Step 1 | loss:0.08306955546140671 lr:4.000000000000001e-06 tokens_per_second_per_gpu:4074.9394488397566 Step 2 | loss:0.08738730847835541 lr:8.000000000000001e-06 tokens_per_second_per_gpu:7091.510769512166 Step 3 | loss:0.12423447519540787 lr:1.2e-05 tokens_per_second_per_gpu:7067.099664606334 Step 4 | loss:0.09388065338134766 lr:1.6000000000000003e-05 tokens_per_second_per_gpu:3605.438095360133 Step 5 | loss:0.09828977286815643 lr:2e-05 tokens_per_second_per_gpu:7047.81769366603 Step 6 | loss:0.10141285508871078 lr:2.4e-05 tokens_per_second_per_gpu:7048.346873633684 Step 7 | loss:0.08292747288942337 lr:2.8000000000000003e-05 tokens_per_second_per_gpu:7096.894243121604 Step 8 | loss:0.08057202398777008 lr:3.2000000000000005e-05 tokens_per_second_per_gpu:7072.097329098864 Step 9 | loss:0.07386106997728348 lr:3.6e-05 tokens_per_second_per_gpu:7092.088713678109 Step 10 | loss:0.14966052770614624 lr:4e-05 tokens_per_second_per_gpu:2334.2291884749375 Step 11 | loss:0.09934940934181213 lr:4.4000000000000006e-05 tokens_per_second_per_gpu:3575.0818051295178 Step 12 | loss:0.08854607492685318 lr:4.8e-05 tokens_per_second_per_gpu:7032.5249887354485 Step 13 | loss:0.1369917094707489 lr:5.2000000000000004e-05 tokens_per_second_per_gpu:2764.5561074938128 Step 14 | loss:0.13063909113407135 lr:5.6000000000000006e-05 tokens_per_second_per_gpu:7092.83641701798 Step 15 | loss:0.06625012308359146 lr:6e-05 tokens_per_second_per_gpu:7105.901732946144 Step 16 | loss:0.1354994922876358 lr:6.400000000000001e-05 tokens_per_second_per_gpu:2805.4260228334174 Step 17 | loss:0.05185336247086525 lr:6.800000000000001e-05 tokens_per_second_per_gpu:7045.346594122187 Step 18 | loss:0.12278998643159866 lr:7.2e-05 tokens_per_second_per_gpu:2332.886142959698 Step 19 | loss:0.05108056962490082 lr:7.6e-05 tokens_per_second_per_gpu:7179.829418359617 Step 20 | loss:0.06817129999399185 lr:8e-05 tokens_per_second_per_gpu:3649.047646608188 Step 21 | loss:0.10004515200853348 lr:8.4e-05 tokens_per_second_per_gpu:7082.001759201794 Step 22 | loss:0.028801823034882545 lr:8.800000000000001e-05 tokens_per_second_per_gpu:7020.761810963064 Step 23 | loss:0.02466510236263275 lr:9.200000000000001e-05 tokens_per_second_per_gpu:7075.057992889289 Step 24 | loss:0.04375017061829567 lr:9.6e-05 tokens_per_second_per_gpu:7110.705794576095 Step 25 | loss:0.06549160182476044 lr:0.0001 tokens_per_second_per_gpu:7092.842531860159 Step 26 | loss:0.032703738659620285 lr:9.999512620046522e-05 tokens_per_second_per_gpu:7100.478225577434 Step 27 | loss:0.048237524926662445 lr:9.998050575201771e-05 tokens_per_second_per_gpu:1532.5748937622652 Step 28 | loss:0.027882128953933716 lr:9.995614150494293e-05 tokens_per_second_per_gpu:7148.0020182936105 Step 29 | loss:0.15793168544769287 lr:9.992203820909906e-05 tokens_per_second_per_gpu:6827.9740696469835 Step 30 | loss:0.13653047382831573 lr:9.987820251299122e-05 tokens_per_second_per_gpu:7136.3591429371245 Step 31 | loss:0.032641638070344925 lr:9.982464296247522e-05 tokens_per_second_per_gpu:6775.487898099672 Step 32 | loss:0.013110242784023285 lr:9.976136999909156e-05 tokens_per_second_per_gpu:7028.501045387356 Step 33 | loss:0.01883864589035511 lr:9.968839595802982e-05 tokens_per_second_per_gpu:7101.882867255467 Step 34 | loss:0.01696568913757801 