Step 1 | loss:5.081948757171631 lr:6.849315068493151e-07 tokens_per_second_per_gpu:440.32463302342023 mfu:2.077086421100731 Step 2 | loss:5.5589599609375 lr:1.3698630136986302e-06 tokens_per_second_per_gpu:1373.7037309699588 mfu:6.479994877010095 Step 3 | loss:5.230297088623047 lr:2.054794520547945e-06 tokens_per_second_per_gpu:4442.222838338357 mfu:20.95472304981263 Step 4 | loss:4.9551568031311035 lr:2.7397260273972604e-06 tokens_per_second_per_gpu:4726.461183003077 mfu:22.295523817658466 Step 5 | loss:5.5650553703308105 lr:3.4246575342465754e-06 tokens_per_second_per_gpu:4061.347993526127 mfu:19.15807142288388 Step 6 | loss:5.270690441131592 lr:4.10958904109589e-06 tokens_per_second_per_gpu:4468.132774480923 mfu:21.076944639288065 Step 7 | loss:4.373228073120117 lr:4.7945205479452054e-06 tokens_per_second_per_gpu:4978.551679346489 mfu:23.48467769998418 Step 8 | loss:4.092312335968018 lr:5.479452054794521e-06 tokens_per_second_per_gpu:4301.023969119634 mfu:20.288663892696636 Step 9 | loss:3.4604618549346924 lr:6.1643835616438354e-06 tokens_per_second_per_gpu:4972.827697471794 mfu:23.457676700869225 Step 10 | loss:3.1078546047210693 lr:6.849315068493151e-06 tokens_per_second_per_gpu:3764.0638146048777 mfu:17.755731229001146 Step 11 | loss:2.922640562057495 lr:7.5342465753424655e-06 tokens_per_second_per_gpu:3244.481330763071 mfu:15.304772002806311 Step 12 | loss:2.974088668823242 lr:8.21917808219178e-06 tokens_per_second_per_gpu:3183.170079473246 mfu:15.015556369694055 Step 13 | loss:2.797309637069702 lr:8.904109589041095e-06 tokens_per_second_per_gpu:5349.204999178386 mfu:25.2331126496087 Step 14 | loss:2.5241711139678955 lr:9.589041095890411e-06 tokens_per_second_per_gpu:4110.165708437857 mfu:19.388352913283548 Step 15 | loss:2.7006828784942627 lr:1.0273972602739726e-05 tokens_per_second_per_gpu:3631.1233173156993 mfu:17.12862822130036 Step 16 | loss:2.430112361907959 lr:1.0958904109589042e-05 tokens_per_second_per_gpu:4281.7402970169915 mfu:20.19769952125474 Step 17 | loss:2.480497360229492 lr:1.1643835616438355e-05 tokens_per_second_per_gpu:4273.158262110154 mfu:20.15721659835305 Step 18 | loss:2.2863008975982666 lr:1.2328767123287671e-05 tokens_per_second_per_gpu:5120.035007239325 mfu:24.152078697199613 Step 19 | loss:2.2043216228485107 lr:1.3013698630136986e-05 tokens_per_second_per_gpu:4620.807108692482 mfu:21.797135522691484 Step 20 | loss:2.525569200515747 lr:1.3698630136986302e-05 tokens_per_second_per_gpu:5302.145635768329 mfu:25.01112560324812 Step 21 | loss:2.3917365074157715 lr:1.4383561643835617e-05 tokens_per_second_per_gpu:4105.774043978016 mfu:19.36763668273126 Step 22 | loss:2.487661838531494 lr:1.5068493150684931e-05 tokens_per_second_per_gpu:2832.5985020911994 mfu:13.361850425504048 Step 23 | loss:2.190711736679077 lr:1.5753424657534248e-05 tokens_per_second_per_gpu:4181.277288657882 mfu:19.723798370068096 Step 24 | loss:1.983615517616272 lr:1.643835616438356e-05 tokens_per_second_per_gpu:5328.721036540481 mfu:25.13648630292129 Step 25 | loss:2.0638980865478516 lr:1.7123287671232875e-05 tokens_per_second_per_gpu:4533.265841580206 mfu:21.38418842964255 Step 26 | loss:2.0230727195739746 lr:1.780821917808219e-05 tokens_per_second_per_gpu:3718.3941413807133 mfu:17.54029958835302 Step 27 | loss:1.9072682857513428 lr:1.8493150684931506e-05 tokens_per_second_per_gpu:5325.325494410076 mfu:25.120468951352944 Step 28 | loss:2.176602840423584 lr:1.9178082191780822e-05 tokens_per_second_per_gpu:4664.321163234365 mfu:22.002398742228813 Step 29 | loss:1.9503653049468994 lr:1.9863013698630137e-05 tokens_per_second_per_gpu:5076.776282869133 mfu:23.948019913645965 Step 30 | loss:1.8743207454681396 lr:2.0547945205479453e-05 tokens_per_second_per_gpu:3856.1509298213327 mfu:18.190121863159156 Step 31 | loss:1.9450348615646362 lr:2.1232876712328768e-05 tokens_per_second_per_gpu:5336.550650166943 mfu:25.173419926267147 Step 32 | loss:1.9066333770751953 lr:2.1917808219178083e-05 tokens_per_second_per_gpu:3579.9592588450614 mfu:16.88727862800583 Step 33 | loss:2.1070351600646973 lr:2.2602739726027396e-05 tokens_per_second_per_gpu:4451.278734006143 mfu:20.9974412547727 Step 34 | loss:1.8664394617080688 lr:2.328767123287671e-05 tokens_per_second_per_gpu:5297.770941121615 mfu:24.990489422199698 Step 35 | loss:1.8009560108184814 lr:2.3972602739726026e-05 tokens_per_second_per_gpu:4955.296754312958 mfu:23.374980250901665 Step 36 | loss:1.7950012683868408 lr:2.4657534246575342e-05 tokens_per_second_per_gpu:5316.37056156186 mfu:25.078227005238816 Step 37 | loss:1.754820704460144 lr:2.534246575342466e-05 tokens_per_second_per_gpu:4169.454887030094 mfu:19.668030084480105 Step 38 | loss:2.00518798828125 lr:2.6027397260273973e-05 tokens_per_second_per_gpu:4842.700106210183 mfu:22.843842650831732 Step 39 | loss:1.7243146896362305 lr:2.671232876712329e-05 tokens_per_second_per_gpu:5330.306377236548 mfu:25.143964625471654 Step 40 | loss:1.6724543571472168 lr:2.7397260273972603e-05 tokens_per_second_per_gpu:5303.281311046025 mfu:25.016482777299196 Step 41 | loss:1.7272483110427856 lr:2.808219178082192e-05 tokens_per_second_per_gpu:5133.16864984143 mfu:24.21403233018424 Step 42 | loss:1.6937143802642822 lr:2.8767123287671234e-05 tokens_per_second_per_gpu:3963.5723262932993 mfu:18.69684691829758 Step 43 | loss:1.7619761228561401 lr:2.945205479452055e-05 tokens_per_second_per_gpu:4956.772882236516 mfu:23.381943398170485 Step 44 | loss:1.883114218711853 lr:3.0136986301369862e-05 tokens_per_second_per_gpu:5363.63015770362 mfu:25.301158583558063 Step 45 | loss:1.6234325170516968 lr:3.082191780821918e-05 tokens_per_second_per_gpu:5292.026397797252 mfu:24.96339143121852 Step 46 | loss:1.6722863912582397 lr:3.1506849315068496e-05 tokens_per_second_per_gpu:5332.616614166815 mfu:25.15486240723879 Step 47 | loss:1.8038501739501953 lr:3.219178082191781e-05 tokens_per_second_per_gpu:4069.5731508964336 mfu:19.196870893556174 Step 48 | loss:1.946854591369629 lr:3.287671232876712e-05 tokens_per_second_per_gpu:3565.2713845680055 mfu:16.817993419031193 Step 49 | loss:1.8749449253082275 lr:3.356164383561644e-05 tokens_per_second_per_gpu:3782.871736310645 mfu:17.84445140464959 Step 50 | loss:1.733234167098999 lr:3.424657534246575e-05 tokens_per_second_per_gpu:3879.6042450614586 mfu:18.300755152695036 Step 51 | loss:1.77200448513031 lr:3.493150684931507e-05 tokens_per_second_per_gpu:3570.683353902494 mfu:16.84352260175916 Step 52 | loss:1.6169968843460083 lr:3.561643835616438e-05 tokens_per_second_per_gpu:5306.6286579133275 mfu:25.032272783588528 Step 53 | loss:1.7243956327438354 lr:3.63013698630137e-05 tokens_per_second_per_gpu:4461.530722273851 mfu:21.045801632601044 Step 54 | loss:1.6737765073776245 lr:3.698630136986301e-05 tokens_per_second_per_gpu:4796.183732331436 mfu:22.62441697873391 Step 55 | loss:1.6827926635742188 lr:3.767123287671233e-05 tokens_per_second_per_gpu:3771.371062979473 mfu:17.790200766329246 Step 56 | loss:1.6578755378723145 lr:3.8356164383561644e-05 tokens_per_second_per_gpu:5347.570289534675 mfu:25.22540144530909 Step 57 | loss:1.9403196573257446 lr:3.904109589041096e-05 tokens_per_second_per_gpu:3114.3413862909792 mfu:14.690879680567305 Step 58 | loss:1.5899044275283813 lr:3.9726027397260274e-05 tokens_per_second_per_gpu:5319.757532012385 mfu:25.09420392273069 Step 59 | loss:1.7926095724105835 lr:4.041095890410959e-05 tokens_per_second_per_gpu:3747.5244888254965 mfu:17.67771240739984 Step 60 | loss:1.6449967622756958 lr:4.1095890410958905e-05 tokens_per_second_per_gpu:4802.755807161283 mfu:22.655418577017898 Step 61 | loss:1.631004810333252 lr:4.1780821917808224e-05 tokens_per_second_per_gpu:4158.124299599168 mfu:19.61458177037087 Step 62 | loss:1.6880601644515991 lr:4.2465753424657536e-05 tokens_per_second_per_gpu:4361.340565072439 mfu:20.573187566878467 Step 63 | loss:1.6016582250595093 lr:4.3150684931506855e-05 tokens_per_second_per_gpu:5328.2750136791265 mfu:25.134382336984935 Step 64 | loss:1.7186912298202515 lr:4.383561643835617e-05 tokens_per_second_per_gpu:5317.9045976239095 mfu:25.085463315077043 Step 65 | loss:1.651291012763977 lr:4.452054794520548e-05 tokens_per_second_per_gpu:5281.363713022074 mfu:24.913093727892388 Step 66 | loss:1.6368006467819214 lr:4.520547945205479e-05 tokens_per_second_per_gpu:5337.210178586128 mfu:25.17653103434759 Step 67 | loss:1.7882657051086426 lr:4.589041095890411e-05 tokens_per_second_per_gpu:3969.416956708805 mfu:18.7244170371643 Step 68 | loss:1.6681416034698486 lr:4.657534246575342e-05 tokens_per_second_per_gpu:5052.987621828919 mfu:23.83580474075518 Step 69 | loss:1.6170293092727661 lr:4.726027397260274e-05 tokens_per_second_per_gpu:3082.4741375927792 mfu:14.54055643134461 Step 70 | loss:1.6805517673492432 lr:4.794520547945205e-05 tokens_per_second_per_gpu:5339.324345301079 mfu:25.186503919456058 Step 71 | loss:1.6577622890472412 lr:4.863013698630137e-05 tokens_per_second_per_gpu:4484.139751663325 mfu:21.152452281729378 Step 72 | loss:1.552563190460205 lr:4.9315068493150684e-05 tokens_per_second_per_gpu:5319.027204796093 mfu:25.090758844644768 Step 73 | loss:1.8100932836532593 lr:5e-05 tokens_per_second_per_gpu:4834.82912498728 mfu:22.80671388947543 Step 74 | loss:1.563002586364746 lr:4.999999761222383e-05 tokens_per_second_per_gpu:4468.674668234134 mfu:21.079500844578565 Step 75 | loss:1.4997555017471313 lr:4.999999044889576e-05 tokens_per_second_per_gpu:5317.583546638059 mfu:25.08394886279984 Step 76 | loss:1.7100895643234253 lr:4.999997851001716e-05 tokens_per_second_per_gpu:4405.495110105059 mfu:20.781472089339555 Step 77 | loss:1.5747263431549072 lr:4.999996179559032e-05 tokens_per_second_per_gpu:4696.666446695073 mfu:22.154976962987405 Step 78 | loss:1.8419746160507202 lr:4.9999940305618423e-05 tokens_per_second_per_gpu:4912.75520792806 mfu:23.174304518267835 Step 79 | loss:1.6756632328033447 lr:4.999991404010558e-05 tokens_per_second_per_gpu:5203.978533858437 mfu:24.54805463450447 Step 80 | loss:1.541156530380249 lr:4.999988299905681e-05 tokens_per_second_per_gpu:4779.090653300619 mfu:22.54378600856554 Step 81 | loss:1.7467527389526367 lr:4.999984718247803e-05 tokens_per_second_per_gpu:4269.775370458459 mfu:20.14125892125117 Step 82 | loss:1.6360151767730713 lr:4.9999806590376094e-05 tokens_per_second_per_gpu:5160.024816364191 mfu:24.340717449806604 Step 83 | loss:1.5890196561813354 lr:4.999976122275876e-05 tokens_per_second_per_gpu:4149.042962468528 mfu:19.571743553689746 Step 84 | loss:1.7217276096343994 lr:4.999971107963468e-05 tokens_per_second_per_gpu:4299.891461716054 mfu:20.283321662048262 Step 85 | loss:1.6859537363052368 lr:4.999965616101344e-05 tokens_per_second_per_gpu:3822.501491298529 mfu:18.031391720460867 Step 86 | loss:1.7289454936981201 lr:4.999959646690553e-05 tokens_per_second_per_gpu:4738.440919718573 mfu:22.352034279699314 Step 87 | loss:1.7713923454284668 lr:4.9999531997322355e-05 tokens_per_second_per_gpu:3592.2083325185927 mfu:16.94505959843135 Step 88 | loss:1.4655795097351074 lr:4.999946275227623e-05 tokens_per_second_per_gpu:4800.611610303074 mfu:22.645304034600017 Step 89 | loss:1.5783082246780396 lr:4.9999388731780374e-05 tokens_per_second_per_gpu:5253.502739338515 mfu:24.781668761454757 Step 90 | loss:1.752044677734375 lr:4.999930993584894e-05 tokens_per_second_per_gpu:4888.453312996523 mfu:23.05966833354494 Step 91 | loss:1.511054515838623 lr:4.9999226364496965e-05 tokens_per_second_per_gpu:4214.851749701689 mfu:19.882174831205486 Step 92 | loss:1.557932734489441 lr:4.9999138017740425e-05 tokens_per_second_per_gpu:4548.354957042288 mfu:21.45536636174576 Step 93 | loss:1.6554217338562012 lr:4.999904489559619e-05 tokens_per_second_per_gpu:5024.859211304015 mfu:23.703118229107492 Step 94 | loss:1.6611045598983765 lr:4.9998946998082055e-05 tokens_per_second_per_gpu:3960.67321539182 mfu:18.68317131753598 Step 95 | loss:1.581343412399292 lr:4.999884432521671e-05 tokens_per_second_per_gpu:5364.678080458464 mfu:25.30610181398672 Step 96 | loss:1.6416637897491455 lr:4.999873687701978e-05 tokens_per_second_per_gpu:3915.613880788146 mfu:18.470618748295216 Step 97 | loss:1.6391007900238037 lr:4.999862465351178e-05 tokens_per_second_per_gpu:5102.4961212684775 mfu:24.069344779632612 Step 98 | loss:1.667188286781311 lr:4.999850765471415e-05 tokens_per_second_per_gpu:4228.55373582205 mfu:19.946809437535123 Step 99 | loss:1.597773551940918 lr:4.999838588064924e-05 tokens_per_second_per_gpu:4204.166798230972 mfu:19.831772092077404 Step 100 | loss:1.8802579641342163 lr:4.9998259331340315e-05 tokens_per_second_per_gpu:2680.4353035408085 mfu:12.644070656223095 Step 101 | loss:1.5992885828018188 lr:4.999812800681154e-05 tokens_per_second_per_gpu:4007.086556419757 mfu:18.90211096609731 Step 102 | loss:1.6615750789642334 lr:4.999799190708801e-05 tokens_per_second_per_gpu:4045.5028009452303 mfu:19.083326946011162 Step 103 | loss:1.4109894037246704 lr:4.999785103219572e-05 tokens_per_second_per_gpu:5325.250789693467 mfu:25.120116556458758 Step 104 | loss:1.4935144186019897 lr:4.999770538216157e-05 tokens_per_second_per_gpu:5291.899400531958 mfu:24.962792363450163 Step 105 | loss:1.718597173690796 lr:4.9997554957013404e-05 tokens_per_second_per_gpu:3820.933158159191 mfu:18.023993625457383 Step 106 | loss:1.5132856369018555 lr:4.999739975677994e-05 tokens_per_second_per_gpu:5154.240193779926 mfu:24.313430398118246 Step 107 | loss:1.522456169128418 lr:4.999723978149083e-05 tokens_per_second_per_gpu:5288.6300549302 mfu:24.947370302438788 Step 108 | loss:1.6965330839157104 lr:4.9997075031176634e-05 tokens_per_second_per_gpu:3403.50304387034 mfu:16.054904555435307 Step 109 | loss:1.6378474235534668 lr:4.999690550586882e-05 tokens_per_second_per_gpu:3877.591796890348 mfu:18.291262091312845 Step 110 | loss:1.5300791263580322 lr:4.9996731205599765e-05 tokens_per_second_per_gpu:5329.643910120371 mfu:25.1408396550561 Step 111 | loss:1.641484022140503 lr:4.999655213040277e-05 tokens_per_second_per_gpu:5333.382990311404 mfu:25.158477534270066 Step 112 | loss:1.590038776397705 lr:4.9996368280312056e-05 tokens_per_second_per_gpu:4763.835496410315 mfu:22.471824830715818 Step 113 | loss:1.7579896450042725 lr:4.999617965536272e-05 tokens_per_second_per_gpu:3364.28476121516 mfu:15.869905224821814 Step 114 | loss:1.5425443649291992 lr:4.999598625559081e-05 tokens_per_second_per_gpu:4574.273749158145 mfu:21.577629726358193 Step 115 | loss:1.66178560256958 lr:4.999578808103326e-05 tokens_per_second_per_gpu:3726.7728484358904 mfu:17.579823379087124 Step 116 | loss:1.7529454231262207 lr:4.9995585131727926e-05 tokens_per_second_per_gpu:4441.553532643358 mfu:20.95156582065399 Step 117 | loss:1.694088101387024 lr:4.9995377407713586e-05 tokens_per_second_per_gpu:4616.095324176306 mfu:21.77490923121535 Step 118 | loss:1.4049636125564575 lr:4.9995164909029904e-05 tokens_per_second_per_gpu:5302.082767375739 mfu:25.010829042313823 Step 119 | loss:1.7629997730255127 lr:4.9994947635717485e-05 tokens_per_second_per_gpu:4248.005943003882 mfu:20.038568817700604 Step 120 | loss:1.6110676527023315 lr:4.9994725587817825e-05 tokens_per_second_per_gpu:5334.529502729152 mfu:25.163885828959774 Step 121 | loss:1.5582327842712402 lr:4.9994498765373345e-05 tokens_per_second_per_gpu:4380.28038154784 mfu:20.662529912658844 Step 122 | loss:1.5513168573379517 lr:4.999426716842738e-05 tokens_per_second_per_gpu:3606.730229794154 mfu:17.01356186557134 Step 123 | loss:1.4423247575759888 lr:4.999403079702415e-05 tokens_per_second_per_gpu:5317.61538509874 mfu:25.084099050251073 Step 124 | loss:1.6242079734802246 lr:4.999378965120882e-05 tokens_per_second_per_gpu:5326.680324782989 mfu:25.126859917379875 Step 125 | loss:1.617388367652893 lr:4.999354373102746e-05 tokens_per_second_per_gpu:3225.655777756284 mfu:15.215968657302744 Step 126 | loss:1.6250661611557007 lr:4.999329303652703e-05 tokens_per_second_per_gpu:4899.763839132113 mfu:23.11302201510127 Step 127 | loss:1.7555445432662964 lr:4.999303756775543e-05 tokens_per_second_per_gpu:3538.01306815526 mfu:16.689411289763925 Step 128 | loss:1.792305588722229 lr:4.999277732476146e-05 tokens_per_second_per_gpu:4307.855538199185 mfu:20.32088956963075 Step 129 | loss:1.5427066087722778 lr:4.999251230759483e-05 tokens_per_second_per_gpu:3926.7969988206087 mfu:18.523371424091025 Step 130 | loss:1.6001532077789307 lr:4.999224251630616e-05 tokens_per_second_per_gpu:4693.4413104691685 mfu:22.13976344514483 Step 131 | loss:1.7872470617294312 lr:4.9991967950947e-05 tokens_per_second_per_gpu:3828.9636681499305 mfu:18.061874911229992 Step 132 | loss:1.81485915184021 lr:4.999168861156978e-05 tokens_per_second_per_gpu:4089.8190759348004 mfu:19.292374376273155 Step 133 | loss:1.6971755027770996 lr:4.999140449822787e-05 tokens_per_second_per_gpu:4358.548133034498 mfu:20.56001518851747 Step 134 | loss:1.4415929317474365 lr:4.999111561097554e-05 tokens_per_second_per_gpu:4384.599364105504 mfu:20.68290329027775 Step 135 | loss:1.6765285730361938 lr:4.999082194986797e-05 tokens_per_second_per_gpu:5360.260552397089 mfu:25.285263580413204 Step 136 | loss:1.5961679220199585 lr:4.999052351496127e-05 tokens_per_second_per_gpu:4588.898829507815 mfu:21.646618725663604 Step 137 | loss:1.66520357131958 lr:4.999022030631243e-05 tokens_per_second_per_gpu:4576.437122116324 mfu:21.58783472571141 Step 138 | loss:1.9405992031097412 lr:4.998991232397937e-05 tokens_per_second_per_gpu:4215.163012802955 mfu:19.883643112361113 Step 139 | loss:1.6871144771575928 lr:4.998959956802094e-05 tokens_per_second_per_gpu:5337.411851708359 mfu:25.17748236087414 Step 140 | loss:1.4356231689453125 lr:4.9989282038496865e-05 tokens_per_second_per_gpu:3830.3758373311925 mfu:18.068536354198912 Step 141 | loss:1.6543318033218384 lr:4.998895973546781e-05 tokens_per_second_per_gpu:5311.26183896516 mfu:25.05412828911222 Step 142 | loss:1.4406427145004272 lr:4.998863265899534e-05 tokens_per_second_per_gpu:4832.445494014787 mfu:22.795469895488797 Step 143 | loss:1.58236563205719 lr:4.998830080914192e-05 tokens_per_second_per_gpu:5360.600354738548 mfu:25.28686648603413 Step 144 | loss:1.5453556776046753 lr:4.998796418597097e-05 tokens_per_second_per_gpu:5206.2072397882475 mfu:24.55856782063183 Step 145 | loss:1.547173023223877 lr:4.998762278954676e-05 tokens_per_second_per_gpu:4047.108695923917 mfu:19.090902226619562 Step 146 | loss:1.5149683952331543 lr:4.998727661993453e-05 tokens_per_second_per_gpu:4936.748536128274 mfu:23.28748514107216 Step 147 | loss:1.5250669717788696 lr:4.99869256772004e-05 tokens_per_second_per_gpu:4402.188399731004 mfu:20.765873772322166 Step 148 | loss:1.8534725904464722 lr:4.998656996141139e-05 tokens_per_second_per_gpu:5249.357295331736 mfu:24.7621139947891 Step 149 | loss:1.6128333806991577 lr:4.998620947263548e-05 tokens_per_second_per_gpu:3819.1245530935744 mfu:18.015462126783024 Step 150 | loss:1.5607655048370361 lr:4.99858442109415e-05 tokens_per_second_per_gpu:5309.682381713178 mfu:25.04667771977143 Step 151 | loss:1.5206942558288574 lr:4.9985474176399246e-05 tokens_per_second_per_gpu:4409.760306434064 mfu:20.801591748141004 Step 152 | loss:1.5995389223098755 lr:4.998509936907939e-05 tokens_per_second_per_gpu:5327.769400491566 mfu:25.131997273312702 Step 153 | loss:1.5746877193450928 lr:4.9984719789053537e-05 tokens_per_second_per_gpu:3571.8702012130725 mfu:16.849121163020193 Step 154 | loss:1.5718907117843628 lr:4.998433543639418e-05 tokens_per_second_per_gpu:3514.8205482782396 mfu:16.58000821645209 Step 155 | loss:1.5806275606155396 lr:4.9983946311174765e-05 tokens_per_second_per_gpu:4610.916301434275 mfu:21.75047889730879 Step 156 | loss:1.4728271961212158 lr:4.9983552413469595e-05 tokens_per_second_per_gpu:5351.469340615032 mfu:25.243793934501845 Step 157 | loss:1.613707184791565 lr:4.998315374335394e-05 tokens_per_second_per_gpu:4805.304155093351 mfu:22.667439569006454 Step 158 | loss:1.458045244216919 lr:4.9982750300903937e-05 tokens_per_second_per_gpu:5305.202414774254 mfu:25.02554495135935 Step 159 | loss:1.5178941488265991 lr:4.998234208619665e-05 tokens_per_second_per_gpu:4456.835230918248 mfu:21.023652198743232 Step 160 | loss:1.6866785287857056 lr:4.998192909931006e-05 tokens_per_second_per_gpu:5122.534331764493 mfu:24.16386843741357 Step 161 | loss:1.5718841552734375 lr:4.998151134032307e-05 tokens_per_second_per_gpu:4992.32714347011 mfu:23.549658914591838 Step 162 | loss:1.4554383754730225 lr:4.998108880931548e-05 tokens_per_second_per_gpu:5340.102843542637 mfu:25.19017622848698 Step 163 | loss:1.4018973112106323 lr:4.998066150636798e-05 tokens_per_second_per_gpu:3808.7491819960123 mfu:17.966519731094976 Step 164 | loss:1.5203691720962524 lr:4.9980229431562215e-05 tokens_per_second_per_gpu:5347.228333814645 mfu:25.223788381834048 Step 165 | loss:1.4984784126281738 lr:4.997979258498071e-05 tokens_per_second_per_gpu:5044.770704060001 mfu:23.797044137688452 Step 166 | loss:1.5441049337387085 lr:4.997935096670692e-05 tokens_per_second_per_gpu:4096.035047353565 mfu:19.321696174009553 Step 167 | loss:1.5786631107330322 lr:4.99789045768252e-05 tokens_per_second_per_gpu:5348.7756916355675 mfu:25.231087532681805 Step 168 | loss:1.5729386806488037 lr:4.9978453415420825e-05 tokens_per_second_per_gpu:5117.950237540198 mfu:24.142244482830442 Step 169 | loss:1.5085170269012451 lr:4.997799748257997e-05 tokens_per_second_per_gpu:4441.980271379446 mfu:20.953578820081255 Step 170 | loss:1.6273016929626465 lr:4.9977536778389735e-05 tokens_per_second_per_gpu:4569.179455845055 mfu:21.55359907562428 Step 171 | loss:1.4354338645935059 lr:4.9977071302938115e-05 tokens_per_second_per_gpu:5324.167777100221 mfu:25.115007801275418 Step 172 | loss:1.5698494911193848 lr:4.997660105631403e-05 tokens_per_second_per_gpu:5300.897754314808 mfu:25.005239133521332 Step 173 | loss:1.475639820098877 lr:4.9976126038607316e-05 tokens_per_second_per_gpu:5315.577014297179 mfu:25.074483707398187 Step 174 | loss:1.6541038751602173 lr:4.9975646249908705e-05 tokens_per_second_per_gpu:5180.495896326279 mfu:24.437283026714177 Step 175 | loss:1.629893183708191 lr:4.9975161690309845e-05 tokens_per_second_per_gpu:4676.709047336716 mfu:22.06083450513058 Step 176 | loss:1.657774567604065 lr:4.9974672359903294e-05 tokens_per_second_per_gpu:3697.243092552116 mfu:17.440526482287474 Step 177 | loss:1.5853694677352905 lr:4.9974178258782545e-05 tokens_per_second_per_gpu:4594.6836857475 mfu:21.673906879544443 Step 178 | loss:1.6343907117843628 lr:4.997367938704196e-05 tokens_per_second_per_gpu:4702.581616345215 mfu:22.182879827459132 Step 179 | loss:1.417911410331726 lr:4.997317574477684e-05 tokens_per_second_per_gpu:5325.680359646487 mfu:25.122142911219346 Step 180 | loss:1.4683585166931152 lr:4.99726673320834e-05 tokens_per_second_per_gpu:4943.978770466411 mfu:23.321591390050337 Step 181 | loss:1.4877567291259766 lr:4.997215414905875e-05 tokens_per_second_per_gpu:5309.26510502301 mfu:25.04470935442916 Step 182 | loss:1.5471042394638062 lr:4.997163619580092e-05 tokens_per_second_per_gpu:4678.500446003032 mfu:22.069284838283725 Step 183 | loss:1.641282320022583 lr:4.997111347240886e-05 tokens_per_second_per_gpu:5039.793065535979 mfu:23.773563767497937 Step 184 | loss:1.4639995098114014 lr:4.99705859789824e-05 tokens_per_second_per_gpu:5329.452271776367 mfu:25.13993566429056 Step 185 | loss:1.4243671894073486 lr:4.9970053715622334e-05 tokens_per_second_per_gpu:4482.597486929652 mfu:21.14517715584315 Step 186 | loss:1.6883078813552856 lr:4.996951668243031e-05 tokens_per_second_per_gpu:5297.993862361907 mfu:24.991540979724444 Step 187 | loss:1.5506043434143066 lr:4.996897487950892e-05 tokens_per_second_per_gpu:4776.390550275592 mfu:22.531049161911408 Step 188 | loss:1.4239617586135864 lr:4.996842830696167e-05 tokens_per_second_per_gpu:4485.04786472658 mfu:21.15673600598882 Step 189 | loss:1.5883870124816895 lr:4.9967876964892954e-05 tokens_per_second_per_gpu:4526.644984402004 mfu:21.35295671669825 Step 190 | loss:1.4334262609481812 lr:4.99673208534081e-05 tokens_per_second_per_gpu:5276.383500837119 mfu:24.889601217304136 Step 191 | loss:1.4989393949508667 lr:4.996675997261333e-05 tokens_per_second_per_gpu:4779.451613280143 mfu:22.54548871837508 Step 192 | loss:1.8384532928466797 lr:4.9966194322615794e-05 tokens_per_second_per_gpu:4977.976613358245 mfu:23.481965015601258 Step 193 | loss:1.6994620561599731 lr:4.996562390352354e-05 tokens_per_second_per_gpu:4436.823620884756 mfu:20.9292540198825 Step 194 | loss:1.585970401763916 lr:4.996504871544552e-05 tokens_per_second_per_gpu:5336.059697476836 mfu:25.171104018662746 Step 195 | loss:1.6955022811889648 lr:4.996446875849162e-05 tokens_per_second_per_gpu:4451.697768944148 mfu:20.99941791407 Step 196 | loss:1.5749914646148682 lr:4.996388403277263e-05 tokens_per_second_per_gpu:5243.641799212165 mfu:24.73515302442889 Step 197 | loss:1.4388989210128784 lr:4.996329453840023e-05 tokens_per_second_per_gpu:4478.009527631624 mfu:21.123534969047775 Step 198 | loss:1.5579456090927124 lr:4.996270027548703e-05 tokens_per_second_per_gpu:4695.715287553514 mfu:22.150490183032183 Step 199 | loss:1.4747066497802734 lr:4.996210124414656e-05 tokens_per_second_per_gpu:4603.47997920245 mfu:21.715400496573864 Step 200 | loss:1.408705234527588 lr:4.9961497444493236e-05 tokens_per_second_per_gpu:5317.039786335118 mfu:25.081383852675792 Step 201 | loss:1.5304076671600342 lr:4.996088887664239e-05 tokens_per_second_per_gpu:5328.859341312575 mfu:25.137138710128486 Step 202 | loss:1.4881840944290161 lr:4.996027554071029e-05 tokens_per_second_per_gpu:5072.3275714161955 mfu:23.927034582694017 Step 203 | loss:1.5957725048065186 lr:4.995965743681409e-05 tokens_per_second_per_gpu:4084.786580038342 mfu:19.268635234497225 Step 204 | loss:1.554337739944458 lr:4.995903456507186e-05 tokens_per_second_per_gpu:4345.863048482512 mfu:20.500177480387148 Step 205 | loss:1.5188404321670532 lr:4.9958406925602574e-05 tokens_per_second_per_gpu:5108.002309686391 mfu:24.09531840985252 Step 206 | loss:1.4898052215576172 lr:4.995777451852615e-05 tokens_per_second_per_gpu:4622.291145646005 mfu:21.804135978204066 Step 207 | loss:1.426466464996338 lr:4.9957137343963354e-05 tokens_per_second_per_gpu:5213.004836313497 mfu:24.590633243230993 Step 208 | loss:1.629171371459961 lr:4.995649540203594e-05 tokens_per_second_per_gpu:3714.524299287598 mfu:17.522044882936648 Step 209 | loss:1.626121163368225 lr:4.9955848692866505e-05 tokens_per_second_per_gpu:5327.525313783168 mfu:25.130845874663706 Step 210 | loss:1.502926230430603 lr:4.99551972165786e-05 tokens_per_second_per_gpu:4713.986045223201 mfu:22.2366764642728 Step 211 | loss:1.7162952423095703 lr:4.995454097329666e-05 tokens_per_second_per_gpu:5292.623477424871 mfu:24.96620795769429 Step 212 | loss:1.6649538278579712 lr:4.9953879963146045e-05 tokens_per_second_per_gpu:5289.1051752636085 mfu:24.949611526115365 Step 213 | loss:1.5068061351776123 lr:4.995321418625303e-05 tokens_per_second_per_gpu:5294.986426743216 mfu:24.977354392789646 Step 214 | loss:1.672782301902771 lr:4.9952543642744786e-05 tokens_per_second_per_gpu:3987.96351086334 mfu:18.811904297479682 Step 215 | loss:1.561669945716858 lr:4.995186833274941e-05 tokens_per_second_per_gpu:4756.1429915957915 mfu:22.435537973029053 Step 216 | loss:1.5325961112976074 lr:4.995118825639589e-05 tokens_per_second_per_gpu:4100.195987418248 mfu:19.341324038224244 Step 217 | loss:1.4756022691726685 lr:4.995050341381414e-05 tokens_per_second_per_gpu:5309.514431175817 mfu:25.045885468431383 Step 218 | loss:1.515748143196106 lr:4.994981380513498e-05 tokens_per_second_per_gpu:4587.209022433244 mfu:21.638647617382034 Step 219 | loss:1.49256432056427 lr:4.994911943049015e-05 tokens_per_second_per_gpu:5306.456002588027 mfu:25.031458338961052 Step 220 | loss:1.4051347970962524 lr:4.9948420290012276e-05 tokens_per_second_per_gpu:4340.0519424705735 mfu:20.47276550185191 Step 221 | loss:1.3348705768585205 lr:4.994771638383491e-05 tokens_per_second_per_gpu:5326.671699285486 mfu:25.12681922943649 Step 222 | loss:1.4768726825714111 lr:4.994700771209253e-05 tokens_per_second_per_gpu:4503.429853661691 mfu:21.24344698408645 Step 223 | loss:1.5384430885314941 lr:4.994629427492049e-05 tokens_per_second_per_gpu:5048.905095521268 mfu:23.816546767611175 Step 224 | loss:1.4636927843093872 lr:4.994557607245508e-05 tokens_per_second_per_gpu:5319.231231014125 mfu:25.091721271125685 Step 225 | loss:1.3466843366622925 lr:4.994485310483349e-05 tokens_per_second_per_gpu:5021.841540528997 mfu:23.688883361194005 Step 226 | loss:1.4990239143371582 lr:4.994412537219383e-05 tokens_per_second_per_gpu:5311.585738606398 mfu:25.055656178982925 Step 227 | loss:1.7582992315292358 lr:4.99433928746751e-05 tokens_per_second_per_gpu:3465.2280831407397 mfu:16.346072097051444 Step 228 | loss:1.5677640438079834 lr:4.994265561241723e-05 tokens_per_second_per_gpu:4995.3052340646345 mfu:23.563707076040856 Step 229 | loss:1.5480350255966187 lr:4.9941913585561065e-05 tokens_per_second_per_gpu:5316.732555619881 mfu:25.079934592973057 Step 230 | loss:1.6568902730941772 lr:4.994116679424834e-05 tokens_per_second_per_gpu:5244.634568692735 mfu:24.73983608745268 Step 231 | loss:1.628925085067749 lr:4.994041523862169e-05 tokens_per_second_per_gpu:4217.507630393061 mfu:19.894703073566657 Step 232 | loss:1.6210094690322876 lr:4.9939658918824706e-05 tokens_per_second_per_gpu:5330.792317408813 mfu:25.146256888174168 Step 233 | loss:1.6474655866622925 lr:4.993889783500185e-05 tokens_per_second_per_gpu:3781.147861938838 mfu:17.836319595114478 Step 234 | loss:1.6769545078277588 lr:4.99381319872985e-05 tokens_per_second_per_gpu:5314.328206664716 mfu:25.068592868727308 Step 235 | loss:1.5664249658584595 lr:4.9937361375860964e-05 tokens_per_second_per_gpu:5320.072654711478 mfu:25.09569041026779 Step 236 | loss:1.5705547332763672 lr:4.9936586000836436e-05 tokens_per_second_per_gpu:4575.624771740429 mfu:21.58400273038705 Step 237 | loss:1.2938519716262817 lr:4.993580586237303e-05 tokens_per_second_per_gpu:5311.562908144622 mfu:25.055548483799445 Step 238 | loss:1.5409516096115112 lr:4.993502096061977e-05 tokens_per_second_per_gpu:4293.500968435435 mfu:20.253176614913 Step 239 | loss:1.4568747282028198 lr:4.99342312957266e-05 tokens_per_second_per_gpu:5309.5696400328525 mfu:25.04614589802962 Step 240 | loss:1.4890227317810059 lr:4.9933436867844354e-05 tokens_per_second_per_gpu:5329.802983061121 mfu:25.14159002925826 Step 241 | loss:1.576435923576355 lr:4.9932637677124784e-05 tokens_per_second_per_gpu:4927.827981794655 mfu:23.245405364276966 Step 242 | loss:1.581976056098938 lr:4.993183372372055e-05 tokens_per_second_per_gpu:4792.628781525767 mfu:22.607647669246425 Step 243 | loss:1.5873498916625977 lr:4.993102500778523e-05 tokens_per_second_per_gpu:5284.37968347375 mfu:24.92732057509057 Step 244 | loss:1.5966395139694214 lr:4.993021152947331e-05 tokens_per_second_per_gpu:5290.026318233476 mfu:24.953956714667427 Step 245 | loss:1.5503787994384766 lr:4.992939328894018e-05 tokens_per_second_per_gpu:4713.947531245812 mfu:22.236494787270296 Step 246 | loss:1.4008572101593018 lr:4.992857028634214e-05 tokens_per_second_per_gpu:5307.037745926093 mfu:25.034202521542355 Step 247 | loss:1.7859666347503662 lr:4.99277425218364e-05 tokens_per_second_per_gpu:3341.6522454702954 mfu:15.763143786547914 Step 248 | loss:1.510225534439087 lr:4.992690999558109e-05 tokens_per_second_per_gpu:3317.162412837886 mfu:15.647621067624533 Step 249 | loss:1.6023104190826416 lr:4.992607270773523e-05 tokens_per_second_per_gpu:4585.782742889998 mfu:21.631919613428156 Step 250 | loss:1.4407260417938232 lr:4.9925230658458764e-05 tokens_per_second_per_gpu:4589.93397664038 mfu:21.651501691302226 Step 251 | loss:1.4945588111877441 lr:4.9924383847912546e-05 tokens_per_second_per_gpu:4383.189075389151 mfu:20.67625071778265 Step 252 | loss:1.3608452081680298 lr:4.992353227625833e-05 tokens_per_second_per_gpu:5040.570301671864 mfu:23.77723012296107 Step 253 | loss:1.4075710773468018 lr:4.9922675943658794e-05 tokens_per_second_per_gpu:4907.989200409552 mfu:23.151822447638292 Step 254 | loss:1.7199009656906128 lr:4.992181485027751e-05 tokens_per_second_per_gpu:5349.33604763088 mfu:25.233730827518286 Step 255 | loss:1.5480073690414429 lr:4.992094899627896e-05 tokens_per_second_per_gpu:5343.184930392213 mfu:25.20471495801467 Step 256 | loss:1.6670904159545898 lr:4.992007838182855e-05 tokens_per_second_per_gpu:4641.656029156063 mfu:21.89548343771083 Step 257 | loss:1.4356358051300049 lr:4.991920300709258e-05 tokens_per_second_per_gpu:5309.772146436959 mfu:25.047101155288946 Step 258 | loss:1.4733573198318481 lr:4.991832287223828e-05 tokens_per_second_per_gpu:3176.0832087622325 mfu:14.982126391405377 Step 259 | loss:1.7327684164047241 lr:4.991743797743377e-05 tokens_per_second_per_gpu:4104.560021476116 mfu:19.361909931456196 Step 260 | loss:1.3967351913452148 lr:4.9916548322848065e-05 tokens_per_second_per_gpu:5265.847386632746 mfu:24.83990056895566 Step 261 | loss:1.5323807001113892 lr:4.991565390865113e-05 tokens_per_second_per_gpu:5305.246993866297 mfu:25.02575523854249 Step 262 | loss:1.6737775802612305 lr:4.99147547350138e-05 tokens_per_second_per_gpu:3918.5573557644007 mfu:18.484503621966823 Step 263 | loss:1.496423363685608 lr:4.9913850802107865e-05 tokens_per_second_per_gpu:4693.778664537467 mfu:22.141354801843534 Step 264 | loss:1.50213623046875 lr:4.991294211010597e-05 tokens_per_second_per_gpu:3823.277341201914 mfu:18.035051536828778 Step 265 | loss:1.373533010482788 lr:4.991202865918171e-05 tokens_per_second_per_gpu:5312.737375912549 mfu:25.061088648645626 Step 266 | loss:1.5892926454544067 lr:4.9911110449509555e-05 tokens_per_second_per_gpu:4717.296053272766 mfu:22.252290336988207 Step 267 | loss:1.2977184057235718 lr:4.991018748126494e-05 tokens_per_second_per_gpu:4779.561953871997 mfu:22.546009213772898 Step 268 | loss:1.6898622512817383 lr:4.990925975462413e-05 tokens_per_second_per_gpu:4179.574411336876 mfu:19.715765607204084 Step 269 | loss:1.4382339715957642 lr:4.9908327269764366e-05 tokens_per_second_per_gpu:5334.868535423452 mfu:25.16548510402373 Step 270 | loss:1.87222421169281 lr:4.9907390026863774e-05 tokens_per_second_per_gpu:3233.4523954318165 mfu:15.252746633118376 Step 271 | loss:1.6200120449066162 lr:4.990644802610138e-05 tokens_per_second_per_gpu:5137.2354577203005 mfu:24.233216156817843 Step 272 | loss:1.712958574295044 lr:4.990550126765712e-05 tokens_per_second_per_gpu:3390.8346917382446 mfu:15.99514577698446 Step 273 | loss:1.3057585954666138 lr:4.990454975171187e-05 tokens_per_second_per_gpu:5259.160457238089 mfu:24.80835718209326 Step 274 | loss:1.6532201766967773 lr:4.990359347844736e-05 tokens_per_second_per_gpu:5186.149284135093 mfu:24.463951021575774 Step 275 | loss:1.5250109434127808 lr:4.990263244804629e-05 tokens_per_second_per_gpu:5004.416996589994 mfu:23.60668881449997 Step 276 | loss:1.5094600915908813 lr:4.9901666660692215e-05 tokens_per_second_per_gpu:5148.563309710746 mfu:24.28665156738762 Step 277 | loss:1.471766471862793 lr:4.990069611656963e-05 tokens_per_second_per_gpu:4410.943478792159 mfu:20.80717297402416 Step 278 | loss:1.4847631454467773 lr:4.9899720815863924e-05 tokens_per_second_per_gpu:5327.486637130818 mfu:25.13066343029565 Step 279 | loss:1.3701748847961426 lr:4.989874075876142e-05 tokens_per_second_per_gpu:4038.9316344306526 mfu:19.052329632405282 Step 280 | loss:1.5071722269058228 lr:4.989775594544931e-05 tokens_per_second_per_gpu:4015.6270515629417 mfu:18.942397938846444 Step 281 | loss:1.6260371208190918 lr:4.9896766376115724e-05 tokens_per_second_per_gpu:4383.802438801378 mfu:20.679144057648717 Step 282 | loss:1.5463939905166626 lr:4.989577205094968e-05 tokens_per_second_per_gpu:4609.073870331995 mfu:21.741787835448175 Step 283 | loss:1.645214557647705 lr:4.989477297014114e-05 tokens_per_second_per_gpu:3780.486902040769 mfu:17.833201734503902 Step 284 | loss:1.353263258934021 lr:4.989376913388093e-05 tokens_per_second_per_gpu:5304.431198619776 mfu:25.021906993175634 Step 285 | loss:1.5524423122406006 lr:4.9892760542360815e-05 tokens_per_second_per_gpu:4866.996689815599 mfu:22.95845378112311 Step 286 | loss:1.5185914039611816 lr:4.9891747195773455e-05 tokens_per_second_per_gpu:3388.0459432547514 mfu:15.981990774578264 Step 287 | loss:1.5653663873672485 lr:4.989072909431242e-05 tokens_per_second_per_gpu:4896.749278471034 mfu:23.09880181812587 Step 288 | loss:1.38550865650177 lr:4.9889706238172194e-05 tokens_per_second_per_gpu:3219.284038574286 mfu:15.185912076450455 Step 289 | loss:1.6792546510696411 lr:4.988867862754816e-05 tokens_per_second_per_gpu:3577.858784046987 mfu:16.877370330005355 Step 290 | loss:1.462934970855713 lr:4.988764626263662e-05 tokens_per_second_per_gpu:5299.649530585374 mfu:24.999351049220664 Step 291 | loss:1.3444358110427856 lr:4.988660914363477e-05 tokens_per_second_per_gpu:4594.0730611636745 mfu:21.671026459199243 Step 292 | loss:1.5134038925170898 lr:4.988556727074073e-05 tokens_per_second_per_gpu:5248.977495680219 mfu:24.760322415032395 Step 293 | loss:1.6222684383392334 lr:4.988452064415352e-05 tokens_per_second_per_gpu:4348.464593768142 mfu:20.512449413368856 Step 294 | loss:1.6459733247756958 lr:4.988346926407307e-05 tokens_per_second_per_gpu:5308.298191832315 mfu:25.040148259936256 Step 295 | loss:1.5090484619140625 lr:4.9882413130700203e-05 tokens_per_second_per_gpu:4203.843249348289 mfu:19.830245856794654 Step 296 | loss:1.5722264051437378 lr:4.988135224423669e-05 tokens_per_second_per_gpu:4506.680654822519 mfu:21.25878156780595 Step 297 | loss:1.3587403297424316 lr:4.988028660488516e-05 tokens_per_second_per_gpu:4670.811931512844 mfu:22.033016803637665 Step 298 | loss:1.405550241470337 lr:4.987921621284918e-05 tokens_per_second_per_gpu:5325.124696960414 mfu:25.119521755523312 Step 299 | loss:1.561415672302246 lr:4.987814106833323e-05 tokens_per_second_per_gpu:4279.140132828444 mfu:20.185434103143603 Step 300 | loss:1.4839575290679932 lr:4.9877061171542675e-05 tokens_per_second_per_gpu:4260.887001816063 mfu:20.099330969852918 Step 301 | loss:1.4848885536193848 lr:4.98759765226838e-05 tokens_per_second_per_gpu:5358.515930168169 mfu:25.277033899696143 Step 302 | loss:1.6238934993743896 lr:4.9874887121963797e-05 tokens_per_second_per_gpu:3315.0506450492667 mfu:15.637659498660875 Step 303 | loss:1.4698081016540527 lr:4.987379296959077e-05 tokens_per_second_per_gpu:5254.83460409519 mfu:24.787951394751556 Step 304 | loss:1.4623703956604004 lr:4.9872694065773726e-05 tokens_per_second_per_gpu:4713.912040771755 mfu:22.23632737264887 Step 305 | loss:1.692704677581787 lr:4.987159041072257e-05 tokens_per_second_per_gpu:4210.593115073705 mfu:19.86208612506729 Step 306 | loss:1.5591987371444702 lr:4.987048200464813e-05 tokens_per_second_per_gpu:4994.060069558748 mfu:23.55783342261962 Step 307 | loss:1.4173791408538818 lr:4.986936884776215e-05 tokens_per_second_per_gpu:5340.3927565300955 mfu:25.19154379751308 Step 308 | loss:1.6231797933578491 lr:4.986825094027725e-05 tokens_per_second_per_gpu:5312.083252774534 mfu:25.058003038198688 Step 309 | loss:1.7151012420654297 lr:4.986712828240698e-05 tokens_per_second_per_gpu:3990.084033682121 mfu:18.82190716541437 Step 310 | loss:1.6383123397827148 lr:4.986600087436579e-05 tokens_per_second_per_gpu:4963.614407661341 mfu:23.414216040883982 Step 311 | loss:1.5687750577926636 lr:4.9864868716369045e-05 tokens_per_second_per_gpu:4050.320942816427 mfu:19.106054943277368 Step 312 | loss:1.4644712209701538 lr:4.9863731808633007e-05 tokens_per_second_per_gpu:3558.4784673263525 mfu:16.785950069411125 Step 313 | loss:1.4154512882232666 lr:4.9862590151374856e-05 tokens_per_second_per_gpu:5302.472225372131 mfu:25.012666182131188 Step 314 | loss:1.6542234420776367 lr:4.986144374481267e-05 tokens_per_second_per_gpu:3925.3654181733045 mfu:18.51661841392485 Step 315 | loss:1.4215209484100342 lr:4.986029258916545e-05 tokens_per_second_per_gpu:4116.231263782894 mfu:19.416965172736543 Step 316 | loss:1.533886432647705 lr:4.985913668465307e-05 tokens_per_second_per_gpu:5313.752638743535 mfu:25.065877816641084 Step 317 | loss:1.4240328073501587 lr:4.985797603149635e-05 tokens_per_second_per_gpu:5274.330353974189 mfu:24.87991617324872 Step 318 | loss:1.4520387649536133 lr:4.9856810629916984e-05 tokens_per_second_per_gpu:3685.393209091624 mfu:17.384628560205734 Step 319 | loss:1.5628740787506104 lr:4.985564048013761e-05 tokens_per_second_per_gpu:3415.016625149515 mfu:16.10921608274871 Step 320 | loss:1.6620465517044067 lr:4.985446558238174e-05 tokens_per_second_per_gpu:3405.7933087813844 mfu:16.06570812578019 Step 321 | loss:1.4814876317977905 lr:4.9853285936873813e-05 tokens_per_second_per_gpu:4943.610543324275 mfu:23.31985439979485 Step 322 | loss:1.526275634765625 lr:4.9852101543839157e-05 tokens_per_second_per_gpu:5020.568969564914 mfu:23.68288042683343 Step 323 | loss:1.5288076400756836 lr:4.9850912403504026e-05 tokens_per_second_per_gpu:5311.570578463998 mfu:25.055584666004634 Step 324 | loss:1.379596471786499 lr:4.984971851609557e-05 tokens_per_second_per_gpu:5339.188783020553 mfu:25.185864449049504 Step 325 | loss:1.5701876878738403 lr:4.984851988184184e-05 tokens_per_second_per_gpu:4087.8425649231444 mfu:19.283050836603625 Step 326 | loss:1.5615607500076294 lr:4.984731650097182e-05 tokens_per_second_per_gpu:4189.723015244517 mfu:19.763638303366804 Step 327 | loss:1.528486967086792 lr:4.984610837371536e-05 tokens_per_second_per_gpu:5223.986284839022 mfu:24.64243460955421 Step 328 | loss:1.5202593803405762 lr:4.984489550030326e-05 tokens_per_second_per_gpu:4478.317789862012 mfu:21.124989094583473 Step 329 | loss:1.5842427015304565 lr:4.984367788096719e-05 tokens_per_second_per_gpu:3607.9699530234466 mfu:17.019409851562507 Step 330 | loss:1.5076749324798584 lr:4.984245551593975e-05 tokens_per_second_per_gpu:4670.630807707477 mfu:22.032162411744842 Step 331 | loss:1.7322670221328735 lr:4.9841228405454434e-05 tokens_per_second_per_gpu:5141.703004705033 mfu:24.254290338186944 Step 332 | loss:1.6323095560073853 lr:4.9839996549745646e-05 tokens_per_second_per_gpu:4716.315520676359 mfu:22.247664997434843 Step 333 | loss:1.5320968627929688 lr:4.983875994904871e-05 tokens_per_second_per_gpu:4026.3349678012605 mfu:18.992909006701492 Step 334 | loss:1.3893804550170898 lr:4.9837518603599826e-05 tokens_per_second_per_gpu:4735.799540037856 mfu:22.339574441079524 Step 335 | loss:1.5289050340652466 lr:4.983627251363614e-05 tokens_per_second_per_gpu:4865.677680429069 mfu:22.952231788800642 Step 336 | loss:1.3503154516220093 lr:4.983502167939566e-05 tokens_per_second_per_gpu:5333.869232880525 mfu:25.160771223430146 Step 337 | loss:1.701777696609497 lr:4.983376610111733e-05 tokens_per_second_per_gpu:4576.079617081014 mfu:21.5861483134632 Step 338 | loss:1.6420841217041016 lr:4.9832505779041004e-05 tokens_per_second_per_gpu:4111.699645834801 mfu:19.395588757701642 Step 339 | loss:1.3236825466156006 lr:4.983124071340742e-05 tokens_per_second_per_gpu:4217.300477830602 mfu:19.893725899585668 Step 340 | loss:1.506545066833496 lr:4.9829970904458244e-05 tokens_per_second_per_gpu:4148.258027008917 mfu:19.568040879202968 Step 341 | loss:1.5275367498397827 lr:4.982869635243603e-05 tokens_per_second_per_gpu:3988.280336564214 mfu:18.81339881836674 Step 342 | loss:1.4082286357879639 lr:4.9827417057584244e-05 tokens_per_second_per_gpu:5027.490472142771 mfu:23.715530335423296 Step 343 | loss:1.3268636465072632 lr:4.982613302014726e-05 tokens_per_second_per_gpu:4486.829107344189 mfu:21.16513843132741 Step 344 | loss:1.5416654348373413 lr:4.9824844240370364e-05 tokens_per_second_per_gpu:3548.685355428885 mfu:16.739754289713584 Step 345 | loss:1.2369282245635986 lr:4.9823550718499735e-05 tokens_per_second_per_gpu:4772.484955516778 mfu:22.512625805070908 Step 346 | loss:1.4576061964035034 lr:4.9822252454782467e-05 tokens_per_second_per_gpu:4785.674294177881 mfu:22.57484216586855 Step 347 | loss:1.558302402496338 lr:4.982094944946656e-05 tokens_per_second_per_gpu:4677.981784508287 mfu:22.066838223520236 Step 348 | loss:1.5336869955062866 lr:4.981964170280091e-05 tokens_per_second_per_gpu:5298.9747736901145 mfu:24.996168105820328 Step 349 | loss:1.6473851203918457 lr:4.981832921503532e-05 tokens_per_second_per_gpu:5336.959306732095 mfu:25.175347629008968 Step 350 | loss:1.3986685276031494 lr:4.9817011986420524e-05 tokens_per_second_per_gpu:4989.474111999152 mfu:23.536200678365965 Step 351 | loss:1.60263991355896 lr:4.981569001720813e-05 tokens_per_second_per_gpu:5306.913197378264 mfu:25.033615004792075 Step 352 | loss:1.5006065368652344 lr:4.981436330765066e-05 tokens_per_second_per_gpu:5111.483984258507 mfu:24.111742062844133 Step 353 | loss:1.6872104406356812 lr:4.981303185800156e-05 tokens_per_second_per_gpu:3211.7749924439067 mfu:15.150490624678074 Step 354 | loss:1.3522461652755737 lr:4.981169566851514e-05 tokens_per_second_per_gpu:4197.520240777252 mfu:19.80041914654857 Step 355 | loss:1.5962333679199219 lr:4.9810354739446665e-05 tokens_per_second_per_gpu:5327.066410530101 mfu:25.12868114972202 Step 356 | loss:1.5436283349990845 lr:4.980900907105227e-05 tokens_per_second_per_gpu:5132.812919809166 mfu:24.212354290928246 Step 357 | loss:1.492647647857666 lr:4.9807658663589015e-05 tokens_per_second_per_gpu:5324.941732555111 mfu:25.118658681206547 Step 358 | loss:1.4759008884429932 lr:4.980630351731485e-05 tokens_per_second_per_gpu:5321.873018923619 mfu:25.104183035430268 Step 359 | loss:1.405469536781311 lr:4.980494363248864e-05 tokens_per_second_per_gpu:5189.61929818996 mfu:24.480319669918032 Step 360 | loss:1.4908846616744995 lr:4.9803579009370164e-05 tokens_per_second_per_gpu:4492.592004119601 mfu:21.19232299866861 Step 361 | loss:1.4338384866714478 lr:4.9802209648220085e-05 tokens_per_second_per_gpu:4446.664156865224 mfu:20.975673507070937 Step 362 | loss:1.605405569076538 lr:4.980083554929998e-05 tokens_per_second_per_gpu:5298.215170658049 mfu:24.992584928716433 Step 363 | loss:1.3875007629394531 lr:4.979945671287233e-05 tokens_per_second_per_gpu:4288.16418944463 mfu:20.22800211786498 Step 364 | loss:1.5052506923675537 lr:4.979807313920053e-05 tokens_per_second_per_gpu:5283.102404503072 mfu:24.921295432259612 Step 365 | loss:1.5329453945159912 lr:4.979668482854888e-05 tokens_per_second_per_gpu:4049.2800872091943 mfu:19.10114504978977 Step 366 | loss:1.5603506565093994 lr:4.9795291781182556e-05 tokens_per_second_per_gpu:4144.1004011592295 mfu:19.548428648705872 Step 367 | loss:1.4769781827926636 lr:4.979389399736768e-05 tokens_per_second_per_gpu:5318.213224268212 mfu:25.086919159615352 Step 368 | loss:1.433994174003601 lr:4.979249147737125e-05 tokens_per_second_per_gpu:5090.574154104248 mfu:24.01310682642159 Step 369 | loss:1.7520415782928467 lr:4.979108422146119e-05 tokens_per_second_per_gpu:3375.3249807296 mfu:15.921983823927114 Step 370 | loss:1.473555326461792 lr:4.97896722299063e-05 tokens_per_second_per_gpu:5330.8630766638635 mfu:25.146590671653016 Step 371 | loss:1.6982985734939575 lr:4.978825550297631e-05 tokens_per_second_per_gpu:5343.938049273227 mfu:25.208267548271746 Step 372 | loss:1.5413968563079834 lr:4.9786834040941855e-05 tokens_per_second_per_gpu:4581.201593139651 mfu:21.610309548431026 Step 373 | loss:1.7553341388702393 lr:4.978540784407445e-05 tokens_per_second_per_gpu:3548.4994972685067 mfu:16.73887756506041 Step 374 | loss:1.3983341455459595 lr:4.9783976912646536e-05 tokens_per_second_per_gpu:4640.272696734282 mfu:21.888958022656446 Step 375 | loss:1.7756692171096802 lr:4.9782541246931455e-05 tokens_per_second_per_gpu:4701.121426080614 mfu:22.17599186084686 Step 376 | loss:1.443861484527588 lr:4.9781100847203455e-05 tokens_per_second_per_gpu:4230.762043197739 mfu:19.95722640020234 Step 377 | loss:1.2948863506317139 lr:4.9779655713737674e-05 tokens_per_second_per_gpu:5213.315101113121 mfu:24.592096815227453 Step 378 | loss:1.3763232231140137 lr:4.9778205846810175e-05 tokens_per_second_per_gpu:5319.264163592962 mfu:25.091876619718942 Step 379 | loss:1.3449511528015137 lr:4.97767512466979e-05 tokens_per_second_per_gpu:4395.26323323463 mfu:20.733206580403532 Step 380 | loss:1.6336826086044312 lr:4.9775291913678726e-05 tokens_per_second_per_gpu:4019.205313171871 mfu:18.959277209370146 Step 381 | loss:1.606052279472351 lr:4.9773827848031404e-05 tokens_per_second_per_gpu:5341.00582091828 mfu:25.194435726831713 Step 382 | loss:1.3939599990844727 lr:4.977235905003561e-05 tokens_per_second_per_gpu:5215.33947880126 mfu:24.601646150176855 Step 383 | loss:1.490114450454712 lr:4.9770885519971924e-05 tokens_per_second_per_gpu:4635.279581190781 mfu:21.86540464472439 Step 384 | loss:1.6552590131759644 lr:4.97694072581218e-05 tokens_per_second_per_gpu:4815.1509225405935 mfu:22.71388845108686 Step 385 | loss:1.5554946660995483 lr:4.9767924264767646e-05 tokens_per_second_per_gpu:3707.602833510642 mfu:17.48939514794291 Step 386 | loss:1.253260612487793 lr:4.976643654019273e-05 tokens_per_second_per_gpu:4280.837240554562 mfu:20.19343964984414 Step 387 | loss:1.4576351642608643 lr:4.976494408468125e-05 tokens_per_second_per_gpu:3399.6571130121515 mfu:16.036762643393764 Step 388 | loss:1.6091960668563843 lr:4.9763446898518284e-05 tokens_per_second_per_gpu:5283.985752125818 mfu:24.925462333710755 Step 389 | loss:1.4567009210586548 lr:4.976194498198984e-05 tokens_per_second_per_gpu:4441.782574099419 mfu:20.952646248280733 Step 390 | loss:1.4510891437530518 lr:4.976043833538281e-05 tokens_per_second_per_gpu:5326.98518986964 mfu:25.12829801800895 Step 391 | loss:1.3204679489135742 lr:4.975892695898501e-05 tokens_per_second_per_gpu:5312.337149286801 mfu:25.059200711366266 Step 392 | loss:1.4791347980499268 lr:4.9757410853085126e-05 tokens_per_second_per_gpu:5339.873367084934 mfu:25.189093748883277 Step 393 | loss:1.3340513706207275 lr:4.975589001797278e-05 tokens_per_second_per_gpu:5287.212936425309 mfu:24.94068551266587 Step 394 | loss:1.4509773254394531 lr:4.975436445393848e-05 tokens_per_second_per_gpu:3927.489670445881 mfu:18.526638874329404 Step 395 | loss:1.6963815689086914 lr:4.975283416127365e-05 tokens_per_second_per_gpu:3181.7124588413217 mfu:15.008680524477542 Step 396 | loss:1.4082560539245605 lr:4.975129914027061e-05 tokens_per_second_per_gpu:4057.1675230052406 mfu:19.13835143017504 Step 397 | loss:1.6021920442581177 lr:4.9749759391222574e-05 tokens_per_second_per_gpu:4022.160645455373 mfu:18.97321801598311 Step 398 | loss:1.4426478147506714 lr:4.974821491442367e-05 tokens_per_second_per_gpu:5301.423334667174 mfu:25.007718385716696 Step 399 | loss:1.3737531900405884 lr:4.974666571016893e-05 tokens_per_second_per_gpu:5291.3869964454525 mfu:24.96037526594896 Step 400 | loss:1.611847162246704 lr:4.974511177875428e-05 tokens_per_second_per_gpu:3971.3033663253887 mfu:18.733315553180393 Step 401 | loss:1.539382815361023 lr:4.974355312047657e-05 tokens_per_second_per_gpu:4672.866777971203 mfu:22.0427098649747 Step 402 | loss:1.517664909362793 lr:4.9741989735633535e-05 tokens_per_second_per_gpu:4134.594457989788 mfu:19.503587492894468 Step 403 | loss:1.6341809034347534 lr:4.9740421624523795e-05 tokens_per_second_per_gpu:4342.048875566134 mfu:20.482185375975586 Step 404 | loss:1.7147492170333862 lr:4.973884878744692e-05 tokens_per_second_per_gpu:4172.687005447491 mfu:19.683276538511237 Step 405 | loss:1.5394511222839355 lr:4.973727122470334e-05 tokens_per_second_per_gpu:5042.014856581563 mfu:23.784044334936603 Step 406 | loss:1.4036848545074463 lr:4.973568893659441e-05 tokens_per_second_per_gpu:4319.059291085483 mfu:20.373739583552776 Step 407 | loss:1.522486686706543 lr:4.973410192342238e-05 tokens_per_second_per_gpu:5322.066443929449 mfu:25.10509545418447 Step 408 | loss:1.3462365865707397 lr:4.9732510185490416e-05 tokens_per_second_per_gpu:4309.833257389657 mfu:20.330218808485895 Step 409 | loss:1.4648970365524292 lr:4.973091372310256e-05 tokens_per_second_per_gpu:4661.483131832496 mfu:21.989011263888113 Step 410 | loss:1.5161843299865723 lr:4.972931253656378e-05 tokens_per_second_per_gpu:5300.969977577363 mfu:25.005579822973367 Step 411 | loss:1.4286842346191406 lr:4.9727706626179926e-05 tokens_per_second_per_gpu:5083.444599346727 mfu:23.979475500202888 Step 412 | loss:1.5655758380889893 lr:4.972609599225778e-05 tokens_per_second_per_gpu:5278.3841426262725 mfu:24.899038585968263 Step 413 | loss:1.4249958992004395 lr:4.9724480635105e-05 tokens_per_second_per_gpu:5102.116076420152 mfu:24.06755204324072 Step 414 | loss:1.5448198318481445 lr:4.972286055503015e-05 tokens_per_second_per_gpu:3899.775790407454 mfu:18.395907773712622 Step 415 | loss:1.640785574913025 lr:4.972123575234271e-05 tokens_per_second_per_gpu:4984.876275243139 mfu:23.51451189791601 Step 416 | loss:1.411759853363037 lr:4.9719606227353056e-05 tokens_per_second_per_gpu:5113.565502818453 mfu:24.121560941035085 Step 417 | loss:1.6253743171691895 lr:4.971797198037245e-05 tokens_per_second_per_gpu:4639.857319055627 mfu:21.886998615275488 Step 418 | loss:1.5807229280471802 lr:4.971633301171307e-05 tokens_per_second_per_gpu:3960.6189107457662 mfu:18.682915153255216 Step 419 | loss:1.4801337718963623 lr:4.971468932168801e-05 tokens_per_second_per_gpu:4229.8614573749 mfu:19.95297818322022 Step 420 | loss:1.2278228998184204 lr:4.971304091061124e-05 tokens_per_second_per_gpu:5328.859741626243 mfu:25.137140598476357 Step 421 | loss:1.6955949068069458 lr:4.9711387778797644e-05 tokens_per_second_per_gpu:5260.511037642977 mfu:24.814728100295895 Step 422 | loss:1.5908892154693604 lr:4.970972992656301e-05 tokens_per_second_per_gpu:4250.881312255926 mfu:20.052132425051077 Step 423 | loss:1.5879396200180054 lr:4.970806735422402e-05 tokens_per_second_per_gpu:4712.978770044686 mfu:22.231924975396883 Step 424 | loss:1.5768089294433594 lr:4.970640006209827e-05 tokens_per_second_per_gpu:4382.661961826989 mfu:20.67376423317508 Step 425 | loss:1.6254304647445679 lr:4.970472805050424e-05 tokens_per_second_per_gpu:4849.980441775867 mfu:22.8781852358484 Step 426 | loss:1.2907787561416626 lr:4.970305131976133e-05 tokens_per_second_per_gpu:4606.566725050537 mfu:21.729961203392442 Step 427 | loss:1.3884546756744385 lr:4.970136987018982e-05 tokens_per_second_per_gpu:5328.479942021711 mfu:25.135349018941287 Step 428 | loss:1.4943451881408691 lr:4.969968370211091e-05 tokens_per_second_per_gpu:5343.416329110938 mfu:25.20580650525159 Step 429 | loss:1.4353548288345337 lr:4.969799281584671e-05 tokens_per_second_per_gpu:4722.850097687201 mfu:22.278489712108794 Step 430 | loss:1.6362287998199463 lr:4.9696297211720194e-05 tokens_per_second_per_gpu:4726.748175937596 mfu:22.296877612296633 Step 431 | loss:1.3956366777420044 lr:4.9694596890055275e-05 tokens_per_second_per_gpu:4526.164563354454 mfu:21.350690488648674 Step 432 | loss:1.4941786527633667 lr:4.969289185117674e-05 tokens_per_second_per_gpu:4746.16255471968 mfu:22.388458549446312 Step 433 | loss:1.4789378643035889 lr:4.9691182095410306e-05 tokens_per_second_per_gpu:4203.121350246036 mfu:19.82684053556064 Step 434 | loss:1.5466406345367432 lr:4.9689467623082554e-05 tokens_per_second_per_gpu:5302.19340150866 mfu:25.01135092239494 Step 435 | loss:1.4379931688308716 lr:4.9687748434521e-05 tokens_per_second_per_gpu:4273.827530784358 mfu:20.160373652878278 Step 436 | loss:1.5382267236709595 lr:4.9686024530054046e-05 tokens_per_second_per_gpu:3286.4624049149115 mfu:15.502803892290386 Step 437 | loss:1.4414770603179932 lr:4.968429591001099e-05 tokens_per_second_per_gpu:5343.7788197226255 mfu:25.207516435314197 Step 438 | loss:1.3586856126785278 lr:4.968256257472203e-05 tokens_per_second_per_gpu:5311.18558926013 mfu:25.053768606244056 Step 439 | loss:1.4181493520736694 lr:4.96808245245183e-05 tokens_per_second_per_gpu:5322.84138617325 mfu:25.108750988967262 Step 440 | loss:1.4379595518112183 lr:4.967908175973178e-05 tokens_per_second_per_gpu:5311.9559415042195 mfu:25.057402489215075 Step 441 | loss:1.62490975856781 lr:4.9677334280695374e-05 tokens_per_second_per_gpu:5339.420637981856 mfu:25.186958148460505 Step 442 | loss:1.5329456329345703 lr:4.967558208774291e-05 tokens_per_second_per_gpu:5326.849408238709 mfu:25.12765751288911 Step 443 | loss:1.4745539426803589 lr:4.967382518120908e-05 tokens_per_second_per_gpu:4578.965818372662 mfu:21.599763017392632 Step 444 | loss:1.4828770160675049 lr:4.967206356142949e-05 tokens_per_second_per_gpu:5348.26540812068 mfu:25.228680438278733 Step 445 | loss:1.4600214958190918 lr:4.967029722874067e-05 tokens_per_second_per_gpu:4931.816489345591 mfu:23.264219834904292 Step 446 | loss:1.5465294122695923 lr:4.966852618348e-05 tokens_per_second_per_gpu:3989.085815420613 mfu:18.81719839956124 Step 447 | loss:1.5327348709106445 lr:4.9666750425985805e-05 tokens_per_second_per_gpu:4723.497022871365 mfu:22.28154136857931 Step 448 | loss:1.5412062406539917 lr:4.9664969956597284e-05 tokens_per_second_per_gpu:5173.157024398672 mfu:24.402664315690984 Step 449 | loss:1.5753051042556763 lr:4.9663184775654564e-05 tokens_per_second_per_gpu:4518.850278054432 mfu:21.316187756942714 Step 450 | loss:1.3737728595733643 lr:4.966139488349863e-05 tokens_per_second_per_gpu:3881.3187205073323 mfu:18.308842625892897 Step 451 | loss:1.5411864519119263 lr:4.965960028047142e-05 tokens_per_second_per_gpu:3877.9413722323357 mfu:18.292911097844705 Step 452 | loss:1.375693917274475 lr:4.965780096691571e-05 tokens_per_second_per_gpu:5306.121947778829 mfu:25.02988254543044 Step 453 | loss:1.310425877571106 lr:4.965599694317524e-05 tokens_per_second_per_gpu:5255.511423123978 mfu:24.79114406558758 Step 454 | loss:1.4634066820144653 lr:4.96541882095946e-05 tokens_per_second_per_gpu:5239.519156848032 mfu:24.715705817001957 Step 455 | loss:1.3741838932037354 lr:4.9652374766519296e-05 tokens_per_second_per_gpu:4058.709462958796 mfu:19.14562502401804 Step 456 | loss:1.6030598878860474 lr:4.965055661429574e-05 tokens_per_second_per_gpu:4780.026497585262 mfu:22.548200545727706 Step 457 | loss:1.5417871475219727 lr:4.9648733753271246e-05 tokens_per_second_per_gpu:5107.076944753632 mfu:24.090953305581166 Step 458 | loss:1.469939112663269 lr:4.964690618379401e-05 tokens_per_second_per_gpu:4481.143966832271 mfu:21.1383206535477 Step 459 | loss:1.3490492105484009 lr:4.964507390621314e-05 tokens_per_second_per_gpu:2993.6765435476514 mfu:14.121683029801936 Step 460 | loss:1.6123100519180298 lr:4.964323692087865e-05 tokens_per_second_per_gpu:4624.304741975868 mfu:21.813634455646987 Step 461 | loss:1.3373429775238037 lr:4.9641395228141455e-05 tokens_per_second_per_gpu:5319.890796623594 mfu:25.094832554639048 Step 462 | loss:1.4600664377212524 lr:4.963954882835332e-05 tokens_per_second_per_gpu:5252.078917982778 mfu:24.774952353190773 Step 463 | loss:1.393691062927246 lr:4.963769772186698e-05 tokens_per_second_per_gpu:5119.261443738992 mfu:24.148429666185002 Step 464 | loss:1.4694124460220337 lr:4.963584190903603e-05 tokens_per_second_per_gpu:4171.88470561042 mfu:19.679491953293297 Step 465 | loss:1.6086598634719849 lr:4.963398139021498e-05 tokens_per_second_per_gpu:4457.977450503109 mfu:21.029040243407778 Step 466 | loss:1.5347737073898315 lr:4.9632116165759204e-05 tokens_per_second_per_gpu:5103.999603913102 mfu:24.076436963787895 Step 467 | loss:1.5627515316009521 lr:4.963024623602502e-05 tokens_per_second_per_gpu:4535.93387297002 mfu:21.3967739889214 Step 468 | loss:1.5295939445495605 lr:4.9628371601369636e-05 tokens_per_second_per_gpu:5015.161187742344 mfu:23.657370997313645 Step 469 | loss:1.3886995315551758 lr:4.962649226215113e-05 tokens_per_second_per_gpu:5302.436451021232 mfu:25.01249742841426 Step 470 | loss:1.4728370904922485 lr:4.96246082187285e-05 tokens_per_second_per_gpu:5083.338283001708 mfu:23.978973987863995 Step 471 | loss:1.6499978303909302 lr:4.962271947146164e-05 tokens_per_second_per_gpu:4606.248638693016 mfu:21.728460735772885 Step 472 | loss:1.5636488199234009 lr:4.9620826020711354e-05 tokens_per_second_per_gpu:4676.749150331842 mfu:22.06102367780087 Step 473 | loss:1.41048264503479 lr:4.961892786683932e-05 tokens_per_second_per_gpu:4727.073492004768 mfu:22.298412183690132 Step 474 | loss:1.4903228282928467 lr:4.961702501020813e-05 tokens_per_second_per_gpu:4626.128489088125 mfu:21.82223738193885 Step 475 | loss:1.6335573196411133 lr:4.961511745118128e-05 tokens_per_second_per_gpu:5320.277108679361 mfu:25.096654854517734 Step 476 | loss:1.5207387208938599 lr:4.961320519012315e-05 tokens_per_second_per_gpu:4227.461283536932 mfu:19.94165615371464 Step 477 | loss:1.3719621896743774 lr:4.9611288227399016e-05 tokens_per_second_per_gpu:4956.102638210533 mfu:23.378781742744497 Step 478 | loss:1.3675333261489868 lr:4.960936656337507e-05 tokens_per_second_per_gpu:4734.514938911412 mfu:22.333514758390535 Step 479 | loss:1.461461067199707 lr:4.96074401984184e-05 tokens_per_second_per_gpu:3693.292034029911 mfu:17.421888665118136 Step 480 | loss:1.6532546281814575 lr:4.9605509132896965e-05 tokens_per_second_per_gpu:4019.148965890707 mfu:18.959011409631056 Step 481 | loss:1.5593034029006958 lr:4.960357336717965e-05 tokens_per_second_per_gpu:4312.737483940621 mfu:20.343918540638942 Step 482 | loss:1.5878956317901611 lr:4.960163290163623e-05 tokens_per_second_per_gpu:5285.5909926573195 mfu:24.933034527180123 Step 483 | loss:1.499602198600769 lr:4.959968773663738e-05 tokens_per_second_per_gpu:4761.722062438198 mfu:22.461855402080328 Step 484 | loss:1.4840840101242065 lr:4.959773787255467e-05 tokens_per_second_per_gpu:4112.939966746409 mfu:19.401439563062265 Step 485 | loss:1.491748571395874 lr:4.9595783309760556e-05 tokens_per_second_per_gpu:5314.162736015914 mfu:25.067812315444705 Step 486 | loss:1.46140718460083 lr:4.959382404862841e-05 tokens_per_second_per_gpu:5322.868269178082 mfu:25.10887780068777 Step 487 | loss:1.3559575080871582 lr:4.959186008953249e-05 tokens_per_second_per_gpu:4020.015770986255 mfu:18.96310027715896 Step 488 | loss:1.3794444799423218 lr:4.958989143284797e-05 tokens_per_second_per_gpu:4910.442270991197 mfu:23.163394000108916 Step 489 | loss:1.343973159790039 lr:4.958791807895089e-05 tokens_per_second_per_gpu:5359.038698035341 mfu:25.279499884918994 Step 490 | loss:1.502185344696045 lr:4.958594002821822e-05 tokens_per_second_per_gpu:5312.851991420814 mfu:25.061629309553528 Step 491 | loss:1.5502148866653442 lr:4.958395728102779e-05 tokens_per_second_per_gpu:5335.309464036383 mfu:25.167565039521104 Step 492 | loss:1.498388409614563 lr:4.9581969837758366e-05 tokens_per_second_per_gpu:4045.8748506728225 mfu:19.085081968054443 Step 493 | loss:1.389285922050476 lr:4.9579977698789584e-05 tokens_per_second_per_gpu:4758.76315422921 mfu:22.44789772721673 Step 494 | loss:1.5753517150878906 lr:4.9577980864501996e-05 tokens_per_second_per_gpu:5305.195704671163 mfu:25.025513298658208 Step 495 | loss:1.3778172731399536 lr:4.957597933527704e-05 tokens_per_second_per_gpu:3913.3862103708307 mfu:18.46011044685697 Step 496 | loss:1.5714342594146729 lr:4.9573973111497044e-05 tokens_per_second_per_gpu:5320.830176548299 mfu:25.099263770018624 Step 497 | loss:1.6230840682983398 lr:4.957196219354524e-05 tokens_per_second_per_gpu:4197.526030498732 mfu:19.80044645765262 Step 498 | loss:1.52046799659729 lr:4.956994658180576e-05 tokens_per_second_per_gpu:4911.127942682705 mfu:23.166628430465412 Step 499 | loss:1.6598751544952393 lr:4.956792627666364e-05 tokens_per_second_per_gpu:4674.038578408741 mfu:22.04823744756834 Step 500 | loss:1.6323952674865723 lr:4.95659012785048e-05 tokens_per_second_per_gpu:3996.550788048292 mfu:18.852411949101665 Step 501 | loss:1.4428828954696655 lr:4.956387158771606e-05 tokens_per_second_per_gpu:5320.051321457681 mfu:25.0955897776698 Step 502 | loss:1.4105042219161987 lr:4.9561837204685124e-05 tokens_per_second_per_gpu:4130.36981733029 mfu:19.483659142105594 Step 503 | loss:1.2796400785446167 lr:4.955979812980062e-05 tokens_per_second_per_gpu:4962.481392457825 mfu:23.408871414856673 Step 504 | loss:1.520546555519104 lr:4.9557754363452035e-05 tokens_per_second_per_gpu:5290.066685520429 mfu:24.954147134047354 Step 505 | loss:1.5409374237060547 lr:4.955570590602979e-05 tokens_per_second_per_gpu:4347.616545210119 mfu:20.50844902362866 Step 506 | loss:1.54373037815094 lr:4.955365275792519e-05 tokens_per_second_per_gpu:3609.965549667549 mfu:17.028823421416636 Step 507 | loss:1.5124262571334839 lr:4.955159491953042e-05 tokens_per_second_per_gpu:4818.93846084233 mfu:22.73175491547682 Step 508 | loss:1.3747214078903198 lr:4.9549532391238574e-05 tokens_per_second_per_gpu:4425.51409208736 mfu:20.875905042940598 Step 509 | loss:1.5380784273147583 lr:4.954746517344365e-05 tokens_per_second_per_gpu:5306.555076661251 mfu:25.03192568826823 Step 510 | loss:1.5520918369293213 lr:4.9545393266540515e-05 tokens_per_second_per_gpu:4554.144511436633 mfu:21.482676677623726 Step 511 | loss:1.406657099723816 lr:4.9543316670924966e-05 tokens_per_second_per_gpu:3751.9503981707517 mfu:17.69859017691941 Step 512 | loss:1.613659381866455 lr:4.9541235386993675e-05 tokens_per_second_per_gpu:5329.339018334502 mfu:25.139401428482252 Step 513 | loss:1.3747520446777344 lr:4.9539149415144206e-05 tokens_per_second_per_gpu:5329.674737067343 mfu:25.140985071024588 Step 514 | loss:1.5213994979858398 lr:4.953705875577503e-05 tokens_per_second_per_gpu:4907.304215478439 mfu:23.14859125684775 Step 515 | loss:1.4742677211761475 lr:4.9534963409285505e-05 tokens_per_second_per_gpu:5001.54379871706 mfu:23.593135449915234 Step 516 | loss:1.4440693855285645 lr:4.95328633760759e-05 tokens_per_second_per_gpu:3935.7670731606577 mfu:18.565684795205534 Step 517 | loss:1.5609687566757202 lr:4.953075865654736e-05 tokens_per_second_per_gpu:4587.725404398509 mfu:21.64108347921604 Step 518 | loss:1.731499433517456 lr:4.952864925110193e-05 tokens_per_second_per_gpu:4453.450829118533 mfu:21.00768739801548 Step 519 | loss:1.573451042175293 lr:4.952653516014255e-05 tokens_per_second_per_gpu:4790.749956982036 mfu:22.59878493331312 Step 520 | loss:1.6032395362854004 lr:4.952441638407308e-05 tokens_per_second_per_gpu:4001.352851372517 mfu:18.875064101118525 Step 521 | loss:1.8596762418746948 lr:4.9522292923298225e-05 tokens_per_second_per_gpu:3323.478427193134 mfu:15.677414784961405 Step 522 | loss:1.5184731483459473 lr:4.952016477822363e-05 tokens_per_second_per_gpu:5190.73038356089 mfu:24.48556084918342 Step 523 | loss:1.6121954917907715 lr:4.951803194925581e-05 tokens_per_second_per_gpu:4234.807418664705 mfu:19.976309126492247 Step 524 | loss:1.3742815256118774 lr:4.951589443680219e-05 tokens_per_second_per_gpu:5299.373972708452 mfu:24.998051195700203 Step 525 | loss:1.496231198310852 lr:4.951375224127107e-05 tokens_per_second_per_gpu:5303.994840683428 mfu:25.019848618339537 Step 526 | loss:1.4762316942214966 lr:4.951160536307167e-05 tokens_per_second_per_gpu:3771.724582172838 mfu:17.79186837668094 Step 527 | loss:1.4945498704910278 lr:4.950945380261409e-05 tokens_per_second_per_gpu:4841.129368824244 mfu:22.83643321458683 Step 528 | loss:1.5186946392059326 lr:4.950729756030931e-05 tokens_per_second_per_gpu:3990.3382691028837 mfu:18.823106437271143 Step 529 | loss:1.5819613933563232 lr:4.950513663656924e-05 tokens_per_second_per_gpu:4189.334389882793 mfu:19.761805091229224 Step 530 | loss:1.4239846467971802 lr:4.950297103180665e-05 tokens_per_second_per_gpu:3785.163167505254 mfu:17.85526047655304 Step 531 | loss:1.551887035369873 lr:4.950080074643523e-05 tokens_per_second_per_gpu:3280.988316145883 mfu:15.476981681591027 Step 532 | loss:1.6034218072891235 lr:4.949862578086953e-05 tokens_per_second_per_gpu:2841.8546549323974 mfu:13.405513277718502 Step 533 | loss:1.7078529596328735 lr:4.9496446135525057e-05 tokens_per_second_per_gpu:5330.332793037866 mfu:25.144089233313473 Step 534 | loss:1.359179973602295 lr:4.9494261810818126e-05 tokens_per_second_per_gpu:5300.873516458548 mfu:25.00512479941795 Step 535 | loss:1.4155988693237305 lr:4.9492072807166024e-05 tokens_per_second_per_gpu:5293.198885333909 mfu:24.968922254975936 Step 536 | loss:1.6782327890396118 lr:4.9489879124986885e-05 tokens_per_second_per_gpu:2965.208076747369 mfu:13.987392414683708 Step 537 | loss:1.4824718236923218 lr:4.948768076469975e-05 tokens_per_second_per_gpu:4145.419172177392 mfu:19.554649516604083 Step 538 | loss:1.4435906410217285 lr:4.948547772672455e-05 tokens_per_second_per_gpu:5021.29784752486 mfu:23.6863186685299 Step 539 | loss:1.4573770761489868 lr:4.948327001148213e-05 tokens_per_second_per_gpu:5302.245562488752 mfu:25.011596974637612 Step 540 | loss:1.446305274963379 lr:4.94810576193942e-05 tokens_per_second_per_gpu:5321.800604888482 mfu:25.103841446071414 Step 541 | loss:1.3648877143859863 lr:4.947884055088339e-05 tokens_per_second_per_gpu:5332.704976976684 mfu:25.15527922968919 Step 542 | loss:1.5003025531768799 lr:4.9476618806373186e-05 tokens_per_second_per_gpu:5317.115947095 mfu:25.08174311597452 Step 543 | loss:1.3644778728485107 lr:4.947439238628801e-05 tokens_per_second_per_gpu:5316.89267136924 mfu:25.08068988628134 Step 544 | loss:1.2882068157196045 lr:4.947216129105315e-05 tokens_per_second_per_gpu:5295.348351642916 mfu:24.979061654292288 Step 545 | loss:1.5855358839035034 lr:4.946992552109479e-05 tokens_per_second_per_gpu:4643.232205276174 mfu:21.90291852939277 Step 546 | loss:1.5146980285644531 lr:4.946768507684002e-05 tokens_per_second_per_gpu:5288.827768090689 mfu:24.94830294915016 Step 547 | loss:1.3660951852798462 lr:4.9465439958716805e-05 tokens_per_second_per_gpu:4775.978861864887 mfu:22.52910715743683 Step 548 | loss:1.676123023033142 lr:4.946319016715403e-05 tokens_per_second_per_gpu:5314.969034691877 mfu:25.071615763867964 Step 549 | loss:1.6870404481887817 lr:4.946093570258143e-05 tokens_per_second_per_gpu:5010.128238624737 mfu:23.633629717616227 Step 550 | loss:1.32241952419281 lr:4.945867656542967e-05 tokens_per_second_per_gpu:5344.54685556176 mfu:25.21113939140782 Step 551 | loss:1.4056309461593628 lr:4.94564127561303e-05 tokens_per_second_per_gpu:4093.7308293122296 mfu:19.31082678436844 Step 552 | loss:1.8032320737838745 lr:4.945414427511576e-05 tokens_per_second_per_gpu:4316.655899799834 mfu:20.362402376797533 Step 553 | loss:1.4498158693313599 lr:4.945187112281936e-05 tokens_per_second_per_gpu:4510.832782081398 mfu:21.278367860512045 Step 554 | loss:1.4178334474563599 lr:4.9449593299675347e-05 tokens_per_second_per_gpu:3644.150068706512 mfu:17.190077630203795 Step 555 | loss:1.4972110986709595 lr:4.9447310806118814e-05 tokens_per_second_per_gpu:5318.118125837748 mfu:25.086470564093393 Step 556 | loss:1.3650989532470703 lr:4.944502364258577e-05 tokens_per_second_per_gpu:5326.238660383422 mfu:25.124776511051397 Step 557 | loss:1.3335026502609253 lr:4.944273180951314e-05 tokens_per_second_per_gpu:3920.9266835865415 mfu:18.495680145552875 Step 558 | loss:1.3341562747955322 lr:4.9440435307338686e-05 tokens_per_second_per_gpu:4913.304758474001 mfu:23.176896841956026 Step 559 | loss:1.494799017906189 lr:4.9438134136501104e-05 tokens_per_second_per_gpu:4290.5033860784115 mfu:20.239036507494628 Step 560 | loss:1.5388513803482056 lr:4.9435828297439965e-05 tokens_per_second_per_gpu:4992.779038021834 mfu:23.55179057829348 Step 561 | loss:1.5496644973754883 lr:4.943351779059573e-05 tokens_per_second_per_gpu:5270.988345403938 mfu:24.864151348617387 Step 562 | loss:1.3743343353271484 lr:4.943120261640977e-05 tokens_per_second_per_gpu:5326.350098486054 mfu:25.125302183594812 Step 563 | loss:1.3802952766418457 lr:4.942888277532431e-05 tokens_per_second_per_gpu:5222.209993779646 mfu:24.63405554156063 Step 564 | loss:1.4693211317062378 lr:4.942655826778253e-05 tokens_per_second_per_gpu:4427.12716931733 mfu:20.88351420345372 Step 565 | loss:1.4397505521774292 lr:4.9424229094228424e-05 tokens_per_second_per_gpu:5295.54633791004 mfu:24.97999558929425 Step 566 | loss:1.670975685119629 lr:4.942189525510694e-05 tokens_per_second_per_gpu:5319.007719711856 mfu:25.090666930177925 Step 567 | loss:1.355080008506775 lr:4.941955675086388e-05 tokens_per_second_per_gpu:5305.790476178343 mfu:25.028318937336056 Step 568 | loss:1.2928297519683838 lr:4.941721358194595e-05 tokens_per_second_per_gpu:4386.676646209452 mfu:20.69270218438295 Step 569 | loss:1.611454725265503 lr:4.941486574880075e-05 tokens_per_second_per_gpu:4799.7833943799815 mfu:22.64139719878258 Step 570 | loss:1.6942245960235596 lr:4.941251325187678e-05 tokens_per_second_per_gpu:4240.799181106411 mfu:20.00457329222986 Step 571 | loss:1.5451257228851318 lr:4.941015609162341e-05 tokens_per_second_per_gpu:5321.880231456555 mfu:25.10421705817871 Step 572 | loss:1.3244327306747437 lr:4.940779426849089e-05 tokens_per_second_per_gpu:3938.1342359191235 mfu:18.576851105816832 Step 573 | loss:1.613653540611267 lr:4.9405427782930416e-05 tokens_per_second_per_gpu:3634.81324106137 mfu:17.1460342211746 Step 574 | loss:1.7142611742019653 lr:4.940305663539401e-05 tokens_per_second_per_gpu:3768.282233804295 mfu:17.775630232101328 Step 575 | loss:1.5696470737457275 lr:4.940068082633463e-05 tokens_per_second_per_gpu:3959.0993411457057 mfu:18.675747084186423 Step 576 | loss:1.3904203176498413 lr:4.93983003562061e-05 tokens_per_second_per_gpu:5314.694020119012 mfu:25.070318473205432 Step 577 | loss:1.4399563074111938 lr:4.939591522546314e-05 tokens_per_second_per_gpu:5293.319425166081 mfu:24.969490861930502 Step 578 | loss:1.4834996461868286 lr:4.939352543456138e-05 tokens_per_second_per_gpu:4483.29957277387 mfu:21.14848901455852 Step 579 | loss:1.5066293478012085 lr:4.93911309839573e-05 tokens_per_second_per_gpu:5326.79122007345 mfu:25.127383029385662 Step 580 | loss:1.4692333936691284 lr:4.938873187410831e-05 tokens_per_second_per_gpu:5160.782496383138 mfu:24.34429155572952 Step 581 | loss:1.5505880117416382 lr:4.938632810547269e-05 tokens_per_second_per_gpu:5194.486044922643 mfu:24.503276944608707 Step 582 | loss:1.3183773756027222 lr:4.93839196785096e-05 tokens_per_second_per_gpu:5314.427099705163 mfu:25.069059364071986 Step 583 | loss:1.4904228448867798 lr:4.9381506593679116e-05 tokens_per_second_per_gpu:4397.414509426342 mfu:20.743354517245404 Step 584 | loss:1.499165415763855 lr:4.937908885144219e-05 tokens_per_second_per_gpu:4933.285573861509 mfu:23.27114975721754 Step 585 | loss:1.508660078048706 lr:4.937666645226066e-05 tokens_per_second_per_gpu:4235.4839256004925 mfu:19.97950032513234 Step 586 | loss:1.5134299993515015 lr:4.937423939659726e-05 tokens_per_second_per_gpu:3586.9747177684917 mfu:16.92037174470837 Step 587 | loss:1.6053653955459595 lr:4.93718076849156e-05 tokens_per_second_per_gpu:4415.393474384008 mfu:20.828164362478446 Step 588 | loss:1.3622335195541382 lr:4.9369371317680204e-05 tokens_per_second_per_gpu:3450.2173550986527 mfu:16.27526393178262 Step 589 | loss:1.571340560913086 lr:4.936693029535647e-05 tokens_per_second_per_gpu:4728.104934097299 mfu:22.303277672022766 Step 590 | loss:1.4935717582702637 lr:4.936448461841069e-05 tokens_per_second_per_gpu:5169.811886355249 mfu:24.386884728800755 Step 591 | loss:1.5025638341903687 lr:4.9362034287310044e-05 tokens_per_second_per_gpu:5320.19987267123 mfu:25.09629051908956 Step 592 | loss:1.4395201206207275 lr:4.9359579302522584e-05 tokens_per_second_per_gpu:5322.100087856318 mfu:25.10525415832776 Step 593 | loss:1.5919055938720703 lr:4.935711966451728e-05 tokens_per_second_per_gpu:5299.3654034916135 mfu:24.998010773242314 Step 594 | loss:1.5206156969070435 lr:4.935465537376397e-05 tokens_per_second_per_gpu:4986.1047889960055 mfu:23.52030700689434 Step 595 | loss:1.5823187828063965 lr:4.935218643073339e-05 tokens_per_second_per_gpu:4215.19807796211 mfu:19.883808520699585 Step 596 | loss:1.4618290662765503 lr:4.934971283589717e-05 tokens_per_second_per_gpu:4363.073060708182 mfu:20.581360044386503 Step 597 | loss:1.2714002132415771 lr:4.934723458972781e-05 tokens_per_second_per_gpu:5341.147326286479 mfu:25.195103231796818 Step 598 | loss:1.6229958534240723 lr:4.934475169269871e-05 tokens_per_second_per_gpu:3912.523407253026 mfu:18.456040457340894 Step 599 | loss:1.4343539476394653 lr:4.934226414528417e-05 tokens_per_second_per_gpu:3920.4946278792095 mfu:18.493642065065085 Step 600 | loss:1.351172924041748 lr:4.9339771947959354e-05 tokens_per_second_per_gpu:3925.4819877320365 mfu:18.517168292422205 Step 601 | loss:1.330119252204895 lr:4.933727510120034e-05 tokens_per_second_per_gpu:4916.201815642013 mfu:23.19056275490646 Step 602 | loss:1.4159538745880127 lr:4.933477360548407e-05 tokens_per_second_per_gpu:5283.402220221764 mfu:24.92270971415852 Step 603 | loss:1.6208009719848633 lr:4.933226746128838e-05 tokens_per_second_per_gpu:5316.191655404842 mfu:25.077383074371625 Step 604 | loss:1.436365008354187 lr:4.932975666909202e-05 tokens_per_second_per_gpu:4149.666394995027 mfu:19.574684391285803 Step 605 | loss:1.52460515499115 lr:4.932724122937459e-05 tokens_per_second_per_gpu:5051.523889327131 mfu:23.828900064805726 Step 606 | loss:1.555437445640564 lr:4.9324721142616594e-05 tokens_per_second_per_gpu:4596.276697626924 mfu:21.681421388375544 Step 607 | loss:1.409151315689087 lr:4.9322196409299435e-05 tokens_per_second_per_gpu:5316.351976353194 mfu:25.07813933563857 Step 608 | loss:1.5150705575942993 lr:4.9319667029905384e-05 tokens_per_second_per_gpu:4158.036627745601 mfu:19.61416820727923 Step 609 | loss:1.4199029207229614 lr:4.93171330049176e-05 tokens_per_second_per_gpu:3984.864838548931 mfu:18.797287331484597 Step 610 | loss:1.6647827625274658 lr:4.9314594334820165e-05 tokens_per_second_per_gpu:5345.66761553046 mfu:25.21642620740155 Step 611 | loss:1.604594111442566 lr:4.9312051020097996e-05 tokens_per_second_per_gpu:4527.252328978303 mfu:21.355821664688325 Step 612 | loss:1.483128547668457 lr:4.930950306123693e-05 tokens_per_second_per_gpu:5076.3414259486635 mfu:23.945968619357874 Step 613 | loss:1.3430858850479126 lr:4.930695045872369e-05 tokens_per_second_per_gpu:5325.1302870568425 mfu:25.11954812496193 Step 614 | loss:1.5984547138214111 lr:4.930439321304587e-05 tokens_per_second_per_gpu:4949.476322305461 mfu:23.347524280054195 Step 615 | loss:1.4887651205062866 lr:4.930183132469196e-05 tokens_per_second_per_gpu:4857.181210712361 mfu:22.912152491499707 Step 616 | loss:1.4679100513458252 lr:4.929926479415135e-05 tokens_per_second_per_gpu:4170.740489841015 mfu:19.67409449228568 Step 617 | loss:1.3006298542022705 lr:4.929669362191429e-05 tokens_per_second_per_gpu:5310.962734339496 mfu:25.052717361560457 Step 618 | loss:1.4870843887329102 lr:4.929411780847194e-05 tokens_per_second_per_gpu:5340.948412714667 mfu:25.194164922540423 Step 619 | loss:1.538230061531067 lr:4.929153735431633e-05 tokens_per_second_per_gpu:3382.6819445690576 mfu:15.956687877585301 Step 620 | loss:1.2687344551086426 lr:4.928895225994039e-05 tokens_per_second_per_gpu:4434.64682072343 mfu:20.918985682121125 Step 621 | loss:1.3536287546157837 lr:4.9286362525837924e-05 tokens_per_second_per_gpu:5338.038815890059 mfu:25.180439857890338 Step 622 | loss:1.6114685535430908 lr:4.928376815250364e-05 tokens_per_second_per_gpu:4725.6367562281175 mfu:22.291634855899268 Step 623 | loss:1.3981000185012817 lr:4.92811691404331e-05 tokens_per_second_per_gpu:3862.8072249378774 mfu:18.221520742904953 Step 624 | loss:1.376578688621521 lr:4.92785654901228e-05 tokens_per_second_per_gpu:3690.178479114387 mfu:17.40720149535436 Step 625 | loss:1.5489636659622192 lr:4.927595720207007e-05 tokens_per_second_per_gpu:4586.062935443712 mfu:21.633241329509808 Step 626 | loss:1.479461431503296 lr:4.927334427677316e-05 tokens_per_second_per_gpu:4746.853434104139 mfu:22.39171754537898 Step 627 | loss:1.6039952039718628 lr:4.92707267147312e-05 tokens_per_second_per_gpu:4772.4301393451215 mfu:22.5123672278366 Step 628 | loss:1.6338385343551636 lr:4.92681045164442e-05 tokens_per_second_per_gpu:4395.4564837661765 mfu:20.734118176132778 Step 629 | loss:1.5595424175262451 lr:4.926547768241305e-05 tokens_per_second_per_gpu:4177.386927191766 mfu:19.705446871268315 Step 630 | loss:1.7055668830871582 lr:4.926284621313955e-05 tokens_per_second_per_gpu:3134.930756424289 mfu:14.788003252394912 Step 631 | loss:1.3817132711410522 lr:4.926021010912636e-05 tokens_per_second_per_gpu:5327.169914326883 mfu:25.12916939479101 Step 632 | loss:1.4919993877410889 lr:4.9257569370877024e-05 tokens_per_second_per_gpu:4613.143095722818 mfu:21.760983065898127 Step 633 | loss:1.5222156047821045 lr:4.9254923998896e-05 tokens_per_second_per_gpu:4134.99921740381 mfu:19.505496812109488 Step 634 | loss:1.4990215301513672 lr:4.92522739936886e-05 tokens_per_second_per_gpu:5342.821318032504 mfu:25.202999736475256 Step 635 | loss:1.4784367084503174 lr:4.9249619355761036e-05 tokens_per_second_per_gpu:4034.5490934461095 mfu:19.031656438842596 Step 636 | loss:1.570934534072876 lr:4.9246960085620396e-05 tokens_per_second_per_gpu:5319.418523230684 mfu:25.09260476046654 Step 637 | loss:1.6674085855484009 lr:4.9244296183774675e-05 tokens_per_second_per_gpu:5305.698170547423 mfu:25.027883515926042 Step 638 | loss:1.3518532514572144 lr:4.924162765073272e-05 tokens_per_second_per_gpu:5341.369004563123 mfu:25.196148926049958 Step 639 | loss:1.5166693925857544 lr:4.9238954487004305e-05 tokens_per_second_per_gpu:4597.157232211042 mfu:21.68557502024352 Step 640 | loss:1.4218406677246094 lr:4.923627669310004e-05 tokens_per_second_per_gpu:5321.168075295508 mfu:25.10085769606068 Step 641 | loss:1.255543828010559 lr:4.923359426953144e-05 tokens_per_second_per_gpu:4835.625161550407 mfu:22.81046892976154 Step 642 | loss:1.514580249786377 lr:4.9230907216810926e-05 tokens_per_second_per_gpu:4561.28669004706 mfu:21.51636755271043 Step 643 | loss:1.4231888055801392 lr:4.9228215535451774e-05 tokens_per_second_per_gpu:4235.437139387483 mfu:19.979279626583022 Step 644 | loss:1.5356916189193726 lr:4.9225519225968146e-05 tokens_per_second_per_gpu:3765.8022679978358 mfu:17.763931810266463 Step 645 | loss:1.4894616603851318 lr:4.922281828887512e-05 tokens_per_second_per_gpu:4676.891218419415 mfu:22.061693837209262 Step 646 | loss:1.558202862739563 lr:4.922011272468862e-05 tokens_per_second_per_gpu:4406.503990592547 mfu:20.786231150731794 Step 647 | loss:1.4039638042449951 lr:4.921740253392546e-05 tokens_per_second_per_gpu:5320.306424324974 mfu:25.096793141419855 Step 648 | loss:1.4916112422943115 lr:4.921468771710336e-05 tokens_per_second_per_gpu:4579.044635577573 mfu:21.600134811595794 Step 649 | loss:1.2959896326065063 lr:4.9211968274740905e-05 tokens_per_second_per_gpu:5344.104710565839 mfu:25.209053718024343 Step 650 | loss:1.521027684211731 lr:4.920924420735757e-05 tokens_per_second_per_gpu:5303.817668331223 mfu:25.019012866125465 Step 651 | loss:1.6063116788864136 lr:4.9206515515473716e-05 tokens_per_second_per_gpu:5004.925690455223 mfu:23.609088410254383 Step 652 | loss:1.3811836242675781 lr:4.9203782199610574e-05 tokens_per_second_per_gpu:4704.41289417372 mfu:22.191518277424407 Step 653 | loss:1.4870648384094238 lr:4.9201044260290276e-05 tokens_per_second_per_gpu:4367.5272443687645 mfu:20.602371188675566 Step 654 | loss:1.6032782793045044 lr:4.919830169803582e-05 tokens_per_second_per_gpu:4892.046737778028 mfu:23.076619131340788 Step 655 | loss:1.473037600517273 lr:4.919555451337111e-05 tokens_per_second_per_gpu:5151.8680643022735 mfu:24.302240658645132 Step 656 | loss:1.5222241878509521 lr:4.919280270682091e-05 tokens_per_second_per_gpu:4262.470058339644 mfu:20.106798517571942 Step 657 | loss:1.3138989210128784 lr:4.9190046278910874e-05 tokens_per_second_per_gpu:5328.037695145797 mfu:25.1332628649725 Step 658 | loss:1.5397968292236328 lr:4.918728523016754e-05 tokens_per_second_per_gpu:5051.515198017606 mfu:23.828859066415806 Step 659 | loss:1.6274570226669312 lr:4.918451956111833e-05 tokens_per_second_per_gpu:3997.622518358534 mfu:18.857467483831122 Step 660 | loss:1.3310930728912354 lr:4.918174927229155e-05 tokens_per_second_per_gpu:5159.637450864501 mfu:24.338890180653202 Step 661 | loss:1.564914345741272 lr:4.91789743642164e-05 tokens_per_second_per_gpu:4393.314569781705 mfu:20.724014402419815 Step 662 | loss:1.4705179929733276 lr:4.917619483742292e-05 tokens_per_second_per_gpu:4604.927402579567 mfu:21.72222823959962 Step 663 | loss:1.4839011430740356 lr:4.917341069244209e-05 tokens_per_second_per_gpu:4157.035001638621 mfu:19.60944336603757 Step 664 | loss:1.3757299184799194 lr:4.9170621929805716e-05 tokens_per_second_per_gpu:4593.747429771071 mfu:21.669490400361887 Step 665 | loss:1.6709297895431519 lr:4.916782855004654e-05 tokens_per_second_per_gpu:3622.0983166764004 mfu:17.086055753460897 Step 666 | loss:1.6596040725708008 lr:4.9165030553698136e-05 tokens_per_second_per_gpu:4390.0394749731995 mfu:20.7085652214193 Step 667 | loss:1.4018851518630981 lr:4.9162227941295e-05 tokens_per_second_per_gpu:5313.575410942931 mfu:25.065041802867455 Step 668 | loss:1.619870662689209 lr:4.915942071337249e-05 tokens_per_second_per_gpu:4429.996633796758 mfu:20.897049956984308 Step 669 | loss:1.4625006914138794 lr:4.915660887046683e-05 tokens_per_second_per_gpu:3236.0653529466053 mfu:15.26507239953216 Step 670 | loss:1.4930106401443481 lr:4.915379241311516e-05 tokens_per_second_per_gpu:3458.010626760931 mfu:16.312026123882845 Step 671 | loss:1.6173486709594727 lr:4.91509713418555e-05 tokens_per_second_per_gpu:4576.041197620504 mfu:21.585967082312948 Step 672 | loss:1.4350861310958862 lr:4.914814565722671e-05 tokens_per_second_per_gpu:4163.939736396841 mfu:19.64201417796132 Step 673 | loss:1.543218731880188 lr:4.914531535976857e-05 tokens_per_second_per_gpu:3545.636877320689 mfu:16.725374098353225 Step 674 | loss:1.2834779024124146 lr:4.914248045002173e-05 tokens_per_second_per_gpu:5319.8976291021145 mfu:25.09486478460597 Step 675 | loss:1.6874985694885254 lr:4.913964092852772e-05 tokens_per_second_per_gpu:3964.70059286874 mfu:18.702169144236066 Step 676 | loss:1.4783421754837036 lr:4.9136796795828954e-05 tokens_per_second_per_gpu:5060.218246641644 mfu:23.86991283166861 Step 677 | loss:1.278855323791504 lr:4.9133948052468716e-05 tokens_per_second_per_gpu:4430.685962260016 mfu:20.90030163695706 Step 678 | loss:1.4576125144958496 lr:4.913109469899119e-05 tokens_per_second_per_gpu:4755.91227100881 mfu:22.434449624655272 Step 679 | loss:1.2594716548919678 lr:4.912823673594141e-05 tokens_per_second_per_gpu:5191.1745079658185 mfu:24.4876558597769 Step 680 | loss:1.4676591157913208 lr:4.912537416386533e-05 tokens_per_second_per_gpu:3890.073729848959 mfu:18.350141498715974 Step 681 | loss:1.3964645862579346 lr:4.9122506983309767e-05 tokens_per_second_per_gpu:5140.783889566761 