:7118.904699312121 Step 242 | loss:0.0007174204220063984 lr:3.1160404197018154e-07 tokens_per_second_per_gpu:7132.685842547171 Step 243 | loss:0.07699286937713623 lr:2.386300009084408e-07 tokens_per_second_per_gpu:7160.626586510428 Step 244 | loss:0.0007208415190689266 lr:1.753570375247815e-07 tokens_per_second_per_gpu:7048.3590423601045 Step 245 | loss:0.0012109825620427728 lr:1.2179748700879012e-07 tokens_per_second_per_gpu:7133.2677856977125 Step 246 | loss:0.00045133952517062426 lr:7.796179090094891e-08 tokens_per_second_per_gpu:7053.0732998925005 Step 247 | loss:0.0003687079588416964 lr:4.385849505708084e-08 tokens_per_second_per_gpu:7118.672578818216 Step 248 | loss:0.0007964439573697746 lr:1.949424798228239e-08 tokens_per_second_per_gpu:7098.20056938414 Step 249 | loss:0.0007312153466045856 lr:4.873799534788059e-09 tokens_per_second_per_gpu:6975.727102927508 Step 250 | loss:0.0015788470627740026 lr:0.0 tokens_per_second_per_gpu:7176.622184945097