lr:9.96057350657239e-05 tokens_per_second_per_gpu:7079.97607031648 Step 35 | loss:0.013057666830718517 lr:9.951340343707852e-05 tokens_per_second_per_gpu:6967.75734771439 Step 36 | loss:0.03596499562263489 lr:9.941141907232765e-05 tokens_per_second_per_gpu:7022.302441878986 Step 37 | loss:0.014112807810306549 lr:9.929980185352526e-05 tokens_per_second_per_gpu:7088.819961505947 Step 38 | loss:0.01363561674952507 lr:9.917857354066931e-05 tokens_per_second_per_gpu:7067.357850836175 Step 39 | loss:0.0502048060297966 lr:9.904775776745958e-05 tokens_per_second_per_gpu:7109.564285441161 Step 40 | loss:0.006524371448904276 lr:9.890738003669029e-05 tokens_per_second_per_gpu:7101.430699980151 Step 41 | loss:0.020542368292808533 lr:9.875746771527816e-05 tokens_per_second_per_gpu:7033.113304933 Step 42 | loss:0.021362179890275 lr:9.859805002892732e-05 tokens_per_second_per_gpu:2307.05468278136 Step 43 | loss:0.012677213177084923 lr:9.842915805643155e-05 tokens_per_second_per_gpu:7084.33994492294 Step 44 | loss:0.012273521162569523 lr:9.825082472361557e-05 tokens_per_second_per_gpu:7027.843479637418 Step 45 | loss:0.10479362308979034 lr:9.806308479691595e-05 tokens_per_second_per_gpu:6776.379662755347 Step 46 | loss:0.007627143990248442 lr:9.786597487660337e-05 tokens_per_second_per_gpu:7045.128111219926 Step 47 | loss:0.007085357792675495 lr:9.765953338964735e-05 tokens_per_second_per_gpu:7098.221352377205 Step 48 | loss:0.0030956317204982042 lr:9.744380058222483e-05 tokens_per_second_per_gpu:7055.233170975742 Step 49 | loss:0.01329227164387703 lr:9.721881851187406e-05 tokens_per_second_per_gpu:3563.555164484798 Step 50 | loss:0.0038517832290381193 lr:9.698463103929542e-05 tokens_per_second_per_gpu:7050.392423319725 Step 51 | loss:0.01506090722978115 lr:9.674128381980072e-05 tokens_per_second_per_gpu:7083.640573544164 Step 52 | loss:0.011021138168871403 lr:9.648882429441257e-05 tokens_per_second_per_gpu:7101.113062444753 Step 53 | loss:0.007797445170581341 lr:9.622730168061567e-05 tokens_per_second_per_gpu:7104.846247172923 Step 54 | loss:0.023812778294086456 lr:9.595676696276172e-05 tokens_per_second_per_gpu:6782.568930226049 Step 55 | loss:0.00946661178022623 lr:9.567727288213005e-05 tokens_per_second_per_gpu:7068.51550376207 Step 56 | loss:0.04945222660899162 lr:9.538887392664544e-05 tokens_per_second_per_gpu:4641.131725896435 Step 57 | loss:0.012027818709611893 lr:9.50916263202557e-05 tokens_per_second_per_gpu:7075.4878961648665 Step 58 | loss:0.005555412732064724 lr:9.478558801197065e-05 tokens_per_second_per_gpu:7055.725470241194 Step 59 | loss:0.009016940370202065 lr:9.447081866456489e-05 tokens_per_second_per_gpu:7089.757091728923 Step 60 | loss:0.053401242941617966 lr:9.414737964294636e-05 tokens_per_second_per_gpu:6757.720803828946 Step 61 | loss:0.01680516079068184 lr:9.381533400219318e-05 tokens_per_second_per_gpu:1361.525297371395 Step 62 | loss:0.0013088873820379376 lr:9.347474647526095e-05 tokens_per_second_per_gpu:7107.973388054621 Step 63 | loss:0.001833366579376161 lr:9.312568346036288e-05 tokens_per_second_per_gpu:7048.961339116082 Step 64 | loss:0.011651388369500637 lr:9.276821300802534e-05 tokens_per_second_per_gpu:2231.981317361645 Step 65 | loss:0.01630333997309208 lr:9.24024048078213e-05 tokens_per_second_per_gpu:6804.865631436417 