mfu:24.2499547152625 Step 682 | loss:1.4412685632705688 lr:4.91196351948224e-05 tokens_per_second_per_gpu:3770.9771154491837 mfu:17.78834244861449 Step 683 | loss:1.3508859872817993 lr:4.911675879895181e-05 tokens_per_second_per_gpu:5307.12282917801 mfu:25.03460387375835 Step 684 | loss:1.5204458236694336 lr:4.9113877796247455e-05 tokens_per_second_per_gpu:3650.274772163965 mfu:17.218968901394767 Step 685 | loss:1.2494808435440063 lr:4.911099218725966e-05 tokens_per_second_per_gpu:4620.917249211424 mfu:21.797655074311244 Step 686 | loss:1.5232013463974 lr:4.910810197253966e-05 tokens_per_second_per_gpu:5357.338665700774 mfu:25.27148054234141 Step 687 | loss:1.4857773780822754 lr:4.910520715263953e-05 tokens_per_second_per_gpu:5295.082826806707 mfu:24.977809128336684 Step 688 | loss:1.6956294775009155 lr:4.9102307728112264e-05 tokens_per_second_per_gpu:3481.8973586347306 mfu:16.424703913628267 Step 689 | loss:1.4503535032272339 lr:4.909940369951169e-05 tokens_per_second_per_gpu:4286.848073299504 mfu:20.22179377345585 Step 690 | loss:1.4575016498565674 lr:4.909649506739257e-05 tokens_per_second_per_gpu:4930.651856159938 mfu:23.258726061460653 Step 691 | loss:1.484847068786621 lr:4.9093581832310486e-05 tokens_per_second_per_gpu:5333.133784449109 mfu:25.15730198769872 Step 692 | loss:1.3901480436325073 lr:4.909066399482196e-05 tokens_per_second_per_gpu:5358.790667015888 mfu:25.278329880281774 Step 693 | loss:1.5866564512252808 lr:4.908774155548435e-05 tokens_per_second_per_gpu:3860.330759735032 mfu:18.209838834014597 Step 694 | loss:1.684582233428955 lr:4.9084814514855905e-05 tokens_per_second_per_gpu:4978.589043993486 mfu:23.484853955399128 Step 695 | loss:1.439354419708252 lr:4.908188287349576e-05 tokens_per_second_per_gpu:5326.1072705558145 mfu:25.12415672281716 Step 696 | loss:1.5090659856796265 lr:4.907894663196392e-05 tokens_per_second_per_gpu:5348.136636305481 mfu:25.228072999655705 Step 697 | loss:1.481117606163025 lr:4.907600579082127e-05 tokens_per_second_per_gpu:3744.480508937525 mfu:17.663353434911755 Step 698 | loss:1.2777186632156372 lr:4.907306035062958e-05 tokens_per_second_per_gpu:4613.204389044069 mfu:21.76127219695219 Step 699 | loss:1.5033981800079346 lr:4.907011031195149e-05 tokens_per_second_per_gpu:5307.881292814736 mfu:25.038181676140027 Step 700 | loss:1.466416358947754 lr:4.906715567535052e-05 tokens_per_second_per_gpu:4393.223045696375 mfu:20.723582667693695 Step 701 | loss:1.4192233085632324 lr:4.9064196441391084e-05 tokens_per_second_per_gpu:4234.0098407149 mfu:19.972546815222184 Step 702 | loss:1.3377622365951538 lr:4.906123261063845e-05 tokens_per_second_per_gpu:5308.215306515572 mfu:25.039757275755484 Step 703 | loss:1.5284323692321777 lr:4.905826418365878e-05 tokens_per_second_per_gpu:5079.3628601161 mfu:23.960221239835494 Step 704 | loss:1.5338234901428223 lr:4.90552911610191e-05 tokens_per_second_per_gpu:4472.936438708279 mfu:21.09960434303813 Step 705 | loss:1.664663553237915 lr:4.905231354328734e-05 tokens_per_second_per_gpu:4146.7088860877275 mfu:19.56073331716702 Step 706 | loss:1.3982874155044556 lr:4.904933133103227e-05 tokens_per_second_per_gpu:5310.833616983148 mfu:25.052108292960874 Step 707 | loss:1.3216747045516968 lr:4.904634452482357e-05 tokens_per_second_per_gpu:5376.580375914104 mfu:25.36224697239198 Step 708 | loss:1.4821513891220093 lr:4.904335312523179e-05 tokens_per_second_per_gpu:5126.989448279315 mfu:24.184883982135243 Step 709 | loss:1.538498878479004 lr:4.9040357132828354e-05 tokens_per_second_per_gpu:3311.0962619360776 mfu:15.61900599882863 Step 710 | loss:1.7269355058670044 lr:4.903735654818554e-05 tokens_per_second_per_gpu:5334.612733031126 mfu:25.164278440494737 Step 711 | loss:1.3479034900665283 lr:4.903435137187656e-05 tokens_per_second_per_gpu:4578.8891042858095 mfu:21.599401143956168 Step 712 | loss:1.586517333984375 lr:4.9031341604475445e-05 tokens_per_second_per_gpu:4535.766881192402 mfu:21.395986260214638 Step 713 | loss:1.4847087860107422 lr:4.9028327246557135e-05 tokens_per_second_per_gpu:4892.120306477868 mfu:23.07696616745005 Step 714 | loss:1.455965280532837 lr:4.9025308298697436e-05 tokens_per_second_per_gpu:5351.726970588433 mfu:25.245009219042583 Step 715 | loss:1.4835383892059326 lr:4.9022284761473034e-05 tokens_per_second_per_gpu:3768.03805803816 mfu:17.77447841335179 Step 716 | loss:1.3859879970550537 lr:4.9019256635461505e-05 tokens_per_second_per_gpu:4470.841475549575 mfu:21.089722044380956 Step 717 | loss:1.4638556241989136 lr:4.901622392124127e-05 tokens_per_second_per_gpu:4696.693301841932 mfu:22.155103643297096 Step 718 | loss:1.4105652570724487 lr:4.901318661939165e-05 tokens_per_second_per_gpu:4021.0170200211746 mfu:18.967823339687378 Step 719 | loss:1.510321021080017 lr:4.9010144730492836e-05 tokens_per_second_per_gpu:4662.54597373887 mfu:21.99402487050001 Step 720 | loss:1.417304277420044 lr:4.900709825512589e-05 tokens_per_second_per_gpu:5315.557515935856 mfu:25.074391730301063 Step 721 | loss:1.3456586599349976 lr:4.900404719387278e-05 tokens_per_second_per_gpu:5331.983107680246 mfu:25.15187404905429 Step 722 | loss:1.6186904907226562 lr:4.90009915473163e-05 tokens_per_second_per_gpu:3824.1471749904586 mfu:18.03915469121829 Step 723 | loss:1.3861585855484009 lr:4.8997931316040155e-05 tokens_per_second_per_gpu:3682.405721960938 mfu:17.370536073692424 Step 724 | loss:1.4639641046524048 lr:4.8994866500628924e-05 tokens_per_second_per_gpu:4959.394096806717 mfu:23.39430811452344 Step 725 | loss:1.399276852607727 lr:4.899179710166805e-05 tokens_per_second_per_gpu:4612.3237283382605 mfu:21.75711797014668 Step 726 | loss:1.5974828004837036 lr:4.8988723119743845e-05 tokens_per_second_per_gpu:4239.147035990668 mfu:19.996779841833877 Step 727 | loss:1.5520192384719849 lr:4.898564455544352e-05 tokens_per_second_per_gpu:4787.3240163437695 mfu:22.58262418679667 Step 728 | loss:1.4170305728912354 lr:4.898256140935514e-05 tokens_per_second_per_gpu:5324.636308399872 mfu:25.117217943355552 Step 729 | loss:1.2717623710632324 lr:4.897947368206767e-05 tokens_per_second_per_gpu:5193.244702854279 mfu:24.497421322277443 Step 730 | loss:1.452661395072937 lr:4.897638137417092e-05 tokens_per_second_per_gpu:5327.922074960496 mfu:25.132717464831597 Step 731 | loss:1.3884224891662598 lr:4.897328448625559e-05 tokens_per_second_per_gpu:3798.537057477568 mfu:17.918347397373363 Step 732 | loss:1.5363320112228394 lr:4.897018301891326e-05 tokens_per_second_per_gpu:4012.403966811048 mfu:18.927194098156797 Step 733 | loss:1.4805169105529785 lr:4.896707697273637e-05 tokens_per_second_per_gpu:4767.169358568198 mfu:22.48755122733009 Step 734 | loss:1.4864909648895264 lr:4.896396634831825e-05 tokens_per_second_per_gpu:4030.0365161145965 mfu:19.010369841644764 Step 735 | loss:1.4254865646362305 lr:4.89608511462531e-05 tokens_per_second_per_gpu:4659.737636558687 mfu:21.98077746486935 Step 736 | loss:1.5596134662628174 lr:4.895773136713599e-05 tokens_per_second_per_gpu:5311.939748138018 mfu:25.05732610234383 Step 737 | loss:1.4757024049758911 lr:4.895460701156287e-05 tokens_per_second_per_gpu:4267.402383765068 mfu:20.130065138145167 Step 738 | loss:1.5476946830749512 lr:4.8951478080130544e-05 tokens_per_second_per_gpu:4343.213317939152 mfu:20.48767824932347 Step 739 | loss:1.3954386711120605 lr:4.8948344573436725e-05 tokens_per_second_per_gpu:3716.3554417539785 mfu:17.530682694375688 Step 740 | loss:1.4354034662246704 lr:4.894520649207998e-05 tokens_per_second_per_gpu:3917.509881563261 mfu:18.47956250744252 Step 741 | loss:1.6853735446929932 lr:4.894206383665975e-05 tokens_per_second_per_gpu:4076.210341148457 mfu:19.228179652396395 Step 742 | loss:1.3793808221817017 lr:4.893891660777634e-05 tokens_per_second_per_gpu:3431.6025747361873 mfu:16.187454836803845 Step 743 | loss:1.5536588430404663 lr:4.8935764806030964e-05 tokens_per_second_per_gpu:4476.554280483692 mfu:21.116670319960214 Step 744 | loss:1.4552053213119507 lr:4.8932608432025667e-05 tokens_per_second_per_gpu:5118.360210694038 mfu:24.14417839614574 Step 745 | loss:1.3963333368301392 lr:4.8929447486363386e-05 tokens_per_second_per_gpu:5286.417373459886 mfu:24.93693270642093 Step 746 | loss:1.599920392036438 lr:4.892628196964795e-05 tokens_per_second_per_gpu:4438.262433777247 mfu:20.936041145783175 Step 747 | loss:1.5652767419815063 lr:4.8923111882484016e-05 tokens_per_second_per_gpu:5313.029928333831 mfu:25.062468668331398 Step 748 | loss:1.4361069202423096 lr:4.891993722547716e-05 tokens_per_second_per_gpu:4273.146926639767 mfu:20.1571631270052 Step 749 | loss:1.5697146654129028 lr:4.891675799923381e-05 tokens_per_second_per_gpu:4023.8098136925087 mfu:18.980997423934795 Step 750 | loss:1.311971664428711 lr:4.891357420436127e-05 tokens_per_second_per_gpu:5331.151418566328 mfu:25.147950829603143 Step 751 | loss:1.3225116729736328 lr:4.89103858414677e-05 tokens_per_second_per_gpu:5307.567683131761 mfu:25.036702325758107 Step 752 | loss:1.7087169885635376 lr:4.890719291116216e-05 tokens_per_second_per_gpu:5317.190400075054 mfu:25.082094323384425 Step 753 | loss:1.4117720127105713 lr:4.890399541405456e-05 tokens_per_second_per_gpu:5298.727750853773 mfu:24.99500285695486 Step 754 | loss:1.416032314300537 lr:4.8900793350755705e-05 tokens_per_second_per_gpu:5331.92607426933 mfu:25.151605012724094 Step 755 | loss:1.4650671482086182 lr:4.8897586721877256e-05 tokens_per_second_per_gpu:4340.341834555793 mfu:20.474132972278582 Step 756 | loss:1.2956702709197998 lr:4.8894375528031756e-05 tokens_per_second_per_gpu:5352.105727712838 mfu:25.246795881021033 Step 757 | loss:1.52629816532135 lr:4.8891159769832594e-05 tokens_per_second_per_gpu:5317.024712574362 mfu:25.081312747174454 Step 758 | loss:1.5674771070480347 lr:4.888793944789407e-05 tokens_per_second_per_gpu:5308.25882787148 mfu:25.039962573416812 Step 759 | loss:1.3991364240646362 lr:4.888471456283134e-05 tokens_per_second_per_gpu:4679.324242861406 mfu:22.07317082861891 Step 760 | loss:1.4215087890625 lr:4.88814851152604e-05 tokens_per_second_per_gpu:5306.909792687122 mfu:25.033598944283057 Step 761 | loss:1.5684624910354614 lr:4.887825110579818e-05 tokens_per_second_per_gpu:4104.443557094064 mfu:19.36136054909519 Step 762 | loss:1.4805022478103638 lr:4.887501253506243e-05 tokens_per_second_per_gpu:5351.131313381955 mfu:25.242199402370026 Step 763 | loss:1.4490982294082642 lr:4.887176940367178e-05 tokens_per_second_per_gpu:4916.476780436093 mfu:23.191859810753964 Step 764 | loss:1.4340646266937256 lr:4.8868521712245766e-05 tokens_per_second_per_gpu:5309.468100978752 mfu:25.045666920987077 Step 765 | loss:1.613995909690857 lr:4.886526946140474e-05 tokens_per_second_per_gpu:2627.7889617663354 mfu:12.395728879680762 Step 766 | loss:1.3259975910186768 lr:4.886201265176997e-05 tokens_per_second_per_gpu:4300.969238031715 mfu:20.288405716816833 Step 767 | loss:1.4500150680541992 lr:4.885875128396358e-05 tokens_per_second_per_gpu:5330.544148256636 mfu:25.145086231941328 Step 768 | loss:1.3554116487503052 lr:4.8855485358608555e-05 tokens_per_second_per_gpu:5344.944649197802 mfu:25.213015851859623 Step 769 | loss:1.4175211191177368 lr:4.885221487632876e-05 tokens_per_second_per_gpu:5307.606345073221 mfu:25.036884700732376 Step 770 | loss:1.416946291923523 lr:4.8848939837748944e-05 tokens_per_second_per_gpu:5336.963043568473 mfu:25.17536525630373 Step 771 | loss:1.503726601600647 lr:4.884566024349469e-05 tokens_per_second_per_gpu:4732.146511185661 mfu:22.322342480712727 Step 772 | loss:1.4985696077346802 lr:4.8842376094192476e-05 tokens_per_second_per_gpu:2976.8897272126933 mfu:14.04249675302373 Step 773 | loss:1.435072898864746 lr:4.883908739046966e-05 tokens_per_second_per_gpu:5360.363821357057 mfu:25.285750717716873 Step 774 | loss:1.6141695976257324 lr:4.883579413295446e-05 tokens_per_second_per_gpu:4850.5629812311845 mfu:22.880933173850618 Step 775 | loss:1.6263582706451416 lr:4.8832496322275944e-05 tokens_per_second_per_gpu:4590.992468453173 mfu:21.656494777780495 Step 776 | loss:1.4657891988754272 lr:4.882919395906407e-05 tokens_per_second_per_gpu:5310.201921955945 mfu:25.049128479739267 Step 777 | loss:1.3519270420074463 lr:4.882588704394967e-05 tokens_per_second_per_gpu:4406.487977891383 mfu:20.786155616088354 Step 778 | loss:1.5172779560089111 lr:4.882257557756444e-05 tokens_per_second_per_gpu:5154.523740358168 mfu:24.314767935705845 Step 779 | loss:1.194474458694458 lr:4.881925956054093e-05 tokens_per_second_per_gpu:5328.415101235533 mfu:25.135043153889907 Step 780 | loss:1.525702953338623 lr:4.881593899351259e-05 tokens_per_second_per_gpu:5335.559967197693 mfu:25.16874670567325 Step 781 | loss:1.3748878240585327 lr:4.8812613877113706e-05 tokens_per_second_per_gpu:4899.320521453933 mfu:23.1109308099755 Step 782 | loss:1.2726640701293945 lr:4.880928421197946e-05 tokens_per_second_per_gpu:5317.7090638793925 mfu:25.084540949042662 Step 783 | loss:1.4302386045455933 lr:4.880594999874587e-05 tokens_per_second_per_gpu:5357.298773357583 mfu:25.27129236335224 Step 784 | loss:1.5150680541992188 lr:4.880261123804988e-05 tokens_per_second_per_gpu:3740.1453942466437 mfu:17.642903959268033 Step 785 | loss:1.4925788640975952 lr:4.8799267930529235e-05 tokens_per_second_per_gpu:4117.097768094883 mfu:19.421052621417076 Step 786 | loss:1.4869695901870728 lr:4.87959200768226e-05 tokens_per_second_per_gpu:5324.637591242143 mfu:25.11722399474142 Step 787 | loss:1.3053630590438843 lr:4.8792567677569485e-05 tokens_per_second_per_gpu:5327.818490300654 mfu:25.132228838317758 Step 788 | loss:1.4119935035705566 lr:4.8789210733410265e-05 tokens_per_second_per_gpu:5270.1561082459075 mfu:24.860225543948655 Step 789 | loss:1.5757222175598145 lr:4.878584924498619e-05 tokens_per_second_per_gpu:4061.343666714149 mfu:19.158051012573548 Step 790 | loss:1.3036494255065918 lr:4.87824832129394e-05 tokens_per_second_per_gpu:4996.54474314263 mfu:23.569554051843824 Step 791 | loss:1.299959659576416 lr:4.877911263791285e-05 tokens_per_second_per_gpu:4404.937628420102 mfu:20.778842353115426 Step 792 | loss:1.4837523698806763 lr:4.8775737520550416e-05 tokens_per_second_per_gpu:4165.859367348065 mfu:19.651069404681056 Step 793 | loss:1.667550802230835 lr:4.877235786149682e-05 tokens_per_second_per_gpu:3743.124096711809 mfu:17.656955007015263 Step 794 | loss:1.4169450998306274 lr:4.876897366139763e-05 tokens_per_second_per_gpu:5324.70795512048 mfu:25.11755591316085 Step 795 | loss:1.4509210586547852 lr:4.876558492089933e-05 tokens_per_second_per_gpu:3469.39366827485 mfu:16.365721872851154 Step 796 | loss:1.4386165142059326 lr:4.876219164064923e-05 tokens_per_second_per_gpu:3970.6439550801615 mfu:18.730204997829496 Step 797 | loss:1.5665382146835327 lr:4.8758793821295525e-05 tokens_per_second_per_gpu:3153.6876799732654 mfu:14.87648286103659 Step 798 | loss:1.46611487865448 lr:4.875539146348727e-05 tokens_per_second_per_gpu:4037.9161179549833 mfu:19.047539267924574 Step 799 | loss:1.5589931011199951 lr:4.875198456787439e-05 tokens_per_second_per_gpu:3484.961536719837 mfu:16.439158164458405 Step 800 | loss:1.4810113906860352 lr:4.8748573135107687e-05 tokens_per_second_per_gpu:4729.338326204117 mfu:22.30909579302902 Step 801 | loss:1.4830862283706665 lr:4.87451571658388e-05 tokens_per_second_per_gpu:3067.284602721082 mfu:14.468904803752928 Step 802 | loss:1.5108553171157837 lr:4.874173666072029e-05 tokens_per_second_per_gpu:5254.840981637453 mfu:24.78798147870653 Step 803 | loss:1.3259295225143433 lr:4.873831162040551e-05 tokens_per_second_per_gpu:5297.914272483958 mfu:24.991165540690723 Step 804 | loss:1.0647417306900024 lr:4.873488204554875e-05 tokens_per_second_per_gpu:5309.661445808322 mfu:25.046578961536195 Step 805 | loss:1.388066291809082 lr:4.8731447936805105e-05 tokens_per_second_per_gpu:4120.905145106169 mfu:19.439012668384816 Step 806 | loss:1.2911850214004517 lr:4.872800929483059e-05 tokens_per_second_per_gpu:5338.765008937858 mfu:25.183865434398115 Step 807 | loss:1.518470287322998 lr:4.8724566120282044e-05 tokens_per_second_per_gpu:3616.994636131644 mfu:17.061980821553586 Step 808 | loss:1.5488468408584595 lr:4.87211184138172e-05 tokens_per_second_per_gpu:5158.104855676528 mfu:24.331660667663826 Step 809 | loss:1.4332886934280396 lr:4.871766617609465e-05 tokens_per_second_per_gpu:5302.6285040858675 mfu:25.013403375487783 Step 810 | loss:1.5526413917541504 lr:4.871420940777384e-05 tokens_per_second_per_gpu:4548.6075335272235 mfu:21.45655780811919 Step 811 | loss:1.4784960746765137 lr:4.871074810951509e-05 tokens_per_second_per_gpu:5362.65947451975 mfu:25.296579705364117 Step 812 | loss:1.4077777862548828 lr:4.870728228197958e-05 tokens_per_second_per_gpu:4240.731157703043 mfu:20.004252414230184 Step 813 | loss:1.6367281675338745 lr:4.870381192582937e-05 tokens_per_second_per_gpu:4208.429875898451 mfu:19.851881756790956 Step 814 | loss:1.5294615030288696 lr:4.870033704172737e-05 tokens_per_second_per_gpu:3319.634868187157 mfu:15.659284061351423 Step 815 | loss:1.440550446510315 lr:4.8696857630337356e-05 tokens_per_second_per_gpu:5329.104841732083 mfu:25.138296777493995 Step 816 | loss:1.374964714050293 lr:4.8693373692323975e-05 tokens_per_second_per_gpu:5311.150094896919 mfu:25.053601173276828 Step 817 | loss:1.4228625297546387 lr:4.868988522835274e-05 tokens_per_second_per_gpu:5286.152882754916 mfu:24.935685058638825 Step 818 | loss:1.4923988580703735 lr:4.868639223909002e-05 tokens_per_second_per_gpu:3255.7344255603252 mfu:15.357854770940913 Step 819 | loss:1.4664695262908936 lr:4.868289472520305e-05 tokens_per_second_per_gpu:4955.609059739729 mfu:23.376453448884543 Step 820 | loss:1.3408994674682617 lr:4.8679392687359944e-05 tokens_per_second_per_gpu:5332.219961621153 mfu:25.152991329504996 Step 821 | loss:1.5043987035751343 lr:4.8675886126229655e-05 tokens_per_second_per_gpu:4163.982465610069 mfu:19.642215738950476 Step 822 | loss:1.4212886095046997 lr:4.867237504248202e-05 tokens_per_second_per_gpu:3995.3730192045155 mfu:18.846856212517483 Step 823 | loss:1.369957685470581 lr:4.866885943678774e-05 tokens_per_second_per_gpu:5301.982594669726 mfu:25.010356510568332 Step 824 | loss:1.3891751766204834 lr:4.866533930981836e-05 tokens_per_second_per_gpu:4938.340723983104 mfu:23.294995762838653 Step 825 | loss:1.4766417741775513 lr:4.866181466224632e-05 tokens_per_second_per_gpu:3958.3095816879195 mfu:18.672021654077184 Step 826 | loss:1.398097276687622 lr:4.8658285494744884e-05 tokens_per_second_per_gpu:4415.33176290347 mfu:20.827873258895686 Step 827 | loss:1.4104199409484863 lr:4.865475180798821e-05 tokens_per_second_per_gpu:4151.530424038874 mfu:19.58347733432178 Step 828 | loss:1.3538379669189453 lr:4.8651213602651326e-05 tokens_per_second_per_gpu:5324.964703962178 mfu:25.118767041253008 Step 829 | loss:1.4312796592712402 lr:4.864767087941008e-05 tokens_per_second_per_gpu:5348.489258210449 mfu:25.229736377344942 Step 830 | loss:1.4519890546798706 lr:4.864412363894123e-05 tokens_per_second_per_gpu:4814.4116300974765 mfu:22.71040108249638 Step 831 | loss:1.4538878202438354 lr:4.864057188192237e-05 tokens_per_second_per_gpu:4722.46287833061 mfu:22.276663132337315 Step 832 | loss:1.278542160987854 lr:4.863701560903195e-05 tokens_per_second_per_gpu:5310.413761226397 mfu:25.050127761721498 Step 833 | loss:1.531822919845581 lr:4.863345482094933e-05 tokens_per_second_per_gpu:4957.908077888927 mfu:23.387298309747255 Step 834 | loss:1.353065848350525 lr:4.862988951835468e-05 tokens_per_second_per_gpu:5015.726193662916 mfu:23.660036226640933 Step 835 | loss:1.5979981422424316 lr:4.8626319701929045e-05 tokens_per_second_per_gpu:4055.380535451267 mfu:19.12992190499143 Step 836 | loss:1.4007961750030518 lr:4.862274537235435e-05 tokens_per_second_per_gpu:4309.785417019236 mfu:20.329993137296213 Step 837 | loss:1.5607316493988037 lr:4.861916653031337e-05 tokens_per_second_per_gpu:4039.2873978151565 mfu:19.05400782898948 Step 838 | loss:1.538848876953125 lr:4.861558317648974e-05 tokens_per_second_per_gpu:4299.717969014261 mfu:20.282503267372995 Step 839 | loss:1.386834740638733 lr:4.861199531156795e-05 tokens_per_second_per_gpu:4355.490280605177 mfu:20.545590776884936 Step 840 | loss:1.291765809059143 lr:4.860840293623338e-05 tokens_per_second_per_gpu:4358.288185700566 mfu:20.558788972591717 Step 841 | loss:1.6413846015930176 lr:4.8604806051172244e-05 tokens_per_second_per_gpu:3435.758092014598 mfu:16.207057120810465 Step 842 | loss:1.3287631273269653 lr:4.860120465707162e-05 tokens_per_second_per_gpu:5324.592601881766 mfu:25.117011772252546 Step 843 | loss:1.430799126625061 lr:4.859759875461947e-05 tokens_per_second_per_gpu:4162.011341737092 mfu:19.63291761133323 Step 844 | loss:1.5791890621185303 lr:4.859398834450459e-05 tokens_per_second_per_gpu:5341.47226048243 mfu:25.19663600183861 Step 845 | loss:1.4558323621749878 lr:4.859037342741665e-05 tokens_per_second_per_gpu:4623.755255214351 mfu:21.811042432840804 Step 846 | loss:1.3160367012023926 lr:4.8586754004046176e-05 tokens_per_second_per_gpu:5323.610690118453 mfu:25.112379926933574 Step 847 | loss:1.5332638025283813 lr:4.858313007508456e-05 tokens_per_second_per_gpu:5307.731545477184 mfu:25.037475292399265 Step 848 | loss:1.4779365062713623 lr:4.8579501641224054e-05 tokens_per_second_per_gpu:5306.980271546886 mfu:25.033931405089497 Step 849 | loss:1.6030335426330566 lr:4.857586870315777e-05 tokens_per_second_per_gpu:2910.184405398705 mfu:13.727836368925667 Step 850 | loss:1.5758246183395386 lr:4.857223126157967e-05 tokens_per_second_per_gpu:4340.611108797656 mfu:20.475403184820372 Step 851 | loss:1.5447759628295898 lr:4.8568589317184604e-05 tokens_per_second_per_gpu:3580.975123520046 mfu:16.89207063500212 Step 852 | loss:1.3799712657928467 lr:4.856494287066825e-05 tokens_per_second_per_gpu:5227.9907224021945 mfu:24.6613242247672 Step 853 | loss:1.5307633876800537 lr:4.856129192272716e-05 tokens_per_second_per_gpu:3636.005448969049 mfu:17.151658069286768 Step 854 | loss:1.4139487743377686 lr:4.8557636474058756e-05 tokens_per_second_per_gpu:4814.676175061258 mfu:22.71164898622656 Step 855 | loss:1.4619054794311523 lr:4.855397652536129e-05 tokens_per_second_per_gpu:3616.2281926060477 mfu:17.0583653766746 Step 856 | loss:1.6057519912719727 lr:4.855031207733391e-05 tokens_per_second_per_gpu:2792.6131489953154 mfu:13.17323269274604 Step 857 | loss:1.549096941947937 lr:4.854664313067661e-05 tokens_per_second_per_gpu:5366.028267474329 mfu:25.312470876506218 Step 858 | loss:1.4162545204162598 lr:4.8542969686090224e-05 tokens_per_second_per_gpu:5323.569558646846 mfu:25.112185902764256 Step 859 | loss:1.4244530200958252 lr:4.853929174427647e-05 tokens_per_second_per_gpu:5309.2686493552565 mfu:25.044726073649095 Step 860 | loss:1.5386615991592407 lr:4.853560930593792e-05 tokens_per_second_per_gpu:4405.182595317247 mfu:20.779997903764926 Step 861 | loss:1.6483213901519775 lr:4.8531922371777996e-05 tokens_per_second_per_gpu:4542.4585123554125 mfu:21.427551826120563 Step 862 | loss:1.5861066579818726 lr:4.8528230942500976e-05 tokens_per_second_per_gpu:4269.817059895209 mfu:20.14145557743727 Step 863 | loss:1.5019747018814087 lr:4.8524535018812014e-05 tokens_per_second_per_gpu:4349.754296238998 mfu:20.51853315996982 Step 864 | loss:1.4933323860168457 lr:4.8520834601417114e-05 tokens_per_second_per_gpu:4390.960504378281 mfu:20.71290987426689 Step 865 | loss:1.3470004796981812 lr:4.8517129691023135e-05 tokens_per_second_per_gpu:4523.070619969392 mfu:21.336095829820163 Step 866 | loss:1.5723503828048706 lr:4.85134202883378e-05 tokens_per_second_per_gpu:3646.2468540687146 mfu:17.19996852450578 Step 867 | loss:1.5636539459228516 lr:4.8509706394069675e-05 tokens_per_second_per_gpu:5299.038235941019 mfu:24.99646746808562 Step 868 | loss:1.4185116291046143 lr:4.8505988008928215e-05 tokens_per_second_per_gpu:5300.762295685856 mfu:25.004600152056938 Step 869 | loss:1.4463074207305908 lr:4.85022651336237e-05 tokens_per_second_per_gpu:4027.4497050649315 mfu:18.99816741256802 Step 870 | loss:1.438977599143982 lr:4.849853776886728e-05 tokens_per_second_per_gpu:4976.861725302131 mfu:23.47670589842105 Step 871 | loss:1.4250036478042603 lr:4.8494805915370965e-05 tokens_per_second_per_gpu:3593.607123709706 mfu:16.95165793513822 Step 872 | loss:1.2726261615753174 lr:4.849106957384763e-05 tokens_per_second_per_gpu:5347.312819043838 mfu:25.224186913074814 Step 873 | loss:1.476394772529602 lr:4.848732874501101e-05 tokens_per_second_per_gpu:5331.464557711263 mfu:25.149427960376848 Step 874 | loss:1.580492615699768 lr:4.848358342957565e-05 tokens_per_second_per_gpu:4501.4544174663515 mfu:21.23412851450887 Step 875 | loss:1.5058104991912842 lr:4.847983362825701e-05 tokens_per_second_per_gpu:3886.393538661359 mfu:18.3327814089787 Step 876 | loss:1.4706230163574219 lr:4.847607934177139e-05 tokens_per_second_per_gpu:5310.484538378063 mfu:25.050461629621736 Step 877 | loss:1.4124865531921387 lr:4.847232057083593e-05 tokens_per_second_per_gpu:4616.255508301355 mfu:21.775664847063428 Step 878 | loss:1.3786972761154175 lr:4.846855731616864e-05 tokens_per_second_per_gpu:4308.175158045659 mfu:20.32239727097934 Step 879 | loss:1.3755072355270386 lr:4.846478957848839e-05 tokens_per_second_per_gpu:5294.125656123077 mfu:24.973293990911838 Step 880 | loss:1.5090305805206299 lr:4.84610173585149e-05 tokens_per_second_per_gpu:3660.432549356166 mfu:17.26688486950588 Step 881 | loss:1.5371612310409546 lr:4.845724065696875e-05 tokens_per_second_per_gpu:5322.46531841691 mfu:25.106977013196833 Step 882 | loss:1.4815120697021484 lr:4.845345947457136e-05 tokens_per_second_per_gpu:4464.398803859784 mfu:21.059330862787064 Step 883 | loss:1.4328088760375977 lr:4.8449673812045036e-05 tokens_per_second_per_gpu:5297.998924137847 mfu:24.991564856985182 Step 884 | loss:1.6335043907165527 lr:4.8445883670112915e-05 tokens_per_second_per_gpu:3726.3382321147055 mfu:17.577773219746906 Step 885 | loss:1.3879005908966064 lr:4.8442089049499e-05 tokens_per_second_per_gpu:4329.865112614169 mfu:20.424712487366854 Step 886 | loss:1.277345061302185 lr:4.843828995092814e-05 tokens_per_second_per_gpu:4374.164091935315 mfu:20.633678331009946 Step 887 | loss:1.5833754539489746 lr:4.843448637512606e-05 tokens_per_second_per_gpu:4415.651146450474 mfu:20.829379845579357 Step 888 | loss:1.463755488395691 lr:4.8430678322819317e-05 tokens_per_second_per_gpu:3736.7759368539478 mfu:17.627009653857975 Step 889 | loss:1.587701439857483 lr:4.842686579473534e-05 tokens_per_second_per_gpu:4211.521263905207 mfu:19.866464361464004 Step 890 | loss:1.5153840780258179 lr:4.84230487916024e-05 tokens_per_second_per_gpu:4621.942816574483 mfu:21.802492850542627 Step 891 | loss:1.3326555490493774 lr:4.841922731414963e-05 tokens_per_second_per_gpu:5220.3597613906995 mfu:24.625327679699772 Step 892 | loss:1.402990698814392 lr:4.841540136310702e-05 tokens_per_second_per_gpu:4592.68075721579 mfu:21.664458723925524 Step 893 | loss:1.4439820051193237 lr:4.84115709392054e-05 tokens_per_second_per_gpu:5339.0450610746975 mfu:25.185186488109412 Step 894 | loss:1.5267497301101685 lr:4.840773604317648e-05 tokens_per_second_per_gpu:3574.435649698443 mfu:16.86122282123633 Step 895 | loss:1.600492238998413 lr:4.840389667575281e-05 tokens_per_second_per_gpu:5297.06828883167 mfu:24.987174891463184 Step 896 | loss:1.5580005645751953 lr:4.840005283766778e-05 tokens_per_second_per_gpu:4053.1124700933124 mfu:19.119223053726103 Step 897 | loss:1.4212164878845215 lr:4.8396204529655665e-05 tokens_per_second_per_gpu:4706.630301973427 mfu:22.201978168344407 Step 898 | loss:1.628829002380371 lr:4.839235175245156e-05 tokens_per_second_per_gpu:5234.286764917195 mfu:24.69102373152608 Step 899 | loss:1.3188552856445312 lr:4.838849450679145e-05 tokens_per_second_per_gpu:5082.737346316363 mfu:23.976139266988852 Step 900 | loss:1.4091763496398926 lr:4.8384632793412135e-05 tokens_per_second_per_gpu:4776.427319529467 mfu:22.53122260875542 Step 901 | loss:1.3952654600143433 lr:4.838076661305129e-05 tokens_per_second_per_gpu:5099.826561009719 mfu:24.056752008418094 Step 902 | loss:1.42682945728302 lr:4.8376895966447456e-05 tokens_per_second_per_gpu:5330.5320408292955 mfu:25.145029119140823 Step 903 | loss:1.3755240440368652 lr:4.837302085434e-05 tokens_per_second_per_gpu:4442.376917529955 mfu:20.955449867648014 Step 904 | loss:1.4647207260131836 lr:4.836914127746915e-05 tokens_per_second_per_gpu:5310.323615745125 mfu:25.04970253010593 Step 905 | loss:1.3128677606582642 lr:4.836525723657601e-05 tokens_per_second_per_gpu:5323.348343706458 mfu:25.11114239414728 Step 906 | loss:1.4094125032424927 lr:4.83613687324025e-05 tokens_per_second_per_gpu:5367.897114167133 mfu:25.321286545214292 Step 907 | loss:1.379960298538208 lr:4.8357475765691415e-05 tokens_per_second_per_gpu:5345.395268583017 mfu:25.21514150038328 Step 908 | loss:1.3729826211929321 lr:4.835357833718639e-05 tokens_per_second_per_gpu:5331.147198735358 mfu:25.147930923940482 Step 909 | loss:1.4218087196350098 lr:4.834967644763194e-05 tokens_per_second_per_gpu:5317.1815417196585 mfu:25.082052537010632 Step 910 | loss:1.4214986562728882 lr:4.834577009777339e-05 tokens_per_second_per_gpu:5056.216798808422 mfu:23.8510373195219 Step 911 | loss:1.3992688655853271 lr:4.834185928835696e-05 tokens_per_second_per_gpu:3825.2405443825055 mfu:18.04431230118863 Step 912 | loss:1.5639116764068604 lr:4.8337944020129674e-05 tokens_per_second_per_gpu:3837.840607584532 mfu:18.10374894910505 Step 913 | loss:1.342976450920105 lr:4.833402429383947e-05 tokens_per_second_per_gpu:5341.497243085432 mfu:25.196753849039442 Step 914 | loss:1.183871865272522 lr:4.833010011023508e-05 tokens_per_second_per_gpu:4816.65146682617 mfu:22.720966774501182 Step 915 | loss:1.283042311668396 lr:4.83261714700661e-05 tokens_per_second_per_gpu:5290.495447931672 mfu:24.9561696794956 Step 916 | loss:1.5770982503890991 lr:4.832223837408301e-05 tokens_per_second_per_gpu:3568.889028190769 mfu:16.835058461233416 Step 917 | loss:1.468976616859436 lr:4.83183008230371e-05 tokens_per_second_per_gpu:5326.7434072437045 mfu:25.127157488110043 Step 918 | loss:1.3625938892364502 lr:4.831435881768054e-05 tokens_per_second_per_gpu:4637.736967095452 mfu:21.876996553309993 Step 919 | loss:1.3592753410339355 lr:4.8310412358766345e-05 tokens_per_second_per_gpu:5084.100631413658 mfu:23.982570115393216 Step 920 | loss:1.3644152879714966 lr:4.8306461447048366e-05 tokens_per_second_per_gpu:5302.80887696348 mfu:25.014254225126265 Step 921 | loss:1.2811692953109741 lr:4.830250608328131e-05 tokens_per_second_per_gpu:5009.43945911621 mfu:23.630380627156608 Step 922 | loss:1.4418398141860962 lr:4.829854626822076e-05 tokens_per_second_per_gpu:5316.004896392445 mfu:25.076502100245772 Step 923 | loss:1.3111536502838135 lr:4.82945820026231e-05 tokens_per_second_per_gpu:5209.542991425651 mfu:24.574303130243376 Step 924 | loss:1.387332558631897 lr:4.8290613287245613e-05 tokens_per_second_per_gpu:3669.660449265553 mfu:17.310414447820534 Step 925 | loss:1.3744714260101318 lr:4.82866401228464e-05 tokens_per_second_per_gpu:5345.457365766609 mfu:25.21543442339315 Step 926 | loss:1.4475957155227661 lr:4.828266251018443e-05 tokens_per_second_per_gpu:3626.665932145068 mfu:17.107601974942163 Step 927 | loss:1.4286640882492065 lr:4.827868045001951e-05 tokens_per_second_per_gpu:5173.822412450162 mfu:24.405803064656773 Step 928 | loss:1.4756550788879395 lr:4.827469394311231e-05 tokens_per_second_per_gpu:5317.156940331582 mfu:25.081936488065647 Step 929 | loss:1.2894200086593628 lr:4.8270702990224325e-05 tokens_per_second_per_gpu:5319.668014888682 mfu:25.093781655184983 Step 930 | loss:1.5797836780548096 lr:4.826670759211794e-05 tokens_per_second_per_gpu:4822.382791171087 mfu:22.748002409300923 Step 931 | loss:1.4506930112838745 lr:4.8262707749556335e-05 tokens_per_second_per_gpu:5167.926813485684 mfu:24.37799251844842 Step 932 | loss:1.3701468706130981 lr:4.825870346330359e-05 tokens_per_second_per_gpu:3553.1457190951196 mfu:16.760794586143728 Step 933 | loss:1.4117461442947388 lr:4.825469473412461e-05 tokens_per_second_per_gpu:4278.93120354787 mfu:20.184448548080127 Step 934 | loss:1.528695821762085 lr:4.825068156278514e-05 tokens_per_second_per_gpu:4490.06168402368 mfu:21.18038704705902 Step 935 | loss:1.3351176977157593 lr:4.824666395005178e-05 tokens_per_second_per_gpu:3805.6667485539256 mfu:17.951979366631278 Step 936 | loss:1.4595369100570679 lr:4.824264189669201e-05 tokens_per_second_per_gpu:5327.447822011855 mfu:25.130480332756964 Step 937 | loss:1.5882244110107422 lr:4.8238615403474106e-05 tokens_per_second_per_gpu:4403.651706009435 mfu:20.77277643770332 Step 938 | loss:1.3631641864776611 lr:4.823458447116723e-05 tokens_per_second_per_gpu:3908.1138648578917 mfu:18.435239893517533 Step 939 | loss:1.3836523294448853 lr:4.823054910054137e-05 tokens_per_second_per_gpu:5340.546135890287 mfu:25.192267314124315 Step 940 | loss:1.2306140661239624 lr:4.8226509292367375e-05 tokens_per_second_per_gpu:5316.1091145796245 mfu:25.076993715216155 Step 941 | loss:1.3504079580307007 lr:4.8222465047416944e-05 tokens_per_second_per_gpu:5325.863652139268 mfu:25.12300753318072 Step 942 | loss:1.2918516397476196 lr:4.821841636646261e-05 tokens_per_second_per_gpu:4318.050730559923 mfu:20.36898203147554 Step 943 | loss:1.3941441774368286 lr:4.821436325027775e-05 tokens_per_second_per_gpu:5288.692886223986 mfu:24.9476666883717 Step 944 | loss:1.3512606620788574 lr:4.821030569963661e-05 tokens_per_second_per_gpu:5143.356634027811 mfu:24.262090789840745 Step 945 | loss:1.4247500896453857 lr:4.820624371531429e-05 tokens_per_second_per_gpu:4820.415531617402 mfu:22.7387225103371 Step 946 | loss:1.371683120727539 lr:4.820217729808669e-05 tokens_per_second_per_gpu:5322.848562678524 mfu:25.108784841767083 Step 947 | loss:1.5176242589950562 lr:4.8198106448730596e-05 tokens_per_second_per_gpu:4684.525503565064 mfu:22.097706062784653 Step 948 | loss:1.3950814008712769 lr:4.819403116802363e-05 tokens_per_second_per_gpu:3923.649839842943 mfu:18.508525738232688 Step 949 | loss:1.5699888467788696 lr:4.8189951456744265e-05 tokens_per_second_per_gpu:4700.280587430942 mfu:22.172025481474492 Step 950 | loss:1.5209767818450928 lr:4.818586731567181e-05 tokens_per_second_per_gpu:5360.946094422578 mfu:25.28849739911297 Step 951 | loss:1.3555357456207275 lr:4.8181778745586433e-05 tokens_per_second_per_gpu:4240.139014665671 mfu:20.001459174492883 Step 952 | loss:1.6257288455963135 lr:4.817768574726913e-05 tokens_per_second_per_gpu:3157.4110684692782 mfu:14.894046719847868 Step 953 | loss:1.5602138042449951 lr:4.817358832150176e-05 tokens_per_second_per_gpu:4003.6782375746734 mfu:18.886033344585893 Step 954 | loss:1.6103774309158325 lr:4.816948646906703e-05 tokens_per_second_per_gpu:5185.4041892144405 mfu:24.460436281708752 Step 955 | loss:1.3824410438537598 lr:4.816538019074847e-05 tokens_per_second_per_gpu:4258.136745731683 mfu:20.08635754266082 Step 956 | loss:1.3854155540466309 lr:4.8161269487330483e-05 tokens_per_second_per_gpu:3406.894546653213 mfu:16.070902852712162 Step 957 | loss:1.4090389013290405 lr:4.815715435959829e-05 tokens_per_second_per_gpu:4602.8575319591255 mfu:21.712464306726652 Step 958 | loss:1.4081424474716187 lr:4.8153034808337986e-05 tokens_per_second_per_gpu:5330.952370016419 mfu:25.147011883632036 Step 959 | loss:1.3440369367599487 lr:4.814891083433649e-05 tokens_per_second_per_gpu:4428.848809730654 mfu:20.891635475025513 Step 960 | loss:1.3192030191421509 lr:4.814478243838157e-05 tokens_per_second_per_gpu:5310.732196313006 mfu:25.051629874355662 Step 961 | loss:1.5220060348510742 lr:4.814064962126184e-05 tokens_per_second_per_gpu:4237.637834222057 mfu:19.989660679594966 Step 962 | loss:1.4161176681518555 lr:4.8136512383766764e-05 tokens_per_second_per_gpu:4214.104576046291 mfu:19.878650285592 Step 963 | loss:1.4081560373306274 lr:4.8132370726686646e-05 tokens_per_second_per_gpu:3982.3104842050434 mfu:18.785238006226688 Step 964 | loss:1.374681830406189 lr:4.8128224650812625e-05 tokens_per_second_per_gpu:5019.07659443061 mfu:23.675840638699466 Step 965 | loss:1.4101324081420898 lr:4.812407415693671e-05 tokens_per_second_per_gpu:5317.685884985668 mfu:25.084431610246238 Step 966 | loss:1.3435988426208496 lr:4.811991924585172e-05 tokens_per_second_per_gpu:4347.9529916033525 mfu:20.510036098669218 Step 967 | loss:1.355586290359497 lr:4.8115759918351345e-05 tokens_per_second_per_gpu:4347.9903079643955 mfu:20.510212126311085 Step 968 | loss:1.460465431213379 lr:4.811159617523011e-05 tokens_per_second_per_gpu:4921.174706493617 mfu:23.21402072951615 Step 969 | loss:1.6330156326293945 lr:4.8107428017283365e-05 tokens_per_second_per_gpu:3872.2487457868933 mfu:18.26605800763933 Step 970 | loss:1.3891409635543823 lr:4.810325544530734e-05 tokens_per_second_per_gpu:4552.52091718263 mfu:21.475017906513845 Step 971 | loss:1.4371429681777954 lr:4.8099078460099076e-05 tokens_per_second_per_gpu:4782.777026245507 mfu:22.56117525870666 Step 972 | loss:1.4085664749145508 lr:4.809489706245648e-05 tokens_per_second_per_gpu:5257.790038128007 mfu:24.801892681333396 Step 973 | loss:1.5638853311538696 lr:4.809071125317829e-05 tokens_per_second_per_gpu:4444.875317466572 mfu:20.96723524642002 Step 974 | loss:1.6907844543457031 lr:4.808652103306407e-05 tokens_per_second_per_gpu:3825.985388381066 mfu:18.04782585741333 Step 975 | loss:1.4486274719238281 lr:4.808232640291427e-05 tokens_per_second_per_gpu:5116.24285754347 mfu:24.13419048007681 Step 976 | loss:1.5032615661621094 lr:4.807812736353014e-05 tokens_per_second_per_gpu:4851.793556643741 mfu:22.88673800802946 Step 977 | loss:1.3688747882843018 lr:4.807392391571379e-05 tokens_per_second_per_gpu:4376.1866296095395 mfu:20.643218986299775 Step 978 | loss:1.3145253658294678 lr:4.8069716060268185e-05 tokens_per_second_per_gpu:5182.505312443238 mfu:24.44676178537961 Step 979 | loss:1.4690237045288086 lr:4.806550379799711e-05 tokens_per_second_per_gpu:4502.328802491971 mfu:21.238253137860188 Step 980 | loss:1.3415182828903198 lr:4.806128712970519e-05 tokens_per_second_per_gpu:4809.653923152907 mfu:22.687958167090336 Step 981 | loss:1.4403669834136963 lr:4.805706605619792e-05 tokens_per_second_per_gpu:4026.804185799572 mfu:18.995122388056377 Step 982 | loss:1.5840970277786255 lr:4.805284057828161e-05 tokens_per_second_per_gpu:4821.5952204759415 mfu:22.744287303958505 Step 983 | loss:1.3641788959503174 lr:4.8048610696763414e-05 tokens_per_second_per_gpu:4549.513731920776 mfu:21.460832500554968 Step 984 | loss:1.5443414449691772 lr:4.804437641245134e-05 tokens_per_second_per_gpu:3559.772535811603 mfu:16.7920544112469 Step 985 | loss:1.3633122444152832 lr:4.804013772615423e-05 tokens_per_second_per_gpu:4836.0877286085815 mfu:22.81265093749703 Step 986 | loss:1.3332480192184448 lr:4.8035894638681764e-05 tokens_per_second_per_gpu:5107.081778448158 mfu:24.090976106942954 Step 987 | loss:1.3999544382095337 lr:4.8031647150844463e-05 tokens_per_second_per_gpu:5312.985986192827 mfu:25.06226138575498 Step 988 | loss:1.2498259544372559 lr:4.80273952634537e-05 tokens_per_second_per_gpu:4442.193267845919 mfu:20.954583560754546 Step 989 | loss:1.5564733743667603 lr:4.8023138977321666e-05 tokens_per_second_per_gpu:4515.891633556741 mfu:21.3022313260503 Step 990 | loss:1.2408428192138672 lr:4.8018878293261416e-05 tokens_per_second_per_gpu:3731.5569291934216 mfu:17.602390704268743 Step 991 | loss:1.617775321006775 lr:4.801461321208683e-05 tokens_per_second_per_gpu:3403.029514356867 mfu:16.05267083592779 Step 992 | loss:1.1919702291488647 lr:4.801034373461264e-05 tokens_per_second_per_gpu:4374.97532779137 mfu:20.637505068954066 Step 993 | loss:1.3656643629074097 lr:4.800606986165441e-05 tokens_per_second_per_gpu:4559.396739353208 mfu:21.507452332828695 Step 994 | loss:1.5395536422729492 lr:4.8001791594028536e-05 tokens_per_second_per_gpu:3101.6257247688723 mfu:14.630897735651958 Step 995 | loss:1.5589083433151245 lr:4.799750893255226e-05 tokens_per_second_per_gpu:5184.345357638288 mfu:24.45544159250875 Step 996 | loss:1.3172292709350586 lr:4.799322187804367e-05 tokens_per_second_per_gpu:4763.976996224971 mfu:22.47249230948391 Step 997 | loss:1.4600822925567627 lr:4.798893043132169e-05 tokens_per_second_per_gpu:3691.6454995989875 mfu:17.414121681279727 Step 998 | loss:1.2997127771377563 lr:4.798463459320608e-05 tokens_per_second_per_gpu:4388.197036082806 mfu:20.699874122820827 Step 999 | loss:1.415252447128296 lr:4.798033436451744e-05 tokens_per_second_per_gpu:4108.92005906483 mfu:19.382476972661284 Step 1000 | loss:1.499133825302124 lr:4.797602974607721e-05 tokens_per_second_per_gpu:5320.704305944685 mfu:25.098670016905636 Step 1001 | loss:1.3302669525146484 lr:4.797172073870767e-05 tokens_per_second_per_gpu:5331.131114326042 mfu:25.147855051037453 Step 1002 | loss:1.4135682582855225 lr:4.7967407343231916e-05 tokens_per_second_per_gpu:5136.401904402362 mfu:24.229284143598264 Step 1003 | loss:1.4204272031784058 lr:4.796308956047393e-05 tokens_per_second_per_gpu:5037.75294235691 mfu:23.763940158381363 Step 1004 | loss:1.5103927850723267 lr:4.7958767391258486e-05 tokens_per_second_per_gpu:3907.6172759512074 mfu:18.432897398917902 Step 1005 | loss:1.456060528755188 lr:4.795444083641122e-05 tokens_per_second_per_gpu:5371.5926659565375 mfu:25.33871909353107 Step 1006 | loss:1.3882919549942017 lr:4.79501098967586e-05 tokens_per_second_per_gpu:5325.061504541253 mfu:25.11922366610039 Step 1007 | loss:1.2673290967941284 lr:4.794577457312792e-05 tokens_per_second_per_gpu:4430.922643559655 mfu:20.90141810302945 Step 1008 | loss:1.564376711845398 lr:4.794143486634734e-05 tokens_per_second_per_gpu:4884.404709050019 mfu:23.040570377966215 Step 1009 | loss:1.3558380603790283 lr:4.793709077724583e-05 tokens_per_second_per_gpu:5081.645184028704 mfu:23.97098735113586 Step 1010 | loss:1.4555326700210571 lr:4.793274230665321e-05 tokens_per_second_per_gpu:5342.91689308708 mfu:25.20345058031448 Step 1011 | loss:1.4810353517532349 lr:4.7928389455400125e-05 tokens_per_second_per_gpu:4341.073904173849 mfu:20.477586269570903 Step 1012 | loss:1.4142309427261353 lr:4.792403222431808e-05 tokens_per_second_per_gpu:5330.108309059903 mfu:25.1430303040885 Step 1013 | loss:1.4191184043884277 lr:4.79196706142394e-05 tokens_per_second_per_gpu:4359.9816831525395 mfu:20.566777489013138 Step 1014 | loss:1.354946494102478 lr:4.7915304625997236e-05 tokens_per_second_per_gpu:5059.8461899684 mfu:23.8681577768615 Step 1015 | loss:1.482694149017334 lr:4.79109342604256e-05 tokens_per_second_per_gpu:3381.8329857379345 mfu:15.952683193931579 Step 1016 | loss:1.3873425722122192 lr:4.790655951835933e-05 tokens_per_second_per_gpu:4014.455660311201 mfu:18.936872286452026 Step 1017 | loss:1.6338140964508057 lr:4.790218040063409e-05 tokens_per_second_per_gpu:3371.0320794163076 mfu:15.901733475987822 Step 1018 | loss:1.4574507474899292 lr:4.789779690808639e-05 tokens_per_second_per_gpu:4379.251270046809 mfu:20.65767541812395 Step 1019 | loss:1.35683274269104 lr:4.7893409041553575e-05 tokens_per_second_per_gpu:5323.662944693751 mfu:25.112626420680808 Step 1020 | loss:1.6232281923294067 lr:4.788901680187383e-05 tokens_per_second_per_gpu:5303.679138147121 mfu:25.01835939561137 Step 1021 | loss:1.537520408630371 lr:4.7884620189886166e-05 tokens_per_second_per_gpu:3934.1138846860326 mfu:18.55788642310769 Step 1022 | loss:1.2711315155029297 lr:4.788021920643043e-05 tokens_per_second_per_gpu:5142.606323014601 mfu:24.258551444775172 Step 1023 | loss:1.3897379636764526 lr:4.787581385234731e-05 tokens_per_second_per_gpu:3937.5041822926587 mfu:18.573879035362562 Step 1024 | loss:1.5038615465164185 lr:4.787140412847832e-05 tokens_per_second_per_gpu:3715.312317234983 mfu:17.525762098044186 Step 1025 | loss:1.5541725158691406 lr:4.786699003566583e-05 tokens_per_second_per_gpu:4205.086060690271 mfu:19.836108409940262 Step 1026 | loss:1.4429254531860352 lr:4.7862571574753006e-05 tokens_per_second_per_gpu:3989.4828903437706 mfu:18.819071469721738 Step 1027 | loss:1.5003471374511719 lr:4.785814874658389e-05 tokens_per_second_per_gpu:4861.667969360476 mfu:22.93331729756283 Step 1028 | loss:1.3286383152008057 lr:4.785372155200334e-05 tokens_per_second_per_gpu:4232.558466481461 mfu:19.965700435333076 Step 1029 | loss:1.3657797574996948 lr:4.784928999185704e-05 tokens_per_second_per_gpu:5331.417742081754 mfu:25.149207123064887 Step 1030 | loss:1.4939876794815063 lr:4.784485406699152e-05 tokens_per_second_per_gpu:4988.3726253055 mfu:23.531004777698996 Step 1031 | loss:1.5570229291915894 lr:4.7840413778254135e-05 tokens_per_second_per_gpu:5331.721266960883 mfu:25.150638901706422 Step 1032 | loss:1.4721746444702148 lr:4.783596912649308e-05 tokens_per_second_per_gpu:3886.7340715619466 mfu:18.33438776077168 Step 1033 | loss:1.377821445465088 lr:4.783152011255738e-05 tokens_per_second_per_gpu:4084.171729344164 mfu:19.26573487886844 Step 1034 | loss:1.414304494857788 lr:4.782706673729691e-05 tokens_per_second_per_gpu:3741.367979620887 mfu:17.648671103072914 Step 1035 | loss:1.4466317892074585 lr:4.7822609001562345e-05 tokens_per_second_per_gpu:5321.511045719948 mfu:25.102475546069552 Step 1036 | loss:1.686382532119751 lr:4.781814690620522e-05 tokens_per_second_per_gpu:3924.7798828395566 mfu:18.51385634385293 Step 1037 | loss:1.3405650854110718 lr:4.781368045207789e-05 tokens_per_second_per_gpu:4611.213064296477 mfu:21.75187877836276 Step 1038 | loss:1.3691738843917847 lr:4.780920964003354e-05 tokens_per_second_per_gpu:5205.1404120004545 mfu:24.55353541193722 Step 1039 | loss:1.3083627223968506 lr:4.780473447092621e-05 tokens_per_second_per_gpu:5316.334738343151 mfu:25.078058021004093 Step 1040 | loss:1.3726296424865723 lr:4.780025494561075e-05 tokens_per_second_per_gpu:5092.994874336715 mfu:24.0245257767756 Step 1041 | loss:1.408242106437683 lr:4.779577106494284e-05 tokens_per_second_per_gpu:5333.911345216055 mfu:25.160969874501948 Step 1042 | loss:1.3672066926956177 lr:4.7791282829779e-05 tokens_per_second_per_gpu:5300.034198601885 mfu:25.001165593885673 Step 1043 | loss:1.5146023035049438 lr:4.77867902409766e-05 tokens_per_second_per_gpu:2708.0337353119867 mfu:12.774257167665755 Step 1044 | loss:1.480478286743164 lr:4.7782293299393796e-05 tokens_per_second_per_gpu:4414.758488952165 mfu:20.825169027856756 Step 1045 | loss:1.3612533807754517 lr:4.777779200588963e-05 tokens_per_second_per_gpu:5341.302896143915 mfu:25.195837081357293 Step 1046 | loss:1.265548586845398 lr:4.777328636132394e-05 tokens_per_second_per_gpu:5305.929910432592 mfu:25.028976672503287 Step 1047 | loss:1.6198807954788208 lr:4.77687763665574e-05 tokens_per_second_per_gpu:4234.27580163904 mfu:19.973801398278965 Step 1048 | loss:1.4192798137664795 lr:4.7764262022451525e-05 tokens_per_second_per_gpu:5014.316472984413 mfu:23.65338633367729 Step 1049 | loss:1.5046825408935547 lr:4.775974332986864e-05 tokens_per_second_per_gpu:4189.555924714263 mfu:19.762850108827006 Step 1050 | loss:1.3713897466659546 lr:4.775522028967193e-05 tokens_per_second_per_gpu:5256.378617398813 mfu:24.795234768940578 Step 1051 | loss:1.531800389289856 lr:4.775069290272538e-05 tokens_per_second_per_gpu:4092.9973548216085 mfu:19.307366860052525 Step 1052 | loss:1.4398616552352905 lr:4.7746161169893844e-05 tokens_per_second_per_gpu:3747.307648779503 mfu:17.676689535906164 Step 1053 | loss:1.685723900794983 lr:4.774162509204296e-05 tokens_per_second_per_gpu:5124.815905294583 mfu:24.174631009031586 Step 1054 | loss:1.5551115274429321 lr:4.773708467003924e-05 tokens_per_second_per_gpu:5232.663170709792 mfu:24.683364960636023 Step 1055 | loss:1.3638529777526855 lr:4.7732539904749987e-05 tokens_per_second_per_gpu:5289.583994499083 mfu:24.951870198144086 Step 1056 | loss:1.2053128480911255 lr:4.7727990797043353e-05 tokens_per_second_per_gpu:3383.6824353886022 mfu:15.96140736348243 Step 1057 | loss:1.2985483407974243 lr:4.772343734778833e-05 tokens_per_second_per_gpu:5342.090205739149 mfu:25.19955095504688 Step 1058 | loss:1.5320111513137817 lr:4.7718879557854724e-05 tokens_per_second_per_gpu:4521.74433945359 mfu:21.329839538340337 Step 1059 | loss:1.4769883155822754 lr:4.771431742811317e-05 tokens_per_second_per_gpu:4466.264283190096 mfu:21.068130647071744 Step 1060 | loss:1.2797564268112183 lr:4.770975095943513e-05 tokens_per_second_per_gpu:4629.059093242676 mfu:21.836061541748492 Step 1061 | loss:1.3109172582626343 lr:4.770518015269292e-05 tokens_per_second_per_gpu:5307.728214580585 mfu:25.037459579991697 Step 1062 | loss:1.4238754510879517 lr:4.7700605008759644e-05 tokens_per_second_per_gpu:5298.959942640751 mfu:24.996098145230043 Step 1063 | loss:1.557490348815918 lr:4.769602552850926e-05 tokens_per_second_per_gpu:4809.625640183187 mfu:22.687824751496596 Step 1064 | loss:1.4078251123428345 lr:4.769144171281655e-05 tokens_per_second_per_gpu:5354.417329141275 mfu:25.257700099358843 Step 1065 | loss:1.2859504222869873 lr:4.768685356255714e-05 tokens_per_second_per_gpu:4462.351564540824 mfu:21.04967368562449 Step 1066 | loss:1.4286186695098877 lr:4.768226107860745e-05 tokens_per_second_per_gpu:4546.882993881174 mfu:21.44842286037197 Step 1067 | loss:1.5628864765167236 lr:4.7677664261844746e-05 tokens_per_second_per_gpu:4202.312252749681 mfu:19.823023884624064 Step 1068 | loss:1.4500961303710938 lr:4.767306311314713e-05 tokens_per_second_per_gpu:4203.104554204387 mfu:19.826761305766478 Step 1069 | loss:1.320973515510559 lr:4.7668457633393527e-05 tokens_per_second_per_gpu:5307.713199975501 mfu:25.03738875353776 Step 1070 | loss:1.2950023412704468 lr:4.766384782346367e-05 tokens_per_second_per_gpu:4514.207023191928 mfu:21.294284731535313 Step 1071 | loss:1.3458791971206665 lr:4.7659233684238144e-05 tokens_per_second_per_gpu:4175.64983448523 mfu:19.697252708593005 Step 1072 | loss:1.39689302444458 lr:4.765461521659835e-05 tokens_per_second_per_gpu:4410.338803283799 mfu:20.804320616482944 Step 1073 | loss:1.2967265844345093 lr:4.764999242142653e-05 tokens_per_second_per_gpu:5312.907173437497 mfu:25.061889612541247 Step 1074 | loss:1.3736575841903687 lr:4.764536529960572e-05 tokens_per_second_per_gpu:5081.374449687775 mfu:23.969710251057663 Step 1075 | loss:1.4238970279693604 lr:4.7640733852019806e-05 tokens_per_second_per_gpu:5337.525118162157 mfu:25.178016658061953 Step 1076 | loss:1.2991138696670532 lr:4.76360980795535e-05 tokens_per_second_per_gpu:5322.099860567849 mfu:25.105253086169274 Step 1077 | loss:1.5400480031967163 lr:4.763145798309234e-05 tokens_per_second_per_gpu:4378.700083012426 mfu:20.65507537484056 Step 1078 | loss:1.3016504049301147 lr:4.762681356352269e-05 tokens_per_second_per_gpu:4601.045222246479 mfu:21.70391533260018 Step 1079 | loss:1.403318166732788 lr:4.762216482173172e-05 tokens_per_second_per_gpu:4263.262034267028 mfu:20.11053440314644 Step 1080 | loss:1.4110016822814941 lr:4.761751175860747e-05 tokens_per_second_per_gpu:5153.750213571579 mfu:24.31111907787622 Step 1081 | loss:1.5255376100540161 lr:4.761285437503875e-05 tokens_per_second_per_gpu:3244.370876873913 mfu:15.304250972965775 Step 1082 | loss:1.3878957033157349 lr:4.760819267191524e-05 tokens_per_second_per_gpu:3348.721050356793 mfu:15.796488545260004 Step 1083 | loss:1.4014718532562256 lr:4.760352665012743e-05 tokens_per_second_per_gpu:5310.900198248205 mfu:25.052422368148083 Step 1084 | loss:1.4860754013061523 lr:4.759885631056661e-05 tokens_per_second_per_gpu:4040.5430015138195 mfu:19.059930725864152 Step 1085 | loss:1.3392482995986938 lr:4.759418165412495e-05 tokens_per_second_per_gpu:5318.815661929531 mfu:25.08976096085026 Step 1086 | loss:1.564755916595459 lr:4.758950268169539e-05 tokens_per_second_per_gpu:3851.611594884391 mfu:18.168709045771198 Step 1087 | loss:1.2670150995254517 lr:4.758481939417173e-05 tokens_per_second_per_gpu:4817.922286882646 mfu:22.72696144953184 Step 1088 | loss:1.398921012878418 lr:4.7580131792448565e-05 tokens_per_second_per_gpu:5288.748695044222 mfu:24.94792994809872 Step 1089 | loss:1.4150452613830566 lr:4.757543987742136e-05 tokens_per_second_per_gpu:5327.11807481762 mfu:25.128924858981083 Step 1090 | loss:1.3767859935760498 lr:4.757074364998634e-05 tokens_per_second_per_gpu:3852.7891836356125 mfu:18.174263932828072 Step 1091 | loss:1.5208736658096313 lr:4.7566043111040615e-05 tokens_per_second_per_gpu:5313.984235247744 mfu:25.066970296865875 Step 1092 | loss:1.6525509357452393 lr:4.756133826148207e-05 tokens_per_second_per_gpu:5331.712075725164 mfu:25.150595545079348 Step 1093 | loss:1.343100666999817 lr:4.755662910220945e-05 tokens_per_second_per_gpu:4598.089695914312 mfu:21.689973610626556 Step 1094 | loss:1.2959520816802979 lr:4.7551915634122314e-05 tokens_per_second_per_gpu:4132.1105935169135 mfu:19.49187068038494 Step 1095 | loss:1.6094558238983154 lr:4.754719785812102e-05 tokens_per_second_per_gpu:3531.0848550558912 mfu:16.656729726499155 Step 1096 | loss:1.486289620399475 lr:4.754247577510678e-05 tokens_per_second_per_gpu:4626.216990125578 mfu:21.82265485643235 Step 1097 | loss:1.4162757396697998 lr:4.75377493859816e-05 tokens_per_second_per_gpu:5313.546362016383 mfu:25.064904774124667 Step 1098 | loss:1.6020989418029785 lr:4.7533018691648354e-05 tokens_per_second_per_gpu:4736.874303498046 mfu:22.344644283694794 Step 1099 | loss:1.539185881614685 lr:4.752828369301068e-05 tokens_per_second_per_gpu:4004.409428488889 mfu:18.88948249688228 Step 1100 | loss:1.5815657377243042 lr:4.752354439097309e-05 tokens_per_second_per_gpu:4901.158565346175 mfu:23.11960117661783 Step 1101 | loss:1.4782122373580933 lr:4.751880078644089e-05 tokens_per_second_per_gpu:4951.713169744608 mfu:23.358075871070184 Step 1102 | loss:1.2894777059555054 lr:4.751405288032019e-05 tokens_per_second_per_gpu:5303.682905274192 mfu:25.0183771657925 Step 1103 | loss:1.5346678495407104 lr:4.750930067351797e-05 tokens_per_second_per_gpu:4533.241379328647 mfu:21.384073037028255 Step 1104 | loss:1.3261442184448242 lr:4.7504544166942014e-05 tokens_per_second_per_gpu:4275.01910280716 mfu:20.165994501412985 Step 1105 | loss:1.375908613204956 lr:4.749978336150089e-05 tokens_per_second_per_gpu:3656.531919737023 mfu:17.248484934076345 Step 1106 | loss:1.4019964933395386 lr:4.7495018258104045e-05 tokens_per_second_per_gpu:5327.934583618047 mfu:25.132776470303465 Step 1107 | loss:1.3617632389068604 lr:4.74902488576617e-05 tokens_per_second_per_gpu:4526.148108582305 mfu:21.350612868680976 Step 1108 | loss:1.6129008531570435 lr:4.748547516108493e-05 tokens_per_second_per_gpu:3971.6418607251094 mfu:18.734912289016975 Step 1109 | loss:1.2661882638931274 lr:4.74806971692856e-05 tokens_per_second_per_gpu:4236.559596100471 mfu:19.984574446409052 Step 1110 | loss:1.3016715049743652 lr:4.747591488317643e-05 tokens_per_second_per_gpu:5039.131168715788 mfu:23.770441487265852 Step 1111 | loss:1.500982642173767 lr:4.7471128303670924e-05 tokens_per_second_per_gpu:5149.45867215941 mfu:24.290875144822557 Step 1112 | loss:1.4576044082641602 lr:4.746633743168344e-05 tokens_per_second_per_gpu:4778.958719346799 mfu:22.54316365359512 Step 1113 | loss:1.392886757850647 lr:4.7461542268129134e-05 tokens_per_second_per_gpu:4160.311363759848 mfu:19.62489852516842 Step 1114 | loss:1.3448041677474976 lr:4.7456742813923985e-05 tokens_per_second_per_gpu:4171.001629153929 mfu:19.67532633097965 Step 1115 | loss:1.4865529537200928 lr:4.745193906998481e-05 tokens_per_second_per_gpu:3564.037167405441 mfu:16.812171406096216 Step 1116 | loss:1.3506773710250854 lr:4.7447131037229205e-05 tokens_per_second_per_gpu:5199.525705903013 mfu:24.527049885307942 Step 1117 | loss:1.284571647644043 lr:4.744231871657563e-05 tokens_per_second_per_gpu:5306.024880729923 mfu:25.0294246635994 Step 1118 | loss:1.2913689613342285 lr:4.743750210894334e-05 tokens_per_second_per_gpu:5323.5437511155205 mfu:25.11206416423577 Step 1119 | loss:1.4339066743850708 lr:4.743268121525241e-05 tokens_per_second_per_gpu:5324.845439192379 mfu:25.118204448985196 Step 1120 | loss:1.6418548822402954 lr:4.742785603642374e-05 tokens_per_second_per_gpu:4285.471307521162 mfu:20.215299334378948 Step 1121 | loss:1.4772868156433105 lr:4.7423026573379046e-05 tokens_per_second_per_gpu:4544.58160793529 mfu:21.437566830208304 Step 1122 | loss:1.2996776103973389 lr:4.7418192827040867e-05 tokens_per_second_per_gpu:5322.8780614590105 mfu:25.108923992547645 Step 1123 | loss:1.406185507774353 lr:4.741335479833254e-05 tokens_per_second_per_gpu:4917.00415521607 mfu:23.194347527570535 Step 1124 | loss:1.5285695791244507 lr:4.740851248817825e-05 tokens_per_second_per_gpu:4269.155491377478 mfu:20.138334845863902 Step 1125 | loss:1.2914938926696777 lr:4.740366589750298e-05 tokens_per_second_per_gpu:4502.84894034651 mfu:21.24070671686471 Step 1126 | loss:1.451568603515625 lr:4.7398815027232535e-05 tokens_per_second_per_gpu:5356.536130094744 mfu:25.267694844961074 Step 1127 | loss:1.3668912649154663 lr:4.7393959878293533e-05 tokens_per_second_per_gpu:3553.69943284382 mfu:16.763406548369655 Step 1128 | loss:1.3646667003631592 lr:4.7389100451613434e-05 tokens_per_second_per_gpu:4654.1380594263155 mfu:21.95436330414958 Step 1129 | loss:1.4108983278274536 lr:4.738423674812048e-05 tokens_per_second_per_gpu:3648.532264316714 mfu:17.210749194576792 Step 1130 | loss:1.4269061088562012 lr:4.737936876874375e-05 tokens_per_second_per_gpu:4185.6968067849175 mfu:19.74464599112087 Step 1131 | loss:1.3590818643569946 lr:4.7374496514413125e-05 tokens_per_second_per_gpu:5276.654605246546 mfu:24.89088006305859 Step 1132 | loss:1.4655635356903076 lr:4.736961998605933e-05 tokens_per_second_per_gpu:4846.539088614515 mfu:22.86195178583091 Step 1133 | loss:1.4097774028778076 lr:4.7364739184613884e-05 tokens_per_second_per_gpu:3988.9760396129077 mfu:18.81668056834661 Step 1134 | loss:1.415848970413208 lr:4.7359854111009124e-05 tokens_per_second_per_gpu:5325.184679888057 mfu:25.119804705227143 Step 1135 | loss:1.540066123008728 lr:4.735496476617821e-05 tokens_per_second_per_gpu:5314.585015119279 mfu:25.069804278023522 Step 1136 | loss:1.571265697479248 lr:4.735007115105511e-05 tokens_per_second_per_gpu:3292.695731527176 mfu:15.532207557435626 Step 1137 | loss:1.5182706117630005 lr:4.7345173266574626e-05 tokens_per_second_per_gpu:4569.285533396204 mfu:21.55409946153175 Step 1138 | loss:1.3589484691619873 lr:4.734027111367235e-05 tokens_per_second_per_gpu:5097.046620308337 mfu:24.043638553822888 Step 1139 | loss:1.4814825057983398 lr:4.73353646932847e-05 tokens_per_second_per_gpu:5183.4151923347745 mfu:24.45105384406951 Step 1140 | loss:1.347045660018921 lr:4.7330454006348916e-05 tokens_per_second_per_gpu:4207.515362920833 mfu:19.847567843043525 Step 1141 | loss:1.329628825187683 lr:4.732553905380305e-05 tokens_per_second_per_gpu:4423.392983754913 mfu:20.865899413038047 Step 1142 | loss:1.3268567323684692 lr:4.732061983658597e-05 tokens_per_second_per_gpu:5312.565946424424 mfu:25.06027998650125 Step 1143 | loss:1.338102102279663 lr:4.731569635563734e-05 tokens_per_second_per_gpu:4527.550432323167 mfu:21.35722786902772 Step 1144 | loss:1.3629721403121948 lr:4.731076861189766e-05 tokens_per_second_per_gpu:4177.52515634576 mfu:19.70609892177203 Step 1145 | loss:1.4841710329055786 lr:4.7305836606308246e-05 tokens_per_second_per_gpu:4794.390887597313 mfu:22.615959824232203 Step 1146 | loss:1.400925874710083 lr:4.7300900339811214e-05 tokens_per_second_per_gpu:4973.687110259162 mfu:23.461730697618183 Step 1147 | loss:1.4714163541793823 lr:4.72959598133495e-05 tokens_per_second_per_gpu:5299.83770309414 mfu:25.000238691050054 Step 1148 | loss:1.5604841709136963 lr:4.729101502786685e-05 tokens_per_second_per_gpu:3419.8857489534344 mfu:16.13218457048998 Step 1149 | loss:1.5601030588150024 lr:4.7286065984307835e-05 tokens_per_second_per_gpu:3948.4935711559183 mfu:18.62571785761364 Step 1150 | loss:1.3415905237197876 lr:4.7281112683617825e-05 tokens_per_second_per_gpu:4266.487115857102 mfu:20.12574766326248 Step 1151 | loss:1.5351427793502808 lr:4.7276155126743014e-05 tokens_per_second_per_gpu:3473.0416710464956 mfu:16.382930124338458 Step 1152 | loss:1.2559069395065308 lr:4.7271193314630405e-05 tokens_per_second_per_gpu:5291.164477213709 mfu:24.95932560476713 Step 1153 | loss:1.375856637954712 lr:4.7266227248227815e-05 tokens_per_second_per_gpu:5300.116790301871 mfu:25.00155519302611 Step 1154 | loss:1.5202021598815918 lr:4.7261256928483866e-05 tokens_per_second_per_gpu:4039.48080770133 mfu:19.05492017642169 Step 1155 | loss:1.3200424909591675 lr:4.7256282356348e-05 tokens_per_second_per_gpu:4599.174254551726 mfu:21.695089658764026 Step 1156 | loss:1.4253662824630737 lr:4.725130353277048e-05 tokens_per_second_per_gpu:5316.3509866880495 mfu:25.07813466721923 Step 1157 | loss:1.2662993669509888 lr:4.724632045870236e-05 tokens_per_second_per_gpu:5341.640143394971 mfu:25.19742793418084 Step 1158 | loss:1.5496591329574585 lr:4.724133313509552e-05 tokens_per_second_per_gpu:4976.580520303719 mfu:23.47537940646502 Step 1159 | loss:1.3229520320892334 lr:4.7236341562902656e-05 tokens_per_second_per_gpu:4911.086381128867 mfu:23.166432377524828 Step 1160 | loss:1.3003112077713013 lr:4.723134574307726e-05 tokens_per_second_per_gpu:4070.2395587085016 mfu:19.200014452906597 Step 1161 | loss:1.608888030052185 lr:4.722634567657365e-05 tokens_per_second_per_gpu:3767.751514882691 mfu:17.773126740398137 Step 1162 | loss:1.415597677230835 lr:4.722134136434694e-05 tokens_per_second_per_gpu:5311.833948348348 mfu:25.056827026684648 Step 1163 | loss:1.5126069784164429 lr:4.721633280735307e-05 tokens_per_second_per_gpu:4332.954228065944 mfu:20.43928437201032 Step 1164 | loss:1.4701942205429077 lr:4.7211320006548786e-05 tokens_per_second_per_gpu:3788.844168405061 mfu:17.87262438584094 Step 1165 | loss:1.6634905338287354 lr:4.7206302962891646e-05 tokens_per_second_per_gpu:4347.078029384668 mfu:20.505908752599737 Step 1166 | loss:1.5166637897491455 lr:4.720128167734001e-05 tokens_per_second_per_gpu:4062.866028075131 mfu:19.16523225085493 Step 1167 | loss:1.2896687984466553 lr:4.719625615085307e-05 tokens_per_second_per_gpu:4853.281663337437 mfu:22.893757661200805 Step 1168 | loss:1.4244810342788696 lr:4.719122638439078e-05 tokens_per_second_per_gpu:5305.147335096163 mfu:25.02528513112023 Step 1169 | loss:1.702206015586853 lr:4.718619237891397e-05 tokens_per_second_per_gpu:5339.660947285754 mfu:25.188091728447986 Step 1170 | loss:1.5590541362762451 lr:4.718115413538424e-05 tokens_per_second_per_gpu:4352.441789739432 mfu:20.531210525345042 Step 1171 | loss:1.5085768699645996 lr:4.717611165476399e-05 tokens_per_second_per_gpu:5325.59981967453 mfu:25.121762990430092 Step 1172 | loss:1.4010735750198364 lr:4.717106493801645e-05 tokens_per_second_per_gpu:4387.983507319605 mfu:20.698866871213042 Step 1173 | loss:1.3768442869186401 lr:4.7166013986105665e-05 tokens_per_second_per_gpu:4606.7427277029865 mfu:21.730791437933192 Step 1174 | loss:1.4478029012680054 lr:4.7160958799996465e-05 tokens_per_second_per_gpu:5142.911830045673 mfu:24.259992573565615 Step 1175 | loss:1.3928241729736328 lr:4.7155899380654524e-05 tokens_per_second_per_gpu:5221.864402163105 mfu:24.632425326941398 Step 1176 | loss:1.3408113718032837 lr:4.715083572904627e-05 tokens_per_second_per_gpu:4476.432305712398 mfu:21.11609494415298 Step 1177 | loss:1.4925847053527832 lr:4.7145767846139e-05 tokens_per_second_per_gpu:2854.753449528473 mfu:13.466359092589485 Step 1178 | loss:1.4141875505447388 lr:4.714069573290079e-05 tokens_per_second_per_gpu:4741.791357361545 mfu:22.367838865704815 Step 1179 | loss:1.3264340162277222 lr:4.71356193903005e-05 tokens_per_second_per_gpu:5320.478147771021 mfu:25.0976031902139 Step 1180 | loss:1.306450366973877 lr:4.7130538819307854e-05 tokens_per_second_per_gpu:4209.16049385241 mfu:19.855328206336054 Step 1181 | loss:1.5793135166168213 lr:4.712545402089334e-05 tokens_per_second_per_gpu:3434.1425737188574 mfu:16.199436445373614 Step 1182 | loss:1.3725957870483398 lr:4.712036499602826e-05 tokens_per_second_per_gpu:3846.698474288835 mfu:18.145533017657147 Step 1183 | loss:1.4781184196472168 lr:4.7115271745684744e-05 tokens_per_second_per_gpu:4067.3374619773085 mfu:19.186324767476798 Step 1184 | loss:1.4238622188568115 lr:4.7110174270835706e-05 tokens_per_second_per_gpu:3967.8166151666205 mfu:18.716867953063392 Step 1185 | loss:1.311867117881775 lr:4.710507257245488e-05 tokens_per_second_per_gpu:4999.227669261956 mfu:23.58220987210308 Step 1186 | loss:1.2904211282730103 lr:4.7099966651516804e-05 tokens_per_second_per_gpu:5316.33331415823 mfu:25.07805130288083 Step 1187 | loss:1.3401330709457397 lr:4.709485650899682e-05 tokens_per_second_per_gpu:4231.18270374597 mfu:19.959210727780434 Step 1188 | loss:1.2831584215164185 lr:4.708974214587107e-05 tokens_per_second_per_gpu:5326.857860112543 mfu:25.127697381820028 Step 1189 | loss:1.4686604738235474 lr:4.7084623563116525e-05 tokens_per_second_per_gpu:5111.515878735357 mfu:24.111892514533192 Step 1190 | loss:1.4917683601379395 lr:4.707950076171095e-05 tokens_per_second_per_gpu:5299.485234564226 mfu:24.998576036857116 Step 1191 | loss:1.391118049621582 lr:4.7074373742632895e-05 tokens_per_second_per_gpu:5346.55441346786 mfu:25.220609384575596 Step 1192 | loss:1.4551646709442139 lr:4.7069242506861746e-05 tokens_per_second_per_gpu:5320.217210515018 mfu:25.09637230465685 Step 1193 | loss:1.5608152151107788 lr:4.7064107055377674e-05 tokens_per_second_per_gpu:3941.8474615336727 mfu:18.594367024582276 Step 1194 | loss:1.402441143989563 lr:4.705896738916167e-05 tokens_per_second_per_gpu:4249.896762133898 mfu:20.047488134143897 Step 1195 | loss:1.4717631340026855 lr:4.7053823509195526e-05 tokens_per_second_per_gpu:4859.017046066 mfu:22.92081244008864 Step 1196 | loss:1.3444063663482666 lr:4.704867541646184e-05 tokens_per_second_per_gpu:4389.007421524622 mfu:20.703696849215884 Step 1197 | loss:1.259442925453186 lr:4.7043523111944e-05 tokens_per_second_per_gpu:3881.5280028046614 mfu:18.30982984619664 Step 1198 | loss:1.5978405475616455 lr:4.703836659662622e-05 tokens_per_second_per_gpu:4933.343100065567 mfu:23.271421118137066 Step 1199 | loss:1.392932653427124 lr:4.703320587149349e-05 tokens_per_second_per_gpu:5328.106961224242 mfu:25.133589604882538 Step 1200 | loss:1.3888394832611084 lr:4.702804093753165e-05 tokens_per_second_per_gpu:5309.956954783289 mfu:25.04797292779014 Step 1201 | loss:1.396758794784546 lr:4.7022871795727295e-05 tokens_per_second_per_gpu:5307.344196635201 mfu:25.035648101823103 Step 1202 | loss:1.3197680711746216 lr:4.701769844706786e-05 tokens_per_second_per_gpu:5325.856086987153 mfu:25.122971847067443 Step 1203 | loss:1.2052760124206543 lr:4.701252089254155e-05 tokens_per_second_per_gpu:5349.041890495847 mfu:25.232343238123953 Step 1204 | loss:1.6073943376541138 lr:4.700733913313742e-05 tokens_per_second_per_gpu:3822.675175824615 mfu:18.032211020004052 Step 1205 | loss:1.5977990627288818 lr:4.700215316984527e-05 tokens_per_second_per_gpu:4585.00440531223 mfu:21.62824806227574 Step 1206 | loss:1.5052558183670044 lr:4.6996963003655757e-05 tokens_per_second_per_gpu:4794.530613893732 mfu:22.616618937012177 Step 1207 | loss:1.3320670127868652 lr:4.699176863556031e-05 tokens_per_second_per_gpu:5285.522410665848 mfu:24.932711014225056 Step 1208 | loss:1.4314160346984863 lr:4.698657006655116e-05 tokens_per_second_per_gpu:4502.447661801774 mfu:21.238813817504017 Step 1209 | loss:1.557737112045288 lr:4.698136729762136e-05 tokens_per_second_per_gpu:4486.054388180988 mfu:21.161483948853874 Step 1210 | loss:1.3411320447921753 lr:4.697616032976474e-05 tokens_per_second_per_gpu:4214.527618467405 mfu:19.88064584887087 Step 1211 | loss:1.431586742401123 lr:4.6970949163975965e-05 tokens_per_second_per_gpu:5312.069304248186 mfu:25.057937240620046 Step 1212 | loss:1.6070252656936646 lr:4.696573380125047e-05 tokens_per_second_per_gpu:3898.797563432822 mfu:18.39129331017055 Step 1213 | loss:1.564874529838562 lr:4.696051424258451e-05 tokens_per_second_per_gpu:3270.2786025011596 mfu:15.426462135063298 Step 1214 | loss:1.5524338483810425 lr:4.6955290488975126e-05 tokens_per_second_per_gpu:3776.513856404634 mfu:17.814460200366767 Step 1215 | loss:1.4610967636108398 lr:4.6950062541420186e-05 tokens_per_second_per_gpu:5314.037636540566 mfu:25.06722219987532 Step 1216 | loss:1.5364570617675781 lr:4.694483040091833e-05 tokens_per_second_per_gpu:4529.391974757955 mfu:21.365914738892155 Step 1217 | loss:1.4619389772415161 lr:4.6939594068469025e-05 tokens_per_second_per_gpu:4078.4094919606205 mfu:19.238553421991192 Step 1218 | loss:1.5446678400039673 lr:4.6934353545072505e-05 tokens_per_second_per_gpu:4241.502474705812 mfu:20.007890848132497 Step 1219 | loss:1.4765089750289917 lr:4.692910883172985e-05 tokens_per_second_per_gpu:4431.531012974114 mfu:20.904287885355977 Step 1220 | loss:1.3841209411621094 lr:4.6923859929442905e-05 tokens_per_second_per_gpu:4625.989597467888 mfu:21.821582206468836 Step 1221 | loss:1.462791085243225 lr:4.691860683921433e-05 tokens_per_second_per_gpu:4758.257920778841 mfu:22.445514454829627 Step 1222 | loss:1.2158678770065308 lr:4.691334956204757e-05 tokens_per_second_per_gpu:3866.612348695896 mfu:18.239470160892584 Step 1223 | loss:1.431551456451416 lr:4.690808809894689e-05 tokens_per_second_per_gpu:5311.086335794865 mfu:25.053300410714016 Step 1224 | loss:1.2931241989135742 lr:4.690282245091735e-05 tokens_per_second_per_gpu:4025.9103932904122 mfu:18.99090621629394 Step 1225 | loss:1.3785908222198486 lr:4.6897552618964805e-05 tokens_per_second_per_gpu:4476.783283659671 mfu:21.117750567013275 Step 1226 | loss:1.359000563621521 lr:4.689227860409589e-05 tokens_per_second_per_gpu:3921.4355223851803 mfu:18.498080424982906 Step 1227 | loss:1.3258962631225586 lr:4.688700040731808e-05 tokens_per_second_per_gpu:5333.679308687767 mfu:25.1598753186085 Step 1228 | loss:1.3410688638687134 lr:4.6881718029639626e-05 tokens_per_second_per_gpu:4976.752102343048 mfu:23.47618878821945 Step 1229 | loss:1.2720998525619507 lr:4.687643147206957e-05 tokens_per_second_per_gpu:5323.865013103948 mfu:25.11357961184813 Step 1230 | loss:1.3993695974349976 lr:4.687114073561776e-05 tokens_per_second_per_gpu:4884.459795152541 mfu:23.040830228510476 Step 1231 | loss:1.6208062171936035 lr:4.686584582129485e-05 tokens_per_second_per_gpu:4623.371678052387 mfu:21.809233033922812 Step 1232 | loss:1.4252263307571411 lr:4.686054673011229e-05 tokens_per_second_per_gpu:4901.052882854325 mfu:23.11910265427248 Step 1233 | loss:1.6151292324066162 lr:4.685524346308231e-05 tokens_per_second_per_gpu:3179.306551870459 mfu:14.997331450805925 Step 1234 | loss:1.4472671747207642 lr:4.684993602121796e-05 tokens_per_second_per_gpu:4344.583844647232 mfu:20.494143257641447 Step 1235 | loss:1.3247812986373901 lr:4.6844624405533064e-05 tokens_per_second_per_gpu:5316.684633966163 mfu:25.07970853835619 Step 1236 | loss:1.5095747709274292 lr:4.6839308617042285e-05 tokens_per_second_per_gpu:5108.445110992019 mfu:24.097407179160864 Step 1237 | loss:1.3319785594940186 lr:4.683398865676104e-05 tokens_per_second_per_gpu:5300.647990981107 mfu:25.004060957262244 Step 1238 | loss:1.1814254522323608 lr:4.682866452570556e-05 tokens_per_second_per_gpu:3882.5991390555064 mfu:18.314882578646568 Step 1239 | loss:1.5348418951034546 lr:4.6823336224892866e-05 tokens_per_second_per_gpu:4561.243916697658 mfu:21.516165783523416 Step 1240 | loss:1.478184700012207 lr:4.6818003755340804e-05 tokens_per_second_per_gpu:5355.7108711703595 mfu:25.26380195781106 Step 1241 | loss:1.2921618223190308 lr:4.681266711806796e-05 tokens_per_second_per_gpu:5302.4547856354075 mfu:25.01258391591754 Step 1242 | loss:1.3583627939224243 lr:4.680732631409377e-05 tokens_per_second_per_gpu:5137.786603194006 mfu:24.235816004052424 Step 1243 | loss:1.2920551300048828 lr:4.680198134443845e-05 tokens_per_second_per_gpu:4580.311243842921 mfu:21.606109618889096 Step 1244 | loss:1.3479995727539062 lr:4.6796632210122995e-05 tokens_per_second_per_gpu:4618.19560380941 mfu:21.784816608589356 Step 1245 | loss:1.396661639213562 lr:4.679127891216921e-05 tokens_per_second_per_gpu:3279.901754485785 mfu:15.47185618485381 Step 1246 | loss:1.5356403589248657 lr:4.67859214515997e-05 tokens_per_second_per_gpu:3064.3765563799675 mfu:14.455187052998022 Step 1247 | loss:1.3798093795776367 lr:4.6780559829437856e-05 tokens_per_second_per_gpu:4956.865744669862 mfu:23.38238144611254 Step 1248 | loss:1.3259357213974 lr:4.677519404670785e-05 tokens_per_second_per_gpu:4456.359516994079 mfu:21.02140817499776 Step 1249 | loss:1.298880696296692 lr:4.676982410443469e-05 tokens_per_second_per_gpu:3800.047945788809 mfu:17.925474515321618 Step 1250 | loss:1.3294677734375 lr:4.6764450003644145e-05 tokens_per_second_per_gpu:5110.58757842645 mfu:24.107513563591713 Step 1251 | loss:1.448383092880249 lr:4.675907174536278e-05 tokens_per_second_per_gpu:3768.8018742328522 mfu:17.778081464662634 Step 1252 | loss:1.3518414497375488 lr:4.675368933061797e-05 tokens_per_second_per_gpu:3911.4100122387586 mfu:18.450788383093816 Step 1253 | loss:1.4811222553253174 lr:4.674830276043787e-05 tokens_per_second_per_gpu:5319.336283440548 mfu:25.092216821344913 Step 1254 | loss:1.28413724899292 lr:4.6742912035851424e-05 tokens_per_second_per_gpu:4156.35219323128 mfu:19.606222442281016 Step 1255 | loss:1.2676247358322144 lr:4.673751715788841e-05 tokens_per_second_per_gpu:3866.7878976558604 mfu:18.240298255288476 Step 1256 | loss:1.3286511898040771 lr:4.673211812757934e-05 tokens_per_second_per_gpu:4640.097413928086 mfu:21.888131183753288 Step 1257 | loss:1.3383301496505737 lr:4.672671494595555e-05 tokens_per_second_per_gpu:5351.990877694952 mfu:25.246254113891233 Step 1258 | loss:1.3755238056182861 lr:4.6721307614049185e-05 tokens_per_second_per_gpu:3445.103637046464 mfu:16.25114165124018 Step 1259 | loss:1.3156534433364868 lr:4.6715896132893154e-05 tokens_per_second_per_gpu:5287.604953885695 mfu:24.94253472591159 Step 1260 | loss:1.4622900485992432 lr:4.671048050352117e-05 tokens_per_second_per_gpu:5326.152795074876 mfu:25.124371469740854 Step 1261 | loss:1.3144736289978027 lr:4.670506072696773e-05 tokens_per_second_per_gpu:5321.676053494132 mfu:25.10325391589361 Step 1262 | loss:1.498639702796936 lr:4.6699636804268145e-05 tokens_per_second_per_gpu:4707.576590077243 mfu:22.206441970783505 Step 1263 | loss:1.4508157968521118 lr:4.6694208736458494e-05 tokens_per_second_per_gpu:5081.225080004673 mfu:23.969005648777372 Step 1264 | loss:1.474985957145691 lr:4.668877652457567e-05 tokens_per_second_per_gpu:4999.7201345569265 mfu:23.584532914922697 Step 1265 | loss:1.391178011894226 lr:4.668334016965733e-05 tokens_per_second_per_gpu:5167.15487693412 mfu:24.374351162028738 Step 1266 | loss:1.6421384811401367 lr:4.6677899672741945e-05 tokens_per_second_per_gpu:3539.9621416232117 mfu:16.698605401858476 Step 1267 | loss:1.3597302436828613 lr:4.667245503486877e-05 tokens_per_second_per_gpu:4637.500929611726 mfu:21.87588312422711 Step 1268 | loss:1.391500473022461 lr:4.666700625707786e-05 tokens_per_second_per_gpu:5313.737936719442 mfu:25.065808464685013 Step 1269 | loss:1.4267140626907349 lr:4.666155334041004e-05 tokens_per_second_per_gpu:5340.474470862175 mfu:25.191929257959398 Step 1270 | loss:1.4474396705627441 lr:4.6656096285906936e-05 tokens_per_second_per_gpu:4221.838780475416 mfu:19.915133847475527 Step 1271 | loss:1.3805609941482544 lr:4.665063509461097e-05 tokens_per_second_per_gpu:4824.257265572796 mfu:22.756844624872098 Step 1272 | loss:1.4779495000839233 lr:4.664516976756535e-05 tokens_per_second_per_gpu:3417.3786033735205 mfu:16.12035793702638 Step 1273 | loss:1.4409441947937012 lr:4.663970030581408e-05 tokens_per_second_per_gpu:4571.31456246215 mfu:21.563670737823873 Step 1274 | loss:1.2841912508010864 lr:4.6634226710401945e-05 tokens_per_second_per_gpu:3950.8193502384925 mfu:18.636688954364974 Step 1275 | loss:1.3830653429031372 lr:4.6628748982374515e-05 tokens_per_second_per_gpu:4583.274034049741 mfu:21.620085605798803 Step 1276 | loss:1.4332945346832275 lr:4.662326712277817e-05 tokens_per_second_per_gpu:5360.982839073252 mfu:25.288670729899483 Step 1277 | loss:1.2121882438659668 lr:4.661778113266005e-05 tokens_per_second_per_gpu:4226.473868263365 mfu:19.93699834739881 Step 1278 | loss:1.4000505208969116 lr:4.661229101306812e-05 tokens_per_second_per_gpu:4634.298874719043 mfu:21.860778484971423 Step 1279 | loss:1.2912702560424805 lr:4.66067967650511e-05 tokens_per_second_per_gpu:5313.167406944659 mfu:25.063117178394943 Step 1280 | loss:1.3319494724273682 lr:4.660129838965852e-05 tokens_per_second_per_gpu:5233.508441416806 mfu:24.68735224677906 Step 1281 | loss:1.4158776998519897 lr:4.659579588794068e-05 tokens_per_second_per_gpu:3852.882393071219 mfu:18.174703617638997 Step 1282 | loss:1.4471615552902222 lr:4.6590289260948696e-05 tokens_per_second_per_gpu:4337.500672685617 mfu:20.46073072698476 Step 1283 | loss:1.3813560009002686 lr:4.658477850973444e-05 tokens_per_second_per_gpu:5231.823241977879 mfu:24.679402873500965 Step 1284 | loss:1.1836016178131104 lr:4.657926363535059e-05 tokens_per_second_per_gpu:5331.011450401796 mfu:25.14729057589001 Step 1285 | loss:1.516081690788269 lr:4.6573744638850624e-05 tokens_per_second_per_gpu:4336.915123303052 mfu:20.45796859064217 Step 1286 | loss:1.2235286235809326 lr:4.656822152128877e-05 tokens_per_second_per_gpu:5019.392895886608 mfu:23.677332686634003 Step 1287 | loss:1.447575569152832 lr:4.656269428372009e-05 tokens_per_second_per_gpu:5314.165304459804 mfu:25.067824431232758 Step 1288 | loss:1.2760292291641235 lr:4.655716292720038e-05 tokens_per_second_per_gpu:4899.344092254179 mfu:23.111041997461854 Step 1289 | loss:1.3563182353973389 lr:4.655162745278627e-05 tokens_per_second_per_gpu:4918.7215791645085 mfu:23.20244890935806 Step 1290 | loss:1.3906996250152588 lr:4.654608786153516e-05 tokens_per_second_per_gpu:5317.899479227529 mfu:25.08543917072803 Step 1291 | loss:1.606476902961731 lr:4.6540544154505226e-05 tokens_per_second_per_gpu:5339.295169725742 mfu:25.186366293289325 Step 1292 | loss:1.5678430795669556 lr:4.653499633275544e-05 tokens_per_second_per_gpu:5188.818426128259 mfu:24.476541819760122 Step 1293 | loss:1.5145277976989746 lr:4.6529444397345564e-05 tokens_per_second_per_gpu:4321.0912080403605 mfu:20.383324482509714 Step 1294 | loss:1.4319946765899658 lr:4.652388834933613e-05 tokens_per_second_per_gpu:5293.828720522369 mfu:24.971893295020863 Step 1295 | loss:1.4756630659103394 lr:4.6518328189788474e-05 tokens_per_second_per_gpu:5318.545497411744 mfu:25.088486548725037 Step 1296 | loss:1.3427605628967285 lr:4.6512763919764704e-05 tokens_per_second_per_gpu:5325.357434143122 mfu:25.120619616523204 Step 1297 | loss:1.540617823600769 lr:4.650719554032773e-05 tokens_per_second_per_gpu:4252.455739708452 mfu:20.05955926796966 Step 1298 | loss:1.4337347745895386 lr:4.650162305254122e-05 tokens_per_second_per_gpu:3754.3068688207563 mfu:17.709706051030835 Step 1299 | loss:1.2762335538864136 lr:4.649604645746965e-05 tokens_per_second_per_gpu:4519.649042908479 mfu:21.31995566704259 Step 1300 | loss:1.5631225109100342 lr:4.649046575617827e-05 tokens_per_second_per_gpu:3663.3046197290046 mfu:17.280432915480294 Step 1301 | loss:1.4739255905151367 lr:4.648488094973312e-05 tokens_per_second_per_gpu:4091.428357177469 mfu:19.29996563046652 Step 1302 | loss:1.3705717325210571 lr:4.647929203920103e-05 tokens_per_second_per_gpu:4798.606799049514 mfu:22.635846997860902 Step 1303 | loss:1.4261295795440674 lr:4.6473699025649587e-05 tokens_per_second_per_gpu:3980.1788086759357 mfu:18.77518252905454 Step 1304 | loss:1.2777032852172852 lr:4.6468101910147194e-05 tokens_per_second_per_gpu:4372.697054737418 mfu:20.62675806624511 Step 1305 | loss:1.5380288362503052 lr:4.6462500693763024e-05 tokens_per_second_per_gpu:3607.7444586129554 mfu:17.018346155954905 Step 1306 | loss:1.4878509044647217 lr:4.6456895377567015e-05 tokens_per_second_per_gpu:4763.181520007453 mfu:22.468739912443645 Step 1307 | loss:1.3897753953933716 lr:4.645128596262993e-05 tokens_per_second_per_gpu:5324.514215587719 mfu:25.116642010729443 Step 1308 | loss:1.401488184928894 lr:4.6445672450023284e-05 tokens_per_second_per_gpu:5322.697042029418 mfu:25.10807009301316 Step 1309 | loss:1.552249550819397 lr:4.644005484081936e-05 tokens_per_second_per_gpu:4616.989172948661 mfu:21.77912566838087 Step 1310 | loss:1.2708148956298828 lr:4.643443313609128e-05 tokens_per_second_per_gpu:4107.979844994168 mfu:19.37804182247291 Step 1311 | loss:1.3797417879104614 lr:4.6428807336912895e-05 tokens_per_second_per_gpu:5298.687412149026 mfu:24.99481257240208 Step 1312 | loss:1.2213069200515747 lr:4.6423177444358854e-05 tokens_per_second_per_gpu:5314.299599007228 mfu:25.068457921525965 Step 1313 | loss:1.3898276090621948 lr:4.641754345950461e-05 tokens_per_second_per_gpu:4163.475295092073 mfu:19.639823329084873 Step 1314 | loss:1.4048714637756348 lr:4.641190538342635e-05 tokens_per_second_per_gpu:4045.1717869900785 mfu:19.081765496707906 Step 1315 | loss:1.2482657432556152 lr:4.6406263217201096e-05 tokens_per_second_per_gpu:4403.663397851275 mfu:20.772831590116112 Step 1316 | loss:1.229372262954712 lr:4.6400616961906615e-05 tokens_per_second_per_gpu:5306.051715768056 mfu:25.029551249052805 Step 1317 | loss:1.3090993165969849 lr:4.6394966618621466e-05 tokens_per_second_per_gpu:4031.548268651079 mfu:19.017501036290934 Step 1318 | loss:1.4071956872940063 lr:4.638931218842499e-05 tokens_per_second_per_gpu:4226.3666873196635 mfu:19.936492756600412 Step 1319 | loss:1.2752397060394287 lr:4.638365367239732e-05 tokens_per_second_per_gpu:4700.546527965937 mfu:22.173279968352194 Step 1320 | loss:1.4779917001724243 lr:4.6377991071619344e-05 tokens_per_second_per_gpu:3790.9106657683487 mfu:17.882372406484375 Step 1321 | loss:1.4498603343963623 lr:4.637232438717274e-05 tokens_per_second_per_gpu:3338.8091078024318 mfu:15.749732221079297 Step 1322 | loss:1.490379810333252 lr:4.6366653620139976e-05 tokens_per_second_per_gpu:4489.356249955936 mfu:21.17705939420201 Step 1323 | loss:1.3467084169387817 lr:4.63609787716043e-05 tokens_per_second_per_gpu:4571.951070165797 mfu:21.56667325326139 Step 1324 | loss:1.5053346157073975 lr:4.635529984264974e-05 tokens_per_second_per_gpu:4357.902848742257 mfu:20.55697127241411 Step 1325 | loss:1.4671622514724731 lr:4.634961683436107e-05 tokens_per_second_per_gpu:3685.815116714425 mfu:17.38661877044735 Step 1326 | loss:1.3560020923614502 lr:4.634392974782389e-05 tokens_per_second_per_gpu:4763.937027548579 mfu:22.47230377041801 Step 1327 | loss:1.4963374137878418 lr:4.6338238584124546e-05 tokens_per_second_per_gpu:4765.580376653851 mfu:22.480055728531852 Step 1328 | loss:1.3064522743225098 lr:4.63325433443502e-05 tokens_per_second_per_gpu:5307.263691537817 mfu:25.035268345543155 Step 1329 | loss:1.3083683252334595 lr:4.632684402958874e-05 tokens_per_second_per_gpu:4737.159502533067 mfu:22.34598961620296 Step 1330 | loss:1.3416892290115356 lr:4.632114064092888e-05 tokens_per_second_per_gpu:4093.965884120172 mfu:19.31193557800199 Step 1331 | loss:1.3718467950820923 lr:4.6315433179460095e-05 tokens_per_second_per_gpu:4620.474758440462 mfu:21.795567769847906 Step 1332 | loss:1.5328558683395386 lr:4.630972164627262e-05 tokens_per_second_per_gpu:5071.819829500868 mfu:23.924639477449716 Step 1333 | loss:1.342654824256897 lr:4.630400604245749e-05 tokens_per_second_per_gpu:4131.628549486115 mfu:19.48959679644647 Step 1334 | loss:1.5035876035690308 lr:4.6298286369106525e-05 tokens_per_second_per_gpu:5353.586916491962 mfu:25.253782901209025 Step 1335 | loss:1.3301903009414673 lr:4.629256262731229e-05 tokens_per_second_per_gpu:3993.7583872980535 mfu:18.839239718330095 Step 1336 | loss:1.191776156425476 lr:4.628683481816816e-05 tokens_per_second_per_gpu:4648.562839974844 mfu:21.92806404276646 Step 1337 | loss:1.532203197479248 lr:4.628110294276826e-05 tokens_per_second_per_gpu:3770.6973854153534 mfu:17.787022914318047 Step 1338 | loss:1.3637093305587769 lr:4.627536700220753e-05 tokens_per_second_per_gpu:3940.9494248162628 mfu:18.590130832165393 Step 1339 | loss:1.6973539590835571 lr:4.626962699758163e-05 tokens_per_second_per_gpu:5324.503270053653 mfu:25.116590378777754 Step 1340 | loss:1.532393455505371 lr:4.626388292998704e-05 tokens_per_second_per_gpu:4432.349041929969 mfu:20.908146667510877 Step 1341 | loss:1.556565761566162 lr:4.625813480052101e-05 tokens_per_second_per_gpu:5338.4442271749485 mfu:25.182352252091462 Step 1342 | loss:1.2442728281021118 lr:4.6252382610281555e-05 tokens_per_second_per_gpu:5087.241099678117 mfu:23.997384240015805 Step 1343 | loss:1.3513615131378174 lr:4.624662636036746e-05 tokens_per_second_per_gpu:4693.639465707105 mfu:22.140698177210943 Step 1344 | loss:1.3038833141326904 lr:4.6240866051878315e-05 tokens_per_second_per_gpu:4461.338279181138 mfu:21.04489384569854 Step 1345 | loss:1.2721796035766602 lr:4.623510168591446e-05 tokens_per_second_per_gpu:5346.34103936181 mfu:25.219602862511977 Step 1346 | loss:1.437943458557129 lr:4.622933326357702e-05 tokens_per_second_per_gpu:4624.775486545316 mfu:21.81585503809838 Step 1347 | loss:1.3912397623062134 lr:4.622356078596788e-05 tokens_per_second_per_gpu:4265.147571303404 mfu:20.119428803052816 Step 1348 | loss:1.4190168380737305 lr:4.621778425418971e-05 tokens_per_second_per_gpu:3672.62337303831 mfu:17.324391064783555 Step 1349 | loss:1.3867783546447754 lr:4.6212003669345966e-05 tokens_per_second_per_gpu:5348.2470414988 mfu:25.228593799789657 Step 1350 | loss:1.4828448295593262 lr:4.620621903254086e-05 tokens_per_second_per_gpu:5313.573472198052 mfu:25.065032657477076 Step 1351 | loss:1.3029388189315796 lr:4.6200430344879386e-05 tokens_per_second_per_gpu:4748.980937214888 mfu:22.401753340541852 Step 1352 | loss:1.3520195484161377 lr:4.619463760746732e-05 tokens_per_second_per_gpu:5345.484685606006 mfu:25.215563295736832 Step 1353 | loss:1.2187122106552124 lr:4.6188840821411193e-05 tokens_per_second_per_gpu:5342.050897038377 mfu:25.199365529198584 Step 1354 | loss:1.4237618446350098 lr:4.618303998781832e-05 tokens_per_second_per_gpu:3562.8801552901664 mfu:16.806713582541843 Step 1355 | loss:1.4213353395462036 lr:4.617723510779679e-05 tokens_per_second_per_gpu:4575.263482431253 mfu:21.58229846707335 Step 1356 | loss:1.2439206838607788 lr:4.617142618245547e-05 tokens_per_second_per_gpu:5219.378180452271 mfu:24.62069739493823 Step 1357 | loss:1.3123852014541626 lr:4.616561321290398e-05 tokens_per_second_per_gpu:4894.952501114353 mfu:23.090326112772583 Step 1358 | loss:1.4851694107055664 