Step 66 | loss:0.006205468904227018 lr:9.202833017478422e-05 tokens_per_second_per_gpu:6984.09762906386 Step 67 | loss:0.004846521653234959 lr:9.164606203550497e-05 tokens_per_second_per_gpu:7085.2109930583 Step 68 | loss:0.007411023136228323 lr:9.125567491391476e-05 tokens_per_second_per_gpu:7073.313692234274 Step 69 | loss:0.007251059170812368 lr:9.085724491675642e-05 tokens_per_second_per_gpu:7051.756341232203 Step 70 | loss:0.012852717190980911 lr:9.045084971874738e-05 tokens_per_second_per_gpu:7088.058760100656 Step 71 | loss:0.005520842969417572 lr:9.003656854743667e-05 tokens_per_second_per_gpu:7019.291922307649 Step 72 | loss:0.020323706790804863 lr:8.961448216775954e-05 tokens_per_second_per_gpu:1383.4987944371805 Step 73 | loss:0.0049658408388495445 lr:8.9184672866292e-05 tokens_per_second_per_gpu:7033.956601588058 Step 74 | loss:0.007142261136323214 lr:8.874722443520899e-05 tokens_per_second_per_gpu:7013.416259028715 Step 75 | loss:0.02031249925494194 lr:8.83022221559489e-05 tokens_per_second_per_gpu:6800.04821381723 Step 76 | loss:0.0035611328203231096 lr:8.784975278258783e-05 tokens_per_second_per_gpu:7131.256085030039 Step 77 | loss:0.0036301363725215197 lr:8.73899045249266e-05 tokens_per_second_per_gpu:7101.68182825781 Step 78 | loss:0.008742338977754116 lr:8.692276703129421e-05 tokens_per_second_per_gpu:7113.893488874398 Step 79 | loss:0.002935765776783228 lr:8.644843137107059e-05 tokens_per_second_per_gpu:7123.291565657171 Step 80 | loss:0.0014299419708549976 lr:8.596699001693255e-05 tokens_per_second_per_gpu:7065.561940710715 Step 81 | loss:0.004565298091620207 lr:8.547853682682604e-05 tokens_per_second_per_gpu:7111.008787999741 Step 82 | loss:0.007290980778634548 lr:8.498316702566828e-05 tokens_per_second_per_gpu:7046.404655033322 Step 83 | loss:0.0014238412259146571 lr:8.44809771867835e-05 tokens_per_second_per_gpu:6967.131040265742 Step 84 | loss:0.008721168152987957 lr:8.397206521307584e-05 tokens_per_second_per_gpu:7087.215162607797 Step 85 | loss:0.000827540410682559 lr:8.345653031794292e-05 tokens_per_second_per_gpu:7107.987005979737 Step 86 | loss:0.013922826386988163 lr:8.293447300593402e-05 tokens_per_second_per_gpu:2156.6264182897758 Step 87 | loss:0.007480362430214882 lr:8.240599505315655e-05 tokens_per_second_per_gpu:7115.504058219385 Step 88 | loss:0.0028591298032552004 lr:8.18711994874345e-05 tokens_per_second_per_gpu:6805.258740950157 Step 89 | loss:0.006332575809210539 lr:8.133019056822304e-05 tokens_per_second_per_gpu:7017.070042103497 Step 90 | loss:0.006402829196304083 lr:8.07830737662829e-05 tokens_per_second_per_gpu:7137.837844356726 Step 91 | loss:0.001602055737748742 lr:8.022995574311876e-05 tokens_per_second_per_gpu:7117.199591071616 Step 92 | loss:0.004749419167637825 lr:7.967094433018508e-05 tokens_per_second_per_gpu:7091.549603600123 Step 93 | loss:0.0053667048923671246 lr:7.910614850786448e-05 tokens_per_second_per_gpu:2340.516343811871 Step 94 | loss:0.002433979883790016 lr:7.85356783842216e-05 tokens_per_second_per_gpu:7028.444252682041 Step 95 | loss:0.007094410713762045 lr:7.795964517353735e-05 tokens_per_second_per_gpu:7074.97711441302 Step 96 | loss:0.0032169013284146786 lr:7.737816117462752e-05 tokens_per_second_per_gpu:3632.421801313573 Step 97 | loss:0.0030325925908982754 lr:7.679133974894983e-05 tokens_per_second_per_gpu:7034.290534976117 Step 98 | loss:0.003934985492378473 lr:7.619929529850397e-05 tokens_per_second_per_gpu:6781.078977544837 Step 99 | loss:0.0030845494475215673 lr:7.560214324352858e-05 tokens_per_second_per_gpu:7083.583662279534 Step 100 | loss:0.003427190240472555 lr:7.500000000000001e-05 tokens_per_second_per_gpu:7033.611084332917 Step 101 | loss:0.0024424113798886538 lr:7.439298295693665e-05 tokens_per_second_per_gpu:7060.698593758902 Step 102 | loss:0.0024672928266227245 lr:7.378121045351378e-05 tokens_per_second_per_gpu:7035.018057985739 Step 103 | loss:0.0020594215020537376 lr:7.316480175599309e-05 tokens_per_second_per_gpu:7090.2010573069865 Step 104 | loss:0.0016850067768245935 lr:7.254387703447154e-05 tokens_per_second_per_gpu:7088.906868915007 Step 105 | loss:0.004630251321941614 lr:7.191855733945387e-05 tokens_per_second_per_gpu:6974.954581183531 Step 106 | loss:0.0013717099791392684 lr:7.128896457825364e-05 tokens_per_second_per_gpu:7060.7087322058005 Step 107 | loss:0.004377284552901983 lr:7.06552214912271e-05 tokens_per_second_per_gpu:7068.348474678991 Step 108 | loss:0.0024556603748351336 lr:7.001745162784477e-05 tokens_per_second_per_gpu:7093.940998574138 Step 109 | loss:0.002266139257699251 lr:6.937577932260515e-05 tokens_per_second_per_gpu:7095.466636875113 Step 110 | loss:0.0020060797687619925 lr:6.873032967079561e-05 tokens_per_second_per_gpu:7074.190453071778 Step 111 | loss:0.001826161053031683 lr:6.808122850410461e-05 tokens_per_second_per_gpu:6178.392871294849 Step 112 | loss:0.0023418734781444073 lr:6.742860236609077e-05 tokens_per_second_per_gpu:7142.712671410775 Step 113 | loss:0.012266136705875397 lr:6.677257848751277e-05 tokens_per_second_per_gpu:7116.583677333169 Step 114 | loss:0.0037689311429858208 lr:6.611328476152557e-05 tokens_per_second_per_gpu:7099.969914356306 Step 115 | loss:0.0009142067283391953 lr:6.545084971874738e-05 tokens_per_second_per_gpu:7067.416126616286 Step 116 | loss:0.002101685618981719 lr:6.478540250220234e-05 tokens_per_second_per_gpu:7077.317448055894 Step 117 | loss:0.0026332733687013388 lr:6.411707284214384e-05 tokens_per_second_per_gpu:7101.140245798473 Step 118 | loss:0.003353646956384182 lr:6.344599103076329e-05 tokens_per_second_per_gpu:7035.725975730565 Step 119 | loss:0.004854643251746893 lr:6.277228789678953e-05 tokens_per_second_per_gpu:7127.74441700687 Step 120 | loss:0.004803529940545559 lr:6.209609477998338e-05 tokens_per_second_per_gpu:6999.484984024637 Step 121 | loss:0.0015108278021216393 lr:6.141754350553279e-05 tokens_per_second_per_gpu:7069.841630387863 Step 122 | loss:0.0027514463290572166 lr:6.073676635835317e-05 tokens_per_second_per_gpu:7113.67084220057 Step 123 | loss:0.004002106375992298 lr:6.005389605729824e-05 tokens_per_second_per_gpu:7034.690801194263 Step 124 | loss:0.0031866503413766623 lr:5.9369065729286245e-05 tokens_per_second_per_gpu:7118.638061109239 Step 125 | loss:0.0033981571905314922 lr:5.868240888334653e-05 tokens_per_second_per_gpu:7164.655523378125 Step 126 | loss:0.006798313930630684 lr:5.799405938459175e-05 tokens_per_second_per_gpu:6785.47080078079 Step 127 | loss:0.0013709062477573752 lr:5.730415142812059e-05 tokens_per_second_per_gpu:7114.4907674081205 