lr:4.615979620025274e-05 tokens_per_second_per_gpu:4626.559215850507 mfu:21.82426919356657 Step 1359 | loss:1.448898434638977 lr:4.615397514561291e-05 tokens_per_second_per_gpu:3364.068428150916 mfu:15.868884744847549 Step 1360 | loss:1.3499478101730347 lr:4.614815005009646e-05 tokens_per_second_per_gpu:4248.73913971615 mfu:20.04202743168863 Step 1361 | loss:1.3189027309417725 lr:4.6142320914816097e-05 tokens_per_second_per_gpu:5347.987372817909 mfu:25.22736889831785 Step 1362 | loss:1.4395102262496948 lr:4.6136487740885325e-05 tokens_per_second_per_gpu:5159.752724813435 mfu:24.339433947538083 Step 1363 | loss:1.5024324655532837 lr:4.613065052941839e-05 tokens_per_second_per_gpu:4708.230618625927 mfu:22.209527135036424 Step 1364 | loss:1.4048594236373901 lr:4.612480928153036e-05 tokens_per_second_per_gpu:3955.7599379814033 mfu:18.659994549699473 Step 1365 | loss:1.4256266355514526 lr:4.6118963998337015e-05 tokens_per_second_per_gpu:5344.21635853719 mfu:25.209580380554318 Step 1366 | loss:1.3459326028823853 lr:4.611311468095495e-05 tokens_per_second_per_gpu:5248.424266270396 mfu:24.757712737515586 Step 1367 | loss:1.3752267360687256 lr:4.610726133050151e-05 tokens_per_second_per_gpu:4309.893289290434 mfu:20.330501989204365 Step 1368 | loss:1.5009348392486572 lr:4.61014039480948e-05 tokens_per_second_per_gpu:5226.107301764817 mfu:24.652439808275993 Step 1369 | loss:1.3741885423660278 lr:4.609554253485373e-05 tokens_per_second_per_gpu:4565.8430384137855 mfu:21.537860625349474 Step 1370 | loss:1.610467791557312 lr:4.608967709189794e-05 tokens_per_second_per_gpu:5329.844010681249 mfu:25.141783563542436 Step 1371 | loss:1.448939561843872 lr:4.608380762034788e-05 tokens_per_second_per_gpu:5294.199823532391 mfu:24.97364385123584 Step 1372 | loss:1.4053800106048584 lr:4.607793412132474e-05 tokens_per_second_per_gpu:5304.947158543483 mfu:25.0243408641676 Step 1373 | loss:1.5126042366027832 lr:4.6072056595950476e-05 tokens_per_second_per_gpu:5342.892695561544 mfu:25.203336436458002 Step 1374 | loss:1.4878019094467163 lr:4.6066175045347834e-05 tokens_per_second_per_gpu:3629.988048803599 mfu:17.123272966032 Step 1375 | loss:1.4862549304962158 lr:4.606028947064034e-05 tokens_per_second_per_gpu:3989.824168509398 mfu:18.820681337057064 Step 1376 | loss:1.4544472694396973 lr:4.605439987295224e-05 tokens_per_second_per_gpu:5340.423383710361 mfu:25.191688271147928 Step 1377 | loss:1.2406617403030396 lr:4.6048506253408576e-05 tokens_per_second_per_gpu:4707.920417078844 mfu:22.208063861412995 Step 1378 | loss:1.41832435131073 lr:4.604260861313519e-05 tokens_per_second_per_gpu:4926.082253903615 mfu:23.23717046796304 Step 1379 | loss:1.2450312376022339 lr:4.6036706953258626e-05 tokens_per_second_per_gpu:5330.732363155475 mfu:25.145974073731924 Step 1380 | loss:1.3176878690719604 lr:4.603080127490625e-05 tokens_per_second_per_gpu:5276.497774264475 mfu:24.890140264558035 Step 1381 | loss:1.2744823694229126 lr:4.602489157920619e-05 tokens_per_second_per_gpu:5220.013847531682 mfu:24.623695945007793 Step 1382 | loss:1.384748935699463 lr:4.6018977867287306e-05 tokens_per_second_per_gpu:5311.5278087914285 mfu:25.055382914161864 Step 1383 | loss:1.4489103555679321 lr:4.601306014027925e-05 tokens_per_second_per_gpu:4885.731438084787 mfu:23.046828785186538 Step 1384 | loss:1.4934734106063843 lr:4.600713839931245e-05 tokens_per_second_per_gpu:4917.834747108211 mfu:23.198265571239354 Step 1385 | loss:1.3707889318466187 lr:4.600121264551808e-05 tokens_per_second_per_gpu:4062.6791063543255 mfu:19.16435050920576 Step 1386 | loss:1.3224565982818604 lr:4.599528288002809e-05 tokens_per_second_per_gpu:4328.333976131234 mfu:20.417489855338026 Step 1387 | loss:1.3955515623092651 lr:4.598934910397521e-05 tokens_per_second_per_gpu:4470.47619889425 mfu:21.08799897207516 Step 1388 | loss:1.4151445627212524 lr:4.598341131849291e-05 tokens_per_second_per_gpu:3742.101895710463 mfu:17.65213311048644 Step 1389 | loss:1.3983279466629028 lr:4.597746952471543e-05 tokens_per_second_per_gpu:5024.892129187604 mfu:23.703273508380754 Step 1390 | loss:1.4062381982803345 lr:4.59715237237778e-05 tokens_per_second_per_gpu:4232.423751120291 mfu:19.965064959989622 Step 1391 | loss:1.3470463752746582 lr:4.5965573916815796e-05 tokens_per_second_per_gpu:4234.43788378824 mfu:19.974565967430806 Step 1392 | loss:1.2862173318862915 lr:4.595962010496596e-05 tokens_per_second_per_gpu:5261.527653390215 mfu:24.819523650228152 Step 1393 | loss:1.2292752265930176 lr:4.5953662289365594e-05 tokens_per_second_per_gpu:5301.31052169709 mfu:25.007186227688933 Step 1394 | loss:1.5143537521362305 lr:4.594770047115279e-05 tokens_per_second_per_gpu:3254.1707618766545 mfu:15.350478702556504 Step 1395 | loss:1.406568169593811 lr:4.594173465146636e-05 tokens_per_second_per_gpu:4846.044994657463 mfu:22.859621060334373 Step 1396 | loss:1.5553359985351562 lr:4.593576483144594e-05 tokens_per_second_per_gpu:4058.1588032681857 mfu:19.143027468305206 Step 1397 | loss:1.4676533937454224 lr:4.592979101223188e-05 tokens_per_second_per_gpu:4570.019780475237 mfu:21.557563030279017 Step 1398 | loss:1.3911670446395874 lr:4.5923813194965305e-05 tokens_per_second_per_gpu:4039.4485351855146 mfu:19.05476794145833 Step 1399 | loss:1.403779149055481 lr:4.591783138078812e-05 tokens_per_second_per_gpu:5175.274968648046 mfu:24.41265502007383 Step 1400 | loss:1.2225388288497925 lr:4.5911845570842994e-05 tokens_per_second_per_gpu:4328.511368674648 mfu:20.4183266462316 Step 1401 | loss:1.4763168096542358 lr:4.590585576627332e-05 tokens_per_second_per_gpu:3871.511581090254 mfu:18.262580675992012 Step 1402 | loss:1.4905716180801392 lr:4.5899861968223315e-05 tokens_per_second_per_gpu:3961.5329970728753 mfu:18.6872270544194 Step 1403 | loss:1.2494240999221802 lr:4.589386417783791e-05 tokens_per_second_per_gpu:4994.606510242232 mfu:23.560411076556008 Step 1404 | loss:1.3101484775543213 lr:4.58878623962628e-05 tokens_per_second_per_gpu:5326.9184821249955 mfu:25.127983346195947 Step 1405 | loss:1.380626916885376 lr:4.588185662464449e-05 tokens_per_second_per_gpu:5336.190529941463 mfu:25.171721177720713 Step 1406 | loss:1.4087858200073242 lr:4.5875846864130204e-05 tokens_per_second_per_gpu:5326.365650909726 mfu:25.125375547030792 Step 1407 | loss:1.407781958580017 lr:4.586983311586793e-05 tokens_per_second_per_gpu:4001.9415823917043 mfu:18.877841245783898 Step 1408 | loss:1.3493828773498535 lr:4.586381538100643e-05 tokens_per_second_per_gpu:4598.62943630263 mfu:21.69251965812746 Step 1409 | loss:1.352165937423706 lr:4.585779366069523e-05 tokens_per_second_per_gpu:5292.979480108209 mfu:24.967887283091915 Step 1410 | loss:1.3768939971923828 lr:4.58517679560846e-05 tokens_per_second_per_gpu:4807.061520409826 mfu:22.675729361041707 Step 1411 | loss:1.3772984743118286 lr:4.58457382683256e-05 tokens_per_second_per_gpu:5312.084317844414 mfu:25.058008062315032 Step 1412 | loss:1.6630406379699707 lr:4.583970459857002e-05 tokens_per_second_per_gpu:3778.231426615714 mfu:17.82256227210013 Step 1413 | loss:1.3632904291152954 lr:4.583366694797043e-05 tokens_per_second_per_gpu:3757.6204330184873 mfu:17.72533669870388 Step 1414 | loss:1.3745636940002441 lr:4.582762531768016e-05 tokens_per_second_per_gpu:3672.4876929093 mfu:17.3237510384656 Step 1415 | loss:1.2844281196594238 lr:4.582157970885328e-05 tokens_per_second_per_gpu:5340.688959372527 mfu:25.192941036858244 Step 1416 | loss:1.5562763214111328 lr:4.581553012264464e-05 tokens_per_second_per_gpu:4253.567268575396 mfu:20.06480253928142 Step 1417 | loss:1.4740428924560547 lr:4.5809476560209855e-05 tokens_per_second_per_gpu:4937.663170223899 mfu:23.291799626153892 Step 1418 | loss:1.304020881652832 lr:4.5803419022705275e-05 tokens_per_second_per_gpu:5295.224824944855 mfu:24.978478957781707 Step 1419 | loss:1.3076764345169067 lr:4.579735751128803e-05 tokens_per_second_per_gpu:5337.868081971441 mfu:25.179634476866006 Step 1420 | loss:1.5622605085372925 lr:4.5791292027116006e-05 tokens_per_second_per_gpu:5297.475172377755 mfu:24.989094230571563 Step 1421 | loss:1.2707171440124512 lr:4.578522257134785e-05 tokens_per_second_per_gpu:4274.757474459005 mfu:20.164760355856334 Step 1422 | loss:1.338639497756958 lr:4.577914914514294e-05 tokens_per_second_per_gpu:4724.037634393556 mfu:22.284091525367323 Step 1423 | loss:1.619244933128357 lr:4.577307174966145e-05 tokens_per_second_per_gpu:4460.347153587343 mfu:21.040218537169146 Step 1424 | loss:1.4727540016174316 lr:4.57669903860643e-05 tokens_per_second_per_gpu:4298.320310046044 mfu:20.275910271554707 Step 1425 | loss:1.2083251476287842 lr:4.576090505551316e-05 tokens_per_second_per_gpu:5292.898777355563 mfu:24.967506594438373 Step 1426 | loss:1.2479647397994995 lr:4.575481575917046e-05 tokens_per_second_per_gpu:4037.2420580154535 mfu:19.044359612183325 Step 1427 | loss:1.339780569076538 lr:4.5748722498199394e-05 tokens_per_second_per_gpu:4770.420949945495 mfu:22.502889538635497 Step 1428 | loss:1.4182950258255005 lr:4.574262527376391e-05 tokens_per_second_per_gpu:3711.5767680154604 mfu:17.508140875025283 Step 1429 | loss:1.393635869026184 lr:4.57365240870287e-05 tokens_per_second_per_gpu:3663.774459699733 mfu:17.282649230785186 Step 1430 | loss:1.328749656677246 lr:4.573041893915925e-05 tokens_per_second_per_gpu:5339.807542045076 mfu:25.188783240939355 Step 1431 | loss:1.4081629514694214 lr:4.5724309831321757e-05 tokens_per_second_per_gpu:3649.362328066598 mfu:17.214664746908472 Step 1432 | loss:1.3352670669555664 lr:4.57181967646832e-05 tokens_per_second_per_gpu:5043.817613937147 mfu:23.792548248965012 Step 1433 | loss:1.3414208889007568 lr:4.5712079740411315e-05 tokens_per_second_per_gpu:4421.98848841547 mfu:20.859274168890277 Step 1434 | loss:1.5611714124679565 lr:4.570595875967458e-05 tokens_per_second_per_gpu:5053.156520258203 mfu:23.836601463463154 Step 1435 | loss:1.4962233304977417 lr:4.569983382364226e-05 tokens_per_second_per_gpu:3603.1318758749967 mfu:16.99658781619219 Step 1436 | loss:1.3160673379898071 lr:4.569370493348432e-05 tokens_per_second_per_gpu:3910.2323577703455 mfu:18.44523318603774 Step 1437 | loss:1.3171241283416748 lr:4.568757209037154e-05 tokens_per_second_per_gpu:5333.538392785108 mfu:25.159210594252926 Step 1438 | loss:1.454052209854126 lr:4.568143529547542e-05 tokens_per_second_per_gpu:5342.192762773567 mfu:25.20003473407627 Step 1439 | loss:1.3207793235778809 lr:4.567529454996821e-05 tokens_per_second_per_gpu:4810.429562198701 mfu:22.691616988807016 Step 1440 | loss:1.3845851421356201 lr:4.5669149855022955e-05 tokens_per_second_per_gpu:5193.837468566679 mfu:24.50021749927909 Step 1441 | loss:1.3982313871383667 lr:4.5663001211813405e-05 tokens_per_second_per_gpu:4951.849382452716 mfu:23.358718409654614 Step 1442 | loss:1.2784348726272583 lr:4.5656848621514095e-05 tokens_per_second_per_gpu:5321.015015133385 mfu:25.100135685161188 Step 1443 | loss:1.4070037603378296 lr:4.565069208530031e-05 tokens_per_second_per_gpu:3318.1597369875344 mfu:15.652325615799468 Step 1444 | loss:1.2052372694015503 lr:4.564453160434807e-05 tokens_per_second_per_gpu:5332.076511171701 mfu:25.15231464925976 Step 1445 | loss:1.3985008001327515 lr:4.563836717983418e-05 tokens_per_second_per_gpu:5323.834601330303 mfu:25.11343615432306 Step 1446 | loss:1.4828563928604126 lr:4.563219881293617e-05 tokens_per_second_per_gpu:3299.07980161782 mfu:15.562322305287868 Step 1447 | loss:1.4411938190460205 lr:4.562602650483234e-05 tokens_per_second_per_gpu:3829.354164211405 mfu:18.063716947777465 Step 1448 | loss:1.4446626901626587 lr:4.5619850256701734e-05 tokens_per_second_per_gpu:5095.347197115994 mfu:24.03562208467311 Step 1449 | loss:1.4772825241088867 lr:4.561367006972416e-05 tokens_per_second_per_gpu:4893.826488614954 mfu:23.085014519695374 Step 1450 | loss:1.4252573251724243 lr:4.5607485945080154e-05 tokens_per_second_per_gpu:5230.315181561729 mfu:24.672289095216353 Step 1451 | loss:1.448430061340332 lr:4.560129788395104e-05 tokens_per_second_per_gpu:5313.056551863392 mfu:25.062594256062784 Step 1452 | loss:1.2460670471191406 lr:4.559510588751886e-05 tokens_per_second_per_gpu:5310.630510188339 mfu:25.051150203556166 Step 1453 | loss:1.6491215229034424 lr:4.558890995696642e-05 tokens_per_second_per_gpu:4791.6966150144235 mfu:22.60325048076841 Step 1454 | loss:1.34735906124115 lr:4.5582710093477296e-05 tokens_per_second_per_gpu:4275.419647732807 mfu:20.167883940167272 Step 1455 | loss:1.3672590255737305 lr:4.557650629823579e-05 tokens_per_second_per_gpu:4548.379346830966 mfu:21.45548141254028 Step 1456 | loss:1.4118545055389404 lr:4.5570298572426954e-05 tokens_per_second_per_gpu:5310.780934185082 mfu:25.05185977921378 Step 1457 | loss:1.5574837923049927 lr:4.556408691723661e-05 tokens_per_second_per_gpu:5115.331222801269 mfu:24.129890143456922 Step 1458 | loss:1.3495619297027588 lr:4.5557871333851335e-05 tokens_per_second_per_gpu:4126.295362384677 mfu:19.46443924295344 Step 1459 | loss:1.2735530138015747 lr:4.555165182345841e-05 tokens_per_second_per_gpu:3942.019145989008 mfu:18.59517688945048 Step 1460 | loss:1.2768865823745728 lr:4.554542838724593e-05 tokens_per_second_per_gpu:4663.020612572566 mfu:21.996263822860286 Step 1461 | loss:1.4660567045211792 lr:4.55392010264027e-05 tokens_per_second_per_gpu:3688.294795532725 mfu:17.398315838510104 Step 1462 | loss:1.4718741178512573 lr:4.553296974211827e-05 tokens_per_second_per_gpu:5293.434191883774 mfu:24.97003223611908 Step 1463 | loss:1.3262720108032227 lr:4.552673453558296e-05 tokens_per_second_per_gpu:5309.124258500154 mfu:25.044044957349957 Step 1464 | loss:1.3901485204696655 lr:4.5520495407987844e-05 tokens_per_second_per_gpu:5303.218034884158 mfu:25.016184292847644 Step 1465 | loss:1.4970712661743164 lr:4.551425236052472e-05 tokens_per_second_per_gpu:4217.389951564834 mfu:19.89414796245583 Step 1466 | loss:1.4130511283874512 lr:4.550800539438617e-05 tokens_per_second_per_gpu:5313.527745191788 mfu:25.064816955386696 Step 1467 | loss:1.5180976390838623 lr:4.550175451076546e-05 tokens_per_second_per_gpu:5216.955073470349 mfu:24.60926718587982 Step 1468 | loss:1.4959107637405396 lr:4.549549971085668e-05 tokens_per_second_per_gpu:4190.793207216994 mfu:19.768686581494553 Step 1469 | loss:1.60683274269104 lr:4.548924099585464e-05 tokens_per_second_per_gpu:4508.11310305456 mfu:21.26553867051736 Step 1470 | loss:1.4435648918151855 lr:4.5482978366954864e-05 tokens_per_second_per_gpu:4916.586452343383 mfu:23.19237715185261 Step 1471 | loss:1.2528597116470337 lr:4.5476711825353676e-05 tokens_per_second_per_gpu:4388.930003699319 mfu:20.703331656125084 Step 1472 | loss:1.6087251901626587 lr:4.5470441372248114e-05 tokens_per_second_per_gpu:3944.91881281547 mfu:18.60885511260508 Step 1473 | loss:1.3209885358810425 lr:4.546416700883597e-05 tokens_per_second_per_gpu:3854.868770653279 mfu:18.184073699604536 Step 1474 | loss:1.2478954792022705 lr:4.54578887363158e-05 tokens_per_second_per_gpu:3957.3490302033338 mfu:18.66749056883741 Step 1475 | loss:1.6053189039230347 lr:4.5451606555886886e-05 tokens_per_second_per_gpu:4011.3372132180825 mfu:18.922162039451845 Step 1476 | loss:1.3491027355194092 lr:4.544532046874925e-05 tokens_per_second_per_gpu:4213.4051800854595 mfu:19.875351115515503 Step 1477 | loss:1.5458991527557373 lr:4.543903047610369e-05 tokens_per_second_per_gpu:2882.1560622261527 mfu:13.595621892052273 Step 1478 | loss:1.2292906045913696 lr:4.543273657915174e-05 tokens_per_second_per_gpu:5332.943744495436 mfu:25.15640553681308 Step 1479 | loss:1.5696251392364502 lr:4.542643877909564e-05 tokens_per_second_per_gpu:4717.4813768086 mfu:22.253164539726193 Step 1480 | loss:1.3000484704971313 lr:4.542013707713845e-05 tokens_per_second_per_gpu:4701.3162410149125 mfu:22.1769108361308 Step 1481 | loss:1.440537691116333 lr:4.54138314744839e-05 tokens_per_second_per_gpu:4061.041570556103 mfu:19.156625973453128 Step 1482 | loss:1.3194608688354492 lr:4.540752197233652e-05 tokens_per_second_per_gpu:4312.101790942241 mfu:20.34091986830517 Step 1483 | loss:1.3639320135116577 lr:4.5401208571901566e-05 tokens_per_second_per_gpu:3454.330081457916 mfu:16.29466436372274 Step 1484 | loss:1.4895766973495483 lr:4.5394891274385024e-05 tokens_per_second_per_gpu:3158.4566497366122 mfu:14.898978905080442 Step 1485 | loss:1.310809850692749 lr:4.538857008099364e-05 tokens_per_second_per_gpu:5324.970061621687 mfu:25.118792314247024 Step 1486 | loss:1.4246381521224976 lr:4.5382244992934916e-05 tokens_per_second_per_gpu:4534.643839677356 mfu:21.390688681777522 Step 1487 | loss:1.268298625946045 lr:4.5375916011417066e-05 tokens_per_second_per_gpu:4582.702011264725 mfu:21.617387276724727 Step 1488 | loss:1.2750552892684937 lr:4.536958313764906e-05 tokens_per_second_per_gpu:5340.229322399043 mfu:25.190772850832165 Step 1489 | loss:1.376225471496582 lr:4.5363246372840646e-05 tokens_per_second_per_gpu:4865.630388328442 mfu:22.952008703893117 Step 1490 | loss:1.3474881649017334 lr:4.535690571820226e-05 tokens_per_second_per_gpu:3912.671559374316 mfu:18.456739316174378 Step 1491 | loss:1.4096249341964722 lr:4.535056117494511e-05 tokens_per_second_per_gpu:5327.401423537589 mfu:25.130261463237453 Step 1492 | loss:1.2918003797531128 lr:4.534421274428117e-05 tokens_per_second_per_gpu:3976.281668131089 mfu:18.75679905218376 Step 1493 | loss:1.423695683479309 lr:4.533786042742309e-05 tokens_per_second_per_gpu:4697.959705011936 mfu:22.161077483120668 Step 1494 | loss:1.3153934478759766 lr:4.533150422558433e-05 tokens_per_second_per_gpu:4932.131813152399 mfu:23.265707271100798 Step 1495 | loss:1.4278475046157837 lr:4.532514413997906e-05 tokens_per_second_per_gpu:5306.247987244272 mfu:25.03047709509348 Step 1496 | loss:1.3324499130249023 lr:4.5318780171822194e-05 tokens_per_second_per_gpu:3843.7628221118107 mfu:18.131685045464213 Step 1497 | loss:1.3733189105987549 lr:4.531241232232939e-05 tokens_per_second_per_gpu:4904.6119585790075 mfu:23.13589142170674 Step 1498 | loss:1.3606454133987427 lr:4.530604059271705e-05 tokens_per_second_per_gpu:5015.049464028814 mfu:23.656843977494894 Step 1499 | loss:1.347259759902954 lr:4.5299664984202314e-05 tokens_per_second_per_gpu:3533.2100443640093 mfu:16.666754607060234 Step 1500 | loss:1.4244401454925537 lr:4.529328549800306e-05 tokens_per_second_per_gpu:5312.32311601045 mfu:25.059134514007393 Step 1501 | loss:1.3342477083206177 lr:4.528690213533792e-05 tokens_per_second_per_gpu:5334.708021101004 mfu:25.164727930578177 Step 1502 | loss:1.483500599861145 lr:4.528051489742625e-05 tokens_per_second_per_gpu:3521.238191085365 mfu:16.610281332536072 Step 1503 | loss:1.4465652704238892 lr:4.527412378548817e-05 tokens_per_second_per_gpu:4107.981163058393 mfu:19.378048040006743 Step 1504 | loss:1.4325478076934814 lr:4.526772880074449e-05 tokens_per_second_per_gpu:4090.5136433486105 mfu:19.29565076926952 Step 1505 | loss:1.3897442817687988 lr:4.5261329944416826e-05 tokens_per_second_per_gpu:3715.431759379712 mfu:17.526325527019807 Step 1506 | loss:1.5600941181182861 lr:4.525492721772748e-05 tokens_per_second_per_gpu:4389.889784332108 mfu:20.707859105125415 Step 1507 | loss:1.3805510997772217 lr:4.5248520621899525e-05 tokens_per_second_per_gpu:3948.198413882399 mfu:18.624325550395426 Step 1508 | loss:1.264342188835144 lr:4.5242110158156764e-05 tokens_per_second_per_gpu:4368.535175774106 mfu:20.607125773085397 Step 1509 | loss:1.498854398727417 lr:4.523569582772373e-05 tokens_per_second_per_gpu:5330.132746211483 mfu:25.14314557830191 Step 1510 | loss:1.2940692901611328 lr:4.522927763182571e-05 tokens_per_second_per_gpu:4615.417186968852 mfu:21.771710342305646 Step 1511 | loss:1.3568240404129028 lr:4.5222855571688707e-05 tokens_per_second_per_gpu:4846.13374563506 mfu:22.86003971383818 Step 1512 | loss:1.3565963506698608 lr:4.521642964853949e-05 tokens_per_second_per_gpu:4790.161570026122 mfu:22.59600941165291 Step 1513 | loss:1.4944746494293213 lr:4.5209999863605546e-05 tokens_per_second_per_gpu:4660.772470359568 mfu:21.98565895246896 Step 1514 | loss:1.27145254611969 lr:4.520356621811511e-05 tokens_per_second_per_gpu:5313.061481225043 mfu:25.062617508702726 Step 1515 | loss:1.3636322021484375 lr:4.519712871329714e-05 tokens_per_second_per_gpu:4031.8013165018488 mfu:19.018694706177428 Step 1516 | loss:1.5858036279678345 lr:4.5190687350381364e-05 tokens_per_second_per_gpu:4329.698626926777 mfu:20.423927145974037 Step 1517 | loss:1.494161605834961 lr:4.51842421305982e-05 tokens_per_second_per_gpu:4629.744418675971 mfu:21.839294338745926 Step 1518 | loss:1.4814176559448242 lr:4.5177793055178844e-05 tokens_per_second_per_gpu:4167.827312266368 mfu:19.660352536626718 Step 1519 | loss:1.562786340713501 lr:4.51713401253552e-05 tokens_per_second_per_gpu:5337.172211128412 mfu:25.176351935371628 Step 1520 | loss:1.3454197645187378 lr:4.5164883342359935e-05 tokens_per_second_per_gpu:3976.327489889597 mfu:18.757015201236634 Step 1521 | loss:1.335148572921753 lr:4.515842270742642e-05 tokens_per_second_per_gpu:4932.1922848547 mfu:23.265992526438083 Step 1522 | loss:1.3395755290985107 lr:4.515195822178878e-05 tokens_per_second_per_gpu:4524.205388577612 mfu:21.341448726956628 Step 1523 | loss:1.4653736352920532 lr:4.514548988668189e-05 tokens_per_second_per_gpu:5298.849590237776 mfu:24.995577594117147 Step 1524 | loss:1.367390751838684 lr:4.513901770334133e-05 tokens_per_second_per_gpu:5319.405345905862 mfu:25.092542600777076 Step 1525 | loss:1.2691798210144043 lr:4.513254167300345e-05 tokens_per_second_per_gpu:4881.848970917265 mfu:23.028514525140128 Step 1526 | loss:1.5481632947921753 lr:4.5126061796905295e-05 tokens_per_second_per_gpu:4001.596129471642 mfu:18.87621168541962 Step 1527 | loss:1.4708757400512695 lr:4.5119578076284676e-05 tokens_per_second_per_gpu:4604.375298567599 mfu:21.71962387077651 Step 1528 | loss:1.5622795820236206 lr:4.511309051238011e-05 tokens_per_second_per_gpu:2512.485540962167 mfu:11.851822970955316 Step 1529 | loss:1.6183288097381592 lr:4.510659910643088e-05 tokens_per_second_per_gpu:3604.3037340175647 mfu:17.002115670990296 Step 1530 | loss:1.438498854637146 lr:4.510010385967699e-05 tokens_per_second_per_gpu:3774.9988543253653 mfu:17.807313677072848 Step 1531 | loss:1.6223543882369995 lr:4.509360477335917e-05 tokens_per_second_per_gpu:4370.992620317086 mfu:20.618717958277905 Step 1532 | loss:1.2872684001922607 lr:4.508710184871888e-05 tokens_per_second_per_gpu:4741.256587500008 mfu:22.3653162650268 Step 1533 | loss:1.482985258102417 lr:4.5080595086998344e-05 tokens_per_second_per_gpu:5024.857595131482 mfu:23.70311060534591 Step 1534 | loss:1.5530177354812622 lr:4.5074084489440484e-05 tokens_per_second_per_gpu:5311.908978447973 mfu:25.057180956466034 Step 1535 | loss:1.3209693431854248 lr:4.5067570057288965e-05 tokens_per_second_per_gpu:4391.676064050186 mfu:20.716285291326333 Step 1536 | loss:1.410542607307434 lr:4.506105179178819e-05 tokens_per_second_per_gpu:5331.01501090435 mfu:25.147307371388045 Step 1537 | loss:1.3113503456115723 lr:4.5054529694183304e-05 tokens_per_second_per_gpu:4781.244766947568 mfu:22.553947330167887 Step 1538 | loss:1.554913878440857 lr:4.5048003765720144e-05 tokens_per_second_per_gpu:4627.645542957341 mfu:21.82939358387602 Step 1539 | loss:1.3722378015518188 lr:4.5041474007645334e-05 tokens_per_second_per_gpu:5114.048782127274 mfu:24.123840651990747 Step 1540 | loss:1.419403076171875 lr:4.503494042120618e-05 tokens_per_second_per_gpu:4307.919797375721 mfu:20.32119269113022 Step 1541 | loss:1.5934832096099854 lr:4.5028403007650766e-05 tokens_per_second_per_gpu:4824.407871896106 mfu:22.75755506059524 Step 1542 | loss:1.3438862562179565 lr:4.502186176822787e-05 tokens_per_second_per_gpu:5301.401115487377 mfu:25.007613574054613 Step 1543 | loss:1.486592173576355 lr:4.501531670418701e-05 tokens_per_second_per_gpu:5315.274385012126 mfu:25.073056153426712 Step 1544 | loss:1.7090067863464355 lr:4.500876781677843e-05 tokens_per_second_per_gpu:3389.5070009764354 mfu:15.988882833133601 Step 1545 | loss:1.5983113050460815 lr:4.5002215107253137e-05 tokens_per_second_per_gpu:4145.088262481089 mfu:19.553088559107607 Step 1546 | loss:1.4833269119262695 lr:4.499565857686282e-05 tokens_per_second_per_gpu:3320.5937507501117 mfu:15.663807274003116 Step 1547 | loss:1.1636937856674194 lr:4.498909822685994e-05 tokens_per_second_per_gpu:5305.454117923996 mfu:25.026732278061665 Step 1548 | loss:1.517668604850769 lr:4.498253405849765e-05 tokens_per_second_per_gpu:4671.9880240715565 mfu:22.038564632899195 Step 1549 | loss:1.2639226913452148 lr:4.4975966073029864e-05 tokens_per_second_per_gpu:4657.046758708812 mfu:21.968084134940387 Step 1550 | loss:1.5252835750579834 lr:4.496939427171121e-05 tokens_per_second_per_gpu:4832.244425403574 mfu:22.794521420543862 Step 1551 | loss:1.6314314603805542 lr:4.4962818655797036e-05 tokens_per_second_per_gpu:4957.43671242087 mfu:23.385074798411193 Step 1552 | loss:1.375640630722046 lr:4.495623922654344e-05 tokens_per_second_per_gpu:5356.994063225881 mfu:25.269854993672098 Step 1553 | loss:1.5965557098388672 lr:4.494965598520725e-05 tokens_per_second_per_gpu:5302.209196716725 mfu:25.011425431086323 Step 1554 | loss:1.4491780996322632 lr:4.4943068933046e-05 tokens_per_second_per_gpu:5256.396675546737 mfu:24.795319952305377 Step 1555 | loss:1.4539791345596313 lr:4.4936478071317944e-05 tokens_per_second_per_gpu:4461.881849985892 mfu:21.047457961927304 Step 1556 | loss:1.3071459531784058 lr:4.4929883401282115e-05 tokens_per_second_per_gpu:5208.256928944613 mfu:24.568236554095435 Step 1557 | loss:1.3932132720947266 lr:4.492328492419822e-05 tokens_per_second_per_gpu:4576.4323765547415 mfu:21.587812340087748 Step 1558 | loss:1.535069227218628 lr:4.4916682641326714e-05 tokens_per_second_per_gpu:5188.27067970369 mfu:24.47395800642025 Step 1559 | loss:1.4611687660217285 lr:4.491007655392878e-05 tokens_per_second_per_gpu:4033.2919435820813 mfu:19.02572624844209 Step 1560 | loss:1.412570834159851 lr:4.490346666326634e-05 tokens_per_second_per_gpu:4378.108539618942 mfu:20.652284963725787 Step 1561 | loss:1.3463683128356934 lr:4.489685297060201e-05 tokens_per_second_per_gpu:5296.379099263012 mfu:24.98392386667996 Step 1562 | loss:1.400026798248291 lr:4.4890235477199174e-05 tokens_per_second_per_gpu:5204.659281872209 mfu:24.55126583903302 Step 1563 | loss:1.5132677555084229 lr:4.48836141843219e-05 tokens_per_second_per_gpu:4263.001000594797 mfu:20.109303062777588 Step 1564 | loss:1.292505145072937 lr:4.4876989093235004e-05 tokens_per_second_per_gpu:5344.585311210818 mfu:25.21132079326564 Step 1565 | loss:1.3334293365478516 lr:4.487036020520403e-05 tokens_per_second_per_gpu:4709.885821818522 mfu:22.217335010902687 Step 1566 | loss:1.4615540504455566 lr:4.4863727521495244e-05 tokens_per_second_per_gpu:4826.839000718114 mfu:22.769023110042 Step 1567 | loss:1.4501371383666992 lr:4.485709104337563e-05 tokens_per_second_per_gpu:5317.644864304219 mfu:25.084238108692986 Step 1568 | loss:1.3666715621948242 lr:4.485045077211291e-05 tokens_per_second_per_gpu:3876.501164082536 mfu:18.28611739027725 Step 1569 | loss:1.3112236261367798 lr:4.4843806708975503e-05 tokens_per_second_per_gpu:5342.250158795735 mfu:25.200305480905605 Step 1570 | loss:1.3372406959533691 lr:4.483715885523259e-05 tokens_per_second_per_gpu:4416.740857609115 mfu:20.83452019903856 Step 1571 | loss:1.4855588674545288 lr:4.483050721215406e-05 tokens_per_second_per_gpu:5346.64028786571 mfu:25.221014468761933 Step 1572 | loss:1.3835545778274536 lr:4.4823851781010506e-05 tokens_per_second_per_gpu:5102.3989231394235 mfu:24.068886279474153 Step 1573 | loss:1.4014748334884644 lr:4.4817192563073276e-05 tokens_per_second_per_gpu:5307.1024004872015 mfu:25.034507508138315 Step 1574 | loss:1.4250446557998657 lr:4.4810529559614434e-05 tokens_per_second_per_gpu:5306.140807224437 mfu:25.02997150865312 Step 1575 | loss:1.5016655921936035 lr:4.480386277190674e-05 tokens_per_second_per_gpu:3821.360016635652 mfu:18.026007189720413 Step 1576 | loss:1.447281002998352 lr:4.479719220122371e-05 tokens_per_second_per_gpu:5309.6903625287005 mfu:25.04671536663992 Step 1577 | loss:1.318406105041504 lr:4.479051784883958e-05 tokens_per_second_per_gpu:4452.881881304383 mfu:21.00500357410363 Step 1578 | loss:1.5336805582046509 lr:4.4783839716029276e-05 tokens_per_second_per_gpu:3970.9181397074126 mfu:18.73149837349696 Step 1579 | loss:1.292163372039795 lr:4.4777157804068486e-05 tokens_per_second_per_gpu:5182.474396989187 mfu:24.446615951908132 Step 1580 | loss:1.4481654167175293 lr:4.47704721142336e-05 tokens_per_second_per_gpu:4837.573292538278 mfu:22.819658596016748 Step 1581 | loss:1.330263376235962 lr:4.4763782647801735e-05 tokens_per_second_per_gpu:5298.091076176246 mfu:24.991999553873068 Step 1582 | loss:1.394109845161438 lr:4.475708940605071e-05 tokens_per_second_per_gpu:3415.7224719551596 mfu:16.112545682560814 Step 1583 | loss:1.3862864971160889 lr:4.47503923902591e-05 tokens_per_second_per_gpu:5345.681396693585 mfu:25.216491215499317 Step 1584 | loss:1.447405457496643 lr:4.4743691601706183e-05 tokens_per_second_per_gpu:4516.548724236426 mfu:21.305330934897604 Step 1585 | loss:1.4911236763000488 lr:4.4736987041671954e-05 tokens_per_second_per_gpu:3413.5332210159722 mfu:16.10221861235594 Step 1586 | loss:1.4957910776138306 lr:4.473027871143712e-05 tokens_per_second_per_gpu:3966.5362642214222 mfu:18.710828319204495 Step 1587 | loss:1.292457103729248 lr:4.472356661228314e-05 tokens_per_second_per_gpu:4345.0671474830515 mfu:20.496423079577976 Step 1588 | loss:1.2378121614456177 lr:4.471685074549216e-05 tokens_per_second_per_gpu:3529.733223097216 mfu:16.65035384793789 Step 1589 | loss:1.2439218759536743 lr:4.4710131112347064e-05 tokens_per_second_per_gpu:5036.469298674361 mfu:23.757884992118584 Step 1590 | loss:1.4146350622177124 lr:4.4703407714131454e-05 tokens_per_second_per_gpu:4498.053358347382 mfu:21.218085138364167 Step 1591 | loss:1.4042444229125977 lr:4.469668055212963e-05 tokens_per_second_per_gpu:5361.567351283992 mfu:25.29142797372561 Step 1592 | loss:1.292551875114441 lr:4.468994962762665e-05 tokens_per_second_per_gpu:5318.3230084073475 mfu:25.08743703013076 Step 1593 | loss:1.2709112167358398 lr:4.468321494190826e-05 tokens_per_second_per_gpu:3493.663649739819 mfu:16.480207516307242 Step 1594 | loss:1.3192604780197144 lr:4.467647649626093e-05 tokens_per_second_per_gpu:5182.864031991635 mfu:24.448453926693265 Step 1595 | loss:1.371630311012268 lr:4.466973429197187e-05 tokens_per_second_per_gpu:4981.678235412868 mfu:23.499426198394758 Step 1596 | loss:1.436889886856079 lr:4.466298833032896e-05 tokens_per_second_per_gpu:5335.6172596216475 mfu:25.169016963812137 Step 1597 | loss:1.399296760559082 lr:4.4656238612620847e-05 tokens_per_second_per_gpu:5369.261094722111 mfu:25.327720674211207 Step 1598 | loss:1.3751376867294312 lr:4.4649485140136884e-05 tokens_per_second_per_gpu:3991.8560148070737 mfu:18.830265902711925 Step 1599 | loss:1.392868995666504 lr:4.464272791416712e-05 tokens_per_second_per_gpu:3992.2485480337305 mfu:18.832117548915143 Step 1600 | loss:1.1981849670410156 lr:4.4635966936002325e-05 tokens_per_second_per_gpu:5337.2726686794085 mfu:25.176825810779505 Step 1601 | loss:1.3122913837432861 lr:4.462920220693402e-05 tokens_per_second_per_gpu:4271.646375612323 mfu:20.15008477178834 Step 1602 | loss:1.4314210414886475 lr:4.4622433728254396e-05 tokens_per_second_per_gpu:4611.167629596519 mfu:21.7516644551311 Step 1603 | loss:1.2645063400268555 lr:4.46156615012564e-05 tokens_per_second_per_gpu:4929.822327149686 mfu:23.254813031587055 Step 1604 | loss:1.468375563621521 lr:4.460888552723367e-05 tokens_per_second_per_gpu:4266.6575853155255 mfu:20.12655179678295 Step 1605 | loss:1.3968474864959717 lr:4.460210580748055e-05 tokens_per_second_per_gpu:5312.480743656651 mfu:25.05987807050857 Step 1606 | loss:1.484591007232666 lr:4.459532234329214e-05 tokens_per_second_per_gpu:4378.20286881842 mfu:20.652729930653944 Step 1607 | loss:1.415522575378418 lr:4.458853513596423e-05 tokens_per_second_per_gpu:4489.9973186321295 mfu:21.180083424525208 Step 1608 | loss:1.4087567329406738 lr:4.458174418679332e-05 tokens_per_second_per_gpu:5323.465395699638 mfu:25.11169454837024 Step 1609 | loss:1.471644639968872 lr:4.4574949497076616e-05 tokens_per_second_per_gpu:5319.702683756542 mfu:25.0939451941498 Step 1610 | loss:1.2963645458221436 lr:4.456815106811207e-05 tokens_per_second_per_gpu:4344.908132632487 mfu:20.49567297939713 Step 1611 | loss:1.2942333221435547 lr:4.456134890119834e-05 tokens_per_second_per_gpu:5358.161403984843 mfu:25.27536153920099 Step 1612 | loss:1.3933427333831787 lr:4.4554542997634785e-05 tokens_per_second_per_gpu:3962.757842380881 mfu:18.69300485871742 Step 1613 | loss:1.4906545877456665 lr:4.4547733358721466e-05 tokens_per_second_per_gpu:4844.89456471018 mfu:22.85419428598945 Step 1614 | loss:1.5874817371368408 lr:4.4540919985759195e-05 tokens_per_second_per_gpu:3588.4825271454783 mfu:16.927484338798422 Step 1615 | loss:1.4869633913040161 lr:4.453410288004947e-05 tokens_per_second_per_gpu:3313.6940256321027 mfu:15.631260093406972 Step 1616 | loss:1.5936003923416138 lr:4.45272820428945e-05 tokens_per_second_per_gpu:5328.751149063728 mfu:25.13662834883117 Step 1617 | loss:1.4747486114501953 lr:4.4520457475597234e-05 tokens_per_second_per_gpu:4865.584620336527 mfu:22.95179280846643 Step 1618 | loss:1.3969093561172485 lr:4.451362917946129e-05 tokens_per_second_per_gpu:5321.349801813214 mfu:25.10171493105044 Step 1619 | loss:1.4202903509140015 lr:4.450679715579105e-05 tokens_per_second_per_gpu:3707.847860878904 mfu:17.490550983844983 Step 1620 | loss:1.374269723892212 lr:4.4499961405891565e-05 tokens_per_second_per_gpu:4894.784594454122 mfu:23.08953406840844 Step 1621 | loss:1.3054522275924683 lr:4.4493121931068624e-05 tokens_per_second_per_gpu:4020.520634187888 mfu:18.965481803019603 Step 1622 | loss:1.3292264938354492 lr:4.448627873262871e-05 tokens_per_second_per_gpu:4927.548004276893 mfu:23.244084662556592 Step 1623 | loss:1.3662816286087036 lr:4.447943181187902e-05 tokens_per_second_per_gpu:5189.6120674411295 mfu:24.480285561242102 Step 1624 | loss:1.6602776050567627 lr:4.447258117012748e-05 tokens_per_second_per_gpu:5316.298541388953 mfu:25.077887273795305 Step 1625 | loss:1.4543594121932983 lr:4.4465726808682705e-05 tokens_per_second_per_gpu:5139.271399616311 mfu:24.242820042108832 Step 1626 | loss:1.3060775995254517 lr:4.4458868728854044e-05 tokens_per_second_per_gpu:4696.109319752493 mfu:22.152348900143597 Step 1627 | loss:1.4332627058029175 lr:4.445200693195152e-05 tokens_per_second_per_gpu:3637.704909914987 mfu:17.15967471652669 Step 1628 | loss:1.4642735719680786 lr:4.444514141928591e-05 tokens_per_second_per_gpu:4792.416765057157 mfu:22.606647551390253 Step 1629 | loss:1.1634385585784912 lr:4.443827219216865e-05 tokens_per_second_per_gpu:4703.018752908635 mfu:22.184941875211976 Step 1630 | loss:1.4086179733276367 lr:4.443139925191194e-05 tokens_per_second_per_gpu:3780.930517704995 mfu:17.83529434528069 Step 1631 | loss:1.3520103693008423 lr:4.442452259982866e-05 tokens_per_second_per_gpu:4359.523792997629 mfu:20.564617543028312 Step 1632 | loss:1.445205569267273 lr:4.4417642237232395e-05 tokens_per_second_per_gpu:4976.677305423145 mfu:23.475835958386597 Step 1633 | loss:1.2713054418563843 lr:4.441075816543745e-05 tokens_per_second_per_gpu:5252.964645599905 mfu:24.779130481481477 Step 1634 | loss:1.6233901977539062 lr:4.440387038575883e-05 tokens_per_second_per_gpu:4054.1623700370765 mfu:19.124175610892237 Step 1635 | loss:1.3775097131729126 lr:4.439697889951225e-05 tokens_per_second_per_gpu:5109.459588204125 mfu:24.102192641258032 Step 1636 | loss:1.3175313472747803 lr:4.439008370801416e-05 tokens_per_second_per_gpu:4168.863667626855 mfu:19.665241201682598 Step 1637 | loss:1.330923080444336 lr:4.438318481258166e-05 tokens_per_second_per_gpu:5316.605516280854 mfu:25.07933532673572 Step 1638 | loss:1.4252114295959473 lr:4.437628221453262e-05 tokens_per_second_per_gpu:3914.7022644803455 mfu:18.466318498633537 Step 1639 | loss:1.3335601091384888 lr:4.436937591518557e-05 tokens_per_second_per_gpu:5323.339896522411 mfu:25.111102547338895 Step 1640 | loss:1.256561517715454 lr:4.436246591585977e-05 tokens_per_second_per_gpu:5335.022976079117 mfu:25.166213626946796 Step 1641 | loss:1.4234192371368408 lr:4.43555522178752e-05 tokens_per_second_per_gpu:3383.718474897342 mfu:15.961577367994128 Step 1642 | loss:1.2616345882415771 lr:4.43486348225525e-05 tokens_per_second_per_gpu:4781.90853721324 mfu:22.55707844776195 Step 1643 | loss:1.4957488775253296 lr:4.4341713731213055e-05 tokens_per_second_per_gpu:4245.1558757914045 mfu:20.02512456438774 Step 1644 | loss:1.3570836782455444 lr:4.433478894517896e-05 tokens_per_second_per_gpu:5331.493964461108 mfu:25.149566677033174 Step 1645 | loss:1.4281716346740723 lr:4.4327860465773e-05 tokens_per_second_per_gpu:5269.229459431487 mfu:24.855854383388444 Step 1646 | loss:1.2742691040039062 lr:4.432092829431865e-05 tokens_per_second_per_gpu:4141.177804753086 mfu:19.53464226281173 Step 1647 | loss:1.244821310043335 lr:4.431399243214012e-05 tokens_per_second_per_gpu:5324.131200230984 mfu:25.114835261942567 Step 1648 | loss:1.2002755403518677 lr:4.430705288056231e-05 tokens_per_second_per_gpu:5303.255258606118 mfu:25.016359883495152 Step 1649 | loss:1.4492976665496826 lr:4.430010964091084e-05 tokens_per_second_per_gpu:3228.9786520639295 mfu:15.231643222352726 Step 1650 | loss:1.4479187726974487 lr:4.4293162714512e-05 tokens_per_second_per_gpu:3422.1116075210975 mfu:16.14268432512428 Step 1651 | loss:1.3310654163360596 lr:4.428621210269281e-05 tokens_per_second_per_gpu:4170.827887340292 mfu:19.674506761201318 Step 1652 | loss:1.7864255905151367 lr:4.427925780678102e-05 tokens_per_second_per_gpu:4568.153155322984 mfu:21.54875784095675 Step 1653 | loss:1.288530945777893 lr:4.4272299828105024e-05 tokens_per_second_per_gpu:4234.826283541333 mfu:19.976398115333982 Step 1654 | loss:1.3089802265167236 lr:4.426533816799395e-05 tokens_per_second_per_gpu:4536.253528356551 mfu:21.398281857918494 Step 1655 | loss:1.28542160987854 lr:4.4258372827777645e-05 tokens_per_second_per_gpu:4591.479605007235 mfu:21.658792684020067 Step 1656 | loss:1.353381633758545 lr:4.425140380878663e-05 tokens_per_second_per_gpu:5335.71435079004 mfu:25.169474959418906 Step 1657 | loss:1.4122313261032104 lr:4.424443111235215e-05 tokens_per_second_per_gpu:4614.75541597642 mfu:21.768588655624573 Step 1658 | loss:1.474891185760498 lr:4.423745473980614e-05 tokens_per_second_per_gpu:4647.090913756376 mfu:21.92112071565744 Step 1659 | loss:1.383421540260315 lr:4.423047469248124e-05 tokens_per_second_per_gpu:5292.63809468815 mfu:24.96627690981914 Step 1660 | loss:1.4202983379364014 lr:4.42234909717108e-05 tokens_per_second_per_gpu:4629.72568981458 mfu:21.839205991511268 Step 1661 | loss:1.4791046380996704 lr:4.421650357882885e-05 tokens_per_second_per_gpu:5319.789859810722 mfu:25.094356418471133 Step 1662 | loss:1.1710599660873413 lr:4.420951251517015e-05 tokens_per_second_per_gpu:5303.658812382355 mfu:25.018263515511034 Step 1663 | loss:1.278549313545227 lr:4.420251778207015e-05 tokens_per_second_per_gpu:5330.965222457359 mfu:25.147072510788806 Step 1664 | loss:1.565186619758606 lr:4.419551938086499e-05 tokens_per_second_per_gpu:5323.170919813668 mfu:25.11030545537335 Step 1665 | loss:1.564383625984192 lr:4.4188517312891516e-05 tokens_per_second_per_gpu:5352.333325589691 mfu:25.247869499038348 Step 1666 | loss:1.2946778535842896 lr:4.418151157948729e-05 tokens_per_second_per_gpu:3798.6697737412965 mfu:17.918973442633103 Step 1667 | loss:1.4913246631622314 lr:4.417450218199055e-05 tokens_per_second_per_gpu:3455.7101092881794 mfu:16.30117419045512 Step 1668 | loss:1.375567078590393 lr:4.4167489121740254e-05 tokens_per_second_per_gpu:5330.7965366779945 mfu:25.14627679118678 Step 1669 | loss:1.416224479675293 lr:4.416047240007605e-05 tokens_per_second_per_gpu:5309.354650534615 mfu:25.045131755885443 Step 1670 | loss:1.4026544094085693 lr:4.4153452018338296e-05 tokens_per_second_per_gpu:3979.727378286621 mfu:18.773053054886176 Step 1671 | loss:1.396547794342041 lr:4.414642797786801e-05 tokens_per_second_per_gpu:4757.864275831205 mfu:22.443657564448873 Step 1672 | loss:1.4346215724945068 lr:4.413940028000697e-05 tokens_per_second_per_gpu:4553.758807380898 mfu:21.48085724578492 Step 1673 | loss:1.4046437740325928 lr:4.413236892609761e-05 tokens_per_second_per_gpu:4107.069867254151 mfu:19.37374930221504 Step 1674 | loss:1.360102653503418 lr:4.412533391748307e-05 tokens_per_second_per_gpu:5132.8684517490365 mfu:24.21261624456334 Step 1675 | loss:1.1503633260726929 lr:4.411829525550719e-05 tokens_per_second_per_gpu:3755.1953764215123 mfu:17.71389729297863 Step 1676 | loss:1.3889697790145874 lr:4.411125294151453e-05 tokens_per_second_per_gpu:5321.581880746912 mfu:25.102809686977444 Step 1677 | loss:1.5122284889221191 lr:4.41042069768503e-05 tokens_per_second_per_gpu:5316.408240065182 mfu:25.078404741167603 Step 1678 | loss:1.4946855306625366 lr:4.4097157362860455e-05 tokens_per_second_per_gpu:4635.769206556675 mfu:21.867714291114016 Step 1679 | loss:1.4913169145584106 lr:4.409010410089162e-05 tokens_per_second_per_gpu:5144.560514655483 mfu:24.267769700164685 Step 1680 | loss:1.3893897533416748 lr:4.408304719229113e-05 tokens_per_second_per_gpu:5311.791292163676 mfu:25.056625810183657 Step 1681 | loss:1.2864632606506348 lr:4.4075986638406995e-05 tokens_per_second_per_gpu:4474.45875760322 mfu:21.106785380999955 Step 1682 | loss:1.3207223415374756 lr:4.406892244058795e-05 tokens_per_second_per_gpu:5313.379072059739 mfu:25.06411563885657 Step 1683 | loss:1.25533926486969 lr:4.406185460018341e-05 tokens_per_second_per_gpu:4658.367301246704 mfu:21.974313359399417 Step 1684 | loss:1.4854692220687866 lr:4.4054783118543485e-05 tokens_per_second_per_gpu:4591.154743552229 mfu:21.657260257109726 Step 1685 | loss:1.2359975576400757 lr:4.4047707997019e-05 tokens_per_second_per_gpu:4427.585371483643 mfu:20.885675621249568 Step 1686 | loss:1.4202555418014526 lr:4.404062923696143e-05 tokens_per_second_per_gpu:4891.29353459257 mfu:23.073066143405267 Step 1687 | loss:1.3488266468048096 lr:4.4033546839723e-05 tokens_per_second_per_gpu:4795.434689876524 mfu:22.620883617674277 Step 1688 | loss:1.4760949611663818 lr:4.40264608066566e-05 tokens_per_second_per_gpu:3612.099198284508 mfu:17.03888820598082 Step 1689 | loss:1.2895283699035645 lr:4.4019371139115805e-05 tokens_per_second_per_gpu:4793.905041552519 mfu:22.613668005545026 Step 1690 | loss:1.3227607011795044 lr:4.401227783845491e-05 tokens_per_second_per_gpu:4202.467747414699 mfu:19.823757379489084 Step 1691 | loss:1.224825143814087 lr:4.4005180906028896e-05 tokens_per_second_per_gpu:4417.246396274559 mfu:20.83690491117725 Step 1692 | loss:1.5783275365829468 lr:4.3998080343193424e-05 tokens_per_second_per_gpu:4585.763948415944 mfu:21.631830956687377 Step 1693 | loss:1.4064568281173706 lr:4.3990976151304866e-05 tokens_per_second_per_gpu:3953.9738192884056 mfu:18.65156912308133 Step 1694 | loss:1.216261625289917 lr:4.398386833172027e-05 tokens_per_second_per_gpu:4882.273446363184 mfu:23.030516848241508 Step 1695 | loss:1.531304121017456 lr:4.397675688579739e-05 tokens_per_second_per_gpu:3747.703483746613 mfu:17.67855675698243 Step 1696 | loss:1.5392634868621826 lr:4.396964181489468e-05 tokens_per_second_per_gpu:5056.731881097107 mfu:23.85346705055973 Step 1697 | loss:1.426095724105835 lr:4.3962523120371264e-05 tokens_per_second_per_gpu:5320.752242154954 mfu:25.098896140188238 Step 1698 | loss:1.339998483657837 lr:4.395540080358698e-05 tokens_per_second_per_gpu:4614.011539206283 mfu:21.765079661981368 Step 1699 | loss:1.3539278507232666 lr:4.394827486590233e-05 tokens_per_second_per_gpu:4510.010896216524 mfu:21.274490884659244 Step 1700 | loss:1.481577754020691 lr:4.394114530867854e-05 tokens_per_second_per_gpu:5326.0811546166915 mfu:25.124033529476474 Step 1701 | loss:1.2998802661895752 lr:4.393401213327751e-05 tokens_per_second_per_gpu:4505.951107234628 mfu:21.255340167360213 Step 1702 | loss:1.3979899883270264 lr:4.3926875341061834e-05 tokens_per_second_per_gpu:3692.8298098491223 mfu:17.419708274793777 Step 1703 | loss:1.4530917406082153 lr:4.39197349333948e-05 tokens_per_second_per_gpu:5290.606579125224 mfu:24.95669390429652 Step 1704 | loss:1.45472252368927 lr:4.3912590911640375e-05 tokens_per_second_per_gpu:5299.555663230377 mfu:24.99890826089172 Step 1705 | loss:1.262152075767517 lr:4.390544327716324e-05 tokens_per_second_per_gpu:5286.164893749221 mfu:24.935741716548243 Step 1706 | loss:1.4553967714309692 lr:4.389829203132874e-05 tokens_per_second_per_gpu:4947.2467697155025 mfu:23.337007100086467 Step 1707 | loss:1.3050462007522583 lr:4.389113717550291e-05 tokens_per_second_per_gpu:5272.757932710483 mfu:24.872498793865088 Step 1708 | loss:1.5392789840698242 lr:4.388397871105251e-05 tokens_per_second_per_gpu:4023.140716095518 mfu:18.977841176409967 Step 1709 | loss:1.4234153032302856 lr:4.3876816639344945e-05 tokens_per_second_per_gpu:4005.4326850366974 mfu:18.894309372603864 Step 1710 | loss:1.3862760066986084 lr:4.386965096174834e-05 tokens_per_second_per_gpu:5304.137718060106 mfu:25.02052259530272 Step 1711 | loss:1.2205215692520142 lr:4.38624816796315e-05 tokens_per_second_per_gpu:4394.559859115534 mfu:20.729888644675754 Step 1712 | loss:1.3444498777389526 lr:4.3855308794363905e-05 tokens_per_second_per_gpu:4980.254007376394 mfu:23.49270787174835 Step 1713 | loss:1.4430642127990723 lr:4.3848132307315736e-05 tokens_per_second_per_gpu:3195.1706323200256 mfu:15.072165024977762 Step 1714 | loss:1.3893848657608032 lr:4.3840952219857875e-05 tokens_per_second_per_gpu:3795.5870451929522 mfu:17.904431686102836 Step 1715 | loss:1.4541360139846802 lr:4.383376853336186e-05 tokens_per_second_per_gpu:3905.715862563493 mfu:18.423928107553472 Step 1716 | loss:1.433123230934143 lr:4.382658124919995e-05 tokens_per_second_per_gpu:3446.3481777693282 mfu:16.257012362170475 Step 1717 | loss:1.3441632986068726 lr:4.381939036874506e-05 tokens_per_second_per_gpu:4595.597144659795 mfu:21.678215821085907 Step 1718 | loss:1.4137459993362427 lr:4.381219589337081e-05 tokens_per_second_per_gpu:5318.108608464983 mfu:25.08642566902223 Step 1719 | loss:1.5690538883209229 lr:4.380499782445151e-05 tokens_per_second_per_gpu:3976.21489680772 mfu:18.75648408045906 Step 1720 | loss:1.3512742519378662 lr:4.3797796163362154e-05 tokens_per_second_per_gpu:4444.670877718185 mfu:20.96627086924586 Step 1721 | loss:1.281761884689331 lr:4.3790590911478405e-05 tokens_per_second_per_gpu:4719.897781474393 mfu:22.26456313281589 Step 1722 | loss:1.5050300359725952 lr:4.3783382070176635e-05 tokens_per_second_per_gpu:4559.061547953441 mfu:21.505871177806444 Step 1723 | loss:1.4423142671585083 lr:4.377616964083389e-05 tokens_per_second_per_gpu:5313.002143069242 mfu:25.062337600497678 Step 1724 | loss:1.3057760000228882 lr:4.37689536248279e-05 tokens_per_second_per_gpu:5163.8830525813155 mfu:24.35891740832576 Step 1725 | loss:1.2936495542526245 lr:4.3761734023537085e-05 tokens_per_second_per_gpu:4793.910963272939 mfu:22.613695939310595 Step 1726 | loss:1.6217436790466309 lr:4.375451083834054e-05 tokens_per_second_per_gpu:4527.262681036832 mfu:21.355870497114648 Step 1727 | loss:1.402127981185913 lr:4.3747284070618075e-05 tokens_per_second_per_gpu:5308.698655927639 mfu:25.042037317400116 Step 1728 | loss:1.5329275131225586 lr:4.3740053721750143e-05 tokens_per_second_per_gpu:4422.876740617839 mfu:20.8634642060803 Step 1729 | loss:1.514548420906067 lr:4.373281979311792e-05 tokens_per_second_per_gpu:4294.28777499292 mfu:20.256888115687694 Step 1730 | loss:1.398983120918274 lr:4.372558228610322e-05 tokens_per_second_per_gpu:4603.680641335227 mfu:21.716347054090665 Step 1731 | loss:1.42782461643219 lr:4.371834120208857e-05 tokens_per_second_per_gpu:4184.18622027533 mfu:19.737520296822513 Step 1732 | loss:1.4548701047897339 lr:4.371109654245721e-05 tokens_per_second_per_gpu:5343.4956803889245 mfu:25.20618081876858 Step 1733 | loss:1.4086350202560425 lr:4.3703848308593e-05 tokens_per_second_per_gpu:5333.53815993657 mfu:25.159209495866644 Step 1734 | loss:1.5769555568695068 lr:4.369659650188051e-05 tokens_per_second_per_gpu:4579.205568953432 mfu:21.600893961787786 Step 1735 | loss:1.6306655406951904 lr:4.3689341123705016e-05 tokens_per_second_per_gpu:4355.7333678676805 mfu:20.546737460977127 Step 1736 | loss:1.4045435190200806 lr:4.368208217545243e-05 tokens_per_second_per_gpu:3479.4997189521637 mfu:16.413393838166087 Step 1737 | loss:1.4431509971618652 lr:4.36748196585094e-05 tokens_per_second_per_gpu:5309.60161977403 mfu:25.046296751925063 Step 1738 | loss:1.3422091007232666 lr:4.366755357426321e-05 tokens_per_second_per_gpu:4082.000522400083 mfu:19.255492925267106 Step 1739 | loss:1.3588402271270752 lr:4.366028392410184e-05 tokens_per_second_per_gpu:5355.982561402351 mfu:25.265083566990498 Step 1740 | loss:1.2730906009674072 lr:4.3653010709413964e-05 tokens_per_second_per_gpu:4537.552306116744 mfu:21.404408414207666 Step 1741 | loss:1.3699156045913696 lr:4.364573393158893e-05 tokens_per_second_per_gpu:4499.522480633224 mfu:21.225015238844595 Step 1742 | loss:1.3842405080795288 lr:4.3638453592016735e-05 tokens_per_second_per_gpu:5317.285632474028 mfu:25.082543550858706 Step 1743 | loss:1.415345311164856 lr:4.363116969208812e-05 tokens_per_second_per_gpu:3764.47263086694 mfu:17.75765968506054 Step 1744 | loss:1.4573307037353516 lr:4.362388223319446e-05 tokens_per_second_per_gpu:4031.109233338529 mfu:19.01543003181449 Step 1745 | loss:1.3908191919326782 lr:4.361659121672781e-05 tokens_per_second_per_gpu:3884.5056260584233 mfu:18.323875803119552 Step 1746 | loss:1.368395447731018 lr:4.3609296644080924e-05 tokens_per_second_per_gpu:5278.313543413257 mfu:24.898705557435 Step 1747 | loss:1.4732860326766968 lr:4.360199851664722e-05 tokens_per_second_per_gpu:3414.831215522167 mfu:16.10834147390236 Step 1748 | loss:1.3907020092010498 lr:4.3594696835820806e-05 tokens_per_second_per_gpu:5338.670048957162 mfu:25.183417491967333 Step 1749 | loss:1.2611846923828125 lr:4.358739160299648e-05 tokens_per_second_per_gpu:4957.814877510114 mfu:23.386858667658768 Step 1750 | loss:1.4091968536376953 lr:4.358008281956967e-05 tokens_per_second_per_gpu:3717.6583523741447 mfu:17.536828746070487 Step 1751 | loss:1.4089866876602173 lr:4.357277048693653e-05 tokens_per_second_per_gpu:5327.162209959586 mfu:25.129133051975966 Step 1752 | loss:1.33683180809021 lr:4.3565454606493895e-05 tokens_per_second_per_gpu:4958.858989633068 mfu:23.391783922686642 Step 1753 | loss:1.3614217042922974 lr:4.355813517963924e-05 tokens_per_second_per_gpu:4767.825706097406 mfu:22.4906473306098 Step 1754 | loss:1.3560148477554321 lr:4.3550812207770734e-05 tokens_per_second_per_gpu:4482.175838688523 mfu:21.143188169149134 Step 1755 | loss:1.4425690174102783 lr:4.354348569228724e-05 tokens_per_second_per_gpu:3894.321616809466 mfu:18.370179506272937 Step 1756 | loss:1.429883599281311 lr:4.353615563458827e-05 tokens_per_second_per_gpu:5272.079454072403 mfu:24.86929829436887 Step 1757 | loss:1.2494173049926758 lr:4.3528822036074045e-05 tokens_per_second_per_gpu:5323.353259967029 mfu:25.111165584987194 Step 1758 | loss:1.3998754024505615 lr:4.352148489814544e-05 tokens_per_second_per_gpu:4399.558068240226 mfu:20.75346604989934 Step 1759 | loss:1.4216080904006958 lr:4.351414422220399e-05 tokens_per_second_per_gpu:3593.4124893434655 mfu:16.950739811624615 Step 1760 | loss:1.355804204940796 lr:4.350680000965195e-05 tokens_per_second_per_gpu:5335.3281108310275 mfu:25.167652999632914 Step 1761 | loss:1.3341705799102783 lr:4.3499452261892214e-05 tokens_per_second_per_gpu:3930.563674312827 mfu:18.54113947504893 Step 1762 | loss:1.6898833513259888 lr:4.349210098032838e-05 tokens_per_second_per_gpu:3423.5075398235335 mfu:16.14926917596548 Step 1763 | loss:1.2860358953475952 lr:4.348474616636468e-05 tokens_per_second_per_gpu:5359.423402116906 mfu:25.281314599709017 Step 1764 | loss:1.352460265159607 lr:4.347738782140607e-05 tokens_per_second_per_gpu:5319.58950328412 mfu:25.093411302550805 Step 1765 | loss:1.3789019584655762 lr:4.3470025946858135e-05 tokens_per_second_per_gpu:4421.243294374913 mfu:20.855758961457756 Step 1766 | loss:1.3982685804367065 lr:4.346266054412718e-05 tokens_per_second_per_gpu:5326.836007879976 mfu:25.127594301110634 Step 1767 | loss:1.2617825269699097 lr:4.345529161462013e-05 tokens_per_second_per_gpu:4826.7990759262 mfu:22.76883477798667 Step 1768 | loss:1.275585651397705 lr:4.344791915974464e-05 tokens_per_second_per_gpu:4807.220653613392 mfu:22.67648001951385 Step 1769 | loss:1.396978735923767 lr:4.3440543180909e-05 tokens_per_second_per_gpu:5285.233324220909 mfu:24.931347344141045 Step 1770 | loss:1.3823552131652832 lr:4.343316367952219e-05 tokens_per_second_per_gpu:4050.0660047307097 mfu:19.10485235683012 Step 1771 | loss:1.3175392150878906 lr:4.3425780656993854e-05 tokens_per_second_per_gpu:4270.185451787024 mfu:20.1431933448451 Step 1772 | loss:1.3639098405838013 lr:4.341839411473431e-05 tokens_per_second_per_gpu:5305.814200914145 mfu:25.028430850962692 Step 1773 | loss:1.545640468597412 lr:4.341100405415455e-05 tokens_per_second_per_gpu:4044.9696460201753 mfu:19.08081196326407 Step 1774 | loss:1.2086580991744995 lr:4.3403610476666246e-05 tokens_per_second_per_gpu:4031.2074228629135 mfu:19.01589320855387 Step 1775 | loss:1.490492820739746 lr:4.3396213383681726e-05 tokens_per_second_per_gpu:4978.708482437798 mfu:23.485417366919247 Step 1776 | loss:1.5316708087921143 lr:4.3388812776614016e-05 tokens_per_second_per_gpu:3045.5806929050327 mfu:14.366523758081762 Step 1777 | loss:1.3698205947875977 lr:4.338140865687677e-05 tokens_per_second_per_gpu:4472.962187088761 mfu:21.099725802541993 Step 1778 | loss:1.3569873571395874 lr:4.3374001025884356e-05 tokens_per_second_per_gpu:5299.809398245722 mfu:25.000105172250763 Step 1779 | loss:1.3674335479736328 lr:4.3366589885051786e-05 tokens_per_second_per_gpu:4357.705284624073 mfu:20.556039328760725 Step 1780 | loss:1.2370178699493408 lr:4.335917523579476e-05 tokens_per_second_per_gpu:3342.9549080368215 mfu:15.76928866813137 Step 1781 | loss:1.354824423789978 lr:4.335175707952964e-05 tokens_per_second_per_gpu:3972.250838791547 mfu:18.737784942458735 Step 1782 | loss:1.3096330165863037 lr:4.334433541767345e-05 tokens_per_second_per_gpu:5290.279297498437 mfu:24.95515006102296 Step 1783 | loss:1.3682563304901123 lr:4.333691025164389e-05 tokens_per_second_per_gpu:4053.6267241398846 mfu:19.121648877804574 Step 1784 | loss:1.5461746454238892 lr:4.332948158285934e-05 tokens_per_second_per_gpu:2626.506198298371 mfu:12.389677865540358 Step 1785 | loss:1.393675684928894 lr:4.3322049412738844e-05 tokens_per_second_per_gpu:4444.758851578597 mfu:20.966685856955316 Step 1786 | loss:1.4213347434997559 lr:4.3314613742702086e-05 tokens_per_second_per_gpu:4227.202255647277 mfu:19.94043427496442 Step 1787 | loss:1.5060944557189941 lr:4.330717457416947e-05 tokens_per_second_per_gpu:3755.498067005464 mfu:17.715325136107467 Step 1788 | loss:1.3960962295532227 lr:4.329973190856202e-05 tokens_per_second_per_gpu:3748.511092649861 mfu:17.68236638597134 Step 1789 | loss:1.510111927986145 lr:4.3292285747301477e-05 tokens_per_second_per_gpu:4028.1206171633053 mfu:19.001332219405455 Step 1790 | loss:1.1894230842590332 lr:4.32848360918102e-05 tokens_per_second_per_gpu:5116.907941932786 mfu:24.137327796616315 Step 1791 | loss:1.6201996803283691 lr:4.327738294351124e-05 tokens_per_second_per_gpu:3033.4757821864296 mfu:14.309422828911373 Step 1792 | loss:1.4969345331192017 lr:4.3269926303828314e-05 tokens_per_second_per_gpu:4361.375322382647 mfu:20.573351523040927 Step 1793 | loss:1.4677280187606812 lr:4.326246617418581e-05 tokens_per_second_per_gpu:3840.889204052059 mfu:18.118129698786568 Step 1794 | loss:1.314170479774475 lr:4.3255002556008775e-05 tokens_per_second_per_gpu:4338.356685663074 mfu:20.4647686862503 Step 1795 | loss:1.2990992069244385 lr:4.324753545072293e-05 tokens_per_second_per_gpu:5318.383558508405 mfu:25.087722655288363 Step 1796 | loss:1.4152014255523682 lr:4.3240064859754645e-05 tokens_per_second_per_gpu:3805.8357097364255 mfu:17.95277638535688 Step 1797 | loss:1.4586424827575684 lr:4.3232590784530985e-05 tokens_per_second_per_gpu:4514.916561245052 mfu:21.297631743591577 Step 1798 | loss:1.5128167867660522 lr:4.3225113226479645e-05 tokens_per_second_per_gpu:4292.963385334392 mfu:20.250640743704242 Step 1799 | loss:1.3396698236465454 lr:4.3217632187029014e-05 tokens_per_second_per_gpu:4776.675354045477 mfu:22.53239262988649 Step 1800 | loss:1.30548894405365 lr:4.321014766760814e-05 tokens_per_second_per_gpu:5030.284794872484 mfu:23.728711632499973 Step 1801 | loss:1.2549681663513184 lr:4.320265966964672e-05 tokens_per_second_per_gpu:4919.788476415177 mfu:23.207481645720907 Step 1802 | loss:1.3645998239517212 lr:4.319516819457514e-05 tokens_per_second_per_gpu:5308.163258653094 mfu:25.039511757107896 Step 1803 | loss:1.3397905826568604 lr:4.3187673243824423e-05 tokens_per_second_per_gpu:5124.142275070924 mfu:24.171453380333425 Step 1804 | loss:1.4443914890289307 lr:4.3180174818826275e-05 tokens_per_second_per_gpu:4414.769029791433 mfu:20.82521875079404 Step 1805 | loss:1.3446331024169922 lr:4.317267292101307e-05 tokens_per_second_per_gpu:5367.689606249653 mfu:25.320307694963038 Step 1806 | loss:1.2957770824432373 lr:4.316516755181782e-05 tokens_per_second_per_gpu:5356.4042328396745 mfu:25.26707266310492 Step 1807 | loss:1.2725193500518799 lr:4.315765871267424e-05 tokens_per_second_per_gpu:4434.93644000408 mfu:20.920351865682097 Step 1808 | loss:1.4295140504837036 lr:4.315014640501666e-05 tokens_per_second_per_gpu:5355.521188298823 mfu:25.26290719134279 Step 1809 | loss:1.5305818319320679 lr:4.3142630630280114e-05 tokens_per_second_per_gpu:5290.486659207609 mfu:24.95612822158468 Step 1810 | loss:1.601088523864746 lr:4.313511138990026e-05 tokens_per_second_per_gpu:3592.208936695513 mfu:16.945062448436968 Step 1811 | loss:1.458393931388855 lr:4.312758868531347e-05 tokens_per_second_per_gpu:5312.8114752779375 mfu:25.061438187994813 Step 1812 | loss:1.424933910369873 lr:4.3120062517956714e-05 tokens_per_second_per_gpu:4437.411134176577 mfu:20.932025420320127 Step 1813 | loss:1.3176391124725342 lr:4.311253288926769e-05 tokens_per_second_per_gpu:4313.958172484817 mfu:20.349676736772853 Step 1814 | loss:1.225135087966919 lr:4.3104999800684685e-05 tokens_per_second_per_gpu:5326.0227961900655 mfu:25.123758242821104 Step 1815 | loss:1.4793400764465332 lr:4.309746325364672e-05 tokens_per_second_per_gpu:4695.315046527039 mfu:22.148602177822145 Step 1816 | loss:1.328535556793213 lr:4.308992324959342e-05 tokens_per_second_per_gpu:4879.723174311276 mfu:23.018486779851376 Step 1817 | loss:1.391626000404358 lr:4.308237978996511e-05 tokens_per_second_per_gpu:3695.0411875224745 mfu:17.430139720578918 Step 1818 | loss:1.348053216934204 lr:4.307483287620273e-05 tokens_per_second_per_gpu:4562.065656636146 mfu:21.520042071016555 Step 1819 | loss:1.4080722332000732 lr:4.306728250974794e-05 tokens_per_second_per_gpu:5317.8913258224875 mfu:25.085400709725334 Step 1820 | loss:1.0785809755325317 lr:4.305972869204301e-05 tokens_per_second_per_gpu:4834.56997915344 mfu:22.805491454362365 Step 1821 | loss:1.4535331726074219 lr:4.305217142453088e-05 tokens_per_second_per_gpu:5268.59529408846 mfu:24.85286291726562 Step 1822 | loss:1.2911527156829834 lr:4.3044610708655165e-05 tokens_per_second_per_gpu:4688.9766731832715 mfu:22.11870298932158 Step 1823 | loss:1.3539613485336304 lr:4.303704654586013e-05 tokens_per_second_per_gpu:4402.813139492562 mfu:20.768820776369033 Step 1824 | loss:1.4291977882385254 lr:4.3029478937590695e-05 tokens_per_second_per_gpu:4816.532669827707 mfu:22.720406388790572 Step 1825 | loss:1.1928766965866089 lr:4.302190788529243e-05 tokens_per_second_per_gpu:4436.321384481645 mfu:20.926884885078657 Step 1826 | loss:1.473602294921875 lr:4.3014333390411596e-05 tokens_per_second_per_gpu:5320.523067629019 mfu:25.097815084848197 Step 1827 | loss:1.3535183668136597 lr:4.3006755454395066e-05 tokens_per_second_per_gpu:5305.581162526528 mfu:25.027331569127856 Step 1828 | loss:1.2812825441360474 lr:4.29991740786904e-05 tokens_per_second_per_gpu:4041.2966358647304 mfu:19.06348574768068 Step 1829 | loss:1.3522356748580933 lr:4.299158926474581e-05 tokens_per_second_per_gpu:5295.106429829069 mfu:24.977920467820255 Step 1830 | loss:1.3680009841918945 lr:4.298400101401017e-05 tokens_per_second_per_gpu:5175.54649886564 mfu:24.41393587443806 Step 1831 | loss:1.3734016418457031 lr:4.2976409327932995e-05 tokens_per_second_per_gpu:5341.197369973164 mfu:25.19533929640524 Step 1832 | loss:1.5985076427459717 lr:4.296881420796447e-05 tokens_per_second_per_gpu:4311.794643586446 mfu:20.339471001823146 Step 1833 | loss:1.3797173500061035 lr:4.296121565555542e-05 tokens_per_second_per_gpu:4139.55544522126 mfu:19.526989316097026 Step 1834 | loss:1.4082030057907104 lr:4.2953613672157354e-05 tokens_per_second_per_gpu:4624.818513587487 mfu:21.816058003997473 Step 1835 | loss:1.2371779680252075 lr:4.2946008259222406e-05 tokens_per_second_per_gpu:3736.485586738621 mfu:17.625640022825138 Step 1836 | loss:1.2129642963409424 lr:4.2938399418203374e-05 tokens_per_second_per_gpu:5330.841818321169 mfu:25.146490392423477 Step 1837 | loss:1.457729458808899 lr:4.2930787150553733e-05 tokens_per_second_per_gpu:3575.608398249967 mfu:16.866754876245405 Step 1838 | loss:1.1637225151062012 lr:4.2923171457727575e-05 tokens_per_second_per_gpu:5313.5238998708255 mfu:25.064798816351637 Step 1839 | loss:1.2440218925476074 lr:4.291555234117967e-05 tokens_per_second_per_gpu:5302.726527409747 mfu:25.013865768231025 Step 1840 | loss:1.3705626726150513 lr:4.2907929802365446e-05 tokens_per_second_per_gpu:4695.617054223251 mfu:22.150026799653 Step 1841 | loss:1.2428233623504639 lr:4.290030384274097e-05 tokens_per_second_per_gpu:3843.8630450022156 mfu:18.132157813938043 Step 1842 | loss:1.3996620178222656 lr:4.289267446376297e-05 tokens_per_second_per_gpu:4655.396309976589 mfu:21.9602986866749 Step 1843 | loss:1.4206281900405884 lr:4.288504166688883e-05 tokens_per_second_per_gpu:4498.031735212628 mfu:21.21798313834824 Step 1844 | loss:1.393239974975586 lr:4.287740545357657e-05 tokens_per_second_per_gpu:3757.890433257216 mfu:17.726610335896755 Step 1845 | loss:1.3549189567565918 lr:4.2869765825284894e-05 tokens_per_second_per_gpu:3792.4600547032137 mfu:17.889681138443148 Step 1846 | loss:1.4427860975265503 lr:4.2862122783473124e-05 tokens_per_second_per_gpu:4353.49552606804 mfu:20.53618117939304 Step 1847 | loss:1.4587472677230835 lr:4.2854476329601264e-05 tokens_per_second_per_gpu:5312.414798856033 mfu:25.05956699763271 Step 1848 | loss:1.346511960029602 lr:4.2846826465129944e-05 tokens_per_second_per_gpu:4428.933617537142 mfu:20.892035527918424 Step 1849 | loss:1.2785167694091797 lr:4.283917319152045e-05 tokens_per_second_per_gpu:5308.309275865427 mfu:25.040200545211572 Step 1850 | loss:1.3458939790725708 lr:4.2831516510234746e-05 tokens_per_second_per_gpu:3311.8201674954075 mfu:15.622420784863015 Step 1851 | loss:1.2949143648147583 lr:4.282385642273542e-05 tokens_per_second_per_gpu:5308.211122916277 mfu:25.039737541003813 Step 1852 | loss:1.322930097579956 lr:4.281619293048572e-05 tokens_per_second_per_gpu:5322.453072037262 mfu:25.106919244934588 Step 1853 | loss:1.5445350408554077 lr:4.2808526034949534e-05 tokens_per_second_per_gpu:4566.236764095362 mfu:21.539717896565993 Step 1854 | loss:1.3828262090682983 lr:4.2800855737591414e-05 tokens_per_second_per_gpu:4148.37959283833 mfu:19.568614325961573 Step 1855 | loss:1.4045058488845825 lr:4.2793182039876556e-05 tokens_per_second_per_gpu:3616.89917088119 mfu:17.061530495679143 Step 1856 | loss:1.3513697385787964 lr:4.27855049432708e-05 tokens_per_second_per_gpu:3899.6206864473966 mfu:18.395176121869564 Step 1857 | loss:1.4905468225479126 lr:4.277782444924065e-05 tokens_per_second_per_gpu:3987.831511256373 mfu:18.811281632812157 Step 1858 | loss:1.304094672203064 lr:4.277014055925325e-05 tokens_per_second_per_gpu:5358.314624097657 mfu:25.27608430461518 Step 1859 | loss:1.2953356504440308 lr:4.2762453274776384e-05 tokens_per_second_per_gpu:4437.664700481073 mfu:20.933221535841305 Step 1860 | loss:1.223490834236145 lr:4.2754762597278495e-05 tokens_per_second_per_gpu:4656.936075346228 mfu:21.96756202263455 Step 1861 | loss:1.3772557973861694 lr:4.274706852822869e-05 tokens_per_second_per_gpu:4827.852133979877 mfu:22.77380223249609 Step 1862 | loss:1.3359683752059937 lr:4.273937106909668e-05 tokens_per_second_per_gpu:5307.804877506108 mfu:25.03782121209143 Step 1863 | loss:1.4138883352279663 lr:4.273167022135286e-05 tokens_per_second_per_gpu:5017.809563667814 mfu:23.669863838413615 Step 1864 | loss:1.4128504991531372 lr:4.272396598646827e-05 tokens_per_second_per_gpu:5022.691864291053 mfu:23.69289448345982 Step 1865 | loss:1.4494765996932983 lr:4.2716258365914575e-05 tokens_per_second_per_gpu:4883.133376031082 mfu:23.034573283204114 Step 1866 | loss:1.2578097581863403 lr:4.2708547361164116e-05 tokens_per_second_per_gpu:5294.050063330277 mfu:24.972937406810743 Step 1867 | loss:1.2327942848205566 lr:4.2700832973689855e-05 tokens_per_second_per_gpu:4967.933104728416 mfu:23.434588071795076 Step 1868 | loss:1.416169285774231 lr:4.269311520496541e-05 tokens_per_second_per_gpu:4337.403962895875 mfu:20.460274530406156 Step 1869 | loss:1.3089463710784912 lr:4.268539405646505e-05 tokens_per_second_per_gpu:5323.348234169956 mfu:25.111141877444915 Step 1870 | loss:1.2970961332321167 lr:4.267766952966369e-05 tokens_per_second_per_gpu:3740.8082710476474 mfu:17.64603086223681 Step 1871 | loss:1.4037147760391235 lr:4.2669941626036876e-05 tokens_per_second_per_gpu:5324.027601796295 mfu:25.114346570450422 Step 1872 | loss:1.3863089084625244 lr:4.2662210347060814e-05 tokens_per_second_per_gpu:5325.8390283896815 mfu:25.122891378752676 Step 1873 | loss:1.2854650020599365 lr:4.2654475694212335e-05 tokens_per_second_per_gpu:4510.558240102611 mfu:21.277072799156418 Step 1874 | loss:1.3186155557632446 lr:4.264673766896895e-05 tokens_per_second_per_gpu:5333.485129211666 mfu:25.158959340889297 Step 1875 | loss:1.340346097946167 lr:4.2638996272808786e-05 tokens_per_second_per_gpu:5331.104386892253 mfu:25.1477289731721 Step 1876 | loss:1.270485758781433 lr:4.26312515072106e-05 tokens_per_second_per_gpu:3705.5360503567044 mfu:17.47964577917622 Step 1877 | loss:1.4302456378936768 lr:4.2623503373653844e-05 tokens_per_second_per_gpu:3877.426606612922 mfu:18.29048286058986 Step 1878 | loss:1.217349886894226 lr:4.261575187361857e-05 tokens_per_second_per_gpu:4838.255727130472 mfu:22.822877756423477 Step 1879 | loss:1.453369379043579 lr:4.260799700858548e-05 tokens_per_second_per_gpu:3420.415991100447 mfu:16.13468581316608 Step 1880 | loss:1.3688987493515015 lr:4.260023878003593e-05 tokens_per_second_per_gpu:5218.0887723402375 mfu:24.61461503687806 Step 1881 | loss:1.3450226783752441 lr:4.2592477189451915e-05 tokens_per_second_per_gpu:4918.543400192725 mfu:23.201608408747692 Step 1882 | loss:1.1931754350662231 lr:4.258471223831607e-05 tokens_per_second_per_gpu:4706.490898483907 mfu:22.20132057829965 Step 1883 | loss:1.2775418758392334 lr:4.2576943928111666e-05 tokens_per_second_per_gpu:5302.4596633801275 mfu:25.012606925071612 Step 1884 | loss:1.1726757287979126 lr:4.256917226032263e-05 tokens_per_second_per_gpu:5322.42375205353 mfu:25.106780937568818 Step 1885 | loss:1.4930442571640015 lr:4.256139723643351e-05 tokens_per_second_per_gpu:5098.078201530634 mfu:24.048504698454366 Step 1886 | loss:1.4419605731964111 lr:4.2553618857929526e-05 tokens_per_second_per_gpu:4714.516307307096 mfu:22.239177800994575 Step 1887 | loss:1.3555983304977417 lr:4.2545837126296505e-05 tokens_per_second_per_gpu:5175.865158182762 mfu:24.415439044805805 Step 1888 | loss:1.4150220155715942 lr:4.253805204302094e-05 tokens_per_second_per_gpu:4609.005955546907 mfu:21.741467469819455 Step 1889 | loss:1.4727121591567993 lr:4.2530263609589934e-05 tokens_per_second_per_gpu:4870.444988171094 mfu:22.97471999280635 Step 1890 | loss:1.2756015062332153 lr:4.2522471827491286e-05 tokens_per_second_per_gpu:4224.958205493556 mfu:19.92984870751489 Step 1891 | loss:1.292527675628662 lr:4.251467669821336e-05 tokens_per_second_per_gpu:4193.718133960847 mfu:19.78248395998927 Step 1892 | loss:1.5217180252075195 lr:4.250687822324522e-05 tokens_per_second_per_gpu:5023.289498496016 mfu:23.69571362597154 Step 1893 | loss:1.3744020462036133 lr:4.249907640407654e-05 tokens_per_second_per_gpu:4636.552000869797 mfu:21.87140686544749 Step 1894 | loss:1.3092584609985352 lr:4.249127124219765e-05 tokens_per_second_per_gpu:3676.486287920545 mfu:17.342613093364296 Step 1895 | loss:1.4441797733306885 lr:4.2483462739099486e-05 tokens_per_second_per_gpu:3653.788322768889 mfu:17.235542919071744 Step 1896 | loss:1.2659655809402466 lr:4.247565089627367e-05 tokens_per_second_per_gpu:4524.818140332774 mfu:21.344339181531957 Step 1897 | loss:1.3598339557647705 lr:4.2467835715212424e-05 tokens_per_second_per_gpu:3229.8185251092104 mfu:15.235605046804436 Step 1898 | loss:1.1302772760391235 lr:4.246001719740862e-05 tokens_per_second_per_gpu:4492.041736075908 mfu:21.1897272904211 Step 1899 | loss:1.2278575897216797 lr:4.245219534435576e-05 tokens_per_second_per_gpu:4655.822953675842 mfu:21.9623112377972 Step 1900 | loss:1.1891733407974243 lr:4.2444370157548014e-05 tokens_per_second_per_gpu:4295.939855125602 mfu:20.26468125954749 Step 1901 | loss:1.4256019592285156 lr:4.2436541638480146e-05 tokens_per_second_per_gpu:4769.6113380888355 mfu:22.49907046137361 Step 1902 | loss:1.2879565954208374 lr:4.242870978864758e-05 tokens_per_second_per_gpu:5305.062001290243 mfu:25.024882596998257 Step 1903 | loss:1.4014369249343872 lr:4.242087460954637e-05 tokens_per_second_per_gpu:4798.744331483956 mfu:22.636495761819617 Step 1904 | loss:1.3638654947280884 lr:4.241303610267322e-05 tokens_per_second_per_gpu:5351.791683154464 mfu:25.245314479257654 Step 1905 | loss:1.2831276655197144 lr:4.240519426952545e-05 tokens_per_second_per_gpu:5128.638506318933 mfu:24.192662870266435 Step 1906 | loss:1.35477876663208 lr:4.239734911160102e-05 tokens_per_second_per_gpu:4852.185081533116 mfu:22.88858489773368 Step 1907 | loss:1.346989393234253 lr:4.238950063039853e-05 tokens_per_second_per_gpu:5313.321428152733 mfu:25.063843722712157 Step 1908 | loss:1.3579264879226685 lr:4.238164882741722e-05 tokens_per_second_per_gpu:4145.58553220827 mfu:19.555434265253684 Step 1909 | loss:1.350023627281189 lr:4.237379370415695e-05 tokens_per_second_per_gpu:5192.277763023652 mfu:24.49286010211943 Step 1910 | loss:1.702903389930725 lr:4.236593526211823e-05 tokens_per_second_per_gpu:5299.08889829579 mfu:24.996706451056966 Step 1911 | loss:1.2617050409317017 lr:4.235807350280219e-05 tokens_per_second_per_gpu:3821.336976371323 mfu:18.0258985048625 Step 1912 | loss:1.3613752126693726 lr:4.2350208427710596e-05 tokens_per_second_per_gpu:4252.186344764135 mfu:20.058288486053808 Step 1913 | loss:1.4328296184539795 lr:4.2342340038345865e-05 tokens_per_second_per_gpu:5313.703223573144 mfu:25.065644716851253 Step 1914 | loss:1.400409460067749 lr:4.233446833621101e-05 tokens_per_second_per_gpu:3975.020540945474 mfu:18.750850100078722 Step 1915 | loss:1.2807368040084839 lr:4.232659332280973e-05 tokens_per_second_per_gpu:3569.3917399865836 mfu:16.837429838545752 Step 1916 | loss:1.403780460357666 lr:4.2318714999646306e-05 tokens_per_second_per_gpu:4342.110637096822 mfu:20.482476715653448 Step 1917 | loss:1.3605115413665771 lr:4.2310833368225665e-05 tokens_per_second_per_gpu:4178.49986051866 mfu:19.710696767657282 Step 1918 | loss:1.6401668787002563 lr:4.23029484300534e-05 tokens_per_second_per_gpu:4608.742712792335 mfu:21.74022570883229 Step 1919 | loss:1.39376699924469 lr:4.229506018663569e-05 tokens_per_second_per_gpu:4885.190694105071 mfu:23.04427800357378 Step 1920 | loss:1.2744579315185547 lr:4.2287168639479365e-05 tokens_per_second_per_gpu:3953.005743496719 mfu:18.647002544401186 Step 1921 | loss:1.3401278257369995 lr:4.227927379009188e-05 tokens_per_second_per_gpu:3031.173129858696 mfu:14.298560825008455 Step 1922 | loss:1.422353982925415 lr:4.227137563998135e-05 tokens_per_second_per_gpu:4139.528094548955 mfu:19.52686029830926 Step 1923 | loss:1.5240095853805542 lr:4.226347419065646e-05 tokens_per_second_per_gpu:5349.2016615670655 mfu:25.233096905526644 Step 1924 | loss:1.3677895069122314 lr:4.2255569443626585e-05 tokens_per_second_per_gpu:3730.1313111141553 mfu:17.595665820553318 Step 1925 | loss:1.3424791097640991 lr:4.224766140040171e-05 tokens_per_second_per_gpu:3659.7825748686587 mfu:17.263818828951226 Step 1926 | loss:1.3209528923034668 lr:4.223975006249242e-05 tokens_per_second_per_gpu:3778.3342702415994 mfu:17.82304740303036 Step 1927 | loss:1.322950005531311 lr:4.223183543140998e-05 tokens_per_second_per_gpu:5161.6975451255785 mfu:24.348607996771026 Step 1928 | loss:1.207518458366394 lr:4.2223917508666264e-05 tokens_per_second_per_gpu:5317.803112465396 mfu:25.08498459226918 Step 1929 | loss:1.2765475511550903 lr:4.221599629577374e-05 tokens_per_second_per_gpu:5095.135233806297 mfu:24.034622217576597 Step 1930 | loss:1.2911360263824463 lr:4.220807179424556e-05 tokens_per_second_per_gpu:4195.869612353658 mfu:19.792632850648225 Step 1931 | loss:1.189482569694519 lr:4.2200144005595476e-05 tokens_per_second_per_gpu:4731.465163750818 mfu:22.319128448612712 Step 1932 | loss:1.5333143472671509 lr:4.2192212931337864e-05 tokens_per_second_per_gpu:5312.605491360639 mfu:25.060466526712435 Step 1933 | loss:1.2989004850387573 lr:4.218427857298773e-05 tokens_per_second_per_gpu:4517.818202022835 mfu:21.311319278211347 Step 1934 | loss:1.3021152019500732 lr:4.217634093206073e-05 tokens_per_second_per_gpu:5319.108832704304 mfu:25.091143897414955 Step 1935 | loss:1.135865330696106 lr:4.216840001007312e-05 tokens_per_second_per_gpu:4062.8788552358255 mfu:19.16529275876047 Step 1936 | loss:1.2717162370681763 lr:4.216045580854178e-05 tokens_per_second_per_gpu:4728.682774217704 mfu:22.30600344246041 Step 1937 | loss:1.3946688175201416 lr:4.215250832898423e-05 tokens_per_second_per_gpu:3792.7263617015356 mfu:17.89093735399089 Step 1938 | loss:1.4263745546340942 lr:4.214455757291863e-05 tokens_per_second_per_gpu:4427.661657200298 mfu:20.886035473990713 Step 1939 | loss:1.361938238143921 lr:4.213660354186374e-05 tokens_per_second_per_gpu:4014.2068073905466 mfu:18.93569840476661 Step 1940 | loss:1.4660438299179077 lr:4.212864623733896e-05 tokens_per_second_per_gpu:4543.438428027027 mfu:21.432174255534424 Step 1941 | loss:1.3165439367294312 lr:4.21206856608643e-05 tokens_per_second_per_gpu:4370.319583940545 mfu:20.615543130857915 Step 1942 | loss:1.383856177330017 lr:4.211272181396042e-05 tokens_per_second_per_gpu:4443.646007059315 mfu:20.961436379487004 Step 1943 | loss:1.2556889057159424 lr:4.210475469814859e-05 tokens_per_second_per_gpu:5339.484956037612 mfu:25.1872615477033 Step 1944 | loss:1.3088358640670776 lr:4.2096784314950685e-05 tokens_per_second_per_gpu:3283.8817656494025 mfu:15.490630576572519 Step 1945 | loss:1.4196833372116089 lr:4.208881066588924e-05 tokens_per_second_per_gpu:4787.06675673743 mfu:22.581410649340555 Step 1946 | loss:1.4061018228530884 lr:4.208083375248742e-05 tokens_per_second_per_gpu:5181.532372834213 mfu:24.44217226324323 Step 1947 | loss:1.2655541896820068 lr:4.2072853576268945e-05 tokens_per_second_per_gpu:4240.221572112894 mfu:20.001848612057184 Step 1948 | loss:1.263735294342041 lr:4.2064870138758236e-05 tokens_per_second_per_gpu:5303.328409442335 mfu:25.016704948470405 Step 1949 | loss:1.3618453741073608 lr:4.20568834414803e-05 tokens_per_second_per_gpu:5283.331390920969 mfu:24.922375600261944 Step 1950 | loss:1.284566044807434 lr:4.204889348596076e-05 tokens_per_second_per_gpu:4157.404484155395 mfu:19.61118627810941 Step 1951 | loss:1.414075255393982 lr:4.2040900273725906e-05 tokens_per_second_per_gpu:4682.507897935552 mfu:22.088188672791222 Step 1952 | loss:1.2874592542648315 lr:4.203290380630258e-05 tokens_per_second_per_gpu:5009.734460943115 mfu:23.631772201106617 Step 1953 | loss:1.4200044870376587 lr:4.202490408521831e-05 tokens_per_second_per_gpu:4258.909750780463 mfu:20.090003939364177 Step 1954 | loss:1.2397348880767822 lr:4.2016901112001205e-05 tokens_per_second_per_gpu:5326.4226234838425 mfu:25.12564429638342 Step 1955 | loss:1.507203221321106 lr:4.200889488818002e-05 tokens_per_second_per_gpu:5320.9895993078535 mfu:25.100015794375768 Step 1956 | loss:1.3728053569793701 lr:4.200088541528412e-05 tokens_per_second_per_gpu:5303.0536837869095 mfu:25.015409020680732 Step 1957 | loss:1.4400396347045898 lr:4.199287269484349e-05 tokens_per_second_per_gpu:5328.537805557138 mfu:25.13562197111043 Step 1958 | loss:1.4312775135040283 lr:4.198485672838872e-05 tokens_per_second_per_gpu:4515.630191384045 mfu:21.300998058715063 Step 1959 | loss:1.2523146867752075 lr:4.197683751745106e-05 tokens_per_second_per_gpu:5331.997257946963 mfu:25.15194079827668 Step 1960 | loss:1.2841169834136963 lr:4.196881506356235e-05 tokens_per_second_per_gpu:5305.515463386776 mfu:25.027021655076215 Step 1961 | loss:1.4550669193267822 lr:4.196078936825505e-05 tokens_per_second_per_gpu:5298.448331846844 mfu:24.99368478982538 Step 1962 | loss:1.4436379671096802 lr:4.195276043306224e-05 tokens_per_second_per_gpu:4401.969764497151 mfu:20.76484243262107 Step 1963 | loss:1.4676449298858643 lr:4.194472825951765e-05 tokens_per_second_per_gpu:3926.1865857614202 mfu:18.520492001543627 Step 1964 | loss:1.260319471359253 lr:4.193669284915557e-05 tokens_per_second_per_gpu:5123.4018116453835 mfu:24.16796048801906 Step 1965 | loss:1.4152578115463257 lr:4.1928654203510966e-05 tokens_per_second_per_gpu:4919.627902831804 mfu:23.206724192731457 Step 1966 | loss:1.2788194417953491 lr:4.192061232411938e-05 tokens_per_second_per_gpu:5062.751449706565 mfu:23.88186238273485 Step 1967 | loss:1.2032495737075806 lr:4.1912567212516994e-05 tokens_per_second_per_gpu:5125.682111488959 mfu:24.178717051440476 Step 1968 | loss:1.3867384195327759 lr:4.1904518870240614e-05 tokens_per_second_per_gpu:4498.089214315102 mfu:21.21825427708156 Step 1969 | loss:1.4721660614013672 lr:4.189646729882763e-05 tokens_per_second_per_gpu:5040.060402911044 mfu:23.77482484350858 Step 1970 | loss:1.3205368518829346 lr:4.188841249981608e-05 tokens_per_second_per_gpu:4011.8135040850657 mfu:18.92440878473501 Step 1971 | loss:1.5961072444915771 lr:4.188035447474462e-05 tokens_per_second_per_gpu:5352.2164693927025 mfu:25.24731826841943 Step 1972 | loss:1.2113523483276367 lr:4.1872293225152494e-05 tokens_per_second_per_gpu:5287.6569267947625 mfu:24.94277989099115 Step 1973 | loss:1.4849498271942139 lr:4.186422875257958e-05 tokens_per_second_per_gpu:4184.043556629133 mfu:19.73684732806247 Step 1974 | loss:1.3875871896743774 lr:4.185616105856639e-05 tokens_per_second_per_gpu:5368.2077967565 mfu:25.322752087996253 Step 1975 | loss:1.2850770950317383 lr:4.1848090144654006e-05 tokens_per_second_per_gpu:4553.530474158527 mfu:21.47978015901733 Step 1976 | loss:1.2924336194992065 lr:4.184001601238417e-05 tokens_per_second_per_gpu:4216.062893349189 mfu:19.887888002433154 Step 1977 | loss:1.4354074001312256 lr:4.1831938663299194e-05 tokens_per_second_per_gpu:4874.298857998643 mfu:22.99289935432089 Step 1978 | loss:1.4990922212600708 lr:4.182385809894207e-05 tokens_per_second_per_gpu:5361.246208994466 mfu:25.289913090753387 Step 1979 | loss:1.4436008930206299 lr:4.181577432085633e-05 tokens_per_second_per_gpu:3880.048599532227 mfu:18.30285124854834 Step 1980 | loss:1.4387158155441284 lr:4.1807687330586165e-05 tokens_per_second_per_gpu:5366.202817680575 mfu:25.313294259610416 Step 1981 | loss:1.3247780799865723 lr:4.179959712967638e-05 tokens_per_second_per_gpu:5341.54033878705 mfu:25.196957138816856 Step 1982 | loss:1.4946802854537964 lr:4.1791503719672365e-05 tokens_per_second_per_gpu:5314.725451484445 mfu:25.070466740318928 Step 1983 | loss:1.3580708503723145 lr:4.1783407102120145e-05 tokens_per_second_per_gpu:3587.126089962524 mfu:16.92108579317438 Step 1984 | loss:1.2271947860717773 lr:4.177530727856636e-05 tokens_per_second_per_gpu:3888.461350774906 mfu:18.34253563152343 Step 1985 | loss:1.565720558166504 lr:4.176720425055825e-05 tokens_per_second_per_gpu:4531.242854919796 mfu:21.37464565640828 Step 1986 | loss:1.3906924724578857 lr:4.175909801964367e-05 tokens_per_second_per_gpu:4858.057164062278 mfu:22.916284512904323 Step 1987 | loss:1.3803229331970215 lr:4.1750988587371095e-05 tokens_per_second_per_gpu:4555.811622461782 mfu:21.49054072476782 Step 1988 | loss:1.3037995100021362 lr:4.174287595528961e-05 tokens_per_second_per_gpu:4151.087993038314 mfu:19.581390311805627 Step 1989 | loss:1.4818452596664429 lr:4.173476012494889e-05 tokens_per_second_per_gpu:5286.899457256986 mfu:24.93920677794383 Step 1990 | loss:1.3492013216018677 lr:4.1726641097899255e-05 tokens_per_second_per_gpu:5016.931309782717 mfu:23.66572096499205 Step 1991 | loss:1.2823338508605957 lr:4.17185188756916e-05 tokens_per_second_per_gpu:3569.9897262804725 mfu:16.84025064192101 Step 1992 | loss:1.2932708263397217 lr:4.171039345987747e-05 tokens_per_second_per_gpu:5337.673143922378 mfu:25.178714920828718 Step 1993 | loss:1.437387466430664 lr:4.1702264852008985e-05 tokens_per_second_per_gpu:4716.861046730406 mfu:22.25023833690813 Step 1994 | loss:1.4918805360794067 lr:4.16941330536389e-05 tokens_per_second_per_gpu:5353.871237082109 mfu:25.25512408994284 Step 1995 | loss:1.561711311340332 lr:4.1685998066320554e-05 tokens_per_second_per_gpu:3568.910178665499 mfu:16.835158231631365 Step 1996 | loss:1.472271203994751 lr:4.167785989160792e-05 tokens_per_second_per_gpu:4597.119871827542 mfu:21.68539878494021 Step 1997 | loss:1.263497233390808 lr:4.1669718531055554e-05 tokens_per_second_per_gpu:5306.690984597244 mfu:25.032566789190593 Step 1998 | loss:1.4612233638763428 lr:4.166157398621866e-05 tokens_per_second_per_gpu:4522.445825482735 mfu:21.33314856762567 Step 1999 | loss:1.4338138103485107 lr:4.165342625865302e-05 tokens_per_second_per_gpu:3794.2652349178975 mfu:17.898196481511313 Step 2000 | loss:1.3427108526229858 lr:4.1645275349915e-05 tokens_per_second_per_gpu:4095.671976391702 mfu:19.319983506336154 Step 2001 | loss:1.3891427516937256 lr:4.163712126156164e-05 tokens_per_second_per_gpu:3983.8845656597064 mfu:18.792663217014326 Step 2002 | loss:1.2932287454605103 lr:4.1628963995150546e-05 tokens_per_second_per_gpu:4037.7085252698635 mfu:19.046560017809895 Step 2003 | loss:1.3321436643600464 lr:4.1620803552239916e-05 tokens_per_second_per_gpu:4284.380825600795 mfu:20.21015534510518 Step 2004 | loss:1.1883141994476318 lr:4.161263993438859e-05 tokens_per_second_per_gpu:5316.430681617543 mfu:25.07851060179901 Step 2005 | loss:1.2687369585037231 lr:4.1604473143156e-05 tokens_per_second_per_gpu:4483.226293302748 mfu:21.148143342790473 Step 2006 | loss:1.3463218212127686 lr:4.159630318010218e-05 tokens_per_second_per_gpu:5344.667166886414 mfu:25.21170692045344 Step 2007 | loss:1.3503786325454712 lr:4.158813004678777e-05 tokens_per_second_per_gpu:5084.949405247003 mfu:23.98657392638085 Step 2008 | loss:1.4551424980163574 lr:4.1579953744774024e-05 tokens_per_second_per_gpu:5330.115046533988 mfu:25.143062085903292 Step 2009 | loss:1.4423574209213257 lr:4.157177427562279e-05 tokens_per_second_per_gpu:3779.8685426487355 mfu:17.830284827748688 Step 2010 | loss:1.2183560132980347 lr:4.1563591640896534e-05 tokens_per_second_per_gpu:5332.314666420275 mfu:25.15343806820076 Step 2011 | loss:1.38624906539917 lr:4.1555405842158326e-05 tokens_per_second_per_gpu:4158.55300965731 mfu:19.616604068860603 Step 2012 | loss:1.3110727071762085 lr:4.154721688097182e-05 tokens_per_second_per_gpu:4820.720083554001 mfu:22.74015913378395 Step 2013 | loss:1.3767038583755493 lr:4.153902475890129e-05 tokens_per_second_per_gpu:3587.487328862096 mfu:16.922789818697375 Step 2014 | loss:1.1685128211975098 lr:4.1530829477511624e-05 tokens_per_second_per_gpu:5308.892925203047 mfu:25.04295371871797 Step 2015 | loss:1.3746976852416992 lr:4.1522631038368295e-05 tokens_per_second_per_gpu:4687.749128618672 mfu:22.11291245216967 Step 2016 | loss:1.5408955812454224 lr:4.151442944303738e-05 tokens_per_second_per_gpu:3387.962078389167 mfu:15.981595169698481 Step 2017 | loss:1.3461698293685913 lr:4.150622469308558e-05 tokens_per_second_per_gpu:4481.783524809125 mfu:21.141337557644363 Step 2018 | loss:1.4274132251739502 lr:4.149801679008017e-05 tokens_per_second_per_gpu:3479.395505125864 mfu:16.41290224376672 Step 2019 | loss:1.6701443195343018 lr:4.1489805735589043e-05 tokens_per_second_per_gpu:4365.942699213159 mfu:20.5948966188253 Step 2020 | loss:1.315219521522522 lr:4.14815915311807e-05 tokens_per_second_per_gpu:3815.173328106578 mfu:17.996823524370864 Step 2021 | loss:1.1225299835205078 lr:4.147337417842423e-05 tokens_per_second_per_gpu:5331.670011036683 mfu:25.150397118766808 Step 2022 | loss:1.223073124885559 lr:4.146515367888932e-05 tokens_per_second_per_gpu:5301.322221969467 mfu:25.00724141987001 Step 2023 | loss:1.1459133625030518 lr:4.145693003414628e-05 tokens_per_second_per_gpu:4399.106457005756 mfu:20.751335722653522 Step 2024 | loss:1.304734468460083 lr:4.144870324576601e-05 tokens_per_second_per_gpu:4701.302993228456 mfu:22.176848344061785 Step 2025 | loss:1.3686301708221436 lr:4.144047331531999e-05 tokens_per_second_per_gpu:5301.595541223521 mfu:25.008530713424452 Step 2026 | loss:1.3188621997833252 lr:4.143224024438034e-05 tokens_per_second_per_gpu:3279.01986257046 mfu:15.467696150222947 Step 2027 | loss:1.4042768478393555 lr:4.142400403451975e-05 tokens_per_second_per_gpu:5066.102092315222 mfu:23.897667935598463 Step 2028 | loss:1.2228312492370605 lr:4.141576468731151e-05 tokens_per_second_per_gpu:4501.041845530907 mfu:21.232182342297346 Step 2029 | loss:1.2681282758712769 lr:4.140752220432953e-05 tokens_per_second_per_gpu:4811.003340712157 mfu:22.694323599951698 Step 2030 | loss:1.679134488105774 lr:4.1399276587148294e-05 tokens_per_second_per_gpu:3771.679255580717 mfu:17.791654563412393 Step 2031 | loss:1.249988317489624 lr:4.13910278373429e-05 tokens_per_second_per_gpu:4719.190086636089 mfu:22.261224815518418 Step 2032 | loss:1.4313656091690063 lr:4.1382775956489057e-05 tokens_per_second_per_gpu:4428.402445845517 mfu:20.889529900421792 Step 2033 | loss:1.442178726196289 lr:4.137452094616304e-05 tokens_per_second_per_gpu:5324.231915128593 mfu:25.115310351298323 Step 2034 | loss:1.4927899837493896 lr:4.136626280794174e-05 tokens_per_second_per_gpu:4142.005427213206 mfu:19.538546299163066 Step 2035 | loss:1.3649507761001587 lr:4.135800154340265e-05 tokens_per_second_per_gpu:4068.6458750919437 mfu:19.192496775376828 Step 2036 | loss:1.329469919204712 lr:4.1349737154123855e-05 tokens_per_second_per_gpu:4181.181187261712 mfu:19.72334504338577 Step 2037 | loss:1.3642233610153198 lr:4.1341469641684025e-05 tokens_per_second_per_gpu:2948.50426429828 mfu:13.90859768139707 Step 2038 | loss:1.1928921937942505 lr:4.1333199007662446e-05 tokens_per_second_per_gpu:5331.824085567137 mfu:25.151123914614786 Step 2039 | loss:1.3992146253585815 lr:4.1324925253639e-05 tokens_per_second_per_gpu:4145.970368455836 mfu:19.557249603493286 Step 2040 | loss:1.4895769357681274 lr:4.1316648381194135e-05 tokens_per_second_per_gpu:4655.73353991025 mfu:21.96188945780934 Step 2041 | loss:1.1631157398223877 lr:4.130836839190893e-05 tokens_per_second_per_gpu:4571.803855151624 mfu:21.56597881492206 Step 2042 | loss:1.4573681354522705 lr:4.1300085287365055e-05 tokens_per_second_per_gpu:4459.826519437769 mfu:21.03776261705626 Step 2043 | loss:1.3157879114151 lr:4.129179906914474e-05 tokens_per_second_per_gpu:4757.91690032688 mfu:22.44390580317364 Step 2044 | loss:1.3051656484603882 lr:4.128350973883086e-05 tokens_per_second_per_gpu:5324.8618209386805 mfu:25.118281724477516 Step 2045 | loss:1.3602572679519653 lr:4.127521729800685e-05 tokens_per_second_per_gpu:5072.1298210473 mfu:23.926101760464245 Step 2046 | loss:1.239646553993225 lr:4.126692174825675e-05 tokens_per_second_per_gpu:5299.948689639876 mfu:25.000762233522547 Step 2047 | loss:1.192996859550476 lr:4.1258623091165195e-05 tokens_per_second_per_gpu:5317.803723306629 mfu:25.0849874737115 Step 2048 | loss:1.4176404476165771 lr:4.1250321328317415e-05 tokens_per_second_per_gpu:5040.951186762998 mfu:23.779026822921644 Step 2049 | loss:1.3893471956253052 lr:4.124201646129922e-05 tokens_per_second_per_gpu:5324.981898799329 mfu:25.118848152233593 Step 2050 | loss:1.2583966255187988 lr:4.123370849169703e-05 tokens_per_second_per_gpu:5034.969087332871 mfu:23.750808239258326 Step 2051 | loss:1.2369410991668701 lr:4.1225397421097854e-05 tokens_per_second_per_gpu:5303.939459859223 mfu:25.019587377542816 Step 2052 | loss:1.2786530256271362 lr:4.1217083251089286e-05 tokens_per_second_per_gpu:3790.476901959786 mfu:17.88032626859165 Step 2053 | loss:1.3102055788040161 lr:4.120876598325951e-05 tokens_per_second_per_gpu:5323.07896197243 mfu:25.109871674546607 Step 2054 | loss:1.3304375410079956 lr:4.120044561919732e-05 tokens_per_second_per_gpu:5321.321002618326 mfu:25.101579080334503 Step 2055 | loss:1.6657147407531738 lr:4.1192122160492084e-05 tokens_per_second_per_gpu:3384.753000973052 mfu:15.966457404001602 Step 2056 | loss:1.456534743309021 lr:4.118379560873376e-05 tokens_per_second_per_gpu:3467.3501906364977 mfu:16.356082440177808 Step 2057 | loss:1.24036705493927 lr:4.117546596551292e-05 tokens_per_second_per_gpu:5063.522463655021 mfu:23.885499387078262 Step 2058 | loss:1.1057357788085938 lr:4.116713323242069e-05 tokens_per_second_per_gpu:3695.7877398251294 mfu:17.4336613351655 Step 2059 | loss:1.4429500102996826 lr:4.115879741104882e-05 tokens_per_second_per_gpu:4965.43790553633 mfu:23.42281779148113 Step 2060 | loss:1.293527603149414 lr:4.115045850298963e-05 tokens_per_second_per_gpu:4223.306432314084 mfu:19.92205701160575 Step 2061 | loss:1.3186322450637817 lr:4.114211650983604e-05 tokens_per_second_per_gpu:5332.613976129993 mfu:25.154849963169003 Step 2062 | loss:1.2474172115325928 lr:4.113377143318154e-05 tokens_per_second_per_gpu:5347.761535937135 mfu:25.22630358721949 Step 2063 | loss:1.6154835224151611 lr:4.1125423274620245e-05 tokens_per_second_per_gpu:5322.526225259204 mfu:25.10726432116371 Step 2064 | loss:1.3452560901641846 lr:4.111707203574683e-05 tokens_per_second_per_gpu:5042.003932114279 mfu:23.78399280236052 Step 2065 | loss:1.2682826519012451 lr:4.110871771815657e-05 tokens_per_second_per_gpu:4775.867298101953 mfu:22.52858089213233 Step 2066 | loss:1.204865574836731 lr:4.1100360323445305e-05 tokens_per_second_per_gpu:3429.5233807438326 mfu:16.177646923994832 Step 2067 | loss:1.3661224842071533 lr:4.1091999853209514e-05 tokens_per_second_per_gpu:5314.529753289824 mfu:25.069543598545344 Step 2068 | loss:1.3674896955490112 lr:4.1083636309046204e-05 tokens_per_second_per_gpu:5316.272052439907 mfu:25.077762320903176 Step 2069 | loss:1.4208488464355469 lr:4.1075269692553e-05 tokens_per_second_per_gpu:4383.854411247278 mfu:20.679389220543438 Step 2070 | loss:1.3047192096710205 lr:4.1066900005328133e-05 tokens_per_second_per_gpu:4651.570651690637 mfu:21.942252403815456 Step 2071 | loss:1.3905805349349976 lr:4.1058527248970367e-05 tokens_per_second_per_gpu:3727.9633287123197 mfu:17.58543907766792 Step 2072 | loss:1.2640681266784668 lr:4.105015142507911e-05 tokens_per_second_per_gpu:5319.440445708855 mfu:25.092708172536437 Step 2073 | loss:1.1725856065750122 lr:4.1041772535254316e-05 tokens_per_second_per_gpu:4913.409606397977 mfu:23.17739142750232 Step 2074 | loss:1.3125241994857788 lr:4.103339058109654e-05 tokens_per_second_per_gpu:4408.599501174182 mfu:20.796116031676334 Step 2075 | loss:1.1856763362884521 lr:4.102500556420691e-05 tokens_per_second_per_gpu:5316.954378058033 mfu:25.08098096726063 Step 2076 | loss:1.462852954864502 lr:4.101661748618718e-05 tokens_per_second_per_gpu:4582.24951015676 mfu:21.615252751793808 Step 2077 | loss:1.2823913097381592 lr:4.1008226348639624e-05 tokens_per_second_per_gpu:5308.656466590674 mfu:25.041838303099414 Step 2078 | loss:1.314624547958374 lr:4.099983215316715e-05 tokens_per_second_per_gpu:4537.0791488290315 mfu:21.402176450552567 Step 2079 | loss:1.3504889011383057 lr:4.0991434901373236e-05 tokens_per_second_per_gpu:4354.29364716235 mfu:20.5399460527684 Step 2080 | loss:1.4268347024917603 lr:4.0983034594861945e-05 tokens_per_second_per_gpu:4851.094059558056 mfu:22.883438360929777 Step 2081 | loss:1.301466703414917 lr:4.097463123523791e-05 tokens_per_second_per_gpu:4476.308153099093 mfu:21.115509295093396 Step 2082 | loss:1.5677274465560913 lr:4.096622482410637e-05 tokens_per_second_per_gpu:3863.1332929765417 mfu:18.223058861476275 Step 2083 | loss:1.3854645490646362 lr:4.095781536307313e-05 tokens_per_second_per_gpu:4110.423408620092 mfu:19.38956852901134 Step 2084 | loss:1.445363998413086 lr:4.0949402853744576e-05 tokens_per_second_per_gpu:3514.0051872486238 mfu:16.576162019360456 Step 2085 | loss:1.2780061960220337 lr:4.09409872977277e-05 tokens_per_second_per_gpu:3949.019245796492 mfu:18.628197554582574 Step 2086 | loss:1.2346761226654053 lr:4.0932568696630044e-05 tokens_per_second_per_gpu:5345.353247578593 mfu:25.214943280135888 Step 2087 | loss:1.373577356338501 lr:4.0924147052059755e-05 tokens_per_second_per_gpu:4335.110827216485 mfu:20.449457418157177 Step 2088 | loss:1.2807766199111938 lr:4.0915722365625545e-05 tokens_per_second_per_gpu:4674.89171565197 mfu:22.052261841504873 Step 2089 | loss:1.3638715744018555 lr:4.0907294638936736e-05 tokens_per_second_per_gpu:5354.0372996982 mfu:25.255907435636146 Step 2090 | loss:1.2601016759872437 lr:4.089886387360318e-05 tokens_per_second_per_gpu:4192.591725609458 mfu:19.777170499610687 Step 2091 | loss:1.401660442352295 lr:4.0890430071235355e-05 tokens_per_second_per_gpu:5334.428113185839 mfu:25.163407557185124 Step 2092 | loss:1.2695884704589844 lr:4.0881993233444306e-05 tokens_per_second_per_gpu:3505.53051877644 mfu:16.536185562249624 Step 2093 | loss:1.3073846101760864 lr:4.0873553361841646e-05 tokens_per_second_per_gpu:5313.839637652503 mfu:25.066288205338232 Step 2094 | loss:1.3022352457046509 lr:4.086511045803959e-05 tokens_per_second_per_gpu:4952.1103932136975 mfu:23.359949641947193 Step 2095 | loss:1.5728709697723389 lr:4.085666452365091e-05 tokens_per_second_per_gpu:3683.8947625757232 mfu:17.377560132328888 Step 2096 | loss:1.313065767288208 lr:4.084821556028897e-05 tokens_per_second_per_gpu:3515.6579520369432 mfu:16.58395839285771 Step 2097 | loss:1.5844330787658691 lr:4.083976356956771e-05 tokens_per_second_per_gpu:4967.550581953862 mfu:23.432783646602395 Step 2098 | loss:1.3788535594940186 lr:4.0831308553101644e-05 tokens_per_second_per_gpu:5304.912412985384 mfu:25.024176963441846 Step 2099 | loss:1.475028157234192 lr:4.082285051250586e-05 tokens_per_second_per_gpu:4400.3922618033985 mfu:20.757401083264924 Step 2100 | loss:1.309264898300171 lr:4.081438944939604e-05 tokens_per_second_per_gpu:4811.165977694001 mfu:22.695090786343787 Step 2101 | loss:1.2844629287719727 lr:4.080592536538843e-05 tokens_per_second_per_gpu:3664.147305050612 mfu:17.28440800591926 Step 2102 | loss:1.2661457061767578 lr:4.079745826209987e-05 tokens_per_second_per_gpu:5182.232314298369 mfu:24.44547400655198 Step 2103 | loss:1.2210955619812012 lr:4.078898814114773e-05 tokens_per_second_per_gpu:5345.469982884844 mfu:25.21549394049257 Step 2104 | loss:1.4043666124343872 lr:4.0780515004150036e-05 tokens_per_second_per_gpu:3944.9230855415335 mfu:18.608875267782924 Step 2105 | loss:1.4161124229431152 lr:4.0772038852725306e-05 tokens_per_second_per_gpu:4519.666461700209 mfu:21.320037834455135 Step 2106 | loss:1.362245798110962 lr:4.076355968849269e-05 tokens_per_second_per_gpu:2945.7232564838864 mfu:13.895479193047715 Step 2107 | loss:1.355181336402893 lr:4.0755077513071894e-05 tokens_per_second_per_gpu:4961.3430911874275 mfu:23.403501853549987 Step 2108 | loss:1.271546721458435 lr:4.07465923280832e-05 tokens_per_second_per_gpu:4341.0790644471945 mfu:20.47761061146071 Step 2109 | loss:1.3275827169418335 lr:4.073810413514747e-05 tokens_per_second_per_gpu:5232.8896141141795 mfu:24.684433132809747 Step 2110 | loss:1.1718249320983887 lr:4.072961293588613e-05 tokens_per_second_per_gpu:4199.042444330458 mfu:19.80759964042375 Step 2111 | loss:1.3042018413543701 lr:4.0721118731921185e-05 tokens_per_second_per_gpu:5283.139625704293 mfu:24.92147101101637 Step 2112 | loss:1.7376645803451538 lr:4.071262152487522e-05 tokens_per_second_per_gpu:3077.119427715448 mfu:14.515297351245527 Step 2113 | loss:1.556727647781372 lr:4.070412131637139e-05 tokens_per_second_per_gpu:4487.762300111529 mfu:21.169540460830056 Step 2114 | loss:1.1559181213378906 lr:4.0695618108033414e-05 tokens_per_second_per_gpu:5323.857086289036 mfu:25.113542219709736 Step 2115 | loss:1.359858512878418 lr:4.068711190148561e-05 tokens_per_second_per_gpu:5346.5476798669515 mfu:25.220577621031236 Step 2116 | loss:1.2577877044677734 lr:4.067860269835284e-05 tokens_per_second_per_gpu:5307.87342633717 mfu:25.03814456862319 Step 2117 | loss:1.363007664680481 lr:4.067009050026055e-05 tokens_per_second_per_gpu:4329.539995340465 mfu:20.423178853716063 Step 2118 | loss:1.3605477809906006 lr:4.0661575308834754e-05 tokens_per_second_per_gpu:5320.791868872666 mfu:25.0990830661767 Step 2119 | loss:1.2622510194778442 lr:4.0653057125702055e-05 tokens_per_second_per_gpu:4447.412061078531 mfu:20.979201498850728 Step 2120 | loss:1.3264644145965576 lr:4.0644535952489595e-05 tokens_per_second_per_gpu:4725.263928947843 mfu:22.28987616600732 Step 2121 | loss:1.3176518678665161 lr:4.063601179082513e-05 tokens_per_second_per_gpu:5278.809617790434 mfu:24.90104562491116 Step 2122 | loss:1.2459908723831177 lr:4.062748464233694e-05 tokens_per_second_per_gpu:5166.319315955023 mfu:24.370409678328933 Step 2123 | loss:1.431668758392334 lr:4.0618954508653916e-05 tokens_per_second_per_gpu:3791.7733254777795 mfu:17.886441719518686 Step 2124 | loss:1.393695592880249 lr:4.061042139140549e-05 tokens_per_second_per_gpu:4769.277314703917 mfu:22.497494816076685 Step 2125 | loss:1.175115704536438 lr:4.060188529222168e-05 tokens_per_second_per_gpu:4919.8298274844465 mfu:23.207676705769874 Step 2126 | loss:1.326676607131958 lr:4.059334621273308e-05 tokens_per_second_per_gpu:4152.603779129346 mfu:19.588540533416797 Step 2127 | loss:1.4509490728378296 lr:4.058480415457083e-05 tokens_per_second_per_gpu:3746.3025734474872 mfu:17.67194842408151 Step 2128 | loss:1.3230679035186768 lr:4.057625911936664e-05 tokens_per_second_per_gpu:5027.32236667593 mfu:23.71473735325446 Step 2129 | loss:1.296797513961792 lr:4.0567711108752835e-05 tokens_per_second_per_gpu:5085.97603498216 mfu:23.991416714002682 Step 2130 | loss:1.351670265197754 lr:4.055916012436225e-05 tokens_per_second_per_gpu:5079.681898642082 mfu:23.961726198996143 Step 2131 | loss:1.4125207662582397 lr:4.055060616782832e-05 tokens_per_second_per_gpu:4139.115884806358 mfu:19.52491583462319 Step 2132 | loss:1.323837161064148 lr:4.054204924078503e-05 tokens_per_second_per_gpu:4105.078816270989 mfu:19.36435717501913 Step 2133 | loss:1.3979560136795044 lr:4.053348934486695e-05 tokens_per_second_per_gpu:3689.467475674227 mfu:17.403847570817433 Step 2134 | loss:1.466706395149231 lr:4.05249264817092e-05 tokens_per_second_per_gpu:4862.831725860711 mfu:22.938806935531776 Step 2135 | loss:1.3775951862335205 lr:4.05163606529475e-05 tokens_per_second_per_gpu:4987.746043416437 mfu:23.528049084022395 Step 2136 | loss:1.3652777671813965 lr:4.050779186021808e-05 tokens_per_second_per_gpu:5292.910124270102 mfu:24.967560119770237 Step 2137 | loss:1.4505730867385864 lr:4.04992201051578e-05 tokens_per_second_per_gpu:4707.541910850942 mfu:22.20627838295616 Step 2138 | loss:1.2516928911209106 lr:4.049064538940403e-05 tokens_per_second_per_gpu:5306.544600183106 mfu:25.031876268933345 Step 2139 | loss:1.3832136392593384 lr:4.048206771459474e-05 tokens_per_second_per_gpu:5046.437012343071 mfu:23.804904398161206 Step 2140 | loss:1.3937013149261475 lr:4.0473487082368454e-05 tokens_per_second_per_gpu:5320.310137877669 mfu:25.096810658881516 Step 2141 | loss:1.4534331560134888 lr:4.046490349436427e-05 tokens_per_second_per_gpu:3967.0711706115358 mfu:18.713351563911104 Step 2142 | loss:1.256292700767517 lr:4.0456316952221833e-05 tokens_per_second_per_gpu:5319.957862585949 mfu:25.095148916226112 Step 2143 | loss:1.4905925989151 lr:4.0447727457581363e-05 tokens_per_second_per_gpu:4369.657079774598 mfu:20.612417985672273 Step 2144 | loss:1.2484869956970215 lr:4.0439135012083656e-05 tokens_per_second_per_gpu:4838.4026917877245 mfu:22.82357101378649 Step 2145 | loss:1.4397975206375122 lr:4.043053961737004e-05 tokens_per_second_per_gpu:4226.657829867093 mfu:19.937866125670677 Step 2146 | loss:1.453647255897522 lr:4.042194127508244e-05 tokens_per_second_per_gpu:5112.113049762237 mfu:24.11470947215487 Step 2147 | loss:1.3256914615631104 lr:4.0413339986863316e-05 tokens_per_second_per_gpu:4677.370236414694 mfu:22.06395344682189 Step 2148 | loss:1.3697773218154907 lr:4.040473575435572e-05 tokens_per_second_per_gpu:4227.859231891678 mfu:19.943533344000972 Step 2149 | loss:1.3699586391448975 lr:4.039612857920323e-05 tokens_per_second_per_gpu:4987.412197584931 mfu:23.526474276275206 Step 2150 | loss:1.4663423299789429 lr:4.038751846305003e-05 tokens_per_second_per_gpu:3793.732329864264 mfu:17.89568267745035 Step 2151 | loss:1.3599846363067627 lr:4.037890540754083e-05 tokens_per_second_per_gpu:4411.885828080522 mfu:20.81161819639873 Step 2152 | loss:1.3731744289398193 lr:4.037028941432091e-05 tokens_per_second_per_gpu:4810.642845738449 mfu:22.692623083653928 Step 2153 | loss:1.4491640329360962 lr:4.036167048503612e-05 tokens_per_second_per_gpu:4899.6304157075765 mfu:23.11239263404335 Step 2154 | loss:1.2318092584609985 lr:4.0353048621332876e-05 tokens_per_second_per_gpu:4774.041047589096 mfu:22.519966156872712 Step 2155 | loss:1.1525160074234009 lr:4.034442382485812e-05 tokens_per_second_per_gpu:4768.384988165813 mfu:22.49328555954984 Step 2156 | loss:1.314204216003418 lr:4.03357960972594e-05 tokens_per_second_per_gpu:5249.833126179172 mfu:24.76435857008157 Step 2157 | loss:1.309501051902771 lr:4.03271654401848e-05 tokens_per_second_per_gpu:4565.103992929301 mfu:21.534374421704996 Step 2158 | loss:1.4152076244354248 lr:4.031853185528296e-05 tokens_per_second_per_gpu:4166.909197478496 mfu:19.656021632525793 Step 2159 | loss:1.4528669118881226 lr:4.0309895344203085e-05 tokens_per_second_per_gpu:4419.012508083181 mfu:20.84523596190827 Step 2160 | loss:1.5311510562896729 lr:4.0301255908594946e-05 tokens_per_second_per_gpu:3988.657272911167 mfu:18.815176891427292 Step 2161 | loss:1.2376567125320435 lr:4.029261355010886e-05 tokens_per_second_per_gpu:4352.817793787463 mfu:20.53298420059251 Step 2162 | loss:1.2196807861328125 lr:4.0283968270395714e-05 tokens_per_second_per_gpu:5108.155971838933 mfu:24.09604326044353 Step 2163 | loss:1.4083503484725952 lr:4.027532007110694e-05 tokens_per_second_per_gpu:4649.189526435362 mfu:21.93102022972446 Step 2164 | loss:1.3832216262817383 lr:4.026666895389454e-05 tokens_per_second_per_gpu:3457.4045421925903 mfu:16.30916711956529 Step 2165 | loss:1.3588968515396118 lr:4.025801492041106e-05 tokens_per_second_per_gpu:3823.903247981933 mfu:18.038004045900834 Step 2166 | loss:1.4048856496810913 lr:4.0249357972309625e-05 tokens_per_second_per_gpu:4140.746541749461 mfu:19.532607921642576 Step 2167 | loss:1.414363145828247 lr:4.0240698111243904e-05 tokens_per_second_per_gpu:5305.726163366559 mfu:25.028015562829978 Step 2168 | loss:1.2875374555587769 lr:4.02320353388681e-05 tokens_per_second_per_gpu:4444.746208078886 mfu:20.966626215409978 Step 2169 | loss:1.335841178894043 lr:4.022336965683702e-05 tokens_per_second_per_gpu:5342.002076671021 mfu:25.199135235196152 Step 2170 | loss:1.336950421333313 lr:4.021470106680599e-05 tokens_per_second_per_gpu:4222.37631231465 mfu:19.917669476873584 Step 2171 | loss:1.3011573553085327 lr:4.0206029570430896e-05 tokens_per_second_per_gpu:4538.443678597536 mfu:21.408613170283385 Step 2172 | loss:1.413191556930542 lr:4.01973551693682e-05 tokens_per_second_per_gpu:4477.190421101079 mfu:21.119671103789205 Step 2173 | loss:1.3958443403244019 lr:4.0188677865274893e-05 tokens_per_second_per_gpu:5332.606184884518 mfu:25.154813210534776 Step 2174 | loss:1.3546921014785767 lr:4.0179997659808535e-05 tokens_per_second_per_gpu:5319.747146533169 mfu:25.094154932653282 Step 2175 | loss:1.2816839218139648 lr:4.017131455462723e-05 tokens_per_second_per_gpu:4011.4081311121104 mfu:18.922496571257817 Step 2176 | loss:1.2001336812973022 lr:4.016262855138966e-05 tokens_per_second_per_gpu:3386.6063009492473 mfu:15.975199736194895 Step 2177 | loss:1.515462875366211 lr:4.0153939651755026e-05 tokens_per_second_per_gpu:3404.700268748965 mfu:16.060552069455408 Step 2178 | loss:1.2960939407348633 lr:4.0145247857383105e-05 tokens_per_second_per_gpu:4188.766941218443 mfu:19.759128339062762 Step 2179 | loss:1.3659316301345825 lr:4.0136553169934226e-05 tokens_per_second_per_gpu:4489.204557817872 mfu:21.176343836505417 Step 2180 | loss:1.2813217639923096 lr:4.012785559106926e-05 tokens_per_second_per_gpu:3947.1693432001866 mfu:18.61947124840987 Step 2181 | loss:1.4427663087844849 lr:4.0119155122449655e-05 tokens_per_second_per_gpu:4242.802647321207 mfu:20.014023984191635 Step 2182 | loss:1.3165634870529175 lr:4.011045176573737e-05 tokens_per_second_per_gpu:5315.091570142307 mfu:25.072193784494345 Step 2183 | loss:1.4005582332611084 lr:4.010174552259494e-05 tokens_per_second_per_gpu:4251.703277704116 mfu:20.056009776311956 Step 2184 | loss:1.4054964780807495 lr:4.009303639468547e-05 tokens_per_second_per_gpu:5175.67513597503 mfu:24.414542677630802 Step 2185 | loss:1.3219820261001587 lr:4.008432438367257e-05 tokens_per_second_per_gpu:4394.568214605171 mfu:20.729928058945966 Step 2186 | loss:1.3080154657363892 lr:4.0075609491220445e-05 tokens_per_second_per_gpu:5306.102582737422 mfu:25.029791197226103 Step 2187 | loss:1.3858623504638672 lr:4.0066891718993824e-05 tokens_per_second_per_gpu:4850.4060614804985 mfu:22.88019295661336 Step 2188 | loss:1.4193201065063477 lr:4.0058171068658e-05 tokens_per_second_per_gpu:5350.325168904165 mfu:25.238396681325863 Step 2189 | loss:1.3373404741287231 lr:4.00494475418788e-05 tokens_per_second_per_gpu:4981.381640428248 mfu:23.498027109247985 Step 2190 | loss:1.2342264652252197 lr:4.0040721140322624e-05 tokens_per_second_per_gpu:5163.781645345265 mfu:24.358439053091455 Step 2191 | loss:1.4664465188980103 lr:4.00319918656564e-05 tokens_per_second_per_gpu:4987.10232897825 mfu:23.52501257318846 Step 2192 | loss:1.5686570405960083 lr:4.0023259719547605e-05 tokens_per_second_per_gpu:4174.127683959676 mfu:19.69007246485831 Step 2193 | loss:1.2720751762390137 lr:4.0014524703664286e-05 tokens_per_second_per_gpu:4876.241337020704 mfu:23.002062359289052 Step 2194 | loss:1.34590482711792 lr:4.000578681967502e-05 tokens_per_second_per_gpu:3957.5500934367687 mfu:18.66843901841445 Step 2195 | loss:1.4959794282913208 lr:3.9997046069248924e-05 tokens_per_second_per_gpu:5316.347290124202 mfu:25.078117229896865 Step 2196 | loss:1.2264149188995361 lr:3.998830245405568e-05 tokens_per_second_per_gpu:4379.986112739883 mfu:20.66114179648427 Step 2197 | loss:1.2488269805908203 lr:3.9979555975765526e-05 tokens_per_second_per_gpu:5345.0481343523115 mfu:25.213504008989833 Step 2198 | loss:1.4311712980270386 lr:3.997080663604922e-05 tokens_per_second_per_gpu:3575.3487673330346 mfu:16.865530152912633 Step 2199 | loss:1.3254677057266235 lr:3.9962054436578076e-05 tokens_per_second_per_gpu:4032.512547078813 mfu:19.02204970215742 Step 2200 | loss:1.340269923210144 lr:3.995329937902397e-05 tokens_per_second_per_gpu:4380.969089605897 mfu:20.66577866607441 Step 2201 | loss:1.3571275472640991 lr:3.99445414650593e-05 tokens_per_second_per_gpu:5249.941442559637 mfu:24.764869516928908 Step 2202 | loss:1.4174526929855347 lr:3.9935780696357024e-05 tokens_per_second_per_gpu:5309.340671467942 mfu:25.045065814242875 Step 2203 | loss:1.2521917819976807 lr:3.992701707459064e-05 tokens_per_second_per_gpu:4737.139917828915 mfu:22.34589723181198 Step 2204 | loss:1.544657826423645 lr:3.99182506014342e-05 tokens_per_second_per_gpu:3439.0555496173697 mfu:16.222611790927022 Step 2205 | loss:1.3526359796524048 lr:3.990948127856229e-05 tokens_per_second_per_gpu:5328.583184411428 mfu:25.13583603090855 Step 2206 | loss:1.279001235961914 lr:3.990070910765006e-05 tokens_per_second_per_gpu:4539.187800366829 mfu:21.41212331962941 Step 2207 | loss:1.2408255338668823 lr:3.9891934090373153e-05 tokens_per_second_per_gpu:5306.99719749697 mfu:25.03401124768391 Step 2208 | loss:1.2654213905334473 lr:3.988315622840782e-05 tokens_per_second_per_gpu:3442.1514876872357 mfu:16.23721585902408 Step 2209 | loss:1.492872714996338 lr:3.987437552343082e-05 tokens_per_second_per_gpu:5332.296228168497 mfu:25.153351091821232 Step 2210 | loss:1.2597436904907227 lr:3.9865591977119456e-05 tokens_per_second_per_gpu:5319.024895397668 mfu:25.090747950818376 Step 2211 | loss:1.3324470520019531 lr:3.9856805591151586e-05 tokens_per_second_per_gpu:3093.4517448491088 mfu:14.59233967774565 Step 2212 | loss:1.5098894834518433 lr:3.98480163672056e-05 tokens_per_second_per_gpu:4926.694777071875 mfu:23.24005984425495 Step 2213 | loss:1.2221485376358032 lr:3.983922430696043e-05 tokens_per_second_per_gpu:5316.511567891198 mfu:25.07889215615246 Step 2214 | loss:1.482353925704956 lr:3.983042941209557e-05 tokens_per_second_per_gpu:4419.228837442351 mfu:20.846256424405063 Step 2215 | loss:1.3695391416549683 lr:3.9821631684291026e-05 tokens_per_second_per_gpu:3915.1446048476905 mfu:18.46840509361735 Step 2216 | loss:1.4084256887435913 lr:3.9812831125227354e-05 tokens_per_second_per_gpu:4754.039896826946 mfu:22.425617316179437 Step 2217 | loss:1.462253212928772 lr:3.980402773658567e-05 tokens_per_second_per_gpu:3688.6687918691123 mfu:17.400080043039196 Step 2218 | loss:1.1904736757278442 lr:3.9795221520047607e-05 tokens_per_second_per_gpu:3854.8539620701267 mfu:18.184003844991203 Step 2219 | loss:1.404293417930603 lr:3.978641247729534e-05 tokens_per_second_per_gpu:4252.250973956882 mfu:20.05859335298287 Step 2220 | loss:1.3797208070755005 lr:3.9777600610011604e-05 tokens_per_second_per_gpu:5216.933009694659 mfu:24.60916310728542 Step 2221 | loss:1.3287538290023804 lr:3.976878591987965e-05 tokens_per_second_per_gpu:5329.059905993397 mfu:25.13808480794778 Step 2222 | loss:1.3971192836761475 lr:3.975996840858329e-05 tokens_per_second_per_gpu:5347.262953256747 mfu:25.22395168764913 Step 2223 | loss:1.296210765838623 lr:3.975114807780685e-05 tokens_per_second_per_gpu:5303.885871153656 mfu:25.01933459047548 Step 2224 | loss:1.459945559501648 lr:3.974232492923522e-05 tokens_per_second_per_gpu:5064.686093620629 mfu:23.89098842816178 Step 2225 | loss:1.3138504028320312 lr:3.9733498964553805e-05 tokens_per_second_per_gpu:4540.905403790098 mfu:21.42022554803033 Step 2226 | loss:1.263269066810608 lr:3.9724670185448574e-05 tokens_per_second_per_gpu:5329.04447343141 mfu:25.138012009919827 Step 2227 | loss:1.35727059841156 lr:3.9715838593606e-05 tokens_per_second_per_gpu:4569.742214465028 mfu:21.556253704051215 Step 2228 | loss:1.2202519178390503 lr:3.9707004190713136e-05 tokens_per_second_per_gpu:5334.47085549341 mfu:25.163609179942533 Step 2229 | loss:1.332971453666687 lr:3.969816697845752e-05 tokens_per_second_per_gpu:3623.8918317709863 mfu:17.094516070167288 Step 2230 | loss:1.5366510152816772 lr:3.968932695852728e-05 tokens_per_second_per_gpu:4454.74957355002 mfu:21.013813797087455 Step 2231 | loss:1.319013237953186 lr:3.968048413261104e-05 tokens_per_second_per_gpu:2991.115701165953 mfu:14.1096030993627 Step 2232 | loss:1.493322730064392 lr:3.967163850239798e-05 tokens_per_second_per_gpu:5163.122898613043 mfu:24.355331632361775 Step 2233 | loss:1.3394036293029785 lr:3.966279006957781e-05 tokens_per_second_per_gpu:3925.2847952875995 mfu:18.516238102017294 Step 2234 | loss:1.3725385665893555 lr:3.9653938835840776e-05 tokens_per_second_per_gpu:5334.76676414562 mfu:25.165005031542226 Step 2235 | loss:1.3999580144882202 lr:3.964508480287766e-05 tokens_per_second_per_gpu:4491.897395634338 mfu:21.189046411931194 Step 2236 | loss:1.3762538433074951 lr:3.963622797237978e-05 tokens_per_second_per_gpu:4992.216008373942 mfu:23.54913467138161 Step 2237 | loss:1.3226019144058228 lr:3.9627368346038985e-05 tokens_per_second_per_gpu:5345.4340937717125 mfu:25.215324645422612 Step 2238 | loss:1.2871395349502563 lr:3.961850592554766e-05 tokens_per_second_per_gpu:5318.854262776911 mfu:25.089943047633334 Step 2239 | loss:1.247029185295105 lr:3.960964071259871e-05 tokens_per_second_per_gpu:5315.936394388936 mfu:25.07617896460757 Step 2240 | loss:1.2784754037857056 lr:3.9600772708885606e-05 tokens_per_second_per_gpu:5321.380758237075 mfu:25.1018609577835 Step 2241 | loss:1.3713274002075195 lr:3.959190191610232e-05 tokens_per_second_per_gpu:3708.695392944366 mfu:17.49454893720165 Step 2242 | loss:1.3541181087493896 lr:3.9583028335943384e-05 tokens_per_second_per_gpu:4118.69705920891 mfu:19.428596750469143 Step 2243 | loss:1.2382400035858154 lr:3.957415197010384e-05 tokens_per_second_per_gpu:5324.127745595829 mfu:25.114818965839117 Step 2244 | loss:1.4164315462112427 lr:3.956527282027925e-05 tokens_per_second_per_gpu:4193.859643833489 mfu:19.7831514862026 Step 2245 | loss:1.2337336540222168 lr:3.9556390888165754e-05 tokens_per_second_per_gpu:5359.973344888264 mfu:25.283908773591424 Step 2246 | loss:1.16059410572052 lr:3.954750617545999e-05 tokens_per_second_per_gpu:5073.934692579815 mfu:23.93461564742596 Step 2247 | loss:1.2167309522628784 lr:3.953861868385914e-05 tokens_per_second_per_gpu:5226.865688225935 mfu:24.65601724660716 Step 2248 | loss:1.2675124406814575 lr:3.9529728415060895e-05 tokens_per_second_per_gpu:4452.258179086091 mfu:21.00206146432538 Step 2249 | loss:1.3126654624938965 lr:3.952083537076351e-05 tokens_per_second_per_gpu:3897.461842786809 mfu:18.384992487985865 Step 2250 | loss:1.438830852508545 lr:3.951193955266574e-05 tokens_per_second_per_gpu:3395.533994111333 mfu:16.017313188061976 Step 2251 | loss:1.3796093463897705 lr:3.950304096246689e-05 tokens_per_second_per_gpu:5157.2819111207855 mfu:24.32777869778557 Step 2252 | loss:1.3661004304885864 lr:3.949413960186679e-05 tokens_per_second_per_gpu:3898.9408856303985 mfu:18.391969385429807 Step 2253 | loss:1.31270432472229 lr:3.948523547256578e-05 tokens_per_second_per_gpu:4662.390790432555 mfu:21.99329284436712 Step 2254 | loss:1.3126810789108276 lr:3.947632857626477e-05 tokens_per_second_per_gpu:3841.285729810012 mfu:18.120000178441103 Step 2255 | loss:1.4483031034469604 lr:3.946741891466515e-05 tokens_per_second_per_gpu:5156.960482173958 mfu:24.32626246260195 Step 2256 | loss:1.3100913763046265 lr:3.945850648946888e-05 tokens_per_second_per_gpu:5296.695896913717 mfu:24.985418255249584 Step 2257 | loss:1.318872332572937 lr:3.944959130237843e-05 tokens_per_second_per_gpu:3777.191302726713 mfu:17.817655830252274 Step 2258 | loss:1.298896074295044 lr:3.944067335509678e-05 tokens_per_second_per_gpu:3561.146386651245 mfu:16.798535100060615 Step 2259 | loss:1.2916315793991089 lr:3.943175264932747e-05 tokens_per_second_per_gpu:4148.9494146620655 mfu:19.571302272725763 Step 2260 | loss:1.2118890285491943 lr:3.942282918677455e-05 tokens_per_second_per_gpu:4646.29891593157 mfu:21.917384726789066 Step 2261 | loss:1.259628415107727 lr:3.94139029691426e-05 tokens_per_second_per_gpu:4511.469847470035 mfu:21.28137300664481 Step 2262 | loss:1.3804110288619995 lr:3.940497399813672e-05 tokens_per_second_per_gpu:4354.025555682155 mfu:20.5386814195152 Step 2263 | loss:1.2112411260604858 lr:3.939604227546254e-05 tokens_per_second_per_gpu:4204.593747569435 mfu:19.833786084952003 Step 2264 | loss:1.4566627740859985 lr:3.938710780282622e-05 tokens_per_second_per_gpu:3138.536849898939 mfu:14.805013810577828 Step 2265 | loss:1.3465746641159058 lr:3.937817058193444e-05 tokens_per_second_per_gpu:4714.931905468747 mfu:22.24113824843144 Step 2266 | loss:1.2524549961090088 lr:3.936923061449441e-05 tokens_per_second_per_gpu:4925.391060528648 mfu:23.23390999088357 Step 2267 | loss:1.3731545209884644 lr:3.936028790221385e-05 tokens_per_second_per_gpu:4574.476612494346 mfu:21.57858666732711 Step 2268 | loss:1.290289282798767 lr:3.935134244680103e-05 tokens_per_second_per_gpu:4658.685692010196 mfu:21.975815262953873 Step 2269 | loss:1.2088432312011719 lr:3.934239424996472e-05 tokens_per_second_per_gpu:4723.72828482422 mfu:22.282632270668287 Step 2270 | loss:1.4123291969299316 lr:3.933344331341423e-05 tokens_per_second_per_gpu:5346.360647231063 mfu:25.219695356176693 Step 2271 | loss:1.399222731590271 lr:3.9324489638859384e-05 tokens_per_second_per_gpu:4050.584147674017 mfu:19.107296525498 Step 2272 | loss:1.5242571830749512 lr:3.931553322801054e-05 tokens_per_second_per_gpu:5380.460059218812 mfu:25.380548100482514 Step 2273 | loss:1.2525806427001953 lr:3.9306574082578546e-05 tokens_per_second_per_gpu:5303.463646921033 mfu:25.017342886731317 Step 2274 | loss:1.3722105026245117 lr:3.929761220427482e-05 tokens_per_second_per_gpu:5350.9322414114395 mfu:25.241260345919926 Step 2275 | loss:1.3259402513504028 lr:3.9288647594811266e-05 tokens_per_second_per_gpu:5311.219108586561 mfu:25.053926722625818 Step 2276 | loss:1.4332412481307983 lr:3.927968025590033e-05 tokens_per_second_per_gpu:3599.270881987636 mfu:16.978374849272022 Step 2277 | loss:1.4399328231811523 lr:3.927071018925498e-05 tokens_per_second_per_gpu:3938.258020279319 mfu:18.577435017763666 Step 2278 | loss:1.2910397052764893 lr:3.926173739658867e-05 tokens_per_second_per_gpu:5325.409871326236 mfu:25.120866971662654 Step 2279 | loss:1.2340234518051147 lr:3.925276187961543e-05 tokens_per_second_per_gpu:3968.941072426087 mfu:18.722172209808484 Step 2280 | loss:1.4092116355895996 lr:3.9243783640049766e-05 tokens_per_second_per_gpu:4374.006374116996 mfu:20.6329343491515 Step 2281 | loss:1.28570556640625 lr:3.923480267960672e-05 tokens_per_second_per_gpu:4838.552477093366 mfu:22.824277576629214 Step 2282 | loss:1.3021345138549805 lr:3.922581900000186e-05 tokens_per_second_per_gpu:4588.448651148699 mfu:21.644495157535303 Step 2283 | loss:1.3459892272949219 lr:3.921683260295127e-05 tokens_per_second_per_gpu:4102.759357403578 mfu:19.353415891801067 Step 2284 | loss:1.2852222919464111 lr:3.920784349017154e-05 tokens_per_second_per_gpu:5330.741544552453 mfu:25.146017383947974 Step 2285 | loss:1.2821357250213623 lr:3.91988516633798e-05 tokens_per_second_per_gpu:5129.283528192139 mfu:24.195705548494427 Step 2286 | loss:1.1825376749038696 lr:3.9189857124293674e-05 tokens_per_second_per_gpu:4315.582145816803 mfu:20.35733729605825 Step 2287 | loss:1.5040757656097412 lr:3.918085987463134e-05 tokens_per_second_per_gpu:4595.458832419568 mfu:21.67756337865025 Step 2288 | loss:1.2225545644760132 lr:3.917185991611144e-05 tokens_per_second_per_gpu:4163.851752568423 mfu:19.641599143231087 Step 2289 | loss:1.1862646341323853 lr:3.9162857250453195e-05 tokens_per_second_per_gpu:4150.517444395867 mfu:19.578698936513565 Step 2290 | loss:1.2951467037200928 lr:3.91538518793763e-05 tokens_per_second_per_gpu:5103.220405159965 mfu:24.072761350324328 Step 2291 | loss:1.2227847576141357 lr:3.914484380460097e-05 tokens_per_second_per_gpu:4990.850535239788 mfu:23.542693501634062 Step 2292 | loss:1.2332621812820435 lr:3.9135833027847966e-05 tokens_per_second_per_gpu:5318.507975124786 mfu:25.088309549695495 Step 2293 | loss:1.2830653190612793 lr:3.912681955083854e-05 tokens_per_second_per_gpu:5072.248584162203 mfu:23.92666198634032 Step 2294 | loss:1.4091320037841797 lr:3.911780337529445e-05 tokens_per_second_per_gpu:4589.238959058442 mfu:21.648223174785993 Step 2295 | loss:1.324866533279419 lr:3.9108784502938e-05 tokens_per_second_per_gpu:3374.109585894353 mfu:15.916250599121511 Step 2296 | loss:1.4309495687484741 lr:3.9099762935492004e-05 tokens_per_second_per_gpu:4087.8738065555613 mfu:19.283198208714108 Step 2297 | loss:1.1871484518051147 lr:3.909073867467975e-05 tokens_per_second_per_gpu:5188.345281187516 mfu:24.474309914347785 Step 2298 | loss:1.42421555519104 lr:3.908171172222509e-05 tokens_per_second_per_gpu:3219.3330792157735 mfu:15.186143409523547 Step 2299 | loss:1.4938745498657227 lr:3.907268207985237e-05 tokens_per_second_per_gpu:4339.4632062772025 mfu:20.469988332779025 Step 2300 | loss:1.2853834629058838 lr:3.9063649749286454e-05 tokens_per_second_per_gpu:4455.722795558391 mfu:21.01840465134974 Step 2301 | loss:1.304703712463379 lr:3.905461473225271e-05 tokens_per_second_per_gpu:5102.3797093755065 mfu:24.068795644871546 Step 2302 | loss:1.5560303926467896 lr:3.904557703047703e-05 tokens_per_second_per_gpu:4897.991955842302 mfu:23.104663739308766 Step 2303 | loss:1.412136435508728 lr:3.903653664568582e-05 tokens_per_second_per_gpu:4556.35891340351 mfu:21.493122389517417 Step 2304 | loss:1.2926424741744995 lr:3.902749357960598e-05 tokens_per_second_per_gpu:5312.793421950918 mfu:25.061353027371048 Step 2305 | loss:1.365965485572815 lr:3.9018447833964944e-05 tokens_per_second_per_gpu:4372.962732208148 mfu:20.628011312203792 Step 2306 | loss:1.214953899383545 lr:3.900939941049064e-05 tokens_per_second_per_gpu:5322.64671313443 mfu:25.107832683028505 Step 2307 | loss:1.2795698642730713 lr:3.900034831091153e-05 tokens_per_second_per_gpu:4983.261961033402 mfu:23.506896902358275 Step 2308 | loss:1.283696174621582 lr:3.899129453695658e-05 tokens_per_second_per_gpu:4032.9649271126814 mfu:19.02418365596117 Step 2309 | loss:1.3546794652938843 lr:3.898223809035523e-05 tokens_per_second_per_gpu:4979.148267829843 mfu:23.487491909648647 Step 2310 | loss:1.2755225896835327 lr:3.8973178972837494e-05 tokens_per_second_per_gpu:5320.6954873724335 mfu:25.098628418195727 Step 2311 | loss:1.296694040298462 lr:3.8964117186133845e-05 tokens_per_second_per_gpu:5336.007684808364 mfu:25.170858666031283 Step 2312 | loss:1.3761051893234253 lr:3.8955052731975296e-05 tokens_per_second_per_gpu:4263.753708424412 mfu:20.112853714035083 Step 2313 | loss:1.2735004425048828 lr:3.894598561209334e-05 tokens_per_second_per_gpu:5334.514860210474 mfu:25.163816757700896 Step 2314 | loss:1.1733864545822144 lr:3.8936915828220025e-05 tokens_per_second_per_gpu:4445.217955869589 mfu:20.96885153022719 Step 2315 | loss:1.3693903684616089 lr:3.892784338208785e-05 tokens_per_second_per_gpu:3528.559975380207 mfu:16.64481943828006 Step 2316 | loss:1.4796364307403564 lr:3.8918768275429876e-05 tokens_per_second_per_gpu:5052.200809311956 mfu:23.832093211868603 Step 2317 | loss:1.2313408851623535 lr:3.8909690509979636e-05 tokens_per_second_per_gpu:4763.467767232372 mfu:22.4700901894424 Step 2318 | loss:1.3465216159820557 lr:3.890061008747118e-05 tokens_per_second_per_gpu:4101.902243750108 mfu:19.34937274045898 Step 2319 | loss:1.2364524602890015 lr:3.8891527009639085e-05 tokens_per_second_per_gpu:5315.042277800485 mfu:25.07196126410783 Step 2320 | loss:1.379263997077942 lr:3.8882441278218405e-05 tokens_per_second_per_gpu:4667.728375844028 mfu:22.018471145439012 Step 2321 | loss:1.3010839223861694 lr:3.887335289494473e-05 tokens_per_second_per_gpu:4559.48408801619 mfu:21.5078643713752 Step 2322 | loss:1.2942596673965454 lr:3.886426186155413e-05 tokens_per_second_per_gpu:5323.64680875291 mfu:25.112550304694782 Step 2323 | loss:1.4391762018203735 lr:3.8855168179783196e-05 tokens_per_second_per_gpu:4377.910022762556 mfu:20.651348525843744 Step 2324 | loss:1.311152696609497 lr:3.8846071851369025e-05 tokens_per_second_per_gpu:5337.296731123572 mfu:25.176939317434098 Step 2325 | loss:1.2940936088562012 lr:3.883697287804922e-05 tokens_per_second_per_gpu:4319.695368632745 mfu:20.376740069869232 Step 2326 | loss:1.259679913520813 lr:3.882787126156187e-05 tokens_per_second_per_gpu:5056.010829933942 mfu:23.850065729199063 Step 2327 | loss:1.3445435762405396 lr:3.881876700364561e-05 tokens_per_second_per_gpu:3859.9419465462893 mfu:18.208004735864925 Step 2328 | loss:1.2844955921173096 lr:3.8809660106039525e-05 tokens_per_second_per_gpu:5252.70012384973 mfu:24.777882687253836 Step 2329 | loss:1.3165193796157837 lr:3.880055057048325e-05 tokens_per_second_per_gpu:4836.153666283429 mfu:22.81296197675941 Step 2330 | loss:1.3619190454483032 lr:3.8791438398716914e-05 tokens_per_second_per_gpu:4258.723191075738 mfu:20.089123905406623 Step 2331 | loss:1.1921629905700684 lr:3.8782323592481135e-05 tokens_per_second_per_gpu:5332.658797247412 mfu:25.15506139202714 Step 2332 | loss:1.3966128826141357 lr:3.877320615351704e-05 tokens_per_second_per_gpu:5297.833848993546 mfu:24.99078616936479 Step 2333 | loss:1.3402955532073975 lr:3.8764086083566264e-05 tokens_per_second_per_gpu:5208.307891660596 mfu:24.568476953921863 Step 2334 | loss:1.3611522912979126 lr:3.875496338437094e-05 tokens_per_second_per_gpu:5150.993778574353 mfu:24.298116503698004 Step 2335 | loss:1.3186774253845215 lr:3.874583805767371e-05 tokens_per_second_per_gpu:4230.49943236024 mfu:19.955987620075827 Step 2336 | loss:1.2160556316375732 lr:3.873671010521771e-05 tokens_per_second_per_gpu:4942.982235586173 mfu:23.316890564993873 Step 2337 | loss:1.3865877389907837 lr:3.8727579528746576e-05 tokens_per_second_per_gpu:4534.496336939672 mfu:21.389992886197305 Step 2338 | loss:1.269025444984436 lr:3.8718446330004454e-05 tokens_per_second_per_gpu:4370.857685666563 mfu:20.618081448509166 Step 2339 | loss:1.677152156829834 lr:3.8709310510736e-05 tokens_per_second_per_gpu:4186.600411413417 mfu:19.748908448324347 Step 2340 | loss:1.2010488510131836 lr:3.870017207268633e-05 tokens_per_second_per_gpu:5333.14261196502 mfu:25.157343628597395 Step 2341 | loss:1.4094350337982178 lr:3.869103101760111e-05 tokens_per_second_per_gpu:3427.712881039856 mfu:16.16910648798807 Step 2342 | loss:1.272460699081421 lr:3.868188734722648e-05 tokens_per_second_per_gpu:5340.665728878512 mfu:25.192831454654442 Step 2343 | loss:1.4846751689910889 lr:3.8672741063309064e-05 tokens_per_second_per_gpu:5323.462882694047 mfu:25.111682694094103 Step 2344 | loss:1.487133502960205 lr:3.8663592167596024e-05 tokens_per_second_per_gpu:4179.457958143271 mfu:19.715216277620883 Step 2345 | loss:1.2979243993759155 lr:3.8654440661835004e-05 tokens_per_second_per_gpu:3994.922435086436 mfu:18.84473073035493 Step 2346 | loss:1.4163117408752441 lr:3.864528654777413e-05 tokens_per_second_per_gpu:5287.070289422024 mfu:24.940012622413285 Step 2347 | loss:1.438765525817871 lr:3.863612982716204e-05 tokens_per_second_per_gpu:3899.0121158886045 mfu:18.3923053907109 Step 2348 | loss:1.4476816654205322 lr:3.862697050174789e-05 tokens_per_second_per_gpu:5309.844400173565 mfu:25.047441988492277 Step 2349 | loss:1.2802945375442505 lr:3.861780857328129e-05 tokens_per_second_per_gpu:4888.649735484137 mfu:23.060594891932144 Step 2350 | loss:1.3419119119644165 lr:3.8608644043512376e-05 tokens_per_second_per_gpu:4257.232101791645 mfu:20.08209018284749 Step 2351 | loss:1.2075873613357544 lr:3.859947691419179e-05 tokens_per_second_per_gpu:3599.856006412497 mfu:16.981134981016613 Step 2352 | loss:1.4406614303588867 lr:3.859030718707064e-05 tokens_per_second_per_gpu:3599.585217756332 mfu:16.979857624724175 Step 2353 | loss:1.175236701965332 lr:3.858113486390056e-05 tokens_per_second_per_gpu:5337.2064543574925 mfu:25.1765134665257 Step 2354 | loss:1.2646446228027344 lr:3.857195994643365e-05 tokens_per_second_per_gpu:3972.056168237663 mfu:18.73686664824184 Step 2355 | loss:1.3954391479492188 lr:3.856278243642254e-05 tokens_per_second_per_gpu:3323.804001655064 mfu:15.67895057524706 Step 2356 | loss:1.4932680130004883 lr:3.855360233562032e-05 tokens_per_second_per_gpu:4360.387130436976 mfu:20.568690053030267 Step 2357 | loss:1.3759721517562866 lr:3.8544419645780604e-05 tokens_per_second_per_gpu:5364.183947592189 mfu:25.303770904948742 Step 2358 | loss:1.420122504234314 lr:3.853523436865748e-05 tokens_per_second_per_gpu:4883.625869695306 mfu:23.036896459846343 Step 2359 | loss:1.3892544507980347 lr:3.8526046506005546e-05 tokens_per_second_per_gpu:3777.5116247396763 mfu:17.819166843839994 Step 2360 | loss:1.3097964525222778 lr:3.851685605957989e-05 tokens_per_second_per_gpu:4151.6593725574985 mfu:19.58408560648502 Step 2361 | loss:1.4763702154159546 lr:3.850766303113608e-05 tokens_per_second_per_gpu:4192.302694892038 mfu:19.77580709240289 Step 2362 | loss:1.18912935256958 lr:3.84984674224302e-05 tokens_per_second_per_gpu:4810.414730541445 mfu:22.691547025349198 Step 2363 | loss:1.4719159603118896 lr:3.848926923521879e-05 tokens_per_second_per_gpu:5310.464570797065 mfu:25.050367439135346 Step 2364 | loss:1.3069794178009033 lr:3.8480068471258934e-05 tokens_per_second_per_gpu:3653.5578280422155 mfu:17.23445563611957 Step 2365 | loss:1.5788204669952393 lr:3.847086513230817e-05 tokens_per_second_per_gpu:3661.5440196927043 mfu:17.272127864719724 Step 2366 | loss:1.4064596891403198 lr:3.846165922012454e-05 tokens_per_second_per_gpu:4566.977577649291 mfu:21.5432124404957 Step 2367 | loss:1.2718563079833984 lr:3.845245073646658e-05 tokens_per_second_per_gpu:3693.68939321607 mfu:17.423763076195716 Step 2368 | loss:1.3402498960494995 lr:3.84432396830933e-05 tokens_per_second_per_gpu:5326.996100445115 mfu:25.128349485055004 Step 2369 | loss:1.6118102073669434 lr:3.8434026061764236e-05 tokens_per_second_per_gpu:4127.176008579249 mfu:19.468593401306972 Step 2370 | loss:1.2141515016555786 lr:3.8424809874239384e-05 tokens_per_second_per_gpu:3944.390006052078 mfu:18.60636064087842 Step 2371 | loss:1.346071720123291 lr:3.841559112227923e-05 tokens_per_second_per_gpu:5313.666019955567 mfu:25.06546922103955 Step 2372 | loss:1.4674930572509766 lr:3.840636980764477e-05 tokens_per_second_per_gpu:3427.822468727504 mfu:16.169623431808294 Step 2373 | loss:1.1991493701934814 lr:3.839714593209748e-05 tokens_per_second_per_gpu:5336.951312109866 mfu:25.17530991701189 Step 2374 | loss:1.2550952434539795 lr:3.838791949739931e-05 tokens_per_second_per_gpu:5319.268364633031 mfu:25.091896436741713 Step 2375 | loss:1.5350908041000366 lr:3.837869050531273e-05 tokens_per_second_per_gpu:4083.230854827277 mfu:19.26129661324254 Step 2376 | loss:1.2226595878601074 lr:3.836945895760067e-05 tokens_per_second_per_gpu:4959.714067054841 mfu:23.395817468776396 Step 2377 | loss:1.2746872901916504 lr:3.836022485602657e-05 tokens_per_second_per_gpu:5096.738140309419 mfu:24.042183401035874 Step 2378 | loss:1.3233345746994019 lr:3.8350988202354334e-05 tokens_per_second_per_gpu:3691.045457019342 mfu:17.41129117805372 Step 2379 | loss:1.2987194061279297 lr:3.834174899834839e-05 tokens_per_second_per_gpu:5309.956826564353 mfu:25.04797232295954 Step 2380 | loss:1.4720739126205444 lr:3.8332507245773594e-05 tokens_per_second_per_gpu:4091.1707815018867 mfu:19.298750602057858 Step 2381 | loss:1.1192920207977295 lr:3.8323262946395356e-05 tokens_per_second_per_gpu:3716.938313785409 mfu:17.533432201196167 Step 2382 | loss:1.4380117654800415 lr:3.831401610197953e-05 tokens_per_second_per_gpu:4978.09759283198 mfu:23.482535696420094 Step 2383 | loss:1.4140607118606567 lr:3.830476671429246e-05 tokens_per_second_per_gpu:3991.4778451148004 mfu:18.82848201175107 Step 2384 | loss:1.360952615737915 lr:3.8295514785101e-05 tokens_per_second_per_gpu:5330.482493984939 mfu:25.144795398222428 Step 2385 | loss:1.2644213438034058 lr:3.8286260316172466e-05 tokens_per_second_per_gpu:3669.440064415555 mfu:17.30937485488156 Step 2386 | loss:1.3715652227401733 lr:3.827700330927466e-05 tokens_per_second_per_gpu:5343.61254882644 mfu:25.206732107128147 Step 2387 | loss:1.419446587562561 lr:3.826774376617588e-05 tokens_per_second_per_gpu:4640.240060255688 mfu:21.888804070818555 Step 2388 | loss:1.2374521493911743 lr:3.8258481688644896e-05 tokens_per_second_per_gpu:5301.037366007332 mfu:25.00589770569518 Step 2389 | loss:1.178662657737732 lr:3.824921707845099e-05 tokens_per_second_per_gpu:5304.762596375062 mfu:25.023470252929602 Step 2390 | loss:1.3791885375976562 lr:3.823994993736388e-05 tokens_per_second_per_gpu:5019.700442940465 mfu:23.678783438559982 Step 2391 | loss:1.325437068939209 lr:3.823068026715382e-05 tokens_per_second_per_gpu:3765.2405455278963 mfu:17.761282069536023 Step 2392 | loss:1.2572473287582397 lr:3.8221408069591503e-05 tokens_per_second_per_gpu:5323.987688407461 mfu:25.114158292185365 Step 2393 | loss:1.480092167854309 lr:3.8212133346448134e-05 tokens_per_second_per_gpu:5343.308865102932 mfu:25.205299579190577 Step 2394 | loss:1.5445334911346436 lr:3.820285609949539e-05 tokens_per_second_per_gpu:3666.26627926968 mfu:17.294403568844885 Step 2395 | loss:1.3368078470230103 lr:3.819357633050542e-05 tokens_per_second_per_gpu:5323.267764719233 mfu:25.110762289316348 Step 2396 | loss:1.3720303773880005 lr:3.818429404125087e-05 tokens_per_second_per_gpu:5088.856728637563 mfu:24.00500543747224 Step 2397 | loss:1.237359642982483 lr:3.817500923350486e-05 tokens_per_second_per_gpu:4985.603546492746 mfu:23.517942560485675 Step 2398 | loss:1.4569122791290283 lr:3.816572190904101e-05 tokens_per_second_per_gpu:4235.35565138032 mfu:19.978895233749945 Step 2399 | loss:1.2468996047973633 lr:3.8156432069633386e-05 tokens_per_second_per_gpu:4719.821850319466 mfu:22.264204952602906 Step 2400 | loss:1.2027405500411987 lr:3.8147139717056554e-05 tokens_per_second_per_gpu:4613.942689017213 mfu:21.764754883892472 Step 2401 | loss:1.1927776336669922 lr:3.8137844853085567e-05 tokens_per_second_per_gpu:4738.706107976111 mfu:22.3532852179559 Step 2402 | loss:1.321772575378418 lr:3.812854747949595e-05 tokens_per_second_per_gpu:5344.824585197114 mfu:25.212449489483348 Step 2403 | loss:1.363229751586914 lr:3.8119247598063694e-05 tokens_per_second_per_gpu:5318.368515715179 mfu:25.087651695866146 Step 2404 | loss:1.239090085029602 lr:3.81099452105653e-05 tokens_per_second_per_gpu:4612.327223112735 mfu:21.757134455594144 Step 2405 | loss:1.3971185684204102 lr:3.81006403187777e-05 tokens_per_second_per_gpu:4793.490262654469 mfu:22.61171142271435 Step 2406 | loss:1.1961723566055298 lr:3.8091332924478376e-05 tokens_per_second_per_gpu:5302.489997655874 mfu:25.012750017025866 Step 2407 | loss:1.1396836042404175 lr:3.8082023029445205e-05 tokens_per_second_per_gpu:5151.30764625222 mfu:24.299597071085852 Step 2408 | loss:1.4502054452896118 lr:3.807271063545661e-05 tokens_per_second_per_gpu:3597.9721196983915 mfu:16.97224836596196 Step 2409 | loss:1.4913818836212158 lr:3.8063395744291454e-05 tokens_per_second_per_gpu:4678.6704140724905 mfu:22.0700866066669 Step 2410 | loss:1.5051172971725464 lr:3.805407835772908e-05 tokens_per_second_per_gpu:3653.3161228761955 mfu:17.2333154716123 Step 2411 | loss:1.3021678924560547 lr:3.804475847754933e-05 tokens_per_second_per_gpu:4726.15590769618 mfu:22.294083781950494 Step 2412 | loss:1.1805740594863892 lr:3.8035436105532496e-05 tokens_per_second_per_gpu:5316.691755316064 mfu:25.079742130978698 Step 2413 | loss:1.4126079082489014 lr:3.802611124345936e-05 tokens_per_second_per_gpu:5212.726188847205 mfu:24.589318815590328 Step 2414 | loss:1.1959595680236816 lr:3.8016783893111186e-05 tokens_per_second_per_gpu:4683.680749495303 mfu:22.09372121370768 Step 2415 | loss:1.507007360458374 lr:3.8007454056269685e-05 tokens_per_second_per_gpu:3859.711373544641 mfu:18.20691708367634 Step 2416 | loss:1.3241182565689087 lr:3.799812173471707e-05 tokens_per_second_per_gpu:4424.831382524612 mfu:20.872684585450855 Step 2417 | loss:1.3435410261154175 lr:3.798878693023603e-05 tokens_per_second_per_gpu:4804.482898434432 mfu:22.663565561225496 Step 2418 | loss:1.2293165922164917 lr:3.7979449644609717e-05 tokens_per_second_per_gpu:4602.840916186653 mfu:21.71238592729296 Step 2419 | loss:1.2120652198791504 lr:3.797010987962174e-05 tokens_per_second_per_gpu:3976.497947756357 mfu:18.757819280077253 Step 2420 | loss:1.4758988618850708 lr:3.7960767637056225e-05 tokens_per_second_per_gpu:4351.296992939336 mfu:20.52581032351651 Step 2421 | loss:1.2979964017868042 lr:3.795142291869773e-05 tokens_per_second_per_gpu:4759.887058371955 mfu:22.45319937481588 Step 2422 | loss:1.3489899635314941 lr:3.794207572633131e-05 tokens_per_second_per_gpu:3682.361242668668 mfu:17.370326257281835 Step 2423 | loss:1.2679004669189453 lr:3.793272606174248e-05 tokens_per_second_per_gpu:5316.012427158452 mfu:25.076537624153907 Step 2424 | loss:1.2112648487091064 lr:3.792337392671724e-05 tokens_per_second_per_gpu:5289.260711557585 mfu:24.95034521735128 Step 2425 | loss:1.337936520576477 lr:3.791401932304206e-05 tokens_per_second_per_gpu:4887.170185133512 mfu:23.05361560049093 Step 2426 | loss:1.3291884660720825 lr:3.7904662252503855e-05 tokens_per_second_per_gpu:5185.263158118095 mfu:24.459771013964907 Step 2427 | loss:1.3369213342666626 lr:3.789530271689004e-05 tokens_per_second_per_gpu:4114.666488368689 mfu:19.409583860129526 Step 2428 | loss:1.253862738609314 lr:3.78859407179885e-05 tokens_per_second_per_gpu:4704.706393079285 mfu:22.192902761838035 Step 2429 | loss:1.3301814794540405 lr:3.787657625758758e-05 tokens_per_second_per_gpu:4212.674875102603 mfu:19.87190614230849 Step 2430 | loss:1.240241527557373 lr:3.786720933747611e-05 tokens_per_second_per_gpu:5145.227557489806 mfu:24.27091625502343 Step 2431 | loss:1.1700077056884766 lr:3.7857839959443356e-05 tokens_per_second_per_gpu:4867.1599966976955 mfu:22.959224127548985 Step 2432 | loss:1.3125157356262207 lr:3.784846812527909e-05 tokens_per_second_per_gpu:4508.44555602065 mfu:21.267106907880727 Step 2433 | loss:1.4397259950637817 lr:3.7839093836773544e-05 tokens_per_second_per_gpu:4631.000332233848 mfu:21.84521869727938 Step 2434 | loss:1.2194108963012695 lr:3.78297170957174e-05 tokens_per_second_per_gpu:4060.4150808813997 mfu:19.15367071476739 Step 2435 | loss:1.3531290292739868 lr:3.7820337903901834e-05 tokens_per_second_per_gpu:3480.8556307962 mfu:16.419789905676822 Step 2436 | loss:1.2787412405014038 lr:3.781095626311848e-05 tokens_per_second_per_gpu:3672.94231976954 mfu:17.32589559093269 Step 2437 | loss:1.389100432395935 lr:3.7801572175159425e-05 tokens_per_second_per_gpu:5167.334971442299 mfu:24.37520069855111 Step 2438 | loss:1.3432707786560059 lr:3.779218564181725e-05 tokens_per_second_per_gpu:4401.432455693391 mfu:20.762307855319392 Step 2439 | loss:1.3548798561096191 lr:3.778279666488499e-05 tokens_per_second_per_gpu:3760.9432682647844 mfu:17.741011079494818 Step 2440 | loss:1.3709659576416016 lr:3.7773405246156143e-05 tokens_per_second_per_gpu:3126.6766251977124 mfu:14.749067107099142 Step 2441 | loss:1.5611066818237305 lr:3.776401138742467e-05 tokens_per_second_per_gpu:4285.6649593196735 mfu:20.21621282295293 Step 2442 | loss:1.3150503635406494 lr:3.775461509048503e-05 tokens_per_second_per_gpu:4541.788859920843 mfu:21.42439296133221 Step 2443 | loss:1.2144684791564941 lr:3.7745216357132085e-05 tokens_per_second_per_gpu:4082.09992939188 mfu:19.255961845007995 Step 2444 | loss:1.2928537130355835 lr:3.773581518916124e-05 tokens_per_second_per_gpu:3808.104783073188 mfu:17.963479991430223 Step 2445 | loss:1.560401439666748 lr:3.77264115883683e-05 tokens_per_second_per_gpu:4795.747880051082 mfu:22.62236098916342 Step 2446 | loss:1.3948532342910767 lr:3.771700555654957e-05 tokens_per_second_per_gpu:4488.526863166494 mfu:21.173147035208235 Step 2447 | loss:1.4238760471343994 lr:3.770759709550181e-05 tokens_per_second_per_gpu:5072.213698753583 mfu:23.926497425915798 Step 2448 | loss:1.3846467733383179 lr:3.769818620702224e-05 tokens_per_second_per_gpu:4901.009972551897 mfu:23.118900239054675 Step 2449 | loss:1.3665424585342407 lr:3.768877289290855e-05 tokens_per_second_per_gpu:4526.683697353691 mfu:21.353139332296468 Step 2450 | loss:1.2422045469284058 lr:3.76793571549589e-05 tokens_per_second_per_gpu:3505.4674309972 mfu:16.535887966431062 Step 2451 | loss:1.3290749788284302 lr:3.766993899497189e-05 tokens_per_second_per_gpu:5317.835583693898 mfu:25.085137764594187 Step 2452 | loss:1.256231427192688 lr:3.766051841474659e-05 tokens_per_second_per_gpu:4467.957916642677 mfu:21.076119805031237 Step 2453 | loss:1.3888604640960693 lr:3.765109541608256e-05 tokens_per_second_per_gpu:4837.196372777904 mfu:22.81788060119792 Step 2454 | loss:1.3676905632019043 lr:3.7641670000779806e-05 tokens_per_second_per_gpu:3790.5625930736705 mfu:17.880730488196257 Step 2455 | loss:1.388717532157898 lr:3.763224217063876e-05 tokens_per_second_per_gpu:4365.64594137183 mfu:20.59349676145564 Step 2456 | loss:1.2669631242752075 lr:3.7622811927460364e-05 tokens_per_second_per_gpu:5300.847887932881 mfu:25.0050039052897 Step 2457 | loss:1.3498138189315796 lr:3.7613379273046e-05 tokens_per_second_per_gpu:3949.9818715255033 mfu:18.6327384243872 Step 2458 | loss:1.158684253692627 lr:3.760394420919752e-05 tokens_per_second_per_gpu:4926.996796234874 mfu:23.2414845201766 Step 2459 | loss:1.306363582611084 lr:3.759450673771722e-05 tokens_per_second_per_gpu:4586.0800933891305 mfu:21.633322266465793 Step 2460 | loss:1.2744745016098022 lr:3.7585066860407876e-05 tokens_per_second_per_gpu:5305.291744474811 mfu:25.025966334798095 Step 2461 | loss:1.3139796257019043 lr:3.75756245790727e-05 tokens_per_second_per_gpu:5257.873223810057 mfu:24.802285082388565 Step 2462 | loss:1.3996657133102417 lr:3.756617989551539e-05 tokens_per_second_per_gpu:4790.79282063315 mfu:22.59898712846872 Step 2463 | loss:1.2580879926681519 lr:3.755673281154007e-05 tokens_per_second_per_gpu:5321.39154928812 mfu:25.101911861012425 Step 2464 | loss:1.2332137823104858 lr:3.754728332895136e-05 tokens_per_second_per_gpu:5341.459934693242 mfu:25.196577858988007 Step 2465 | loss:1.1909302473068237 lr:3.753783144955432e-05 tokens_per_second_per_gpu:5283.471844625164 mfu:24.923038144348507 Step 2466 | loss:1.312386393547058 lr:3.752837717515446e-05 tokens_per_second_per_gpu:5317.797524882105 mfu:25.084958234685455 Step 2467 | loss:1.2886866331100464 lr:3.7518920507557753e-05 tokens_per_second_per_gpu:4674.326301682278 mfu:22.049594687340267 Step 2468 | loss:1.3160921335220337 lr:3.7509461448570635e-05 tokens_per_second_per_gpu:4904.264173282869 mfu:23.134250859126567 Step 2469 | loss:1.2847238779067993 lr:3.7500000000000003e-05 tokens_per_second_per_gpu:3473.034202113088 mfu:16.382894892105245 Step 2470 | loss:1.3366955518722534 lr:3.749053616365319e-05 tokens_per_second_per_gpu:4335.469353929873 mfu:20.4511486498352 Step 2471 | loss:1.3229423761367798 lr:3.7481069941338e-05 tokens_per_second_per_gpu:5318.437845756326 mfu:25.087978737499167 Step 2472 | loss:1.306091070175171 lr:3.7471601334862704e-05 tokens_per_second_per_gpu:5335.942233413962 mfu:25.17054992063673 Step 2473 | loss:1.157356858253479 lr:3.7462130346036e-05 tokens_per_second_per_gpu:3898.205587212547 mfu:18.388500857337952 Step 2474 | loss:1.3197689056396484 lr:3.745265697666706e-05 tokens_per_second_per_gpu:3407.11684472273 mfu:16.071951470634037 Step 2475 | loss:1.3001654148101807 lr:3.744318122856551e-05 tokens_per_second_per_gpu:4062.5210055769326 mfu:19.163604720864026 Step 2476 | loss:1.2961561679840088 lr:3.7433703103541425e-05 tokens_per_second_per_gpu:5295.216976811035 mfu:24.97844193679545 Step 2477 | loss:1.2669544219970703 lr:3.7424222603405326e-05 tokens_per_second_per_gpu:4561.810851533796 mfu:21.51884011187454 Step 2478 | loss:1.2576667070388794 lr:3.741473972996823e-05 tokens_per_second_per_gpu:5343.767872755565 mfu:25.207464796602828 Step 2479 | loss:1.354512333869934 lr:3.740525448504154e-05 tokens_per_second_per_gpu:3502.863963242818 mfu:16.52360696483624 Step 2480 | loss:1.3460999727249146 lr:3.739576687043716e-05 tokens_per_second_per_gpu:4925.359846162515 mfu:23.233762747392802 Step 2481 | loss:1.4635753631591797 lr:3.738627688796744e-05 tokens_per_second_per_gpu:3900.9124853819308 mfu:18.401269757847388 Step 2482 | loss:1.3907099962234497 lr:3.737678453944518e-05 tokens_per_second_per_gpu:4276.406136423939 mfu:20.172537375635667 Step 2483 | loss:1.2335906028747559 lr:3.73672898266836e-05 tokens_per_second_per_gpu:4742.001430865017 mfu:22.368829818262927 Step 2484 | loss:1.3055751323699951 lr:3.7357792751496435e-05 tokens_per_second_per_gpu:4024.5450230624074 mfu:18.98446553197226 Step 2485 | loss:1.215757966041565 lr:3.7348293315697816e-05 tokens_per_second_per_gpu:5042.495270108256 mfu:23.786310527509006 Step 2486 | loss:1.4364571571350098 lr:3.7338791521102344e-05 tokens_per_second_per_gpu:5313.991927227847 mfu:25.067006581248407 Step 2487 | loss:1.192606806755066 lr:3.732928736952508e-05 tokens_per_second_per_gpu:5314.174505930423 mfu:25.067867836139598 Step 2488 | loss:1.1777971982955933 lr:3.731978086278154e-05 tokens_per_second_per_gpu:4868.500450643572 mfu:22.965547277516713 Step 2489 | loss:1.3948246240615845 lr:3.731027200268764e-05 tokens_per_second_per_gpu:4584.563504877314 mfu:21.626168259698872 Step 2490 | loss:1.3925786018371582 lr:3.730076079105982e-05 tokens_per_second_per_gpu:4947.189119298716 mfu:23.336735153234308 Step 2491 | loss:1.5547711849212646 lr:3.729124722971491e-05 tokens_per_second_per_gpu:4922.210146975716 mfu:23.218905078934572 Step 2492 | loss:1.4809532165527344 lr:3.728173132047022e-05 tokens_per_second_per_gpu:5336.0927481247545 mfu:25.171259924208 Step 2493 | loss:1.438497543334961 lr:3.727221306514348e-05 tokens_per_second_per_gpu:4182.001354956325 mfu:19.7272139143363 Step 2494 | loss:1.3600966930389404 lr:3.726269246555292e-05 tokens_per_second_per_gpu:4609.730816953907 mfu:21.744886764750387 Step 2495 | loss:1.653106451034546 lr:3.725316952351715e-05 tokens_per_second_per_gpu:5308.074156927003 mfu:25.039091449063598 Step 2496 | loss:1.2962281703948975 lr:3.724364424085529e-05 tokens_per_second_per_gpu:5338.335904560905 mfu:25.181841275839272 Step 2497 | loss:1.3694772720336914 lr:3.723411661938687e-05 tokens_per_second_per_gpu:5320.869765802918 mfu:25.099450519287284 Step 2498 | loss:1.1640667915344238 lr:3.722458666093187e-05 tokens_per_second_per_gpu:5323.847406584465 mfu:25.113496558891747 Step 2499 | loss:1.3569800853729248 lr:3.721505436731073e-05 tokens_per_second_per_gpu:4231.631383777732 mfu:19.96132722804296 Step 2500 | loss:1.1916035413742065 lr:3.720551974034433e-05 tokens_per_second_per_gpu:4463.24380369575 mfu:21.053882529949973 Step 2501 | loss:1.1655179262161255 lr:3.719598278185398e-05 tokens_per_second_per_gpu:4931.756432903445 mfu:23.26393653842 Step 2502 | loss:1.2257252931594849 lr:3.7186443493661465e-05 tokens_per_second_per_gpu:5289.536287438993 mfu:24.951645155801977 Step 2503 | loss:1.1989479064941406 lr:3.7176901877589e-05 tokens_per_second_per_gpu:5229.012576624317 mfu:24.66614448547926 Step 2504 | loss:1.4610079526901245 lr:3.716735793545923e-05 tokens_per_second_per_gpu:3337.4247260176753 mfu:15.743201856000711 Step 2505 | loss:1.274376392364502 lr:3.7157811669095274e-05 tokens_per_second_per_gpu:4619.803031652375 mfu:21.79239911998009 Step 2506 | loss:1.3985865116119385 lr:3.7148263080320675e-05 tokens_per_second_per_gpu:4795.219361585501 mfu:22.619867877386724 Step 2507 | loss:1.4824700355529785 lr:3.713871217095942e-05 tokens_per_second_per_gpu:5305.165707660548 mfu:25.025371797641117 Step 2508 | loss:1.4024406671524048 lr:3.7129158942835953e-05 tokens_per_second_per_gpu:4577.413800078258 mfu:21.592441882296296 Step 2509 | loss:1.2618448734283447 lr:3.711960339777514e-05 tokens_per_second_per_gpu:3459.7164735446363 mfu:16.32007289420906 Step 2510 | loss:1.2288802862167358 lr:3.71100455376023e-05 tokens_per_second_per_gpu:5314.6891391066465 mfu:25.070295448637317 Step 2511 | loss:1.3071796894073486 lr:3.710048536414322e-05 tokens_per_second_per_gpu:5333.731288911254 mfu:25.160120518191427 Step 2512 | loss:1.430150032043457 lr:3.709092287922408e-05 tokens_per_second_per_gpu:5326.084108691303 mfu:25.124047464350436 Step 2513 | loss:1.3827992677688599 lr:3.708135808467153e-05 tokens_per_second_per_gpu:4685.319944834759 mfu:22.101453577799457 Step 2514 | loss:1.2004693746566772 lr:3.707179098231266e-05 tokens_per_second_per_gpu:3775.9386106898355 mfu:17.811746668183023 Step 2515 | loss:1.3520781993865967 lr:3.7062221573975e-05 tokens_per_second_per_gpu:4249.051759417616 mfu:20.04350211215887 Step 2516 | loss:1.415610909461975 lr:3.705264986148652e-05 tokens_per_second_per_gpu:5332.2709695221565 mfu:25.15323194247688 Step 2517 | loss:1.520146131515503 lr:3.704307584667562e-05 tokens_per_second_per_gpu:4533.673299621547 mfu:21.386110478743067 Step 2518 | loss:1.3562229871749878 lr:3.703349953137115e-05 tokens_per_second_per_gpu:3678.712543922474 mfu:17.353114722763838 Step 2519 | loss:1.3305559158325195 lr:3.702392091740241e-05 tokens_per_second_per_gpu:5118.86644708684 mfu:24.14656639958342 Step 2520 | loss:1.5147331953048706 lr:3.701434000659911e-05 tokens_per_second_per_gpu:3643.8762561621884 mfu:17.188786009714985 Step 2521 | loss:1.166002869606018 lr:3.700475680079142e-05 tokens_per_second_per_gpu:4969.406571942479 mfu:23.441538668043243 Step 2522 | loss:1.4830271005630493 lr:3.6995171301809964e-05 tokens_per_second_per_gpu:4283.510088885476 mfu:20.206047931456013 Step 2523 | loss:1.4370362758636475 lr:3.698558351148575e-05 tokens_per_second_per_gpu:4082.496638968213 mfu:19.257833191765194 Step 2524 | loss:1.3067303895950317 lr:3.697599343165028e-05 tokens_per_second_per_gpu:4343.610587557598 mfu:20.489552237894863 Step 2525 | loss:1.2650219202041626 lr:3.696640106413547e-05 tokens_per_second_per_gpu:5309.585254867369 mfu:25.046219555868202 Step 2526 | loss:1.3068722486495972 lr:3.695680641077367e-05 tokens_per_second_per_gpu:5333.776698049098 mfu:25.160334720842236 Step 2527 | loss:1.2519252300262451 lr:3.694720947339767e-05 tokens_per_second_per_gpu:4966.707993169992 mfu:23.428809011548406 Step 2528 | loss:1.1502207517623901 lr:3.69376102538407e-05 tokens_per_second_per_gpu:5294.91795537834 mfu:24.977031401679106 Step 2529 | loss:1.4172309637069702 lr:3.692800875393642e-05 tokens_per_second_per_gpu:4803.430471916023 mfu:22.65860108577568 Step 2530 | loss:1.3578850030899048 lr:3.6918404975518934e-05 tokens_per_second_per_gpu:5125.136193858008 mfu:24.176141864832125 Step 2531 | loss:1.3971338272094727 lr:3.690879892042278e-05 tokens_per_second_per_gpu:5280.001637796448 mfu:24.90666858665912 Step 2532 | loss:1.3155858516693115 lr:3.6899190590482903e-05 tokens_per_second_per_gpu:5297.202926494204 mfu:24.98781000028891 Step 2533 | loss:1.1579817533493042 lr:3.688957998753472e-05 tokens_per_second_per_gpu:5019.859500080966 mfu:23.679533738229676 Step 2534 | loss:1.177112102508545 lr:3.687996711341409e-05 tokens_per_second_per_gpu:5115.754017894421 mfu:24.131884540047604 Step 2535 | loss:1.202065110206604 lr:3.6870351969957246e-05 tokens_per_second_per_gpu:4949.0915415604195 mfu:23.34570920362947 Step 2536 | loss:1.5308897495269775 lr:3.686073455900092e-05 tokens_per_second_per_gpu:3848.7172176903337 mfu:18.15505577471516 Step 2537 | loss:1.3807834386825562 lr:3.685111488238224e-05 tokens_per_second_per_gpu:4688.802962171855 mfu:22.117883564842575 Step 2538 | loss:1.522257685661316 lr:3.6841492941938775e-05 tokens_per_second_per_gpu:3735.8781097616593 mfu:17.622774450278552 Step 2539 | loss:1.519602656364441 lr:3.683186873950854e-05 tokens_per_second_per_gpu:3787.4993007656617 mfu:17.866280415727815 Step 2540 | loss:1.3342034816741943 lr:3.6822242276929964e-05 tokens_per_second_per_gpu:4522.737731740486 mfu:21.334525539247824 Step 2541 | loss:1.3012655973434448 lr:3.6812613556041896e-05 tokens_per_second_per_gpu:4473.763000976803 mfu:21.103503378284824 Step 2542 | loss:1.4933738708496094 lr:3.6802982578683664e-05 tokens_per_second_per_gpu:3163.0116902497716 mfu:14.920465808351066 Step 2543 | loss:1.5007826089859009 lr:3.679334934669498e-05 tokens_per_second_per_gpu:4154.882998507472 mfu:19.59929200009834 Step 2544 | loss:1.3525538444519043 lr:3.678371386191601e-05 tokens_per_second_per_gpu:4357.174173715372 mfu:20.553533987987514 Step 2545 | loss:1.2414493560791016 lr:3.677407612618734e-05 tokens_per_second_per_gpu:4218.566944648648 mfu:19.89970003964791 Step 2546 | loss:1.5928407907485962 lr:3.676443614135e-05 tokens_per_second_per_gpu:5211.969841386028 mfu:24.585750995569775 Step 2547 | loss:1.4632339477539062 lr:3.675479390924542e-05 tokens_per_second_per_gpu:3811.8818002275757 mfu:17.981296825773047 Step 2548 | loss:1.2571916580200195 lr:3.6745149431715504e-05 tokens_per_second_per_gpu:5322.238596603596 mfu:25.105907527720703 Step 2549 | loss:1.45608389377594 lr:3.673550271060255e-05 tokens_per_second_per_gpu:4619.217928108643 mfu:21.78963908673535 Step 2550 | loss:1.2427103519439697 lr:3.6725853747749286e-05 tokens_per_second_per_gpu:5318.739458700587 mfu:25.08940149721772 Step 2551 | loss:1.2927790880203247 lr:3.6716202544998886e-05 tokens_per_second_per_gpu:4281.683209163447 mfu:20.19743022810938 Step 2552 | loss:1.2767382860183716 lr:3.670654910419495e-05 tokens_per_second_per_gpu:4882.266991181065 mfu:23.030486398046087 Step 2553 | loss:1.309913158416748 lr:3.6696893427181475e-05 tokens_per_second_per_gpu:4337.253528479802 mfu:20.459564905598782 Step 2554 | loss:1.2509493827819824 lr:3.668723551580293e-05 tokens_per_second_per_gpu:5113.554965984996 mfu:24.121511236993896 Step 2555 | loss:1.4433362483978271 lr:3.667757537190419e-05 tokens_per_second_per_gpu:5300.762666828788 mfu:25.004601902801472 Step 2556 | loss:1.3100632429122925 lr:3.666791299733054e-05 tokens_per_second_per_gpu:4759.583344355467 mfu:22.45176670398115 Step 2557 | loss:1.2135114669799805 lr:3.665824839392773e-05 tokens_per_second_per_gpu:3320.9398711724302 mfu:15.665439983089428 Step 2558 | loss:1.325790286064148 lr:3.6648581563541884e-05 tokens_per_second_per_gpu:5302.862316031418 mfu:25.014506306327377 Step 2559 | loss:1.2690452337265015 lr:3.66389125080196e-05 tokens_per_second_per_gpu:5311.961580976246 mfu:25.05742909156682 Step 2560 | loss:1.3260794878005981 lr:3.662924122920788e-05 tokens_per_second_per_gpu:5336.905508525601 mfu:25.17509385369002 Step 2561 | loss:1.3232207298278809 lr:3.661956772895415e-05 tokens_per_second_per_gpu:5325.404912576441 mfu:25.120843580393824 Step 2562 | loss:1.2840021848678589 lr:3.660989200910625e-05 tokens_per_second_per_gpu:4533.890065139589 mfu:21.387132998675682 Step 2563 | loss:1.3152134418487549 lr:3.660021407151248e-05 tokens_per_second_per_gpu:5344.278506262054 mfu:25.209873541975995 Step 2564 | loss:1.5582456588745117 lr:3.6590533918021517e-05 tokens_per_second_per_gpu:3450.4781872006215 mfu:16.276494321310157 Step 2565 | loss:1.274543046951294 lr:3.65808515504825e-05 tokens_per_second_per_gpu:5200.581037507905 mfu:24.532028064546363 Step 2566 | loss:1.1719919443130493 lr:3.657116697074496e-05 tokens_per_second_per_gpu:5308.514383679808 mfu:25.041168073767007 Step 2567 | loss:1.4222065210342407 lr:3.6561480180658884e-05 tokens_per_second_per_gpu:5027.529170580951 mfu:23.715712882558826 Step 2568 | loss:1.3630954027175903 lr:3.655179118207466e-05 tokens_per_second_per_gpu:5333.506538000388 mfu:25.159060329798415 Step 2569 | loss:1.336881399154663 lr:3.654209997684308e-05 tokens_per_second_per_gpu:5319.408656161601 mfu:25.092558215818183 Step 2570 | loss:1.4270910024642944 lr:3.65324065668154e-05 tokens_per_second_per_gpu:5296.003429538987 mfu:24.98215176849587 Step 2571 | loss:1.1453132629394531 lr:3.652271095384326e-05 tokens_per_second_per_gpu:5307.2489101194515 mfu:25.035198619070755 Step 2572 | loss:1.299247145652771 lr:3.651301313977876e-05 tokens_per_second_per_gpu:4233.462198485594 mfu:19.969963493389148 Step 2573 | loss:1.3829481601715088 lr:3.650331312647437e-05 tokens_per_second_per_gpu:3791.600201317853 mfu:17.885625063318287 Step 2574 | loss:1.2578258514404297 lr:3.649361091578303e-05 tokens_per_second_per_gpu:4300.019422217372 mfu:20.28392527356529 Step 2575 | loss:1.4650059938430786 lr:3.6483906509558055e-05 tokens_per_second_per_gpu:5062.413862645575 mfu:23.88026992696987 Step 2576 | loss:1.261587142944336 lr:3.6474199909653207e-05 tokens_per_second_per_gpu:4477.82616389783 mfu:21.12267001103039 Step 2577 | loss:1.361556887626648 lr:3.646449111792267e-05 tokens_per_second_per_gpu:4480.405900056269 mfu:21.134839066638122 Step 2578 | loss:1.486104965209961 lr:3.645478013622103e-05 tokens_per_second_per_gpu:5301.844965641208 mfu:25.009707290958875 Step 2579 | loss:1.291974425315857 lr:3.644506696640331e-05 tokens_per_second_per_gpu:4371.944343323208 mfu:20.62320739807847 Step 2580 | loss:1.3070813417434692 lr:3.643535161032493e-05 tokens_per_second_per_gpu:4476.128130832444 mfu:21.11466009934665 Step 2581 | loss:1.4896116256713867 lr:3.642563406984173e-05 tokens_per_second_per_gpu:3971.666287230579 mfu:18.735027513010866 Step 2582 | loss:1.326822280883789 lr:3.641591434680999e-05 tokens_per_second_per_gpu:5313.690556950809 mfu:25.06558496623255 Step 2583 | loss:1.1633062362670898 lr:3.640619244308639e-05 tokens_per_second_per_gpu:4816.706866217509 mfu:22.721228102882236 Step 2584 | loss:1.2828305959701538 lr:3.6396468360528016e-05 tokens_per_second_per_gpu:4882.271795774902 mfu:23.03050906213496 Step 2585 | loss:1.3896124362945557 lr:3.63867421009924e-05 tokens_per_second_per_gpu:4647.8098254755605 mfu:21.924511944895823 Step 2586 | loss:1.1623159646987915 lr:3.637701366633746e-05 tokens_per_second_per_gpu:3969.857487993469 mfu:18.726495098396448 Step 2587 | loss:1.3336576223373413 lr:3.636728305842154e-05 tokens_per_second_per_gpu:5363.824399310341 mfu:25.302074854357997 Step 2588 | loss:1.1910529136657715 lr:3.6357550279103416e-05 tokens_per_second_per_gpu:5212.687386089748 mfu:24.589135776362973 Step 2589 | loss:1.1427136659622192 lr:3.6347815330242255e-05 tokens_per_second_per_gpu:4434.513006645688 mfu:20.918354458285375 Step 2590 | loss:1.2875653505325317 lr:3.6338078213697634e-05 tokens_per_second_per_gpu:5307.636943234984 mfu:25.037029037481997 Step 2591 | loss:1.2449092864990234 lr:3.6328338931329585e-05 tokens_per_second_per_gpu:5302.346262930986 mfu:25.0120719958049 Step 2592 | loss:1.4173849821090698 lr:3.631859748499851e-05 tokens_per_second_per_gpu:5290.104801116992 mfu:24.954326931819534 Step 2593 | loss:1.2498688697814941 lr:3.630885387656523e-05 tokens_per_second_per_gpu:5312.343848325524 mfu:25.059232311874897 Step 2594 | loss:1.3550482988357544 lr:3.629910810789101e-05 tokens_per_second_per_gpu:3619.9464000856165 mfu:17.075904795747338 Step 2595 | loss:1.282987356185913 lr:3.62893601808375e-05 tokens_per_second_per_gpu:4531.78137380159 mfu:21.3771859418545 Step 2596 | loss:1.3755062818527222 lr:3.627961009726676e-05 tokens_per_second_per_gpu:5308.212251129461 mfu:25.039742862977896 Step 2597 | loss:1.3953540325164795 lr:3.626985785904129e-05 tokens_per_second_per_gpu:5298.983943579195 mfu:24.99621136175166 Step 2598 | loss:1.327476143836975 lr:3.6260103468023966e-05 tokens_per_second_per_gpu:4410.023573960553 mfu:20.802833625981524 Step 2599 | loss:1.3016386032104492 lr:3.6250346926078096e-05 tokens_per_second_per_gpu:4551.56817421857 mfu:21.470523655397663 Step 2600 | loss:1.179420828819275 lr:3.6240588235067405e-05 tokens_per_second_per_gpu:4628.648890626697 mfu:21.834126546021135 Step 2601 | loss:1.2248663902282715 lr:3.6230827396856e-05 tokens_per_second_per_gpu:4732.178736955093 mfu:22.32249449516542 Step 2602 | loss:1.1205098628997803 lr:3.622106441330844e-05 tokens_per_second_per_gpu:5145.416527560865 mfu:24.271807659090236 Step 2603 | loss:1.307477355003357 lr:3.621129928628965e-05 tokens_per_second_per_gpu:5314.475776981917 mfu:25.06928898309164 Step 2604 | loss:1.2656372785568237 lr:3.6201532017665e-05 tokens_per_second_per_gpu:5339.9397253987745 mfu:25.189406772371555 Step 2605 | loss:1.3196572065353394 lr:3.6191762609300246e-05 tokens_per_second_per_gpu:4186.537563265783 mfu:19.748611982888963 Step 2606 | loss:1.1765869855880737 lr:3.618199106306156e-05 tokens_per_second_per_gpu:5349.195415755899 mfu:25.233067442969727 Step 2607 | loss:1.491439700126648 lr:3.617221738081553e-05 tokens_per_second_per_gpu:3084.0079875516913 mfu:14.547791863302587 Step 2608 | loss:1.1793253421783447 lr:3.6162441564429136e-05 tokens_per_second_per_gpu:4827.574170825423 mfu:22.772491032871127 Step 2609 | loss:1.4058860540390015 lr:3.615266361576978e-05 tokens_per_second_per_gpu:4156.439441848176 mfu:19.606634008893064 Step 2610 | loss:1.3076543807983398 lr:3.6142883536705265e-05 tokens_per_second_per_gpu:3542.9306018857465 mfu:16.712608135388397 Step 2611 | loss:1.3840630054473877 lr:3.613310132910381e-05 tokens_per_second_per_gpu:4284.036021010784 mfu:20.208528843024364 Step 2612 | loss:1.333837628364563 lr:3.612331699483402e-05 tokens_per_second_per_gpu:4120.097791250272 mfu:19.43520424249778 Step 2613 | loss:1.2687162160873413 lr:3.611353053576493e-05 tokens_per_second_per_gpu:4360.128337098774 mfu:20.567469280699267 Step 2614 | loss:1.5017768144607544 lr:3.610374195376596e-05 tokens_per_second_per_gpu:3761.3254449151364 mfu:17.74281387196059 Step 2615 | loss:1.4096674919128418 lr:3.609395125070695e-05 tokens_per_second_per_gpu:4344.025746414964 mfu:20.491510613058463 Step 2616 | loss:1.2367186546325684 lr:3.608415842845814e-05 tokens_per_second_per_gpu:4766.421081470294 mfu:22.484021476590044 Step 2617 | loss:1.2227270603179932 lr:3.6074363488890185e-05 tokens_per_second_per_gpu:5210.213907508194 mfu:24.57746795587482 Step 2618 | loss:1.0810612440109253 lr:3.606456643387412e-05 tokens_per_second_per_gpu:3466.540705937601 mfu:16.352263962740782 Step 2619 | loss:1.2330561876296997 lr:3.605476726528141e-05 tokens_per_second_per_gpu:5227.370576627722 mfu:24.65839889134123 Step 2620 | loss:1.3329898118972778 lr:3.60449659849839e-05 tokens_per_second_per_gpu:4840.080455744624 mfu:22.831485312627237 Step 2621 | loss:1.363142490386963 lr:3.6035162594853864e-05 tokens_per_second_per_gpu:3510.7770979134425 mfu:16.56093457119757 Step 2622 | loss:1.2064729928970337 lr:3.6025357096763965e-05 tokens_per_second_per_gpu:3709.078933972175 mfu:17.496358165668674 Step 2623 | loss:1.373703122138977 lr:3.6015549492587255e-05 tokens_per_second_per_gpu:4858.8372537777295 mfu:22.919964329189135 Step 2624 | loss:1.4506877660751343 lr:3.6005739784197224e-05 tokens_per_second_per_gpu:5315.106119073148 mfu:25.072262414283426 Step 2625 | loss:1.364694595336914 lr:3.5995927973467725e-05 tokens_per_second_per_gpu:4978.904935540031 mfu:23.486344069720836 Step 2626 | loss:1.3323966264724731 lr:3.598611406227304e-05 tokens_per_second_per_gpu:4844.504133926983 mfu:22.85235255737075 Step 2627 | loss:1.2696205377578735 lr:3.597629805248785e-05 tokens_per_second_per_gpu:3341.732149851593 mfu:15.76352070914759 Step 2628 | loss:1.4226402044296265 lr:3.596647994598722e-05 tokens_per_second_per_gpu:5286.7323771522 mfu:24.938418632582746 Step 2629 | loss:1.3978490829467773 lr:3.5956659744646615e-05 tokens_per_second_per_gpu:5301.02288525096 mfu:25.0058293974967 Step 2630 | loss:1.312413215637207 lr:3.594683745034193e-05 tokens_per_second_per_gpu:4832.312713110049 mfu:22.79484354530639 Step 2631 | loss:1.2988336086273193 lr:3.593701306494943e-05 tokens_per_second_per_gpu:4146.3412170505235 mfu:19.558998959587722 Step 2632 | loss:1.3218865394592285 lr:3.59271865903458e-05 tokens_per_second_per_gpu:4669.130808819276 mfu:22.025086661062996 Step 2633 | loss:1.293389081954956 lr:3.59173580284081e-05 tokens_per_second_per_gpu:4896.011466032316 mfu:23.09532143096866 Step 2634 | loss:1.180067539215088 lr:3.5907527381013806e-05 tokens_per_second_per_gpu:5085.3753195303625 mfu:23.988583036723927 Step 2635 | loss:1.318212628364563 lr:3.589769465004079e-05 tokens_per_second_per_gpu:3692.908668326977 mfu:17.42008026368846 Step 2636 | loss:1.3228163719177246 lr:3.588785983736732e-05 tokens_per_second_per_gpu:4349.378323666599 mfu:20.516759633198276 Step 2637 | loss:1.473704218864441 lr:3.587802294487207e-05 tokens_per_second_per_gpu:3748.300985246335 mfu:17.681375273500887 Step 2638 | loss:1.457792043685913 lr:3.586818397443409e-05 tokens_per_second_per_gpu:3906.8130104912266 mfu:18.429103541521336 Step 2639 | loss:1.4290390014648438 lr:3.5858342927932864e-05 tokens_per_second_per_gpu:5015.126479462941 mfu:23.657207272437862 Step 2640 | loss:1.3085111379623413 lr:3.584849980724823e-05 tokens_per_second_per_gpu:4292.909202354635 mfu:20.25038515334416 Step 2641 | loss:1.3710339069366455 lr:3.583865461426043e-05 tokens_per_second_per_gpu:4826.707618696017 mfu:22.76840335862768 Step 2642 | loss:1.3384596109390259 lr:3.5828807350850145e-05 tokens_per_second_per_gpu:5206.510844452808 mfu:24.559999975634856 Step 2643 | loss:1.3661690950393677 lr:3.5818958018898405e-05 tokens_per_second_per_gpu:5307.212667813409 mfu:25.03502765792958 Step 2644 | loss:1.4086631536483765 lr:3.580910662028664e-05 tokens_per_second_per_gpu:5306.9659783903835 mfu:25.03386398183161 Step 2645 | loss:1.422140121459961 lr:3.57992531568967e-05 tokens_per_second_per_gpu:4248.013742489568 mfu:20.038605609205316 Step 2646 | loss:1.2941268682479858 lr:3.5789397630610796e-05 tokens_per_second_per_gpu:5314.237902553236 mfu:25.06816688882599 Step 2647 | loss:1.1842002868652344 lr:3.5779540043311574e-05 tokens_per_second_per_gpu:4350.583506407765 mfu:20.522444685813735 Step 2648 | loss:1.469372272491455 lr:3.576968039688205e-05 tokens_per_second_per_gpu:3891.187194319093 mfu:18.35539390059823 Step 2649 | loss:1.3142441511154175 lr:3.57598186932056e-05 tokens_per_second_per_gpu:4528.368959880534 mfu:21.361089003171024 Step 2650 | loss:1.2748075723648071 lr:3.574995493416607e-05 tokens_per_second_per_gpu:5301.905671606355 mfu:25.00999365135398 Step 2651 | loss:1.0881155729293823 lr:3.5740089121647636e-05 tokens_per_second_per_gpu:4873.552374905742 mfu:22.98937806620853 Step 2652 | loss:1.4880577325820923 lr:3.573022125753488e-05 tokens_per_second_per_gpu:3181.8848768950766 mfu:15.009493849854657 Step 2653 | loss:1.5410408973693848 lr:3.57203513437128e-05 tokens_per_second_per_gpu:4518.080864253401 mfu:21.31255830076772 Step 2654 | loss:1.3676725625991821 lr:3.571047938206674e-05 tokens_per_second_per_gpu:5267.492831972102 mfu:24.847662415363327 Step 2655 | loss:1.3582707643508911 lr:3.57006053744825e-05 tokens_per_second_per_gpu:5305.377420490725 mfu:25.026370483182998 Step 2656 | loss:1.2207993268966675 lr:3.569072932284621e-05 tokens_per_second_per_gpu:4739.834593513501 mfu:22.358608476775256 Step 2657 | loss:1.432196855545044 lr:3.56808512290444e-05 tokens_per_second_per_gpu:3528.2984335901506 mfu:16.64358570103273 Step 2658 | loss:1.3582684993743896 lr:3.567097109496405e-05 tokens_per_second_per_gpu:3940.1302090265526 mfu:18.586266451512703 Step 2659 | loss:1.2977784872055054 lr:3.566108892249244e-05 tokens_per_second_per_gpu:4658.036534916851 mfu:21.972753078186944 Step 2660 | loss:1.2706677913665771 lr:3.565120471351729e-05 tokens_per_second_per_gpu:3775.595605260771 mfu:17.810128653051365 Step 2661 | loss:1.3823093175888062 lr:3.564131846992673e-05 tokens_per_second_per_gpu:5276.836185224706 mfu:24.891736606796307 Step 2662 | loss:1.2938698530197144 lr:3.5631430193609236e-05 tokens_per_second_per_gpu:4268.496141789125 mfu:20.135224581359005 Step 2663 | loss:1.3825782537460327 lr:3.562153988645366e-05 tokens_per_second_per_gpu:5072.026246567624 mfu:23.925613181971986 Step 2664 | loss:1.243187427520752 lr:3.5611647550349315e-05 tokens_per_second_per_gpu:4243.085151053512 mfu:20.01535660249703 Step 2665 | loss:1.3589540719985962 lr:3.5601753187185825e-05 tokens_per_second_per_gpu:3030.244084737432 mfu:14.294178360660007 Step 2666 | loss:1.4305704832077026 lr:3.559185679885324e-05 tokens_per_second_per_gpu:3923.7340169413815 mfu:18.508922815968113 Step 2667 | loss:1.4573323726654053 lr:3.5581958387242e-05 tokens_per_second_per_gpu:5357.022466832038 mfu:25.26998897832849 Step 2668 | loss:1.3630266189575195 lr:3.55720579542429e-05 tokens_per_second_per_gpu:4197.9084901255865 mfu:19.80225058496683 Step 2669 | loss:1.2965404987335205 lr:3.556215550174714e-05 tokens_per_second_per_gpu:4260.35724745641 mfu:20.09683202815302 Step 2670 | loss:1.2857005596160889 lr:3.555225103164634e-05 tokens_per_second_per_gpu:5014.104787747296 mfu:23.65238777829658 Step 2671 | loss:1.4258376359939575 lr:3.554234454583244e-05 tokens_per_second_per_gpu:4786.962039519933 mfu:22.580916680359017 Step 2672 | loss:1.359808325767517 lr:3.553243604619781e-05 tokens_per_second_per_gpu:4257.459472163419 mfu:20.083162727684538 Step 2673 | loss:1.32943594455719 lr:3.55225255346352e-05 tokens_per_second_per_gpu:3571.4539620399105 mfu:16.84715769182266 Step 2674 | loss:1.1914420127868652 lr:3.551261301303771e-05 tokens_per_second_per_gpu:3775.8612674715387 mfu:17.811381827026203 Step 2675 | loss:1.2942291498184204 lr:3.550269848329888e-05 tokens_per_second_per_gpu:3612.413064193202 mfu:17.040368765023178 Step 2676 | loss:1.2041065692901611 lr:3.549278194731259e-05 tokens_per_second_per_gpu:5142.331054089207 mfu:24.25725295428837 Step 2677 | loss:1.110803246498108 lr:3.5482863406973125e-05 tokens_per_second_per_gpu:5224.983371299402 mfu:24.64713803650832 Step 2678 | loss:1.3772462606430054 lr:3.547294286417514e-05 tokens_per_second_per_gpu:4326.185354400403 mfu:20.407354440041033 Step 2679 | loss:1.2647887468338013 lr:3.546302032081367e-05 tokens_per_second_per_gpu:4417.161711753573 mfu:20.836505439843094 Step 2680 | loss:1.1732088327407837 lr:3.5453095778784156e-05 tokens_per_second_per_gpu:4186.788055789184 mfu:19.749793598860276 Step 2681 | loss:1.2629326581954956 lr:3.544316923998239e-05 tokens_per_second_per_gpu:4459.188715201797 mfu:21.034753985654557 Step 2682 | loss:1.1223814487457275 lr:3.5433240706304584e-05 tokens_per_second_per_gpu:5324.67093891161 mfu:25.117381301387997 Step 2683 | loss:1.2348928451538086 lr:3.5423310179647276e-05 tokens_per_second_per_gpu:4601.170559322675 mfu:21.704506568973308 Step 2684 | loss:1.441386103630066 lr:3.5413377661907424e-05 tokens_per_second_per_gpu:4510.407050407353 mfu:21.276359611568264 Step 2685 | loss:1.453413963317871 lr:3.540344315498238e-05 tokens_per_second_per_gpu:3639.5324780010974 mfu:17.168295667004145 Step 2686 | loss:1.365351676940918 lr:3.5393506660769835e-05 tokens_per_second_per_gpu:2745.8286459575534 mfu:12.952542209657596 Step 2687 | loss:1.2222131490707397 lr:3.538356818116788e-05 tokens_per_second_per_gpu:4872.691489721844 mfu:22.985317123913923 Step 2688 | loss:1.427319884300232 lr:3.537362771807499e-05 tokens_per_second_per_gpu:5305.010868081692 mfu:25.024641392929297 Step 2689 | loss:1.2973769903182983 lr:3.5363685273390015e-05 tokens_per_second_per_gpu:4548.700855268833 mfu:21.456998022696695 Step 2690 | loss:1.307582974433899 lr:3.535374084901217e-05 tokens_per_second_per_gpu:4993.562115784164 mfu:23.555484489705233 Step 2691 | loss:1.2196311950683594 lr:3.534379444684107e-05 tokens_per_second_per_gpu:5222.476978148961 mfu:24.63531495238292 Step 2692 | loss:1.3646152019500732 lr:3.53338460687767e-05 tokens_per_second_per_gpu:4683.714769324255 mfu:22.09388169104523 Step 2693 | loss:1.1450095176696777 lr:3.5323895716719404e-05 tokens_per_second_per_gpu:4802.739293477309 mfu:22.655340679153063 Step 2694 | loss:1.240631103515625 lr:3.531394339256994e-05 tokens_per_second_per_gpu:5333.437965803742 mfu:25.158736863047217 Step 2695 | loss:1.3109256029129028 lr:3.5303989098229404e-05 tokens_per_second_per_gpu:4383.748282375501 mfu:20.678888592547814 Step 2696 | loss:1.2558308839797974 lr:3.529403283559929e-05 tokens_per_second_per_gpu:5308.175341559246 mfu:25.039568754237767 Step 2697 | loss:1.2855850458145142 lr:3.5284074606581475e-05 tokens_per_second_per_gpu:4514.9878503446 mfu:21.297968026437314 Step 2698 | loss:1.251725435256958 lr:3.5274114413078195e-05 tokens_per_second_per_gpu:5351.196317556376 mfu:25.242506038151628 Step 2699 | loss:1.1621894836425781 lr:3.5264152256992055e-05 tokens_per_second_per_gpu:4852.932778258684 mfu:22.8921119107584 Step 2700 | loss:1.4173049926757812 lr:3.5254188140226066e-05 tokens_per_second_per_gpu:4512.248648434972 mfu:21.28504674367356 Step 2701 | loss:1.640120029449463 lr:3.5244222064683594e-05 tokens_per_second_per_gpu:5304.159109390016 mfu:25.020623501855646 Step 2702 | loss:1.3619897365570068 lr:3.5234254032268354e-05 tokens_per_second_per_gpu:4970.009486242388 mfu:23.444382717663704 Step 2703 | loss:1.332250714302063 lr:3.522428404488449e-05 tokens_per_second_per_gpu:4250.336142069472 mfu:20.049560764265944 Step 2704 | loss:1.2021613121032715 lr:3.521431210443648e-05 tokens_per_second_per_gpu:4289.583821621574 mfu:20.234698765057853 Step 2705 | loss:1.326938271522522 lr:3.5204338212829166e-05 tokens_per_second_per_gpu:5339.357507706346 mfu:25.18666035217979 Step 2706 | loss:1.3778038024902344 lr:3.519436237196781e-05 tokens_per_second_per_gpu:4359.799784852379 mfu:20.56591944369623 Step 