Step 128 | loss:0.0031615360639989376 lr:5.661281951285613e-05 tokens_per_second_per_gpu:7072.738712719659 Step 129 | loss:0.003979001194238663 lr:5.5920198415325064e-05 tokens_per_second_per_gpu:7066.142386105441 Step 130 | loss:0.004991436842828989 lr:5.522642316338268e-05 tokens_per_second_per_gpu:6951.1125522514 Step 131 | loss:0.0020699473097920418 lr:5.453162900988902e-05 tokens_per_second_per_gpu:6786.60464411376 Step 132 | loss:0.0047590951435267925 lr:5.383595140634093e-05 tokens_per_second_per_gpu:7169.973727950711 Step 133 | loss:0.005938543006777763 lr:5.313952597646568e-05 tokens_per_second_per_gpu:6778.8658464663185 Step 134 | loss:0.001649044337682426 lr:5.244248848978067e-05 tokens_per_second_per_gpu:7007.584981930694 Step 135 | loss:0.0008870766032487154 lr:5.174497483512506e-05 tokens_per_second_per_gpu:7069.009104543238 Step 136 | loss:0.0020156551618129015 lr:5.104712099416785e-05 tokens_per_second_per_gpu:7111.395856025719 Step 137 | loss:0.0009183238144032657 lr:5.034906301489808e-05 tokens_per_second_per_gpu:6999.253430788709 Step 138 | loss:0.004217950161546469 lr:4.965093698510193e-05 tokens_per_second_per_gpu:7130.88122586147 Step 139 | loss:0.0010270746424794197 lr:4.895287900583216e-05 tokens_per_second_per_gpu:7113.413812282198 Step 140 | loss:0.001091530080884695 lr:4.825502516487497e-05 tokens_per_second_per_gpu:6848.628830636361 Step 141 | loss:0.003317818744108081 lr:4.755751151021934e-05 tokens_per_second_per_gpu:7090.422818366356 Step 142 | loss:0.003257043892517686 lr:4.6860474023534335e-05 tokens_per_second_per_gpu:7167.550883430316 Step 143 | loss:0.0034374704118818045 lr:4.616404859365907e-05 tokens_per_second_per_gpu:7083.855860338497 Step 144 | loss:0.0011866542045027018 lr:4.5468370990111006e-05 tokens_per_second_per_gpu:7028.9049100319635 Step 145 | loss:0.0009017881820909679 lr:4.477357683661734e-05 tokens_per_second_per_gpu:7013.863499264959 Step 146 | loss:0.0011286574881523848 lr:4.407980158467495e-05 tokens_per_second_per_gpu:7106.913383873531 Step 147 | loss:0.003700129920616746 lr:4.3387180487143876e-05 tokens_per_second_per_gpu:7108.5311604455555 Step 148 | loss:0.0009112973348237574 lr:4.269584857187943e-05 tokens_per_second_per_gpu:7081.600399118515 Step 149 | loss:0.0009054307593032718 lr:4.2005940615408264e-05 tokens_per_second_per_gpu:7126.035151924929 Step 150 | loss:0.002454703440889716 lr:4.131759111665349e-05 tokens_per_second_per_gpu:7086.506499432845 Step 151 | loss:0.001739362021908164 lr:4.063093427071376e-05 tokens_per_second_per_gpu:7043.067681378559 Step 152 | loss:0.002288701944053173 lr:3.9946103942701777e-05 tokens_per_second_per_gpu:6768.955727680779 Step 153 | loss:0.002506113378331065 lr:3.926323364164684e-05 tokens_per_second_per_gpu:7096.75824116386 Step 154 | loss:0.0011422057868912816 lr:3.858245649446721e-05 tokens_per_second_per_gpu:7026.3713914700675 Step 155 | loss:0.0012262844247743487 lr:3.790390522001662e-05 tokens_per_second_per_gpu:7084.269443572842 Step 156 | loss:0.003845866536721587 lr:3.7227712103210486e-05 tokens_per_second_per_gpu:7082.043511646926 Step 157 | loss:0.0046083964407444 lr:3.655400896923672e-05 tokens_per_second_per_gpu:7128.276893713962 Step 158 | loss:0.0009942419128492475 lr:3.588292715785617e-05 tokens_per_second_per_gpu:7094.498950254412 Step 159 | loss:0.0008828302379697561 lr:3.5214597497797684e-05 tokens_per_second_per_gpu:7071.422289560471 Step 160 | loss:0.0012416349491104484 lr:3.4549150281252636e-05 tokens_per_second_per_gpu:7084.5713311259415 Step 161 | loss:0.0014082695124670863 lr:3.388671523847445e-05 tokens_per_second_per_gpu:7119.899100492797 Step 162 | loss:0.0014703223714604974 lr:3.322742151248725e-05 tokens_per_second_per_gpu:7116.649096728678 Step 163 | loss:0.003265992971137166 lr:3.257139763390925e-05 tokens_per_second_per_gpu:7129.820485904622 Step 164 | loss:0.0032932583708316088 lr:3.1918771495895396e-05 tokens_per_second_per_gpu:7071.049933020474 Step 165 | loss:0.0012423135340213776 lr:3.12696703292044e-05 tokens_per_second_per_gpu:7089.894448476486 Step 166 | loss:0.0013641252880916 lr:3.062422067739485e-05 tokens_per_second_per_gpu:7081.37894283927 Step 167 | loss:0.0032141294796019793 lr:2.9982548372155263e-05 tokens_per_second_per_gpu:7016.00879323321 Step 168 | loss:0.006354935467243195 lr:2.934477850877292e-05 tokens_per_second_per_gpu:6798.182297040389 Step 169 | loss:0.0006811489583924413 lr:2.8711035421746367e-05 tokens_per_second_per_gpu:6936.269732583515 Step 170 | loss:0.0022023101337254047 lr:2.8081442660546125e-05 tokens_per_second_per_gpu:7007.542538320278 Step 171 | loss:0.009234899654984474 lr:2.7456122965528475e-05 tokens_per_second_per_gpu:7121.979658800933 Step 172 | loss:0.001224864972755313 lr:2.6835198244006927e-05 tokens_per_second_per_gpu:7102.45384334688 Step 173 | loss:0.0005341346841305494 lr:2.6218789546486234e-05 tokens_per_second_per_gpu:7013.335438185653 Step 174 | loss:0.0005438377847895026 lr:2.560701704306336e-05 tokens_per_second_per_gpu:6995.400453453779 Step 175 | loss:0.001315005007199943 lr:2.500000000000001e-05 tokens_per_second_per_gpu:7116.343408831521 Step 176 | loss:0.0005872685578651726 lr:2.4397856756471432e-05 tokens_per_second_per_gpu:6993.247911118323 Step 177 | loss:0.0011959145776927471 lr:2.3800704701496053e-05 tokens_per_second_per_gpu:7101.100713031046 Step 178 | loss:0.002665150910615921 lr:2.3208660251050158e-05 tokens_per_second_per_gpu:7111.381357821258 Step 179 | loss:0.0012093295808881521 lr:2.2621838825372493e-05 tokens_per_second_per_gpu:7121.423047525469 Step 180 | loss:0.004232932813465595 lr:2.2040354826462668e-05 tokens_per_second_per_gpu:7090.721252280985 Step 181 | loss:0.00044165176223032176 lr:2.1464321615778422e-05 tokens_per_second_per_gpu:7005.2663154561005 Step 182 | loss:0.0033288833219558 lr:2.0893851492135537e-05 tokens_per_second_per_gpu:7147.752252844287 Step 183 | loss:0.0008819952490739524 lr:2.0329055669814934e-05 tokens_per_second_per_gpu:7014.182027669998 Step 184 | loss:0.0004541981325019151 lr:1.977004425688126e-05 tokens_per_second_per_gpu:6998.970036156952 Step 185 | loss:0.0023643302265554667 lr:1.9216926233717085e-05 tokens_per_second_per_gpu:7106.750822064895 Step 186 | loss:0.0007187752053141594 lr:1.866980943177699e-05 tokens_per_second_per_gpu:7109.113903040281 Step 187 | loss:0.009922114200890064 lr:1.8128800512565513e-05 tokens_per_second_per_gpu:6788.648931586378 Step 188 | loss:0.005204517859965563 lr:1.7594004946843456e-05 tokens_per_second_per_gpu:2360.4625467985534 Step 189 | loss:0.0020576894748955965 