2707 | loss:1.3901416063308716 lr:3.5184384583758015e-05 tokens_per_second_per_gpu:3617.3613269611656 mfu:17.06371056476035 Step 2708 | loss:1.3782306909561157 lr:3.517440485010573e-05 tokens_per_second_per_gpu:3959.072130579547 mfu:18.67561872730325 Step 2709 | loss:1.551216959953308 lr:3.516442317291734e-05 tokens_per_second_per_gpu:5339.405307410114 mfu:25.186885831537932 Step 2710 | loss:1.2024691104888916 lr:3.515443955409955e-05 tokens_per_second_per_gpu:5336.349980970011 mfu:25.172473335427522 Step 2711 | loss:1.4400289058685303 lr:3.514445399555944e-05 tokens_per_second_per_gpu:5358.161619404695 mfu:25.275362555373185 Step 2712 | loss:1.436850905418396 lr:3.513446649920449e-05 tokens_per_second_per_gpu:4128.110122155454 mfu:19.47299977442214 Step 2713 | loss:1.3239781856536865 lr:3.512447706694254e-05 tokens_per_second_per_gpu:5319.964239796296 mfu:25.09517899861538 Step 2714 | loss:1.355043649673462 lr:3.5114485700681764e-05 tokens_per_second_per_gpu:4222.50513166105 mfu:19.9182771397094 Step 2715 | loss:1.4613828659057617 lr:3.510449240233076e-05 tokens_per_second_per_gpu:5264.767675653784 mfu:24.83480738805021 Step 2716 | loss:1.1770012378692627 lr:3.5094497173798455e-05 tokens_per_second_per_gpu:4614.345282821264 mfu:21.76665398755577 Step 2717 | loss:1.352020502090454 lr:3.508450001699416e-05 tokens_per_second_per_gpu:4068.7692008902877 mfu:19.19307852420917 Step 2718 | loss:1.4111909866333008 lr:3.507450093382756e-05 tokens_per_second_per_gpu:4048.701271841529 mfu:19.098414678944412 Step 2719 | loss:1.5831149816513062 lr:3.506449992620869e-05 tokens_per_second_per_gpu:3424.28376489793 mfu:16.152930762079063 Step 2720 | loss:1.4029357433319092 lr:3.505449699604797e-05 tokens_per_second_per_gpu:4917.737632398457 mfu:23.197807464583967 Step 2721 | loss:1.4599320888519287 lr:3.5044492145256174e-05 tokens_per_second_per_gpu:3362.7811782961207 mfu:15.862812567655007 Step 2722 | loss:1.324320673942566 lr:3.503448537574446e-05 tokens_per_second_per_gpu:5316.987867391861 mfu:25.081138942162163 Step 2723 | loss:1.257902979850769 lr:3.502447668942434e-05 tokens_per_second_per_gpu:5333.236004346432 mfu:25.157784176394905 Step 2724 | loss:1.5230530500411987 lr:3.501446608820769e-05 tokens_per_second_per_gpu:4916.8258617519205 mfu:23.193506486880143 Step 2725 | loss:1.470993995666504 lr:3.5004453574006755e-05 tokens_per_second_per_gpu:5033.31774031539 mfu:23.743018553628016 Step 2726 | loss:1.3164618015289307 lr:3.4994439148734146e-05 tokens_per_second_per_gpu:4045.7125456509725 mfu:19.084316347574283 Step 2727 | loss:1.2996244430541992 lr:3.4984422814302846e-05 tokens_per_second_per_gpu:4879.473736057392 mfu:23.01731013704925 Step 2728 | loss:1.3631829023361206 lr:3.497440457262619e-05 tokens_per_second_per_gpu:3595.455955504234 mfu:16.960379190156242 Step 2729 | loss:1.2291780710220337 lr:3.496438442561789e-05 tokens_per_second_per_gpu:4437.222136822716 mfu:20.93113388755569 Step 2730 | loss:1.4736013412475586 lr:3.4954362375192005e-05 tokens_per_second_per_gpu:4101.904408331616 mfu:19.349382951159267 Step 2731 | loss:1.4130878448486328 lr:3.494433842326298e-05 tokens_per_second_per_gpu:3793.8561931903364 mfu:17.896266961892692 Step 2732 | loss:1.3240519762039185 lr:3.49343125717456e-05 tokens_per_second_per_gpu:4858.2842784698505 mfu:22.917355850314557 Step 2733 | loss:1.328341007232666 lr:3.492428482255504e-05 tokens_per_second_per_gpu:4572.256072165947 mfu:21.568111999734803 Step 2734 | loss:1.2430869340896606 lr:3.4914255177606806e-05 tokens_per_second_per_gpu:5304.047715162094 mfu:25.020098036276725 Step 2735 | loss:1.3621587753295898 lr:3.490422363881678e-05 tokens_per_second_per_gpu:4571.193345081417 mfu:21.563098934757136 Step 2736 | loss:1.3246921300888062 lr:3.4894190208101224e-05 tokens_per_second_per_gpu:4099.987775427542 mfu:19.340341866739458 Step 2737 | loss:1.3681483268737793 lr:3.488415488737673e-05 tokens_per_second_per_gpu:4798.883865447785 mfu:22.637153967333948 Step 2738 | loss:1.2581442594528198 lr:3.4874117678560275e-05 tokens_per_second_per_gpu:5313.132726926628 mfu:25.06295358683287 Step 2739 | loss:1.431503176689148 lr:3.486407858356918e-05 tokens_per_second_per_gpu:5231.978401972924 mfu:24.68013478967062 Step 2740 | loss:1.2460136413574219 lr:3.485403760432114e-05 tokens_per_second_per_gpu:5295.73534151113 mfu:24.980887151527934 Step 2741 | loss:1.309138536453247 lr:3.484399474273421e-05 tokens_per_second_per_gpu:4179.460840858669 mfu:19.715229875881256 Step 2742 | loss:1.211937665939331 lr:3.4833950000726784e-05 tokens_per_second_per_gpu:4912.010108480291 mfu:23.17078975704563 Step 2743 | loss:1.3478177785873413 lr:3.482390338021764e-05 tokens_per_second_per_gpu:3793.4937112381513 mfu:17.894557072678438 Step 2744 | loss:1.2423306703567505 lr:3.48138548831259e-05 tokens_per_second_per_gpu:4469.008094260144 mfu:21.081073672031604 Step 2745 | loss:1.414804458618164 lr:3.480380451137104e-05 tokens_per_second_per_gpu:4675.009832042796 mfu:22.052819016673137 Step 2746 | loss:1.344724416732788 lr:3.4793752266872917e-05 tokens_per_second_per_gpu:3504.7468701157627 mfu:16.53248895781296 Step 2747 | loss:1.316593050956726 lr:3.4783698151551736e-05 tokens_per_second_per_gpu:5321.259632335725 mfu:25.101289586240622 Step 2748 | loss:1.378082036972046 lr:3.477364216732804e-05 tokens_per_second_per_gpu:5309.827149102736 mfu:25.047360612247843 Step 2749 | loss:1.1676316261291504 lr:3.4763584316122755e-05 tokens_per_second_per_gpu:5345.382911688466 mfu:25.215083210803378 Step 2750 | loss:1.5063053369522095 lr:3.475352459985714e-05 tokens_per_second_per_gpu:3981.4678582868914 mfu:18.78126319600396 Step 2751 | loss:1.1940855979919434 lr:3.474346302045284e-05 tokens_per_second_per_gpu:5317.477496195644 mfu:25.083448604768893 Step 2752 | loss:1.3380976915359497 lr:3.473339957983183e-05 tokens_per_second_per_gpu:5319.957283425323 mfu:25.095146184226625 Step 2753 | loss:1.2757803201675415 lr:3.472333427991645e-05 tokens_per_second_per_gpu:5321.558236666772 mfu:25.102698153817325 Step 2754 | loss:1.1865817308425903 lr:3.4713267122629386e-05 tokens_per_second_per_gpu:5291.101297503391 mfu:24.959027575293995 Step 2755 | loss:1.0969302654266357 lr:3.470319810989371e-05 tokens_per_second_per_gpu:4875.047718407519 mfu:22.99643185663832 Step 2756 | loss:1.3324416875839233 lr:3.469312724363281e-05 tokens_per_second_per_gpu:4583.736244438869 mfu:21.62226593106554 Step 2757 | loss:1.2116615772247314 lr:3.4683054525770434e-05 tokens_per_second_per_gpu:4765.202435910739 mfu:22.47827291756325 Step 2758 | loss:1.3183499574661255 lr:3.467297995823071e-05 tokens_per_second_per_gpu:4333.070503078359 mfu:20.439832861082447 Step 2759 | loss:1.116244912147522 lr:3.466290354293811e-05 tokens_per_second_per_gpu:4778.208831375914 mfu:22.539626304092376 Step 2760 | loss:1.277965784072876 lr:3.465282528181743e-05 tokens_per_second_per_gpu:4282.234506201267 mfu:20.200030790297753 Step 2761 | loss:1.4156450033187866 lr:3.464274517679386e-05 tokens_per_second_per_gpu:5307.408423137363 mfu:25.03595106919197 Step 2762 | loss:1.3150739669799805 lr:3.463266322979291e-05 tokens_per_second_per_gpu:4486.916564764844 mfu:21.165550982902413 Step 2763 | loss:1.324500560760498 lr:3.4622579442740454e-05 tokens_per_second_per_gpu:4637.102217522129 mfu:21.874002331273182 Step 2764 | loss:1.2840455770492554 lr:3.461249381756272e-05 tokens_per_second_per_gpu:4105.7718842989025 mfu:19.3676264951564 Step 2765 | loss:1.2993837594985962 lr:3.46024063561863e-05 tokens_per_second_per_gpu:5160.053706964597 mfu:24.340853731697965 Step 2766 | loss:1.425856590270996 lr:3.4592317060538106e-05 tokens_per_second_per_gpu:5262.353212353249 mfu:24.823417952711665 Step 2767 | loss:1.258333683013916 lr:3.458222593254541e-05 tokens_per_second_per_gpu:5309.4499281941735 mfu:25.045581196861626 Step 2768 | loss:1.2345325946807861 lr:3.457213297413587e-05 tokens_per_second_per_gpu:4433.08227894325 mfu:20.911605471605657 Step 2769 | loss:1.2961989641189575 lr:3.4562038187237435e-05 tokens_per_second_per_gpu:4526.631671690531 mfu:21.352893918366853 Step 2770 | loss:1.3706563711166382 lr:3.455194157377844e-05 tokens_per_second_per_gpu:5328.363388935298 mfu:25.134799218146664 Step 2771 | loss:1.2132823467254639 lr:3.454184313568756e-05 tokens_per_second_per_gpu:4292.413399452605 mfu:20.24804636646258 Step 2772 | loss:1.3809462785720825 lr:3.4531742874893834e-05 tokens_per_second_per_gpu:4906.900625866304 mfu:23.146687455787827 Step 2773 | loss:1.3613113164901733 lr:3.4521640793326614e-05 tokens_per_second_per_gpu:3935.1465934761713 mfu:18.562757886669065 Step 2774 | loss:1.2918031215667725 lr:3.451153689291564e-05 tokens_per_second_per_gpu:5306.726496222681 mfu:25.032734303586686 Step 2775 | loss:1.248009204864502 lr:3.450143117559097e-05 tokens_per_second_per_gpu:4198.750353828904 mfu:19.80622179969214 Step 2776 | loss:1.3743422031402588 lr:3.4491323643283016e-05 tokens_per_second_per_gpu:5319.585044368094 mfu:25.093390269083137 Step 2777 | loss:1.2565160989761353 lr:3.448121429792255e-05 tokens_per_second_per_gpu:5127.265666007243 mfu:24.186186948285485 Step 2778 | loss:1.2492705583572388 lr:3.447110314144067e-05 tokens_per_second_per_gpu:4796.391452705278 mfu:22.625396831178083 Step 2779 | loss:1.2698911428451538 lr:3.446099017576884e-05 tokens_per_second_per_gpu:4728.498059169878 mfu:22.305132110064175 Step 2780 | loss:1.2645288705825806 lr:3.4450875402838845e-05 tokens_per_second_per_gpu:4329.010720569541 mfu:20.42068217431803 Step 2781 | loss:1.3031895160675049 lr:3.444075882458285e-05 tokens_per_second_per_gpu:5350.884834036056 mfu:25.241036717241712 Step 2782 | loss:1.3167774677276611 lr:3.4430640442933326e-05 tokens_per_second_per_gpu:3824.2274694521343 mfu:18.03953345389366 Step 2783 | loss:1.4189387559890747 lr:3.442052025982312e-05 tokens_per_second_per_gpu:3684.0367473133488 mfu:17.378229898561365 Step 2784 | loss:1.4872852563858032 lr:3.441039827718541e-05 tokens_per_second_per_gpu:3628.159896339623 mfu:17.114649258944453 Step 2785 | loss:1.3132504224777222 lr:3.440027449695372e-05 tokens_per_second_per_gpu:3801.309107418973 mfu:17.931423629907464 Step 2786 | loss:1.199059247970581 lr:3.4390148921061905e-05 tokens_per_second_per_gpu:5318.757906433836 mfu:25.089488518322966 Step 2787 | loss:1.1442902088165283 lr:3.438002155144418e-05 tokens_per_second_per_gpu:5314.611705613735 mfu:25.069930181639737 Step 2788 | loss:1.4147849082946777 lr:3.436989239003509e-05 tokens_per_second_per_gpu:2520.0825761721208 mfu:11.887659482228534 Step 2789 | loss:1.502908706665039 lr:3.435976143876955e-05 tokens_per_second_per_gpu:5390.448855507419 mfu:25.42766695684026 Step 2790 | loss:1.4592348337173462 lr:3.434962869958277e-05 tokens_per_second_per_gpu:4438.521343764383 mfu:20.937262468367095 Step 2791 | loss:1.312465786933899 lr:3.433949417441034e-05 tokens_per_second_per_gpu:5321.88819746431 mfu:25.104254635196433 Step 2792 | loss:1.3143630027770996 lr:3.432935786518817e-05 tokens_per_second_per_gpu:4368.680922949105 mfu:20.607813287376892 Step 2793 | loss:1.2966500520706177 lr:3.431921977385253e-05 tokens_per_second_per_gpu:4512.9462036759005 mfu:21.28833723076022 Step 2794 | loss:1.40213143825531 lr:3.430907990234002e-05 tokens_per_second_per_gpu:3643.3127024856853 mfu:17.186127630870747 Step 2795 | loss:1.2632004022598267 lr:3.4298938252587565e-05 tokens_per_second_per_gpu:5246.745142693497 mfu:24.74979202511533 Step 2796 | loss:1.2274048328399658 lr:3.428879482653245e-05 tokens_per_second_per_gpu:5325.188284193866 mfu:25.119821707352603 Step 2797 | loss:1.3221184015274048 lr:3.427864962611231e-05 tokens_per_second_per_gpu:5310.496334297058 mfu:25.050517272984223 Step 2798 | loss:1.2094690799713135 lr:3.426850265326508e-05 tokens_per_second_per_gpu:4242.7725201223 mfu:20.013881869054163 Step 2799 | loss:1.2174310684204102 lr:3.4258353909929055e-05 tokens_per_second_per_gpu:3674.941093535068 mfu:17.335324147810656 Step 2800 | loss:1.374447226524353 lr:3.4248203398042896e-05 tokens_per_second_per_gpu:5023.474315098207 mfu:23.696585437417035 Step 2801 | loss:1.4013335704803467 lr:3.423805111954555e-05 tokens_per_second_per_gpu:4159.211822391568 mfu:19.619711800933135 Step 2802 | loss:1.3771971464157104 lr:3.4227897076376334e-05 tokens_per_second_per_gpu:5333.491422472208 mfu:25.158989027273016 Step 2803 | loss:1.2416892051696777 lr:3.421774127047489e-05 tokens_per_second_per_gpu:5312.776953932388 mfu:25.06127534491791 Step 2804 | loss:1.4492225646972656 lr:3.420758370378122e-05 tokens_per_second_per_gpu:5046.318832178758 mfu:23.804346922162527 Step 2805 | loss:1.4265809059143066 lr:3.4197424378235615e-05 tokens_per_second_per_gpu:5322.725546913433 mfu:25.108204555414495 Step 2806 | loss:1.4878358840942383 lr:3.418726329577875e-05 tokens_per_second_per_gpu:4722.017472607118 mfu:22.274562077545554 Step 2807 | loss:1.3374013900756836 lr:3.417710045835162e-05 tokens_per_second_per_gpu:5354.890267428051 mfu:25.259931029949158 Step 2808 | loss:1.3883423805236816 lr:3.4166935867895534e-05 tokens_per_second_per_gpu:5328.58463701236 mfu:25.135842883074986 Step 2809 | loss:1.4219759702682495 lr:3.415676952635217e-05 tokens_per_second_per_gpu:3701.6300704820524 mfu:17.4612206056786 Step 2810 | loss:1.1999591588974 lr:3.414660143566351e-05 tokens_per_second_per_gpu:3974.1437236787824 mfu:18.74671400343129 Step 2811 | loss:1.3280144929885864 lr:3.413643159777189e-05 tokens_per_second_per_gpu:5335.760000849151 mfu:25.169690298536437 Step 2812 | loss:1.3843059539794922 lr:3.4126260014619974e-05 tokens_per_second_per_gpu:3877.6702985488328 mfu:18.291632397029684 Step 2813 | loss:1.2224478721618652 lr:3.411608668815077e-05 tokens_per_second_per_gpu:5325.022678150303 mfu:25.119040515389813 Step 2814 | loss:1.3285317420959473 lr:3.410591162030758e-05 tokens_per_second_per_gpu:4714.651207164249 mfu:22.239814146637055 Step 2815 | loss:1.3000280857086182 lr:3.4095734813034094e-05 tokens_per_second_per_gpu:5318.6944726750025 mfu:25.08918929045963 Step 2816 | loss:1.276535153388977 lr:3.4085556268274305e-05 tokens_per_second_per_gpu:4529.0741075201395 mfu:21.364415304897637 Step 2817 | loss:1.2272002696990967 lr:3.407537598797252e-05 tokens_per_second_per_gpu:5340.004198602501 mfu:25.189710903473795 Step 2818 | loss:1.18864107131958 lr:3.4065193974073417e-05 tokens_per_second_per_gpu:3704.648222585231 mfu:17.475457744099142 Step 2819 | loss:1.320350170135498 lr:3.405501022852198e-05 tokens_per_second_per_gpu:5290.638457967633 mfu:24.956844282235256 Step 2820 | loss:1.294450283050537 lr:3.4044824753263515e-05 tokens_per_second_per_gpu:5312.901121201751 mfu:25.061861063112616 Step 2821 | loss:1.4928194284439087 lr:3.403463755024369e-05 tokens_per_second_per_gpu:4221.600936548808 mfu:19.91401189709336 Step 2822 | loss:1.406704306602478 lr:3.402444862140849e-05 tokens_per_second_per_gpu:4538.6155252176795 mfu:21.409423800110662 Step 2823 | loss:1.3104950189590454 lr:3.401425796870421e-05 tokens_per_second_per_gpu:5146.487701917397 mfu:24.27686057129119 Step 2824 | loss:1.4500350952148438 lr:3.4004065594077494e-05 tokens_per_second_per_gpu:3457.095348317669 mfu:16.307708599303375 Step 2825 | loss:1.285361409187317 lr:3.3993871499475326e-05 tokens_per_second_per_gpu:5333.738837641697 mfu:25.160156126840874 Step 2826 | loss:1.4736963510513306 lr:3.398367568684498e-05 tokens_per_second_per_gpu:4874.7239136774515 mfu:22.994904414479805 Step 2827 | loss:1.3267806768417358 lr:3.3973478158134094e-05 tokens_per_second_per_gpu:4882.84852058754 mfu:23.033229571475577 Step 2828 | loss:1.24372136592865 lr:3.3963278915290617e-05 tokens_per_second_per_gpu:3900.5583870748633 mfu:18.399599415717553 Step 2829 | loss:1.324196457862854 lr:3.3953077960262844e-05 tokens_per_second_per_gpu:3713.6626396983365 mfu:17.517980287639816 Step 2830 | loss:1.3098554611206055 lr:3.394287529499936e-05 tokens_per_second_per_gpu:4244.527823214304 mfu:20.022161933224734 Step 2831 | loss:1.3735508918762207 lr:3.3932670921449114e-05 tokens_per_second_per_gpu:2975.056831772856 mfu:14.033850672509812 Step 2832 | loss:1.3334540128707886 lr:3.392246484156136e-05 tokens_per_second_per_gpu:5280.938098391092 mfu:24.911086031060705 Step 2833 | loss:1.4019817113876343 lr:3.3912257057285685e-05 tokens_per_second_per_gpu:5122.822709873741 mfu:24.16522876615727 Step 2834 | loss:1.281995177268982 lr:3.3902047570572015e-05 tokens_per_second_per_gpu:5017.892366031748 mfu:23.670254431291834 Step 2835 | loss:1.284334659576416 lr:3.3891836383370566e-05 tokens_per_second_per_gpu:5322.135702966727 mfu:25.105422160880124 Step 2836 | loss:1.3256776332855225 lr:3.388162349763191e-05 tokens_per_second_per_gpu:4153.308869741125 mfu:19.591866566133422 Step 2837 | loss:1.1060595512390137 lr:3.387140891530695e-05 tokens_per_second_per_gpu:5327.029142147073 mfu:25.128505348400633 Step 2838 | loss:1.3618534803390503 lr:3.386119263834687e-05 tokens_per_second_per_gpu:5325.755084913726 mfu:25.12249540305436 Step 2839 | loss:1.3774527311325073 lr:3.3850974668703225e-05 tokens_per_second_per_gpu:3637.764221587703 mfu:17.159954499806506 Step 2840 | loss:1.3142389059066772 lr:3.3840755008327865e-05 tokens_per_second_per_gpu:4621.293090388059 mfu:21.799427981266547 Step 2841 | loss:1.2501318454742432 lr:3.383053365917296e-05 tokens_per_second_per_gpu:4715.627760791684 mfu:22.244420716714895 Step 2842 | loss:1.5390923023223877 lr:3.3820310623191026e-05 tokens_per_second_per_gpu:3686.3656449907307 mfu:17.389215706256493 Step 2843 | loss:1.5133917331695557 lr:3.381008590233489e-05 tokens_per_second_per_gpu:4391.199008237747 mfu:20.71403493766494 Step 2844 | loss:1.3675365447998047 lr:3.37998594985577e-05 tokens_per_second_per_gpu:4731.937891692791 mfu:22.3213583869707 Step 2845 | loss:1.247707486152649 lr:3.3789631413812916e-05 tokens_per_second_per_gpu:5297.804742188576 mfu:24.99064886759961 Step 2846 | loss:1.274354338645935 lr:3.377940165005434e-05 tokens_per_second_per_gpu:4487.520918649833 mfu:21.168401823291312 Step 2847 | loss:1.1645277738571167 lr:3.376917020923607e-05 tokens_per_second_per_gpu:4728.799541349321 mfu:22.30655425294277 Step 2848 | loss:1.4690173864364624 lr:3.375893709331254e-05 tokens_per_second_per_gpu:4296.314511528882 mfu:20.266448577724738 Step 2849 | loss:1.355992078781128 lr:3.374870230423852e-05 tokens_per_second_per_gpu:3952.7520492973213 mfu:18.645805825577934 Step 2850 | loss:1.2147622108459473 lr:3.373846584396905e-05 tokens_per_second_per_gpu:5306.3458371260695 mfu:25.030938669680832 Step 2851 | loss:1.3255302906036377 lr:3.372822771445954e-05 tokens_per_second_per_gpu:4750.457844689791 mfu:22.408720165087367 Step 2852 | loss:1.3387787342071533 lr:3.371798791766569e-05 tokens_per_second_per_gpu:4650.617685957566 mfu:21.93775710185984 Step 2853 | loss:1.333621621131897 lr:3.370774645554355e-05 tokens_per_second_per_gpu:4874.795374067927 mfu:22.99524150533408 Step 2854 | loss:1.3574090003967285 lr:3.369750333004943e-05 tokens_per_second_per_gpu:4521.917533785721 mfu:21.330656525554996 Step 2855 | loss:1.2428297996520996 lr:3.368725854314002e-05 tokens_per_second_per_gpu:5321.394234180531 mfu:25.10192452610802 Step 2856 | loss:1.3048921823501587 lr:3.367701209677229e-05 tokens_per_second_per_gpu:4184.114336337911 mfu:19.73718120802504 Step 2857 | loss:1.3430132865905762 lr:3.366676399290354e-05 tokens_per_second_per_gpu:5044.225806018451 mfu:23.794473760657272 Step 2858 | loss:1.5036969184875488 lr:3.365651423349138e-05 tokens_per_second_per_gpu:4858.954688105498 mfu:22.92051828694958 Step 2859 | loss:1.4265674352645874 lr:3.364626282049375e-05 tokens_per_second_per_gpu:3649.5148184518694 mfu:17.21538407007334 Step 2860 | loss:1.4859167337417603 lr:3.363600975586888e-05 tokens_per_second_per_gpu:3405.9835883067585 mfu:16.066605706766413 Step 2861 | loss:1.3618719577789307 lr:3.3625755041575355e-05 tokens_per_second_per_gpu:3645.4600999791223 mfu:17.196257271231083 Step 2862 | loss:1.348870038986206 lr:3.361549867957203e-05 tokens_per_second_per_gpu:5203.032799557327 mfu:24.54359344444722 Step 2863 | loss:1.4640636444091797 lr:3.360524067181811e-05 tokens_per_second_per_gpu:5270.078217884474 mfu:24.859858121824306 Step 2864 | loss:1.343968152999878 lr:3.35949810202731e-05 tokens_per_second_per_gpu:4674.471418323735 mfu:22.050279227297473 Step 2865 | loss:1.3509705066680908 lr:3.358471972689682e-05 tokens_per_second_per_gpu:3166.1108697851732 mfu:14.935085166994112 Step 2866 | loss:1.1820091009140015 lr:3.357445679364939e-05 tokens_per_second_per_gpu:5324.598893513319 mfu:25.117041450952044 Step 2867 | loss:1.1183650493621826 lr:3.356419222249127e-05 tokens_per_second_per_gpu:5304.392026337458 mfu:25.021722210836458 Step 2868 | loss:1.4305933713912964 lr:3.355392601538323e-05 tokens_per_second_per_gpu:5318.077497182776 mfu:25.086278911795922 Step 2869 | loss:1.3501904010772705 lr:3.354365817428631e-05 tokens_per_second_per_gpu:4268.5286689241075 mfu:20.135378017404417 Step 2870 | loss:1.345282793045044 lr:3.3533388701161934e-05 tokens_per_second_per_gpu:4845.013537016547 mfu:22.854755498657354 Step 2871 | loss:1.3320976495742798 lr:3.352311759797178e-05 tokens_per_second_per_gpu:3706.1614209610975 mfu:17.48259575901637 Step 2872 | loss:1.2733031511306763 lr:3.351284486667783e-05 tokens_per_second_per_gpu:3832.436251183057 mfu:18.07825567788101 Step 2873 | loss:1.4663071632385254 lr:3.350257050924245e-05 tokens_per_second_per_gpu:4231.771944779397 mfu:19.961990278269997 Step 2874 | loss:1.2801176309585571 lr:3.349229452762824e-05 tokens_per_second_per_gpu:4244.7693592888745 mfu:20.023301300098787 Step 2875 | loss:1.3752777576446533 lr:3.348201692379815e-05 tokens_per_second_per_gpu:5317.154902547169 mfu:25.081926875488886 Step 2876 | loss:1.211040735244751 lr:3.347173769971542e-05 tokens_per_second_per_gpu:3999.2545114165982 mfu:18.86516587353274 Step 2877 | loss:1.2353239059448242 lr:3.346145685734362e-05 tokens_per_second_per_gpu:5279.389638793635 mfu:24.90378168294505 Step 2878 | loss:1.4794143438339233 lr:3.345117439864661e-05 tokens_per_second_per_gpu:3000.447293487075 mfu:14.153621812475258 Step 2879 | loss:1.208682894706726 lr:3.344089032558856e-05 tokens_per_second_per_gpu:5292.603981496983 mfu:24.966115992076094 Step 2880 | loss:1.3981014490127563 lr:3.3430604640133985e-05 tokens_per_second_per_gpu:3783.968332481165 mfu:17.849624235884534 Step 2881 | loss:1.1835696697235107 lr:3.3420317344247636e-05 tokens_per_second_per_gpu:4146.088209937906 mfu:19.557805481870037 Step 2882 | loss:1.247713565826416 lr:3.3410028439894645e-05 tokens_per_second_per_gpu:4367.961228337465 mfu:20.60441836510123 Step 2883 | loss:1.292256236076355 lr:3.339973792904042e-05 tokens_per_second_per_gpu:5203.909030498958 mfu:24.54772677529931 Step 2884 | loss:1.3749408721923828 lr:3.338944581365065e-05 tokens_per_second_per_gpu:3907.928733327369 mfu:18.434366596501363 Step 2885 | loss:1.250324010848999 lr:3.337915209569138e-05 tokens_per_second_per_gpu:3568.2107945377425 mfu:16.831859117373497 Step 2886 | loss:1.065882921218872 lr:3.336885677712893e-05 tokens_per_second_per_gpu:4278.746166825243 mfu:20.183575698288976 Step 2887 | loss:1.1778661012649536 lr:3.3358559859929936e-05 tokens_per_second_per_gpu:4040.936573267921 mfu:19.06178727097852 Step 2888 | loss:1.2437177896499634 lr:3.3348261346061335e-05 tokens_per_second_per_gpu:5345.874756308543 mfu:25.217403325793622 Step 2889 | loss:1.2768621444702148 lr:3.3337961237490364e-05 tokens_per_second_per_gpu:4164.937461240958 mfu:19.646720616280437 Step 2890 | loss:1.3917418718338013 lr:3.3327659536184585e-05 tokens_per_second_per_gpu:5230.735588175486 mfu:24.674272224942204 Step 2891 | loss:1.3218108415603638 lr:3.331735624411184e-05 tokens_per_second_per_gpu:3663.811937377333 mfu:17.28282601938478 Step 2892 | loss:1.3054683208465576 lr:3.3307051363240285e-05 tokens_per_second_per_gpu:4782.477710642262 mfu:22.559763335937642 Step 2893 | loss:1.1587220430374146 lr:3.3296744895538394e-05 tokens_per_second_per_gpu:4664.448775956096 mfu:22.003000713210195 Step 2894 | loss:1.217677354812622 lr:3.3286436842974906e-05 tokens_per_second_per_gpu:5002.047284878505 mfu:23.59551048004237 Step 2895 | loss:1.4421876668930054 lr:3.32761272075189e-05 tokens_per_second_per_gpu:3432.577817753558 mfu:16.192055224510398 Step 2896 | loss:1.2863030433654785 lr:3.326581599113976e-05 tokens_per_second_per_gpu:5332.765169594283 mfu:25.155563168536325 Step 2897 | loss:1.206305980682373 lr:3.3255503195807124e-05 tokens_per_second_per_gpu:4699.958111570211 mfu:22.170504307819368 Step 2898 | loss:1.199326753616333 lr:3.324518882349099e-05 tokens_per_second_per_gpu:4064.941743135097 mfu:19.175023752946302 Step 2899 | loss:1.4186832904815674 lr:3.3234872876161624e-05 tokens_per_second_per_gpu:4351.584629088796 mfu:20.527167152309303 Step 2900 | loss:1.338151216506958 lr:3.3224555355789587e-05 tokens_per_second_per_gpu:3907.199444949488 mfu:18.430926418793472 Step 2901 | loss:1.179908037185669 lr:3.3214236264345765e-05 tokens_per_second_per_gpu:5303.647101793782 mfu:25.018208274666705 Step 2902 | loss:1.2624784708023071 lr:3.320391560380134e-05 tokens_per_second_per_gpu:5319.492534806781 mfu:25.09295388569867 Step 2903 | loss:1.2352107763290405 lr:3.3193593376127766e-05 tokens_per_second_per_gpu:4495.436799418128 mfu:21.205742383463893 Step 2904 | loss:1.3876850605010986 lr:3.318326958329683e-05 tokens_per_second_per_gpu:5324.518721447858 mfu:25.1166632656405 Step 2905 | loss:1.116861343383789 lr:3.317294422728061e-05 tokens_per_second_per_gpu:5230.077107358294 mfu:24.671166058579097 Step 2906 | loss:1.3552378416061401 lr:3.3162617310051463e-05 tokens_per_second_per_gpu:4765.143373622903 mfu:22.477994310674458 Step 2907 | loss:1.425158143043518 lr:3.315228883358207e-05 tokens_per_second_per_gpu:5314.139697185229 mfu:25.06770363734954 Step 2908 | loss:1.3225576877593994 lr:3.3141958799845386e-05 tokens_per_second_per_gpu:4153.427791926662 mfu:19.59242754237282 Step 2909 | loss:1.2191590070724487 lr:3.313162721081468e-05 tokens_per_second_per_gpu:5322.719117988635 mfu:25.10817422907933 Step 2910 | loss:1.3962708711624146 lr:3.3121294068463526e-05 tokens_per_second_per_gpu:3713.8612968022653 mfu:17.518917387093445 Step 2911 | loss:1.1221182346343994 lr:3.311095937476577e-05 tokens_per_second_per_gpu:5325.772884630709 mfu:25.122579367356312 Step 2912 | loss:1.2958202362060547 lr:3.310062313169556e-05 tokens_per_second_per_gpu:5336.219561530291 mfu:25.17185812467851 Step 2913 | loss:1.2676029205322266 lr:3.309028534122737e-05 tokens_per_second_per_gpu:4435.13690704914 mfu:20.921297502936845 Step 2914 | loss:1.3121285438537598 lr:3.307994600533593e-05 tokens_per_second_per_gpu:3511.362768304614 mfu:16.563697278358397 Step 2915 | loss:1.3218330144882202 lr:3.306960512599627e-05 tokens_per_second_per_gpu:4685.871915726924 mfu:22.104057318673746 Step 2916 | loss:1.1861704587936401 lr:3.3059262705183755e-05 tokens_per_second_per_gpu:5355.080420718382 mfu:25.260828015463144 Step 2917 | loss:1.1781452894210815 lr:3.304891874487401e-05 tokens_per_second_per_gpu:3250.4299324944823 mfu:15.332832572109488 Step 2918 | loss:1.1568282842636108 lr:3.303857324704293e-05 tokens_per_second_per_gpu:5291.43931426848 mfu:24.96062205804653 Step 2919 | loss:1.3528821468353271 lr:3.3028226213666766e-05 tokens_per_second_per_gpu:3731.1061832886785 mfu:17.60026445893089 Step 2920 | loss:1.4419645071029663 lr:3.301787764672202e-05 tokens_per_second_per_gpu:4063.4956627284514 mfu:19.168202344941395 Step 2921 | loss:1.2811449766159058 lr:3.30075275481855e-05 tokens_per_second_per_gpu:5381.278787454242 mfu:25.384410181258485 Step 2922 | loss:1.253895878791809 lr:3.299717592003429e-05 tokens_per_second_per_gpu:4524.015088625899 mfu:21.340551049615875 Step 2923 | loss:1.1639413833618164 lr:3.29868227642458e-05 tokens_per_second_per_gpu:5326.905791131866 mfu:25.127923480616047 Step 2924 | loss:1.2908709049224854 lr:3.297646808279769e-05 tokens_per_second_per_gpu:4922.710569767638 mfu:23.221265658625 Step 2925 | loss:1.188376784324646 lr:3.2966111877667946e-05 tokens_per_second_per_gpu:4201.0633997841815 mfu:19.817132832109518 Step 2926 | loss:1.2663406133651733 lr:3.295575415083484e-05 tokens_per_second_per_gpu:5248.746638060797 mfu:24.759233420253207 Step 2927 | loss:1.283187985420227 lr:3.2945394904276906e-05 tokens_per_second_per_gpu:4584.912125714416 mfu:21.62781276366833 Step 2928 | loss:1.2933775186538696 lr:3.2935034139973e-05 tokens_per_second_per_gpu:3541.381868551079 mfu:16.70530249600762 Step 2929 | loss:1.4676539897918701 lr:3.2924671859902265e-05 tokens_per_second_per_gpu:3939.3602030968677 mfu:18.58263420216582 Step 2930 | loss:1.2745332717895508 lr:3.291430806604411e-05 tokens_per_second_per_gpu:5327.947363421716 mfu:25.132836754817827 Step 2931 | loss:1.3558741807937622 lr:3.290394276037826e-05 tokens_per_second_per_gpu:4023.832250290061 mfu:18.981103261193525 Step 2932 | loss:1.3127707242965698 lr:3.2893575944884705e-05 tokens_per_second_per_gpu:4464.012936370957 mfu:21.057510660006486 Step 2933 | loss:1.248836636543274 lr:3.288320762154375e-05 tokens_per_second_per_gpu:5295.140103306971 mfu:24.978079311360805 Step 2934 | loss:1.3060697317123413 lr:3.287283779233597e-05 tokens_per_second_per_gpu:4206.820216398236 mfu:19.844288718292212 Step 2935 | loss:1.23276686668396 lr:3.286246645924222e-05 tokens_per_second_per_gpu:5322.141299670272 mfu:25.10544856148564 Step 2936 | loss:1.3075717687606812 lr:3.285209362424366e-05 tokens_per_second_per_gpu:3483.3756078687093 mfu:16.431677067480273 Step 2937 | loss:1.278799057006836 lr:3.284171928932175e-05 tokens_per_second_per_gpu:5312.873196377447 mfu:25.061729336951906 Step 2938 | loss:1.2763229608535767 lr:3.2831343456458184e-05 tokens_per_second_per_gpu:3697.4171319507177 mfu:17.44134745582486 Step 2939 | loss:1.2306344509124756 lr:3.2820966127635e-05 tokens_per_second_per_gpu:4797.204059655374 mfu:22.629230036806725 Step 2940 | loss:1.0892009735107422 lr:3.281058730483449e-05 tokens_per_second_per_gpu:5323.81337967331 mfu:25.11333604814624 Step 2941 | loss:1.197086215019226 lr:3.2800206990039235e-05 tokens_per_second_per_gpu:5357.386905362471 mfu:25.271708097056173 Step 2942 | loss:1.3299777507781982 lr:3.27898251852321e-05 tokens_per_second_per_gpu:4141.258142128363 mfu:19.53502122791788 Step 2943 | loss:1.3979746103286743 lr:3.2779441892396256e-05 tokens_per_second_per_gpu:2421.8723959858735 mfu:11.424385305905401 Step 2944 | loss:1.526341199874878 lr:3.2769057113515134e-05 tokens_per_second_per_gpu:3660.8077010978454 mfu:17.26865452427887 Step 2945 | loss:1.3713659048080444 lr:3.275867085057245e-05 tokens_per_second_per_gpu:5165.724623210936 mfu:24.36760441119003 Step 2946 | loss:1.270317792892456 lr:3.274828310555221e-05 tokens_per_second_per_gpu:3826.810525648078 mfu:18.05171817068476 Step 2947 | loss:1.332590937614441 lr:3.2737893880438705e-05 tokens_per_second_per_gpu:5327.103969339287 mfu:25.12885832103314 Step 2948 | loss:1.3801366090774536 lr:3.272750317721651e-05 tokens_per_second_per_gpu:4514.945716829859 mfu:21.29776927545956 Step 2949 | loss:1.2493590116500854 lr:3.2717110997870473e-05 tokens_per_second_per_gpu:4310.5051592020645 mfu:20.333388283973296 Step 2950 | loss:1.3140888214111328 lr:3.270671734438574e-05 tokens_per_second_per_gpu:5333.514855781579 mfu:25.159099566191454 Step 2951 | loss:1.2775611877441406 lr:3.2696322218747716e-05 tokens_per_second_per_gpu:4905.298787082049 mfu:23.139131308940616 Step 2952 | loss:1.3525410890579224 lr:3.268592562294211e-05 tokens_per_second_per_gpu:5274.211229280179 mfu:24.87935424174231 Step 2953 | loss:1.5284634828567505 lr:3.26755275589549e-05 tokens_per_second_per_gpu:3771.8102998054524 mfu:17.792272721378918 Step 2954 | loss:1.3497203588485718 lr:3.266512802877233e-05 tokens_per_second_per_gpu:5354.390765348985 mfu:25.257574793418357 Step 2955 | loss:1.351114273071289 lr:3.2654727034380964e-05 tokens_per_second_per_gpu:4378.111170564316 mfu:20.652297374344005 Step 2956 | loss:1.471617579460144 lr:3.2644324577767605e-05 tokens_per_second_per_gpu:4889.223764241689 mfu:23.063302683520927 Step 2957 | loss:1.36380934715271 lr:3.263392066091936e-05 tokens_per_second_per_gpu:4792.8439950872025 mfu:22.608662868334935 Step 2958 | loss:1.4025497436523438 lr:3.26235152858236e-05 tokens_per_second_per_gpu:5326.491208932992 mfu:25.125967825648942 Step 2959 | loss:1.437689185142517 lr:3.261310845446799e-05 tokens_per_second_per_gpu:4787.439915662969 mfu:22.5831709036598 Step 2960 | loss:1.4741771221160889 lr:3.260270016884046e-05 tokens_per_second_per_gpu:3757.381591281202 mfu:17.724210041478504 Step 2961 | loss:1.4969772100448608 lr:3.259229043092923e-05 tokens_per_second_per_gpu:4718.923496330146 mfu:22.259967263560288 Step 2962 | loss:1.4765921831130981 lr:3.2581879242722776e-05 tokens_per_second_per_gpu:3997.4854486989357 mfu:18.856820902860303 Step 2963 | loss:1.2315155267715454 lr:3.257146660620988e-05 tokens_per_second_per_gpu:4056.979596196247 mfu:19.137464947353397 Step 2964 | loss:1.351503610610962 lr:3.256105252337956e-05 tokens_per_second_per_gpu:4664.239911981993 mfu:22.002015466208487 Step 2965 | loss:1.1871412992477417 lr:3.255063699622117e-05 tokens_per_second_per_gpu:4403.866422045924 mfu:20.773789289881776 Step 2966 | loss:1.2268871068954468 lr:3.254022002672429e-05 tokens_per_second_per_gpu:4550.876350486923 mfu:21.467260204818185 Step 2967 | loss:1.2251678705215454 lr:3.2529801616878785e-05 tokens_per_second_per_gpu:4912.218064836621 mfu:23.171770722659453 Step 2968 | loss:1.3065028190612793 lr:3.251938176867481e-05 tokens_per_second_per_gpu:4509.457616179562 mfu:21.271880968325586 Step 2969 | loss:1.4174582958221436 lr:3.250896048410278e-05 tokens_per_second_per_gpu:5314.011234324413 mfu:25.06709765611704 Step 2970 | loss:1.4126213788986206 lr:3.2498537765153405e-05 tokens_per_second_per_gpu:5298.767561510692 mfu:24.995190650615946 Step 2971 | loss:1.2751785516738892 lr:3.248811361381763e-05 tokens_per_second_per_gpu:5355.883400665421 mfu:25.26461580887583 Step 2972 | loss:1.1406506299972534 lr:3.247768803208672e-05 tokens_per_second_per_gpu:3513.083956241359 mfu:16.571816415520967 Step 2973 | loss:1.3213492631912231 lr:3.246726102195219e-05 tokens_per_second_per_gpu:4901.12128334455 mfu:23.1194253110552 Step 2974 | loss:1.4657517671585083 lr:3.245683258540581e-05 tokens_per_second_per_gpu:4401.524725278215 mfu:20.762743106693826 Step 2975 | loss:1.3482247591018677 lr:3.244640272443966e-05 tokens_per_second_per_gpu:3788.1698632003227 mfu:17.86944357314186 Step 2976 | loss:1.3712644577026367 lr:3.243597144104607e-05 tokens_per_second_per_gpu:5178.8766357015675 mfu:24.42964469807306 Step 2977 | loss:1.3700392246246338 lr:3.242553873721764e-05 tokens_per_second_per_gpu:5341.323128740183 mfu:25.19593252196593 Step 2978 | loss:1.3175907135009766 lr:3.241510461494725e-05 tokens_per_second_per_gpu:3784.313603768531 mfu:17.85125293945639 Step 2979 | loss:1.1600242853164673 lr:3.240466907622805e-05 tokens_per_second_per_gpu:3980.660927953256 mfu:18.77745676794369 Step 2980 | loss:1.3468444347381592 lr:3.239423212305347e-05 tokens_per_second_per_gpu:4043.451716827659 mfu:19.073651632277542 Step 2981 | loss:1.169167160987854 lr:3.2383793757417174e-05 tokens_per_second_per_gpu:5299.6460501730335 mfu:24.999334631521833 Step 2982 | loss:1.339745283126831 lr:3.237335398131314e-05 tokens_per_second_per_gpu:5344.043820132095 mfu:25.208766487459393 Step 2983 | loss:1.3210170269012451 lr:3.2362912796735576e-05 tokens_per_second_per_gpu:3826.591877506041 mfu:18.050686770093552 Step 2984 | loss:1.463620662689209 lr:3.2352470205679004e-05 tokens_per_second_per_gpu:4495.11491223726 mfu:21.20422398671212 Step 2985 | loss:1.3267117738723755 lr:3.234202621013817e-05 tokens_per_second_per_gpu:4395.845820073012 mfu:20.73595474191974 Step 2986 | loss:1.1822329759597778 lr:3.233158081210812e-05 tokens_per_second_per_gpu:5309.75501122388 mfu:25.04702032556528 Step 2987 | loss:1.2269343137741089 lr:3.232113401358414e-05 tokens_per_second_per_gpu:5011.70857388902 mfu:23.641084428690853 Step 2988 | loss:1.2395211458206177 lr:3.231068581656181e-05 tokens_per_second_per_gpu:5304.020644525472 mfu:25.019970339465047 Step 2989 | loss:1.2091166973114014 lr:3.230023622303699e-05 tokens_per_second_per_gpu:5349.175975761994 mfu:25.23297574120167 Step 2990 | loss:1.4037357568740845 lr:3.2289785235005736e-05 tokens_per_second_per_gpu:5307.4545828928885 mfu:25.03616881263445 Step 2991 | loss:1.4548633098602295 lr:3.2279332854464444e-05 tokens_per_second_per_gpu:4707.1577390058 mfu:22.20446617881615 Step 2992 | loss:1.1543827056884766 lr:3.226887908340976e-05 tokens_per_second_per_gpu:5319.605331531244 mfu:25.093485967093066 Step 2993 | loss:1.4186782836914062 lr:3.225842392383857e-05 tokens_per_second_per_gpu:5000.611921909291 mfu:23.58873962801841 Step 2994 | loss:1.3402818441390991 lr:3.224796737774802e-05 tokens_per_second_per_gpu:5337.141141947447 mfu:25.17620537674407 Step 2995 | loss:1.140838861465454 lr:3.2237509447135597e-05 tokens_per_second_per_gpu:4816.264762056869 mfu:22.71914262212575 Step 2996 | loss:1.375694751739502 lr:3.2227050133998944e-05 tokens_per_second_per_gpu:4246.581954579448 mfu:20.031851621345073 Step 2997 | loss:1.2068101167678833 lr:3.2216589440336036e-05 tokens_per_second_per_gpu:3923.7652420417076 mfu:18.509070110093905 Step 2998 | loss:1.3580284118652344 lr:3.2206127368145114e-05 tokens_per_second_per_gpu:4125.802644389223 mfu:19.46211500810253 Step 2999 | loss:1.3744388818740845 lr:3.219566391942465e-05 tokens_per_second_per_gpu:4916.127993318328 mfu:23.19021452241025 Step 3000 | loss:1.4054087400436401 lr:3.218519909617339e-05 tokens_per_second_per_gpu:4853.826452608817 mfu:22.896327525144542 Step 3001 | loss:1.365229845046997 lr:3.217473290039036e-05 tokens_per_second_per_gpu:5231.3545547548565 mfu:24.677191995903684 Step 3002 | loss:1.4344184398651123 lr:3.2164265334074826e-05 tokens_per_second_per_gpu:4184.067647974081 mfu:19.736960971047 Step 3003 | loss:1.2528294324874878 lr:3.215379639922632e-05 tokens_per_second_per_gpu:5317.815213577862 mfu:25.085041675281346 Step 3004 | loss:1.3003113269805908 lr:3.214332609784465e-05 tokens_per_second_per_gpu:4798.581245576954 mfu:22.635726457770964 Step 3005 | loss:1.2307813167572021 lr:3.213285443192987e-05 tokens_per_second_per_gpu:5334.67877947945 mfu:25.16458999286017 Step 3006 | loss:1.2571395635604858 lr:3.212238140348229e-05 tokens_per_second_per_gpu:4920.942321816816 mfu:23.21292453134676 Step 3007 | loss:1.3334699869155884 lr:3.211190701450252e-05 tokens_per_second_per_gpu:5330.1233214415715 mfu:25.143101120054208 Step 3008 | loss:1.3212802410125732 lr:3.2101431266991374e-05 tokens_per_second_per_gpu:4762.977455516048 mfu:22.467777305420693 Step 3009 | loss:1.386414647102356 lr:3.2090954162949944e-05 tokens_per_second_per_gpu:4340.881008859772 mfu:20.47667634946307 Step 3010 | loss:1.3684709072113037 lr:3.208047570437961e-05 tokens_per_second_per_gpu:5239.698047385552 mfu:24.71654967418931 Step 3011 | loss:1.2878903150558472 lr:3.206999589328198e-05 tokens_per_second_per_gpu:3885.3967459034307 mfu:18.328079367469172 Step 3012 | loss:1.2269281148910522 lr:3.205951473165893e-05 tokens_per_second_per_gpu:4888.804819746879 mfu:23.061326450859603 Step 3013 | loss:1.3676053285598755 lr:3.204903222151259e-05 tokens_per_second_per_gpu:4440.034474199071 mfu:20.944400162794192 Step 3014 | loss:1.342614769935608 lr:3.2038548364845354e-05 tokens_per_second_per_gpu:5087.127496631304 mfu:23.99684835506131 Step 3015 | loss:1.3300145864486694 lr:3.202806316365987e-05 tokens_per_second_per_gpu:4211.475094143027 mfu:19.866246570818426 Step 3016 | loss:1.3315263986587524 lr:3.201757661995906e-05 tokens_per_second_per_gpu:3450.1624904791315 mfu:16.27500512601147 Step 3017 | loss:1.3298734426498413 lr:3.2007088735746046e-05 tokens_per_second_per_gpu:4314.909664759523 mfu:20.354165088173964 Step 3018 | loss:1.1597105264663696 lr:3.199659951302427e-05 tokens_per_second_per_gpu:5323.099134053854 mfu:25.109966829696397 Step 3019 | loss:1.2195852994918823 lr:3.1986108953797415e-05 tokens_per_second_per_gpu:4036.3486027477447 mfu:19.040145031246357 Step 3020 | loss:1.2748351097106934 lr:3.19756170600694e-05 tokens_per_second_per_gpu:3871.8608501403464 mfu:18.264228237692745 Step 3021 | loss:1.3153387308120728 lr:3.196512383384439e-05 tokens_per_second_per_gpu:4894.878739425215 mfu:23.089978166299876 Step 3022 | loss:1.2821178436279297 lr:3.195462927712686e-05 tokens_per_second_per_gpu:5316.929059742122 mfu:25.08086153644473 Step 3023 | loss:1.4234381914138794 lr:3.1944133391921475e-05 tokens_per_second_per_gpu:4416.009231079188 mfu:20.831068991868538 Step 3024 | loss:1.4547991752624512 lr:3.193363618023318e-05 tokens_per_second_per_gpu:5318.6684229486755 mfu:25.089066409456002 Step 3025 | loss:1.169631004333496 lr:3.19231376440672e-05 tokens_per_second_per_gpu:3418.524838439211 mfu:16.125764923399114 Step 3026 | loss:1.232885718345642 lr:3.1912637785428964e-05 tokens_per_second_per_gpu:4349.513664431288 mfu:20.51739805867683 Step 3027 | loss:1.2744548320770264 lr:3.1902136606324174e-05 tokens_per_second_per_gpu:5320.95164983792 mfu:25.09983678025125 Step 3028 | loss:1.2720890045166016 lr:3.18916341087588e-05 tokens_per_second_per_gpu:3723.702046060992 mfu:17.565337880351816 Step 3029 | loss:1.191770076751709 lr:3.188113029473905e-05 tokens_per_second_per_gpu:5302.672490101771 mfu:25.013610865029584 Step 3030 | loss:1.3254450559616089 lr:3.187062516627138e-05 tokens_per_second_per_gpu:4131.961803895207 mfu:19.491168814353227 Step 3031 | loss:1.2462199926376343 lr:3.18601187253625e-05 tokens_per_second_per_gpu:4154.871564133384 mfu:19.599238062204865 Step 3032 | loss:1.3932217359542847 lr:3.184961097401938e-05 tokens_per_second_per_gpu:3760.0099275181406 mfu:17.736608351948547 Step 3033 | loss:1.444977045059204 lr:3.1839101914249234e-05 tokens_per_second_per_gpu:3733.3993812091644 mfu:17.611081864781735 Step 3034 | loss:1.3387612104415894 lr:3.1828591548059507e-05 tokens_per_second_per_gpu:4866.213427853899 mfu:22.9547590008115 Step 3035 | loss:1.3178259134292603 lr:3.181807987745793e-05 tokens_per_second_per_gpu:4684.804869319636 mfu:22.099023878713677 Step 3036 | loss:1.3000761270523071 lr:3.1807566904452454e-05 tokens_per_second_per_gpu:3861.0143130788315 mfu:18.213063271763527 Step 3037 | loss:1.3801798820495605 lr:3.179705263105129e-05 tokens_per_second_per_gpu:4066.186932515885 mfu:19.180897523706694 Step 3038 | loss:1.4820035696029663 lr:3.178653705926292e-05 tokens_per_second_per_gpu:4449.031047844933 mfu:20.986838535655465 Step 3039 | loss:1.3316822052001953 lr:3.177602019109601e-05 tokens_per_second_per_gpu:5020.968075798003 mfu:23.68476307902946 Step 3040 | loss:1.2233128547668457 lr:3.176550202855954e-05 tokens_per_second_per_gpu:4539.7573339390865 mfu:21.414809906662192 Step 3041 | loss:1.2068066596984863 lr:3.17549825736627e-05 tokens_per_second_per_gpu:4621.652944861874 mfu:21.801125476217035 Step 3042 | loss:1.3725935220718384 lr:3.1744461828414954e-05 tokens_per_second_per_gpu:3998.0053006975927 mfu:18.859273133433863 Step 3043 | loss:1.2947944402694702 lr:3.173393979482597e-05 tokens_per_second_per_gpu:4248.25337192678 mfu:20.039735982145643 Step 3044 | loss:1.205396294593811 lr:3.172341647490572e-05 tokens_per_second_per_gpu:5226.40152753595 mfu:24.65382772143852 Step 3045 | loss:1.1939555406570435 lr:3.171289187066437e-05 tokens_per_second_per_gpu:3604.2522720808693 mfu:17.00187291625459 Step 3046 | loss:1.277134656906128 lr:3.1702365984112356e-05 tokens_per_second_per_gpu:5349.905911749678 mfu:25.236418973795498 Step 3047 | loss:1.3347499370574951 lr:3.169183881726036e-05 tokens_per_second_per_gpu:5203.498422344207 mfu:24.545789866576378 Step 3048 | loss:1.3466320037841797 lr:3.16813103721193e-05 tokens_per_second_per_gpu:4441.402957047584 mfu:20.950855529877877 Step 3049 | loss:1.317083716392517 lr:3.167078065070034e-05 tokens_per_second_per_gpu:4022.3699748831573 mfu:18.97420545860925 Step 3050 | loss:1.2840615510940552 lr:3.1660249655014894e-05 tokens_per_second_per_gpu:4447.620152649967 mfu:20.98018310229727 Step 3051 | loss:1.3635125160217285 lr:3.1649717387074605e-05 tokens_per_second_per_gpu:5320.964054974052 mfu:25.099895297394916 Step 3052 | loss:1.4209216833114624 lr:3.163918384889138e-05 tokens_per_second_per_gpu:4610.384135913374 mfu:21.747968581749898 Step 3053 | loss:1.2774913311004639 lr:3.162864904247735e-05 tokens_per_second_per_gpu:5248.909796277647 mfu:24.76000306539975 Step 3054 | loss:1.2397065162658691 lr:3.161811296984491e-05 tokens_per_second_per_gpu:4990.11322050141 mfu:23.53921546221427 Step 3055 | loss:1.2306551933288574 lr:3.160757563300667e-05 tokens_per_second_per_gpu:4525.547341498313 mfu:21.347778947844347 Step 3056 | loss:1.3214495182037354 lr:3.159703703397549e-05 tokens_per_second_per_gpu:4729.006372963585 mfu:22.30752991295637 Step 3057 | loss:1.2724698781967163 lr:3.158649717476449e-05 tokens_per_second_per_gpu:5308.469999547348 mfu:25.040958706241483 Step 3058 | loss:1.4194496870040894 lr:3.157595605738699e-05 tokens_per_second_per_gpu:4264.65564564893 mfu:20.11710830580949 Step 3059 | loss:1.3204257488250732 lr:3.156541368385661e-05 tokens_per_second_per_gpu:4657.727920530407 mfu:21.971297291471043 Step 3060 | loss:1.2936310768127441 lr:3.155487005618716e-05 tokens_per_second_per_gpu:4682.773722524853 mfu:22.08944261273331 Step 3061 | loss:1.2274775505065918 lr:3.15443251763927e-05 tokens_per_second_per_gpu:4389.27583696614 mfu:20.704963010649916 Step 3062 | loss:1.247377872467041 lr:3.1533779046487535e-05 tokens_per_second_per_gpu:4869.661280542068 mfu:22.97102311020592 Step 3063 | loss:1.3268882036209106 lr:3.152323166848622e-05 tokens_per_second_per_gpu:4174.33527592466 mfu:19.691051711575984 Step 3064 | loss:1.2796002626419067 lr:3.1512683044403535e-05 tokens_per_second_per_gpu:3870.0844218705497 mfu:18.255848522454198 Step 3065 | loss:1.3422660827636719 lr:3.150213317625449e-05 tokens_per_second_per_gpu:5194.746209788338 mfu:24.504504186668896 Step 3066 | loss:1.5853495597839355 lr:3.1491582066054366e-05 tokens_per_second_per_gpu:4756.175582000876 mfu:22.435691707530335 Step 3067 | loss:1.3198555707931519 lr:3.1481029715818624e-05 tokens_per_second_per_gpu:4975.7482273955275 mfu:23.471453338813266 Step 3068 | loss:1.3872653245925903 lr:3.147047612756302e-05 tokens_per_second_per_gpu:5315.2439042876285 mfu:25.072912370648712 Step 3069 | loss:1.231042742729187 lr:3.145992130330352e-05 tokens_per_second_per_gpu:5334.050398272521 mfu:25.161625811494197 Step 3070 | loss:1.0603690147399902 lr:3.1449365245056323e-05 tokens_per_second_per_gpu:5218.196369385801 mfu:24.615122590499926 Step 3071 | loss:1.5024150609970093 lr:3.143880795483787e-05 tokens_per_second_per_gpu:4469.329541445275 mfu:21.082589993248412 Step 3072 | loss:1.481789469718933 lr:3.142824943466485e-05 tokens_per_second_per_gpu:4535.310145625219 mfu:21.39383176061711 Step 3073 | loss:1.0991418361663818 lr:3.141768968655414e-05 tokens_per_second_per_gpu:3492.7995375872524 mfu:16.476131351850853 Step 3074 | loss:1.3287478685379028 lr:3.140712871252292e-05 tokens_per_second_per_gpu:3236.952214828295 mfu:15.26925587834233 Step 3075 | loss:1.3953227996826172 lr:3.1396566514588566e-05 tokens_per_second_per_gpu:4762.201032752996 mfu:22.46411478677599 Step 3076 | loss:1.3548120260238647 lr:3.1386003094768664e-05 tokens_per_second_per_gpu:5038.026299801228 mfu:23.7652296320858 Step 3077 | loss:1.1379181146621704 lr:3.1375438455081084e-05 tokens_per_second_per_gpu:4589.935850444001 mfu:21.651510530353605 Step 3078 | loss:1.4169714450836182 lr:3.136487259754391e-05 tokens_per_second_per_gpu:4956.227904877946 mfu:23.37937264698738 Step 3079 | loss:1.3507097959518433 lr:3.135430552417543e-05 tokens_per_second_per_gpu:4493.430315770135 mfu:21.196277457754892 Step 3080 | loss:1.3952399492263794 lr:3.1343737236994205e-05 tokens_per_second_per_gpu:3314.604694624791 mfu:15.635555874421636 Step 3081 | loss:1.3530220985412598 lr:3.133316773801902e-05 tokens_per_second_per_gpu:4946.552989433032 mfu:23.333734420122934 Step 3082 | loss:1.390358805656433 lr:3.132259702926886e-05 tokens_per_second_per_gpu:5337.687330884301 mfu:25.178781843148656 Step 3083 | loss:1.1426939964294434 lr:3.1312025112762985e-05 tokens_per_second_per_gpu:4574.285655342931 mfu:21.577685889863236 Step 3084 | loss:1.438528060913086 lr:3.1301451990520855e-05 tokens_per_second_per_gpu:2902.5538106414087 mfu:13.691841551541783 Step 3085 | loss:1.5118463039398193 lr:3.1290877664562155e-05 tokens_per_second_per_gpu:5332.661273681375 mfu:25.155073073788667 Step 3086 | loss:1.04567289352417 lr:3.128030213690685e-05 tokens_per_second_per_gpu:4992.9437508881465 mfu:23.552567556986787 Step 3087 | loss:1.32906973361969 lr:3.126972540957507e-05 tokens_per_second_per_gpu:5267.492860622514 mfu:24.847662550512208 Step 3088 | loss:1.08322274684906 lr:3.125914748458721e-05 tokens_per_second_per_gpu:5312.883407420274 mfu:25.061777504183105 Step 3089 | loss:1.4531753063201904 lr:3.12485683639639e-05 tokens_per_second_per_gpu:4945.254077067435 mfu:23.32760722887711 Step 3090 | loss:1.2716808319091797 lr:3.123798804972597e-05 tokens_per_second_per_gpu:5208.283203339968 mfu:24.568360494901203 Step 3091 | loss:1.2841973304748535 lr:3.12274065438945e-05 tokens_per_second_per_gpu:4232.033176653096 mfu:19.96322255358899 Step 3092 | loss:1.237609624862671 lr:3.12168238484908e-05 tokens_per_second_per_gpu:3987.063832335306 mfu:18.807660360361957 Step 3093 | loss:1.250131368637085 lr:3.120623996553638e-05 tokens_per_second_per_gpu:4093.380706858082 mfu:19.309175197015175 Step 3094 | loss:1.2408086061477661 lr:3.1195654897053005e-05 tokens_per_second_per_gpu:5315.656351938386 mfu:25.07485795658816 Step 3095 | loss:1.4256560802459717 lr:3.1185068645062664e-05 tokens_per_second_per_gpu:3686.436059343715 mfu:17.389547862773448 Step 3096 | loss:1.3477575778961182 lr:3.1174481211587555e-05 tokens_per_second_per_gpu:5321.596742111788 mfu:25.102879790571176 Step 3097 | loss:1.3177714347839355 lr:3.116389259865012e-05 tokens_per_second_per_gpu:3635.242997023454 mfu:17.148061453371678 Step 3098 | loss:1.3984049558639526 lr:3.115330280827301e-05 tokens_per_second_per_gpu:4333.9793536101315 mfu:20.444120064106706 Step 3099 | loss:1.3872239589691162 lr:3.114271184247911e-05 tokens_per_second_per_gpu:5272.41151461415 mfu:24.870864680599663 Step 3100 | loss:1.3364399671554565 lr:3.1132119703291536e-05 tokens_per_second_per_gpu:4001.051274393296 mfu:18.873641511053197 Step 3101 | loss:1.2767338752746582 lr:3.112152639273361e-05 tokens_per_second_per_gpu:5310.844147255099 mfu:25.052157966050313 Step 3102 | loss:1.4299216270446777 lr:3.11109319128289e-05 tokens_per_second_per_gpu:4202.300815227786 mfu:19.822969931881843 Step 3103 | loss:1.154877781867981 lr:3.110033626560117e-05 tokens_per_second_per_gpu:4703.297101458121 mfu:22.186254892811057 Step 3104 | loss:1.1601487398147583 lr:3.108973945307444e-05 tokens_per_second_per_gpu:4530.949113939226 mfu:21.37326003008555 Step 3105 | loss:1.5075390338897705 lr:3.107914147727293e-05 tokens_per_second_per_gpu:3211.480236519326 mfu:15.14910021069128 Step 3106 | loss:1.3069084882736206 lr:3.106854234022108e-05 tokens_per_second_per_gpu:4611.643213405106 mfu:21.753907865099166 Step 3107 | loss:1.2156686782836914 lr:3.105794204394357e-05 tokens_per_second_per_gpu:4712.829698564638 mfu:22.23122177979128 Step 3108 | loss:1.3962311744689941 lr:3.104734059046527e-05 tokens_per_second_per_gpu:4217.042608190789 mfu:19.89250948449757 Step 3109 | loss:1.4821892976760864 lr:3.103673798181133e-05 tokens_per_second_per_gpu:4045.4518836417296 mfu:19.083086760403162 Step 3110 | loss:1.3891510963439941 lr:3.102613422000704e-05 tokens_per_second_per_gpu:4313.371752539824 mfu:20.346910493838763 Step 3111 | loss:1.2355245351791382 lr:3.101552930707798e-05 tokens_per_second_per_gpu:4834.608087808136 mfu:22.805671219388575 Step 3112 | loss:1.436708927154541 lr:3.100492324504991e-05 tokens_per_second_per_gpu:4566.209191635787 mfu:21.539587832569833 Step 3113 | loss:1.2337863445281982 lr:3.099431603594884e-05 tokens_per_second_per_gpu:3856.8775292627474 mfu:18.19354935669496 Step 3114 | loss:1.1921427249908447 lr:3.0983707681800955e-05 tokens_per_second_per_gpu:5151.471452250828 mfu:24.30036977192947 Step 3115 | loss:1.100622296333313 lr:3.097309818463271e-05 tokens_per_second_per_gpu:4223.144992047773 mfu:19.92129547032501 Step 3116 | loss:1.2561681270599365 lr:3.096248754647073e-05 tokens_per_second_per_gpu:4905.573333607291 mfu:23.14042639174265 Step 3117 | loss:1.4361097812652588 lr:3.09518757693419e-05 tokens_per_second_per_gpu:3521.0776106808394 mfu:16.60952384737008 Step 3118 | loss:1.3045063018798828 lr:3.09412628552733e-05 tokens_per_second_per_gpu:4725.479098193873 mfu:22.290891156052506 Step 3119 | loss:1.3375970125198364 lr:3.0930648806292224e-05 tokens_per_second_per_gpu:4855.966337072888 mfu:22.9064217252635 Step 3120 | loss:1.4312183856964111 lr:3.092003362442619e-05 tokens_per_second_per_gpu:5329.168304503023 mfu:25.138596142212386 Step 3121 | loss:1.1852613687515259 lr:3.090941731170294e-05 tokens_per_second_per_gpu:4273.6864164379795 mfu:20.15970799242982 Step 3122 | loss:1.2954769134521484 lr:3.089879987015042e-05 tokens_per_second_per_gpu:5351.857738865016 mfu:25.245626075314593 Step 3123 | loss:1.187577247619629 lr:3.0888181301796804e-05 tokens_per_second_per_gpu:5218.830205794502 mfu:24.618112504983415 Step 3124 | loss:1.309011459350586 lr:3.087756160867046e-05 tokens_per_second_per_gpu:4529.05651171187 mfu:21.36433230246788 Step 3125 | loss:1.3694545030593872 lr:3.086694079279999e-05 tokens_per_second_per_gpu:5230.302910266108 mfu:24.672231209421206 Step 3126 | loss:1.217881679534912 lr:3.085631885621421e-05 tokens_per_second_per_gpu:5323.630305601497 mfu:25.11247245651384 Step 3127 | loss:1.2354710102081299 lr:3.0845695800942125e-05 tokens_per_second_per_gpu:5231.3886528447865 mfu:24.67735284241162 Step 3128 | loss:1.463313341140747 lr:3.0835071629012995e-05 tokens_per_second_per_gpu:4598.9477752145685 mfu:21.69402131708929 Step 3129 | loss:1.2920302152633667 lr:3.082444634245626e-05 tokens_per_second_per_gpu:5334.724502412898 mfu:25.164805675738382 Step 3130 | loss:1.35849928855896 lr:3.0813819943301594e-05 tokens_per_second_per_gpu:3734.2518255725995 mfu:17.61510299028606 Step 3131 | loss:1.376954197883606 lr:3.080319243357887e-05 tokens_per_second_per_gpu:3137.4730294125593 mfu:14.799995587837081 Step 3132 | loss:1.2282859086990356 lr:3.079256381531816e-05 tokens_per_second_per_gpu:4618.9151486833525 mfu:21.788210824526754 Step 3133 | loss:1.2078698873519897 lr:3.07819340905498e-05 tokens_per_second_per_gpu:4497.693303024397 mfu:21.216386695973874 Step 3134 | loss:1.277945637702942 lr:3.0771303261304266e-05 tokens_per_second_per_gpu:4871.017101989782 mfu:22.97741875130178 Step 3135 | loss:1.3548976182937622 lr:3.076067132961231e-05 tokens_per_second_per_gpu:5064.638731348581 mfu:23.890765012243694 Step 3136 | loss:1.2436347007751465 lr:3.0750038297504845e-05 tokens_per_second_per_gpu:5204.134564730193 mfu:24.548790658748157 Step 3137 | loss:1.360592246055603 lr:3.0739404167013034e-05 tokens_per_second_per_gpu:5323.495268429883 mfu:25.11183546313562 Step 3138 | loss:1.24617600440979 lr:3.0728768940168206e-05 tokens_per_second_per_gpu:4860.689365027118 mfu:22.92870105395527 Step 3139 | loss:1.261818766593933 lr:3.071813261900195e-05 tokens_per_second_per_gpu:4662.677765677319 mfu:21.994646555559697 Step 3140 | loss:1.4462007284164429 lr:3.070749520554602e-05 tokens_per_second_per_gpu:4748.292765364088 mfu:22.3985071165074 Step 3141 | loss:1.2987924814224243 lr:3.069685670183241e-05 tokens_per_second_per_gpu:3381.345889628446 mfu:15.950385478475958 Step 3142 | loss:1.3415597677230835 lr:3.06862171098933e-05 tokens_per_second_per_gpu:4424.919221119634 mfu:20.873098935090383 Step 3143 | loss:1.305723786354065 lr:3.0675576431761095e-05 tokens_per_second_per_gpu:4808.39863893464 mfu:22.6820367772592 Step 3144 | loss:1.338399052619934 lr:3.066493466946839e-05 tokens_per_second_per_gpu:4896.051709361851 mfu:23.095511265620296 Step 3145 | loss:1.3366094827651978 lr:3.0654291825048e-05 tokens_per_second_per_gpu:4502.74611799781 mfu:21.240221686302593 Step 3146 | loss:1.3789565563201904 lr:3.064364790053296e-05 tokens_per_second_per_gpu:3743.419973159769 mfu:17.65835070670202 Step 3147 | loss:1.3343071937561035 lr:3.063300289795646e-05 tokens_per_second_per_gpu:4884.918538091328 mfu:23.042994197222345 Step 3148 | loss:1.3449958562850952 lr:3.062235681935196e-05 tokens_per_second_per_gpu:4759.282353608937 mfu:22.450346879275454 Step 3149 | loss:1.4133297204971313 lr:3.061170966675309e-05 tokens_per_second_per_gpu:5310.490322207671 mfu:25.050488912932817 Step 3150 | loss:1.2593951225280762 lr:3.0601061442193686e-05 tokens_per_second_per_gpu:4555.943842451002 mfu:21.491164429016028 Step 3151 | loss:1.456213116645813 lr:3.059041214770779e-05 tokens_per_second_per_gpu:3197.2106546411947 mfu:15.081788158330415 Step 3152 | loss:1.327314853668213 lr:3.057976178532966e-05 tokens_per_second_per_gpu:4634.1018999011085 mfu:21.85984932114786 Step 3153 | loss:1.27486252784729 lr:3.056911035709377e-05 tokens_per_second_per_gpu:5320.859543350346 mfu:25.099402298234374 Step 3154 | loss:1.512302279472351 lr:3.055845786503473e-05 tokens_per_second_per_gpu:4143.3644896778305 mfu:19.544957228688666 Step 3155 | loss:1.1783347129821777 lr:3.054780431118744e-05 tokens_per_second_per_gpu:4152.330750376845 mfu:19.58725261020774 Step 3156 | loss:1.3074722290039062 lr:3.053714969758696e-05 tokens_per_second_per_gpu:3616.9960888854785 mfu:17.06198767444129 Step 3157 | loss:1.3718183040618896 lr:3.052649402626854e-05 tokens_per_second_per_gpu:5330.964065799755 mfu:25.147067054637542 Step 3158 | loss:1.283780813217163 lr:3.0515837299267665e-05 tokens_per_second_per_gpu:4716.895466981657 mfu:22.250400703105978 Step 3159 | loss:1.399312138557434 lr:3.0505179518619998e-05 tokens_per_second_per_gpu:4610.982342674612 mfu:21.750790425107255 Step 3160 | loss:1.2114769220352173 lr:3.049452068636141e-05 tokens_per_second_per_gpu:4826.903849503974 mfu:22.769329012829242 Step 3161 | loss:1.2401598691940308 lr:3.0483860804527975e-05 tokens_per_second_per_gpu:5300.991108349836 mfu:25.005679500432404 Step 3162 | loss:1.289003849029541 lr:3.0473199875155968e-05 tokens_per_second_per_gpu:4999.358957662211 mfu:23.582829181887192 Step 3163 | loss:1.4230079650878906 lr:3.0462537900281853e-05 tokens_per_second_per_gpu:3879.7049161398886 mfu:18.301230035348247 Step 3164 | loss:1.2565391063690186 lr:3.0451874881942317e-05 tokens_per_second_per_gpu:5306.742126354863 mfu:25.032808033586964 Step 3165 | loss:1.2325688600540161 lr:3.0441210822174214e-05 tokens_per_second_per_gpu:5292.173445350333 mfu:24.964085079615305 Step 3166 | loss:1.199224591255188 lr:3.0430545723014638e-05 tokens_per_second_per_gpu:5347.171214340477 mfu:25.223518939528805 Step 3167 | loss:1.2557485103607178 lr:3.0419879586500838e-05 tokens_per_second_per_gpu:5178.672414823368 mfu:24.428681353346917 Step 3168 | loss:1.3498823642730713 lr:3.0409212414670295e-05 tokens_per_second_per_gpu:4265.395289548758 mfu:20.120597332281246 Step 3169 | loss:1.2807862758636475 lr:3.0398544209560665e-05 tokens_per_second_per_gpu:5254.611736116689 mfu:24.786900088471764 Step 3170 | loss:1.2306610345840454 lr:3.0387874973209817e-05 tokens_per_second_per_gpu:5312.839283931063 mfu:25.061569366156252 Step 3171 | loss:1.1885818243026733 lr:3.0377204707655816e-05 tokens_per_second_per_gpu:3761.3722233711114 mfu:17.74303453391865 Step 3172 | loss:1.2449061870574951 lr:3.0366533414936906e-05 tokens_per_second_per_gpu:5356.584459689257 mfu:25.26792282390427 Step 3173 | loss:1.3206440210342407 lr:3.0355861097091543e-05 tokens_per_second_per_gpu:5075.907310901659 mfu:23.94392082461349 Step 3174 | loss:1.235424518585205 lr:3.0345187756158377e-05 tokens_per_second_per_gpu:5321.613515979051 mfu:25.102958915764972 Step 3175 | loss:1.3308002948760986 lr:3.0334513394176256e-05 tokens_per_second_per_gpu:4994.829394875425 mfu:23.561462461398822 Step 3176 | loss:1.2223761081695557 lr:3.032383801318422e-05 tokens_per_second_per_gpu:4905.070633267022 mfu:23.138055068468077 Step 3177 | loss:1.2799689769744873 lr:3.0313161615221493e-05 tokens_per_second_per_gpu:5310.632613513273 mfu:25.051160125298743 Step 3178 | loss:1.304013967514038 lr:3.0302484202327507e-05 tokens_per_second_per_gpu:3842.6896092370516 mfu:18.12662251722498 Step 3179 | loss:1.2966166734695435 lr:3.0291805776541887e-05 tokens_per_second_per_gpu:4256.289155244113 mfu:20.077642143099514 Step 3180 | loss:1.185118317604065 lr:3.0281126339904447e-05 tokens_per_second_per_gpu:4671.047826242291 mfu:22.03412955932426 Step 3181 | loss:1.3797516822814941 lr:3.0270445894455195e-05 tokens_per_second_per_gpu:5313.342701048075 mfu:25.063944070589017 Step 3182 | loss:1.4254332780838013 lr:3.0259764442234332e-05 tokens_per_second_per_gpu:4484.550910572666 mfu:21.154391788455683 Step 3183 | loss:1.3447606563568115 lr:3.0249081985282253e-05 tokens_per_second_per_gpu:4518.887911282697 mfu:21.31636527930133 Step 3184 | loss:1.2370802164077759 lr:3.023839852563954e-05 tokens_per_second_per_gpu:5314.13474013852 mfu:25.06768025411445 Step 3185 | loss:1.404903769493103 lr:3.022771406534697e-05 tokens_per_second_per_gpu:4498.137621711444 mfu:21.218482623029256 Step 3186 | loss:1.2833000421524048 lr:3.0217028606445502e-05 tokens_per_second_per_gpu:4308.994690935206 mfu:20.326263147446063 Step 3187 | loss:1.3096981048583984 lr:3.020634215097632e-05 tokens_per_second_per_gpu:5325.472356233959 mfu:25.121161723633406 Step 3188 | loss:1.4183250665664673 lr:3.0195654700980757e-05 tokens_per_second_per_gpu:5314.3251564508755 mfu:25.0685784803482 Step 3189 | loss:1.4678791761398315 lr:3.018496625850034e-05 tokens_per_second_per_gpu:3788.516537934397 mfu:17.871078897011298 Step 3190 | loss:1.4270687103271484 lr:3.017427682557683e-05 tokens_per_second_per_gpu:4993.537454334347 mfu:23.55536815743877 Step 3191 | loss:1.2533434629440308 lr:3.0163586404252114e-05 tokens_per_second_per_gpu:5037.450092477914 mfu:23.76251156383062 Step 3192 | loss:1.2524991035461426 lr:3.015289499656831e-05 tokens_per_second_per_gpu:5314.439256097204 mfu:25.06911670784734 Step 3193 | loss:1.390451192855835 lr:3.014220260456772e-05 tokens_per_second_per_gpu:5296.976445922097 mfu:24.986741652788712 Step 3194 | loss:1.3291207551956177 lr:3.0131509230292814e-05 tokens_per_second_per_gpu:4542.933337527479 mfu:21.42979165747073 Step 3195 | loss:1.5144420862197876 lr:3.012081487578627e-05 tokens_per_second_per_gpu:4906.946542002063 mfu:23.146904050034305 Step 3196 | loss:1.138379454612732 lr:3.0110119543090946e-05 tokens_per_second_per_gpu:4289.250412109954 mfu:20.23312601550601 Step 3197 | loss:1.284472107887268 lr:3.009942323424989e-05 tokens_per_second_per_gpu:3746.96092124708 mfu:17.675053962977906 Step 3198 | loss:1.2607094049453735 lr:3.0088725951306322e-05 tokens_per_second_per_gpu:4940.620992128713 mfu:23.305752176735353 Step 3199 | loss:1.2690702676773071 lr:3.0078027696303678e-05 tokens_per_second_per_gpu:4159.27562682516 mfu:19.62001277733255 Step 3200 | loss:1.4613527059555054 lr:3.006732847128554e-05 tokens_per_second_per_gpu:3409.429736589344 mfu:16.0828617761889 Step 3201 | loss:1.328324317932129 lr:3.0056628278295707e-05 tokens_per_second_per_gpu:4848.294973429271 mfu:22.870234594086952 Step 3202 | loss:1.3501091003417969 lr:3.0045927119378157e-05 tokens_per_second_per_gpu:4285.563184091614 mfu:20.21573273183753 Step 3203 | loss:1.346245527267456 lr:3.0035224996577037e-05 tokens_per_second_per_gpu:3616.818366767626 mfu:17.06114932888886 Step 3204 | loss:1.1553174257278442 lr:3.0024521911936692e-05 tokens_per_second_per_gpu:4683.598973422399 mfu:22.093335462019354 Step 3205 | loss:1.2173030376434326 lr:3.0013817867501658e-05 tokens_per_second_per_gpu:4129.742563115228 mfu:19.480700276952543 Step 3206 | loss:1.5254086256027222 lr:3.0003112865316635e-05 tokens_per_second_per_gpu:5226.596541851494 mfu:24.654747637237815 Step 3207 | loss:1.3548388481140137 lr:2.9992406907426506e-05 tokens_per_second_per_gpu:4536.916301352064 mfu:21.40140827121906 Step 3208 | loss:1.1508355140686035 lr:2.9981699995876374e-05 tokens_per_second_per_gpu:5280.745032270294 mfu:24.910175305228424 Step 3209 | loss:1.1929000616073608 lr:2.997099213271146e-05 tokens_per_second_per_gpu:4435.599534584085 mfu:20.923479795951575 Step 3210 | loss:1.4089683294296265 lr:2.996028331997722e-05 tokens_per_second_per_gpu:3613.0911555149764 mfu:17.0435674374823 Step 3211 | loss:1.3420060873031616 lr:2.9949573559719285e-05 tokens_per_second_per_gpu:4200.542959345456 mfu:19.814677825763756 Step 3212 | loss:1.296090006828308 lr:2.9938862853983434e-05 tokens_per_second_per_gpu:5249.826118156951 mfu:24.764325512045065 Step 3213 | loss:1.3914486169815063 lr:2.992815120481566e-05 tokens_per_second_per_gpu:5309.646240778224 mfu:25.04650723681497 Step 3214 | loss:1.2841734886169434 lr:2.9917438614262127e-05 tokens_per_second_per_gpu:3828.7828290534812 mfu:18.06102186235771 Step 3215 | loss:1.4802221059799194 lr:2.990672508436917e-05 tokens_per_second_per_gpu:5322.0318215269135 mfu:25.104932134404525 Step 3216 | loss:1.2762340307235718 lr:2.9896010617183307e-05 tokens_per_second_per_gpu:4212.383344157214 mfu:19.870530941098778 Step 3217 | loss:1.2166574001312256 lr:2.9885295214751258e-05 tokens_per_second_per_gpu:4567.086534629562 mfu:21.54372640916162 Step 3218 | loss:1.234444499015808 lr:2.9874578879119873e-05 tokens_per_second_per_gpu:5348.781162366976 mfu:25.23111333905526 Step 3219 | loss:1.2021981477737427 lr:2.9863861612336225e-05 tokens_per_second_per_gpu:3319.383299241804 mfu:15.658097367714106 Step 3220 | loss:1.4619367122650146 lr:2.9853143416447548e-05 tokens_per_second_per_gpu:5342.9042815275125 mfu:25.203391089436245 Step 3221 | loss:1.2551919221878052 lr:2.9842424293501263e-05 tokens_per_second_per_gpu:5287.17089782852 mfu:24.94048720943229 Step 3222 | loss:1.3932135105133057 lr:2.9831704245544933e-05 tokens_per_second_per_gpu:4510.552859423678 mfu:21.277047417575847 Step 3223 | loss:1.4341801404953003 lr:2.9820983274626352e-05 tokens_per_second_per_gpu:4473.827873621706 mfu:21.103809393619247 Step 3224 | loss:1.2997604608535767 lr:2.9810261382793452e-05 tokens_per_second_per_gpu:3708.4425156648886 mfu:17.493356071929043 Step 3225 | loss:1.243777871131897 lr:2.979953857209434e-05 tokens_per_second_per_gpu:5339.074895024615 mfu:25.18532721994137 Step 3226 | loss:1.394245982170105 lr:2.9788814844577324e-05 tokens_per_second_per_gpu:5106.577221310061 mfu:24.088596024836228 Step 3227 | loss:1.2711130380630493 lr:2.9778090202290876e-05 tokens_per_second_per_gpu:5283.740372450783 mfu:24.92430483591752 Step 3228 | loss:1.25494384765625 lr:2.976736464728362e-05 tokens_per_second_per_gpu:4312.597428953266 mfu:20.34325787736774 Step 3229 | loss:1.3109482526779175 lr:2.9756638181604392e-05 tokens_per_second_per_gpu:3431.4514084477582 mfu:16.186741759629697 Step 3230 | loss:1.3860118389129639 lr:2.974591080730218e-05 tokens_per_second_per_gpu:5188.05650049184 mfu:24.472947686535214 Step 3231 | loss:1.2968991994857788 lr:2.9735182526426142e-05 tokens_per_second_per_gpu:5316.336122476026 mfu:25.07806455019502 Step 3232 | loss:1.3265185356140137 lr:2.972445334102562e-05 tokens_per_second_per_gpu:5329.9367385300775 mfu:25.142220976626366 Step 3233 | loss:1.3950376510620117 lr:2.9713723253150138e-05 tokens_per_second_per_gpu:5073.893378638965 mfu:23.934420762518084 Step 3234 | loss:1.5232274532318115 lr:2.9702992264849362e-05 tokens_per_second_per_gpu:5342.649590096773 mfu:25.20218966650261 Step 3235 | loss:1.2883673906326294 lr:2.9692260378173154e-05 tokens_per_second_per_gpu:4288.270396387926 mfu:20.22850311413728 Step 3236 | loss:1.3529503345489502 lr:2.9681527595171554e-05 tokens_per_second_per_gpu:5315.65247141239 mfu:25.07483965148495 Step 3237 | loss:1.2648884057998657 lr:2.9670793917894736e-05 tokens_per_second_per_gpu:5306.825465135769 mfu:25.033201156835563 Step 3238 | loss:1.2889082431793213 lr:2.9660059348393086e-05 tokens_per_second_per_gpu:3765.080523096217 mfu:17.76052721642315 Step 3239 | loss:1.5842859745025635 lr:2.964932388871715e-05 tokens_per_second_per_gpu:3471.4218140291005 mfu:16.375288982411302 Step 3240 | loss:1.379894733428955 lr:2.9638587540917617e-05 tokens_per_second_per_gpu:5338.371562348259 mfu:25.18200947970607 Step 3241 | loss:1.3018325567245483 lr:2.9627850307045386e-05 tokens_per_second_per_gpu:5325.833565791965 mfu:25.122865610747233 Step 3242 | loss:1.2510815858840942 lr:2.96171121891515e-05 tokens_per_second_per_gpu:5120.9886160526 mfu:24.156577032674274 Step 3243 | loss:1.5248439311981201 lr:2.960637318928717e-05 tokens_per_second_per_gpu:3568.6413946028592 mfu:16.833890331348602 Step 3244 | loss:1.3495146036148071 lr:2.9595633309503784e-05 tokens_per_second_per_gpu:4506.639370615432 mfu:21.25858682315731 Step 3245 | loss:1.4486005306243896 lr:2.9584892551852912e-05 tokens_per_second_per_gpu:4036.313463538489 mfu:19.03997927360093 Step 3246 | loss:1.2550923824310303 lr:2.957415091838625e-05 tokens_per_second_per_gpu:5362.7517979724735 mfu:25.29701521084262 Step 3247 | loss:1.235485315322876 lr:2.9563408411155712e-05 tokens_per_second_per_gpu:4042.9614931490596 mfu:19.071339163544806 Step 3248 | loss:1.4418604373931885 lr:2.9552665032213344e-05 tokens_per_second_per_gpu:4086.3106186690793 mfu:19.275824384746215 Step 3249 | loss:1.326867938041687 lr:2.9541920783611356e-05 tokens_per_second_per_gpu:3846.5729810796815 mfu:18.14494104477822 Step 3250 | loss:1.3347493410110474 lr:2.9531175667402156e-05 tokens_per_second_per_gpu:4762.5554132015195 mfu:22.465786459815217 Step 3251 | loss:1.4878227710723877 lr:2.9520429685638302e-05 tokens_per_second_per_gpu:5300.011882486516 mfu:25.00106032496196 Step 3252 | loss:1.228624701499939 lr:2.9509682840372487e-05 tokens_per_second_per_gpu:4599.041829812911 mfu:21.69446498867704 Step 3253 | loss:1.2906866073608398 lr:2.9498935133657617e-05 tokens_per_second_per_gpu:3496.36763292387 mfu:16.492962666333515 Step 3254 | loss:1.153926134109497 lr:2.9488186567546737e-05 tokens_per_second_per_gpu:4694.6530509916265 mfu:22.145479431933516 Step 3255 | loss:1.1442103385925293 lr:2.947743714409307e-05 tokens_per_second_per_gpu:5302.68956684616 mfu:25.013691418946465 Step 3256 | loss:1.4666180610656738 lr:2.946668686534997e-05 tokens_per_second_per_gpu:3832.663243467108 mfu:18.07932643921375 Step 3257 | loss:1.243007779121399 lr:2.9455935733370998e-05 tokens_per_second_per_gpu:3873.869351021673 mfu:18.273702679035548 Step 3258 | loss:1.2481552362442017 lr:2.9445183750209855e-05 tokens_per_second_per_gpu:5141.222892583337 mfu:24.252025567393325 Step 3259 | loss:1.4025089740753174 lr:2.9434430917920395e-05 tokens_per_second_per_gpu:3407.9470302686805 mfu:16.075867597498544 Step 3260 | loss:1.2685374021530151 lr:2.9423677238556663e-05 tokens_per_second_per_gpu:5278.9992305391725 mfu:24.901940060598232 Step 3261 | loss:1.1904999017715454 lr:2.9412922714172835e-05 tokens_per_second_per_gpu:5308.254516066846 mfu:25.03994223389868 Step 3262 | loss:1.2440760135650635 lr:2.9402167346823272e-05 tokens_per_second_per_gpu:3240.7696513250976 mfu:15.287263377619576 Step 3263 | loss:1.2156239748001099 lr:2.9391411138562486e-05 tokens_per_second_per_gpu:4842.921953964772 mfu:22.844889144541263 Step 3264 | loss:1.3705153465270996 lr:2.9380654091445147e-05 tokens_per_second_per_gpu:4009.21757639289 mfu:18.91216335090008 Step 3265 | loss:1.3484020233154297 lr:2.936989620752609e-05 tokens_per_second_per_gpu:4726.578882999204 mfu:22.29607902862189 Step 3266 | loss:1.324206829071045 lr:2.935913748886031e-05 tokens_per_second_per_gpu:5238.576421947757 mfu:24.7112587756302 Step 3267 | loss:1.4893543720245361 lr:2.9348377937502963e-05 tokens_per_second_per_gpu:3623.4792174155873 mfu:17.0925696978536 Step 3268 | loss:1.2423720359802246 lr:2.9337617555509352e-05 tokens_per_second_per_gpu:5307.022991381731 mfu:25.034132921839216 Step 3269 | loss:1.2332377433776855 lr:2.932685634493495e-05 tokens_per_second_per_gpu:5322.584957988414 mfu:25.107541373468234 Step 3270 | loss:1.3581851720809937 lr:2.931609430783539e-05 tokens_per_second_per_gpu:5362.35248707954 mfu:25.295131593231186 Step 3271 | loss:1.389794111251831 lr:2.930533144626646e-05 tokens_per_second_per_gpu:4603.91871517451 mfu:21.71747008901015 Step 3272 | loss:1.3486021757125854 lr:2.9294567762284098e-05 tokens_per_second_per_gpu:5310.793035424316 mfu:25.051916862823937 Step 3273 | loss:1.2611522674560547 lr:2.928380325794441e-05 tokens_per_second_per_gpu:4285.51703427901 mfu:20.215515035297503 Step 3274 | loss:1.2787741422653198 lr:2.9273037935303654e-05 tokens_per_second_per_gpu:2949.136327054676 mfu:13.911579229260017 Step 3275 | loss:1.520018458366394 lr:2.9262271796418246e-05 tokens_per_second_per_gpu:5345.956826937114 mfu:25.21779046695129 Step 3276 | loss:1.4461408853530884 lr:2.9251504843344756e-05 tokens_per_second_per_gpu:5323.703123869232 mfu:25.11281595270682 Step 3277 | loss:1.385573387145996 lr:2.92407370781399e-05 tokens_per_second_per_gpu:4809.179305098509 mfu:22.685719312749548 Step 3278 | loss:1.3229587078094482 lr:2.9229968502860573e-05 tokens_per_second_per_gpu:4699.277200701707 mfu:22.167292335077263 Step 3279 | loss:1.2650809288024902 lr:2.9219199119563807e-05 tokens_per_second_per_gpu:3622.2775909530515 mfu:17.086901420811206 Step 3280 | loss:1.3382648229599 lr:2.9208428930306782e-05 tokens_per_second_per_gpu:4813.508237800442 mfu:22.706139626896647 Step 3281 | loss:1.3117815256118774 lr:2.919765793714685e-05 tokens_per_second_per_gpu:3621.8837338385188 mfu:17.085043529603002 Step 3282 | loss:1.3328255414962769 lr:2.918688614214152e-05 tokens_per_second_per_gpu:3705.4462566607513 mfu:17.479222206992027 Step 3283 | loss:1.2847703695297241 lr:2.9176113547348417e-05 tokens_per_second_per_gpu:4878.902578525816 mfu:23.014615889523284 Step 3284 | loss:1.327014684677124 lr:2.916534015482537e-05 tokens_per_second_per_gpu:5306.902864010585 mfu:25.03356626053368 Step 3285 | loss:1.118237853050232 lr:2.915456596663032e-05 tokens_per_second_per_gpu:5292.113866290661 mfu:24.963804035025593 Step 3286 | loss:1.2657285928726196 lr:2.914379098482138e-05 tokens_per_second_per_gpu:4394.159738653637 mfu:20.728001208189394 Step 3287 | loss:1.3841214179992676 lr:2.913301521145681e-05 tokens_per_second_per_gpu:4561.046550984937 mfu:21.51523477578245 Step 3288 | loss:1.1426081657409668 lr:2.912223864859502e-05 tokens_per_second_per_gpu:5345.357678333616 mfu:25.214964180763292 Step 3289 | loss:1.3239033222198486 lr:2.911146129829457e-05 tokens_per_second_per_gpu:4492.626992704884 mfu:21.19248804579506 Step 3290 | loss:1.289091944694519 lr:2.9100683162614172e-05 tokens_per_second_per_gpu:4416.617926965637 mfu:20.83394031421914 Step 3291 | loss:1.2887928485870361 lr:2.908990424361269e-05 tokens_per_second_per_gpu:4891.580834297143 mfu:23.074421385130123 Step 3292 | loss:1.43006432056427 lr:2.9079124543349135e-05 tokens_per_second_per_gpu:3874.414664139649 mfu:18.276275014053052 Step 3293 | loss:1.1665773391723633 lr:2.9068344063882667e-05 tokens_per_second_per_gpu:5157.270930193703 mfu:24.327726898878982 Step 3294 | loss:1.211026668548584 lr:2.9057562807272598e-05 tokens_per_second_per_gpu:5268.64183393074 mfu:24.853082453642173 Step 3295 | loss:1.2403124570846558 lr:2.9046780775578386e-05 tokens_per_second_per_gpu:5266.11705051163 mfu:24.841172619481757 Step 3296 | loss:1.407984733581543 lr:2.9035997970859636e-05 tokens_per_second_per_gpu:5263.981568341865 mfu:24.831099185736146 Step 3297 | loss:1.2483755350112915 lr:2.9025214395176103e-05 tokens_per_second_per_gpu:4380.656128109415 mfu:20.664302373298764 Step 3298 | loss:1.2947922945022583 lr:2.901443005058768e-05 tokens_per_second_per_gpu:3957.5680530361456 mfu:18.668523736908934 Step 3299 | loss:1.4443823099136353 lr:2.9003644939154433e-05 tokens_per_second_per_gpu:3050.888664017988 mfu:14.39156236345483 Step 3300 | loss:1.3260068893432617 lr:2.899285906293654e-05 tokens_per_second_per_gpu:5165.355055955563 mfu:24.36586109939176 Step 3301 | loss:1.3328819274902344 lr:2.898207242399435e-05 tokens_per_second_per_gpu:3797.0460171123245 mfu:17.911313905572793 Step 3302 | loss:1.4419077634811401 lr:2.8971285024388346e-05 tokens_per_second_per_gpu:4431.4042905642245 mfu:20.903690114127457 Step 3303 | loss:1.2423349618911743 lr:2.896049686617916e-05 tokens_per_second_per_gpu:5338.470043298552 mfu:25.182474031151184 Step 3304 | loss:1.2383321523666382 lr:2.8949707951427567e-05 tokens_per_second_per_gpu:5325.799777907053 mfu:25.12270622752929 Step 3305 | loss:1.1596864461898804 lr:2.8938918282194492e-05 tokens_per_second_per_gpu:4367.184805620635 mfu:20.60075584667457 Step 3306 | loss:1.1977187395095825 lr:2.8928127860541004e-05 tokens_per_second_per_gpu:5328.826683667908 mfu:25.13698465844662 Step 3307 | loss:1.2188822031021118 lr:2.8917336688528302e-05 tokens_per_second_per_gpu:5307.2840385382415 mfu:25.035364325815713 Step 3308 | loss:1.3474534749984741 lr:2.890654476821774e-05 tokens_per_second_per_gpu:4532.563053287586 mfu:21.380873257358214 Step 3309 | loss:1.2645232677459717 lr:2.889575210167082e-05 tokens_per_second_per_gpu:5188.459702934972 mfu:24.474849661252897 Step 3310 | loss:1.0779975652694702 lr:2.888495869094917e-05 tokens_per_second_per_gpu:5204.278854072014 mfu:24.549471296191825 Step 3311 | loss:1.2142058610916138 lr:2.8874164538114584e-05 tokens_per_second_per_gpu:4930.093960193242 mfu:23.256094370998884 Step 3312 | loss:1.1459540128707886 lr:2.886336964522897e-05 tokens_per_second_per_gpu:4139.181577701962 mfu:19.52522571922012 Step 3313 | loss:1.1768983602523804 lr:2.8852574014354394e-05 tokens_per_second_per_gpu:4188.339019800597 mfu:19.757109760723857 Step 3314 | loss:1.3738747835159302 lr:2.884177764755307e-05 tokens_per_second_per_gpu:3304.819504799479 mfu:15.5893974644901 Step 3315 | loss:1.315070629119873 lr:2.883098054688733e-05 tokens_per_second_per_gpu:5336.990406178002 mfu:25.175494330401424 Step 3316 | loss:1.3110555410385132 lr:2.8820182714419663e-05 tokens_per_second_per_gpu:5314.037649382175 mfu:25.067222260451377 Step 3317 | loss:1.304396390914917 lr:2.8809384152212697e-05 tokens_per_second_per_gpu:3963.5450216703584 mfu:18.696718117732523 Step 3318 | loss:1.2864309549331665 lr:2.8798584862329192e-05 tokens_per_second_per_gpu:4772.353370903754 mfu:22.512005098000618 Step 3319 | loss:1.2661781311035156 lr:2.878778484683205e-05 tokens_per_second_per_gpu:3567.257633036551 mfu:16.827362891946258 Step 3320 | loss:1.411932110786438 lr:2.877698410778432e-05 tokens_per_second_per_gpu:5332.599919575835 mfu:25.154783656004746 Step 3321 | loss:1.1442915201187134 lr:2.8766182647249174e-05 tokens_per_second_per_gpu:4670.445021506438 mfu:22.031286026536147 Step 3322 | loss:1.3265535831451416 lr:2.875538046728993e-05 tokens_per_second_per_gpu:4904.346659099712 mfu:23.134639958798147 Step 3323 | loss:1.2452114820480347 lr:2.874457756997005e-05 tokens_per_second_per_gpu:5322.63517620838 mfu:25.107778261379924 Step 3324 | loss:1.4757589101791382 lr:2.8733773957353116e-05 tokens_per_second_per_gpu:4501.214475017474 mfu:21.23299666503911 Step 3325 | loss:1.2632557153701782 lr:2.8722969631502867e-05 tokens_per_second_per_gpu:5315.7578772492125 mfu:25.075336868801333 Step 3326 | loss:1.450732946395874 lr:2.871216459448316e-05 tokens_per_second_per_gpu:4286.261526804136 mfu:20.219026933562052 Step 3327 | loss:1.463555097579956 lr:2.8701358848357996e-05 tokens_per_second_per_gpu:4623.205806659611 mfu:21.808450590262506 Step 3328 | loss:1.4455208778381348 lr:2.8690552395191517e-05 tokens_per_second_per_gpu:5243.115773102275 mfu:24.73267166951923 Step 3329 | loss:1.2732359170913696 lr:2.8679745237047993e-05 tokens_per_second_per_gpu:5319.6929097668 mfu:25.09389908857257 Step 3330 | loss:1.4472702741622925 lr:2.8668937375991827e-05 tokens_per_second_per_gpu:4855.183253282056 mfu:22.902727785414278 Step 3331 | loss:1.5041638612747192 lr:2.865812881408756e-05 tokens_per_second_per_gpu:3559.708025349221 mfu:16.791750104389227 Step 3332 | loss:1.408048391342163 lr:2.8647319553399867e-05 tokens_per_second_per_gpu:5305.429900137086 mfu:25.026618038628833 Step 3333 | loss:1.1449557542800903 lr:2.8636509595993555e-05 tokens_per_second_per_gpu:5325.949966048397 mfu:25.12341469061675 Step 3334 | loss:1.4100074768066406 lr:2.8625698943933564e-05 tokens_per_second_per_gpu:2770.7961797473176 mfu:13.070318326444445 Step 3335 | loss:1.2950611114501953 lr:2.8614887599284972e-05 tokens_per_second_per_gpu:3828.4125966072816 mfu:18.059275412740813 Step 3336 | loss:1.1996819972991943 lr:2.860407556411298e-05 tokens_per_second_per_gpu:5244.520319772721 mfu:24.739297155804103 Step 3337 | loss:1.2766603231430054 lr:2.8593262840482925e-05 tokens_per_second_per_gpu:3962.5126278543794 mfu:18.691848139957997 Step 3338 | loss:1.3946338891983032 lr:2.8582449430460277e-05 tokens_per_second_per_gpu:5354.319191092913 mfu:25.25723716544064 Step 3339 | loss:1.1324716806411743 lr:2.857163533611064e-05 tokens_per_second_per_gpu:5313.9222892949 mfu:25.066678087237243 Step 3340 | loss:1.348904013633728 lr:2.856082055949974e-05 tokens_per_second_per_gpu:4846.08188081558 mfu:22.85979505863564 Step 3341 | loss:1.3971290588378906 lr:2.8550005102693437e-05 tokens_per_second_per_gpu:4461.564309254703 mfu:21.045960068120255 Step 3342 | loss:1.338477373123169 lr:2.8539188967757734e-05 tokens_per_second_per_gpu:3817.7342803423717 mfu:18.00890397301061 Step 3343 | loss:1.397261381149292 lr:2.8528372156758737e-05 tokens_per_second_per_gpu:4930.571166392707 mfu:23.25834543406153 Step 3344 | loss:1.4055099487304688 lr:2.85175546717627e-05 tokens_per_second_per_gpu:3498.486831213965 mfu:16.502959286240408 Step 3345 | loss:1.3074917793273926 lr:2.850673651483601e-05 tokens_per_second_per_gpu:3813.7819702893694 mfu:17.990260252156972 Step 3346 | loss:1.324999213218689 lr:2.8495917688045164e-05 tokens_per_second_per_gpu:5285.417698687037 mfu:24.9322170699553 Step 3347 | loss:1.4158591032028198 lr:2.8485098193456806e-05 tokens_per_second_per_gpu:5356.024984508458 mfu:25.265283684020133 Step 3348 | loss:1.3864201307296753 lr:2.8474278033137687e-05 tokens_per_second_per_gpu:4909.629337434919 mfu:23.159559253823183 Step 3349 | loss:1.2995284795761108 lr:2.8463457209154703e-05 tokens_per_second_per_gpu:3379.2948326939804 mfu:15.940710292969685 Step 3350 | loss:1.4883052110671997 lr:2.845263572357487e-05 tokens_per_second_per_gpu:5279.542918290875 mfu:24.90450472848571 Step 3351 | loss:1.207801103591919 lr:2.8441813578465337e-05 tokens_per_second_per_gpu:4474.774649745348 mfu:21.108275498131132 Step 3352 | loss:1.2682881355285645 lr:2.8430990775893363e-05 tokens_per_second_per_gpu:4972.6863015791305 mfu:23.457009712318907 Step 3353 | loss:1.450901985168457 lr:2.8420167317926338e-05 tokens_per_second_per_gpu:5357.870263567297 mfu:25.273988180177753 Step 3354 | loss:1.2552701234817505 lr:2.8409343206631804e-05 tokens_per_second_per_gpu:3855.9498739150717 mfu:18.18917344814565 Step 3355 | loss:1.5331674814224243 lr:2.8398518444077387e-05 tokens_per_second_per_gpu:3518.060733362687 mfu:16.59529272232801 Step 3356 | loss:1.3029875755310059 lr:2.8387693032330855e-05 tokens_per_second_per_gpu:5298.965650318453 mfu:24.996125069319593 Step 3357 | loss:1.2442970275878906 lr:2.8376866973460116e-05 tokens_per_second_per_gpu:5197.5965818610075 mfu:24.517949878059305 Step 3358 | loss:1.2003437280654907 lr:2.8366040269533167e-05 tokens_per_second_per_gpu:4895.911024879943 mfu:23.09484763291589 Step 3359 | loss:1.2512836456298828 lr:2.8355212922618158e-05 tokens_per_second_per_gpu:5220.781753016112 mfu:24.62731828619604 Step 3360 | loss:1.288549780845642 lr:2.8344384934783357e-05 tokens_per_second_per_gpu:5258.312117834393 mfu:24.8043554203844 Step 3361 | loss:1.3312890529632568 lr:2.833355630809714e-05 tokens_per_second_per_gpu:5334.1762606393295 mfu:25.162219525752764 Step 3362 | loss:1.3544740676879883 lr:2.8322727044628007e-05 tokens_per_second_per_gpu:5241.462491289617 mfu:24.724872857129956 Step 3363 | loss:1.2352240085601807 lr:2.831189714644461e-05 tokens_per_second_per_gpu:5281.765313054315 mfu:24.9149881437645 Step 3364 | loss:1.288136601448059 lr:2.8301066615615678e-05 tokens_per_second_per_gpu:4721.9576674052505 mfu:22.274279966204524 Step 3365 | loss:1.3597853183746338 lr:2.8290235454210086e-05 tokens_per_second_per_gpu:4184.635875192194 mfu:19.7396413957844 Step 3366 | loss:1.2081592082977295 lr:2.8279403664296838e-05 tokens_per_second_per_gpu:4088.507113346738 mfu:19.286185624901368 Step 3367 | loss:1.319777250289917 lr:2.826857124794503e-05 tokens_per_second_per_gpu:4893.443852239052 mfu:23.083209558625747 Step 3368 | loss:1.393271803855896 lr:2.825773820722389e-05 tokens_per_second_per_gpu:3795.567313217347 mfu:17.904338607007283 Step 3369 | loss:1.1630446910858154 lr:2.8246904544202785e-05 tokens_per_second_per_gpu:3575.3717003601955 mfu:16.86563833191453 Step 3370 | loss:1.1663373708724976 lr:2.823607026095117e-05 tokens_per_second_per_gpu:4728.8824626704645 mfu:22.30694540696244 Step 3371 | loss:1.219009518623352 lr:2.8225235359538636e-05 tokens_per_second_per_gpu:5324.280005161422 mfu:25.115537200188182 Step 3372 | loss:1.3145017623901367 lr:2.82143998420349e-05 tokens_per_second_per_gpu:5308.714150296603 mfu:25.042110406982136 Step 3373 | loss:1.4268814325332642 lr:2.8203563710509767e-05 tokens_per_second_per_gpu:3254.8176547828425 mfu:15.353530206766301 Step 3374 | loss:1.1128822565078735 lr:2.819272696703318e-05 tokens_per_second_per_gpu:4215.564167979193 mfu:19.885535429771565 Step 3375 | loss:1.222253680229187 lr:2.818188961367521e-05 tokens_per_second_per_gpu:3896.2828416750203 mfu:18.379430938583223 Step 3376 | loss:1.1730326414108276 lr:2.8171051652506025e-05 tokens_per_second_per_gpu:4221.684950781494 mfu:19.914408206563248 Step 3377 | loss:1.1681103706359863 lr:2.8160213085595906e-05 tokens_per_second_per_gpu:5330.901781498233 mfu:25.14677324896046 Step 3378 | loss:1.3316727876663208 lr:2.8149373915015274e-05 tokens_per_second_per_gpu:4774.905504536158 mfu:22.52404394778357 Step 3379 | loss:1.2484036684036255 lr:2.813853414283464e-05 tokens_per_second_per_gpu:4148.8279571111725 mfu:19.57072933673541 Step 3380 | loss:1.162934422492981 lr:2.812769377112463e-05 