lr:1.7065526994065973e-05 tokens_per_second_per_gpu:7018.4462244138185 Step 190 | loss:0.0016829757951200008 lr:1.6543469682057106e-05 tokens_per_second_per_gpu:6783.876555883064 Step 191 | loss:0.000494220876134932 lr:1.602793478692419e-05 tokens_per_second_per_gpu:6980.5693273946945 Step 192 | loss:0.0008372340234927833 lr:1.551902281321651e-05 tokens_per_second_per_gpu:6998.04938634989 Step 193 | loss:0.002383846789598465 lr:1.5016832974331724e-05 tokens_per_second_per_gpu:7088.593565642524 Step 194 | loss:0.006373848300427198 lr:1.4521463173173965e-05 tokens_per_second_per_gpu:7146.4038953249155 Step 195 | loss:0.0005375099717639387 lr:1.4033009983067452e-05 tokens_per_second_per_gpu:7047.352628074002 Step 196 | loss:0.0005737715400755405 lr:1.3551568628929434e-05 tokens_per_second_per_gpu:7039.643459435588 Step 197 | loss:0.0035601723939180374 lr:1.3077232968705805e-05 tokens_per_second_per_gpu:7128.217691096629 Step 198 | loss:0.0015496446285396814 lr:1.2610095475073414e-05 tokens_per_second_per_gpu:4917.531651452785 Step 199 | loss:0.006769964005798101 lr:1.2150247217412186e-05 tokens_per_second_per_gpu:6825.138993469563 Step 200 | loss:0.0021398740354925394 lr:1.1697777844051105e-05 tokens_per_second_per_gpu:7007.847619470847 Step 201 | loss:0.0006493188557215035 lr:1.1252775564791024e-05 tokens_per_second_per_gpu:7058.216015774152 Step 202 | loss:0.004032281693071127 lr:1.0815327133708015e-05 tokens_per_second_per_gpu:7057.318727825849 Step 203 | loss:0.0007151448517106473 lr:1.0385517832240471e-05 tokens_per_second_per_gpu:7103.6910819011955 Step 204 | loss:0.0006049590883776546 lr:9.963431452563332e-06 tokens_per_second_per_gpu:7011.314075487803 Step 205 | loss:0.003260341240093112 lr:9.549150281252633e-06 tokens_per_second_per_gpu:7054.5269025019525 Step 206 | loss:0.007215019781142473 lr:9.142755083243576e-06 tokens_per_second_per_gpu:6834.509121120686 Step 207 | loss:0.004177152644842863 lr:8.744325086085248e-06 tokens_per_second_per_gpu:7113.643108858418 Step 208 | loss:0.005002874415367842 lr:8.353937964495029e-06 tokens_per_second_per_gpu:7124.319750180345 Step 209 | loss:0.00899567361921072 lr:7.971669825215788e-06 tokens_per_second_per_gpu:6826.569537379147 Step 210 | loss:0.0025386284105479717 lr:7.597595192178702e-06 tokens_per_second_per_gpu:6783.578337772751 Step 211 | loss:0.014848333783447742 lr:7.2317869919746705e-06 tokens_per_second_per_gpu:7008.719791914991 Step 212 | loss:0.0021301431115716696 lr:6.874316539637127e-06 tokens_per_second_per_gpu:6764.7191797331625 Step 213 | loss:0.01420518010854721 lr:6.52525352473905e-06 tokens_per_second_per_gpu:6784.243221561812 Step 214 | loss:0.0011578178964555264 lr:6.184665997806832e-06 tokens_per_second_per_gpu:7090.18401304448 Step 215 | loss:0.0007164228009060025 lr:5.852620357053651e-06 tokens_per_second_per_gpu:7106.5604189528 Step 216 | loss:0.007493870798498392 lr:5.529181335435124e-06 tokens_per_second_per_gpu:6803.776537198445 Step 217 | loss:0.0024108646903187037 lr:5.214411988029355e-06 tokens_per_second_per_gpu:7098.476540815278 Step 218 | loss:0.0007690793136134744 lr:4.908373679744316e-06 tokens_per_second_per_gpu:7091.956950100153 Step 219 | loss:0.0006122945924289525 lr:4.611126073354571e-06 tokens_per_second_per_gpu:7054.06142014693 Step 220 | loss:0.0007160824607126415 lr:4.322727117869951e-06 tokens_per_second_per_gpu:7042.2012871258885 Step 221 | loss:0.0012269176077097654 lr:4.043233037238281e-06 tokens_per_second_per_gpu:7076.370612581842 Step 222 | loss:0.0005973738734610379 lr:3.772698319384349e-06 tokens_per_second_per_gpu:6936.97568616373 Step 223 | loss:0.005888126790523529 lr:3.511175705587433e-06 tokens_per_second_per_gpu:3371.2196453442752 Step 224 | loss:0.002613009884953499 lr:3.258716180199278e-06 tokens_per_second_per_gpu:6987.188824763654 Step 225 | loss:0.0006440908182412386 lr:3.0153689607045845e-06 tokens_per_second_per_gpu:7052.494487185873 Step 226 | loss:0.0007862089551053941 lr:2.7811814881259503e-06 tokens_per_second_per_gpu:7082.4725745492005 Step 227 | loss:0.0006963695050217211 lr:2.5561994177751737e-06 tokens_per_second_per_gpu:6902.455043219747 Step 228 | loss:0.0005707860109396279 lr:2.340466610352654e-06 tokens_per_second_per_gpu:6981.621312896846 Step 229 | loss:0.009474636055529118 lr:2.134025123396638e-06 tokens_per_second_per_gpu:7016.0987565174055 Step 230 | loss:0.001349342754110694 lr:1.9369152030840556e-06 tokens_per_second_per_gpu:7095.632264815667 Step 231 | loss:0.0036563100293278694 lr:1.7491752763844293e-06 tokens_per_second_per_gpu:7053.076991838695 Step 232 | loss:0.0008136473479680717 lr:1.5708419435684462e-06 tokens_per_second_per_gpu:7088.886170431751 Step 233 | loss:0.0024451015051454306 lr:1.4019499710726913e-06 tokens_per_second_per_gpu:7092.6722640512535 Step 234 | loss:0.003582577221095562 lr:1.2425322847218368e-06 tokens_per_second_per_gpu:7063.692617470226 Step 235 | loss:0.0036203006748110056 lr:1.0926199633097157e-06 tokens_per_second_per_gpu:7047.2949129515 Step 236 | loss:0.004718224983662367 lr:9.522422325404235e-07 tokens_per_second_per_gpu:7006.445167094263 Step 237 | loss:0.0044596088118851185 lr:8.214264593307098e-07 tokens_per_second_per_gpu:7005.721437740373 Step 238 | loss:0.0007192895282059908 lr:7.001981464747565e-07 tokens_per_second_per_gpu:6976.617113396402 Step 239 | loss:0.0037662587128579617 lr:5.885809276723608e-07 tokens_per_second_per_gpu:7054.499879430889 Step 240 | loss:0.0036025492008775473 lr:4.865965629214819e-07 tokens_per_second_per_gpu:7039.812848323273 Step 241 | loss:0.0010571421589702368 lr:3.9426493427611177e-07 tokens_per_second_per_gpu:7016.863406543254 Step 242 | loss:0.00470284279435873 lr:3.1160404197018154e-07 tokens_per_second_per_gpu:7052.980524523945 Step 243 | loss:0.004519009031355381 lr:2.386300009084408e-07 tokens_per_second_per_gpu:7022.959735350045 Step 244 | loss:0.006832956336438656 lr:1.753570375247815e-07 tokens_per_second_per_gpu:6922.428592835645 Step 245 | loss:0.007278790231794119 lr:1.2179748700879012e-07 tokens_per_second_per_gpu:6736.016708820595 Step 246 | loss:0.0009208635310642421 lr:7.796179090094891e-08 tokens_per_second_per_gpu:7089.016085222295 Step 247 | loss:0.0006743083940818906 lr:4.385849505708084e-08 tokens_per_second_per_gpu:7053.398613737493 Step 248 | loss:0.00095297273946926 lr:1.949424798228239e-08 tokens_per_second_per_gpu:7021.102793992177 Step 249 | loss:0.0019298767438158393 lr:4.873799534788059e-09 tokens_per_second_per_gpu:6776.606245017599 Step 250 | loss:0.0012648148695006967 lr:0.0 tokens_per_second_per_gpu:7102.769590185656