tokens_per_second_per_gpu:5275.151338893771 mfu:24.88378889918886 Step 3381 | loss:1.322590947151184 lr:2.8116852801956023e-05 tokens_per_second_per_gpu:5331.965285820304 mfu:25.151789980300222 Step 3382 | loss:1.2543822526931763 lr:2.810601123739966e-05 tokens_per_second_per_gpu:5356.812438649054 mfu:25.26899823955485 Step 3383 | loss:1.2300143241882324 lr:2.8095169079526518e-05 tokens_per_second_per_gpu:5328.03646230208 mfu:25.133257049438342 Step 3384 | loss:1.218764305114746 lr:2.808432633040771e-05 tokens_per_second_per_gpu:5325.430828433204 mfu:25.120965829911874 Step 3385 | loss:1.3814467191696167 lr:2.8073482992114426e-05 tokens_per_second_per_gpu:4683.617177793107 mfu:22.09342133514197 Step 3386 | loss:1.2587512731552124 lr:2.806263906671797e-05 tokens_per_second_per_gpu:4183.691552127182 mfu:19.73518686276861 Step 3387 | loss:1.2669461965560913 lr:2.80517945562898e-05 tokens_per_second_per_gpu:3717.4973449294157 mfu:17.536069246482995 Step 3388 | loss:1.2689939737319946 lr:2.8040949462901444e-05 tokens_per_second_per_gpu:4104.3583741646635 mfu:19.3609587266835 Step 3389 | loss:1.5831540822982788 lr:2.8030103788624546e-05 tokens_per_second_per_gpu:4072.1809592995746 mfu:19.209172370731782 Step 3390 | loss:1.3269776105880737 lr:2.8019257535530886e-05 tokens_per_second_per_gpu:4976.788002479217 mfu:23.47635813528695 Step 3391 | loss:1.2263588905334473 lr:2.800841070569233e-05 tokens_per_second_per_gpu:4205.371013002577 mfu:19.837452578615288 Step 3392 | loss:1.2997932434082031 lr:2.799756330118085e-05 tokens_per_second_per_gpu:4525.755906076369 mfu:21.348762782543826 Step 3393 | loss:1.2726244926452637 lr:2.7986715324068556e-05 tokens_per_second_per_gpu:3850.0692031508643 mfu:18.16143332080499 Step 3394 | loss:1.4348498582839966 lr:2.7975866776427657e-05 tokens_per_second_per_gpu:5333.388060944662 mfu:25.158501453312287 Step 3395 | loss:1.1487300395965576 lr:2.796501766033044e-05 tokens_per_second_per_gpu:4573.109713683661 mfu:21.572138772420118 Step 3396 | loss:1.2764567136764526 lr:2.7954167977849343e-05 tokens_per_second_per_gpu:4511.363773214807 mfu:21.280872636284766 Step 3397 | loss:1.2905057668685913 lr:2.7943317731056902e-05 tokens_per_second_per_gpu:5326.383738537849 mfu:25.125460869458713 Step 3398 | loss:1.4275604486465454 lr:2.7932466922025735e-05 tokens_per_second_per_gpu:5336.847981199272 mfu:25.174822487476547 Step 3399 | loss:1.4796065092086792 lr:2.79216155528286e-05 tokens_per_second_per_gpu:4278.624586484162 mfu:20.18300218307635 Step 3400 | loss:1.3357157707214355 lr:2.791076362553835e-05 tokens_per_second_per_gpu:5276.345716138455 mfu:24.889422980433803 Step 3401 | loss:1.4462941884994507 lr:2.7899911142227925e-05 tokens_per_second_per_gpu:5091.629821772061 mfu:24.018086590926142 Step 3402 | loss:1.3710169792175293 lr:2.7889058104970407e-05 tokens_per_second_per_gpu:4751.788992293092 mfu:22.414999415449333 Step 3403 | loss:1.4234814643859863 lr:2.7878204515838963e-05 tokens_per_second_per_gpu:3518.895747694485 mfu:16.599231627399238 Step 3404 | loss:1.0958119630813599 lr:2.786735037690686e-05 tokens_per_second_per_gpu:4792.535925452451 mfu:22.607209651305713 Step 3405 | loss:1.402138352394104 lr:2.7856495690247487e-05 tokens_per_second_per_gpu:5340.934539196571 mfu:25.194099478788498 Step 3406 | loss:1.25251042842865 lr:2.7845640457934325e-05 tokens_per_second_per_gpu:5315.408896224328 mfu:25.07369066576465 Step 3407 | loss:1.3441486358642578 lr:2.783478468204096e-05 tokens_per_second_per_gpu:5203.775300211701 mfu:24.547095946717576 Step 3408 | loss:1.3017491102218628 lr:2.7823928364641093e-05 tokens_per_second_per_gpu:5156.074035231254 mfu:24.322080941129773 Step 3409 | loss:1.3759677410125732 lr:2.781307150780852e-05 tokens_per_second_per_gpu:4286.970607862945 mfu:20.222371789898155 Step 3410 | loss:1.3688102960586548 lr:2.780221411361713e-05 tokens_per_second_per_gpu:3690.021022693511 mfu:17.406458746552254 Step 3411 | loss:1.1359329223632812 lr:2.7791356184140933e-05 tokens_per_second_per_gpu:5311.509858068308 mfu:25.055298237538196 Step 3412 | loss:1.4857052564620972 lr:2.778049772145404e-05 tokens_per_second_per_gpu:3988.983205836348 mfu:18.81671437264526 Step 3413 | loss:1.4813923835754395 lr:2.7769638727630643e-05 tokens_per_second_per_gpu:3553.538559976908 mfu:16.76264768360869 Step 3414 | loss:1.2001758813858032 lr:2.775877920474505e-05 tokens_per_second_per_gpu:3594.4890177784355 mfu:16.95581797992706 Step 3415 | loss:1.385591745376587 lr:2.7747919154871695e-05 tokens_per_second_per_gpu:4818.1844360375335 mfu:22.7281980518227 Step 3416 | loss:1.2385812997817993 lr:2.7737058580085057e-05 tokens_per_second_per_gpu:4494.342808818774 mfu:21.20058184315269 Step 3417 | loss:1.3830868005752563 lr:2.772619748245975e-05 tokens_per_second_per_gpu:4600.466363224724 mfu:21.701184755831026 Step 3418 | loss:1.430586338043213 lr:2.77153358640705e-05 tokens_per_second_per_gpu:4458.5113687227495 mfu:21.031558826745663 Step 3419 | loss:1.4092820882797241 lr:2.7704473726992114e-05 tokens_per_second_per_gpu:4725.698604177897 mfu:22.29192660323073 Step 3420 | loss:1.161083698272705 lr:2.769361107329948e-05 tokens_per_second_per_gpu:5315.341405292855 mfu:25.07337229952575 Step 3421 | loss:1.2538565397262573 lr:2.7682747905067623e-05 tokens_per_second_per_gpu:5238.260039336496 mfu:24.709766344872445 Step 3422 | loss:1.300262689590454 lr:2.7671884224371653e-05 tokens_per_second_per_gpu:4707.7883850492035 mfu:22.20744104380219 Step 3423 | loss:1.2207883596420288 lr:2.766102003328675e-05 tokens_per_second_per_gpu:4356.086084342806 mfu:20.548401284769934 Step 3424 | loss:1.1741218566894531 lr:2.7650155333888226e-05 tokens_per_second_per_gpu:4162.364220753253 mfu:19.63458220185983 Step 3425 | loss:1.3456791639328003 lr:2.76392901282515e-05 tokens_per_second_per_gpu:5314.405021835847 mfu:25.068955218995555 Step 3426 | loss:1.2937630414962769 lr:2.7628424418452027e-05 tokens_per_second_per_gpu:3229.649748579631 mfu:15.234808899118162 Step 3427 | loss:1.1607134342193604 lr:2.7617558206565423e-05 tokens_per_second_per_gpu:5350.373106602604 mfu:25.238622811628414 Step 3428 | loss:1.2118252515792847 lr:2.760669149466738e-05 tokens_per_second_per_gpu:2895.1826981113545 mfu:13.657070756096036 Step 3429 | loss:1.3855388164520264 lr:2.7595824284833653e-05 tokens_per_second_per_gpu:3732.3095224086665 mfu:17.6059408148707 Step 3430 | loss:1.3131664991378784 lr:2.7584956579140147e-05 tokens_per_second_per_gpu:3212.8259394711677 mfu:15.155448121115716 Step 3431 | loss:1.1536922454833984 lr:2.757408837966282e-05 tokens_per_second_per_gpu:4199.89723125762 mfu:19.81163181620086 Step 3432 | loss:1.2214127779006958 lr:2.7563219688477737e-05 tokens_per_second_per_gpu:4557.329675154553 mfu:21.49770163832612 Step 3433 | loss:1.3678269386291504 lr:2.7552350507661063e-05 tokens_per_second_per_gpu:4332.618830256739 mfu:20.437702243319535 Step 3434 | loss:1.2812013626098633 lr:2.754148083928906e-05 tokens_per_second_per_gpu:5311.882873250253 mfu:25.057057813794387 Step 3435 | loss:1.3370614051818848 lr:2.7530610685438046e-05 tokens_per_second_per_gpu:4293.550393257541 mfu:20.253409760231616 Step 3436 | loss:1.329960584640503 lr:2.751974004818449e-05 tokens_per_second_per_gpu:4904.027646034481 mfu:23.133135119740214 Step 3437 | loss:1.26258385181427 lr:2.750886892960492e-05 tokens_per_second_per_gpu:4894.339557488154 mfu:23.087434753108834 Step 3438 | loss:1.3295197486877441 lr:2.7497997331775936e-05 tokens_per_second_per_gpu:3822.3735596866104 mfu:18.030788245220062 Step 3439 | loss:1.2644178867340088 lr:2.7487125256774282e-05 tokens_per_second_per_gpu:5290.463850663858 mfu:24.956020629792267 Step 3440 | loss:1.2348971366882324 lr:2.7476252706676757e-05 tokens_per_second_per_gpu:4173.380717733019 mfu:19.68654889772159 Step 3441 | loss:1.3183515071868896 lr:2.746537968356025e-05 tokens_per_second_per_gpu:5275.904789063634 mfu:24.88734305219196 Step 3442 | loss:1.1865673065185547 lr:2.745450618950175e-05 tokens_per_second_per_gpu:3901.9946235691777 mfu:18.40637438830845 Step 3443 | loss:1.4842201471328735 lr:2.744363222657835e-05 tokens_per_second_per_gpu:4796.8521907662325 mfu:22.62757021122162 Step 3444 | loss:1.1811550855636597 lr:2.7432757796867192e-05 tokens_per_second_per_gpu:4265.205736349778 mfu:20.119703177500543 Step 3445 | loss:1.1924949884414673 lr:2.742188290244555e-05 tokens_per_second_per_gpu:5298.312073451311 mfu:24.993042035725573 Step 3446 | loss:1.1711524724960327 lr:2.7411007545390767e-05 tokens_per_second_per_gpu:5198.42279354313 mfu:24.521847259530123 Step 3447 | loss:1.4863473176956177 lr:2.7400131727780266e-05 tokens_per_second_per_gpu:3042.2733102349594 mfu:14.350922269729352 Step 3448 | loss:1.3985897302627563 lr:2.738925545169158e-05 tokens_per_second_per_gpu:4738.859798733049 mfu:22.354010203478722 Step 3449 | loss:1.3836451768875122 lr:2.7378378719202325e-05 tokens_per_second_per_gpu:5328.570517764864 mfu:25.135776280175556 Step 3450 | loss:1.1546884775161743 lr:2.7367501532390173e-05 tokens_per_second_per_gpu:4641.824630002332 mfu:21.896278756668956 Step 3451 | loss:1.2568758726119995 lr:2.735662389333292e-05 tokens_per_second_per_gpu:5355.612796567834 mfu:25.2633393231777 Step 3452 | loss:1.3811860084533691 lr:2.7345745804108446e-05 tokens_per_second_per_gpu:4208.605215391394 mfu:19.85270886309517 Step 3453 | loss:1.133364200592041 lr:2.7334867266794688e-05 tokens_per_second_per_gpu:3985.6813646564774 mfu:18.801139024447615 Step 3454 | loss:1.3521686792373657 lr:2.7323988283469705e-05 tokens_per_second_per_gpu:5153.770107436957 mfu:24.311212920633455 Step 3455 | loss:1.152148962020874 lr:2.7313108856211606e-05 tokens_per_second_per_gpu:5234.589904613236 mfu:24.69245369319327 Step 3456 | loss:1.2868659496307373 lr:2.730222898709861e-05 tokens_per_second_per_gpu:4565.67450429626 mfu:21.53706562116222 Step 3457 | loss:1.2352168560028076 lr:2.7291348678209017e-05 tokens_per_second_per_gpu:5002.036439505945 mfu:23.595459320569592 Step 3458 | loss:1.205162525177002 lr:2.7280467931621195e-05 tokens_per_second_per_gpu:5327.067855851858 mfu:25.128687967551343 Step 3459 | loss:1.2296332120895386 lr:2.7269586749413615e-05 tokens_per_second_per_gpu:4641.27702199787 mfu:21.89369559628035 Step 3460 | loss:1.242706060409546 lr:2.7258705133664825e-05 tokens_per_second_per_gpu:5317.089353577031 mfu:25.081617669812942 Step 3461 | loss:1.1891850233078003 lr:2.724782308645345e-05 tokens_per_second_per_gpu:4383.468054871844 mfu:20.677566711601322 Step 3462 | loss:1.279186487197876 lr:2.7236940609858195e-05 tokens_per_second_per_gpu:4707.760852038657 mfu:22.207311165893827 Step 3463 | loss:1.3412599563598633 lr:2.7226057705957868e-05 tokens_per_second_per_gpu:4782.508682263578 mfu:22.559909434359692 Step 3464 | loss:1.3383071422576904 lr:2.7215174376831337e-05 tokens_per_second_per_gpu:4919.180292031134 mfu:23.20461273621442 Step 3465 | loss:1.3482913970947266 lr:2.7204290624557554e-05 tokens_per_second_per_gpu:4154.617924443087 mfu:19.598041600510342 Step 3466 | loss:1.1170141696929932 lr:2.7193406451215558e-05 tokens_per_second_per_gpu:5359.172527439873 mfu:25.28013118105382 Step 3467 | loss:1.4560916423797607 lr:2.7182521858884473e-05 tokens_per_second_per_gpu:4506.046427873369 mfu:21.255789811076532 Step 3468 | loss:1.2600418329238892 lr:2.717163684964349e-05 tokens_per_second_per_gpu:4510.626277217518 mfu:21.27739374183576 Step 3469 | loss:1.3693128824234009 lr:2.716075142557189e-05 tokens_per_second_per_gpu:5280.9966102435255 mfu:24.91136204145178 Step 3470 | loss:1.3181008100509644 lr:2.714986558874903e-05 tokens_per_second_per_gpu:3474.7472356984254 mfu:16.39097556380095 Step 3471 | loss:1.1049400568008423 lr:2.713897934125434e-05 tokens_per_second_per_gpu:5315.5729604251055 mfu:25.074464584591954 Step 3472 | loss:1.2310435771942139 lr:2.712809268516734e-05 tokens_per_second_per_gpu:5326.852414780068 mfu:25.127671695257675 Step 3473 | loss:1.4024367332458496 lr:2.7117205622567616e-05 tokens_per_second_per_gpu:4377.685806032581 mfu:20.650290857273138 Step 3474 | loss:1.423953652381897 lr:2.7106318155534844e-05 tokens_per_second_per_gpu:4057.492224507956 mfu:19.139883102563136 Step 3475 | loss:1.267611026763916 lr:2.709543028614876e-05 tokens_per_second_per_gpu:5319.615922354072 mfu:25.093535925811324 Step 3476 | loss:1.3112703561782837 lr:2.70845420164892e-05 tokens_per_second_per_gpu:5321.258138657865 mfu:25.101282540307313 Step 3477 | loss:1.3112839460372925 lr:2.7073653348636057e-05 tokens_per_second_per_gpu:4818.36911608053 mfu:22.72906921909518 Step 3478 | loss:1.221541166305542 lr:2.706276428466931e-05 tokens_per_second_per_gpu:3592.0610460341773 mfu:16.944364822954697 Step 3479 | loss:1.319189429283142 lr:2.7051874826669015e-05 tokens_per_second_per_gpu:4324.524573307246 mfu:20.399520252266136 Step 3480 | loss:1.2217780351638794 lr:2.7040984976715288e-05 tokens_per_second_per_gpu:5097.330073913644 mfu:24.04497565284129 Step 3481 | loss:1.1934928894042969 lr:2.7030094736888338e-05 tokens_per_second_per_gpu:3449.775950179011 mfu:16.273181749465227 Step 3482 | loss:1.2677861452102661 lr:2.701920410926844e-05 tokens_per_second_per_gpu:3720.5540355607195 mfu:17.550488177716055 Step 3483 | loss:1.350280523300171 lr:2.7008313095935943e-05 tokens_per_second_per_gpu:5309.299606382372 mfu:25.044872103227814 Step 3484 | loss:1.2536624670028687 lr:2.6997421698971277e-05 tokens_per_second_per_gpu:5314.620240720145 mfu:25.06997044319292 Step 3485 | loss:1.4873225688934326 lr:2.6986529920454935e-05 tokens_per_second_per_gpu:3567.016962191216 mfu:16.82622760650613 Step 3486 | loss:1.2705191373825073 lr:2.6975637762467486e-05 tokens_per_second_per_gpu:5330.190264515288 mfu:25.14341690195459 Step 3487 | loss:1.3301926851272583 lr:2.6964745227089576e-05 tokens_per_second_per_gpu:4882.100992843352 mfu:23.02970335556486 Step 3488 | loss:1.3411592245101929 lr:2.695385231640192e-05 tokens_per_second_per_gpu:4845.964597303132 mfu:22.859241812296794 Step 3489 | loss:1.388435959815979 lr:2.69429590324853e-05 tokens_per_second_per_gpu:5310.249944813467 mfu:25.049355011751747 Step 3490 | loss:1.4495980739593506 lr:2.6932065377420575e-05 tokens_per_second_per_gpu:5346.1075302484405 mfu:25.21850136018345 Step 3491 | loss:1.2417627573013306 lr:2.6921171353288677e-05 tokens_per_second_per_gpu:4649.0028123706925 mfu:21.930139467624713 Step 3492 | loss:1.3324726819992065 lr:2.6910276962170607e-05 tokens_per_second_per_gpu:5330.899319621412 mfu:25.146761635867463 Step 3493 | loss:1.2849524021148682 lr:2.689938220614743e-05 tokens_per_second_per_gpu:3017.6163544520286 mfu:14.23461120239081 Step 3494 | loss:1.2874125242233276 lr:2.6888487087300284e-05 tokens_per_second_per_gpu:4995.444359408515 mfu:23.564363354025176 Step 3495 | loss:1.2859350442886353 lr:2.6877591607710385e-05 tokens_per_second_per_gpu:4624.0401278595955 mfu:21.812386225712707 Step 3496 | loss:1.4397952556610107 lr:2.6866695769458998e-05 tokens_per_second_per_gpu:3679.9398140483027 mfu:17.35890396534125 Step 3497 | loss:1.3843938112258911 lr:2.6855799574627482e-05 tokens_per_second_per_gpu:3710.390680822247 mfu:17.50254589936755 Step 3498 | loss:1.3244954347610474 lr:2.6844903025297248e-05 tokens_per_second_per_gpu:4564.029580823421 mfu:21.52930623648795 Step 3499 | loss:1.3703988790512085 lr:2.683400612354977e-05 tokens_per_second_per_gpu:5314.49305184992 mfu:25.069370471591405 Step 3500 | loss:1.2329925298690796 lr:2.68231088714666e-05 tokens_per_second_per_gpu:4807.7776534800005 mfu:22.67910748291862 Step 3501 | loss:1.5783721208572388 lr:2.6812211271129362e-05 tokens_per_second_per_gpu:4387.178996021447 mfu:20.69507185415585 Step 3502 | loss:1.2642550468444824 lr:2.6801313324619725e-05 tokens_per_second_per_gpu:5300.232158564484 mfu:25.002099404804706 Step 3503 | loss:1.1246058940887451 lr:2.679041503401945e-05 tokens_per_second_per_gpu:5322.76796661115 mfu:25.10840465636617 Step 3504 | loss:1.2672713994979858 lr:2.6779516401410344e-05 tokens_per_second_per_gpu:4658.556773533318 mfu:21.97520713250268 Step 3505 | loss:1.2170027494430542 lr:2.6768617428874292e-05 tokens_per_second_per_gpu:5142.965988885072 mfu:24.260248050051505 Step 3506 | loss:1.3863551616668701 lr:2.675771811849323e-05 tokens_per_second_per_gpu:5344.954659105168 mfu:25.213063070300535 Step 3507 | loss:1.5275211334228516 lr:2.674681847234918e-05 tokens_per_second_per_gpu:4689.598680081318 mfu:22.121637101984987 Step 3508 | loss:1.4234471321105957 lr:2.67359184925242e-05 tokens_per_second_per_gpu:4821.7404897449815 mfu:22.74497256388606 Step 3509 | loss:1.2307102680206299 lr:2.6725018181100437e-05 tokens_per_second_per_gpu:5328.910465728557 mfu:25.137379872721397 Step 3510 | loss:1.4389703273773193 lr:2.6714117540160082e-05 tokens_per_second_per_gpu:5312.469708693563 mfu:25.059826016704932 Step 3511 | loss:1.1366777420043945 lr:2.6703216571785416e-05 tokens_per_second_per_gpu:5319.704105781741 mfu:25.093951902085287 Step 3512 | loss:1.1670275926589966 lr:2.669231527805875e-05 tokens_per_second_per_gpu:4487.5703732722195 mfu:21.16863510918294 Step 3513 | loss:1.1537392139434814 lr:2.668141366106247e-05 tokens_per_second_per_gpu:4450.193698456438 mfu:20.99232295695859 Step 3514 | loss:1.5355455875396729 lr:2.6670511722879037e-05 tokens_per_second_per_gpu:5301.137509388613 mfu:25.006370099110903 Step 3515 | loss:1.3824890851974487 lr:2.6659609465590958e-05 tokens_per_second_per_gpu:3399.0336291939125 mfu:16.033821563845823 Step 3516 | loss:1.0925366878509521 lr:2.66487068912808e-05 tokens_per_second_per_gpu:5285.7537446840615 mfu:24.93380225625862 Step 3517 | loss:1.3647006750106812 lr:2.6637804002031204e-05 tokens_per_second_per_gpu:5326.382867697018 mfu:25.125456761553934 Step 3518 | loss:1.459638237953186 lr:2.662690079992485e-05 tokens_per_second_per_gpu:3783.5391436121413 mfu:17.847599678762176 Step 3519 | loss:1.1559950113296509 lr:2.661599728704451e-05 tokens_per_second_per_gpu:5268.677726698401 mfu:24.853251765951168 Step 3520 | loss:1.5484859943389893 lr:2.6605093465472968e-05 tokens_per_second_per_gpu:4480.772636180331 mfu:21.136569023506958 Step 3521 | loss:1.3697677850723267 lr:2.659418933729313e-05 tokens_per_second_per_gpu:5303.812647373101 mfu:25.01898918140934 Step 3522 | loss:1.3077043294906616 lr:2.6583284904587897e-05 tokens_per_second_per_gpu:4568.289568026801 mfu:21.549401322955063 Step 3523 | loss:1.2951189279556274 lr:2.657238016944026e-05 tokens_per_second_per_gpu:5251.566777031379 mfu:24.77253649694277 Step 3524 | loss:1.3780354261398315 lr:2.6561475133933285e-05 tokens_per_second_per_gpu:4268.69198564905 mfu:20.13614841026068 Step 3525 | loss:1.3403215408325195 lr:2.6550569800150048e-05 tokens_per_second_per_gpu:4166.165675326502 mfu:19.652514311676878 Step 3526 | loss:1.325169324874878 lr:2.6539664170173718e-05 tokens_per_second_per_gpu:5297.09172217067 mfu:24.987285430521393 Step 3527 | loss:1.2024993896484375 lr:2.6528758246087528e-05 tokens_per_second_per_gpu:3471.7216355502374 mfu:16.376703291681327 Step 3528 | loss:1.3066601753234863 lr:2.651785202997473e-05 tokens_per_second_per_gpu:4237.343229609526 mfu:19.988270979372928 Step 3529 | loss:1.3621066808700562 lr:2.650694552391865e-05 tokens_per_second_per_gpu:5351.168301240676 mfu:25.242373880410394 Step 3530 | loss:1.5241124629974365 lr:2.6496038730002697e-05 tokens_per_second_per_gpu:5239.314443502547 mfu:24.714740149223605 Step 3531 | loss:1.308003306388855 lr:2.6485131650310287e-05 tokens_per_second_per_gpu:4136.956938469319 mfu:19.514731716397147 Step 3532 | loss:1.34166419506073 lr:2.647422428692491e-05 tokens_per_second_per_gpu:4687.593976723817 mfu:22.112180574209994 Step 3533 | loss:1.2816557884216309 lr:2.6463316641930135e-05 tokens_per_second_per_gpu:5360.169915228615 mfu:25.284836029425218 Step 3534 | loss:1.2035977840423584 lr:2.6452408717409543e-05 tokens_per_second_per_gpu:4220.371330588589 mfu:19.9082116359866 Step 3535 | loss:1.2757782936096191 lr:2.6441500515446793e-05 tokens_per_second_per_gpu:4384.1707406579 mfu:20.680881400344703 Step 3536 | loss:1.3350201845169067 lr:2.6430592038125606e-05 tokens_per_second_per_gpu:4721.387827730851 mfu:22.27159193523571 Step 3537 | loss:1.324912190437317 lr:2.641968328752973e-05 tokens_per_second_per_gpu:5353.238606766346 mfu:25.252139864805525 Step 3538 | loss:1.3384829759597778 lr:2.640877426574297e-05 tokens_per_second_per_gpu:4579.789846122196 mfu:21.60365009688081 Step 3539 | loss:1.405479907989502 lr:2.639786497484921e-05 tokens_per_second_per_gpu:4237.323014627907 mfu:19.988175621855596 Step 3540 | loss:1.5138674974441528 lr:2.6386955416932358e-05 tokens_per_second_per_gpu:4101.600720349587 mfu:19.347950403133524 Step 3541 | loss:1.3693461418151855 lr:2.6376045594076366e-05 tokens_per_second_per_gpu:3617.3208429295396 mfu:17.06351959467588 Step 3542 | loss:1.3807445764541626 lr:2.6365135508365273e-05 tokens_per_second_per_gpu:3797.417407089757 mfu:17.913065815462005 Step 3543 | loss:1.4764918088912964 lr:2.6354225161883135e-05 tokens_per_second_per_gpu:4723.209773821945 mfu:22.28018636580346 Step 3544 | loss:1.4414544105529785 lr:2.6343314556714072e-05 tokens_per_second_per_gpu:5083.584338540925 mfu:23.980134673823887 Step 3545 | loss:1.534675121307373 lr:2.6332403694942243e-05 tokens_per_second_per_gpu:5309.794147366529 mfu:25.047204937427473 Step 3546 | loss:1.387290596961975 lr:2.6321492578651873e-05 tokens_per_second_per_gpu:4232.683262987858 mfu:19.96628912174623 Step 3547 | loss:1.1428393125534058 lr:2.6310581209927226e-05 tokens_per_second_per_gpu:5264.656853473892 mfu:24.83428462091944 Step 3548 | loss:1.3181633949279785 lr:2.629966959085261e-05 tokens_per_second_per_gpu:5332.889309439256 mfu:25.156148757365504 Step 3549 | loss:1.3898898363113403 lr:2.6288757723512386e-05 tokens_per_second_per_gpu:5350.567066157337 mfu:25.239537751941 Step 3550 | loss:1.2896056175231934 lr:2.6277845609990964e-05 tokens_per_second_per_gpu:5198.348968522673 mfu:24.52149901431278 Step 3551 | loss:1.254195213317871 lr:2.6266933252372794e-05 tokens_per_second_per_gpu:5309.437641942732 mfu:25.045523240517326 Step 3552 | loss:1.2727833986282349 lr:2.6256020652742385e-05 tokens_per_second_per_gpu:4747.982625678487 mfu:22.397044134695136 Step 3553 | loss:1.3067125082015991 lr:2.6245107813184284e-05 tokens_per_second_per_gpu:4925.810506014568 mfu:23.23588858680543 Step 3554 | loss:1.2189433574676514 lr:2.6234194735783075e-05 tokens_per_second_per_gpu:4110.563985210481 mfu:19.390231652773043 Step 3555 | loss:1.280849814414978 lr:2.6223281422623408e-05 tokens_per_second_per_gpu:5301.480695136443 mfu:25.007988964836944 Step 3556 | loss:1.3899692296981812 lr:2.6212367875789963e-05 tokens_per_second_per_gpu:4794.500806696765 mfu:22.616478331378453 Step 3557 | loss:1.3003392219543457 lr:2.6201454097367458e-05 tokens_per_second_per_gpu:5318.1423824310305 mfu:25.086584986582505 Step 3558 | loss:1.2365436553955078 lr:2.6190540089440684e-05 tokens_per_second_per_gpu:3594.926060363292 mfu:16.95787958436698 Step 3559 | loss:1.2729429006576538 lr:2.617962585409445e-05 tokens_per_second_per_gpu:5376.168810169647 mfu:25.360305546555022 Step 3560 | loss:1.5591676235198975 lr:2.6168711393413603e-05 tokens_per_second_per_gpu:5212.093511156756 mfu:24.58633436697854 Step 3561 | loss:1.2688004970550537 lr:2.615779670948307e-05 tokens_per_second_per_gpu:4903.843957702881 mfu:23.132268630539595 Step 3562 | loss:1.378612756729126 lr:2.614688180438779e-05 tokens_per_second_per_gpu:4948.778250456474 mfu:23.344231356039188 Step 3563 | loss:1.2608932256698608 lr:2.613596668021273e-05 tokens_per_second_per_gpu:4402.992688243072 mfu:20.76966773845936 Step 3564 | loss:1.1403539180755615 lr:2.612505133904295e-05 tokens_per_second_per_gpu:3354.4759788152683 mfu:15.823635524690676 Step 3565 | loss:1.262034296989441 lr:2.6114135782963504e-05 tokens_per_second_per_gpu:5340.500280685979 mfu:25.192051007301895 Step 3566 | loss:1.3907290697097778 lr:2.61032200140595e-05 tokens_per_second_per_gpu:5334.218474868123 mfu:25.16241865747247 Step 3567 | loss:1.5526307821273804 lr:2.609230403441611e-05 tokens_per_second_per_gpu:3507.402283541373 mfu:16.54501499600181 Step 3568 | loss:1.3023815155029297 lr:2.608138784611851e-05 tokens_per_second_per_gpu:4777.04364886491 mfu:22.534129939387334 Step 3569 | loss:1.3326141834259033 lr:2.6070471451251932e-05 tokens_per_second_per_gpu:5243.587548438144 mfu:24.734897114271696 Step 3570 | loss:1.1870040893554688 lr:2.6059554851901673e-05 tokens_per_second_per_gpu:4714.473934596063 mfu:22.238977921687106 Step 3571 | loss:1.2461694478988647 lr:2.6048638050153018e-05 tokens_per_second_per_gpu:5047.165762240225 mfu:23.808342035763637 Step 3572 | loss:1.1604522466659546 lr:2.603772104809132e-05 tokens_per_second_per_gpu:4566.314702301444 mfu:21.540085544381714 Step 3573 | loss:1.2897412776947021 lr:2.602680384780199e-05 tokens_per_second_per_gpu:4818.933893639176 mfu:22.7317333712003 Step 3574 | loss:1.1921226978302002 lr:2.6015886451370425e-05 tokens_per_second_per_gpu:4750.441491931317 mfu:22.408643026335575 Step 3575 | loss:1.2307292222976685 lr:2.6004968860882107e-05 tokens_per_second_per_gpu:4573.54557096955 mfu:21.57419478560258 Step 3576 | loss:1.19390869140625 lr:2.5994051078422537e-05 tokens_per_second_per_gpu:4659.06116632298 mfu:21.9775864393498 Step 3577 | loss:1.3242032527923584 lr:2.5983133106077245e-05 tokens_per_second_per_gpu:3159.1292481941487 mfu:14.902151666761773 Step 3578 | loss:1.4414869546890259 lr:2.59722149459318e-05 tokens_per_second_per_gpu:4074.245419374064 mfu:19.21891078113636 Step 3579 | loss:1.3021795749664307 lr:2.5961296600071832e-05 tokens_per_second_per_gpu:5288.800935268497 mfu:24.948176374149728 Step 3580 | loss:1.4242606163024902 lr:2.5950378070582976e-05 tokens_per_second_per_gpu:3780.4166728647197 mfu:17.832870451498145 Step 3581 | loss:1.2353593111038208 lr:2.59394593595509e-05 tokens_per_second_per_gpu:3876.287449026997 mfu:18.285109259896725 Step 3582 | loss:1.3783625364303589 lr:2.592854046906134e-05 tokens_per_second_per_gpu:4084.3674344325523 mfu:19.266658053161102 Step 3583 | loss:1.3322560787200928 lr:2.5917621401200033e-05 tokens_per_second_per_gpu:2670.0874184695276 mfu:12.595257916810613 Step 3584 | loss:1.4184900522232056 lr:2.5906702158052752e-05 tokens_per_second_per_gpu:3231.918042921576 mfu:15.245508830540041 Step 3585 | loss:1.4096428155899048 lr:2.5895782741705336e-05 tokens_per_second_per_gpu:3001.0064077460042 mfu:14.156259249829358 Step 3586 | loss:1.1937518119812012 lr:2.588486315424363e-05 tokens_per_second_per_gpu:3652.5904741546074 mfu:17.22989246278413 Step 3587 | loss:1.345454216003418 lr:2.5873943397753503e-05 tokens_per_second_per_gpu:4734.75515253336 mfu:22.334647887029934 Step 3588 | loss:1.1830124855041504 lr:2.5863023474320886e-05 tokens_per_second_per_gpu:4486.851348680843 mfu:21.16524334750717 Step 3589 | loss:1.2364377975463867 lr:2.5852103386031716e-05 tokens_per_second_per_gpu:4552.679114830721 mfu:21.47576415181119 Step 3590 | loss:1.463719367980957 lr:2.5841183134971962e-05 tokens_per_second_per_gpu:3401.4183962926327 mfu:16.04507091713371 Step 3591 | loss:1.256857991218567 lr:2.5830262723227656e-05 tokens_per_second_per_gpu:5266.971010655525 mfu:24.845200895181137 Step 3592 | loss:1.2982274293899536 lr:2.581934215288483e-05 tokens_per_second_per_gpu:4517.7900855853595 mfu:21.311186648178612 Step 3593 | loss:1.458380937576294 lr:2.580842142602953e-05 tokens_per_second_per_gpu:5351.91150679921 mfu:25.245879707833943 Step 3594 | loss:1.3290091753005981 lr:2.5797500544747893e-05 tokens_per_second_per_gpu:4647.123943683582 mfu:21.92127652345956 Step 3595 | loss:1.4013997316360474 lr:2.5786579511126034e-05 tokens_per_second_per_gpu:5319.574543746894 mfu:25.09334073586135 Step 3596 | loss:1.2917752265930176 lr:2.5775658327250095e-05 tokens_per_second_per_gpu:4403.285157972135 mfu:20.771047368071834 Step 3597 | loss:1.232527494430542 lr:2.576473699520629e-05 tokens_per_second_per_gpu:5237.583719716281 mfu:24.70657602983186 Step 3598 | loss:1.514450192451477 lr:2.5753815517080826e-05 tokens_per_second_per_gpu:3718.8743312352403 mfu:17.54256472582566 Step 3599 | loss:1.2105183601379395 lr:2.574289389495993e-05 tokens_per_second_per_gpu:5339.768208581845 mfu:25.188597698282315 Step 3600 | loss:1.4540164470672607 lr:2.5731972130929895e-05 tokens_per_second_per_gpu:4274.358981034581 mfu:20.162880594383342 Step 3601 | loss:1.2654775381088257 lr:2.572105022707701e-05 tokens_per_second_per_gpu:3600.058746026038 mfu:16.98209133836463 Step 3602 | loss:1.41458261013031 lr:2.5710128185487598e-05 tokens_per_second_per_gpu:4378.788247429269 mfu:20.655491261437213 Step 3603 | loss:1.2822614908218384 lr:2.569920600824801e-05 tokens_per_second_per_gpu:4802.688409317091 mfu:22.655100649887583 Step 3604 | loss:1.2308473587036133 lr:2.5688283697444638e-05 tokens_per_second_per_gpu:5312.898785029606 mfu:25.061850042990017 Step 3605 | loss:1.4301857948303223 lr:2.5677361255163863e-05 tokens_per_second_per_gpu:4406.909413265508 mfu:20.788143598652393 Step 3606 | loss:1.3045257329940796 lr:2.566643868349212e-05 tokens_per_second_per_gpu:5151.068396171752 mfu:24.29846848763601 Step 3607 | loss:1.145459532737732 lr:2.5655515984515878e-05 tokens_per_second_per_gpu:5334.9671719141725 mfu:25.165950389179578 Step 3608 | loss:1.4232032299041748 lr:2.5644593160321588e-05 tokens_per_second_per_gpu:5321.113732296655 mfu:25.10060135086322 Step 3609 | loss:1.3049894571304321 lr:2.5633670212995765e-05 tokens_per_second_per_gpu:5267.528637767619 mfu:24.84783131740988 Step 3610 | loss:1.2415995597839355 lr:2.5622747144624936e-05 tokens_per_second_per_gpu:4091.028830443042 mfu:19.298080994693937 Step 3611 | loss:1.2439639568328857 lr:2.5611823957295638e-05 tokens_per_second_per_gpu:5196.545658204049 mfu:24.512992491863365 Step 3612 | loss:1.3880001306533813 lr:2.5600900653094445e-05 tokens_per_second_per_gpu:4459.738710735837 mfu:21.03734840842754 Step 3613 | loss:1.1490521430969238 lr:2.5589977234107958e-05 tokens_per_second_per_gpu:5298.512529966655 mfu:24.993987623309856 Step 3614 | loss:1.2488164901733398 lr:2.5579053702422778e-05 tokens_per_second_per_gpu:5219.263825358497 mfu:24.620157962449905 Step 3615 | loss:1.2899502515792847 lr:2.5568130060125552e-05 tokens_per_second_per_gpu:4014.5734455022684 mfu:18.937427899294516 Step 3616 | loss:1.1568151712417603 lr:2.5557206309302933e-05 tokens_per_second_per_gpu:5358.671220699498 mfu:25.27776643162772 Step 3617 | loss:1.1075299978256226 lr:2.5546282452041586e-05 tokens_per_second_per_gpu:4628.75649539888 mfu:21.834634136090795 Step 3618 | loss:1.3685146570205688 lr:2.5535358490428236e-05 tokens_per_second_per_gpu:4716.512451506162 mfu:22.24859395375889 Step 3619 | loss:1.289307713508606 lr:2.5524434426549575e-05 tokens_per_second_per_gpu:5026.172765658335 mfu:23.7093144891123 Step 3620 | loss:1.1985150575637817 lr:2.5513510262492356e-05 tokens_per_second_per_gpu:4148.343791376557 mfu:19.568445444358034 Step 3621 | loss:1.145944356918335 lr:2.5502586000343337e-05 tokens_per_second_per_gpu:5310.577465910351 mfu:25.05089998464661 Step 3622 | loss:1.321657419204712 lr:2.549166164218928e-05 tokens_per_second_per_gpu:5291.823440767688 mfu:24.96243404828203 Step 3623 | loss:1.192398190498352 lr:2.5480737190116988e-05 tokens_per_second_per_gpu:4853.667226023867 mfu:22.895576426176476 Step 3624 | loss:1.0928943157196045 lr:2.5469812646213274e-05 tokens_per_second_per_gpu:4468.211762108787 mfu:21.077317237405378 Step 3625 | loss:1.4903991222381592 lr:2.5458888012564963e-05 tokens_per_second_per_gpu:3744.2552112122685 mfu:17.662290667101967 Step 3626 | loss:1.3863211870193481 lr:2.5447963291258902e-05 tokens_per_second_per_gpu:5302.51038478563 mfu:25.01284618659533 Step 3627 | loss:1.3557934761047363 lr:2.543703848438196e-05 tokens_per_second_per_gpu:4571.870190159224 mfu:21.56629172847083 Step 3628 | loss:1.1984052658081055 lr:2.5426113594021007e-05 tokens_per_second_per_gpu:5312.452305803442 mfu:25.05974392430299 Step 3629 | loss:1.300830602645874 lr:2.5415188622262943e-05 tokens_per_second_per_gpu:4427.126582707027 mfu:20.883511436312837 Step 3630 | loss:1.1640174388885498 lr:2.5404263571194675e-05 tokens_per_second_per_gpu:4653.946758268547 mfu:21.95346090394904 Step 3631 | loss:1.2857004404067993 lr:2.539333844290314e-05 tokens_per_second_per_gpu:4229.0621555873695 mfu:19.949207740313494 Step 3632 | loss:1.4119118452072144 lr:2.538241323947527e-05 tokens_per_second_per_gpu:5367.445883224749 mfu:25.319158011871135 Step 3633 | loss:1.2990280389785767 lr:2.537148796299802e-05 tokens_per_second_per_gpu:5324.305678027583 mfu:25.115658303478106 Step 3634 | loss:1.2488813400268555 lr:2.5360562615558364e-05 tokens_per_second_per_gpu:3526.4603032503082 mfu:16.63491492660232 Step 3635 | loss:1.332275152206421 lr:2.534963719924328e-05 tokens_per_second_per_gpu:5301.721186791166 mfu:25.00912340500438 Step 3636 | loss:1.293419361114502 lr:2.533871171613977e-05 tokens_per_second_per_gpu:3740.1225469750843 mfu:17.64279618478994 Step 3637 | loss:1.3320870399475098 lr:2.532778616833484e-05 tokens_per_second_per_gpu:4701.486725562394 mfu:22.177715040828936 Step 3638 | loss:1.3402845859527588 lr:2.5316860557915502e-05 tokens_per_second_per_gpu:3516.0550296862702 mfu:16.585831475878017 Step 3639 | loss:1.475886344909668 lr:2.5305934886968803e-05 tokens_per_second_per_gpu:5345.824644429054 mfu:25.217166939508108 Step 3640 | loss:1.1734325885772705 lr:2.5295009157581778e-05 tokens_per_second_per_gpu:5355.715671296308 mfu:25.263824600824144 Step 3641 | loss:1.2464474439620972 lr:2.528408337184148e-05 tokens_per_second_per_gpu:4481.240797569871 mfu:21.138777420657984 Step 3642 | loss:1.2856953144073486 lr:2.5273157531834996e-05 tokens_per_second_per_gpu:4070.6576119497813 mfu:19.201986481372952 Step 3643 | loss:1.2785797119140625 lr:2.5262231639649376e-05 tokens_per_second_per_gpu:5327.853459112374 mfu:25.132393792168937 Step 3644 | loss:1.3588463068008423 lr:2.5251305697371723e-05 tokens_per_second_per_gpu:5317.908378556206 mfu:25.08548115037978 Step 3645 | loss:1.2374224662780762 lr:2.5240379707089134e-05 tokens_per_second_per_gpu:4768.041142180737 mfu:22.491663579372062 Step 3646 | loss:1.3899271488189697 lr:2.5229453670888703e-05 tokens_per_second_per_gpu:4148.576737834494 mfu:19.56954429254489 Step 3647 | loss:1.2229329347610474 lr:2.5218527590857556e-05 tokens_per_second_per_gpu:5350.785959615075 mfu:25.240570309728227 Step 3648 | loss:1.3148736953735352 lr:2.520760146908281e-05 tokens_per_second_per_gpu:4308.142264270121 mfu:20.322242105427872 Step 3649 | loss:1.2011216878890991 lr:2.5196675307651596e-05 tokens_per_second_per_gpu:3935.865955074278 mfu:18.566151238063078 Step 3650 | loss:1.2971941232681274 lr:2.5185749108651053e-05 tokens_per_second_per_gpu:4976.069293748078 mfu:23.472967863577814 Step 3651 | loss:1.3796648979187012 lr:2.5174822874168324e-05 tokens_per_second_per_gpu:4888.847141615243 mfu:23.061526090333537 Step 3652 | loss:1.3847490549087524 lr:2.5163896606290565e-05 tokens_per_second_per_gpu:5339.393068944997 mfu:25.18682810060988 Step 3653 | loss:1.329635739326477 lr:2.5152970307104933e-05 tokens_per_second_per_gpu:3737.850306673745 mfu:17.63207763960435 Step 3654 | loss:1.259903907775879 lr:2.5142043978698593e-05 tokens_per_second_per_gpu:3306.787560861193 mfu:15.598681120718192 Step 3655 | loss:1.2315716743469238 lr:2.5131117623158718e-05 tokens_per_second_per_gpu:4486.960026129892 mfu:21.165755997576618 Step 3656 | loss:1.184979796409607 lr:2.5120191242572478e-05 tokens_per_second_per_gpu:3393.969909446413 mfu:16.00993513383719 Step 3657 | loss:1.2034083604812622 lr:2.510926483902705e-05 tokens_per_second_per_gpu:5325.505520903964 mfu:25.1213181670403 Step 3658 | loss:1.164799690246582 lr:2.5098338414609628e-05 tokens_per_second_per_gpu:5300.984449301098 mfu:25.00564808856335 Step 3659 | loss:1.3252620697021484 lr:2.50874119714074e-05 tokens_per_second_per_gpu:5327.503410900409 mfu:25.130742555028714 Step 3660 | loss:1.4182627201080322 lr:2.5076485511507546e-05 tokens_per_second_per_gpu:5355.780454272543 mfu:25.26413019317616 Step 3661 | loss:1.4307664632797241 lr:2.5065559036997278e-05 tokens_per_second_per_gpu:4383.573488900347 mfu:20.67806406190267 Step 3662 | loss:1.470343828201294 lr:2.505463254996378e-05 tokens_per_second_per_gpu:3728.6865957996974 mfu:17.588850851921173 Step 3663 | loss:1.3493350744247437 lr:2.504370605249426e-05 tokens_per_second_per_gpu:4599.645735953729 mfu:21.69731371698029 Step 3664 | loss:1.3599720001220703 lr:2.5032779546675916e-05 tokens_per_second_per_gpu:5371.028136141091 mfu:25.33605611007289 Step 3665 | loss:1.3669401407241821 lr:2.5021853034595956e-05 tokens_per_second_per_gpu:4533.806522097832 mfu:21.3867389118938 Step 3666 | loss:1.383161187171936 lr:2.501092651834158e-05 tokens_per_second_per_gpu:3572.3899917291346 mfu:16.851573103569862 Step 3667 | loss:1.2876337766647339 lr:2.5e-05 tokens_per_second_per_gpu:3472.9864154988522 mfu:16.38266947449266 Step 3668 | loss:1.192631721496582 lr:2.498907348165843e-05 tokens_per_second_per_gpu:5222.553369260059 mfu:24.63567530228764 Step 3669 | loss:1.1848856210708618 lr:2.4978146965404046e-05 tokens_per_second_per_gpu:4682.676172564765 mfu:22.088982452927834 Step 3670 | loss:1.281066656112671 lr:2.496722045332409e-05 tokens_per_second_per_gpu:5331.840898114782 mfu:25.151203222270546 Step 3671 | loss:1.2423044443130493 lr:2.4956293947505754e-05 tokens_per_second_per_gpu:4495.476731658455 mfu:21.20593075065465 Step 3672 | loss:1.1353962421417236 lr:2.494536745003622e-05 tokens_per_second_per_gpu:5294.505545456181 mfu:24.975085993711893 Step 3673 | loss:1.2485228776931763 lr:2.493444096300273e-05 tokens_per_second_per_gpu:4877.94151184169 mfu:23.010082373999378 Step 3674 | loss:1.220925211906433 lr:2.4923514488492464e-05 tokens_per_second_per_gpu:4997.579932596321 mfu:23.574437217118412 Step 3675 | loss:1.1994783878326416 lr:2.49125880285926e-05 tokens_per_second_per_gpu:5340.1579511728105 mfu:25.190436180580843 Step 3676 | loss:1.2985659837722778 lr:2.4901661585390378e-05 tokens_per_second_per_gpu:4332.430225840584 mfu:20.4368125641093 Step 3677 | loss:1.333814024925232 lr:2.4890735160972958e-05 tokens_per_second_per_gpu:5333.626527416909 mfu:25.15962634034845 Step 3678 | loss:1.321459412574768 lr:2.487980875742753e-05 tokens_per_second_per_gpu:4425.19085643105 mfu:20.874380285200093 Step 3679 | loss:1.4176692962646484 lr:2.4868882376841288e-05 tokens_per_second_per_gpu:3376.46660993507 mfu:15.927369083671342 Step 3680 | loss:1.3244725465774536 lr:2.4857956021301416e-05 tokens_per_second_per_gpu:4480.783110454632 mfu:21.13661843244593 Step 3681 | loss:1.3499772548675537 lr:2.4847029692895072e-05 tokens_per_second_per_gpu:4654.013142910304 mfu:21.953774051630596 Step 3682 | loss:1.2116860151290894 lr:2.483610339370944e-05 tokens_per_second_per_gpu:3451.4315345042655 mfu:16.280991423199268 Step 3683 | loss:1.3795000314712524 lr:2.4825177125831685e-05 tokens_per_second_per_gpu:4433.292645325881 mfu:20.912597805724733 Step 3684 | loss:1.421618938446045 lr:2.4814250891348953e-05 tokens_per_second_per_gpu:4591.103562703687 mfu:21.657018828314804 Step 3685 | loss:1.3296793699264526 lr:2.4803324692348413e-05 tokens_per_second_per_gpu:3390.1814675985042 mfu:15.992064407265772 Step 3686 | loss:1.3310563564300537 lr:2.4792398530917203e-05 tokens_per_second_per_gpu:5174.5214434301915 mfu:24.409100513056554 Step 3687 | loss:1.2392505407333374 lr:2.478147240914245e-05 tokens_per_second_per_gpu:5317.882645174252 mfu:25.08535976162653 Step 3688 | loss:1.2921262979507446 lr:2.4770546329111303e-05 tokens_per_second_per_gpu:5320.221573954528 mfu:25.096392887745495 Step 3689 | loss:1.2810500860214233 lr:2.475962029291088e-05 tokens_per_second_per_gpu:5365.151203475288 mfu:25.308333615980185 Step 3690 | loss:1.3150309324264526 lr:2.474869430262828e-05 tokens_per_second_per_gpu:4370.06494827715 mfu:20.614341970988356 Step 3691 | loss:1.2868536710739136 lr:2.4737768360350626e-05 tokens_per_second_per_gpu:5345.459301860183 mfu:25.21544355627687 Step 3692 | loss:1.2029609680175781 lr:2.4726842468165017e-05 tokens_per_second_per_gpu:4934.027876803305 mfu:23.274651326843934 Step 3693 | loss:1.3028279542922974 lr:2.471591662815852e-05 tokens_per_second_per_gpu:5316.044317490236 mfu:25.076688056289985 Step 3694 | loss:1.3256971836090088 lr:2.470499084241823e-05 tokens_per_second_per_gpu:4769.061856511036 mfu:22.49647846301991 Step 3695 | loss:1.2543625831604004 lr:2.4694065113031213e-05 tokens_per_second_per_gpu:5310.23489670312 mfu:25.049284027247765 Step 3696 | loss:1.157773494720459 lr:2.4683139442084504e-05 tokens_per_second_per_gpu:4373.05904559834 mfu:20.628465638898092 Step 3697 | loss:1.452166199684143 lr:2.467221383166517e-05 tokens_per_second_per_gpu:3904.173181514488 mfu:18.416651017836788 Step 3698 | loss:1.3268120288848877 lr:2.466128828386024e-05 tokens_per_second_per_gpu:5026.1070328092255 mfu:23.709004416047875 Step 3699 | loss:1.3348592519760132 lr:2.4650362800756725e-05 tokens_per_second_per_gpu:3909.6316164053787 mfu:18.442399386522148 Step 3700 | loss:1.221513271331787 lr:2.4639437384441642e-05 tokens_per_second_per_gpu:5310.683318256047 mfu:25.05139930822153 Step 3701 | loss:1.4300123453140259 lr:2.4628512037001976e-05 tokens_per_second_per_gpu:4671.8379227655905 mfu:22.037856579429032 Step 3702 | loss:1.2090519666671753 lr:2.4617586760524735e-05 tokens_per_second_per_gpu:5359.256528493972 mfu:25.280527428358063 Step 3703 | loss:1.2994476556777954 lr:2.4606661557096865e-05 tokens_per_second_per_gpu:4263.583232251717 mfu:20.112049548842243 Step 3704 | loss:1.1538876295089722 lr:2.459573642880532e-05 tokens_per_second_per_gpu:4168.123464166861 mfu:19.661749535670072 Step 3705 | loss:1.2346192598342896 lr:2.4584811377737062e-05 tokens_per_second_per_gpu:4912.013522119614 mfu:23.170805859764744 Step 3706 | loss:1.250723123550415 lr:2.4573886405979002e-05 tokens_per_second_per_gpu:4322.730255011487 mfu:20.39105614672277 Step 3707 | loss:1.2977885007858276 lr:2.4562961515618044e-05 tokens_per_second_per_gpu:5023.674016681349 mfu:23.697527463857323 Step 3708 | loss:1.41008460521698 lr:2.4552036708741103e-05 tokens_per_second_per_gpu:4904.784191294024 mfu:23.136703872809406 Step 3709 | loss:1.3369998931884766 lr:2.4541111987435043e-05 tokens_per_second_per_gpu:5299.382963391976 mfu:24.998093606288354 Step 3710 | loss:1.2029316425323486 lr:2.4530187353786728e-05 tokens_per_second_per_gpu:3922.0198533446273 mfu:18.500836813815756 Step 3711 | loss:1.162106990814209 lr:2.4519262809883014e-05 tokens_per_second_per_gpu:5315.418230484827 mfu:25.073734697064015 Step 3712 | loss:1.3451762199401855 lr:2.4508338357810726e-05 tokens_per_second_per_gpu:4401.572862756315 mfu:20.76297017939112 Step 3713 | loss:1.2197942733764648 lr:2.4497413999656666e-05 tokens_per_second_per_gpu:5273.894687632335 mfu:24.877861060781854 Step 3714 | loss:1.1393519639968872 lr:2.4486489737507647e-05 tokens_per_second_per_gpu:4370.25186914325 mfu:20.615223708605736 Step 3715 | loss:1.208823800086975 lr:2.447556557345043e-05 tokens_per_second_per_gpu:4248.537255287991 mfu:20.04107510839597 Step 3716 | loss:1.336018443107605 lr:2.4464641509571767e-05 tokens_per_second_per_gpu:5300.314552028431 mfu:25.00248806883192 Step 3717 | loss:1.3766025304794312 lr:2.4453717547958416e-05 tokens_per_second_per_gpu:3021.393212215887 mfu:14.252427284861312 Step 3718 | loss:1.384384036064148 lr:2.4442793690697076e-05 tokens_per_second_per_gpu:5327.994591137181 mfu:25.133059536009558 Step 3719 | loss:1.338714361190796 lr:2.443186993987445e-05 tokens_per_second_per_gpu:4451.564613191415 mfu:20.998789795665648 Step 3720 | loss:1.2262221574783325 lr:2.4420946297577227e-05 tokens_per_second_per_gpu:4964.619223942261 mfu:23.418955930720422 Step 3721 | loss:1.3758113384246826 lr:2.4410022765892048e-05 tokens_per_second_per_gpu:4903.634697084541 mfu:23.131281512499342 Step 3722 | loss:1.33843195438385 lr:2.4399099346905554e-05 tokens_per_second_per_gpu:5322.051811787703 mfu:25.105026431875356 Step 3723 | loss:1.3676048517227173 lr:2.4388176042704368e-05 tokens_per_second_per_gpu:4825.236300228886 mfu:22.761462898385407 Step 3724 | loss:1.3111588954925537 lr:2.4377252855375073e-05 tokens_per_second_per_gpu:4188.830312375946 mfu:19.759427271624933 Step 3725 | loss:1.409453272819519 lr:2.4366329787004234e-05 tokens_per_second_per_gpu:4145.392710880218 mfu:19.55452469415055 Step 3726 | loss:1.2525410652160645 lr:2.4355406839678418e-05 tokens_per_second_per_gpu:5327.186594293908 mfu:25.12924807704136 Step 3727 | loss:1.2552558183670044 lr:2.434448401548413e-05 tokens_per_second_per_gpu:4957.887786298246 mfu:23.38720259085191 Step 3728 | loss:1.395694613456726 lr:2.4333561316507874e-05 tokens_per_second_per_gpu:5080.802943610939 mfu:23.967014359384233 Step 3729 | loss:1.1397595405578613 lr:2.4322638744836142e-05 tokens_per_second_per_gpu:4442.568102872026 mfu:20.956351721526147 Step 3730 | loss:1.2974179983139038 lr:2.431171630255537e-05 tokens_per_second_per_gpu:4433.775791152575 mfu:20.91487688702243 Step 3731 | loss:1.2793084383010864 lr:2.4300793991751986e-05 tokens_per_second_per_gpu:4623.310347752861 mfu:21.808943728435914 Step 3732 | loss:1.385022521018982 lr:2.428987181451241e-05 tokens_per_second_per_gpu:5278.714801191638 mfu:24.90059835883726 Step 3733 | loss:1.2504364252090454 lr:2.4278949772923e-05 tokens_per_second_per_gpu:4015.1131459283497 mfu:18.93997375828673 Step 3734 | loss:1.2226030826568604 lr:2.4268027869070108e-05 tokens_per_second_per_gpu:5371.176799389774 mfu:25.336757379981492 Step 3735 | loss:1.2775990962982178 lr:2.4257106105040076e-05 tokens_per_second_per_gpu:5315.109671208315 mfu:25.072279170311067 Step 3736 | loss:1.3202600479125977 lr:2.4246184482919187e-05 tokens_per_second_per_gpu:5029.615574926393 mfu:23.72555480783356 Step 3737 | loss:1.347923755645752 lr:2.4235263004793712e-05 tokens_per_second_per_gpu:5325.227312883892 mfu:25.120005812342438 Step 3738 | loss:1.2191972732543945 lr:2.4224341672749908e-05 tokens_per_second_per_gpu:5343.06685383142 mfu:25.204157970731472 Step 3739 | loss:1.4513827562332153 lr:2.421342048887398e-05 tokens_per_second_per_gpu:3211.5330096929083 mfu:15.1493491507551 Step 3740 | loss:1.37189519405365 lr:2.4202499455252106e-05 tokens_per_second_per_gpu:5306.475869607575 mfu:25.03155205508192 Step 3741 | loss:1.2818130254745483 lr:2.419157857397047e-05 tokens_per_second_per_gpu:4032.8296909274404 mfu:19.023545723801714 Step 3742 | loss:1.2520877122879028 lr:2.4180657847115183e-05 tokens_per_second_per_gpu:4870.927074434566 mfu:22.976994075963542 Step 3743 | loss:1.1676219701766968 lr:2.4169737276772343e-05 tokens_per_second_per_gpu:5025.70509550869 mfu:23.70710840922367 Step 3744 | loss:1.3320499658584595 lr:2.415881686502804e-05 tokens_per_second_per_gpu:4757.31852956417 mfu:22.44108318619335 Step 3745 | loss:1.3216438293457031 lr:2.4147896613968297e-05 tokens_per_second_per_gpu:4240.767685795341 mfu:20.00442472347389 Step 3746 | loss:1.285631775856018 lr:2.4136976525679117e-05 tokens_per_second_per_gpu:3892.662227525301 mfu:18.362351883898526 Step 3747 | loss:1.2000324726104736 lr:2.4126056602246503e-05 tokens_per_second_per_gpu:4356.411483304812 mfu:20.5499362471925 Step 3748 | loss:1.336215853691101 lr:2.4115136845756378e-05 tokens_per_second_per_gpu:4335.86181371494 mfu:20.4529999496019 Step 3749 | loss:1.3053933382034302 lr:2.4104217258294663e-05 tokens_per_second_per_gpu:3872.340387882282 mfu:18.26649029903903 Step 3750 | loss:1.3124421834945679 lr:2.409329784194725e-05 tokens_per_second_per_gpu:4112.635447569189 mfu:19.40000309414699 Step 3751 | loss:1.3825860023498535 lr:2.4082378598799982e-05 tokens_per_second_per_gpu:3753.7346954975565 mfu:17.707007011842464 Step 3752 | loss:1.3432652950286865 lr:2.407145953093867e-05 tokens_per_second_per_gpu:4128.205750747118 mfu:19.473450870804943 Step 3753 | loss:1.2633789777755737 lr:2.4060540640449107e-05 tokens_per_second_per_gpu:4590.008789670448 mfu:21.65185459712947 Step 3754 | loss:1.2827576398849487 lr:2.4049621929417037e-05 tokens_per_second_per_gpu:4092.9066398390964 mfu:19.306938942002446 Step 3755 | loss:1.287858247756958 lr:2.403870339992817e-05 tokens_per_second_per_gpu:4418.610021291523 mfu:20.84333736304069 Step 3756 | loss:1.2000865936279297 lr:2.4027785054068203e-05 tokens_per_second_per_gpu:5359.174773877081 mfu:25.28014177788141 Step 3757 | loss:1.2810369729995728 lr:2.4016866893922767e-05 tokens_per_second_per_gpu:4801.043764212953 mfu:22.647342578325972 Step 3758 | loss:1.1902315616607666 lr:2.400594892157747e-05 tokens_per_second_per_gpu:5331.62083730074 mfu:25.15016515786446 Step 3759 | loss:1.7573521137237549 lr:2.3995031139117902e-05 tokens_per_second_per_gpu:5331.645281859987 mfu:25.1502804670211 Step 3760 | loss:1.3063186407089233 lr:2.3984113548629584e-05 tokens_per_second_per_gpu:5042.253971166083 mfu:23.785172279228934 Step 3761 | loss:1.390363097190857 lr:2.397319615219802e-05 tokens_per_second_per_gpu:4775.626125315334 mfu:22.527443238949523 Step 3762 | loss:1.3764458894729614 lr:2.3962278951908683e-05 tokens_per_second_per_gpu:5315.127528306945 mfu:25.07236340529204 Step 3763 | loss:1.2169235944747925 lr:2.3951361949846995e-05 tokens_per_second_per_gpu:5331.7723881322 mfu:25.150880048993695 Step 3764 | loss:1.3943049907684326 lr:2.3940445148098332e-05 tokens_per_second_per_gpu:4186.150752562334 mfu:19.746787330804082 Step 3765 | loss:1.2506965398788452 lr:2.392952854874807e-05 tokens_per_second_per_gpu:4787.829406192437 mfu:22.58500819694124 Step 3766 | loss:1.2522448301315308 lr:2.39186121538815e-05 tokens_per_second_per_gpu:5312.165873951657 mfu:25.058392776387805 Step 3767 | loss:1.2333908081054688 lr:2.3907695965583897e-05 tokens_per_second_per_gpu:5320.4031006676505 mfu:25.09724918022295 Step 3768 | loss:1.3417850732803345 lr:2.3896779985940503e-05 tokens_per_second_per_gpu:5293.862365220523 mfu:24.972052002802435 Step 3769 | loss:1.2702643871307373 lr:2.38858642170365e-05 tokens_per_second_per_gpu:4642.778961094846 mfu:21.900780499258016 Step 3770 | loss:1.1557576656341553 lr:2.3874948660957053e-05 tokens_per_second_per_gpu:5325.066217647173 mfu:25.119245898625152 Step 3771 | loss:1.358406662940979 lr:2.3864033319787275e-05 tokens_per_second_per_gpu:5048.710299956411 mfu:23.815627883696195 Step 3772 | loss:1.2617946863174438 lr:2.3853118195612216e-05 tokens_per_second_per_gpu:4784.216891344757 mfu:22.56796734804614 Step 3773 | loss:1.1600738763809204 lr:2.384220329051693e-05 tokens_per_second_per_gpu:5326.885415988234 mfu:25.12782736758718 Step 3774 | loss:1.335615634918213 lr:2.38312886065864e-05 tokens_per_second_per_gpu:5337.798944093314 mfu:25.179308341698746 Step 3775 | loss:1.2345045804977417 lr:2.3820374145905557e-05 tokens_per_second_per_gpu:3716.6905196045377 mfu:17.53226331376695 Step 3776 | loss:1.4841669797897339 lr:2.380945991055932e-05 tokens_per_second_per_gpu:5329.322182814401 mfu:25.139322012461502 Step 3777 | loss:1.119110345840454 lr:2.3798545902632548e-05 tokens_per_second_per_gpu:4130.594177048296 mfu:19.484717485175143 Step 3778 | loss:1.2180454730987549 lr:2.3787632124210046e-05 tokens_per_second_per_gpu:5268.235589950326 mfu:24.851166131474187 Step 3779 | loss:1.2305583953857422 lr:2.3776718577376598e-05 tokens_per_second_per_gpu:5296.652871140216 mfu:24.985215295335028 Step 3780 | loss:1.4075546264648438 lr:2.3765805264216934e-05 tokens_per_second_per_gpu:5241.400817047394 mfu:24.724581929206686 Step 3781 | loss:1.3243069648742676 lr:2.3754892186815722e-05 tokens_per_second_per_gpu:4037.082906079526 mfu:19.043608865347434 Step 3782 | loss:1.407684087753296 lr:2.3743979347257617e-05 tokens_per_second_per_gpu:5321.023577256944 mfu:25.100176074158867 Step 3783 | loss:1.4367519617080688 lr:2.3733066747627216e-05 tokens_per_second_per_gpu:3205.938243132977 mfu:15.122957682326298 Step 3784 | loss:1.1306451559066772 lr:2.372215439000904e-05 tokens_per_second_per_gpu:5313.499614775352 mfu:25.064684259412825 Step 3785 | loss:1.2221180200576782 lr:2.371124227648762e-05 tokens_per_second_per_gpu:3953.853686836852 mfu:18.651002437810646 Step 3786 | loss:1.3868190050125122 lr:2.3700330409147403e-05 tokens_per_second_per_gpu:4592.73017006785 mfu:21.66469181277939 Step 3787 | loss:1.3693758249282837 lr:2.368941879007278e-05 tokens_per_second_per_gpu:3390.2383278936472 mfu:15.992332626979328 Step 3788 | loss:1.2796357870101929 lr:2.367850742134813e-05 tokens_per_second_per_gpu:5139.296508074312 mfu:24.242938482989167 Step 3789 | loss:1.2491127252578735 lr:2.3667596305057767e-05 tokens_per_second_per_gpu:4504.848106724982 mfu:21.250137125764923 Step 3790 | loss:1.3021154403686523 lr:2.3656685443285937e-05 tokens_per_second_per_gpu:5120.864589680812 mfu:24.155991979117466 Step 3791 | loss:1.3027037382125854 lr:2.3645774838116867e-05 tokens_per_second_per_gpu:4706.08019964722 mfu:22.199383241814555 Step 3792 | loss:1.377576470375061 lr:2.3634864491634736e-05 tokens_per_second_per_gpu:4418.813438236985 mfu:20.844296915478946 Step 3793 | loss:1.179923415184021 lr:2.3623954405923634e-05 tokens_per_second_per_gpu:4413.412196317592 mfu:20.81881833579827 Step 3794 | loss:1.4447767734527588 lr:2.3613044583067648e-05 tokens_per_second_per_gpu:5326.967762721449 mfu:25.128215811177554 Step 3795 | loss:1.3134450912475586 lr:2.3602135025150795e-05 tokens_per_second_per_gpu:3515.2949216614998 mfu:16.582245916637373 Step 3796 | loss:1.0615818500518799 lr:2.3591225734257026e-05 tokens_per_second_per_gpu:5308.623210280374 mfu:25.041681427409614 Step 3797 | loss:1.1989580392837524 lr:2.3580316712470273e-05 tokens_per_second_per_gpu:4977.121348888647 mfu:23.477930587174995 Step 3798 | loss:1.1549129486083984 lr:2.3569407961874404e-05 tokens_per_second_per_gpu:5247.540554689465 mfu:24.753544119211597 Step 3799 | loss:1.3572633266448975 lr:2.3558499484553206e-05 tokens_per_second_per_gpu:4044.0956097103312 mfu:19.07668898486456 Step 3800 | loss:1.4267412424087524 lr:2.3547591282590462e-05 tokens_per_second_per_gpu:4413.1906328569285 mfu:20.817773183151694 Step 3801 | loss:1.3142849206924438 lr:2.3536683358069878e-05 tokens_per_second_per_gpu:5254.201915561168 mfu:24.784966894988777 Step 3802 | loss:1.1205947399139404 lr:2.352577571307509e-05 tokens_per_second_per_gpu:3538.9602319511023 mfu:16.69387922299172 Step 3803 | loss:1.309576153755188 lr:2.3514868349689722e-05 tokens_per_second_per_gpu:3349.784449401508 mfu:15.801504779988509 Step 3804 | loss:1.298921823501587 lr:2.3503961269997316e-05 tokens_per_second_per_gpu:4120.177464631508 mfu:19.43558007543075 Step 3805 | loss:1.234621286392212 lr:2.3493054476081347e-05 tokens_per_second_per_gpu:5274.454648109581 mfu:24.880502489892134 Step 3806 | loss:1.4791613817214966 lr:2.3482147970025274e-05 tokens_per_second_per_gpu:4277.628379226094 mfu:20.178302903469557 Step 3807 | loss:1.1812688112258911 lr:2.347124175391248e-05 tokens_per_second_per_gpu:5311.105038135106 mfu:25.05338863284388 Step 3808 | loss:1.405564546585083 lr:2.346033582982628e-05 tokens_per_second_per_gpu:3236.3973995970546 mfu:15.266638720235328 Step 3809 | loss:1.1104816198349 lr:2.3449430199849955e-05 tokens_per_second_per_gpu:5150.689718311181 mfu:24.296682199558596 Step 3810 | loss:1.2057268619537354 lr:2.343852486606673e-05 tokens_per_second_per_gpu:5345.1998583291515 mfu:25.214219716875366 Step 3811 | loss:1.3936543464660645 lr:2.342761983055974e-05 tokens_per_second_per_gpu:5279.627269576853 mfu:24.90490262789348 Step 3812 | loss:1.1677987575531006 lr:2.341671509541211e-05 tokens_per_second_per_gpu:4476.144744944188 mfu:21.114738470946403 Step 3813 | loss:1.3578228950500488 lr:2.3405810662706885e-05 tokens_per_second_per_gpu:4453.698127439792 mfu:21.008853946390307 Step 3814 | loss:1.3593025207519531 lr:2.339490653452703e-05 tokens_per_second_per_gpu:5196.414474878838 mfu:24.512373677736157 Step 3815 | loss:1.0196319818496704 lr:2.3384002712955496e-05 tokens_per_second_per_gpu:5199.762823616845 mfu:24.52816841002054 Step 3816 | loss:1.2490406036376953 lr:2.3373099200075154e-05 tokens_per_second_per_gpu:4703.3891960961555 mfu:22.18668931893163 Step 3817 | loss:1.2960251569747925 lr:2.3362195997968802e-05 tokens_per_second_per_gpu:4949.136284386837 mfu:23.3459202631756 Step 3818 | loss:1.3137692213058472 lr:2.33512931087192e-05 tokens_per_second_per_gpu:5316.4891899232625 mfu:25.078786595459636 Step 3819 | loss:1.3228645324707031 lr:2.334039053440905e-05 tokens_per_second_per_gpu:3630.7936401223174 mfu:17.127073077730447 Step 3820 | loss:1.1938749551773071 lr:2.3329488277120965e-05 tokens_per_second_per_gpu:4900.606594391934 mfu:23.116997435450717 Step 3821 | loss:1.2637510299682617 lr:2.3318586338937533e-05 tokens_per_second_per_gpu:3780.95322866322 mfu:17.835401476745528 Step 3822 | loss:1.428789496421814 lr:2.3307684721941265e-05 tokens_per_second_per_gpu:4707.006437132685 mfu:22.203752462065903 Step 3823 | loss:1.3277077674865723 lr:2.329678342821459e-05 tokens_per_second_per_gpu:4239.440056856872 mfu:19.998162071254274 Step 3824 | loss:1.3785090446472168 lr:2.328588245983992e-05 tokens_per_second_per_gpu:4422.8917699013755 mfu:20.86353510177501 Step 3825 | loss:1.3803622722625732 lr:2.3274981818899576e-05 tokens_per_second_per_gpu:4514.052196205365 mfu:21.29355438622349 Step 3826 | loss:1.2406024932861328 lr:2.3264081507475807e-05 tokens_per_second_per_gpu:4314.192634197 mfu:20.350782732672517 Step 3827 | loss:1.2673170566558838 lr:2.325318152765083e-05 tokens_per_second_per_gpu:4494.3375288663265 mfu:21.20055693671614 Step 3828 | loss:1.3337886333465576 lr:2.324228188150678e-05 tokens_per_second_per_gpu:3402.628019772686 mfu:16.050776917472167 Step 3829 | loss:1.374462366104126 lr:2.3231382571125714e-05 tokens_per_second_per_gpu:5311.723200224359 mfu:25.056304608888215 Step 3830 | loss:1.3702424764633179 lr:2.322048359858966e-05 tokens_per_second_per_gpu:4796.693524073806 mfu:22.626821753362115 Step 3831 | loss:1.1244139671325684 lr:2.320958496598056e-05 tokens_per_second_per_gpu:4639.421019673926 mfu:21.884940516651653 Step 3832 | loss:1.4398189783096313 lr:2.3198686675380278e-05 tokens_per_second_per_gpu:4543.437193009488 mfu:21.432168429745975 Step 3833 | loss:1.32148277759552 lr:2.3187788728870644e-05 tokens_per_second_per_gpu:5345.153637340832 mfu:25.21400168458735 Step 3834 | loss:1.202082633972168 lr:2.3176891128533398e-05 tokens_per_second_per_gpu:4320.304674696295 mfu:20.37961427052933 Step 3835 | loss:1.0533405542373657 lr:2.3165993876450238e-05 tokens_per_second_per_gpu:5323.732911643349 mfu:25.112956466719652 Step 3836 | loss:1.3038779497146606 lr:2.3155096974702758e-05 tokens_per_second_per_gpu:5189.504125632822 mfu:24.479776381315546 Step 3837 | loss:1.213594913482666 lr:2.3144200425372514e-05 tokens_per_second_per_gpu:5000.942153831006 mfu:23.590297388336516 Step 3838 | loss:1.3621995449066162 lr:2.3133304230541005e-05 tokens_per_second_per_gpu:5221.2203898101025 mfu:24.629387410792447 Step 3839 | loss:1.0313564538955688 lr:2.312240839228962e-05 tokens_per_second_per_gpu:4772.387744565779 mfu:22.512167244429143 Step 3840 | loss:1.22639799118042 lr:2.3111512912699715e-05 tokens_per_second_per_gpu:4346.078270725722 mfu:20.50119272042907 Step 3841 | loss:1.357271432876587 lr:2.3100617793852577e-05 tokens_per_second_per_gpu:5239.694787389856 mfu:24.716534296233405 Step 3842 | loss:1.2404600381851196 lr:2.30897230378294e-05 tokens_per_second_per_gpu:4666.058243790792 mfu:22.01059284758999 Step 3843 | loss:1.3287479877471924 lr:2.3078828646711322e-05 tokens_per_second_per_gpu:4286.1129071766245 mfu:20.218325869421953 Step 3844 | loss:1.4106148481369019 lr:2.306793462257943e-05 tokens_per_second_per_gpu:4215.262739006765 mfu:19.884113537879532 Step 3845 | loss:1.289435863494873 lr:2.305704096751471e-05 tokens_per_second_per_gpu:4391.771868589525 mfu:20.716737217684337 Step 3846 | loss:1.0975455045700073 lr:2.3046147683598084e-05 tokens_per_second_per_gpu:5343.412821874556 mfu:25.205789961019182 Step 3847 | loss:1.38169264793396 lr:2.303525477291043e-05 tokens_per_second_per_gpu:3175.5007737138785 mfu:14.979378945908625 Step 3848 | loss:1.1420215368270874 lr:2.302436223753252e-05 tokens_per_second_per_gpu:3935.5333235333683 mfu:18.56458215833181 Step 3849 | loss:1.3839420080184937 lr:2.3013470079545064e-05 tokens_per_second_per_gpu:5339.205058686688 mfu:25.18594122414358 Step 3850 | loss:1.3311569690704346 lr:2.3002578301028725e-05 tokens_per_second_per_gpu:4531.523082791323 mfu:21.375967539090073 Step 3851 | loss:1.2676572799682617 lr:2.299168690406406e-05 tokens_per_second_per_gpu:4018.9692215807036 mfu:18.95816352505323 Step 3852 | loss:1.235442876815796 lr:2.298079589073156e-05 tokens_per_second_per_gpu:5359.470484144706 mfu:25.28153669366717 Step 3853 | loss:1.1991544961929321 lr:2.2969905263111668e-05 tokens_per_second_per_gpu:5321.555332683399 mfu:25.102684455232282 Step 3854 | loss:1.2663843631744385 lr:2.2959015023284715e-05 tokens_per_second_per_gpu:5265.689877582543 mfu:24.839157571892038 Step 3855 | loss:1.3499066829681396 lr:2.2948125173330988e-05 tokens_per_second_per_gpu:4542.009199626319 mfu:21.42543234131677 Step 3856 | loss:1.222351312637329 lr:2.2937235715330695e-05 tokens_per_second_per_gpu:4796.046729320971 mfu:22.623770712158432 Step 3857 | loss:1.1865234375 lr:2.2926346651363946e-05 tokens_per_second_per_gpu:4618.912453354703 mfu:21.788198110201645 Step 3858 | loss:1.2470356225967407 lr:2.29154579835108e-05 tokens_per_second_per_gpu:3842.0609495067138 mfu:18.123657022016562 Step 3859 | loss:1.2425557374954224 lr:2.2904569713851242e-05 tokens_per_second_per_gpu:4458.248988138985 mfu:21.030321132765298 Step 3860 | loss:1.1541904211044312 lr:2.2893681844465166e-05 tokens_per_second_per_gpu:4914.65586663254 mfu:23.183270249662677 Step 3861 | loss:1.3068734407424927 lr:2.2882794377432383e-05 tokens_per_second_per_gpu:2771.36042139045 mfu:13.072979950544651 Step 3862 | loss:1.301313877105713 lr:2.2871907314832666e-05 tokens_per_second_per_gpu:3860.1035424051943 mfu:18.20876701110248 Step 3863 | loss:1.2643755674362183 lr:2.2861020658745666e-05 tokens_per_second_per_gpu:5327.870020728975 mfu:25.132471916140144 Step 3864 | loss:1.2727446556091309 lr:2.285013441125097e-05 tokens_per_second_per_gpu:5139.363695150917 mfu:24.24325541589281 Step 3865 | loss:1.2943986654281616 lr:2.2839248574428113e-05 tokens_per_second_per_gpu:3800.49325231334 mfu:17.927575102174956 Step 3866 | loss:1.3677763938903809 lr:2.2828363150356512e-05 tokens_per_second_per_gpu:4998.6835924862025 mfu:23.579643369122778 Step 3867 | loss:1.3377838134765625 lr:2.2817478141115526e-05 tokens_per_second_per_gpu:4839.2696877011795 mfu:22.827660781435018 Step 3868 | loss:1.347713589668274 lr:2.2806593548784444e-05 tokens_per_second_per_gpu:5283.594211735408 mfu:24.923615370885507 Step 3869 | loss:1.478602647781372 lr:2.2795709375442452e-05 tokens_per_second_per_gpu:3353.646101305353 mfu:15.819720850884702 Step 3870 | loss:1.3615764379501343 lr:2.2784825623168666e-05 tokens_per_second_per_gpu:4507.836749991777 mfu:21.264235065969515 Step 3871 | loss:1.2368375062942505 lr:2.2773942294042135e-05 tokens_per_second_per_gpu:4648.365033334718 mfu:21.92713095509569 Step 3872 | loss:1.2728413343429565 lr:2.2763059390141807e-05 tokens_per_second_per_gpu:4057.096114155421 mfu:19.138014582446836 Step 3873 | loss:1.4468966722488403 lr:2.275217691354655e-05 tokens_per_second_per_gpu:5307.5549922966175 mfu:25.036642460923453 Step 3874 | loss:1.3318520784378052 lr:2.274129486633518e-05 tokens_per_second_per_gpu:5318.389989826903 mfu:25.087752992915014 Step 3875 | loss:1.3496167659759521 lr:2.2730413250586387e-05 tokens_per_second_per_gpu:3536.014543628871 mfu:16.6799839085895 Step 3876 | loss:1.3670644760131836 lr:2.2719532068378804e-05 tokens_per_second_per_gpu:4279.778471409521 mfu:20.18844525514234 Step 3877 | loss:1.2954764366149902 lr:2.2708651321790992e-05 tokens_per_second_per_gpu:5184.796162121737 mfu:24.457568114172354 Step 3878 | loss:1.2930736541748047 lr:2.2697771012901395e-05 tokens_per_second_per_gpu:3555.0446860233656 mfu:16.769752337141433 Step 3879 | loss:1.2584729194641113 lr:2.2686891143788393e-05 tokens_per_second_per_gpu:4275.617986800733 mfu:20.168819539390814 Step 3880 | loss:1.280630111694336 lr:2.26760117165303e-05 tokens_per_second_per_gpu:5308.696355489338 mfu:25.04202646584016 Step 3881 | loss:1.2586841583251953 lr:2.2665132733205314e-05 tokens_per_second_per_gpu:4041.191816745691 mfu:19.062991298012186 Step 3882 | loss:1.2692840099334717 lr:2.2654254195891556e-05 tokens_per_second_per_gpu:5176.774514108918 mfu:24.419728631861606 Step 3883 | loss:1.2639074325561523 lr:2.264337610666708e-05 tokens_per_second_per_gpu:5063.238489891332 mfu:23.884159834384025 Step 3884 | loss:1.2963333129882812 lr:2.2632498467609833e-05 tokens_per_second_per_gpu:4584.819451786759 mfu:21.62737560493977 Step 3885 | loss:1.2197265625 lr:2.262162128079768e-05 tokens_per_second_per_gpu:4589.081636613197 mfu:21.647481057969795 Step 3886 | loss:1.5004161596298218 lr:2.2610744548308422e-05 tokens_per_second_per_gpu:4229.48693630648 mfu:19.9512115034406 Step 3887 | loss:1.149157166481018 lr:2.2599868272219736e-05 tokens_per_second_per_gpu:5327.066068556765 mfu:25.128679536575447 Step 3888 | loss:1.2168523073196411 lr:2.2588992454609235e-05 tokens_per_second_per_gpu:3396.5967127801214 mfu:16.022326213341156 Step 3889 | loss:1.208025336265564 lr:2.2578117097554458e-05 tokens_per_second_per_gpu:4635.434580665596 mfu:21.86613580369273 Step 3890 | loss:1.2516919374465942 lr:2.2567242203132817e-05 tokens_per_second_per_gpu:4684.884078269779 mfu:22.09939752084594 Step 3891 | loss:1.4627422094345093 lr:2.2556367773421653e-05 tokens_per_second_per_gpu:5327.115764840564 mfu:25.128913962425187 Step 3892 | loss:1.3417476415634155 lr:2.254549381049825e-05 tokens_per_second_per_gpu:5285.476256849197 mfu:24.932493298797258 Step 3893 | loss:1.358806848526001 lr:2.2534620316439756e-05 tokens_per_second_per_gpu:5007.320980641881 mfu:23.620387402743493 Step 3894 | loss:1.3452231884002686 lr:2.2523747293323245e-05 tokens_per_second_per_gpu:4227.891250079515 mfu:19.943684379255863 Step 3895 | loss:1.5389806032180786 lr:2.251287474322572e-05 tokens_per_second_per_gpu:4659.716098124552 mfu:21.980675864400705 Step 3896 | loss:1.1926237344741821 lr:2.2502002668224066e-05 tokens_per_second_per_gpu:5320.433904479824 mfu:25.097394487060644 Step 3897 | loss:1.3453304767608643 lr:2.249113107039509e-05 tokens_per_second_per_gpu:3990.686917227648 mfu:18.82475106996116 Step 3898 | loss:1.3220763206481934 lr:2.2480259951815517e-05 tokens_per_second_per_gpu:4952.686057622793 mfu:23.362665149183368 Step 3899 | loss:1.2455883026123047 lr:2.246938931456196e-05 tokens_per_second_per_gpu:4021.7204178905235 mfu:18.971141387449144 Step 3900 | loss:1.2479734420776367 lr:2.245851916071095e-05 tokens_per_second_per_gpu:5309.988165890864 mfu:25.04812015590974 Step 3901 | loss:1.369297981262207 lr:2.2447649492338943e-05 tokens_per_second_per_gpu:4212.590173458943 mfu:19.871506590203754 Step 3902 | loss:1.1505405902862549 lr:2.2436780311522266e-05 tokens_per_second_per_gpu:4926.175384448704 mfu:23.23760978063393 Step 3903 | loss:1.1834120750427246 lr:2.2425911620337184e-05 tokens_per_second_per_gpu:5283.384693382705 mfu:24.922627037068292 Step 3904 | loss:1.2469394207000732 lr:2.241504342085986e-05 tokens_per_second_per_gpu:5324.162994686292 mfu:25.11498524181295 Step 3905 | loss:1.233100175857544 lr:2.2404175715166346e-05 tokens_per_second_per_gpu:4600.8378450307155 mfu:21.70293709889122 Step 3906 | loss:1.2723193168640137 lr:2.2393308505332626e-05 tokens_per_second_per_gpu:4261.984118730367 mfu:20.104506257525138 Step 3907 | loss:1.4979828596115112 lr:2.238244179343458e-05 tokens_per_second_per_gpu:4136.747512082111 mfu:19.513743816396865 Step 3908 | loss:1.1673601865768433 lr:2.2371575581547972e-05 tokens_per_second_per_gpu:5007.952345832097 mfu:23.62336566006776 Step 3909 | loss:1.522251009941101 lr:2.236070987174851e-05 tokens_per_second_per_gpu:3482.0467053981365 mfu:16.425408407792442 Step 3910 | loss:1.2303273677825928 lr:2.2349844666111776e-05 tokens_per_second_per_gpu:4920.762406138177 mfu:23.21207583839384 Step 3911 | loss:1.187488317489624 lr:2.233897996671325e-05 tokens_per_second_per_gpu:5325.838789763573 mfu:25.122890253112608 Step 3912 | loss:1.1660953760147095 lr:2.2328115775628356e-05 tokens_per_second_per_gpu:5301.766425939151 mfu:25.009336805784024 Step 3913 | loss:1.1318165063858032 lr:2.2317252094932382e-05 tokens_per_second_per_gpu:5307.46921814328 mfu:25.03623784960758 Step 3914 | loss:1.3871536254882812 lr:2.2306388926700524e-05 tokens_per_second_per_gpu:5228.0405619388 mfu:24.66155932636487 Step 3915 | loss:1.2871084213256836 lr:2.2295526273007895e-05 tokens_per_second_per_gpu:5195.385613221003 mfu:24.507520361754253 Step 3916 | loss:1.3824154138565063 lr:2.2284664135929505e-05 tokens_per_second_per_gpu:5193.1146079191385 mfu:24.4968076422719 Step 3917 | loss:1.2734143733978271 lr:2.227380251754025e-05 tokens_per_second_per_gpu:5317.648471269796 mfu:25.08425512336503 Step 3918 | loss:1.241455078125 lr:2.2262941419914953e-05 tokens_per_second_per_gpu:3351.877071671707 mfu:15.811376036275215 Step 3919 | loss:1.200798749923706 lr:2.225208084512832e-05 tokens_per_second_per_gpu:4612.848134719102 mfu:21.759591684518064 Step 3920 | loss:1.2296289205551147 lr:2.2241220795254946e-05 tokens_per_second_per_gpu:5325.693754191472 mfu:25.122206095573386 Step 3921 | loss:1.2719389200210571 lr:2.2230361272369363e-05 tokens_per_second_per_gpu:5316.222558269692 mfu:25.07752884845769 Step 3922 | loss:1.307947039604187 lr:2.2219502278545973e-05 tokens_per_second_per_gpu:3882.4826558835316 mfu:18.31433310765028 Step 3923 | loss:1.2577201128005981 lr:2.220864381585907e-05 tokens_per_second_per_gpu:4504.3950990054755 mfu:21.248000211060923 Step 3924 | loss:1.4004930257797241 lr:2.219778588638287e-05 tokens_per_second_per_gpu:4172.520026571654 mfu:19.682488870664375 Step 3925 | loss:1.4560978412628174 lr:2.2186928492191492e-05 tokens_per_second_per_gpu:5359.871142631229 mfu:25.28342666810749 Step 3926 | loss:1.3450629711151123 lr:2.217607163535891e-05 tokens_per_second_per_gpu:4879.000885726634 mfu:23.015079621362478 Step 3927 | loss:1.3902404308319092 lr:2.2165215317959045e-05 tokens_per_second_per_gpu:4816.454057408514 mfu:22.72003556059658 Step 3928 | loss:1.19895601272583 lr:2.2154359542065684e-05 tokens_per_second_per_gpu:3949.205824119041 mfu:18.62907767636358 Step 3929 | loss:1.2631250619888306 lr:2.2143504309752515e-05 tokens_per_second_per_gpu:4784.090496285277 mfu:22.567371120985356 Step 3930 | loss:1.226430892944336 lr:2.213264962309315e-05 tokens_per_second_per_gpu:5038.753835043864 mfu:23.768661539955623 Step 3931 | loss:1.2341458797454834 lr:2.212179548416105e-05 tokens_per_second_per_gpu:5014.721389177263 mfu:23.655296392444786 Step 3932 | loss:1.3930072784423828 lr:2.2110941895029592e-05 tokens_per_second_per_gpu:3821.5800515469064 mfu:18.027045131938632 Step 3933 | loss:1.3378567695617676 lr:2.2100088857772084e-05 tokens_per_second_per_gpu:4889.456671918947 mfu:23.064401348772698 Step 3934 | loss:1.4178519248962402 lr:2.2089236374461665e-05 tokens_per_second_per_gpu:5326.466837415142 mfu:25.12585286104104 Step 3935 | loss:1.2698755264282227 lr:2.20783844471714e-05 tokens_per_second_per_gpu:4464.546442977539 mfu:21.060027301695353 Step 3936 | loss:1.3202916383743286 lr:2.2067533077974274e-05 tokens_per_second_per_gpu:4791.091448956957 mfu:22.60039580922336 Step 3937 | loss:1.2403695583343506 lr:2.2056682268943107e-05 tokens_per_second_per_gpu:4030.2129867525036 mfu:19.01120228375277 Step 3938 | loss:1.4315227270126343 lr:2.2045832022150656e-05 tokens_per_second_per_gpu:4865.376416448897 mfu:22.950810675205233 Step 3939 | loss:1.3246736526489258 lr:2.203498233966957e-05 tokens_per_second_per_gpu:4596.819983816076 mfu:21.683984162023954 Step 3940 | loss:1.2935776710510254 lr:2.2024133223572356e-05 tokens_per_second_per_gpu:5254.665183538708 mfu:24.787152209080503 Step 3941 | loss:1.2690820693969727 lr:2.2013284675931446e-05 tokens_per_second_per_gpu:5327.391827737024 mfu:25.130216198208974 Step 3942 | loss:1.3279958963394165 lr:2.2002436698819156e-05 tokens_per_second_per_gpu:4056.116186951716 mfu:19.133392098634136 Step 3943 | loss:1.3821803331375122 lr:2.1991589294307684e-05 tokens_per_second_per_gpu:4288.305379723844 mfu:20.228668136501582 Step 3944 | loss:1.4316612482070923 lr:2.1980742464469117e-05 tokens_per_second_per_gpu:5342.514027648702 mfu:25.201550195305717 Step 3945 | loss:1.2860033512115479 lr:2.1969896211375456e-05 tokens_per_second_per_gpu:5311.06130334189 mfu:25.053182328362357 Step 3946 | loss:1.288652777671814 lr:2.1959050537098565e-05 tokens_per_second_per_gpu:4630.451076226386 mfu:21.842627762979443 Step 3947 | loss:1.1834105253219604 lr:2.19482054437102e-05 tokens_per_second_per_gpu:5181.854464658598 mfu:24.443691625333383 Step 3948 | loss:1.1279343366622925 lr:2.1937360933282035e-05 tokens_per_second_per_gpu:5096.879606008865 mfu:24.0428507188767 Step 3949 | loss:1.4015333652496338 lr:2.192651700788559e-05 tokens_per_second_per_gpu:5325.060240837118 mfu:25.119217704992373 Step 3950 | loss:1.28498375415802 lr:2.1915673669592295e-05 tokens_per_second_per_gpu:3780.128235532858 mfu:17.831509843391267 Step 3951 | loss:1.503121256828308 lr:2.1904830920473488e-05 tokens_per_second_per_gpu:4798.246735582659 mfu:22.634148517054587 Step 3952 | loss:1.3720999956130981 lr:2.1893988762600355e-05 tokens_per_second_per_gpu:4438.774434659817 mfu:20.938456341302615 Step 3953 | loss:1.4105849266052246 lr:2.1883147198043986e-05 tokens_per_second_per_gpu:5324.153299862251 mfu:25.114939509673835 Step 3954 | loss:1.1755684614181519 lr:2.1872306228875374e-05 tokens_per_second_per_gpu:4202.569565132595 mfu:19.82423767103629 Step 3955 | loss:1.175727128982544 lr:2.1861465857165374e-05 tokens_per_second_per_gpu:5347.149403162796 mfu:25.223416052482317 Step 3956 | loss:1.6133406162261963 lr:2.185062608498473e-05 tokens_per_second_per_gpu:4643.417301693476 mfu:21.903791660773887 Step 3957 | loss:1.3107894659042358 lr:2.18397869144041e-05 tokens_per_second_per_gpu:5310.769333207829 mfu:25.051805055424747 Step 3958 | loss:1.3268240690231323 lr:2.1828948347493984e-05 tokens_per_second_per_gpu:4492.115998748622 mfu:21.19007760011881 Step 3959 | loss:1.303181767463684 lr:2.1818110386324793e-05 tokens_per_second_per_gpu:4535.0901614466375 mfu:21.39279405771357 Step 3960 | loss:1.31959867477417 lr:2.1807273032966827e-05 tokens_per_second_per_gpu:3914.5743196218727 mfu:18.465714960906478 Step 3961 | loss:1.274654746055603 lr:2.1796436289490246e-05 tokens_per_second_per_gpu:4156.132654944726 mfu:19.605186842726244 Step 3962 | loss:1.3677968978881836 lr:2.178560015796511e-05 tokens_per_second_per_gpu:5312.499227130735 mfu:25.05996526020943 Step 3963 | loss:1.1858121156692505 lr:2.177476464046137e-05 tokens_per_second_per_gpu:5303.192251640076 mfu:25.016062668886235 Step 3964 | loss:1.3380701541900635 lr:2.176392973904884e-05 tokens_per_second_per_gpu:3636.375433555247 mfu:17.15340334970574 Step 3965 | loss:1.2587924003601074 lr:2.175309545579722e-05 tokens_per_second_per_gpu:4011.037131841731 mfu:18.920746504400437 Step 3966 | loss:1.221238613128662 lr:2.1742261792776116e-05 tokens_per_second_per_gpu:5325.81085130865 mfu:25.12275846265394 Step 3967 | loss:1.2965868711471558 lr:2.1731428752054977e-05 tokens_per_second_per_gpu:5291.044569057374 mfu:24.95875997753526 Step 3968 | loss:1.4459939002990723 lr:2.1720596335703168e-05 tokens_per_second_per_gpu:4391.642996119413 mfu:20.716129304254903 Step 3969 | loss:1.3703069686889648 lr:2.1709764545789916e-05 tokens_per_second_per_gpu:5352.506699339151 mfu:25.248687332595164 Step 3970 | loss:1.4289343357086182 lr:2.1698933384384324e-05 tokens_per_second_per_gpu:3718.1950953821906 mfu:17.539360654417237 Step 3971 | loss:1.404299259185791 lr:2.1688102853555394e-05 tokens_per_second_per_gpu:3808.679148214673 mfu:17.966189369799405 Step 3972 | loss:1.1369481086730957 lr:2.1677272955371995e-05 tokens_per_second_per_gpu:5323.911710900842 mfu:25.11379989332355 Step 3973 | loss:1.350786566734314 lr:2.1666443691902865e-05 tokens_per_second_per_gpu:4462.44691489239 mfu:21.050123469501273 Step 3974 | loss:1.1244831085205078 lr:2.165561506521665e-05 tokens_per_second_per_gpu:5305.999595283189 mfu:25.029305387833013 Step 3975 | loss:1.2058179378509521 lr:2.1644787077381848e-05 tokens_per_second_per_gpu:5322.324148967886 mfu:25.106311092819794 Step 3976 | loss:1.4214160442352295 lr:2.1633959730466836e-05 tokens_per_second_per_gpu:4281.149206317017 mfu:20.194911245572488 Step 3977 | loss:1.235255479812622 lr:2.162313302653989e-05 tokens_per_second_per_gpu:5324.478787802898 mfu:25.11647489182384 Step 3978 | loss:1.255748987197876 lr:2.161230696766915e-05 tokens_per_second_per_gpu:3597.4614612085525 mfu:16.96983950273807 Step 3979 | loss:1.2666511535644531 lr:2.160148155592262e-05 tokens_per_second_per_gpu:5289.746586739934 mfu:24.95263717348528 Step 3980 | loss:1.1632853746414185 lr:2.15906567933682e-05 tokens_per_second_per_gpu:4385.106543804375 mfu:20.68529574345111 Step 3981 | loss:1.342954397201538 lr:2.1579832682073668e-05 tokens_per_second_per_gpu:4051.003225610496 mfu:19.109273387626438 Step 3982 | loss:1.3779408931732178 lr:2.1569009224106643e-05 tokens_per_second_per_gpu:4119.047439779476 mfu:19.430249555401595 Step 3983 | loss:1.444709062576294 lr:2.1558186421534672e-05 tokens_per_second_per_gpu:3934.823575825254 mfu:18.56123415729719 Step 3984 | loss:1.3021481037139893 lr:2.1547364276425138e-05 tokens_per_second_per_gpu:4632.5695373109 mfu:21.852620905361828 Step 3985 | loss:1.3482136726379395 lr:2.1536542790845302e-05 tokens_per_second_per_gpu:5319.454696762612 mfu:25.09277539718849 Step 3986 | loss:1.3248260021209717 lr:2.152572196686232e-05 tokens_per_second_per_gpu:5145.198668588314 mfu:24.270779981146138 Step 3987 | loss:1.1550850868225098 lr:2.151490180654321e-05 tokens_per_second_per_gpu:4555.296770925648 mfu:21.488112082229147 Step 3988 | loss:1.4941617250442505 lr:2.150408231195484e-05 tokens_per_second_per_gpu:4015.071489127824 mfu:18.93977725605127 Step 3989 | loss:1.3110922574996948 lr:2.1493263485163994e-05 tokens_per_second_per_gpu:4042.5929410999374 mfu:19.069600640647632 Step 3990 | loss:1.29452645778656 lr:2.1482445328237308e-05 tokens_per_second_per_gpu:5028.829624790537 mfu:23.72184734694581 Step 3991 | loss:1.3234009742736816 lr:2.147162784324127e-05 tokens_per_second_per_gpu:3574.8700790769967 mfu:16.863272098736264 Step 3992 | loss:1.2092311382293701 lr:2.146081103224227e-05 tokens_per_second_per_gpu:4699.384380151239 mfu:22.167797918827404 Step 3993 | loss:1.5100502967834473 lr:2.144999489730657e-05 tokens_per_second_per_gpu:5316.313231880598 mfu:25.07795657135085 Step 3994 | loss:1.2204893827438354 lr:2.1439179440500266e-05 tokens_per_second_per_gpu:4003.260227836044 mfu:18.884061521328963 Step 3995 | loss:1.2440001964569092 lr:2.1428364663889365e-05 tokens_per_second_per_gpu:5325.081633623714 mfu:25.11931861841673 Step 3996 | loss:1.2805691957473755 lr:2.1417550569539732e-05 tokens_per_second_per_gpu:4793.840274601293 mfu:22.61336248878571 Step 3997 | loss:1.2129768133163452 lr:2.140673715951708e-05 tokens_per_second_per_gpu:3850.193779488564 mfu:18.162020968644832 Step 3998 | loss:1.2623072862625122 lr:2.1395924435887026e-05 tokens_per_second_per_gpu:4805.30650162815 mfu:22.66745063801146 Step 3999 | loss:1.3532017469406128 lr:2.1385112400715037e-05 tokens_per_second_per_gpu:3768.2385520613366 mfu:17.77542417786692 Step 4000 | loss:1.347792387008667 lr:2.137430105606644e-05 tokens_per_second_per_gpu:4046.978566868703 mfu:19.090288385663815 Step 4001 | loss:1.274384617805481 lr:2.1363490404006448e-05 tokens_per_second_per_gpu:3686.0508719949294 mfu:17.387730868329488 Step 4002 | loss:1.230697512626648 lr:2.1352680446600142e-05 tokens_per_second_per_gpu:5288.22545932816 mfu:24.945461755952838 Step 4003 | loss:1.4919847249984741 lr:2.1341871185912446e-05 tokens_per_second_per_gpu:5346.9373661821655 mfu:25.22241583786744 Step 4004 | loss:1.2328450679779053 lr:2.133106262400818e-05 tokens_per_second_per_gpu:4071.5870131027123 mfu:19.20637062518351 Step 4005 | loss:1.3190662860870361 lr:2.132025476295202e-05 tokens_per_second_per_gpu:5342.385753279443 mfu:25.200945103220057 Step 4006 | loss:1.2963613271713257 lr:2.1309447604808485e-05 tokens_per_second_per_gpu:4905.0719126705535 mfu:23.138061103632825 Step 4007 | loss:1.4049537181854248 lr:2.1298641151642006e-05 tokens_per_second_per_gpu:3357.015142932879 mfu:15.835613195059517 Step 4008 | loss:1.1711692810058594 lr:2.1287835405516853e-05 tokens_per_second_per_gpu:4119.342676467105 mfu:19.431642237229713 Step 4009 | loss:1.4629446268081665 lr:2.1277030368497142e-05 tokens_per_second_per_gpu:5171.796864512369 mfu:24.39624820944009 Step 4010 | loss:1.3536932468414307 lr:2.126622604264689e-05 tokens_per_second_per_gpu:3580.010536107247 mfu:16.88752051160036 Step 4011 | loss:1.3255611658096313 lr:2.1255422430029964e-05 tokens_per_second_per_gpu:3238.303132890593 mfu:15.275628389332578 Step 4012 | loss:1.2391743659973145 lr:2.1244619532710074e-05 tokens_per_second_per_gpu:5332.458705104763 mfu:25.154117523251024 Step 4013 | loss:1.4833749532699585 lr:2.1233817352750835e-05 tokens_per_second_per_gpu:5325.7855186324605 mfu:25.122638964098154 Step 4014 | loss:1.296661615371704 lr:2.122301589221569e-05 tokens_per_second_per_gpu:4288.838598074141 mfu:20.23118341843636 Step 4015 | loss:1.4142810106277466 lr:2.1212215153167952e-05 tokens_per_second_per_gpu:5107.223468740718 mfu:24.091644484227817 Step 4016 | loss:1.3412798643112183 lr:2.1201415137670814e-05 tokens_per_second_per_gpu:5328.883353782354 mfu:25.137251981045384 Step 4017 | loss:1.1594254970550537 lr:2.1190615847787316e-05 tokens_per_second_per_gpu:4058.440000890296 mfu:19.144353925465957 Step 4018 | loss:1.3703919649124146 lr:2.1179817285580343e-05 tokens_per_second_per_gpu:4323.968823337751 mfu:20.396898684839304 Step 4019 | loss:1.1450990438461304 lr:2.1169019453112678e-05 tokens_per_second_per_gpu:5316.5083030868955 mfu:25.078876755513534 Step 4020 | loss:1.2508021593093872 lr:2.1158222352446944e-05 tokens_per_second_per_gpu:5315.050602322585 mfu:25.072000532298887 Step 4021 | loss:1.2446035146713257 lr:2.114742598564561e-05 tokens_per_second_per_gpu:4897.033323991148 mfu:23.100141709307415 Step 4022 | loss:1.4440544843673706 lr:2.1136630354771038e-05 tokens_per_second_per_gpu:4541.328275510426 mfu:21.42222030608447 Step 4023 | loss:1.2141249179840088 lr:2.112583546188543e-05 tokens_per_second_per_gpu:5323.880660576979 mfu:25.11365342364815 Step 4024 | loss:1.294613003730774 lr:2.1115041309050832e-05 tokens_per_second_per_gpu:4141.0189539426 mfu:19.533892936435922 Step 4025 | loss:1.2198716402053833 lr:2.1104247898329187e-05 tokens_per_second_per_gpu:4022.221862114107 mfu:18.973506785406997 Step 4026 | loss:1.2630853652954102 lr:2.1093455231782273e-05 tokens_per_second_per_gpu:5341.7161346746125 mfu:25.19778639801236 Step 4027 | loss:1.192064642906189 lr:2.1082663311471707e-05 tokens_per_second_per_gpu:4687.331282425019 mfu:22.110941400382295 Step 4028 | loss:1.205877661705017 lr:2.1071872139459005e-05 tokens_per_second_per_gpu:4586.54128632033 mfu:21.63549779220989 Step 4029 | loss:1.4000881910324097 lr:2.1061081717805517e-05 tokens_per_second_per_gpu:3688.1586436347216 mfu:17.39767358677731 Step 4030 | loss:1.2330137491226196 lr:2.1050292048572436e-05 tokens_per_second_per_gpu:4138.030057372838 mfu:19.51979380135802 Step 4031 | loss:1.3785902261734009 lr:2.1039503133820844e-05 tokens_per_second_per_gpu:5246.92196997199 mfu:24.750626149557824 Step 4032 | loss:1.3249783515930176 lr:2.1028714975611667e-05 tokens_per_second_per_gpu:3934.416122650045 mfu:18.55931213115105 Step 4033 | loss:1.3109033107757568 lr:2.1017927576005655e-05 tokens_per_second_per_gpu:4084.5540066982353 mfu:19.26753814637084 Step 4034 | loss:1.2770212888717651 lr:2.1007140937063463e-05 tokens_per_second_per_gpu:4446.003899577555 mfu:20.972558960793492 Step 4035 | loss:1.1152238845825195 lr:2.099635506084557e-05 tokens_per_second_per_gpu:4435.084950686632 mfu:20.921052415910225 Step 4036 | loss:1.162366509437561 lr:2.098556994941232e-05 tokens_per_second_per_gpu:5323.788278660623 mfu:25.113217642386722 Step 4037 | loss:1.36675226688385 lr:2.0974785604823903e-05 tokens_per_second_per_gpu:4684.482183903016 mfu:22.097501716547676 Step 4038 | loss:1.4225658178329468 lr:2.0964002029140363e-05 tokens_per_second_per_gpu:5325.754007905683 mfu:25.122490322623662 Step 4039 | loss:1.1749168634414673 lr:2.0953219224421616e-05 tokens_per_second_per_gpu:3797.440715275473 mfu:17.913175764150814 Step 4040 | loss:1.268737554550171 lr:2.0942437192727405e-05 tokens_per_second_per_gpu:5135.5850500318065 mfu:24.22543090216263 Step 4041 | loss:1.2976394891738892 lr:2.0931655936117332e-05 tokens_per_second_per_gpu:4129.223489747112 mfu:19.478251719312087 Step 4042 | loss:1.2326009273529053 lr:2.0920875456650868e-05 tokens_per_second_per_gpu:5303.1205177329475 mfu:25.015724287807245 Step 4043 | loss:1.3629685640335083 lr:2.0910095756387314e-05 tokens_per_second_per_gpu:5165.0460879786 mfu:24.36440364472905 Step 4044 | loss:1.4683780670166016 lr:2.089931683738583e-05 tokens_per_second_per_gpu:4060.539240215589 mfu:19.154256395530528 Step 4045 | loss:1.3269082307815552 lr:2.0888538701705437e-05 tokens_per_second_per_gpu:3966.5988548742384 mfu:18.711123569992893 Step 4046 | loss:1.2911947965621948 lr:2.0877761351404986e-05 tokens_per_second_per_gpu:3948.3313962745688 mfu:18.62495285102843 Step 4047 | loss:1.289172649383545 lr:2.0866984788543193e-05 tokens_per_second_per_gpu:3803.1339985044237 mfu:17.94003195251606 Step 4048 | loss:1.4232689142227173 lr:2.0856209015178624e-05 tokens_per_second_per_gpu:4196.946472348992 mfu:19.797712582977475 Step 4049 | loss:1.4076169729232788 lr:2.0845434033369688e-05 tokens_per_second_per_gpu:3848.5507836925644 mfu:18.154270677151114 Step 4050 | loss:1.4748345613479614 lr:2.083465984517463e-05 tokens_per_second_per_gpu:2916.4333504862584 mfu:13.757313709083627 Step 4051 | loss:1.2822740077972412 lr:2.0823886452651585e-05 tokens_per_second_per_gpu:5323.933062236558 mfu:25.11390061121703 Step 4052 | loss:1.3593618869781494 lr:2.081311385785849e-05 tokens_per_second_per_gpu:4372.389207309505 mfu:20.625305897403457 Step 4053 | loss:1.1396384239196777 lr:2.080234206285315e-05 tokens_per_second_per_gpu:3919.699170624897 mfu:18.48988975747749 Step 4054 | loss:1.1768214702606201 lr:2.0791571069693227e-05 tokens_per_second_per_gpu:4680.043733912177 mfu:22.07656479066323 Step 4055 | loss:1.1867643594741821 lr:2.0780800880436206e-05 tokens_per_second_per_gpu:5017.557574716336 mfu:23.668675163535745 Step 4056 | loss:1.2377207279205322 lr:2.077003149713943e-05 tokens_per_second_per_gpu:4564.427758456673 mfu:21.53118450832011 Step 4057 | loss:1.301857590675354 lr:2.0759262921860108e-05 tokens_per_second_per_gpu:4231.246103395966 mfu:19.95950979474656 Step 4058 | loss:1.2701644897460938 lr:2.0748495156655253e-05 tokens_per_second_per_gpu:4769.022744391497 mfu:22.496293964478827 Step 4059 | loss:1.1042146682739258 lr:2.0737728203581756e-05 tokens_per_second_per_gpu:3947.9275852892933 mfu:18.623048005713628 Step 4060 | loss:1.2817413806915283 lr:2.072696206469635e-05 tokens_per_second_per_gpu:5258.663010662917 mfu:24.806010641725038 Step 4061 | loss:1.3512606620788574 lr:2.0716196742055593e-05 tokens_per_second_per_gpu:3521.70417713078 mfu:16.61247946821771 Step 4062 | loss:1.373236894607544 lr:2.0705432237715898e-05 tokens_per_second_per_gpu:4209.146403444782 mfu:19.855261739479204 Step 4063 | loss:1.2789825201034546 lr:2.0694668553733545e-05 tokens_per_second_per_gpu:3631.8803871582113 mfu:17.132199448916925 Step 4064 | loss:1.2147722244262695 lr:2.0683905692164615e-05 tokens_per_second_per_gpu:5341.302487471699 mfu:25.195835153580727 Step 4065 | loss:1.2498705387115479 lr:2.067314365506505e-05 tokens_per_second_per_gpu:4472.1128691361 mfu:21.095719424850707 Step 4066 | loss:1.3392404317855835 lr:2.0662382444490654e-05 tokens_per_second_per_gpu:5315.776445454319 mfu:25.075424458192884 Step 4067 | loss:1.4522013664245605 lr:2.0651622062497046e-05 tokens_per_second_per_gpu:5316.894554687614 mfu:25.08069877021544 Step 4068 | loss:1.1607179641723633 lr:2.0640862511139684e-05 tokens_per_second_per_gpu:5310.275848023792 mfu:25.04947720161439 Step 4069 | loss:1.2565721273422241 lr:2.063010379247391e-05 tokens_per_second_per_gpu:4082.5979515763124 mfu:19.25831110062331 Step 4070 | loss:1.3838725090026855 lr:2.0619345908554855e-05 tokens_per_second_per_gpu:5347.329378331642 mfu:25.224265026060692 Step 4071 | loss:1.4559364318847656 lr:2.060858886143751e-05 tokens_per_second_per_gpu:5204.820378071531 mfu:24.55202575729107 Step 4072 | loss:1.2199972867965698 lr:2.059783265317673e-05 tokens_per_second_per_gpu:3742.3458575870177 mfu:17.653283920282334 Step 4073 | loss:1.2448935508728027 lr:2.058707728582717e-05 tokens_per_second_per_gpu:5362.0616101556725 mfu:25.293759477152587 Step 4074 | loss:1.4542652368545532 lr:2.057632276144334e-05 tokens_per_second_per_gpu:4801.563426558412 mfu:22.649793914273047 Step 4075 | loss:1.22812819480896 lr:2.0565569082079607e-05 tokens_per_second_per_gpu:5143.4228642028065 mfu:24.26240320887623 Step 4076 | loss:1.3866708278656006 lr:2.0554816249790154e-05 tokens_per_second_per_gpu:5332.183002513512 mfu:25.15281698708838 Step 4077 | loss:1.18089759349823 lr:2.0544064266629e-05 tokens_per_second_per_gpu:4045.414804453073 mfu:19.08291185154391 Step 4078 | loss:1.1070009469985962 lr:2.0533313134650033e-05 tokens_per_second_per_gpu:3834.6233709994613 mfu:18.088572695216108 Step 4079 | loss:1.2181934118270874 lr:2.052256285590694e-05 tokens_per_second_per_gpu:4320.902458749994 mfu:20.382434119903106 Step 4080 | loss:1.3024768829345703 lr:2.0511813432453262e-05 tokens_per_second_per_gpu:5113.602699265937 mfu:24.12173640302424 Step 4081 | loss:1.3093432188034058 lr:2.050106486634239e-05 tokens_per_second_per_gpu:4555.442647441904 mfu:21.48880020664543 Step 4082 | loss:1.3152728080749512 lr:2.049031715962752e-05 tokens_per_second_per_gpu:4114.278075114568 mfu:19.407751648539705 Step 4083 | loss:1.1765002012252808 lr:2.0479570314361707e-05 tokens_per_second_per_gpu:4732.077745557195 mfu:22.32201810151063 Step 4084 | loss:1.1431574821472168 lr:2.0468824332597846e-05 tokens_per_second_per_gpu:5326.44064053998 mfu:25.12572928591125 Step 4085 | loss:1.209228277206421 lr:2.0458079216388647e-05 tokens_per_second_per_gpu:4910.089444206669 mfu:23.161729655967843 Step 4086 | loss:1.3545888662338257 lr:2.0447334967786662e-05 tokens_per_second_per_gpu:3863.4201945579275 mfu:18.224412225186132 Step 4087 | loss:1.2138842344284058 lr:2.0436591588844293e-05 tokens_per_second_per_gpu:5341.862660633018 mfu:25.198477585958067 Step 4088 | loss:1.1630454063415527 lr:2.0425849081613753e-05 tokens_per_second_per_gpu:5142.297956406953 mfu:24.25709682687413 Step 4089 | loss:1.2443406581878662 lr:2.041510744814709e-05 tokens_per_second_per_gpu:5285.628975447723 mfu:24.933213698482984 Step 4090 | loss:1.525776982307434 lr:2.0404366690496218e-05 tokens_per_second_per_gpu:4944.42631989574 mfu:23.323702557068284 Step 4091 | loss:1.1734557151794434 lr:2.039362681071284e-05 tokens_per_second_per_gpu:5209.771085287898 mfu:24.575379087908424 Step 4092 | loss:1.2553914785385132 lr:2.0382887810848505e-05 tokens_per_second_per_gpu:4743.965076990126 mfu:22.37809267206765 Step 4093 | loss:1.4083964824676514 lr:2.037214969295462e-05 tokens_per_second_per_gpu:5300.0699149967195 mfu:25.001334074213958 Step 4094 | loss:1.1982216835021973 lr:2.036141245908239e-05 tokens_per_second_per_gpu:4876.245465746872 mfu:23.002081835194815 Step 4095 | loss:1.2747310400009155 lr:2.0350676111282856e-05 tokens_per_second_per_gpu:4275.126896531428 mfu:20.166502982801866 Step 4096 | loss:1.3350095748901367 lr:2.0339940651606916e-05 tokens_per_second_per_gpu:5309.978232801477 mfu:25.04807329983234 Step 4097 | loss:1.206981897354126 lr:2.032920608210527e-05 tokens_per_second_per_gpu:5322.432344475757 mfu:25.106821469490484 Step 4098 | loss:1.355465054512024 lr:2.0318472404828452e-05 tokens_per_second_per_gpu:3829.4731390547513 mfu:18.06427817241273 Step 4099 | loss:1.2067149877548218 lr:2.0307739621826848e-05 tokens_per_second_per_gpu:4324.329383760142 mfu:20.398599509869676 Step 4100 | loss:1.132790207862854 lr:2.029700773515064e-05 tokens_per_second_per_gpu:5220.65830695223 mfu:24.626735970050635 Step 4101 | loss:1.416615605354309 lr:2.0286276746849868e-05 tokens_per_second_per_gpu:5328.162686513888 mfu:25.133852470581513 Step 4102 | loss:1.3684756755828857 lr:2.0275546658974386e-05 tokens_per_second_per_gpu:4743.342411245049 mfu:22.375155451510388 Step 4103 | loss:1.2626821994781494 lr:2.026481747357386e-05 tokens_per_second_per_gpu:4873.865527007339 mfu:22.990855258101018 Step 4104 | loss:1.2386783361434937 lr:2.0254089192697827e-05 tokens_per_second_per_gpu:3995.2997741736904 mfu:18.846510703210193 Step 4105 | loss:1.2719839811325073 lr:2.0243361818395617e-05 tokens_per_second_per_gpu:5356.450713844555 mfu:25.267291921935417 Step 4106 | loss:1.2737892866134644 lr:2.023263535271638e-05 tokens_per_second_per_gpu:4437.248435366871 mfu:20.93125794227546 Step 4107 | loss:1.208500862121582 lr:2.0221909797709133e-05 tokens_per_second_per_gpu:4290.741841046627 mfu:20.24016134026431 Step 4108 | loss:1.352957010269165 lr:2.0211185155422678e-05 tokens_per_second_per_gpu:3832.9555437559497 mfu:18.080705269547792 Step 4109 | loss:1.3732470273971558 lr:2.020046142790566e-05 tokens_per_second_per_gpu:5335.538393044886 mfu:25.16864493671353 Step 4110 | loss:1.4055774211883545 lr:2.0189738617206554e-05 tokens_per_second_per_gpu:3705.329886603176 mfu:17.478673269575665 Step 4111 | loss:1.3782331943511963 lr:2.0179016725373654e-05 tokens_per_second_per_gpu:4077.33444227161 mfu:19.233482229185736 Step 4112 | loss:1.3113112449645996 lr:2.0168295754455063e-05 tokens_per_second_per_gpu:4221.842928414617 mfu:19.915153414012448 Step 4113 | loss:1.3694722652435303 lr:2.015757570649874e-05 tokens_per_second_per_gpu:3712.946565158088 mfu:17.51460244185855 Step 4114 | loss:1.1802623271942139 lr:2.0146856583552454e-05 tokens_per_second_per_gpu:4905.010271814388 mfu:23.137770333197277 Step 4115 | loss:1.2314246892929077 lr:2.0136138387663774e-05 tokens_per_second_per_gpu:5286.224370704211 mfu:24.936022279492743 Step 4116 | loss:1.2839621305465698 lr:2.012542112088013e-05 tokens_per_second_per_gpu:4784.800451771814 mfu:22.57072010214624 Step 4117 | loss:1.2898311614990234 lr:2.0114704785248755e-05 tokens_per_second_per_gpu:5191.725594672366 mfu:24.490255429796775 Step 4118 | loss:1.222832202911377 lr:2.010398938281669e-05 tokens_per_second_per_gpu:3850.9952959572483 mfu:18.165801858580426 Step 4119 | loss:1.3181931972503662 lr:2.0093274915630834e-05 tokens_per_second_per_gpu:5318.575699871051 mfu:25.08862901887866 Step 4120 | loss:1.2519934177398682 lr:2.0082561385737882e-05 tokens_per_second_per_gpu:4996.96548694484 mfu:23.57153877214514 Step 4121 | loss:1.2505710124969482 lr:2.007184879518434e-05 tokens_per_second_per_gpu:4391.718516218706 mfu:20.716485545448332 Step 4122 | loss:1.3805514574050903 lr:2.006113714601657e-05 tokens_per_second_per_gpu:5332.920258005603 mfu:25.156294747033332 Step 4123 | loss:1.4835517406463623 lr:2.0050426440280728e-05 tokens_per_second_per_gpu:3613.240322441942 mfu:17.0442710833273 Step 4124 | loss:1.2212144136428833 lr:2.003971668002278e-05 tokens_per_second_per_gpu:5184.922138428887 mfu:24.458162365906954 Step 4125 | loss:1.453094720840454 lr:2.0029007867288544e-05 tokens_per_second_per_gpu:4105.708463796474 mfu:19.367327329825788 Step 4126 | loss:1.3535617589950562 lr:2.0018300004123642e-05 tokens_per_second_per_gpu:5120.497447481138 mfu:24.154260106720688 Step 4127 | loss:1.3170307874679565 lr:2.000759309257349e-05 tokens_per_second_per_gpu:4354.954382494041 mfu:20.54306285406106 Step 4128 | loss:1.338493824005127 lr:1.999688713468337e-05 tokens_per_second_per_gpu:5312.973680581486 mfu:25.062203338086736 Step 4129 | loss:1.399304747581482 lr:1.9986182132498348e-05 tokens_per_second_per_gpu:4076.523549569951 mfu:19.22965710995945 Step 4130 | loss:1.2557753324508667 lr:1.9975478088063307e-05 tokens_per_second_per_gpu:5326.652912958282 mfu:25.12673061112579 Step 4131 | loss:1.25918447971344 lr:1.9964775003422966e-05 tokens_per_second_per_gpu:3941.6310360943276 mfu:18.5933461088589 Step 4132 | loss:1.2925376892089844 lr:1.9954072880621855e-05 tokens_per_second_per_gpu:5313.769851129268 mfu:25.065959010401322 Step 4133 | loss:1.206950306892395 lr:1.9943371721704296e-05 tokens_per_second_per_gpu:3525.572669699051 mfu:16.630727807695138 Step 4134 | loss:1.108862280845642 lr:1.9932671528714463e-05 tokens_per_second_per_gpu:3859.386355570751 mfu:18.20538391843972 Step 4135 | loss:1.3938217163085938 lr:1.9921972303696335e-05 tokens_per_second_per_gpu:4723.120367711692 mfu:22.279764621927136 Step 4136 | loss:1.4189188480377197 lr:1.991127404869368e-05 tokens_per_second_per_gpu:5368.116084714762 mfu:25.322319466647688 Step 4137 | loss:1.5186129808425903 lr:1.9900576765750115e-05 tokens_per_second_per_gpu:4158.802442428067 mfu:19.617780685797882 Step 4138 | loss:1.1993119716644287 lr:1.988988045690906e-05 tokens_per_second_per_gpu:5238.474054932813 mfu:24.710775892955095 Step 4139 | loss:1.5321131944656372 lr:1.9879185124213733e-05 tokens_per_second_per_gpu:3328.3657412038065 mfu:15.700469079011503 Step 4140 | loss:1.185878038406372 lr:1.986849076970719e-05 tokens_per_second_per_gpu:5019.907708158038 mfu:23.67976114395437 Step 4141 | loss:1.3942962884902954 lr:1.9857797395432293e-05 tokens_per_second_per_gpu:4191.948727537616 mfu:19.77413736799902 Step 4142 | loss:1.4393107891082764 lr:1.9847105003431692e-05 tokens_per_second_per_gpu:5330.686799083308 mfu:25.14575914022948 Step 4143 | loss:1.2769761085510254 lr:1.9836413595747892e-05 tokens_per_second_per_gpu:4608.457525436477 mfu:21.73888043141673 Step 4144 | loss:1.258745551109314 lr:1.9825723174423185e-05 tokens_per_second_per_gpu:4566.786284674316 mfu:21.542310078894804 Step 4145 | loss:1.1463011503219604 lr:1.9815033741499658e-05 tokens_per_second_per_gpu:3762.620660283446 mfu:17.748923623839435 Step 4146 | loss:1.3628056049346924 lr:1.9804345299019252e-05 tokens_per_second_per_gpu:4053.3649780329324 mfu:19.12041417675959 Step 4147 | loss:1.2479040622711182 lr:1.979365784902369e-05 tokens_per_second_per_gpu:5311.896698900545 mfu:25.05712303174571 Step 4148 | loss:1.344679832458496 lr:1.9782971393554497e-05 tokens_per_second_per_gpu:4290.7568643980685 mfu:20.240232207976312 Step 4149 | loss:1.4463372230529785 lr:1.977228593465304e-05 tokens_per_second_per_gpu:4734.446357474988 mfu:22.333191248053723 Step 4150 | loss:1.2377490997314453 lr:1.9761601474360473e-05 tokens_per_second_per_gpu:5318.780837383168 mfu:25.089596687523386 Step 4151 | loss:1.2636206150054932 lr:1.9750918014717757e-05 tokens_per_second_per_gpu:5315.399253640027 mfu:25.07364518004931 Step 4152 | loss:1.1358715295791626 lr:1.9740235557765673e-05 tokens_per_second_per_gpu:5320.425344253858 mfu:25.097354107014237 Step 4153 | loss:1.3690789937973022 lr:1.9729554105544814e-05 tokens_per_second_per_gpu:4920.514764081258 mfu:23.21090766855927 Step 4154 | loss:1.4535133838653564 lr:1.971887366009556e-05 tokens_per_second_per_gpu:3360.3830770898026 mfu:15.851500315106547 Step 4155 | loss:1.0250869989395142 lr:1.970819422345812e-05 tokens_per_second_per_gpu:4371.465381396016 mfu:20.620948052948574 Step 4156 | loss:1.377846598625183 lr:1.9697515797672502e-05 tokens_per_second_per_gpu:5331.599650473819 mfu:25.150065215987027 Step 4157 | loss:1.4590201377868652 lr:1.9686838384778513e-05 tokens_per_second_per_gpu:5342.270748986455 mfu:25.20040260834828 Step 4158 | loss:1.3801569938659668 lr:1.967616198681579e-05 tokens_per_second_per_gpu:4275.593266940223 mfu:20.16870293159114 Step 4159 | loss:1.3175432682037354 lr:1.9665486605823753e-05 tokens_per_second_per_gpu:4615.614929270615 mfu:21.77264312648138 Step 4160 | loss:1.2757134437561035 lr:1.9654812243841625e-05 tokens_per_second_per_gpu:5028.042261920374 mfu:23.718133221949294 Step 4161 | loss:1.1641480922698975 lr:1.9644138902908463e-05 tokens_per_second_per_gpu:3437.940497841464 mfu:16.217351901452624 Step 4162 | loss:1.2324872016906738 lr:1.963346658506311e-05 tokens_per_second_per_gpu:3644.0138584404326 mfu:17.189435103138834 Step 4163 | loss:1.2909390926361084 lr:1.9622795292344193e-05 tokens_per_second_per_gpu:4610.273110313181 mfu:21.74744485505087 Step 4164 | loss:1.319779872894287 lr:1.9612125026790185e-05 tokens_per_second_per_gpu:3780.748622360081 mfu:17.834436313904185 Step 4165 | loss:1.2603470087051392 lr:1.9601455790439344e-05 tokens_per_second_per_gpu:4469.49763214265 mfu:21.083382905747158 Step 4166 | loss:1.2857067584991455 lr:1.959078758532971e-05 tokens_per_second_per_gpu:5339.969724955068 mfu:25.189548285397045 Step 4167 | loss:1.1549657583236694 lr:1.9580120413499164e-05 tokens_per_second_per_gpu:4492.7816483901515 mfu:21.193217583049442 Step 4168 | loss:1.0684093236923218 lr:1.9569454276985365e-05 tokens_per_second_per_gpu:5336.0117763830785 mfu:25.170877966687307 Step 4169 | loss:1.2511258125305176 lr:1.955878917782579e-05 tokens_per_second_per_gpu:4417.067704350588 mfu:20.836061990883895 Step 4170 | loss:1.1581196784973145 lr:1.9548125118057692e-05 tokens_per_second_per_gpu:4555.038827424869 mfu:21.486895318726273 Step 4171 | loss:1.3249965906143188 lr:1.9537462099718146e-05 tokens_per_second_per_gpu:5300.857848356222 mfu:25.005050890306027 Step 4172 | loss:1.4542306661605835 lr:1.952680012484404e-05 tokens_per_second_per_gpu:3880.1622446519514 mfu:18.30338733196794 Step 4173 | loss:1.3632150888442993 lr:1.951613919547203e-05 tokens_per_second_per_gpu:4395.962670865875 mfu:20.736505947046478 Step 4174 | loss:1.358683705329895 lr:1.9505479313638588e-05 tokens_per_second_per_gpu:5331.866689195565 mfu:25.15132488319901 Step 4175 | loss:1.310755729675293 lr:1.9494820481380005e-05 tokens_per_second_per_gpu:5319.483031815976 mfu:25.09290905846966 Step 4176 | loss:1.1047182083129883 lr:1.9484162700732344e-05 tokens_per_second_per_gpu:4342.643628711614 mfu:20.48499092803817 Step 4177 | loss:1.2118104696273804 lr:1.9473505973731454e-05 tokens_per_second_per_gpu:5321.648931401205 mfu:25.103125976353763 Step 4178 | loss:1.2688465118408203 lr:1.9462850302413045e-05 tokens_per_second_per_gpu:3834.3338872429235 mfu:18.0872071509455 Step 4179 | loss:1.2170671224594116 lr:1.9452195688812562e-05 tokens_per_second_per_gpu:5302.929189911846 mfu:25.014821761831215 Step 4180 | loss:1.2305271625518799 lr:1.9441542134965263e-05 tokens_per_second_per_gpu:4113.9844222303245 mfu:19.406366437782378 Step 4181 | loss:1.3892804384231567 lr:1.943088964290624e-05 tokens_per_second_per_gpu:5322.3167935334595 mfu:25.10627639598064 Step 4182 | loss:1.3876174688339233 lr:1.942023821467034e-05 tokens_per_second_per_gpu:5291.342083393718 mfu:24.960163403420975 Step 4183 | loss:1.2621427774429321 lr:1.9409587852292204e-05 tokens_per_second_per_gpu:4960.1321713476245 mfu:23.3977897380614 Step 4184 | loss:1.4010248184204102 lr:1.939893855780632e-05 tokens_per_second_per_gpu:4423.980907102517 mfu:20.868672747778763 Step 4185 | loss:1.2994303703308105 lr:1.9388290333246924e-05 tokens_per_second_per_gpu:5226.695646981041 mfu:24.655215133042965 Step 4186 | loss:1.3844653367996216 lr:1.9377643180648038e-05 tokens_per_second_per_gpu:5342.460026542465 mfu:25.201295462874057 Step 4187 | loss:1.2109228372573853 lr:1.9366997102043544e-05 tokens_per_second_per_gpu:3914.6623128392284 mfu:18.466130039925932 Step 4188 | loss:1.2720954418182373 lr:1.9356352099467057e-05 tokens_per_second_per_gpu:5333.759051785161 mfu:25.160251480404487 Step 4189 | loss:1.1841415166854858 lr:1.9345708174951994e-05 tokens_per_second_per_gpu:4176.66317140877 mfu:19.702032791754455 Step 4190 | loss:1.3009097576141357 lr:1.9335065330531614e-05 tokens_per_second_per_gpu:4530.13738169582 mfu:21.369430950597607 Step 4191 | loss:1.258230209350586 lr:1.9324423568238917e-05 tokens_per_second_per_gpu:3729.8709548433767 mfu:17.594437675602695 Step 4192 | loss:1.2886277437210083 lr:1.9313782890106696e-05 tokens_per_second_per_gpu:4310.802288916154 mfu:20.33478989553021 Step 4193 | loss:1.2307968139648438 lr:1.9303143298167594e-05 tokens_per_second_per_gpu:4250.579760009631 mfu:20.050709951655186 Step 4194 | loss:1.2518274784088135 lr:1.9292504794453987e-05 tokens_per_second_per_gpu:3297.4021085708723 mfu:15.554408340941466 Step 4195 | loss:1.2990292310714722 lr:1.9281867380998055e-05 tokens_per_second_per_gpu:5270.888345166775 mfu:24.86367963043689 Step 4196 | loss:1.1559600830078125 lr:1.9271231059831796e-05 tokens_per_second_per_gpu:5327.59177858317 mfu:25.13115940046538 Step 4197 | loss:1.1891945600509644 lr:1.9260595832986982e-05 tokens_per_second_per_gpu:5146.775623054155 mfu:24.27821874441769 Step 4198 | loss:1.2085436582565308 lr:1.9249961702495157e-05 tokens_per_second_per_gpu:4696.473798415555 mfu:22.154068208183734 Step 4199 | loss:1.2587217092514038 lr:1.9239328670387696e-05 tokens_per_second_per_gpu:5346.275210746014 mfu:25.219292337699745 Step 4200 | loss:1.2834748029708862 lr:1.922869673869574e-05 tokens_per_second_per_gpu:5175.766543105936 mfu:24.414973860662954 Step 4201 | loss:1.2010576725006104 lr:1.9218065909450208e-05 tokens_per_second_per_gpu:5340.418202420157 mfu:25.191663830118017 Step 4202 | loss:1.4688950777053833 lr:1.9207436184681836e-05 tokens_per_second_per_gpu:3975.2759324598596 mfu:18.752054825426367 Step 4203 | loss:1.3199201822280884 lr:1.919680756642114e-05 tokens_per_second_per_gpu:4837.027626742251 mfu:22.817084597356708 Step 4204 | loss:1.2491519451141357 lr:1.918618005669841e-05 tokens_per_second_per_gpu:5314.695349554197 mfu:25.070324744378027 Step 4205 | loss:1.2688084840774536 lr:1.9175553657543743e-05 tokens_per_second_per_gpu:4066.6220384514017 mfu:19.182949992641255 Step 4206 | loss:1.4287071228027344 lr:1.9164928370987014e-05 tokens_per_second_per_gpu:5335.142464209767 mfu:25.16677727284585 Step 4207 | loss:1.1785651445388794 lr:1.915430419905788e-05 tokens_per_second_per_gpu:5324.60944621151 mfu:25.117091229829885 Step 4208 | loss:1.2991095781326294 lr:1.9143681143785804e-05 tokens_per_second_per_gpu:3526.7378674060355 mfu:16.636224244082214 Step 4209 | loss:1.4102225303649902 lr:1.913305920720002e-05 tokens_per_second_per_gpu:4474.536598264885 mfu:21.107152568682015 Step 4210 | loss:1.1722490787506104 lr:1.9122438391329546e-05 tokens_per_second_per_gpu:5272.977279607393 mfu:24.873533490602252 Step 4211 | loss:1.3352468013763428 lr:1.9111818698203202e-05 tokens_per_second_per_gpu:3413.3824425854355 mfu:16.101507364773646 Step 4212 | loss:1.3517197370529175 lr:1.9101200129849584e-05 tokens_per_second_per_gpu:4166.546582115314 mfu:19.6543111139891 Step 4213 | loss:1.2433996200561523 lr:1.909058268829706e-05 tokens_per_second_per_gpu:4236.755509507218 mfu:19.985498603374953 Step 4214 | loss:1.1257656812667847 lr:1.907996637557381e-05 tokens_per_second_per_gpu:5020.446441249268 mfu:23.68230243986304 Step 4215 | loss:1.233896017074585 lr:1.906935119370779e-05 tokens_per_second_per_gpu:4296.7609694805815 mfu:20.268554596056486 Step 4216 | loss:1.3020864725112915 lr:1.9058737144726708e-05 tokens_per_second_per_gpu:5324.154884498179 mfu:25.114946984671878 Step 4217 | loss:1.1987861394882202 lr:1.9048124230658104e-05 tokens_per_second_per_gpu:3632.341014409708 mfu:17.134372306253347 Step 4218 | loss:1.3586061000823975 lr:1.9037512453529278e-05 tokens_per_second_per_gpu:3304.8905796925046 mfu:15.589732736887129 Step 4219 | loss:1.2922046184539795 lr:1.90269018153673e-05 tokens_per_second_per_gpu:3690.46097283514 mfu:17.408534066433553 Step 4220 | loss:1.261788249015808 lr:1.9016292318199047e-05 tokens_per_second_per_gpu:4188.178015781589 mfu:19.756350277296082 Step 4221 | loss:1.1603574752807617 lr:1.9005683964051172e-05 tokens_per_second_per_gpu:5244.812638559206 mfu:24.740676073394674 Step 4222 | loss:1.4853118658065796 lr:1.8995076754950093e-05 tokens_per_second_per_gpu:5332.317032628719 mfu:25.153449230009706 Step 4223 | loss:1.4535326957702637 lr:1.8984470692922023e-05 tokens_per_second_per_gpu:5109.137494437399 mfu:24.100673270005522 Step 4224 | loss:1.332283854484558 lr:1.8973865779992972e-05 tokens_per_second_per_gpu:3361.6742201719594 mfu:15.857590857316806 Step 4225 | loss:1.240620732307434 lr:1.8963262018188682e-05 tokens_per_second_per_gpu:5303.309275817782 mfu:25.016614691898855 Step 4226 | loss:1.1685646772384644 lr:1.8952659409534728e-05 tokens_per_second_per_gpu:5313.496173923316 mfu:25.0646680283267 Step 4227 | loss:1.1973257064819336 lr:1.8942057956056447e-05 tokens_per_second_per_gpu:3922.706506668996 mfu:18.50407587470194 Step 4228 | loss:1.3269469738006592 lr:1.8931457659778925e-05 tokens_per_second_per_gpu:3711.6698936019684 mfu:17.508580164305705 Step 4229 | loss:1.3608189821243286 lr:1.8920858522727077e-05 tokens_per_second_per_gpu:3921.1042760940018 mfu:18.496517879710968 Step 4230 | loss:1.2135335206985474 lr:1.8910260546925567e-05 tokens_per_second_per_gpu:5324.24228589855 mfu:25.115359271989647 Step 4231 | loss:1.3323768377304077 lr:1.8899663734398833e-05 tokens_per_second_per_gpu:4443.142495973312 mfu:20.95906123178648 Step 4232 | loss:1.3077280521392822 lr:1.888906808717111e-05 tokens_per_second_per_gpu:4391.924588089897 mfu:20.717457621624224 Step 4233 | loss:1.265965223312378 lr:1.887847360726639e-05 tokens_per_second_per_gpu:5329.917965268505 mfu:25.142132419948478 Step 4234 | loss:1.271113634109497 lr:1.8867880296708474e-05 tokens_per_second_per_gpu:4798.5971228174985 mfu:22.635801353423552 Step 4235 | loss:1.219456434249878 lr:1.8857288157520895e-05 tokens_per_second_per_gpu:5321.690702887707 mfu:25.103323019582543 Step 4236 | loss:1.4586490392684937 lr:1.884669719172699e-05 tokens_per_second_per_gpu:4273.197674325142 mfu:20.15740251249556 Step 4237 | loss:1.3265515565872192 lr:1.883610740134989e-05 tokens_per_second_per_gpu:5335.8789976274165 mfu:25.170251626642457 Step 4238 | loss:1.498509168624878 lr:1.882551878841245e-05 tokens_per_second_per_gpu:3821.233290775032 mfu:18.025409402214212 Step 4239 | loss:1.4305944442749023 lr:1.881493135493734e-05 tokens_per_second_per_gpu:3461.440389495629 mfu:16.32820489988028 Step 4240 | loss:1.2825868129730225 lr:1.8804345102947e-05 tokens_per_second_per_gpu:5316.701505426244 mfu:25.07978812391196 Step 4241 | loss:1.3567954301834106 lr:1.879376003446363e-05 tokens_per_second_per_gpu:4104.722744145824 mfu:19.36267752205256 Step 4242 | loss:1.1607122421264648 lr:1.8783176151509208e-05 tokens_per_second_per_gpu:5354.917892412227 mfu:25.26006134171282 Step 4243 | loss:1.223501205444336 lr:1.8772593456105505e-05 tokens_per_second_per_gpu:4452.136329184179 mfu:21.001486677548318 Step 4244 | loss:1.251336693763733 lr:1.8762011950274037e-05 tokens_per_second_per_gpu:5184.86574573117 mfu:24.457896351930238 Step 4245 | loss:1.5410641431808472 lr:1.8751431636036104e-05 tokens_per_second_per_gpu:3503.2986971735018 mfu:16.52565767896053 Step 4246 | loss:1.2346705198287964 lr:1.8740852515412793e-05 tokens_per_second_per_gpu:4091.8183399653917 mfu:19.301805245815075 Step 4247 | loss:1.2374037504196167 lr:1.8730274590424937e-05 tokens_per_second_per_gpu:3772.599438426397 mfu:17.795995222894845 Step 4248 | loss:1.2560800313949585 lr:1.8719697863093154e-05 tokens_per_second_per_gpu:3181.4796810089774 mfu:15.00758247172638 Step 4249 | loss:1.2413705587387085 lr:1.8709122335437844e-05 tokens_per_second_per_gpu:5182.585798261818 mfu:24.447141450718153 Step 4250 | loss:1.3782975673675537 lr:1.8698548009479154e-05 tokens_per_second_per_gpu:4983.911652141194 mfu:23.509961606162463 Step 4251 | loss:1.3890146017074585 lr:1.8687974887237017e-05 tokens_per_second_per_gpu:4539.0205807722405 mfu:21.411334516271125 Step 4252 | loss:1.1401423215866089 lr:1.8677402970731146e-05 tokens_per_second_per_gpu:4540.08839765378 mfu:21.416371590689696 Step 4253 | loss:1.393483281135559 lr:1.866683226198099e-05 tokens_per_second_per_gpu:4825.317696562477 mfu:22.761846858778604 Step 4254 | loss:1.3170126676559448 lr:1.8656262763005787e-05 tokens_per_second_per_gpu:4849.650051174993 mfu:22.87662672701363 Step 4255 | loss:1.2910913228988647 lr:1.8645694475824577e-05 tokens_per_second_per_gpu:5294.2000274669535 mfu:24.973644813229967 Step 4256 | loss:1.1157371997833252 lr:1.86351274024561e-05 tokens_per_second_per_gpu:5319.273807337993 mfu:25.091922110909643 Step 4257 | loss:1.309834361076355 lr:1.8624561544918915e-05 tokens_per_second_per_gpu:5346.8988701780545 mfu:25.222234245647954 Step 4258 | loss:1.1928448677062988 lr:1.8613996905231342e-05 tokens_per_second_per_gpu:4382.108470519395 mfu:20.671153320241807 Step 4259 | loss:1.2988108396530151 lr:1.8603433485411447e-05 tokens_per_second_per_gpu:4600.665206004319 mfu:21.702122731148453 Step 4260 | loss:1.2905642986297607 lr:1.8592871287477077e-05 tokens_per_second_per_gpu:4336.722478912784 mfu:20.457059854184756 Step 4261 | loss:1.242313027381897 lr:1.858231031344586e-05 tokens_per_second_per_gpu:4811.331119183242 mfu:22.69586978692458 Step 4262 | loss:1.188984751701355 lr:1.8571750565335167e-05 tokens_per_second_per_gpu:3262.722172009986 mfu:15.390817163176445 Step 4263 | loss:1.4885612726211548 lr:1.856119204516213e-05 tokens_per_second_per_gpu:5087.466448541464 mfu:23.998447249052695 Step 4264 | loss:1.108197569847107 lr:1.8550634754943686e-05 tokens_per_second_per_gpu:4858.033792320108 mfu:22.916174264408873 Step 4265 | loss:1.3957479000091553 lr:1.854007869669649e-05 tokens_per_second_per_gpu:5330.683613762526 mfu:25.14574411452788 Step 4266 | loss:1.3842414617538452 lr:1.852952387243698e-05 tokens_per_second_per_gpu:4139.6084644634 mfu:19.52723941690822 Step 4267 | loss:1.0552760362625122 lr:1.851897028418138e-05 tokens_per_second_per_gpu:5328.616542784568 mfu:25.135993388046177 Step 4268 | loss:1.264474630355835 lr:1.850841793394565e-05 tokens_per_second_per_gpu:4692.49886042352 mfu:22.135317747480943 Step 4269 | loss:1.09195077419281 lr:1.849786682374551e-05 tokens_per_second_per_gpu:4798.814523021886 mfu:22.636826867279947 Step 4270 | loss:1.3473584651947021 lr:1.8487316955596474e-05 tokens_per_second_per_gpu:5252.894806619124 mfu:24.778801039093374 Step 4271 | loss:1.4576014280319214 lr:1.8476768331513783e-05 tokens_per_second_per_gpu:5048.146984016714 mfu:23.81297062629703 Step 4272 | loss:1.3324514627456665 lr:1.8466220953512464e-05 tokens_per_second_per_gpu:3832.951774499772 mfu:18.080687489323303 Step 4273 | loss:1.217217206954956 lr:1.845567482360731e-05 tokens_per_second_per_gpu:5297.987800320581 mfu:24.99151238404122 Step 4274 | loss:1.10926353931427 lr:1.844512994381285e-05 tokens_per_second_per_gpu:4840.078235808111 mfu:22.831474840807942 Step 4275 | loss:1.3686579465866089 lr:1.8434586316143392e-05 tokens_per_second_per_gpu:5336.977965060873 mfu:25.175435643529255 Step 4276 | loss:1.2708841562271118 lr:1.8424043942613012e-05 tokens_per_second_per_gpu:3365.479700546772 mfu:15.875541957526702 Step 4277 | loss:1.3082560300827026 lr:1.8413502825235525e-05 tokens_per_second_per_gpu:5304.638169408074 mfu:25.02288330969689 Step 4278 | loss:1.5449371337890625 lr:1.840296296602451e-05 tokens_per_second_per_gpu:3260.5409890294895 mfu:15.380528150909251 Step 4279 | loss:1.178645372390747 lr:1.8392424366993338e-05 tokens_per_second_per_gpu:5328.246015198931 mfu:25.1342455462062 Step 4280 | loss:1.1508150100708008 lr:1.8381887030155097e-05 tokens_per_second_per_gpu:5322.887441120235 mfu:25.10896823800998 Step 4281 | loss:1.394045114517212 lr:1.8371350957522644e-05 tokens_per_second_per_gpu:3872.980570113731 mfu:18.269510147851125 Step 4282 | loss:1.2647051811218262 lr:1.8360816151108624e-05 tokens_per_second_per_gpu:4752.673567084164 mfu:22.41917210566284 Step 4283 | loss:1.225159764289856 lr:1.83502826129254e-05 tokens_per_second_per_gpu:5305.012216505763 mfu:25.024647753675705 Step 4284 | loss:1.2067431211471558 lr:1.833975034498511e-05 tokens_per_second_per_gpu:4192.810029927142 mfu:19.77820027832376 Step 4285 | loss:1.3362388610839844 lr:1.832921934929967e-05 tokens_per_second_per_gpu:4892.177695904 mfu:23.077236883164755 Step 4286 | loss:1.3488398790359497 lr:1.831868962788071e-05 tokens_per_second_per_gpu:4578.7378190787695 mfu:21.598687505822646 Step 4287 | loss:1.3235633373260498 lr:1.8308161182739646e-05 tokens_per_second_per_gpu:3642.9313231164983 mfu:17.184328599316263 Step 4288 | loss:1.3302983045578003 lr:1.8297634015887653e-05 tokens_per_second_per_gpu:4394.828430421625 mfu:20.731155541349576 Step 4289 | loss:1.2110252380371094 lr:1.828710812933564e-05 tokens_per_second_per_gpu:5118.650090017326 mfu:24.1455458063722 Step 4290 | loss:1.216569185256958 lr:1.8276583525094288e-05 tokens_per_second_per_gpu:3466.509314991622 mfu:16.35211588629275 Step 4291 | loss:1.2197027206420898 lr:1.8266060205174038e-05 tokens_per_second_per_gpu:3520.956580948382 mfu:16.608952929472277 Step 4292 | loss:1.3346375226974487 lr:1.8255538171585062e-05 tokens_per_second_per_gpu:5167.941794334493 mfu:24.37806318566825 Step 4293 | loss:1.2918680906295776 lr:1.8245017426337306e-05 tokens_per_second_per_gpu:5101.623731020333 mfu:24.06522956598699 Step 4294 | loss:1.3005415201187134 lr:1.8234497971440472e-05 tokens_per_second_per_gpu:3536.3578590519737 mfu:16.681603386015926 Step 4295 | loss:1.3166530132293701 lr:1.8223979808904003e-05 tokens_per_second_per_gpu:5043.940614536659 mfu:23.793128463778977 Step 4296 | loss:1.2690500020980835 lr:1.8213462940737092e-05 tokens_per_second_per_gpu:5332.260050258214 mfu:25.15318043444584 Step 4297 | loss:1.2604411840438843 lr:1.8202947368948707e-05 tokens_per_second_per_gpu:4510.4940501462725 mfu:21.276770004180428 Step 4298 | loss:1.5134663581848145 lr:1.8192433095547552e-05 tokens_per_second_per_gpu:5309.336870661534 mfu:25.04504788519056 Step 4299 | loss:1.37993323802948 lr:1.8181920122542073e-05 tokens_per_second_per_gpu:5066.657991369815 mfu:23.900290206285142 Step 4300 | loss:1.565258502960205 lr:1.81714084519405e-05 tokens_per_second_per_gpu:3723.900471326058 mfu:17.566273886181975 Step 4301 | loss:1.3786194324493408 lr:1.816089808575077e-05 tokens_per_second_per_gpu:5289.985189885362 mfu:24.953762705232155 Step 4302 | loss:1.1636487245559692 lr:1.815038902598062e-05 tokens_per_second_per_gpu:4092.7748071449814 mfu:19.306317064691328 Step 4303 | loss:1.268534779548645 lr:1.8139881274637504e-05 tokens_per_second_per_gpu:5039.768281650818 mfu:23.773446857683066 Step 4304 | loss:1.2010672092437744 lr:1.8129374833728623e-05 tokens_per_second_per_gpu:5320.288403692266 mfu:25.096708135020737 Step 4305 | loss:1.3171210289001465 lr:1.8118869705260956e-05 tokens_per_second_per_gpu:3609.204862369902 mfu:17.025235129646997 Step 4306 | loss:1.169438123703003 lr:1.8108365891241208e-05 tokens_per_second_per_gpu:4443.301748094708 mfu:20.959812451214322 Step 4307 | loss:1.2245813608169556 lr:1.809786339367583e-05 tokens_per_second_per_gpu:4860.8781750621265 mfu:22.929591703104716 Step 4308 | loss:1.1129655838012695 lr:1.8087362214571045e-05 tokens_per_second_per_gpu:4585.229474874817 mfu:21.62930975380329 Step 4309 | loss:1.2314492464065552 lr:1.807686235593281e-05 tokens_per_second_per_gpu:4882.962107985314 mfu:23.033765382610884 Step 4310 | loss:1.5131100416183472 lr:1.8066363819766814e-05 tokens_per_second_per_gpu:5288.934586919114 mfu:24.94880683178901 Step 4311 | loss:1.2520276308059692 lr:1.8055866608078527e-05 tokens_per_second_per_gpu:4140.024494232629 mfu:19.52920190031167 Step 4312 | loss:1.1233164072036743 lr:1.8045370722873146e-05 tokens_per_second_per_gpu:5002.410984044631 mfu:23.59722611106246 Step 4313 | loss:1.1723545789718628 lr:1.8034876166155603e-05 tokens_per_second_per_gpu:5305.704622428041 mfu:25.027913950547724 Step 4314 | loss:1.2854111194610596 lr:1.8024382939930605e-05 tokens_per_second_per_gpu:4115.528160382405 mfu:19.41364851403463 Step 4315 | loss:1.270707130432129 lr:1.801389104620259e-05 tokens_per_second_per_gpu:4423.52221013462 mfu:20.866508995919418 Step 4316 | loss:1.3815703392028809 lr:1.8003400486975726e-05 tokens_per_second_per_gpu:5112.0316758581 mfu:24.11432561756524 Step 4317 | loss:1.2340168952941895 lr:1.799291126425396e-05 tokens_per_second_per_gpu:5296.244766242555 mfu:24.98329019490289 Step 4318 | loss:1.398756980895996 lr:1.7982423380040958e-05 tokens_per_second_per_gpu:5298.511672971839 mfu:24.993983580719092 Step 4319 | loss:1.1705622673034668 lr:1.7971936836340127e-05 tokens_per_second_per_gpu:4573.225817125264 mfu:21.572686452163452 Step 4320 | loss:1.3468024730682373 lr:1.7961451635154645e-05 tokens_per_second_per_gpu:3624.5910142964512 mfu:17.097814233432747 Step 4321 | loss:1.1938886642456055 lr:1.7950967778487417e-05 tokens_per_second_per_gpu:5280.127967126958 mfu:24.907264503665136 Step 4322 | loss:1.2820724248886108 lr:1.7940485268341072e-05 tokens_per_second_per_gpu:4972.211401352765 mfu:23.45476952692481 Step 4323 | loss:1.2687242031097412 lr:1.7930004106718024e-05 tokens_per_second_per_gpu:5335.927874460305 mfu:25.17048218700244 Step 4324 | loss:1.476723313331604 lr:1.79195242956204e-05 tokens_per_second_per_gpu:3441.2488137972578 mfu:16.23295779227301 Step 4325 | loss:1.2326128482818604 lr:1.7909045837050058e-05 tokens_per_second_per_gpu:5302.576917346715 mfu:25.013160032037593 Step 4326 | loss:1.200812578201294 lr:1.7898568733008636e-05 tokens_per_second_per_gpu:4758.920419807712 mfu:22.448639575782803 Step 4327 | loss:1.2455731630325317 lr:1.788809298549749e-05 tokens_per_second_per_gpu:4304.604226118086 mfu:20.30555257581317 Step 4328 | loss:1.265730381011963 lr:1.7877618596517704e-05 tokens_per_second_per_gpu:3971.994943865504 mfu:18.736577842432414 Step 4329 | loss:1.160055160522461 lr:1.786714556807013e-05 tokens_per_second_per_gpu:5143.506795369681 mfu:24.262799126510508 Step 4330 | loss:1.478979229927063 lr:1.785667390215536e-05 tokens_per_second_per_gpu:3925.5138660297616 mfu:18.51731866779157 Step 4331 | loss:1.2690162658691406 lr:1.784620360077368e-05 tokens_per_second_per_gpu:5316.061866010498 mfu:25.07677083565415 Step 4332 | loss:1.2694166898727417 lr:1.783573466592518e-05 tokens_per_second_per_gpu:5344.622351518966 mfu:25.2114955187189 Step 4333 | loss:1.315815806388855 lr:1.7825267099609648e-05 tokens_per_second_per_gpu:4936.0273780785255 mfu:23.284083315509246 Step 4334 | loss:1.258208990097046 lr:1.7814800903826612e-05 tokens_per_second_per_gpu:4075.776925702547 mfu:19.226135157789738 Step 4335 | loss:1.2609957456588745 lr:1.7804336080575358e-05 tokens_per_second_per_gpu:3624.5285558758455 mfu:17.09751960640624 Step 4336 | loss:1.2752553224563599 lr:1.7793872631854892e-05 tokens_per_second_per_gpu:5339.130752749358 mfu:25.185590710359293 Step 4337 | loss:1.303505778312683 lr:1.7783410559663963e-05 tokens_per_second_per_gpu:4484.963254696055 mfu:21.156336886038872 Step 4338 | loss:1.2800318002700806 lr:1.7772949866001062e-05 tokens_per_second_per_gpu:4083.9480480718053 mfu:19.264679736142764 Step 4339 | loss:1.220164179801941 lr:1.776249055286442e-05 tokens_per_second_per_gpu:4298.700998846377 mfu:20.277706045578082 Step 4340 | loss:1.1440095901489258 lr:1.7752032622251975e-05 tokens_per_second_per_gpu:5332.070693155009 mfu:25.15228720468237 Step 4341 | loss:1.2287373542785645 lr:1.7741576076161442e-05 tokens_per_second_per_gpu:5235.753541194543 mfu:24.697942765484164 Step 4342 | loss:1.2361677885055542 lr:1.7731120916590248e-05 tokens_per_second_per_gpu:4371.260565244072 mfu:20.61998190021462 Step 4343 | loss:1.2671656608581543 lr:1.7720667145535552e-05 tokens_per_second_per_gpu:5316.520102674142 mfu:25.078932416179793 Step 4344 | loss:1.2746464014053345 lr:1.7710214764994266e-05 tokens_per_second_per_gpu:5297.758775658156 mfu:24.99043203563292 Step 4345 | loss:1.277503490447998 lr:1.7699763776963026e-05 tokens_per_second_per_gpu:4474.919154792195 mfu:21.10895715309221 Step 4346 | loss:1.3236345052719116 lr:1.7689314183438183e-05 tokens_per_second_per_gpu:4284.027811557374 mfu:20.20849011763195 Step 4347 | loss:1.3600856065750122 lr:1.767886598641586e-05 tokens_per_second_per_gpu:4491.788201054711 mfu:21.188531322468577 Step 4348 | loss:1.477494478225708 lr:1.7668419187891895e-05 tokens_per_second_per_gpu:4066.6640759807433 mfu:19.183148290839497 Step 4349 | loss:1.2325767278671265 lr:1.7657973789861837e-05 tokens_per_second_per_gpu:5211.617591814005 mfu:24.584089374238573 Step 4350 | loss:1.2100545167922974 lr:1.7647529794321002e-05 tokens_per_second_per_gpu:4075.317591461844 mfu:19.22396839980584 Step 4351 | loss:1.264362096786499 lr:1.763708720326443e-05 tokens_per_second_per_gpu:5313.493310829683 mfu:25.06465452262554 Step 4352 | loss:1.3215123414993286 lr:1.762664601868687e-05 tokens_per_second_per_gpu:3212.5607552114784 mfu:15.154197201717663 Step 4353 | loss:1.1729037761688232 lr:1.761620624258283e-05 tokens_per_second_per_gpu:4826.4585945189865 mfu:22.767228669096724 Step 4354 | loss:1.3139333724975586 lr:1.7605767876946542e-05 tokens_per_second_per_gpu:4210.743094299707 mfu:19.862793602665437 Step 4355 | loss:1.3161324262619019 lr:1.7595330923771946e-05 tokens_per_second_per_gpu:4563.893739715483 mfu:21.528665450804926 Step 4356 | loss:1.1604933738708496 lr:1.758489538505275e-05 tokens_per_second_per_gpu:5261.304486676638 mfu:24.81847093476404 Step 4357 | loss:1.351302146911621 lr:1.757446126278237e-05 tokens_per_second_per_gpu:4850.009367856935 mfu:22.878321685108098 Step 4358 | loss:1.3954143524169922 lr:1.7564028558953935e-05 tokens_per_second_per_gpu:4944.38959940151 mfu:23.323529340231843 Step 4359 | loss:1.2676663398742676 lr:1.7553597275560342e-05 tokens_per_second_per_gpu:5308.365747490372 mfu:25.04046693150149 Step 4360 | loss:1.2342923879623413 lr:1.75431674145942e-05 tokens_per_second_per_gpu:5312.060090818333 mfu:25.057893779299455 Step 4361 | loss:1.2641799449920654 lr:1.753273897804782e-05 tokens_per_second_per_gpu:4693.430680923152 mfu:22.139713303762683 Step 4362 | loss:1.2729979753494263 lr:1.752231196791328e-05 tokens_per_second_per_gpu:5187.334150686663 mfu:24.46954023925861 Step 4363 | loss:1.1294100284576416 lr:1.7511886386182374e-05 tokens_per_second_per_gpu:5304.788670025288 mfu:25.023593246786344 Step 4364 | loss:1.3468211889266968 lr:1.75014622348466e-05 tokens_per_second_per_gpu:4720.989647513079 mfu:22.269713651211926 Step 4365 | loss:1.1936967372894287 lr:1.749103951589722e-05 tokens_per_second_per_gpu:3825.3060544005066 mfu:18.0446213231207 Step 4366 | loss:1.358242154121399 lr:1.748061823132519e-05 tokens_per_second_per_gpu:4717.988307881123 mfu:22.255555820086645 Step 4367 | loss:1.3253973722457886 lr:1.7470198383121217e-05 tokens_per_second_per_gpu:3400.153760132302 mfu:16.03910541259625 Step 4368 | loss:1.289165735244751 lr:1.7459779973275715e-05 tokens_per_second_per_gpu:5371.104559200333 mfu:25.336416610682452 Step 4369 | loss:1.4054369926452637 lr:1.7449363003778826e-05 tokens_per_second_per_gpu:3817.9372830676675 mfu:18.00986157150167 Step 4370 | loss:1.2500903606414795 lr:1.7438947476620437e-05 tokens_per_second_per_gpu:5307.836272279437 mfu:25.037969306593727 Step 4371 | loss:1.306789517402649 lr:1.742853339379013e-05 tokens_per_second_per_gpu:4380.110943419843 mfu:20.661730644099954 Step 4372 | loss:1.1982471942901611 lr:1.7418120757277223e-05 tokens_per_second_per_gpu:4548.192851852449 mfu:21.454601683907292 Step 4373 | loss:1.3081532716751099 lr:1.740770956907078e-05 tokens_per_second_per_gpu:4303.132841790352 mfu:20.298611804895195 Step 4374 | loss:1.2823050022125244 lr:1.739729983115954e-05 tokens_per_second_per_gpu:4841.321459447702 mfu:22.837339338831722 Step 4375 | loss:1.1840629577636719 lr:1.7386891545532007e-05 tokens_per_second_per_gpu:3999.610135776725 mfu:18.86684341431523 Step 4376 | loss:1.3215988874435425 lr:1.7376484714176404e-05 tokens_per_second_per_gpu:4614.187890383814 mfu:21.765911540574397 Step 4377 | loss:1.1608837842941284 lr:1.7366079339080647e-05 tokens_per_second_per_gpu:4900.09389279476 mfu:23.114578934540937 Step 4378 | loss:1.3640201091766357 lr:1.7355675422232398e-05 tokens_per_second_per_gpu:5217.2793014684 mfu:24.61079662466563 Step 4379 | loss:1.1346359252929688 lr:1.734527296561905e-05 tokens_per_second_per_gpu:4572.50290219033 mfu:21.56927633907336 Step 4380 | loss:1.20900559425354 lr:1.7334871971227676e-05 tokens_per_second_per_gpu:5314.8774976750765 mfu:25.071183968141888 Step 4381 | loss:1.2472670078277588 lr:1.732447244104511e-05 tokens_per_second_per_gpu:5314.4918445320745 mfu:25.06936477646714 Step 4382 | loss:1.2188992500305176 lr:1.73140743770579e-05 tokens_per_second_per_gpu:4899.857473532216 mfu:23.113463704542234 Step 4383 | loss:1.350412130355835 lr:1.730367778125229e-05 tokens_per_second_per_gpu:4058.9242105252674 mfu:19.1466380249288 Step 4384 | loss:1.40535306930542 lr:1.7293282655614262e-05 tokens_per_second_per_gpu:3519.99431284881 mfu:16.60441374666673 Step 4385 | loss:1.3017154932022095 lr:1.7282889002129532e-05 tokens_per_second_per_gpu:3767.861838971841 mfu:17.77364715794989 Step 4386 | loss:1.2096740007400513 lr:1.7272496822783495e-05 tokens_per_second_per_gpu:4357.718807660532 mfu:20.556103119230965 Step 4387 | loss:1.3614720106124878 lr:1.7262106119561294e-05 tokens_per_second_per_gpu:4972.9948077127565 mfu:23.458464988387792 Step 4388 | loss:1.225846767425537 lr:1.7251716894447802e-05 tokens_per_second_per_gpu:4676.457616118852 mfu:22.05964846117732 Step 4389 | loss:1.1687917709350586 lr:1.724132914942756e-05 tokens_per_second_per_gpu:4328.196349322553 mfu:20.416840646199923 Step 4390 | loss:1.1300395727157593 lr:1.723094288648487e-05 tokens_per_second_per_gpu:3809.5433790511343 mfu:17.970266094107977 Step 4391 | loss:1.429531216621399 lr:1.7220558107603746e-05 tokens_per_second_per_gpu:4874.6332662974955 mfu:22.994476815322514 Step 4392 | loss:1.2563341856002808 lr:1.72101748147679e-05 tokens_per_second_per_gpu:5108.041620763432 mfu:24.095503846910088 Step 4393 | loss:1.2600163221359253 lr:1.7199793009960767e-05 tokens_per_second_per_gpu:5326.642913421949 mfu:25.126683441606808 Step 4394 | loss:1.2172714471817017 lr:1.7189412695165515e-05 tokens_per_second_per_gpu:5314.137616765536 mfu:25.06769382365489 Step 4395 | loss:1.3030359745025635 lr:1.7179033872365002e-05 tokens_per_second_per_gpu:4525.196161379606 mfu:21.3461223713069 Step 4396 | loss:1.2176023721694946 lr:1.716865654354181e-05 tokens_per_second_per_gpu:3948.3902698160528 mfu:18.62523056756847 Step 4397 | loss:1.3047436475753784 lr:1.715828071067826e-05 tokens_per_second_per_gpu:4600.634002373423 mfu:21.701975538297624 Step 4398 | loss:1.2281335592269897 lr:1.714790637575634e-05 tokens_per_second_per_gpu:5311.213650282409 mfu:25.05390097487385 Step 4399 | loss:1.2925764322280884 lr:1.7137533540757784e-05 tokens_per_second_per_gpu:5126.392403322885 mfu:24.182067619209388 Step 4400 | loss:1.524665355682373 lr:1.7127162207664042e-05 tokens_per_second_per_gpu:5319.702651584034 mfu:25.093945042386594 Step 4401 | loss:1.2114337682724 lr:1.7116792378456255e-05 tokens_per_second_per_gpu:5308.842043170146 mfu:25.04271369948741 Step 4402 | loss:1.2893418073654175 lr:1.7106424055115294e-05 tokens_per_second_per_gpu:5114.806604380101 mfu:24.127415428855144 Step 4403 | loss:1.2603799104690552 lr:1.7096057239621748e-05 tokens_per_second_per_gpu:4910.22336003773 mfu:23.16236135979135 Step 4404 | loss:1.1395237445831299 lr:1.7085691933955895e-05 tokens_per_second_per_gpu:4645.437895923706 mfu:21.913323148506812 Step 4405 | loss:1.1632341146469116 lr:1.7075328140097734e-05 tokens_per_second_per_gpu:4096.579040701543 mfu:19.324262283446803 Step 4406 | loss:1.2192707061767578 lr:1.7064965860027e-05 tokens_per_second_per_gpu:4674.5207109423745 mfu:22.050511748989784 Step 4407 | loss:1.3904999494552612 lr:1.7054605095723096e-05 tokens_per_second_per_gpu:5325.663998659119 mfu:25.12206573365046 Step 4408 | loss:1.4680120944976807 lr:1.7044245849165165e-05 tokens_per_second_per_gpu:4382.2750143113835 mfu:20.67193893572392 Step 4409 | loss:1.3284671306610107 lr:1.7033888122332053e-05 tokens_per_second_per_gpu:5368.693699423493 mfu:25.325044173780004 Step 4410 | loss:1.0757672786712646 lr:1.702353191720231e-05 tokens_per_second_per_gpu:4862.681236270728 mfu:22.938097050459653 Step 4411 | loss:1.0835931301116943 lr:1.7013177235754205e-05 tokens_per_second_per_gpu:5197.481184306537 mfu:24.517405528106014 Step 4412 | loss:1.342750072479248 lr:1.7002824079965712e-05 tokens_per_second_per_gpu:4180.343068806439 mfu:19.7193914956345 Step 4413 | loss:1.3592877388000488 lr:1.699247245181451e-05 tokens_per_second_per_gpu:4758.99248935103 mfu:22.448979540114962 Step 4414 | loss:1.1818397045135498 lr:1.698212235327798e-05 tokens_per_second_per_gpu:4368.552297388353 mfu:20.607206538661043 Step 4415 | loss:1.252690315246582 lr:1.6971773786333237e-05 tokens_per_second_per_gpu:5337.340406795235 mfu:25.177145343029178 Step 4416 | loss:1.1888262033462524 lr:1.696142675295707e-05 tokens_per_second_per_gpu:4355.767239263748 mfu:20.546897238131432 Step 4417 | loss:1.2744766473770142 lr:1.6951081255126e-05 tokens_per_second_per_gpu:4634.687467935722 mfu:21.862611545475342 Step 4418 | loss:1.2900047302246094 lr:1.6940737294816248e-05 tokens_per_second_per_gpu:5317.845948850727 mfu:25.08518665880743 Step 4419 | loss:1.2356435060501099 lr:1.693039487400373e-05 tokens_per_second_per_gpu:5317.506813142545 mfu:25.083586897809415 Step 4420 | loss:1.272758960723877 lr:1.6920053994664077e-05 tokens_per_second_per_gpu:4972.180449919167 mfu:23.454623523731666 Step 4421 | loss:1.4738911390304565 lr:1.6909714658772638e-05 tokens_per_second_per_gpu:5296.446516616351 mfu:24.984241885838244 Step 4422 | loss:1.2427128553390503 lr:1.6899376868304446e-05 tokens_per_second_per_gpu:5312.024661756995 mfu:25.0577266543723 Step 4423 | loss:1.314218282699585 lr:1.6889040625234236e-05 tokens_per_second_per_gpu:5329.279329243203 mfu:25.13911986485459 Step 4424 | loss:1.2443699836730957 lr:1.6878705931536483e-05 tokens_per_second_per_gpu:3711.6841885461326 mfu:17.508647595996297 Step 4425 | loss:1.0690885782241821 lr:1.6868372789185326e-05 tokens_per_second_per_gpu:5314.287719374646 mfu:25.068401883272205 Step 4426 | loss:1.3135052919387817 lr:1.6858041200154616e-05 tokens_per_second_per_gpu:4244.5833717793075 mfu:20.02242396528342 Step 4427 | loss:1.186627745628357 lr:1.684771116641794e-05 tokens_per_second_per_gpu:4076.6160588507464 mfu:19.23009349202067 Step 4428 | loss:1.3649446964263916 lr:1.683738268994855e-05 tokens_per_second_per_gpu:4406.981760199487 mfu:20.788484871483632 Step 4429 | loss:1.230930209159851 lr:1.682705577271939e-05 tokens_per_second_per_gpu:5279.3619706951595 mfu:24.903651167803876 Step 4430 | loss:1.2539564371109009 lr:1.681673041670317e-05 tokens_per_second_per_gpu:3367.713120310671 mfu:15.886077379613718 Step 4431 | loss:1.3089507818222046 lr:1.6806406623872246e-05 tokens_per_second_per_gpu:4828.582039153238 mfu:22.7772453197335 Step 4432 | loss:1.4633721113204956 lr:1.6796084396198665e-05 tokens_per_second_per_gpu:4086.317978271808 mfu:19.275859101247963 Step 4433 | loss:1.2842952013015747 lr:1.6785763735654237e-05 tokens_per_second_per_gpu:4379.0682983872475 mfu:20.656812309587615 Step 4434 | loss:1.092551589012146 lr:1.6775444644210412e-05 tokens_per_second_per_gpu:4548.401107123373 mfu:21.45558405955225 Step 4435 | loss:1.27073073387146 lr:1.6765127123838382e-05 tokens_per_second_per_gpu:4312.4891516826565 mfu:20.342747115008272 Step 4436 | loss:1.352254033088684 lr:1.6754811176509016e-05 tokens_per_second_per_gpu:5353.052819280637 mfu:25.25126347353682 Step 4437 | loss:1.3243539333343506 lr:1.674449680419287e-05 tokens_per_second_per_gpu:3856.2340365741798 mfu:18.19051389189181 Step 4438 | loss:1.2995824813842773 lr:1.6734184008860242e-05 tokens_per_second_per_gpu:5326.985247938817 mfu:25.128298291931166 Step 4439 | loss:1.2155778408050537 lr:1.67238727924811e-05 tokens_per_second_per_gpu:5310.454118976066 mfu:25.050318136112427 Step 4440 | loss:1.3236740827560425 lr:1.6713563157025093e-05 tokens_per_second_per_gpu:4517.464394697742 mfu:21.309650308693126 Step 4441 | loss:1.4257123470306396 lr:1.6703255104461612e-05 tokens_per_second_per_gpu:4232.795076320087 mfu:19.96681656431167 Step 4442 | loss:1.3114807605743408 lr:1.669294863675972e-05 tokens_per_second_per_gpu:4803.021550212679 mfu:22.656672132331774 Step 4443 | loss:1.1980514526367188 lr:1.668264375588816e-05 tokens_per_second_per_gpu:5324.746228951812 mfu:25.11773645735343 Step 4444 | loss:1.184082269668579 lr:1.6672340463815424e-05 tokens_per_second_per_gpu:3904.750594786412 mfu:18.41937477475732 Step 4445 | loss:1.2020752429962158 lr:1.6662038762509638e-05 tokens_per_second_per_gpu:4460.731835964421 mfu:21.042033149575406 Step 4446 | loss:1.347493052482605 lr:1.6651738653938664e-05 tokens_per_second_per_gpu:4682.91598994299 mfu:22.090113712417985 Step 4447 | loss:1.2759116888046265 lr:1.664144014007007e-05 tokens_per_second_per_gpu:4454.03432840246 mfu:21.010439863693012 Step 4448 | loss:1.2105436325073242 lr:1.6631143222871074e-05 tokens_per_second_per_gpu:4688.095210906639 mfu:22.114544981369736 Step 4449 | loss:1.215504765510559 lr:1.6620847904308618e-05 tokens_per_second_per_gpu:5309.980034292618 mfu:25.048081797773417 Step 4450 | loss:1.3169405460357666 lr:1.6610554186349353e-05 tokens_per_second_per_gpu:5107.446210709892 mfu:24.09269519610011 Step 4451 | loss:1.253853678703308 lr:1.6600262070959593e-05 tokens_per_second_per_gpu:3731.360590909179 mfu:17.601464543083207 Step 4452 | loss:1.257332444190979 lr:1.6589971560105354e-05 tokens_per_second_per_gpu:4083.439548106979 mfu:19.262281055049638 Step 4453 | loss:1.3946542739868164 lr:1.6579682655752366e-05 tokens_per_second_per_gpu:5136.899883452008 mfu:24.231633195739434 Step 4454 | loss:1.1874133348464966 lr:1.656939535986603e-05 tokens_per_second_per_gpu:5316.208543014474 mfu:25.077462736107584 Step 4455 | loss:1.2510069608688354 lr:1.6559109674411438e-05 tokens_per_second_per_gpu:3880.349143708984 mfu:18.304268966708225 Step 4456 | loss:1.1931785345077515 lr:1.65488256013534e-05 tokens_per_second_per_gpu:4434.641451840913 mfu:20.91896035618626 Step 4457 | loss:1.1626253128051758 lr:1.653854314265639e-05 tokens_per_second_per_gpu:4327.628446898755 mfu:20.414161753572724 Step 4458 | loss:1.3378504514694214 lr:1.652826230028458e-05 tokens_per_second_per_gpu:3788.483376985444 mfu:17.870922471157243 Step 4459 | loss:1.3185473680496216 lr:1.651798307620186e-05 tokens_per_second_per_gpu:5317.104093437017 mfu:25.081687200247373 Step 4460 | loss:1.330237865447998 lr:1.6507705472371763e-05 tokens_per_second_per_gpu:4912.170850674186 mfu:23.171548005399682 Step 4461 | loss:1.240430235862732 lr:1.6497429490757552e-05 tokens_per_second_per_gpu:5316.053609002827 mfu:25.076731885940173 Step 4462 | loss:1.2943789958953857 lr:1.648715513332217e-05 tokens_per_second_per_gpu:4816.743762023983 mfu:22.72140214669645 Step 4463 | loss:1.2779110670089722 lr:1.6476882402028236e-05 tokens_per_second_per_gpu:3771.2295990976477 mfu:17.789533457062447 Step 4464 | loss:1.3638317584991455 lr:1.6466611298838068e-05 tokens_per_second_per_gpu:3300.7393070432086 mfu:15.570150475520249 Step 4465 | loss:1.1120859384536743 lr:1.645634182571369e-05 tokens_per_second_per_gpu:4714.030553452219 mfu:22.236886417182966 Step 4466 | loss:1.2808538675308228 lr:1.6446073984616784e-05 tokens_per_second_per_gpu:4863.774744929266 mfu:22.94325531737379 Step 4467 | loss:1.1826103925704956 lr:1.643580777750873e-05 tokens_per_second_per_gpu:5334.381515404476 mfu:25.163187747500036 Step 4468 | loss:1.2545075416564941 lr:1.6425543206350617e-05 tokens_per_second_per_gpu:4669.333279803919 mfu:22.02604175124267 Step 4469 | loss:1.2755399942398071 lr:1.6415280273103196e-05 tokens_per_second_per_gpu:3957.8043052938956 mfu:18.669638179117534 Step 4470 | loss:1.210107684135437 lr:1.64050189797269e-05 tokens_per_second_per_gpu:5280.393304391865 mfu:24.908516144814907 Step 4471 | loss:1.4431214332580566 lr:1.6394759328181894e-05 tokens_per_second_per_gpu:4758.108712145865 mfu:22.44481061225026 Step 4472 | loss:1.3841183185577393 lr:1.6384501320427975e-05 tokens_per_second_per_gpu:3323.536183250255 mfu:15.677687230137046 Step 4473 | loss:1.3341633081436157 lr:1.6374244958424648e-05 tokens_per_second_per_gpu:5192.28818097849 mfu:24.492909245389885 Step 4474 | loss:1.4340609312057495 lr:1.636399024413112e-05 tokens_per_second_per_gpu:4125.491836132898 mfu:19.460648872528086 Step 4475 | loss:1.1893013715744019 lr:1.6353737179506258e-05 tokens_per_second_per_gpu:3276.5252171807037 mfu:15.455928482289071 Step 4476 | loss:1.2346946001052856 lr:1.634348576650862e-05 tokens_per_second_per_gpu:5325.302560626615 mfu:25.12036076878345 Step 4477 | loss:1.3523788452148438 lr:1.633323600709647e-05 tokens_per_second_per_gpu:3281.9947213760975 mfu:15.481729066772386 Step 4478 | loss:1.3489049673080444 lr:1.6322987903227716e-05 tokens_per_second_per_gpu:4644.357455380739 mfu:21.90822652612347 Step 4479 | loss:1.0962713956832886 lr:1.6312741456859983e-05 tokens_per_second_per_gpu:4837.03408727569 mfu:22.817115072795215 Step 4480 | loss:1.368131399154663 lr:1.6302496669950573e-05 tokens_per_second_per_gpu:4047.8437880770693 mfu:19.09436978172564 Step 4481 | loss:1.2343839406967163 lr:1.629225354445646e-05 tokens_per_second_per_gpu:3902.8800522177416 mfu:18.410551106313427 Step 4482 | loss:1.1306591033935547 lr:1.6282012082334307e-05 tokens_per_second_per_gpu:5320.646026666619 mfu:25.09839510360753 Step 4483 | loss:1.1696089506149292 lr:1.6271772285540464e-05 tokens_per_second_per_gpu:4158.495151795401 mfu:19.61633114345441 Step 4484 | loss:1.1454700231552124 lr:1.626153415603096e-05 tokens_per_second_per_gpu:4229.348354333188 mfu:19.950557788628057 Step 4485 | loss:1.1664445400238037 lr:1.6251297695761492e-05 tokens_per_second_per_gpu:5330.7758216165275 mfu:25.146179074707486 Step 4486 | loss:1.2268809080123901 lr:1.6241062906687464e-05 tokens_per_second_per_gpu:5295.984661218084 mfu:24.982063235123963 Step 4487 | loss:1.1504298448562622 lr:1.6230829790763942e-05 tokens_per_second_per_gpu:3924.4361929808697 mfu:18.512235100149965 Step 4488 | loss:1.252042293548584 lr:1.6220598349945668e-05 tokens_per_second_per_gpu:5300.107120086558 mfu:25.00150957697057 Step 4489 | loss:1.2798080444335938 lr:1.621036858618709e-05 tokens_per_second_per_gpu:5092.482162696535 mfu:24.022107228491244 Step 4490 | loss:1.3080414533615112 lr:1.620014050144231e-05 tokens_per_second_per_gpu:4187.099158278586 mfu:19.751261122382346 Step 4491 | loss:1.2688511610031128 lr:1.618991409766511e-05 tokens_per_second_per_gpu:5310.064462129265 mfu:25.048480058283754 Step 4492 | loss:1.3747247457504272 lr:1.6179689376808983e-05 tokens_per_second_per_gpu:3955.080897148916 mfu:18.65679139823632 Step 4493 | loss:1.2271114587783813 lr:1.616946634082705e-05 tokens_per_second_per_gpu:4232.687894381882 mfu:19.966310968822036 Step 4494 | loss:1.3168624639511108 lr:1.6159244991672144e-05 tokens_per_second_per_gpu:4498.688046531738 mfu:21.221079070818746 Step 4495 | loss:1.255340814590454 lr:1.6149025331296784e-05 tokens_per_second_per_gpu:5335.355430788789 mfu:25.167781872534942 Step 4496 | loss:1.2844865322113037 lr:1.6138807361653136e-05 tokens_per_second_per_gpu:3918.229755446603 mfu:18.482958275373395 Step 4497 | loss:1.4370914697647095 lr:1.612859108469305e-05 tokens_per_second_per_gpu:3978.035856739287 mfu:18.765073859144064 Step 4498 | loss:1.1825085878372192 lr:1.611837650236809e-05 tokens_per_second_per_gpu:3737.7616961301255 mfu:17.63165964855158 Step 4499 | loss:1.2788327932357788 lr:1.6108163616629433e-05 tokens_per_second_per_gpu:3659.055719712726 mfu:17.260390129166414 Step 4500 | loss:1.3624285459518433 lr:1.6097952429427994e-05 tokens_per_second_per_gpu:4910.817246356191 mfu:23.165162822882987 Step 4501 | loss:1.3361313343048096 lr:1.608774294271432e-05 tokens_per_second_per_gpu:4165.931070891555 mfu:19.651407642529584 Step 4502 | loss:1.2422367334365845 lr:1.6077535158438643e-05 tokens_per_second_per_gpu:5331.536440013998 mfu:25.149767041463235 Step 4503 | loss:1.2995566129684448 lr:1.6067329078550895e-05 tokens_per_second_per_gpu:5317.567698273402 mfu:25.083874103359744 Step 4504 | loss:1.2829294204711914 lr:1.6057124705000655e-05 tokens_per_second_per_gpu:4420.89248171659 mfu:20.854104118293634 Step 4505 | loss:1.3767868280410767 lr:1.6046922039737166e-05 tokens_per_second_per_gpu:4777.339006804888 mfu:22.53552319318347 Step 4506 | loss:1.3601346015930176 lr:1.6036721084709382e-05 tokens_per_second_per_gpu:3299.962900592242 mfu:15.56648803382244 Step 4507 | loss:1.4070738554000854 lr:1.6026521841865915e-05 tokens_per_second_per_gpu:3524.550383365447 mfu:16.625905508639494 Step 4508 | loss:1.1513713598251343 lr:1.6016324313155023e-05 tokens_per_second_per_gpu:4345.300669489621 mfu:20.497524642725928 Step 4509 | loss:1.1988804340362549 lr:1.600612850052468e-05 tokens_per_second_per_gpu:3750.720101098823 mfu:17.6927866557208 Step 4510 | loss:1.0599862337112427 lr:1.599593440592251e-05 tokens_per_second_per_gpu:5304.870450172275 mfu:25.023979017692813 Step 4511 | loss:1.341604471206665 lr:1.598574203129579e-05 tokens_per_second_per_gpu:4955.191603012356 mfu:23.37448423427606 Step 4512 | loss:1.256743311882019 lr:1.5975551378591512e-05 tokens_per_second_per_gpu:4855.923719860815 mfu:22.906220692602908 Step 4513 | loss:1.2792038917541504 lr:1.5965362449756315e-05 tokens_per_second_per_gpu:4705.853484380534 mfu:22.19831378721998 Step 4514 | loss:1.280036449432373 lr:1.5955175246736487e-05 tokens_per_second_per_gpu:5329.235397944618 mfu:25.138912633423708 Step 4515 | loss:1.378587007522583 lr:1.594498977147803e-05 tokens_per_second_per_gpu:3767.267243014021 mfu:17.77084234736832 Step 4516 | loss:1.3875713348388672 lr:1.5934806025926593e-05 tokens_per_second_per_gpu:5226.073952670609 mfu:24.652282494908672 Step 4517 | loss:1.2296169996261597 lr:1.5924624012027484e-05 tokens_per_second_per_gpu:3828.3845702137874 mfu:18.05914320746091 Step 4518 | loss:1.301699161529541 lr:1.5914443731725704e-05 tokens_per_second_per_gpu:5330.517420247285 mfu:25.14496015136095 Step 4519 | loss:1.2643355131149292 lr:1.590426518696591e-05 tokens_per_second_per_gpu:3736.051656618377 mfu:17.623593100411835 Step 4520 | loss:1.3450125455856323 lr:1.5894088379692417e-05 tokens_per_second_per_gpu:4594.434474949545 mfu:21.672731309690747 Step 4521 | loss:1.316178560256958 lr:1.588391331184924e-05 tokens_per_second_per_gpu:3253.6347803904773 mfu:15.347950386438333 Step 4522 | loss:1.239258050918579 lr:1.587373998538003e-05 tokens_per_second_per_gpu:4752.810174489541 mfu:22.41981650610164 Step 4523 | loss:1.2398284673690796 lr:1.5863568402228114e-05 tokens_per_second_per_gpu:5314.590332645875 mfu:25.069829361703736 Step 4524 | loss:1.2139571905136108 lr:1.5853398564336498e-05 tokens_per_second_per_gpu:5292.15893254216 mfu:24.964016620223013 Step 4525 | loss:1.23077392578125 lr:1.5843230473647847e-05 tokens_per_second_per_gpu:5302.496582381176 mfu:25.012781078298588 Step 4526 | loss:1.3242872953414917 lr:1.583306413210447e-05 tokens_per_second_per_gpu:3996.727216576485 mfu:18.853244192570962 Step 4527 | loss:1.262080430984497 lr:1.582289954164839e-05 tokens_per_second_per_gpu:3621.8874272291423 mfu:17.08506095195673 Step 4528 | loss:1.3282390832901 lr:1.5812736704221258e-05 tokens_per_second_per_gpu:4708.564548498286 mfu:22.21110233921866 Step 4529 | loss:1.2409636974334717 lr:1.580257562176439e-05 tokens_per_second_per_gpu:5255.261557098289 mfu:24.789965404912866 Step 4530 | loss:1.2638188600540161 lr:1.5792416296218794e-05 tokens_per_second_per_gpu:3375.1829243317407 mfu:15.92131371966109 Step 4531 | loss:1.3348698616027832 lr:1.5782258729525118e-05 tokens_per_second_per_gpu:5320.1156370718545 mfu:25.095893165395232 Step 4532 | loss:1.2066315412521362 lr:1.5772102923623672e-05 tokens_per_second_per_gpu:4409.069581581672 mfu:20.798333481162455 Step 4533 | loss:1.1250874996185303 lr:1.576194888045446e-05 tokens_per_second_per_gpu:4611.820111785447 mfu:21.754742324941212 Step 4534 | loss:1.4814926385879517 lr:1.5751796601957116e-05 tokens_per_second_per_gpu:3255.0210725670017 mfu:15.354489763160833 Step 4535 | loss:1.1622363328933716 lr:1.5741646090070944e-05 tokens_per_second_per_gpu:5329.275951873808 mfu:25.139103933226913 Step 4536 | loss:1.3697861433029175 lr:1.573149734673493e-05 tokens_per_second_per_gpu:3261.640406991101 mfu:15.385714293014221 Step 4537 | loss:1.1804778575897217 lr:1.5721350373887707e-05 tokens_per_second_per_gpu:5342.451538065025 mfu:25.20125542127769 Step 4538 | loss:1.5193315744400024 lr:1.571120517346755e-05 tokens_per_second_per_gpu:5084.7497868419505 mfu:23.98563229230581 Step 4539 | loss:1.323357105255127 lr:1.570106174741244e-05 tokens_per_second_per_gpu:3915.946870755726 mfu:18.472189518786237 Step 4540 | loss:1.3580867052078247 lr:1.5690920097659992e-05 tokens_per_second_per_gpu:5334.4358450541895 mfu:25.16344402972733 Step 4541 | loss:1.1550463438034058 lr:1.568078022614747e-05 tokens_per_second_per_gpu:3673.594640038116 mfu:17.328972696936876 Step 4542 | loss:1.2639080286026 lr:1.567064213481183e-05 tokens_per_second_per_gpu:3954.2767275739325 mfu:18.652997993145647 Step 4543 | loss:1.3214515447616577 lr:1.5660505825589672e-05 tokens_per_second_per_gpu:4861.124540107581 mfu:22.930753849058338 Step 4544 | loss:1.2308318614959717 lr:1.5650371300417232e-05 tokens_per_second_per_gpu:3259.4416047484992 mfu:15.37534216768152 Step 4545 | loss:1.0546239614486694 lr:1.564023856123046e-05 tokens_per_second_per_gpu:5320.413688231061 mfu:25.097299123565982 Step 4546 | loss:1.2727149724960327 lr:1.5630107609964912e-05 tokens_per_second_per_gpu:5024.126668661296 mfu:23.699662700477123 Step 4547 | loss:1.1803650856018066 lr:1.5619978448555824e-05 tokens_per_second_per_gpu:3995.991286685722 mfu:18.849772685713646 Step 4548 | loss:1.2153822183609009 lr:1.56098510789381e-05 tokens_per_second_per_gpu:5209.027642981006 mfu:24.571872143702475 Step 4549 | loss:1.0276305675506592 lr:1.5599725503046292e-05 tokens_per_second_per_gpu:5080.915282754733 mfu:23.967544282292543 Step 4550 | loss:1.2244126796722412 lr:1.558960172281459e-05 tokens_per_second_per_gpu:5338.062982427802 mfu:25.18055385557211 Step 4551 | loss:1.2031257152557373 lr:1.557947974017688e-05 tokens_per_second_per_gpu:3864.4917634300737 mfu:18.229466998384545 Step 4552 | loss:1.288446068763733 lr:1.5569359557066683e-05 tokens_per_second_per_gpu:5332.5600909196 mfu:25.154595777437812 Step 4553 | loss:1.4066880941390991 lr:1.555924117541716e-05 tokens_per_second_per_gpu:5382.93036600236 mfu:25.39220095905831 Step 4554 | loss:1.2364503145217896 lr:1.5549124597161157e-05 tokens_per_second_per_gpu:4639.259261198692 mfu:21.88417747432513 Step 4555 | loss:1.2048815488815308 lr:1.5539009824231175e-05 tokens_per_second_per_gpu:5324.944666024347 mfu:25.118672518881436 Step 4556 | loss:1.0955029726028442 lr:1.552889685855934e-05 tokens_per_second_per_gpu:5349.392452101426 mfu:25.233996897029442 Step 4557 | loss:1.1831326484680176 lr:1.5518785702077458e-05 tokens_per_second_per_gpu:4494.055782470707 mfu:21.199227890897113 Step 4558 | loss:1.3110941648483276 lr:1.5508676356716996e-05 tokens_per_second_per_gpu:4823.6070494947035 mfu:22.753777444693426 Step 4559 | loss:1.4847426414489746 lr:1.5498568824409036e-05 tokens_per_second_per_gpu:3603.084831932737 mfu:16.996365901890023 Step 4560 | loss:1.495840072631836 lr:1.5488463107084366e-05 tokens_per_second_per_gpu:4035.945885314743 mfu:19.038245344404206 Step 4561 | loss:1.357055425643921 lr:1.547835920667339e-05 tokens_per_second_per_gpu:4582.881787895857 mfu:21.618235313766835 Step 4562 | loss:1.2609881162643433 lr:1.546825712510617e-05 tokens_per_second_per_gpu:5304.538180029169 mfu:25.022411642736646 Step 4563 | loss:1.2420318126678467 lr:1.545815686431244e-05 tokens_per_second_per_gpu:4875.836097804262 mfu:23.000150776764155 Step 4564 | loss:1.25108802318573 lr:1.5448058426221572e-05 tokens_per_second_per_gpu:5301.634282370321 mfu:25.00871346202383 Step 4565 | loss:1.20352041721344 lr:1.5437961812762574e-05 tokens_per_second_per_gpu:2928.512326482732 mfu:13.81429229974481 Step 4566 | loss:1.1623022556304932 lr:1.542786702586414e-05 tokens_per_second_per_gpu:4937.781419256842 mfu:23.29235742701765 Step 4567 | loss:1.3606640100479126 lr:1.5417774067454582e-05 tokens_per_second_per_gpu:4894.321597531502 mfu:23.087350032929024 Step 4568 | loss:1.199257731437683 lr:1.5407682939461903e-05 tokens_per_second_per_gpu:5000.603276896573 mfu:23.588698848018435 Step 4569 | loss:1.3303349018096924 lr:1.5397593643813708e-05 tokens_per_second_per_gpu:5218.639411870498 mfu:24.61721249749109 Step 4570 | loss:1.106552243232727 lr:1.5387506182437278e-05 tokens_per_second_per_gpu:5337.803219809683 mfu:25.179328510982366 Step 4571 | loss:1.2199074029922485 lr:1.537742055725955e-05 tokens_per_second_per_gpu:5238.284171849505 mfu:24.709880182053734 Step 4572 | loss:1.2783700227737427 lr:1.5367336770207103e-05 tokens_per_second_per_gpu:5334.013232649396 mfu:25.161450494908806 Step 4573 | loss:1.4709358215332031 lr:1.5357254823206148e-05 tokens_per_second_per_gpu:3714.492462379433 mfu:17.521894702808897 Step 4574 | loss:1.2871057987213135 lr:1.5347174718182576e-05 tokens_per_second_per_gpu:3973.413468078429 mfu:18.74326926316997 Step 4575 | loss:1.4069701433181763 lr:1.53370964570619e-05 tokens_per_second_per_gpu:4387.53341992405 mfu:20.696743732175378 Step 4576 | loss:1.3213977813720703 lr:1.5327020041769284e-05 tokens_per_second_per_gpu:4288.020467237555 mfu:20.227324155692667 Step 4577 | loss:1.2964415550231934 lr:1.531694547422957e-05 tokens_per_second_per_gpu:5217.884551121549 mfu:24.61365169054577 Step 4578 | loss:1.37052321434021 lr:1.5306872756367202e-05 tokens_per_second_per_gpu:5052.745539737079 mfu:23.834662798224503 Step 4579 | loss:1.505790114402771 lr:1.5296801890106292e-05 tokens_per_second_per_gpu:4861.9295148378105 mfu:22.93455105220368 Step 4580 | loss:1.2505172491073608 lr:1.5286732877370616e-05 tokens_per_second_per_gpu:5321.1754211171565 mfu:25.100892347554723 Step 4581 | loss:1.337037444114685 lr:1.527666572008356e-05 tokens_per_second_per_gpu:4258.426972306413 mfu:20.087726590931585 Step 4582 | loss:1.3824331760406494 lr:1.5266600420168173e-05 tokens_per_second_per_gpu:3259.2133817166614 mfu:15.374265600701476 Step 4583 | loss:1.3426297903060913 lr:1.5256536979547165e-05 tokens_per_second_per_gpu:4730.489557948555 mfu:22.314526349587922 Step 4584 | loss:1.3328821659088135 lr:1.5246475400142862e-05 tokens_per_second_per_gpu:5334.275369707281 mfu:25.162687040136046 Step 4585 | loss:1.272478699684143 lr:1.5236415683877247e-05 tokens_per_second_per_gpu:3777.18878161332 mfu:17.817643937730253 Step 4586 | loss:1.415299415588379 lr:1.5226357832671967e-05 tokens_per_second_per_gpu:4365.7618143009995 mfu:20.59404335383249 Step 4587 | loss:1.382495403289795 lr:1.5216301848448273e-05 tokens_per_second_per_gpu:3910.6233115498303 mfu:18.44707738171916 Step 4588 | loss:1.458798885345459 lr:1.5206247733127077e-05 tokens_per_second_per_gpu:5316.849194724859 mfu:25.080484799531924 Step 4589 | loss:1.172192931175232 lr:1.5196195488628963e-05 tokens_per_second_per_gpu:4063.280833940671 mfu:19.167188960895864 Step 4590 | loss:1.2436611652374268 lr:1.5186145116874113e-05 tokens_per_second_per_gpu:4849.024262200756 mfu:22.873674773651548 Step 4591 | loss:1.3413231372833252 lr:1.5176096619782362e-05 tokens_per_second_per_gpu:4673.886929996411 mfu:22.04752209613349 Step 4592 | loss:1.2768785953521729 lr:1.516604999927322e-05 tokens_per_second_per_gpu:5212.4048015189255 mfu:24.587802776728505 Step 4593 | loss:1.0830740928649902 lr:1.5156005257265796e-05 tokens_per_second_per_gpu:4696.477870346693 mfu:22.15408741617765 Step 4594 | loss:1.34114408493042 lr:1.5145962395678852e-05 tokens_per_second_per_gpu:4884.584852322257 mfu:23.041420144516973 Step 4595 | loss:1.10227632522583 lr:1.513592141643082e-05 tokens_per_second_per_gpu:4588.419603741976 mfu:21.64435813596179 Step 4596 | loss:1.322644829750061 lr:1.5125882321439728e-05 tokens_per_second_per_gpu:4867.01778471904 mfu:22.9585532893818 Step 4597 | loss:1.2224236726760864 lr:1.5115845112623268e-05 tokens_per_second_per_gpu:4544.783645323434 mfu:21.43851987503931 Step 4598 | loss:1.4625647068023682 lr:1.5105809791898781e-05 tokens_per_second_per_gpu:4598.372479311428 mfu:21.691307548158576 Step 4599 | loss:1.2845810651779175 lr:1.5095776361183222e-05 tokens_per_second_per_gpu:4397.522555169962 mfu:20.743864187452562 Step 4600 | loss:1.2395330667495728 lr:1.5085744822393197e-05 tokens_per_second_per_gpu:5202.554269416996 mfu:24.541336136129623 Step 4601 | loss:1.4163215160369873 lr:1.5075715177444966e-05 tokens_per_second_per_gpu:4918.413951431426 mfu:23.200997776854408 Step 4602 | loss:1.2936954498291016 lr:1.50656874282544e-05 tokens_per_second_per_gpu:4755.270681365258 mfu:22.431423136840152 Step 4603 | loss:1.3508554697036743 lr:1.5055661576737018e-05 tokens_per_second_per_gpu:5011.287875598486 mfu:23.63909992307587 Step 4604 | loss:1.416519284248352 lr:1.5045637624807995e-05 tokens_per_second_per_gpu:5323.26248780206 mfu:25.110737397197706 Step 4605 | loss:1.1276377439498901 lr:1.5035615574382117e-05 tokens_per_second_per_gpu:3778.6670881587434 mfu:17.82461736193012 Step 4606 | loss:1.1913706064224243 lr:1.5025595427373806e-05 tokens_per_second_per_gpu:5355.355346631663 mfu:25.26212488790329 Step 4607 | loss:1.1402689218521118 lr:1.5015577185697159e-05 tokens_per_second_per_gpu:5149.041576419165 mfu:24.28890763305195 Step 4608 | loss:1.2314680814743042 lr:1.5005560851265857e-05 tokens_per_second_per_gpu:5324.940114313026 mfu:25.118651047682537 Step 4609 | loss:1.4394174814224243 lr:1.4995546425993245e-05 tokens_per_second_per_gpu:5317.752696042783 mfu:25.08474676940179 Step 4610 | loss:1.3316569328308105 lr:1.4985533911792315e-05 tokens_per_second_per_gpu:5298.056675659463 mfu:24.991837280766067 Step 4611 | loss:1.2513437271118164 lr:1.4975523310575664e-05 tokens_per_second_per_gpu:4048.5900668358936 mfu:19.0978901059593 Step 4612 | loss:1.4441694021224976 lr:1.496551462425554e-05 tokens_per_second_per_gpu:5087.438314377525 mfu:23.99831453540121 Step 4613 | loss:1.2674906253814697 lr:1.4955507854743827e-05 tokens_per_second_per_gpu:3526.624470943087 mfu:16.635689333619055 Step 4614 | loss:1.3030790090560913 lr:1.4945503003952038e-05 tokens_per_second_per_gpu:4046.684242678709 mfu:19.088900008242724 Step 4615 | loss:1.279106616973877 lr:1.4935500073791314e-05 tokens_per_second_per_gpu:3633.2411633846746 mfu:17.138618462549516 Step 4616 | loss:1.342809796333313 lr:1.4925499066172449e-05 tokens_per_second_per_gpu:5307.406636200294 mfu:25.035942639904935 Step 4617 | loss:1.2398911714553833 lr:1.4915499983005842e-05 tokens_per_second_per_gpu:4558.750579820625 mfu:21.504404288067313 Step 4618 | loss:1.2683908939361572 lr:1.4905502826201544e-05 tokens_per_second_per_gpu:4578.400622527652 mfu:21.59709689215936 Step 4619 | loss:1.3191250562667847 lr:1.4895507597669245e-05 tokens_per_second_per_gpu:3970.856675625427 mfu:18.731208436935386 Step 4620 | loss:1.4204262495040894 lr:1.4885514299318237e-05 tokens_per_second_per_gpu:4095.3217863108703 mfu:19.318331599976283 Step 4621 | loss:1.200225830078125 lr:1.4875522933057461e-05 tokens_per_second_per_gpu:4014.3782404584163 mfu:18.93650708379725 Step 4622 | loss:1.212968111038208 lr:1.4865533500795508e-05 tokens_per_second_per_gpu:4226.418007576341 mfu:19.9367348430073 Step 4623 | loss:1.3302868604660034 lr:1.4855546004440563e-05 tokens_per_second_per_gpu:3666.890026834898 mfu:17.297345892532327 Step 4624 | loss:1.2229344844818115 lr:1.4845560445900459e-05 tokens_per_second_per_gpu:5300.52075451187 mfu:25.00346076112808 Step 4625 | loss:1.309632420539856 lr:1.483557682708267e-05 tokens_per_second_per_gpu:5345.06508236886 mfu:25.213583955675524 Step 4626 | loss:1.3133366107940674 lr:1.4825595149894275e-05 tokens_per_second_per_gpu:3558.418886465417 mfu:16.785669016324547 Step 4627 | loss:1.469146966934204 lr:1.4815615416241996e-05 tokens_per_second_per_gpu:3277.7301809046753 mfu:15.461612501763055 Step 4628 | loss:1.3442796468734741 lr:1.4805637628032196e-05 tokens_per_second_per_gpu:4025.8092461020306 mfu:18.990429087748854 Step 4629 | loss:1.3850220441818237 lr:1.479566178717084e-05 tokens_per_second_per_gpu:5151.221798584886 mfu:24.299192112991914 Step 4630 | loss:1.3500542640686035 lr:1.478568789556353e-05 tokens_per_second_per_gpu:4770.164070532257 mfu:22.50167779461511 Step 4631 | loss:1.374415636062622 lr:1.4775715955115518e-05 tokens_per_second_per_gpu:5305.098105442122 mfu:25.025052906442674 Step 4632 | loss:1.4123603105545044 lr:1.476574596773165e-05 tokens_per_second_per_gpu:4385.494422939864 mfu:20.687125435512215 Step 4633 | loss:1.4121814966201782 lr:1.4755777935316412e-05 tokens_per_second_per_gpu:3606.7361417579195 mfu:17.013589753313106 Step 4634 | loss:1.3058691024780273 lr:1.4745811859773936e-05 tokens_per_second_per_gpu:4424.058833348422 mfu:20.869040339176284 Step 4635 | loss:1.1579103469848633 lr:1.473584774300794e-05 tokens_per_second_per_gpu:4326.490535025163 mfu:20.408794029117207 Step 4636 | loss:1.217678189277649 lr:1.4725885586921809e-05 tokens_per_second_per_gpu:4854.347925422007 mfu:22.898787401376797 Step 4637 | loss:1.4613608121871948 lr:1.4715925393418531e-05 tokens_per_second_per_gpu:4169.411296350915 mfu:19.66782445980908 Step 4638 | loss:1.1838223934173584 lr:1.4705967164400709e-05 tokens_per_second_per_gpu:4821.164315688274 mfu:22.74225465255514 Step 4639 | loss:1.4359298944473267 lr:1.4696010901770602e-05 tokens_per_second_per_gpu:4514.287308355211 mfu:21.294663450348583 Step 4640 | loss:1.2304021120071411 lr:1.468605660743007e-05 tokens_per_second_per_gpu:5304.634387870228 mfu:25.022865471537674 Step 4641 | loss:1.2516666650772095 lr:1.4676104283280595e-05 tokens_per_second_per_gpu:3857.8182536729837 mfu:18.19798691424218 Step 4642 | loss:1.3047584295272827 lr:1.4666153931223306e-05 tokens_per_second_per_gpu:4660.3796642854695 mfu:21.98380601919781 Step 4643 | loss:1.2121741771697998 lr:1.4656205553158936e-05 tokens_per_second_per_gpu:3663.56234453436 mfu:17.281648647359543 Step 4644 | loss:1.1382488012313843 lr:1.464625915098783e-05 tokens_per_second_per_gpu:5298.739816980957 mfu:24.99505977493548 Step 4645 | loss:1.0711638927459717 lr:1.463631472660999e-05 tokens_per_second_per_gpu:4610.087251198237 mfu:21.746568125894843 Step 4646 | loss:1.2882788181304932 lr:1.4626372281925016e-05 tokens_per_second_per_gpu:4053.6222351724145 mfu:19.12162770257912 Step 4647 | loss:1.3532003164291382 lr:1.4616431818832121e-05 tokens_per_second_per_gpu:3603.192798319991 mfu:16.996875197759667 Step 4648 | loss:1.1592316627502441 lr:1.4606493339230167e-05 tokens_per_second_per_gpu:5280.047118146105 mfu:24.906883125228195 Step 4649 | loss:1.3020734786987305 lr:1.4596556845017629e-05 tokens_per_second_per_gpu:4271.6580960822575 mfu:20.15014005924474 Step 4650 | loss:1.2592755556106567 lr:1.4586622338092573e-05 tokens_per_second_per_gpu:3991.203058141233 mfu:18.827185794713262 Step 4651 | loss:1.1215221881866455 lr:1.457668982035273e-05 tokens_per_second_per_gpu:5313.656358014131 mfu:25.065423644013297 Step 4652 | loss:1.3037407398223877 lr:1.4566759293695426e-05 tokens_per_second_per_gpu:4452.9697537685615 mfu:21.005418083509753 Step 4653 | loss:1.233057975769043 lr:1.455683076001761e-05 tokens_per_second_per_gpu:5349.63992621516 mfu:25.235164274647364 Step 4654 | loss:1.227677345275879 lr:1.4546904221215846e-05 tokens_per_second_per_gpu:4264.863241231278 mfu:20.118087569590887 Step 4655 | loss:1.288540005683899 lr:1.453697967918633e-05 tokens_per_second_per_gpu:3604.5677231493814 mfu:17.00336095276627 Step 4656 | loss:1.236446499824524 lr:1.4527057135824868e-05 tokens_per_second_per_gpu:5351.049253075703 mfu:25.241812309904507 Step 4657 | loss:1.342278003692627 lr:1.4517136593026878e-05 tokens_per_second_per_gpu:3934.3410026731935 mfu:18.55895777740345 Step 4658 | loss:1.3630715608596802 lr:1.4507218052687411e-05 tokens_per_second_per_gpu:4445.41414952157 mfu:20.969777009157674 Step 4659 | loss:1.3427486419677734 lr:1.4497301516701123e-05 tokens_per_second_per_gpu:5314.101851780462 mfu:25.06752511411816 Step 4660 | loss:1.3657208681106567 lr:1.448738698696229e-05 tokens_per_second_per_gpu:3558.1158568192895 mfu:16.784239573781576 Step 4661 | loss:1.046464443206787 lr:1.447747446536481e-05 tokens_per_second_per_gpu:4527.807630464865 mfu:21.35844111654464 Step 4662 | loss:1.0979771614074707 lr:1.4467563953802193e-05 tokens_per_second_per_gpu:4351.506197671192 mfu:20.526797177930685 Step 4663 | loss:1.2439334392547607 lr:1.4457655454167563e-05 tokens_per_second_per_gpu:5243.166418827136 mfu:24.732910574044453 Step 4664 | loss:1.4579521417617798 lr:1.4447748968353665e-05 tokens_per_second_per_gpu:3166.367885389608 mfu:14.936297553451613 Step 4665 | loss:1.3421967029571533 lr:1.4437844498252857e-05 tokens_per_second_per_gpu:3450.052221150834 mfu:16.274484966776004 Step 4666 | loss:1.327365517616272 lr:1.4427942045757109e-05 tokens_per_second_per_gpu:3742.2211344207713 mfu:17.652695579827185 Step 4667 | loss:1.3238285779953003 lr:1.441804161275801e-05 tokens_per_second_per_gpu:5338.598719403398 mfu:25.18308101829215 Step 4668 | loss:1.4554716348648071 lr:1.4408143201146762e-05 tokens_per_second_per_gpu:3955.099964699678 mfu:18.656881343126525 Step 4669 | loss:1.35623037815094 lr:1.4398246812814178e-05 tokens_per_second_per_gpu:3931.0395960293095 mfu:18.54338447898619 Step 4670 | loss:1.31733238697052 lr:1.4388352449650689e-05 tokens_per_second_per_gpu:4084.660273142885 mfu:19.268039423321177 Step 4671 | loss:1.1119801998138428 lr:1.4378460113546336e-05 tokens_per_second_per_gpu:5328.735518142436 mfu:25.13655461510853 Step 4672 | loss:1.341918706893921 lr:1.4368569806390775e-05 tokens_per_second_per_gpu:4784.140885898444 mfu:22.567608817388017 Step 4673 | loss:1.3339941501617432 lr:1.4358681530073271e-05 tokens_per_second_per_gpu:5328.832675392423 mfu:25.137012922433453 Step 4674 | loss:1.4140146970748901 lr:1.4348795286482703e-05 tokens_per_second_per_gpu:5162.1034707036015 mfu:24.350522816980607 Step 4675 | loss:1.2360026836395264 lr:1.4338911077507566e-05 tokens_per_second_per_gpu:5331.733295763802 mfu:25.150695643622115 Step 4676 | loss:1.1586453914642334 lr:1.4329028905035957e-05 tokens_per_second_per_gpu:3970.412655400664 mfu:18.729113917777514 Step 4677 | loss:1.258850336074829 lr:1.4319148770955593e-05 tokens_per_second_per_gpu:4419.311330309545 mfu:20.84664555733436 Step 4678 | loss:1.1453588008880615 lr:1.4309270677153796e-05 tokens_per_second_per_gpu:5367.906122656607 mfu:25.321329039796154 Step 4679 | loss:1.1503037214279175 lr:1.4299394625517503e-05 tokens_per_second_per_gpu:5309.314386407112 mfu:25.04494182312624 Step 4680 | loss:1.3243969678878784 lr:1.4289520617933255e-05 tokens_per_second_per_gpu:3445.1627834044293 mfu:16.251420654702113 Step 4681 | loss:1.1311407089233398 lr:1.4279648656287208e-05 tokens_per_second_per_gpu:5326.590116492542 mfu:25.12643438948271 Step 4682 | loss:1.2050155401229858 lr:1.4269778742465134e-05 tokens_per_second_per_gpu:4471.392334243135 mfu:21.09232053882466 Step 4683 | loss:1.242531180381775 lr:1.4259910878352373e-05 tokens_per_second_per_gpu:5309.366950379512 mfu:25.04518977635239 Step 4684 | loss:1.3054343461990356 lr:1.4250045065833934e-05 tokens_per_second_per_gpu:3789.1224729798296 mfu:17.87393719600378 Step 4685 | loss:1.2604329586029053 lr:1.424018130679441e-05 tokens_per_second_per_gpu:4283.5143435522905 mfu:20.2060680014453 Step 4686 | loss:1.3968008756637573 lr:1.4230319603117964e-05 tokens_per_second_per_gpu:5334.426463292147 mfu:25.163399774355078 Step 4687 | loss:1.4396090507507324 lr:1.4220459956688425e-05 tokens_per_second_per_gpu:3365.939929395675 mfu:15.877712935530115 Step 4688 | loss:1.3043348789215088 lr:1.4210602369389215e-05 tokens_per_second_per_gpu:4327.119953056491 mfu:20.41176310136077 Step 4689 | loss:1.2214787006378174 lr:1.4200746843103308e-05 tokens_per_second_per_gpu:4166.83158870692 mfu:19.65565553870885 Step 4690 | loss:1.366380214691162 lr:1.4190893379713367e-05 tokens_per_second_per_gpu:3175.6857739593947 mfu:14.980251623631021 Step 4691 | loss:1.342455267906189 lr:1.4181041981101611e-05 tokens_per_second_per_gpu:5324.384135531595 mfu:25.116028400910764 Step 4692 | loss:1.158021330833435 lr:1.4171192649149856e-05 tokens_per_second_per_gpu:5290.9670716681885 mfu:24.958394409128054 Step 4693 | loss:1.1889309883117676 lr:1.4161345385739566e-05 tokens_per_second_per_gpu:5288.0528931379895 mfu:24.944647731790976 Step 4694 | loss:1.287397861480713 lr:1.4151500192751788e-05 tokens_per_second_per_gpu:5252.335181566877 mfu:24.776161192240046 Step 4695 | loss:1.3463257551193237 lr:1.4141657072067142e-05 tokens_per_second_per_gpu:3416.966721888637 mfu:16.118415021787957 Step 4696 | loss:1.3956162929534912 lr:1.4131816025565905e-05 tokens_per_second_per_gpu:4606.647492444371 mfu:21.73034219696949 Step 4697 | loss:1.3249105215072632 lr:1.4121977055127943e-05 tokens_per_second_per_gpu:5320.01514219485 mfu:25.095419113914208 Step 4698 | loss:1.052250623703003 lr:1.4112140162632682e-05 tokens_per_second_per_gpu:5024.777455889212 mfu:23.702732574866957 Step 4699 | loss:1.165602445602417 lr:1.4102305349959217e-05 tokens_per_second_per_gpu:5322.622531382613 mfu:25.107718613579348 Step 4700 | loss:1.189396858215332 lr:1.4092472618986202e-05 tokens_per_second_per_gpu:3798.040374619877 mfu:17.916004459590802 Step 4701 | loss:1.3249728679656982 lr:1.4082641971591909e-05 tokens_per_second_per_gpu:4085.314353300797 mfu:19.271124831023627 Step 4702 | loss:1.1329997777938843 lr:1.4072813409654206e-05 tokens_per_second_per_gpu:5341.842242280327 mfu:25.19838126910469 Step 4703 | loss:1.3058090209960938 lr:1.406298693505057e-05 tokens_per_second_per_gpu:5036.904753729269 mfu:23.759939107908878 Step 4704 | loss:1.3117291927337646 lr:1.4053162549658073e-05 tokens_per_second_per_gpu:4309.695767061956 mfu:20.329570243151863 Step 4705 | loss:1.284249186515808 lr:1.4043340255353387e-05 tokens_per_second_per_gpu:4540.47919014201 mfu:21.418215025532753 Step 4706 | loss:1.2866184711456299 lr:1.4033520054012789e-05 tokens_per_second_per_gpu:5296.978392839249 mfu:24.986750836729097 Step 4707 | loss:1.2115471363067627 lr:1.4023701947512155e-05 tokens_per_second_per_gpu:4669.442507512548 mfu:22.026556996980446 Step 4708 | loss:1.307157039642334 lr:1.401388593772696e-05 tokens_per_second_per_gpu:4264.645069270847 mfu:20.117058415229558 Step 4709 | loss:1.271682620048523 lr:1.4004072026532277e-05 tokens_per_second_per_gpu:5336.111232064248 mfu:25.171347116104275 Step 4710 | loss:1.3065414428710938 lr:1.3994260215802785e-05 tokens_per_second_per_gpu:3531.9373388573063 mfu:16.660751038039166 Step 4711 | loss:1.187314748764038 lr:1.3984450507412749e-05 tokens_per_second_per_gpu:4219.879712622495 mfu:19.905892590161862 Step 4712 | loss:1.1825870275497437 lr:1.3974642903236046e-05 tokens_per_second_per_gpu:5336.28253345296 mfu:25.17215517398186 Step 4713 | loss:1.305205225944519 lr:1.3964837405146142e-05 tokens_per_second_per_gpu:3814.587225903137 mfu:17.994058780277886 Step 4714 | loss:1.305584192276001 lr:1.3955034015016106e-05 tokens_per_second_per_gpu:5322.1074555724235 mfu:25.105288913101695 Step 4715 | loss:1.1676441431045532 lr:1.39452327347186e-05 tokens_per_second_per_gpu:5319.081177101958 mfu:25.09101344122016 Step 4716 | loss:1.333587646484375 lr:1.3935433566125882e-05 tokens_per_second_per_gpu:4237.1239588316585 mfu:19.987236641702275 Step 4717 | loss:1.3124423027038574 lr:1.3925636511109822e-05 tokens_per_second_per_gpu:4011.786968127252 mfu:18.9242836100945 Step 4718 | loss:1.293228030204773 lr:1.391584157154186e-05 tokens_per_second_per_gpu:5109.543845465789 mfu:24.102590097137067 Step 4719 | loss:1.366886019706726 lr:1.3906048749293055e-05 tokens_per_second_per_gpu:5006.299962878652 mfu:23.61557108775075 Step 4720 | loss:1.311814785003662 lr:1.3896258046234044e-05 tokens_per_second_per_gpu:4443.690967133508 mfu:20.961648463827956 Step 4721 | loss:1.1524485349655151 lr:1.388646946423508e-05 tokens_per_second_per_gpu:5310.090325062447 mfu:25.048602058152248 Step 4722 | loss:1.1970170736312866 lr:1.3876683005165985e-05 tokens_per_second_per_gpu:5308.458165185505 mfu:25.04090288153752 Step 4723 | loss:1.2375109195709229 lr:1.3866898670896197e-05 tokens_per_second_per_gpu:4872.249520598639 mfu:22.983232280152055 Step 4724 | loss:1.1761465072631836 lr:1.3857116463294739e-05 tokens_per_second_per_gpu:5329.808066266299 mfu:25.141614007604367 Step 4725 | loss:1.212469458580017 lr:1.3847336384230225e-05 tokens_per_second_per_gpu:4813.052267280203 mfu:22.703988736156088 Step 4726 | loss:1.1792858839035034 lr:1.3837558435570872e-05 tokens_per_second_per_gpu:4381.948162279585 mfu:20.670397118923216 Step 4727 | loss:1.2492220401763916 lr:1.3827782619184478e-05 tokens_per_second_per_gpu:5140.5660758302465 mfu:24.248927250704504 Step 4728 | loss:1.2713223695755005 lr:1.3818008936938448e-05 tokens_per_second_per_gpu:4444.9699811691435 mfu:20.967681791256343 Step 4729 | loss:1.1632297039031982 lr:1.3808237390699763e-05 tokens_per_second_per_gpu:4509.940171714854 mfu:21.27415726511802 Step 4730 | loss:1.301644206047058 lr:1.3798467982335007e-05 tokens_per_second_per_gpu:5330.963387313684 mfu:25.14706385410298 Step 4731 | loss:1.2796787023544312 lr:1.378870071371035e-05 tokens_per_second_per_gpu:5297.784525240615 mfu:24.990553500806715 Step 4732 | loss:1.2378407716751099 lr:1.3778935586691566e-05 tokens_per_second_per_gpu:5351.440273087509 mfu:25.243656818015086 Step 4733 | loss:1.1654722690582275 lr:1.3769172603144002e-05 tokens_per_second_per_gpu:3729.07552198484 mfu:17.59068548309414 Step 4734 | loss:1.326094150543213 lr:1.3759411764932603e-05 tokens_per_second_per_gpu:4768.355259244321 mfu:22.493145323154884 Step 4735 | loss:1.2245776653289795 lr:1.3749653073921908e-05 tokens_per_second_per_gpu:5293.95755399556 mfu:24.972501024495163 Step 4736 | loss:1.2358301877975464 lr:1.3739896531976043e-05 tokens_per_second_per_gpu:4889.056441811495 mfu:23.062513395069548 Step 4737 | loss:1.0901427268981934 lr:1.3730142140958718e-05 tokens_per_second_per_gpu:5320.979672523999 mfu:25.099968968042646 Step 4738 | loss:1.1898415088653564 lr:1.3720389902733244e-05 tokens_per_second_per_gpu:4222.710921582587 mfu:19.919247885880672 Step 4739 | loss:1.1669132709503174 lr:1.3710639819162508e-05 tokens_per_second_per_gpu:5040.306171299626 mfu:23.775984174929928 Step 4740 | loss:1.2120109796524048 lr:1.3700891892108996e-05 tokens_per_second_per_gpu:5322.587212505937 mfu:25.10755200841205 Step 4741 | loss:1.232659101486206 lr:1.3691146123434773e-05 tokens_per_second_per_gpu:4608.1595314914675 mfu:21.737474743135113 Step 4742 | loss:1.152928352355957 lr:1.3681402515001502e-05 tokens_per_second_per_gpu:4627.98653947979 mfu:21.831002122652418 Step 4743 | loss:1.274509072303772 lr:1.3671661068670421e-05 tokens_per_second_per_gpu:4863.110811363274 mfu:22.940123429464258 Step 4744 | loss:1.2101746797561646 lr:1.3661921786302367e-05 tokens_per_second_per_gpu:4831.036509242461 mfu:22.788823473920147 Step 4745 | loss:1.2405391931533813 lr:1.3652184669757756e-05 tokens_per_second_per_gpu:5296.371246601316 mfu:24.983886824334935 Step 4746 | loss:1.3002971410751343 lr:1.3642449720896588e-05 tokens_per_second_per_gpu:4862.91656833284 mfu:22.93920715194843 Step 4747 | loss:1.1450732946395874 lr:1.3632716941578461e-05 tokens_per_second_per_gpu:3934.5981688835423 mfu:18.560170874294744 Step 4748 | loss:1.3260034322738647 lr:1.3622986333662546e-05 tokens_per_second_per_gpu:4420.7617482063215 mfu:20.853487426020262 Step 4749 | loss:1.5105000734329224 lr:1.3613257899007605e-05 tokens_per_second_per_gpu:4431.366149613897 mfu:20.903510196757242 Step 4750 | loss:1.3017473220825195 lr:1.3603531639471987e-05 tokens_per_second_per_gpu:4038.4842574867807 mfu:19.05021927903066 Step 4751 | loss:1.3852673768997192 lr:1.3593807556913618e-05 tokens_per_second_per_gpu:5067.625875096764 mfu:23.904855878963147 Step 4752 | loss:1.2213836908340454 lr:1.3584085653190015e-05 tokens_per_second_per_gpu:5037.329849014742 mfu:23.761944354899185 Step 4753 | loss:1.307628870010376 lr:1.3574365930158273e-05 tokens_per_second_per_gpu:4693.158031993207 mfu:22.13842717224143 Step 4754 | loss:1.4042115211486816 lr:1.3564648389675078e-05 tokens_per_second_per_gpu:4545.352225033309 mfu:21.441201962540493 Step 4755 | loss:1.3609472513198853 lr:1.3554933033596694e-05 tokens_per_second_per_gpu:5321.652453651689 mfu:25.103142591410258 Step 4756 | loss:1.3633811473846436 lr:1.354521986377897e-05 tokens_per_second_per_gpu:4478.2168056677865 mfu:21.124512734909633 Step 4757 | loss:1.371346354484558 lr:1.3535508882077336e-05 tokens_per_second_per_gpu:3337.9053341591684 mfu:15.74546896660434 Step 4758 | loss:1.1774282455444336 lr:1.3525800090346796e-05 tokens_per_second_per_gpu:4459.836180859078 mfu:21.037808191628983 Step 4759 | loss:1.158804178237915 lr:1.3516093490441956e-05 tokens_per_second_per_gpu:5067.36073418276 mfu:23.903605164034087 Step 4760 | loss:1.4500809907913208 lr:1.350638908421698e-05 tokens_per_second_per_gpu:4737.132172972767 mfu:22.34586069800412 Step 4761 | loss:1.29476797580719 lr:1.3496686873525633e-05 tokens_per_second_per_gpu:4487.695439247763 mfu:21.169225066728032 Step 4762 | loss:1.2568559646606445 lr:1.3486986860221245e-05 tokens_per_second_per_gpu:5297.403137946559 mfu:24.988754431869268 Step 4763 | loss:1.1020965576171875 lr:1.3477289046156738e-05 tokens_per_second_per_gpu:5221.201377733537 mfu:24.62929772758349 Step 4764 | loss:1.4018595218658447 lr:1.3467593433184605e-05 tokens_per_second_per_gpu:4520.555301012366 mfu:21.324230641142204 Step 4765 | loss:1.1810837984085083 lr:1.3457900023156924e-05 tokens_per_second_per_gpu:4101.76162431474 mfu:19.3487094145902 Step 4766 | loss:1.3861467838287354 lr:1.344820881792535e-05 tokens_per_second_per_gpu:5007.119464650303 mfu:23.619436817429047 Step 4767 | loss:1.1589218378067017 lr:1.3438519819341116e-05 tokens_per_second_per_gpu:5322.567347051558 mfu:25.107458299674345 Step 4768 | loss:1.3390464782714844 lr:1.3428833029255039e-05 tokens_per_second_per_gpu:5163.874553280095 mfu:24.358877315671773 Step 4769 | loss:1.2780448198318481 lr:1.3419148449517505e-05 tokens_per_second_per_gpu:4040.5468653164717 mfu:19.059948952080497 Step 4770 | loss:1.1381490230560303 lr:1.340946608197849e-05 tokens_per_second_per_gpu:5137.554320753604 mfu:24.234720288149582 Step 4771 | loss:1.212514042854309 lr:1.3399785928487529e-05 tokens_per_second_per_gpu:5311.9380415528785 mfu:25.05731805209055 Step 4772 | loss:1.2557423114776611 lr:1.3390107990893751e-05 tokens_per_second_per_gpu:4513.546649257282 mfu:21.291169635014175 Step 4773 | loss:1.3433616161346436 lr:1.338043227104586e-05 tokens_per_second_per_gpu:4238.07091764797 mfu:19.99170360800665 Step 4774 | loss:1.3685306310653687 lr:1.3370758770792124e-05 tokens_per_second_per_gpu:5189.5735792744235 mfu:24.48010400599299 Step 4775 | loss:1.2404978275299072 lr:1.3361087491980403e-05 tokens_per_second_per_gpu:4630.587851194915 mfu:21.84327295384221 Step 4776 | loss:1.253279447555542 lr:1.3351418436458119e-05 tokens_per_second_per_gpu:4665.830382827084 mfu:22.009517988547085 Step 4777 | loss:1.1394455432891846 lr:1.3341751606072281e-05 tokens_per_second_per_gpu:4088.773762161225 mfu:19.28744345285428 Step 4778 | loss:1.4327620267868042 lr:1.3332087002669463e-05 tokens_per_second_per_gpu:5329.296532583198 mfu:25.139201015944536 Step 4779 | loss:1.2871607542037964 lr:1.3322424628095817e-05 tokens_per_second_per_gpu:3128.9231454985534 mfu:14.759664326654097 Step 4780 | loss:1.5797630548477173 lr:1.3312764484197071e-05 tokens_per_second_per_gpu:4412.59524503032 mfu:20.814964637189945 Step 4781 | loss:1.3193366527557373 lr:1.330310657281853e-05 tokens_per_second_per_gpu:3989.5650482900037 mfu:18.819459022771714 Step 4782 | loss:1.3291739225387573 lr:1.3293450895805066e-05 tokens_per_second_per_gpu:4887.578627550631 mfu:23.05554229305994 Step 4783 | loss:1.28489351272583 lr:1.328379745500112e-05 tokens_per_second_per_gpu:5145.682088438135 mfu:24.273060355057673 Step 4784 | loss:1.3464065790176392 lr:1.3274146252250724e-05 tokens_per_second_per_gpu:5351.830282206802 mfu:25.245496557573208 Step 4785 | loss:1.1811885833740234 lr:1.326449728939746e-05 tokens_per_second_per_gpu:3904.212577757711 mfu:18.41683685663777 Step 4786 | loss:1.3335232734680176 lr:1.3254850568284502e-05 tokens_per_second_per_gpu:5027.3815246585345 mfu:23.715016411551797 Step 4787 | loss:1.1519558429718018 lr:1.324520609075458e-05 tokens_per_second_per_gpu:4352.9593321728535 mfu:20.533651861305334 Step 4788 | loss:1.2490525245666504 lr:1.323556385865001e-05 tokens_per_second_per_gpu:5318.816453109414 mfu:25.08976469298076 Step 4789 | loss:1.3653419017791748 lr:1.3225923873812666e-05 tokens_per_second_per_gpu:4247.303491668086 mfu:20.035255234899097 Step 4790 | loss:1.098273754119873 lr:1.3216286138083995e-05 tokens_per_second_per_gpu:4994.8846999041425 mfu:23.56172334465529 Step 4791 | loss:1.3568739891052246 lr:1.3206650653305025e-05 tokens_per_second_per_gpu:5286.454043988138 mfu:24.937105687559338 Step 4792 | loss:1.2638300657272339 lr:1.3197017421316344e-05 tokens_per_second_per_gpu:5292.193651336483 mfu:24.964180394699465 Step 4793 | loss:1.274523138999939 lr:1.3187386443958105e-05 tokens_per_second_per_gpu:5253.714748093979 mfu:24.782668842926707 Step 4794 | loss:1.3762826919555664 lr:1.317775772307005e-05 tokens_per_second_per_gpu:5322.120877233559 mfu:25.105352225367245 Step 4795 | loss:1.0901883840560913 lr:1.3168131260491468e-05 tokens_per_second_per_gpu:5306.061196436825 mfu:25.029595970984957 Step 4796 | loss:1.4933534860610962 lr:1.3158507058061226e-05 tokens_per_second_per_gpu:4401.678999010241 mfu:20.763470842209603 Step 4797 | loss:1.189540147781372 lr:1.3148885117617765e-05 tokens_per_second_per_gpu:5355.123292488048 mfu:25.261030248915336 Step 4798 | loss:1.2328429222106934 lr:1.3139265440999089e-05 tokens_per_second_per_gpu:4556.328384118553 mfu:21.49297837767144 Step 4799 | loss:1.3077542781829834 lr:1.312964803004276e-05 tokens_per_second_per_gpu:5326.654912870054 mfu:25.126740045050838 Step 4800 | loss:1.2219525575637817 lr:1.3120032886585922e-05 tokens_per_second_per_gpu:5326.360406552649 mfu:25.125350808503676 Step 4801 | loss:1.2656748294830322 lr:1.311042001246528e-05 tokens_per_second_per_gpu:3364.529335708133 mfu:15.87105892443388 Step 4802 | loss:1.2872682809829712 lr:1.3100809409517106e-05 tokens_per_second_per_gpu:4556.611817333264 mfu:21.494315380503927 Step 4803 | loss:1.2527635097503662 lr:1.3091201079577236e-05 tokens_per_second_per_gpu:3677.123472767815 mfu:17.345618803003816 Step 4804 | loss:1.2968218326568604 lr:1.308159502448107e-05 tokens_per_second_per_gpu:5318.23799620566 mfu:25.087036013070826 Step 4805 | loss:1.2936296463012695 lr:1.3071991246063581e-05 tokens_per_second_per_gpu:3932.6469745871473 mfu:18.550966757890578 Step 4806 | loss:1.163392424583435 lr:1.3062389746159304e-05 tokens_per_second_per_gpu:4125.113434833542 mfu:19.4588638890371 Step 4807 | loss:1.1448086500167847 lr:1.3052790526602332e-05 tokens_per_second_per_gpu:5317.190637926803 mfu:25.082095445371706 Step 4808 | loss:1.1708879470825195 lr:1.3043193589226335e-05 tokens_per_second_per_gpu:5314.848624402599 mfu:25.071047767989327 Step 4809 | loss:1.3392994403839111 lr:1.3033598935864533e-05 tokens_per_second_per_gpu:5124.165947850215 mfu:24.171565048872328 Step 4810 | loss:1.1603599786758423 lr:1.3024006568349723e-05 tokens_per_second_per_gpu:5320.820546470728 mfu:25.09921834329966 Step 4811 | loss:1.389533519744873 lr:1.3014416488514256e-05 tokens_per_second_per_gpu:3603.2899148651613 mfu:16.997333313073028 Step 4812 | loss:1.1534278392791748 lr:1.3004828698190049e-05 tokens_per_second_per_gpu:4206.580279272411 mfu:19.8431568939322 Step 4813 | loss:1.169371485710144 lr:1.2995243199208585e-05 tokens_per_second_per_gpu:5007.6324640668 mfu:23.62185672320339 Step 4814 | loss:1.164744257926941 lr:1.29856599934009e-05 tokens_per_second_per_gpu:5348.712860339601 mfu:25.230791146738607 Step 4815 | loss:1.1910802125930786 lr:1.2976079082597603e-05 tokens_per_second_per_gpu:5336.010216145778 mfu:25.170870606781758 Step 4816 | loss:1.2031524181365967 lr:1.2966500468628856e-05 tokens_per_second_per_gpu:5330.8760320592 mfu:25.146651784463234 Step 4817 | loss:1.275107979774475 lr:1.295692415332439e-05 tokens_per_second_per_gpu:4820.110286992246 mfu:22.737282619360133 Step 4818 | loss:1.318878173828125 lr:1.294735013851349e-05 tokens_per_second_per_gpu:3401.878571811768 mfu:16.047241643571507 Step 4819 | loss:1.0752661228179932 lr:1.2937778426025004e-05 tokens_per_second_per_gpu:4775.980382480334 mfu:22.529114330439334 Step 4820 | loss:1.2133468389511108 lr:1.2928209017687343e-05 tokens_per_second_per_gpu:4615.833480447243 mfu:21.77367406967021 Step 4821 | loss:1.1029695272445679 lr:1.2918641915328478e-05 tokens_per_second_per_gpu:3918.362568947287 mfu:18.48358477931644 Step 4822 | loss:1.214991807937622 lr:1.2909077120775926e-05 tokens_per_second_per_gpu:4993.3351108229035 mfu:23.55441366857193 Step 4823 | loss:1.1077901124954224 lr:1.2899514635856785e-05 tokens_per_second_per_gpu:3341.881547884042 mfu:15.764225445156585 Step 4824 | loss:1.2935895919799805 lr:1.2889954462397696e-05 tokens_per_second_per_gpu:5028.937106743606 mfu:23.722354357656748 Step 4825 | loss:1.3081231117248535 lr:1.2880396602224867e-05 tokens_per_second_per_gpu:5322.92914830205 mfu:25.109164977902577 Step 4826 | loss:1.2229253053665161 lr:1.2870841057164057e-05 tokens_per_second_per_gpu:5324.8446526647895 mfu:25.118200738800365 Step 4827 | loss:1.2574496269226074 lr:1.2861287829040586e-05 tokens_per_second_per_gpu:4630.029404742355 mfu:21.84063866664469 Step 4828 | loss:1.2662864923477173 lr:1.2851736919679332e-05 tokens_per_second_per_gpu:5357.977219822486 mfu:25.274492711082097 Step 4829 | loss:1.3375792503356934 lr:1.2842188330904731e-05 tokens_per_second_per_gpu:4528.304447592463 mfu:21.360784687701262 Step 4830 | loss:1.1868150234222412 lr:1.2832642064540776e-05 tokens_per_second_per_gpu:4202.031612516643 mfu:19.821700056762666 Step 4831 | loss:1.2903788089752197 lr:1.282309812241101e-05 tokens_per_second_per_gpu:5300.191029860671 mfu:25.001905393691544 Step 4832 | loss:1.3090319633483887 lr:1.2813556506338542e-05 tokens_per_second_per_gpu:4699.135194067844 mfu:22.166622465556497 Step 4833 | loss:1.384135365486145 lr:1.2804017218146017e-05 tokens_per_second_per_gpu:3911.8264662770143 mfu:18.45275286784665 Step 4834 | loss:1.2646204233169556 lr:1.2794480259655681e-05 tokens_per_second_per_gpu:4308.509307658656 mfu:20.323973511715653 Step 4835 | loss:1.3061065673828125 lr:1.2784945632689276e-05 tokens_per_second_per_gpu:4907.1231721648155 mfu:23.14773724464822 Step 4836 | loss:1.3110263347625732 lr:1.2775413339068126e-05 tokens_per_second_per_gpu:5316.650582008495 mfu:25.079547909462008 Step 4837 | loss:1.2535650730133057 lr:1.2765883380613136e-05 tokens_per_second_per_gpu:4722.255065731084 mfu:22.275682844848866 Step 4838 | loss:1.2324318885803223 lr:1.2756355759144711e-05 tokens_per_second_per_gpu:5322.450366752828 mfu:25.10690648364634 Step 4839 | loss:1.2503935098648071 lr:1.274683047648284e-05 tokens_per_second_per_gpu:4074.0241489387204 mfu:19.217867010740214 Step 4840 | loss:1.2684755325317383 lr:1.273730753444709e-05 tokens_per_second_per_gpu:5288.425875259966 mfu:24.946407152097652 Step 4841 | loss:1.3112447261810303 lr:1.2727786934856522e-05 tokens_per_second_per_gpu:4215.745051782679 mfu:19.886388689534563 Step 4842 | loss:1.2379405498504639 lr:1.2718268679529782e-05 tokens_per_second_per_gpu:5341.635855041779 mfu:25.197407705287166 Step 4843 | loss:1.19268798828125 lr:1.27087527702851e-05 tokens_per_second_per_gpu:4357.76848610697 mfu:20.556337460938835 Step 4844 | loss:1.2422882318496704 lr:1.2699239208940189e-05 tokens_per_second_per_gpu:4386.078107881911 mfu:20.68987877697077 Step 4845 | loss:1.2862104177474976 lr:1.2689727997312354e-05 tokens_per_second_per_gpu:5292.290614197066 mfu:24.964637785056407 Step 4846 | loss:1.265397310256958 lr:1.2680219137218475e-05 tokens_per_second_per_gpu:5219.117164335881 mfu:24.619466137383277 Step 4847 | loss:1.3736156225204468 lr:1.267071263047492e-05 tokens_per_second_per_gpu:5326.54196536684 mfu:25.126207252407344 Step 4848 | loss:1.2579312324523926 lr:1.2661208478897651e-05 tokens_per_second_per_gpu:3769.5233070879626 mfu:17.781484586529327 Step 4849 | loss:1.3777731657028198 lr:1.2651706684302195e-05 tokens_per_second_per_gpu:4747.147975504198 mfu:22.393106947417007 Step 4850 | loss:1.328801155090332 lr:1.2642207248503576e-05 tokens_per_second_per_gpu:4652.5309902329545 mfu:21.946782484570218 Step 4851 | loss:1.401593565940857 lr:1.2632710173316398e-05 tokens_per_second_per_gpu:3433.074758917295 mfu:16.194399380766654 Step 4852 | loss:1.3242478370666504 lr:1.2623215460554838e-05 tokens_per_second_per_gpu:4186.742047773702 mfu:19.749576571201473 Step 4853 | loss:1.1632055044174194 lr:1.2613723112032566e-05 tokens_per_second_per_gpu:3635.93899156118 mfu:17.151344578355044 Step 4854 | loss:1.1865978240966797 lr:1.2604233129562836e-05 tokens_per_second_per_gpu:4625.52537069924 mfu:21.81939236959587 Step 4855 | loss:1.192371129989624 lr:1.2594745514958469e-05 tokens_per_second_per_gpu:3913.87234982522 mfu:18.462403649607268 Step 4856 | loss:1.2074612379074097 lr:1.2585260270031781e-05 tokens_per_second_per_gpu:3906.9051382612006 mfu:18.42953812393092 Step 4857 | loss:1.2674087285995483 lr:1.2575777396594663e-05 tokens_per_second_per_gpu:3875.9703591587295 mfu:18.283613492886996 Step 4858 | loss:1.1527645587921143 lr:1.2566296896458585e-05 tokens_per_second_per_gpu:5327.024599775929 mfu:25.128483921260944 Step 4859 | loss:1.1876716613769531 lr:1.2556818771434497e-05 tokens_per_second_per_gpu:4972.487845134816 mfu:23.456073559410918 Step 4860 | loss:1.3476102352142334 lr:1.2547343023332939e-05 tokens_per_second_per_gpu:4873.507657451752 mfu:22.98916712634847 Step 4861 | loss:1.2529953718185425 lr:1.2537869653964007e-05 tokens_per_second_per_gpu:5329.17168173598 mfu:25.138612073196455 Step 4862 | loss:1.1879136562347412 lr:1.2528398665137302e-05 tokens_per_second_per_gpu:4733.561573331671 mfu:22.329017570289952 Step 4863 | loss:1.2242281436920166 lr:1.2518930058661994e-05 tokens_per_second_per_gpu:3854.3433713711765 mfu:18.181595301548498 Step 4864 | loss:1.2960715293884277 lr:1.2509463836346818e-05 tokens_per_second_per_gpu:3291.4930774648356 mfu:15.526534433029624 Step 4865 | loss:1.3109501600265503 lr:1.2500000000000006e-05 tokens_per_second_per_gpu:4051.5246599922575 mfu:19.11173308257109 Step 4866 | loss:1.0456980466842651 lr:1.249053855142936e-05 tokens_per_second_per_gpu:5314.083808945551 mfu:25.067440002987457 Step 4867 | loss:1.1899616718292236 lr:1.2481079492442254e-05 tokens_per_second_per_gpu:4633.9640311895455 mfu:21.859198970912587 Step 4868 | loss:1.2625495195388794 lr:1.2471622824845549e-05 tokens_per_second_per_gpu:4362.263706954655 mfu:20.57754218464113 Step 4869 | loss:1.289177656173706 lr:1.2462168550445677e-05 tokens_per_second_per_gpu:5359.694476350585 mfu:25.282593303119317 Step 4870 | loss:1.3113185167312622 lr:1.2452716671048643e-05 tokens_per_second_per_gpu:5304.02611364174 mfu:25.01999613821961 Step 4871 | loss:1.324744701385498 lr:1.2443267188459935e-05 tokens_per_second_per_gpu:4190.915049925852 mfu:19.769261334340747 Step 4872 | loss:1.26697838306427 lr:1.2433820104484612e-05 tokens_per_second_per_gpu:4497.74035456178 mfu:21.216608646103527 Step 4873 | loss:1.458540916442871 lr:1.2424375420927308e-05 tokens_per_second_per_gpu:4382.495183704007 mfu:20.6729775123137 Step 4874 | loss:1.2689648866653442 lr:1.2414933139592133e-05 tokens_per_second_per_gpu:5333.602271668512 mfu:25.159511921844803 Step 4875 | loss:1.2932848930358887 lr:1.2405493262282774e-05 tokens_per_second_per_gpu:4909.51416634445 mfu:23.159015972139226 Step 4876 | loss:1.2913850545883179 lr:1.2396055790802489e-05 tokens_per_second_per_gpu:5287.083338260554 mfu:24.94007417601099 Step 4877 | loss:1.3273817300796509 lr:1.2386620726954005e-05 tokens_per_second_per_gpu:4903.837428200076 mfu:23.132237829760815 Step 4878 | loss:1.1644872426986694 lr:1.2377188072539633e-05 tokens_per_second_per_gpu:5319.379704263371 mfu:25.092421644774532 Step 4879 | loss:1.400970220565796 lr:1.2367757829361251e-05 tokens_per_second_per_gpu:3567.627854548509 mfu:16.829109289984466 Step 4880 | loss:1.2893099784851074 lr:1.2358329999220208e-05 tokens_per_second_per_gpu:5328.149757213333 mfu:25.13379148086483 Step 4881 | loss:1.2947609424591064 lr:1.2348904583917431e-05 tokens_per_second_per_gpu:5289.683173667105 mfu:24.952338043201355 Step 4882 | loss:1.3223228454589844 lr:1.2339481585253413e-05 tokens_per_second_per_gpu:5097.5226907555925 mfu:24.045884259348586 Step 4883 | loss:1.1327687501907349 lr:1.2330061005028124e-05 tokens_per_second_per_gpu:4771.862204651133 mfu:22.509688182985403 Step 4884 | loss:1.2642465829849243 lr:1.2320642845041102e-05 tokens_per_second_per_gpu:5267.595498900422 mfu:24.848146712781 Step 4885 | loss:1.2684706449508667 lr:1.2311227107091459e-05 tokens_per_second_per_gpu:3437.3629654116207 mfu:16.214627582443857 Step 4886 | loss:1.226682424545288 lr:1.230181379297777e-05 tokens_per_second_per_gpu:5065.761699207433 mfu:23.896062243231967 Step 4887 | loss:1.211578607559204 lr:1.2292402904498193e-05 tokens_per_second_per_gpu:5305.668253996523 mfu:25.02774239445116 Step 4888 | loss:1.277047872543335 lr:1.2282994443450441e-05 tokens_per_second_per_gpu:5218.497987075868 mfu:24.61654537260526 Step 4889 | loss:1.2481685876846313 lr:1.2273588411631711e-05 tokens_per_second_per_gpu:4213.082709363407 mfu:19.873829966100402 Step 4890 | loss:1.237977147102356 lr:1.2264184810838763e-05 tokens_per_second_per_gpu:4415.538556728748 mfu:20.828848740652187 Step 4891 | loss:1.2164041996002197 lr:1.2254783642867922e-05 tokens_per_second_per_gpu:4462.3311454845725 mfu:21.0495773654523 Step 4892 | loss:1.257615566253662 lr:1.2245384909514987e-05 tokens_per_second_per_gpu:5019.458865230616 mfu:23.677643875285217 Step 4893 | loss:1.0914207696914673 lr:1.2235988612575327e-05 tokens_per_second_per_gpu:5332.824645813096 mfu:25.155843728008154 Step 4894 | loss:1.2467453479766846 lr:1.2226594753843871e-05 tokens_per_second_per_gpu:4167.655463506293 mfu:19.659541896705022 Step 4895 | loss:1.2130987644195557 lr:1.2217203335115022e-05 tokens_per_second_per_gpu:5006.331104320855 mfu:23.6157179872469 Step 4896 | loss:1.2740392684936523 lr:1.2207814358182747e-05 tokens_per_second_per_gpu:4285.7818939573535 mfu:20.216764423589975 Step 4897 | loss:1.3412162065505981 lr:1.2198427824840583e-05 tokens_per_second_per_gpu:5336.384912940415 mfu:25.172638115491928 Step 4898 | loss:1.2669885158538818 lr:1.2189043736881534e-05 tokens_per_second_per_gpu:5327.9682436874 mfu:25.1329352505936 Step 4899 | loss:1.2393275499343872 lr:1.2179662096098165e-05 tokens_per_second_per_gpu:4414.546500925684 mfu:20.82416904416696 Step 4900 | loss:1.3773969411849976 lr:1.2170282904282607e-05 tokens_per_second_per_gpu:3890.7315004943425 mfu:18.353244315077497 Step 4901 | loss:1.215063452720642 lr:1.2160906163226456e-05 tokens_per_second_per_gpu:4627.293331619394 mfu:21.82773214290147 Step 4902 | loss:1.213841438293457 lr:1.2151531874720906e-05 tokens_per_second_per_gpu:5329.77721194137 mfu:25.141468462489392 Step 4903 | loss:1.21091890335083 lr:1.2142160040556652e-05 tokens_per_second_per_gpu:5292.946856121885 mfu:24.967733390182197 Step 4904 | loss:1.3686988353729248 lr:1.2132790662523894e-05 tokens_per_second_per_gpu:5027.091869254055 mfu:23.71365005758856 Step 4905 | loss:1.330654501914978 lr:1.2123423742412416e-05 tokens_per_second_per_gpu:4931.102735435276 mfu:23.260852935930362 Step 4906 | loss:1.2419326305389404 lr:1.2114059282011508e-05 tokens_per_second_per_gpu:4477.250598634915 mfu:21.11995497148366 Step 4907 | loss:1.3441388607025146 lr:1.210469728310996e-05 tokens_per_second_per_gpu:5340.191448141991 mfu:25.190594191499635 Step 4908 | loss:1.2454736232757568 lr:1.209533774749615e-05 tokens_per_second_per_gpu:3470.1541580859034 mfu:16.369309233042834 Step 4909 | loss:1.1980942487716675 lr:1.2085980676957955e-05 tokens_per_second_per_gpu:5315.066596269246 mfu:25.072075978474132 Step 4910 | loss:1.3042129278182983 lr:1.2076626073282756e-05 tokens_per_second_per_gpu:5303.350574435362 mfu:25.016809504524254 Step 4911 | loss:1.253931999206543 lr:1.2067273938257515e-05 tokens_per_second_per_gpu:5349.5526605580735 mfu:25.234752627653833 Step 4912 | loss:1.3639339208602905 lr:1.2057924273668697e-05 tokens_per_second_per_gpu:3643.1033125053677 mfu:17.185139902607975 Step 4913 | loss:1.226728916168213 lr:1.2048577081302268e-05 tokens_per_second_per_gpu:4092.7970854759405 mfu:19.30642215537954 Step 4914 | loss:1.3629968166351318 lr:1.2039232362943776e-05 tokens_per_second_per_gpu:3628.2917772103324 mfu:17.115271363512786 Step 4915 | loss:1.3805781602859497 lr:1.2029890120378265e-05 tokens_per_second_per_gpu:3889.141238823444 mfu:18.345742779449246 Step 4916 | loss:1.259681224822998 lr:1.2020550355390284e-05 tokens_per_second_per_gpu:4881.626150989796 mfu:23.027463445525257 Step 4917 | loss:1.3808808326721191 lr:1.2011213069763966e-05 tokens_per_second_per_gpu:4366.80281134096 mfu:20.598953914482394 Step 4918 | loss:1.2523161172866821 lr:1.2001878265282934e-05 tokens_per_second_per_gpu:4317.0179118398155 mfu:20.364110049355748 Step 4919 | loss:1.2078005075454712 lr:1.1992545943730312e-05 tokens_per_second_per_gpu:3941.5062713767547 mfu:18.592757572399055 Step 4920 | loss:1.1595476865768433 lr:1.1983216106888817e-05 tokens_per_second_per_gpu:4080.637299058251 mfu:19.2490623681738 Step 4921 | loss:1.2885500192642212 lr:1.1973888756540646e-05 tokens_per_second_per_gpu:4691.643731631254 mfu:22.13128395906781 Step 4922 | loss:1.180212378501892 lr:1.1964563894467503e-05 tokens_per_second_per_gpu:4699.070592819686 mfu:22.166317730446828 Step 4923 | loss:1.1544395685195923 lr:1.195524152245067e-05 tokens_per_second_per_gpu:5143.835411891049 mfu:24.264349266709566 Step 4924 | loss:1.2774553298950195 lr:1.1945921642270928e-05 tokens_per_second_per_gpu:4819.161702720996 mfu:22.73280798550748 Step 4925 | loss:1.235254168510437 lr:1.193660425570855e-05 tokens_per_second_per_gpu:5281.747981993555 mfu:24.914906390193913 Step 4926 | loss:1.4615415334701538 lr:1.1927289364543392e-05 tokens_per_second_per_gpu:4637.103175925216 mfu:21.87400685222407 Step 4927 | loss:1.2628273963928223 lr:1.1917976970554803e-05 tokens_per_second_per_gpu:4059.757544211421 mfu:19.150569002107776 Step 4928 | loss:1.27186119556427 lr:1.1908667075521628e-05 tokens_per_second_per_gpu:4553.206052031707 mfu:21.478249804493004 Step 4929 | loss:1.2378484010696411 lr:1.1899359681222293e-05 tokens_per_second_per_gpu:4154.798571359065 mfu:19.59889374283455 Step 4930 | loss:1.5041871070861816 lr:1.1890054789434716e-05 tokens_per_second_per_gpu:4022.115079363752 mfu:18.973003072954555 Step 4931 | loss:1.18775475025177 lr:1.1880752401936304e-05 tokens_per_second_per_gpu:5209.175568541636 mfu:24.57256993381067 Step 4932 | loss:1.2105897665023804 lr:1.187145252050405e-05 tokens_per_second_per_gpu:4234.086174635835 mfu:19.97290689535114 Step 4933 | loss:1.2980680465698242 lr:1.186215514691444e-05 tokens_per_second_per_gpu:5325.949475877075 mfu:25.123412378394992 Step 4934 | loss:1.331796646118164 lr:1.185286028294344e-05 tokens_per_second_per_gpu:4273.785343487153 mfu:20.160174648199465 Step 4935 | loss:1.5271307229995728 lr:1.1843567930366611e-05 tokens_per_second_per_gpu:3864.6166637650094 mfu:18.23005617457463 Step 4936 | loss:1.4066160917282104 lr:1.1834278090958997e-05 tokens_per_second_per_gpu:3385.2191310815933 mfu:15.968656219253589 Step 4937 | loss:1.3361999988555908 lr:1.1824990766495134e-05 tokens_per_second_per_gpu:5356.830179061349 mfu:25.269081924106477 Step 4938 | loss:1.1819416284561157 lr:1.1815705958749129e-05 tokens_per_second_per_gpu:3794.063870386194 mfu:17.89724661065894 Step 4939 | loss:1.191088318824768 lr:1.1806423669494593e-05 tokens_per_second_per_gpu:4361.566147005982 mfu:20.574251675347234 Step 4940 | loss:1.3146190643310547 lr:1.1797143900504614e-05 tokens_per_second_per_gpu:5166.136760688655 mfu:24.369548533990336 Step 4941 | loss:1.2232496738433838 lr:1.1787866653551865e-05 tokens_per_second_per_gpu:4706.873600355691 mfu:22.203125848324532 Step 4942 | loss:1.317899227142334 lr:1.1778591930408502e-05 tokens_per_second_per_gpu:4421.4227075020435 mfu:20.856605283789467 Step 4943 | loss:1.1937922239303589 lr:1.1769319732846178e-05 tokens_per_second_per_gpu:4613.326956885284 mfu:21.76185037037143 Step 4944 | loss:1.1490983963012695 lr:1.1760050062636114e-05 tokens_per_second_per_gpu:5340.144373543088 mfu:25.190372132584855 Step 4945 | loss:1.2343472242355347 lr:1.175078292154902e-05 tokens_per_second_per_gpu:4720.297434064669 mfu:22.266448362271984 Step 4946 | loss:1.3514865636825562 lr:1.1741518311355098e-05 tokens_per_second_per_gpu:4541.283462533815 mfu:21.422008915627917 Step 4947 | loss:1.280870795249939 lr:1.1732256233824122e-05 tokens_per_second_per_gpu:5326.3452024909275 mfu:25.12527908835046 Step 4948 | loss:1.2554278373718262 lr:1.1722996690725351e-05 tokens_per_second_per_gpu:5336.799307690243 mfu:25.174592886229902 Step 4949 | loss:1.3482407331466675 lr:1.1713739683827538e-05 tokens_per_second_per_gpu:4729.756774845709 mfu:22.31106968666611 Step 4950 | loss:1.28589928150177 lr:1.1704485214899008e-05 tokens_per_second_per_gpu:3891.553868089511 mfu:18.357123563334284 Step 4951 | loss:1.1642091274261475 lr:1.1695233285707547e-05 tokens_per_second_per_gpu:4287.20169393928 mfu:20.223461862347577 Step 4952 | loss:1.1952341794967651 lr:1.1685983898020475e-05 tokens_per_second_per_gpu:4544.284073047412 mfu:21.436163307377498 Step 4953 | loss:1.3374271392822266 lr:1.1676737053604655e-05 tokens_per_second_per_gpu:4274.743670005644 mfu:20.164695237894552 Step 4954 | loss:1.2636348009109497 lr:1.1667492754226416e-05 tokens_per_second_per_gpu:5331.48170406905 mfu:25.149508842671995 Step 4955 | loss:1.326585292816162 lr:1.1658251001651618e-05 tokens_per_second_per_gpu:4507.647466294862 mfu:21.26334218247604 Step 4956 | loss:1.2174686193466187 lr:1.1649011797645673e-05 tokens_per_second_per_gpu:5311.6913937907875 mfu:25.05615457251432 Step 4957 | loss:1.1713707447052002 lr:1.163977514397344e-05 tokens_per_second_per_gpu:5332.062567346281 mfu:25.152248873856195 Step 4958 | loss:1.4106756448745728 lr:1.1630541042399329e-05 tokens_per_second_per_gpu:4315.499467328651 mfu:20.356947287523237 Step 4959 | loss:1.2517528533935547 lr:1.162130949468728e-05 tokens_per_second_per_gpu:4063.926323428503 mfu:19.170233844941833 Step 4960 | loss:1.3040558099746704 lr:1.16120805026007e-05 tokens_per_second_per_gpu:4889.887769507737 mfu:23.066434909651854 Step 4961 | loss:1.3045248985290527 lr:1.1602854067902524e-05 tokens_per_second_per_gpu:5181.722117757992 mfu:24.443067322422515 Step 4962 | loss:1.24472177028656 lr:1.159363019235524e-05 tokens_per_second_per_gpu:5333.037323915895 mfu:25.156846966905682 Step 4963 | loss:1.275758981704712 lr:1.1584408877720782e-05 tokens_per_second_per_gpu:3968.6192075909485 mfu:18.720653918465334 Step 4964 | loss:1.23025381565094 lr:1.1575190125760621e-05 tokens_per_second_per_gpu:4276.47367518661 mfu:20.172855967502493 Step 4965 | loss:1.2908552885055542 lr:1.1565973938235772e-05 tokens_per_second_per_gpu:4801.8214688472335 mfu:22.65101114377597 Step 4966 | loss:1.1686360836029053 lr:1.1556760316906696e-05 tokens_per_second_per_gpu:5335.253582684064 mfu:25.167301437647875 Step 4967 | loss:1.357710838317871 lr:1.1547549263533422e-05 tokens_per_second_per_gpu:5321.8564816897615 mfu:25.104105026476613 Step 4968 | loss:1.1565827131271362 lr:1.153834077987547e-05 tokens_per_second_per_gpu:4910.352478351918 mfu:23.16297043290923 Step 4969 | loss:1.13090980052948 lr:1.152913486769183e-05 tokens_per_second_per_gpu:3605.799963750497 mfu:17.009173641923656 Step 4970 | loss:1.4141796827316284 lr:1.1519931528741065e-05 tokens_per_second_per_gpu:3391.7547383504375 mfu:15.999485793830312 Step 4971 | loss:1.2782281637191772 lr:1.1510730764781218e-05 tokens_per_second_per_gpu:5329.221598125703 mfu:25.138847537323397 Step 4972 | loss:1.341182827949524 lr:1.1501532577569809e-05 tokens_per_second_per_gpu:4482.237705322031 mfu:21.143480004614926 Step 4973 | loss:1.2928770780563354 lr:1.149233696886392e-05 tokens_per_second_per_gpu:4927.859089976105 mfu:23.245552106876467 Step 4974 | loss:1.2204383611679077 lr:1.1483143940420122e-05 tokens_per_second_per_gpu:5193.657897016627 mfu:24.499370429639434 Step 4975 | loss:1.2451237440109253 lr:1.1473953493994452e-05 tokens_per_second_per_gpu:5308.91174026726 mfu:25.043042472586045 Step 4976 | loss:1.2823188304901123 lr:1.146476563134252e-05 tokens_per_second_per_gpu:4513.090878289475 mfu:21.289019685596486 Step 4977 | loss:1.1641371250152588 lr:1.1455580354219408e-05 tokens_per_second_per_gpu:5315.125543465235 mfu:25.072354042455043 Step 4978 | loss:1.4934282302856445 lr:1.1446397664379682e-05 tokens_per_second_per_gpu:4360.530894422235 mfu:20.5693682122774 Step 4979 | loss:1.247943639755249 lr:1.1437217563577465e-05 tokens_per_second_per_gpu:4888.234820979983 mfu:23.05863766942434 Step 4980 | loss:1.2555080652236938 lr:1.1428040053566358e-05 tokens_per_second_per_gpu:4136.91229963494 mfu:19.514521147399215 Step 4981 | loss:1.2179921865463257 lr:1.1418865136099444e-05 tokens_per_second_per_gpu:4041.758925938557 mfu:19.06566644883374 Step 4982 | loss:1.3392709493637085 lr:1.1409692812929356e-05 tokens_per_second_per_gpu:4334.624383745507 mfu:20.44716278130876 Step 4983 | loss:1.4173823595046997 lr:1.140052308580822e-05 tokens_per_second_per_gpu:5340.061223414296 mfu:25.189979899240473 Step 4984 | loss:1.3761941194534302 lr:1.139135595648762e-05 tokens_per_second_per_gpu:5292.762260502932 mfu:24.966862621152337 Step 4985 | loss:1.2017409801483154 lr:1.1382191426718713e-05 tokens_per_second_per_gpu:5204.719434152601 mfu:24.551549587602665 Step 4986 | loss:1.4118667840957642 lr:1.1373029498252124e-05 tokens_per_second_per_gpu:5312.67088334299 mfu:25.060774991850213 Step 4987 | loss:1.2466163635253906 lr:1.1363870172837957e-05 tokens_per_second_per_gpu:4278.624153478028 mfu:20.183000140512544 Step 4988 | loss:1.107847809791565 lr:1.1354713452225873e-05 tokens_per_second_per_gpu:4903.047169963942 mfu:23.12851004682901 Step 4989 | loss:1.1267668008804321 lr:1.134555933816501e-05 tokens_per_second_per_gpu:5313.37963695054 mfu:25.06411830354286 Step 4990 | loss:1.4717562198638916 lr:1.1336407832403975e-05 tokens_per_second_per_gpu:4170.606187076939 mfu:19.673460963233115 Step 4991 | loss:1.3547793626785278 lr:1.1327258936690938e-05 tokens_per_second_per_gpu:5340.335782998054 mfu:25.191275043641753 Step 4992 | loss:1.2215571403503418 lr:1.1318112652773537e-05 tokens_per_second_per_gpu:4781.696930007316 mfu:22.55608026046769 Step 4993 | loss:1.2511942386627197 lr:1.1308968982398892e-05 tokens_per_second_per_gpu:4443.623822069976 mfu:20.961331729107147 Step 4994 | loss:1.276186466217041 lr:1.129982792731367e-05 tokens_per_second_per_gpu:4734.747534654533 mfu:22.33461195219576 Step 4995 | loss:1.3039332628250122 lr:1.1290689489264015e-05 tokens_per_second_per_gpu:3944.8832443939245 mfu:18.608687330292053 Step 4996 | loss:1.3678652048110962 lr:1.1281553669995543e-05 tokens_per_second_per_gpu:4668.079121850132 mfu:22.020125674193242 Step 4997 | loss:1.3766635656356812 lr:1.1272420471253425e-05 tokens_per_second_per_gpu:4412.472599466848 mfu:20.814386097141554 Step 4998 | loss:1.3659775257110596 lr:1.1263289894782303e-05 tokens_per_second_per_gpu:4509.92191585824 mfu:21.274071149127604 Step 4999 | loss:1.154418706893921 lr:1.1254161942326291e-05 tokens_per_second_per_gpu:4629.636818020791 mfu:21.838786768096874 Step 5000 | loss:1.2896260023117065 lr:1.1245036615629062e-05 tokens_per_second_per_gpu:5315.929487099829 mfu:25.076146381746355 Step 5001 | loss:1.3211379051208496 lr:1.1235913916433749e-05 tokens_per_second_per_gpu:3918.775192028724 mfu:18.485531192792337 Step 5002 | loss:1.337033748626709 lr:1.1226793846482964e-05 tokens_per_second_per_gpu:3589.3341897825153 mfu:16.931501776765955 Step 5003 | loss:1.0502113103866577 lr:1.1217676407518868e-05 tokens_per_second_per_gpu:4514.262525548952 mfu:21.294546545623074 Step 5004 | loss:1.1878578662872314 lr:1.1208561601283097e-05 tokens_per_second_per_gpu:4467.031361895405 mfu:21.071749088201813 Step 5005 | loss:1.2406898736953735 lr:1.1199449429516747e-05 tokens_per_second_per_gpu:5353.525607774204 mfu:25.253493697527013 Step 5006 | loss:1.2572232484817505 lr:1.1190339893960477e-05 tokens_per_second_per_gpu:5241.36443267297 mfu:24.724410297904708 Step 5007 | loss:1.308849811553955 lr:1.1181232996354407e-05 tokens_per_second_per_gpu:5334.023926203815 mfu:25.16150093822951 Step 5008 | loss:1.1843435764312744 lr:1.1172128738438129e-05 tokens_per_second_per_gpu:4055.094102674958 mfu:19.128570752715106 Step 5009 | loss:1.1348580121994019 lr:1.1163027121950784e-05 tokens_per_second_per_gpu:4099.264270277604 mfu:19.336928969504488 Step 5010 | loss:1.1232833862304688 lr:1.1153928148630982e-05 tokens_per_second_per_gpu:5321.803116324921 mfu:25.103853292945594 Step 5011 | loss:1.2504881620407104 lr:1.1144831820216803e-05 tokens_per_second_per_gpu:5135.342755122186 mfu:24.224287955734177 Step 5012 | loss:1.1714844703674316 lr:1.113573813844587e-05 tokens_per_second_per_gpu:4369.44128459541 mfu:20.611400042993594 Step 5013 | loss:1.399938702583313 lr:1.112664710505528e-05 tokens_per_second_per_gpu:5188.271230768585 mfu:24.473960605887385 Step 5014 | loss:1.37897789478302 lr:1.1117558721781593e-05 tokens_per_second_per_gpu:5068.57349496193 mfu:23.909325963547758 Step 5015 | loss:1.3987116813659668 lr:1.1108472990360919e-05 tokens_per_second_per_gpu:3671.9217879941875 mfu:17.321081568427676 Step 5016 | loss:1.2633395195007324 lr:1.1099389912528832e-05 tokens_per_second_per_gpu:4455.123171109874 mfu:21.015576120519608 Step 5017 | loss:1.3205565214157104 lr:1.1090309490020374e-05 tokens_per_second_per_gpu:5349.959998407194 mfu:25.23667410978714 Step 5018 | loss:1.2491250038146973 lr:1.1081231724570131e-05 tokens_per_second_per_gpu:5341.716017893048 mfu:25.197785847133797 Step 5019 | loss:1.4032785892486572 lr:1.1072156617912163e-05 tokens_per_second_per_gpu:3009.3896102483104 mfu:14.195804246354573 Step 5020 | loss:1.3515732288360596 lr:1.1063084171779983e-05 tokens_per_second_per_gpu:4310.035126110968 mfu:20.331171057686678 Step 5021 | loss:1.2653347253799438 lr:1.105401438790666e-05 tokens_per_second_per_gpu:4660.192017816137 mfu:21.98292085878618 Step 5022 | loss:1.2053477764129639 lr:1.1044947268024721e-05 tokens_per_second_per_gpu:4636.084332502789 mfu:21.869200793967863 Step 5023 | loss:1.2352043390274048 lr:1.1035882813866157e-05 tokens_per_second_per_gpu:5327.843771324362 mfu:25.132348093219974 Step 5024 | loss:1.2135072946548462 lr:1.102682102716251e-05 tokens_per_second_per_gpu:3568.168170505451 mfu:16.83165805254077 Step 5025 | loss:1.383115530014038 lr:1.101776190964478e-05 tokens_per_second_per_gpu:5304.098249462272 mfu:25.0203364151927 Step 5026 | loss:1.3781170845031738 lr:1.1008705463043428e-05 tokens_per_second_per_gpu:4850.084370932082 mfu:22.878675487410412 Step 5027 | loss:1.328688144683838 lr:1.0999651689088469e-05 tokens_per_second_per_gpu:4117.979533378527 mfu:19.425212058704695 Step 5028 | loss:1.2942967414855957 lr:1.099060058950937e-05 tokens_per_second_per_gpu:4547.942958737141 mfu:21.45342289544622 Step 5029 | loss:1.207563042640686 lr:1.0981552166035063e-05 tokens_per_second_per_gpu:3561.6475218133896 mfu:16.80089904012293 Step 5030 | loss:1.0817251205444336 lr:1.0972506420394027e-05 tokens_per_second_per_gpu:5331.81554036057 mfu:25.151083605417444 Step 5031 | loss:1.2392361164093018 lr:1.0963463354314197e-05 tokens_per_second_per_gpu:4145.438471585725 mfu:19.55474055520601 Step 5032 | loss:1.2051398754119873 lr:1.0954422969522973e-05 tokens_per_second_per_gpu:5309.395370353742 mfu:25.045323838219783 Step 5033 | loss:1.2862167358398438 lr:1.0945385267747293e-05 tokens_per_second_per_gpu:5302.840519564601 mfu:25.01440348867454 Step 5034 | loss:1.1749886274337769 lr:1.093635025071355e-05 tokens_per_second_per_gpu:4860.304289471375 mfu:22.926884586858165 Step 5035 | loss:1.1709370613098145 lr:1.0927317920147631e-05 tokens_per_second_per_gpu:4254.770130560805 mfu:20.07047664449601 Step 5036 | loss:1.214748740196228 lr:1.0918288277774913e-05 tokens_per_second_per_gpu:5344.522279567859 mfu:25.211023462251493 Step 5037 | loss:1.1425541639328003 lr:1.0909261325320255e-05 tokens_per_second_per_gpu:5297.610112391597 mfu:24.98973076563999 Step 5038 | loss:1.0974292755126953 lr:1.0900237064508007e-05 tokens_per_second_per_gpu:4828.5779225028455 mfu:22.777225900791226 Step 5039 | loss:1.5251188278198242 lr:1.0891215497062e-05 tokens_per_second_per_gpu:4864.70043015269 mfu:22.94762193251087 Step 5040 | loss:1.1198196411132812 lr:1.0882196624705552e-05 tokens_per_second_per_gpu:5358.72144313292 mfu:25.278003339415005 Step 5041 | loss:1.2876993417739868 lr:1.0873180449161467e-05 tokens_per_second_per_gpu:4713.167543999562 mfu:22.23281545435019 Step 5042 | loss:1.3296936750411987 lr:1.0864166972152035e-05 tokens_per_second_per_gpu:3777.6977536349887 mfu:17.820044845596048 Step 5043 | loss:1.3163604736328125 lr:1.085515619539903e-05 tokens_per_second_per_gpu:4403.263290002748 mfu:20.770944213129177 Step 5044 | loss:1.2565934658050537 lr:1.0846148120623706e-05 tokens_per_second_per_gpu:5284.504203132799 mfu:24.927907955567548 Step 5045 | loss:1.3355967998504639 lr:1.0837142749546809e-05 tokens_per_second_per_gpu:4562.560969615479 mfu:21.522378546849176 Step 5046 | loss:1.3730319738388062 lr:1.082814008388856e-05 tokens_per_second_per_gpu:3909.495718883268 mfu:18.441758334723843 Step 5047 | loss:1.3101825714111328 lr:1.0819140125368668e-05 tokens_per_second_per_gpu:4681.364056404349 mfu:22.082792977129053 Step 5048 | loss:1.4507746696472168 lr:1.0810142875706327e-05 tokens_per_second_per_gpu:5300.244882694555 mfu:25.00215942669721 Step 5049 | loss:1.2196550369262695 lr:1.0801148336620206e-05 tokens_per_second_per_gpu:4904.2612237285575 mfu:23.134236945575637 Step 5050 | loss:1.2475309371948242 lr:1.0792156509828463e-05 tokens_per_second_per_gpu:3615.772647779618 mfu:17.05621649400437 Step 5051 | loss:1.417500376701355 lr:1.0783167397048735e-05 tokens_per_second_per_gpu:3668.6305264116854 mfu:17.30555612599588 Step 5052 | loss:1.2187983989715576 lr:1.0774180999998142e-05 tokens_per_second_per_gpu:4522.80844407765 mfu:21.334859101406998 Step 5053 | loss:1.2492856979370117 lr:1.0765197320393284e-05 tokens_per_second_per_gpu:4296.354103701568 mfu:20.26663534075842 Step 5054 | loss:1.0719375610351562 lr:1.0756216359950242e-05 tokens_per_second_per_gpu:5314.777596002007 mfu:25.07071271490504 Step 5055 | loss:1.2648991346359253 lr:1.0747238120384576e-05 tokens_per_second_per_gpu:5325.446007929992 mfu:25.121037434188114 Step 5056 | loss:1.0979479551315308 lr:1.0738262603411331e-05 tokens_per_second_per_gpu:5305.386431556172 mfu:25.026412989916157 Step 5057 | loss:1.1010944843292236 lr:1.0729289810745028e-05 tokens_per_second_per_gpu:5300.284562018515 mfu:25.002346600838326 Step 5058 | loss:1.1687206029891968 lr:1.0720319744099669e-05 tokens_per_second_per_gpu:3450.2030853523256 mfu:16.275196618954528 Step 5059 | loss:1.4247924089431763 lr:1.0711352405188735e-05 tokens_per_second_per_gpu:4491.081485123598 mfu:21.185197622843344 Step 5060 | loss:1.171700119972229 lr:1.0702387795725186e-05 tokens_per_second_per_gpu:4364.98764013015 mfu:20.590391442180856 Step 5061 | loss:1.1688324213027954 lr:1.0693425917421456e-05 tokens_per_second_per_gpu:4952.838322398815 mfu:23.363383408110916 Step 5062 | loss:1.2757645845413208 lr:1.0684466771989471e-05 tokens_per_second_per_gpu:3980.826987985254 mfu:18.778240101447388 Step 5063 | loss:1.2046208381652832 lr:1.0675510361140617e-05 tokens_per_second_per_gpu:4739.078037725639 mfu:22.35503967404218 Step 5064 | loss:1.3205699920654297 lr:1.0666556686585771e-05 tokens_per_second_per_gpu:3347.902715504807 mfu:15.792628320140864 Step 5065 | loss:1.2566031217575073 lr:1.0657605750035279e-05 tokens_per_second_per_gpu:4874.276707437896 mfu:22.99279486634657 Step 5066 | loss:1.1958324909210205 lr:1.0648657553198974e-05 tokens_per_second_per_gpu:3662.0916550071784 mfu:17.27471115393432 Step 5067 | loss:1.2245707511901855 lr:1.0639712097786153e-05 tokens_per_second_per_gpu:4454.220785716233 mfu:21.011319414654977 Step 5068 | loss:1.3427608013153076 lr:1.06307693855056e-05 tokens_per_second_per_gpu:4210.102284867479 mfu:19.859770795240255 Step 5069 | loss:1.229000210762024 lr:1.0621829418065566e-05 tokens_per_second_per_gpu:5302.40705708917 mfu:25.012358772221607 Step 5070 | loss:1.3043714761734009 lr:1.0612892197173787e-05 tokens_per_second_per_gpu:4959.549016691394 mfu:23.395038898051524 Step 5071 | loss:1.1224181652069092 lr:1.0603957724537466e-05 tokens_per_second_per_gpu:3575.93799489437 mfu:16.86830963985204 Step 5072 | loss:1.0991435050964355 lr:1.0595026001863287e-05 tokens_per_second_per_gpu:4259.785900869984 mfu:20.09413688882307 Step 5073 | loss:1.3750970363616943 lr:1.0586097030857405e-05 tokens_per_second_per_gpu:3783.5441693923804 mfu:17.84762338622505 Step 5074 | loss:1.2746467590332031 lr:1.057717081322545e-05 tokens_per_second_per_gpu:4972.124984870208 mfu:23.454361885632416 Step 5075 | loss:1.2496012449264526 lr:1.0568247350672533e-05 tokens_per_second_per_gpu:3719.403123357452 mfu:17.54505912848737 Step 5076 | loss:1.3555554151535034 lr:1.0559326644903225e-05 tokens_per_second_per_gpu:4039.1356064959814 mfu:19.05329180343866 Step 5077 | loss:1.2040687799453735 lr:1.0550408697621579e-05 tokens_per_second_per_gpu:5316.786423520788 mfu:25.080188697052446 Step 5078 | loss:1.398459553718567 lr:1.0541493510531123e-05 tokens_per_second_per_gpu:4370.152265438039 mfu:20.614753860934112 Step 5079 | loss:1.2834115028381348 lr:1.0532581085334852e-05 tokens_per_second_per_gpu:4301.341486391892 mfu:20.290161675843912 Step 5080 | loss:1.3607121706008911 lr:1.0523671423735238e-05 tokens_per_second_per_gpu:3917.0456063129227 mfu:18.477372441873147 Step 5081 | loss:1.1801552772521973 lr:1.0514764527434222e-05 tokens_per_second_per_gpu:5144.793235635947 mfu:24.26886748473583 Step 5082 | loss:1.1586333513259888 lr:1.0505860398133222e-05 tokens_per_second_per_gpu:3298.0046458221236 mfu:15.557250611959073 Step 5083 | loss:1.3142757415771484 lr:1.0496959037533117e-05 tokens_per_second_per_gpu:3910.292817983597 mfu:18.445518387179224 Step 5084 | loss:1.1700828075408936 lr:1.0488060447334267e-05 tokens_per_second_per_gpu:4744.791558562414 mfu:22.381991326656426 Step 5085 | loss:1.4281682968139648 lr:1.0479164629236497e-05 tokens_per_second_per_gpu:4067.5738612203436 mfu:19.187439903040065 Step 5086 | loss:1.3624943494796753 lr:1.047027158493911e-05 tokens_per_second_per_gpu:4662.258029615533 mfu:21.992666588941894 Step 5087 | loss:1.0779801607131958 lr:1.0461381316140867e-05 tokens_per_second_per_gpu:4152.060713012165 mfu:19.585978797885424 Step 5088 | loss:1.3046162128448486 lr:1.045249382454001e-05 tokens_per_second_per_gpu:5190.428279048689 mfu:24.484135770655023 Step 5089 | loss:1.2599514722824097 lr:1.0443609111834245e-05 tokens_per_second_per_gpu:4527.817593377985 mfu:21.358488113305675 Step 5090 | loss:1.2846829891204834 lr:1.0434727179720751e-05 tokens_per_second_per_gpu:3563.0317019327676 mfu:16.807428453911516 Step 5091 | loss:1.4085248708724976 lr:1.0425848029896174e-05 tokens_per_second_per_gpu:5359.025056875342 mfu:25.279435537239852 Step 5092 | loss:1.192888617515564 lr:1.0416971664056622e-05 tokens_per_second_per_gpu:4547.906086581646 mfu:21.453248963197716 Step 5093 | loss:1.3263733386993408 lr:1.040809808389768e-05 tokens_per_second_per_gpu:5239.115185703674 mfu:24.713800216189437 Step 5094 | loss:1.2876274585723877 lr:1.0399227291114396e-05 tokens_per_second_per_gpu:3622.186883951389 mfu:17.086473540408154 Step 5095 | loss:1.3307431936264038 lr:1.0390359287401292e-05 tokens_per_second_per_gpu:4264.828249460312 mfu:20.117922507437026 Step 5096 | loss:1.4530200958251953 lr:1.038149407445235e-05 tokens_per_second_per_gpu:5302.866970741595 mfu:25.01452826338945 Step 5097 | loss:1.3787050247192383 lr:1.037263165396102e-05 tokens_per_second_per_gpu:4606.25990328717 mfu:21.72851387278545 Step 5098 | loss:1.4192191362380981 lr:1.0363772027620222e-05 tokens_per_second_per_gpu:4931.326740287103 mfu:23.2619096050356 Step 5099 | loss:1.1392149925231934 lr:1.0354915197122342e-05 tokens_per_second_per_gpu:5037.907242057972 mfu:23.76466801639752 Step 5100 | loss:1.1973282098770142 lr:1.0346061164159226e-05 tokens_per_second_per_gpu:5098.630611203838 mfu:24.051110509133682 Step 5101 | loss:1.2574161291122437 lr:1.0337209930422192e-05 tokens_per_second_per_gpu:4659.213012156683 mfu:21.97830272205495 Step 5102 | loss:1.3545969724655151 lr:1.0328361497602023e-05 tokens_per_second_per_gpu:3926.5145372253287 mfu:18.52203900455317 Step 5103 | loss:1.1895564794540405 lr:1.0319515867388964e-05 tokens_per_second_per_gpu:5331.300441689328 mfu:25.148653797100298 Step 5104 | loss:1.235813856124878 lr:1.0310673041472724e-05 tokens_per_second_per_gpu:3971.832771768053 mfu:18.735812848979325 Step 5105 | loss:1.0720504522323608 lr:1.0301833021542481e-05 tokens_per_second_per_gpu:5323.487587575075 mfu:25.111799231233004 Step 5106 | loss:1.271085262298584 lr:1.0292995809286871e-05 tokens_per_second_per_gpu:5308.026705136153 mfu:25.038867610870053 Step 5107 | loss:1.2111798524856567 lr:1.0284161406394e-05 tokens_per_second_per_gpu:4297.604050171522 mfu:20.272531551520053 Step 5108 | loss:1.3034827709197998 lr:1.0275329814551432e-05 tokens_per_second_per_gpu:4471.56495219091 mfu:21.09313480713597 Step 5109 | loss:1.4916164875030518 lr:1.0266501035446196e-05 tokens_per_second_per_gpu:3613.8817190279196 mfu:17.047296660456897 Step 5110 | loss:1.3725568056106567 lr:1.0257675070764785e-05 tokens_per_second_per_gpu:3707.173840004084 mfu:17.48737151237864 Step 5111 | loss:1.200312614440918 lr:1.0248851922193154e-05 tokens_per_second_per_gpu:4864.994966545179 mfu:22.94901131092733 Step 5112 | loss:1.274376392364502 lr:1.0240031591416718e-05 tokens_per_second_per_gpu:4812.797862559055 mfu:22.702788665680515 Step 5113 | loss:1.3193572759628296 lr:1.0231214080120355e-05 tokens_per_second_per_gpu:4047.381063677151 mfu:19.092187031782302 Step 5114 | loss:1.3071043491363525 lr:1.0222399389988402e-05 tokens_per_second_per_gpu:4461.10585944508 mfu:21.043797482148655 Step 5115 | loss:1.2374340295791626 lr:1.0213587522704665e-05 tokens_per_second_per_gpu:3925.135511281428 mfu:18.515533903889708 Step 5116 | loss:1.4181407690048218 lr:1.0204778479952404e-05 tokens_per_second_per_gpu:4785.194201435774 mfu:22.57257748649176 Step 5117 | loss:1.2616761922836304 lr:1.0195972263414336e-05 tokens_per_second_per_gpu:4735.172405277629 mfu:22.33661613941531 Step 5118 | loss:1.076154351234436 lr:1.0187168874772648e-05 tokens_per_second_per_gpu:3827.1282569249443 mfu:18.053216963328286 Step 5119 | loss:1.3190170526504517 lr:1.0178368315708981e-05 tokens_per_second_per_gpu:4961.29067446772 mfu:23.40325459493991 Step 5120 | loss:1.2764091491699219 lr:1.0169570587904433e-05 tokens_per_second_per_gpu:3524.398879591465 mfu:16.62519083948841 Step 5121 | loss:1.2019176483154297 lr:1.016077569303957e-05 tokens_per_second_per_gpu:4019.415671855161 mfu:18.960269507170118 Step 5122 | loss:1.199872374534607 lr:1.0151983632794407e-05 tokens_per_second_per_gpu:5317.1969763623365 mfu:25.082125344853566 Step 5123 | loss:1.2419015169143677 lr:1.014319440884842e-05 tokens_per_second_per_gpu:3549.6509788527205 mfu:16.74430930015616 Step 5124 | loss:1.4159849882125854 lr:1.0134408022880551e-05 tokens_per_second_per_gpu:3554.165833098577 mfu:16.765606637947435 Step 5125 | loss:1.4953014850616455 lr:1.0125624476569187e-05 tokens_per_second_per_gpu:4277.23846753831 mfu:20.17646362351249 Step 5126 | loss:1.3582782745361328 lr:1.0116843771592185e-05 tokens_per_second_per_gpu:3562.963778837209 mfu:16.807108049080888 Step 5127 | loss:1.232641577720642 lr:1.010806590962685e-05 tokens_per_second_per_gpu:5298.541611005311 mfu:24.994124803530937 Step 5128 | loss:1.3356046676635742 lr:1.0099290892349953e-05 tokens_per_second_per_gpu:4083.303691467964 mfu:19.261640196103876 Step 5129 | loss:1.193487524986267 lr:1.009051872143771e-05 tokens_per_second_per_gpu:5230.490275398534 mfu:24.67311504271865 Step 5130 | loss:1.349886178970337 lr:1.0081749398565801e-05 tokens_per_second_per_gpu:4080.9740236737553 mfu:19.250650755636276 Step 5131 | loss:1.2020604610443115 lr:1.0072982925409364e-05 tokens_per_second_per_gpu:4996.322949633193 mfu:23.568507814017934 Step 5132 | loss:1.3285564184188843 lr:1.0064219303642983e-05 tokens_per_second_per_gpu:4881.957048190283 mfu:23.029024344076838 Step 5133 | loss:1.127339243888855 lr:1.0055458534940706e-05 tokens_per_second_per_gpu:4153.0504450040125 mfu:19.59064753255666 Step 5134 | loss:1.1899248361587524 lr:1.0046700620976039e-05 tokens_per_second_per_gpu:5112.765321818698 mfu:24.117786350734285 Step 5135 | loss:1.3120616674423218 lr:1.0037945563421928e-05 tokens_per_second_per_gpu:5342.751844091491 mfu:25.202672016042023 Step 5136 | loss:1.3531569242477417 lr:1.0029193363950787e-05 tokens_per_second_per_gpu:4147.981975262742 mfu:19.566738696016976 Step 5137 | loss:1.329753041267395 lr:1.0020444024234477e-05 tokens_per_second_per_gpu:4730.928402153393 mfu:22.316596452576686 Step 5138 | loss:1.2016823291778564 lr:1.0011697545944322e-05 tokens_per_second_per_gpu:5319.463421147424 mfu:25.092816551600176 Step 5139 | loss:1.1744424104690552 lr:1.0002953930751082e-05 tokens_per_second_per_gpu:4440.905783717037 mfu:20.948510278451167 Step 5140 | loss:1.3005597591400146 lr:9.99421318032499e-06 tokens_per_second_per_gpu:5315.869147070587 mfu:25.075861747533345 Step 5141 | loss:1.3259494304656982 lr:9.98547529633572e-06 tokens_per_second_per_gpu:5340.831265151086 mfu:25.193612317495575 Step 5142 | loss:1.2015116214752197 lr:9.976740280452399e-06 tokens_per_second_per_gpu:3914.580838804813 mfu:18.465745713004697 Step 5143 | loss:1.3837342262268066 lr:9.968008134343607e-06 tokens_per_second_per_gpu:4133.174685614417 mfu:19.4968901843617 Step 5144 | loss:1.2038699388504028 lr:9.959278859677378e-06 tokens_per_second_per_gpu:5328.160420815647 mfu:25.13384178289634 Step 5145 | loss:1.117342472076416 lr:9.950552458121201e-06 tokens_per_second_per_gpu:5300.7262127873955 mfu:25.004429942868526 Step 5146 | loss:1.3064751625061035 lr:9.941828931342006e-06 tokens_per_second_per_gpu:4037.988284334862 mfu:19.047879689051314 Step 5147 | loss:1.2095838785171509 lr:9.933108281006179e-06 tokens_per_second_per_gpu:5365.442814991794 mfu:25.3097091972576 Step 5148 | loss:1.3342641592025757 lr:9.924390508779561e-06 tokens_per_second_per_gpu:4845.602205892136 mfu:22.857532350180772 Step 5149 | loss:1.5210304260253906 lr:9.915675616327436e-06 tokens_per_second_per_gpu:4742.132481530547 mfu:22.369448006611787 Step 5150 | loss:1.2002193927764893 lr:9.906963605314539e-06 tokens_per_second_per_gpu:5158.998858037025 mfu:24.33587782933082 Step 5151 | loss:1.289688229560852 lr:9.898254477405064e-06 tokens_per_second_per_gpu:5317.111068061263 mfu:25.081720100739936 Step 5152 | loss:1.2009838819503784 lr:9.88954823426264e-06 tokens_per_second_per_gpu:5264.275058108105 mfu:24.832483627038023 Step 5153 | loss:1.3249413967132568 lr:9.880844877550354e-06 tokens_per_second_per_gpu:4065.9803440523397 mfu:19.179923010676525 Step 5154 | loss:1.2628097534179688 lr:9.87214440893074e-06 tokens_per_second_per_gpu:4267.215262620826 mfu:20.129182455781613 Step 5155 | loss:1.4386427402496338 lr:9.863446830065778e-06 tokens_per_second_per_gpu:2919.365515737461 mfu:13.771145232852529 Step 5156 | loss:1.2226489782333374 lr:9.854752142616902e-06 tokens_per_second_per_gpu:4384.677516790946 mfu:20.68327194982921 Step 5157 | loss:1.416544795036316 lr:9.846060348244985e-06 tokens_per_second_per_gpu:4020.693676950537 mfu:18.96629807525516 Step 5158 | loss:1.3825759887695312 lr:9.837371448610349e-06 tokens_per_second_per_gpu:5048.632740882536 mfu:23.815262024311785 Step 5159 | loss:1.2345728874206543 lr:9.828685445372777e-06 tokens_per_second_per_gpu:4866.881305859245 mfu:22.957909495314453 Step 5160 | loss:1.2805103063583374 lr:9.820002340191476e-06 tokens_per_second_per_gpu:4585.539802499395 mfu:21.63077362215578 Step 5161 | loss:1.3283295631408691 lr:9.811322134725116e-06 tokens_per_second_per_gpu:4392.559470039865 mfu:20.720452468104256 Step 5162 | loss:1.1804646253585815 lr:9.802644830631808e-06 tokens_per_second_per_gpu:4478.508363893573 mfu:21.12588806480563 Step 5163 | loss:1.4170244932174683 lr:9.793970429569108e-06 tokens_per_second_per_gpu:5319.044895240517 mfu:25.090842293489416 Step 5164 | loss:1.4765375852584839 lr:9.785298933194018e-06 tokens_per_second_per_gpu:5310.841120278617 mfu:25.052143687285795 Step 5165 | loss:1.4609767198562622 lr:9.776630343162985e-06 tokens_per_second_per_gpu:5315.682886150418 mfu:25.074983122993522 Step 5166 | loss:1.3592205047607422 lr:9.767964661131904e-06 tokens_per_second_per_gpu:5306.345773103769 mfu:25.030938367676715 Step 5167 | loss:1.3081425428390503 lr:9.7593018887561e-06 tokens_per_second_per_gpu:3388.276702701355 mfu:15.983079306259517 Step 5168 | loss:1.3509941101074219 lr:9.750642027690382e-06 tokens_per_second_per_gpu:4163.409142622276 mfu:19.639511276598068 Step 5169 | loss:1.221551775932312 lr:9.741985079588947e-06 tokens_per_second_per_gpu:3345.249173843243 mfu:15.780111111382373 Step 5170 | loss:1.1313323974609375 lr:9.733331046105466e-06 tokens_per_second_per_gpu:5346.881624512029 mfu:25.222152894898898 Step 5171 | loss:1.2626088857650757 lr:9.724679928893072e-06 tokens_per_second_per_gpu:5306.057842030228 mfu:25.02958014767672 Step 5172 | loss:1.2866400480270386 lr:9.716031729604297e-06 tokens_per_second_per_gpu:5326.571053342291 mfu:25.126344465350467 Step 5173 | loss:1.3141549825668335 lr:9.707386449891138e-06 tokens_per_second_per_gpu:4928.162100599884 mfu:23.246981459687778 Step 5174 | loss:1.2375530004501343 lr:9.69874409140506e-06 tokens_per_second_per_gpu:5297.796056795247 mfu:24.990607897117396 Step 5175 | loss:1.220949649810791 lr:9.69010465579692e-06 tokens_per_second_per_gpu:4794.449875518683 mfu:22.616238080321683 Step 5176 | loss:1.2596843242645264 lr:9.681468144717037e-06 tokens_per_second_per_gpu:3888.2036459269893 mfu:18.341319993786826 Step 5177 | loss:1.356902003288269 lr:9.672834559815206e-06 tokens_per_second_per_gpu:4275.131234734701 mfu:20.166523446846874 Step 5178 | loss:1.119573712348938 lr:9.664203902740601e-06 tokens_per_second_per_gpu:3458.7635632432493 mfu:16.315577853734155 Step 5179 | loss:1.3377892971038818 lr:9.655576175141872e-06 tokens_per_second_per_gpu:5320.073240332622 mfu:25.095693172742642 Step 5180 | loss:1.362379550933838 lr:9.646951378667135e-06 tokens_per_second_per_gpu:3607.912026531005 mfu:17.01913660241438 Step 5181 | loss:1.4462395906448364 lr:9.638329514963883e-06 tokens_per_second_per_gpu:5319.909297187937 mfu:25.09491982495758 Step 5182 | loss:1.173254370689392 lr:9.62971058567909e-06 tokens_per_second_per_gpu:5330.562212588788 mfu:25.14517144447818 Step 5183 | loss:1.128318190574646 lr:9.621094592459179e-06 tokens_per_second_per_gpu:5313.7241014828605 mfu:25.065743201513524 Step 5184 | loss:1.319059133529663 lr:9.612481536949977e-06 tokens_per_second_per_gpu:4887.262401370553 mfu:23.05405060021476 Step 5185 | loss:1.1744701862335205 lr:9.603871420796765e-06 tokens_per_second_per_gpu:4033.9691454975573 mfu:19.02892072541995 Step 5186 | loss:1.1441458463668823 lr:9.595264245644292e-06 tokens_per_second_per_gpu:4752.651159294378 mfu:22.41906640429526 Step 5187 | loss:1.3806020021438599 lr:9.586660013136691e-06 tokens_per_second_per_gpu:5332.066749839805 mfu:25.152268603391754 Step 5188 | loss:1.312997579574585 lr:9.578058724917563e-06 tokens_per_second_per_gpu:4573.127001912777 mfu:21.572220323946535 Step 5189 | loss:1.2629637718200684 lr:9.569460382629966e-06 tokens_per_second_per_gpu:3774.6695859624438 mfu:17.80576046202597 Step 5190 | loss:1.2136164903640747 lr:9.560864987916355e-06 tokens_per_second_per_gpu:4545.857784899757 mfu:21.443586774687937 Step 5191 | loss:1.2312595844268799 lr:9.55227254241863e-06 tokens_per_second_per_gpu:5361.098421698711 mfu:25.289215952864204 Step 5192 | loss:1.043455958366394 lr:9.543683047778174e-06 tokens_per_second_per_gpu:5314.791932598298 mfu:25.07078034307582 Step 5193 | loss:1.2183512449264526 lr:9.535096505635735e-06 tokens_per_second_per_gpu:3672.9809064429464 mfu:17.326077610854714 Step 5194 | loss:1.362775444984436 lr:9.526512917631538e-06 tokens_per_second_per_gpu:5327.858202978782 mfu:25.13241616979617 Step 5195 | loss:1.3494361639022827 lr:9.517932285405265e-06 tokens_per_second_per_gpu:5309.322364923389 mfu:25.044979459148795 Step 5196 | loss:1.2389241456985474 lr:9.509354610595977e-06 tokens_per_second_per_gpu:5323.822711252628 mfu:25.113380066798015 Step 5197 | loss:1.1979502439498901 lr:9.500779894842202e-06 tokens_per_second_per_gpu:4978.393860614634 mfu:23.483933242099365 Step 5198 | loss:1.390708088874817 lr:9.492208139781924e-06 tokens_per_second_per_gpu:4316.1589826412865 mfu:20.360058333777854 Step 5199 | loss:1.1918247938156128 lr:9.48363934705251e-06 tokens_per_second_per_gpu:4259.590705150408 mfu:20.093216117310007 Step 5200 | loss:1.472300410270691 lr:9.475073518290795e-06 tokens_per_second_per_gpu:4017.521263703809 mfu:18.951333260700828 Step 5201 | loss:1.3224149942398071 lr:9.46651065513306e-06 tokens_per_second_per_gpu:5053.734840994078 mfu:23.83932950104597 Step 5202 | loss:1.23374342918396 lr:9.457950759214978e-06 tokens_per_second_per_gpu:4544.787026465391 mfu:21.438535824462807 Step 5203 | loss:1.3688747882843018 lr:9.449393832171682e-06 tokens_per_second_per_gpu:3355.654719782076 mfu:15.829195846945055 Step 5204 | loss:1.2109707593917847 lr:9.440839875637756e-06 tokens_per_second_per_gpu:5216.702446409803 mfu:24.608075500932603 Step 5205 | loss:1.2360191345214844 lr:9.432288891247171e-06 tokens_per_second_per_gpu:4387.927039657567 mfu:20.69860050361683 Step 5206 | loss:1.3321788311004639 lr:9.42374088063335e-06 tokens_per_second_per_gpu:4149.7092278095 mfu:19.574886440979704 Step 5207 | loss:1.0870683193206787 lr:9.41519584542918e-06 tokens_per_second_per_gpu:3670.266750559302 mfu:17.313274474468816 Step 5208 | loss:1.3790634870529175 lr:9.406653787266928e-06 tokens_per_second_per_gpu:3879.7773448271673 mfu:18.30157169382375 Step 5209 | loss:1.2208619117736816 lr:9.398114707778314e-06 tokens_per_second_per_gpu:4841.242147502718 mfu:22.836965210855215 Step 5210 | loss:1.2692161798477173 lr:9.389578608594515e-06 tokens_per_second_per_gpu:4728.667743594368 mfu:22.305932540445646 Step 5211 | loss:1.4419045448303223 lr:9.381045491346093e-06 tokens_per_second_per_gpu:5334.7007996395405 mfu:25.164693865712344 Step 5212 | loss:1.1865670680999756 lr:9.372515357663058e-06 tokens_per_second_per_gpu:4571.308388163086 mfu:21.563641612601742 Step 5213 | loss:1.1760224103927612 lr:9.363988209174879e-06 tokens_per_second_per_gpu:3883.7580883487863 mfu:18.320349540200105 Step 5214 | loss:1.2532018423080444 lr:9.355464047510409e-06 tokens_per_second_per_gpu:3647.8613553097834 mfu:17.20758440232222 Step 5215 | loss:1.1398780345916748 lr:9.346942874297945e-06 tokens_per_second_per_gpu:4255.859709065972 mfu:20.07561637220615 Step 5216 | loss:1.2249069213867188 lr:9.338424691165252e-06 tokens_per_second_per_gpu:4461.312635063276 mfu:21.044772878019245 Step 5217 | loss:1.1546685695648193 lr:9.329909499739459e-06 tokens_per_second_per_gpu:4583.560197720828 mfu:21.621435488659873 Step 5218 | loss:1.3911585807800293 lr:9.32139730164717e-06 tokens_per_second_per_gpu:3268.5257596489614 mfu:15.41819367626365 Step 5219 | loss:1.3301639556884766 lr:9.312888098514396e-06 tokens_per_second_per_gpu:5310.0752830828105 mfu:25.048531102567875 Step 5220 | loss:1.3547720909118652 lr:9.30438189196659e-06 tokens_per_second_per_gpu:3899.7919386358744 mfu:18.395983947661254 Step 5221 | loss:1.3711731433868408 lr:9.29587868362862e-06 tokens_per_second_per_gpu:5050.564898312477 mfu:23.824376340568865 Step 5222 | loss:1.2679479122161865 lr:9.287378475124788e-06 tokens_per_second_per_gpu:4426.803578978823 mfu:20.881987772616778 Step 5223 | loss:1.3360387086868286 lr:9.278881268078826e-06 tokens_per_second_per_gpu:4761.463813811675 mfu:22.46063719924726 Step 5224 | loss:1.175411581993103 lr:9.270387064113883e-06 tokens_per_second_per_gpu:3735.6926821822844 mfu:17.621899756749436 Step 5225 | loss:1.360194206237793 lr:9.26189586485254e-06 tokens_per_second_per_gpu:5298.853356891415 mfu:24.995595362065025 Step 5226 | loss:1.340569019317627 lr:9.253407671916808e-06 tokens_per_second_per_gpu:5149.846078121483 mfu:24.292702604843928 Step 5227 | loss:1.266993761062622 lr:9.244922486928115e-06 tokens_per_second_per_gpu:5317.600906009983 mfu:25.08403074991902 Step 5228 | loss:1.3005119562149048 lr:9.236440311507318e-06 tokens_per_second_per_gpu:4177.328640116932 mfu:19.70517192119152 Step 5229 | loss:1.2024750709533691 lr:9.227961147274705e-06 tokens_per_second_per_gpu:3868.4286780097823 mfu:18.248038096163924 Step 5230 | loss:1.298913836479187 lr:9.219484995849978e-06 tokens_per_second_per_gpu:4307.780795165317 mfu:20.32053699398752 Step 5231 | loss:1.263169765472412 lr:9.211011858852276e-06 tokens_per_second_per_gpu:4219.964075639006 mfu:19.906290544904557 Step 5232 | loss:1.1983435153961182 lr:9.202541737900139e-06 tokens_per_second_per_gpu:3483.6422072723176 mfu:16.43293466235364 Step 5233 | loss:1.3427025079727173 lr:9.194074634611576e-06 tokens_per_second_per_gpu:5211.3463041166815 mfu:24.582809663883843 Step 5234 | loss:1.2978515625 lr:9.18561055060397e-06 tokens_per_second_per_gpu:3357.3710243452156 mfu:15.83729194840114 Step 5235 | loss:1.3829014301300049 lr:9.17714948749414e-06 tokens_per_second_per_gpu:5227.407408522552 mfu:24.658572633673316 Step 5236 | loss:1.2064248323440552 lr:9.16869144689837e-06 tokens_per_second_per_gpu:5084.54695369565 mfu:23.984675493747805 Step 5237 | loss:1.2872419357299805 lr:9.160236430432299e-06 tokens_per_second_per_gpu:5148.533105873833 mfu:24.2865090907356 Step 5238 | loss:1.2083650827407837 lr:9.151784439711028e-06 tokens_per_second_per_gpu:5325.684035562091 mfu:25.122160251140425 Step 5239 | loss:1.293613076210022 lr:9.143335476349093e-06 tokens_per_second_per_gpu:4138.287328436721 mfu:19.521007392861318 Step 5240 | loss:1.2489124536514282 lr:9.134889541960414e-06 tokens_per_second_per_gpu:4955.161252713589 mfu:23.374341066738488 Step 5241 | loss:1.257797122001648 lr:9.126446638158348e-06 tokens_per_second_per_gpu:5352.4150344515965 mfu:25.248254933680926 Step 5242 | loss:1.2293956279754639 lr:9.118006766555703e-06 tokens_per_second_per_gpu:5336.647950148159 mfu:25.173878906879633 Step 5243 | loss:1.29114830493927 lr:9.109569928764652e-06 tokens_per_second_per_gpu:4466.490427843653 mfu:21.06919740998683 Step 5244 | loss:1.1802793741226196 lr:9.101136126396823e-06 tokens_per_second_per_gpu:5306.644985390863 mfu:25.03234980308582 Step 5245 | loss:1.4204820394515991 lr:9.092705361063278e-06 tokens_per_second_per_gpu:4350.91009669154 mfu:20.52398526790435 Step 5246 | loss:1.3272022008895874 lr:9.084277634374458e-06 tokens_per_second_per_gpu:4192.757908253197 mfu:19.777954411494882 Step 5247 | loss:1.370252013206482 lr:9.075852947940244e-06 tokens_per_second_per_gpu:3590.544177624754 mfu:16.93720949586301 Step 5248 | loss:1.2836177349090576 lr:9.067431303369961e-06 tokens_per_second_per_gpu:5098.038207308144 mfu:24.04831603888316 Step 5249 | loss:1.2834597826004028 lr:9.059012702272306e-06 tokens_per_second_per_gpu:5300.978047230786 mfu:25.005617888905384 Step 5250 | loss:1.0781192779541016 lr:9.050597146255418e-06 tokens_per_second_per_gpu:3902.217472953286 mfu:18.407425606875307 Step 5251 | loss:1.1780623197555542 lr:9.042184636926878e-06 tokens_per_second_per_gpu:4429.26068196424 mfu:20.893578346623986 Step 5252 | loss:1.1970192193984985 lr:9.033775175893638e-06 tokens_per_second_per_gpu:4818.552812179182 mfu:22.72993574493431 Step 5253 | loss:1.3136345148086548 lr:9.025368764762088e-06 tokens_per_second_per_gpu:5307.480843137104 mfu:25.036292686686874 Step 5254 | loss:1.2547155618667603 lr:9.016965405138064e-06 tokens_per_second_per_gpu:5354.433287099545 mfu:25.25777537577071 Step 5255 | loss:1.1648216247558594 lr:9.00856509862677e-06 tokens_per_second_per_gpu:4783.711293497979 mfu:22.565582356738997 Step 5256 | loss:1.3072755336761475 lr:9.000167846832846e-06 tokens_per_second_per_gpu:5028.824816701827 mfu:23.72182466637102 Step 5257 | loss:1.2690253257751465 lr:8.991773651360385e-06 tokens_per_second_per_gpu:3998.3690755633284 mfu:18.860989121541934 Step 5258 | loss:1.4031261205673218 lr:8.983382513812832e-06 tokens_per_second_per_gpu:3541.0480952773637 mfu:16.703728030527913 Step 5259 | loss:1.4575793743133545 lr:8.974994435793083e-06 tokens_per_second_per_gpu:3888.0676035419415 mfu:18.34067825864533 Step 5260 | loss:1.3547066450119019 lr:8.96660941890347e-06 tokens_per_second_per_gpu:4821.456468956696 mfu:22.74363278936877 Step 5261 | loss:1.3070143461227417 lr:8.958227464745695e-06 tokens_per_second_per_gpu:3694.2844332433447 mfu:17.42656998152867 Step 5262 | loss:1.245981216430664 lr:8.949848574920889e-06 tokens_per_second_per_gpu:5331.581327042089 mfu:25.149978781233255 Step 5263 | loss:1.3133174180984497 lr:8.941472751029636e-06 tokens_per_second_per_gpu:5318.520645429878 mfu:25.08836931768639 Step 5264 | loss:1.150841236114502 lr:8.933099994671879e-06 tokens_per_second_per_gpu:5196.8148956163695 mfu:24.51426253067392 Step 5265 | loss:1.2812861204147339 lr:8.924730307446993e-06 tokens_per_second_per_gpu:4308.4421328254 mfu:20.323656636565975 Step 5266 | loss:1.1812756061553955 lr:8.916363690953805e-06 tokens_per_second_per_gpu:4801.753808111649 mfu:22.650691976542106 Step 5267 | loss:1.2571910619735718 lr:8.908000146790496e-06 tokens_per_second_per_gpu:5334.607414185799 mfu:25.164253350593846 Step 5268 | loss:1.2719002962112427 lr:8.899639676554689e-06 tokens_per_second_per_gpu:4073.1573090102765 mfu:19.213777978899603 Step 5269 | loss:1.3448785543441772 lr:8.891282281843442e-06 tokens_per_second_per_gpu:5343.396442641672 mfu:25.20571269738308 Step 5270 | loss:1.3689110279083252 lr:8.882927964253174e-06 tokens_per_second_per_gpu:4841.928921945734 mfu:22.840204843078727 Step 5271 | loss:1.4233537912368774 lr:8.874576725379748e-06 tokens_per_second_per_gpu:4331.8697898015025 mfu:20.434168891692703 Step 5272 | loss:1.1429259777069092 lr:8.866228566818463e-06 tokens_per_second_per_gpu:5318.829645907837 mfu:25.089826925661843 Step 5273 | loss:1.2652561664581299 lr:8.857883490163974e-06 tokens_per_second_per_gpu:4427.58746173505 mfu:20.885685481322092 Step 5274 | loss:1.2414641380310059 lr:8.849541497010373e-06 tokens_per_second_per_gpu:4959.961421501773 mfu:23.396984281905592 Step 5275 | loss:1.2789307832717896 lr:8.84120258895119e-06 tokens_per_second_per_gpu:5355.924680776047 mfu:25.264810534200773 Step 5276 | loss:1.248613953590393 lr:8.832866767579317e-06 tokens_per_second_per_gpu:4749.281458907079 mfu:22.4031709526382 Step 5277 | loss:1.2135765552520752 lr:8.824534034487083e-06 tokens_per_second_per_gpu:4087.9457959252572 mfu:19.283537794853615 Step 5278 | loss:1.52007257938385 lr:8.816204391266244e-06 tokens_per_second_per_gpu:4537.8919444777075 mfu:21.406010546304607 Step 5279 | loss:1.2391808032989502 lr:8.807877839507925e-06 tokens_per_second_per_gpu:4379.4856607472175 mfu:20.658781079048953 Step 5280 | loss:1.3049176931381226 lr:8.799554380802678e-06 tokens_per_second_per_gpu:5330.696936569713 mfu:25.14580696048249 Step 5281 | loss:1.2186307907104492 lr:8.791234016740496e-06 tokens_per_second_per_gpu:5064.015482272064 mfu:23.887825040012505 Step 5282 | loss:1.2941293716430664 lr:8.782916748910725e-06 tokens_per_second_per_gpu:5057.428150276385 mfu:23.856751471074155 Step 5283 | loss:1.2489111423492432 lr:8.774602578902145e-06 tokens_per_second_per_gpu:5325.168882583546 mfu:25.119730186646468 Step 5284 | loss:1.414634108543396 lr:8.766291508302976e-06 tokens_per_second_per_gpu:5317.505366575083 mfu:25.083580074103885 Step 5285 | loss:1.3690093755722046 lr:8.757983538700788e-06 tokens_per_second_per_gpu:4321.4367222187675 mfu:20.384954331840056 Step 5286 | loss:1.2942450046539307 lr:8.749678671682587e-06 tokens_per_second_per_gpu:5349.738497991677 mfu:25.235629254535276 Step 5287 | loss:1.3369077444076538 lr:8.74137690883481e-06 tokens_per_second_per_gpu:5299.431774140876 mfu:24.998323854918883 Step 5288 | loss:1.2940539121627808 lr:8.733078251743256e-06 tokens_per_second_per_gpu:5343.938951836974 mfu:25.208271805818935 Step 5289 | loss:1.4373576641082764 lr:8.72478270199315e-06 tokens_per_second_per_gpu:4690.343235638501 mfu:22.1251492975825 Step 5290 | loss:1.0244507789611816 lr:8.71649026116915e-06 tokens_per_second_per_gpu:5342.141512964184 mfu:25.199792979981286 Step 5291 | loss:1.192603349685669 lr:8.708200930855267e-06 tokens_per_second_per_gpu:4624.500759379004 mfu:21.8145591031816 Step 5292 | loss:1.2564780712127686 lr:8.699914712634952e-06 tokens_per_second_per_gpu:5309.120049406177 mfu:25.044025102335524 Step 5293 | loss:1.2443218231201172 lr:8.691631608091078e-06 tokens_per_second_per_gpu:4589.5184278124125 mfu:21.64954147658076 Step 5294 | loss:1.140615463256836 lr:8.683351618805874e-06 tokens_per_second_per_gpu:5334.047493577662 mfu:25.161612109552955 Step 5295 | loss:1.2581881284713745 lr:8.675074746361006e-06 tokens_per_second_per_gpu:5180.713410522413 mfu:24.438309078289087 Step 5296 | loss:1.369040608406067 lr:8.66680099233756e-06 tokens_per_second_per_gpu:4622.811972483773 mfu:21.806592807260042 Step 5297 | loss:1.2098398208618164 lr:8.658530358315983e-06 tokens_per_second_per_gpu:5335.245848445033 mfu:25.167264953922768 Step 5298 | loss:1.3497626781463623 lr:8.650262845876148e-06 tokens_per_second_per_gpu:3733.2369142631487 mfu:17.610315480477656 Step 5299 | loss:1.155915379524231 lr:8.641998456597356e-06 tokens_per_second_per_gpu:4728.837750640724 mfu:22.306734492689497 Step 5300 | loss:1.181728482246399 lr:8.633737192058257e-06 tokens_per_second_per_gpu:5327.144439669742 mfu:25.12904922648685 Step 5301 | loss:1.3080819845199585 lr:8.62547905383696e-06 tokens_per_second_per_gpu:5355.021444629922 mfu:25.260549815191524 Step 5302 | loss:1.1638885736465454 lr:8.617224043510953e-06 tokens_per_second_per_gpu:4653.692073705961 mfu:21.952259513413658 Step 5303 | loss:1.2862272262573242 lr:8.608972162657097e-06 tokens_per_second_per_gpu:4809.071702272681 mfu:22.685211731861184 Step 5304 | loss:1.1401231288909912 lr:8.60072341285171e-06 tokens_per_second_per_gpu:4964.245675422324 mfu:23.41719383861793 Step 5305 | loss:1.2800925970077515 lr:8.592477795670487e-06 tokens_per_second_per_gpu:4998.03421837345 mfu:23.576580160638276 Step 5306 | loss:1.2888613939285278 lr:8.584235312688493e-06 tokens_per_second_per_gpu:4722.822113218189 mfu:22.27835770459382 Step 5307 | loss:1.2538453340530396 lr:8.575995965480258e-06 tokens_per_second_per_gpu:3663.7823991743207 mfu:17.282686682641433 Step 5308 | loss:1.2148011922836304 lr:8.567759755619673e-06 tokens_per_second_per_gpu:4563.7887711644435 mfu:21.52817029624019 Step 5309 | loss:1.1929895877838135 lr:8.55952668468001e-06 tokens_per_second_per_gpu:4790.897230682093 mfu:22.59947964848378 Step 5310 | loss:1.2500028610229492 lr:8.551296754233994e-06 tokens_per_second_per_gpu:4706.4933880081 mfu:22.201332321810025 Step 5311 | loss:1.3119029998779297 lr:8.543069965853728e-06 tokens_per_second_per_gpu:5217.832539376637 mfu:24.613406342270903 Step 5312 | loss:1.470824956893921 lr:8.534846321110682e-06 tokens_per_second_per_gpu:4660.263948679055 mfu:21.983260168939236 Step 5313 | loss:1.2902276515960693 lr:8.526625821575776e-06 tokens_per_second_per_gpu:3706.7987583107174 mfu:17.485602188035493 Step 5314 | loss:1.3094708919525146 lr:8.51840846881931e-06 tokens_per_second_per_gpu:4757.582641722184 mfu:22.442329048304888 Step 5315 | loss:1.1161235570907593 lr:8.510194264410956e-06 tokens_per_second_per_gpu:4488.898268828046 mfu:21.174899019082115 Step 5316 | loss:1.2469727993011475 lr:8.501983209919834e-06 tokens_per_second_per_gpu:4464.462144047824 mfu:21.059629649261 Step 5317 | loss:1.0984041690826416 lr:8.493775306914431e-06 tokens_per_second_per_gpu:4009.9878517528205 mfu:18.9157968711954 Step 5318 | loss:1.2956238985061646 lr:8.485570556962618e-06 tokens_per_second_per_gpu:4302.872321258785 mfu:20.297382885098404 Step 5319 | loss:1.2975354194641113 lr:8.47736896163171e-06 tokens_per_second_per_gpu:4258.160212561952 mfu:20.086468239703052 Step 5320 | loss:1.2610632181167603 lr:8.469170522488387e-06 tokens_per_second_per_gpu:4062.3719513776286 mfu:19.162901606774636 Step 5321 | loss:1.0370925664901733 lr:8.460975241098712e-06 tokens_per_second_per_gpu:4945.288678813598 mfu:23.32777045121743 Step 5322 | loss:1.3493075370788574 lr:8.452783119028185e-06 tokens_per_second_per_gpu:5355.0501598566625 mfu:25.260685269815376 Step 5323 | loss:1.0999943017959595 lr:8.44459415784169e-06 tokens_per_second_per_gpu:5303.428102248497 mfu:25.01717521644642 Step 5324 | loss:1.4673084020614624 lr:8.436408359103465e-06 tokens_per_second_per_gpu:3440.052712497663 mfu:16.227315578366895 Step 5325 | loss:1.2213337421417236 lr:8.428225724377211e-06 tokens_per_second_per_gpu:4064.336346692779 mfu:19.172167994636602 Step 5326 | loss:1.1972745656967163 lr:8.420046255225989e-06 tokens_per_second_per_gpu:5321.090266198518 mfu:25.10049065727458 Step 5327 | loss:1.2201637029647827 lr:8.411869953212234e-06 tokens_per_second_per_gpu:5305.966797393188 mfu:25.029150674589985 Step 5328 | loss:1.200772762298584 lr:8.403696819897825e-06 tokens_per_second_per_gpu:5246.808223816362 mfu:24.750089589534635 Step 5329 | loss:1.2392542362213135 lr:8.39552685684401e-06 tokens_per_second_per_gpu:4504.0623687144225 mfu:21.246430665508385 Step 5330 | loss:1.230566143989563 lr:8.38736006561141e-06 tokens_per_second_per_gpu:5292.397834064688 mfu:24.965143559465577 Step 5331 | loss:1.239162564277649 lr:8.379196447760085e-06 tokens_per_second_per_gpu:5322.999557228672 mfu:25.109497108822456 Step 5332 | loss:1.3953334093093872 lr:8.371036004849467e-06 tokens_per_second_per_gpu:4694.001707418102 mfu:22.142406933166527 Step 5333 | loss:1.2077114582061768 lr:8.362878738438357e-06 tokens_per_second_per_gpu:4520.4468216167315 mfu:21.323718925324503 Step 5334 | loss:1.4250205755233765 lr:8.354724650084997e-06 tokens_per_second_per_gpu:3682.6517186709693 mfu:17.37169648214501 Step 5335 | loss:1.3331269025802612 lr:8.346573741346997e-06 tokens_per_second_per_gpu:5338.723066189046 mfu:25.1836675832958 Step 5336 | loss:1.2496925592422485 lr:8.338426013781339e-06 tokens_per_second_per_gpu:5304.229481407139 mfu:25.020955458667117 Step 5337 | loss:1.1856998205184937 lr:8.330281468944443e-06 tokens_per_second_per_gpu:5296.159531258182 mfu:24.982888126939013 Step 5338 | loss:1.3136464357376099 lr:8.322140108392093e-06 tokens_per_second_per_gpu:3714.59464610553 mfu:17.52237672087924 Step 5339 | loss:1.27849280834198 lr:8.314001933679449e-06 tokens_per_second_per_gpu:4848.432506240123 mfu:22.870883359821264 Step 5340 | loss:1.3654223680496216 lr:8.305866946361104e-06 tokens_per_second_per_gpu:5359.02747296851 mfu:25.279446934363555 Step 5341 | loss:1.257108211517334 lr:8.297735147991023e-06 tokens_per_second_per_gpu:4052.8446043977274 mfu:19.117959485537426 Step 5342 | loss:1.2017921209335327 lr:8.28960654012253e-06 tokens_per_second_per_gpu:4931.322164157057 mfu:23.261888018649405 Step 5343 | loss:1.2903814315795898 lr:8.281481124308399e-06 tokens_per_second_per_gpu:4278.785003901381 mfu:20.183758899403404 Step 5344 | loss:1.2784823179244995 lr:8.27335890210076e-06 tokens_per_second_per_gpu:5317.992116675405 mfu:25.085876157375235 Step 5345 | loss:1.3954812288284302 lr:8.265239875051112e-06 tokens_per_second_per_gpu:4842.1587247093075 mfu:22.8412888619229 Step 5346 | loss:1.1396775245666504 lr:8.257124044710393e-06 tokens_per_second_per_gpu:5273.961736140721 mfu:24.878177340035563 Step 5347 | loss:1.2408208847045898 lr:8.24901141262891e-06 tokens_per_second_per_gpu:4879.743919416035 mfu:23.018584638050005 Step 5348 | loss:1.329398274421692 lr:8.240901980356328e-06 tokens_per_second_per_gpu:3969.22802877307 mfu:18.723525831857007 Step 5349 | loss:1.1333105564117432 lr:8.232795749441751e-06 tokens_per_second_per_gpu:4777.281426770894 mfu:22.535251578338954 Step 5350 | loss:1.3211627006530762 lr:8.224692721433649e-06 tokens_per_second_per_gpu:5327.1633972308155 mfu:25.129138652536927 Step 5351 | loss:1.4138842821121216 lr:8.216592897879854e-06 tokens_per_second_per_gpu:5306.239312556483 mfu:25.030436175111127 Step 5352 | loss:1.1577380895614624 lr:8.208496280327638e-06 tokens_per_second_per_gpu:4164.227726081558 mfu:19.64337267444024 Step 5353 | loss:1.3545392751693726 lr:8.200402870323633e-06 tokens_per_second_per_gpu:4814.385746057386 mfu:22.710278983063002 Step 5354 | loss:1.2502857446670532 lr:8.192312669413835e-06 tokens_per_second_per_gpu:5142.643224935007 mfu:24.258725517429845 Step 5355 | loss:1.2909737825393677 lr:8.184225679143672e-06 tokens_per_second_per_gpu:5213.617399181747 mfu:24.593522806794528 Step 5356 | loss:1.4677304029464722 lr:8.176141901057944e-06 tokens_per_second_per_gpu:5307.569399720262 mfu:25.03671042319894 Step 5357 | loss:1.2069637775421143 lr:8.168061336700803e-06 tokens_per_second_per_gpu:5299.862904557677 mfu:25.00035757065337 Step 5358 | loss:1.084536075592041 lr:8.159983987615837e-06 tokens_per_second_per_gpu:5321.729995857238 mfu:25.103508371223896 Step 5359 | loss:1.2805492877960205 lr:8.151909855346005e-06 tokens_per_second_per_gpu:4474.027280660602 mfu:21.10475003064407 Step 5360 | loss:1.449753761291504 lr:8.143838941433616e-06 tokens_per_second_per_gpu:3356.5943135909674 mfu:15.83362807125283 Step 5361 | loss:1.4019078016281128 lr:8.135771247420414e-06 tokens_per_second_per_gpu:4320.998899849786 mfu:20.382889049025373 Step 5362 | loss:1.3037554025650024 lr:8.127706774847515e-06 tokens_per_second_per_gpu:3566.2955019027945 mfu:16.822824355231827 Step 5363 | loss:1.3815139532089233 lr:8.119645525255382e-06 tokens_per_second_per_gpu:5058.575108494653 mfu:23.862161868680975 Step 5364 | loss:1.2591415643692017 lr:8.111587500183917e-06 tokens_per_second_per_gpu:4601.723891076366 mfu:21.7071167292636 Step 5365 | loss:1.1224559545516968 lr:8.103532701172373e-06 tokens_per_second_per_gpu:5334.373447251478 mfu:25.163149688645774 Step 5366 | loss:1.1107064485549927 lr:8.095481129759392e-06 tokens_per_second_per_gpu:4831.037922596323 mfu:22.788830140951458 Step 5367 | loss:1.3318859338760376 lr:8.087432787483006e-06 tokens_per_second_per_gpu:5313.329477683321 mfu:25.06388169372133 Step 5368 | loss:1.33661687374115 lr:8.079387675880623e-06 tokens_per_second_per_gpu:4500.161247118177 mfu:21.228028409338915 Step 5369 | loss:1.4683640003204346 lr:8.071345796489041e-06 tokens_per_second_per_gpu:5290.567706223997 mfu:24.956510534189032 Step 5370 | loss:1.0786430835723877 lr:8.063307150844432e-06 tokens_per_second_per_gpu:4910.1829683731 mfu:23.162170825417764 Step 5371 | loss:1.208147406578064 lr:8.055271740482357e-06 tokens_per_second_per_gpu:5342.188038769241 mfu:25.20001245014186 Step 5372 | loss:1.2222777605056763 lr:8.047239566937759e-06 tokens_per_second_per_gpu:5326.389918290592 mfu:25.125490020406776 Step 5373 | loss:1.237984538078308 lr:8.039210631744956e-06 tokens_per_second_per_gpu:4634.534243325991 mfu:21.861888758848426 Step 5374 | loss:1.2172218561172485 lr:8.031184936437656e-06 tokens_per_second_per_gpu:5042.207684749055 mfu:23.78495393830254 Step 5375 | loss:1.113416314125061 lr:8.02316248254894e-06 tokens_per_second_per_gpu:5305.6850236090895 mfu:25.027821499574827 Step 5376 | loss:1.5012506246566772 lr:8.01514327161128e-06 tokens_per_second_per_gpu:4633.91781346656 mfu:21.858980954027707 Step 5377 | loss:1.2266179323196411 lr:8.007127305156517e-06 tokens_per_second_per_gpu:5327.905041852008 mfu:25.13263711675271 Step 5378 | loss:1.411841869354248 lr:7.999114584715884e-06 tokens_per_second_per_gpu:4734.6681498160815 mfu:22.334237480368337 Step 5379 | loss:1.216222882270813 lr:7.991105111819976e-06 tokens_per_second_per_gpu:5032.003766569412 mfu:23.736820315281193 Step 5380 | loss:1.2549934387207031 lr:7.983098887998794e-06 tokens_per_second_per_gpu:5301.094903422033 mfu:25.00616911949722 Step 5381 | loss:1.285787582397461 lr:7.97509591478169e-06 tokens_per_second_per_gpu:5320.2381010292465 mfu:25.096470848776754 Step 5382 | loss:1.1832435131072998 lr:7.96709619369742e-06 tokens_per_second_per_gpu:5336.148705326487 mfu:25.171523883875853 Step 5383 | loss:1.3182828426361084 lr:7.959099726274103e-06 tokens_per_second_per_gpu:4862.807320652397 mfu:22.938691812000197 Step 5384 | loss:1.2413876056671143 lr:7.951106514039236e-06 tokens_per_second_per_gpu:5287.938187979574 mfu:24.94410664798801 Step 5385 | loss:1.328432321548462 lr:7.943116558519706e-06 tokens_per_second_per_gpu:4708.689875800175 mfu:22.21169352948471 Step 5386 | loss:1.1936695575714111 lr:7.93512986124177e-06 tokens_per_second_per_gpu:5329.522917961609 mfu:25.14026891439983 Step 5387 | loss:1.304222583770752 lr:7.92714642373106e-06 tokens_per_second_per_gpu:3841.0413420441387 mfu:18.118847359652626 Step 5388 | loss:1.3772481679916382 lr:7.919166247512594e-06 tokens_per_second_per_gpu:3429.359393435919 mfu:16.176873367884284 Step 5389 | loss:1.3583663702011108 lr:7.911189334110755e-06 tokens_per_second_per_gpu:4195.822934495053 mfu:19.792412663225125 Step 5390 | loss:1.3110827207565308 lr:7.903215685049318e-06 tokens_per_second_per_gpu:3802.629550504763 mfu:17.937652385233957 Step 5391 | loss:1.02774977684021 lr:7.89524530185142e-06 tokens_per_second_per_gpu:5321.3354569036455 mfu:25.101647263664514 Step 5392 | loss:1.3315120935440063 lr:7.887278186039582e-06 tokens_per_second_per_gpu:5008.167916761879 mfu:23.62438254492373 Step 5393 | loss:1.1203758716583252 lr:7.879314339135701e-06 tokens_per_second_per_gpu:4775.176082271506 mfu:22.525320309126528 Step 5394 | loss:1.367280125617981 lr:7.871353762661046e-06 tokens_per_second_per_gpu:4451.185838592105 mfu:20.99700305125509 Step 5395 | loss:1.3445380926132202 lr:7.863396458136263e-06 tokens_per_second_per_gpu:4856.137196785821 mfu:22.90722769968108 Step 5396 | loss:1.2063401937484741 lr:7.855442427081372e-06 tokens_per_second_per_gpu:3879.645165061682 mfu:18.300948179317764 Step 5397 | loss:1.154873251914978 lr:7.84749167101577e-06 tokens_per_second_per_gpu:5312.894285978598 mfu:25.061828820198794 Step 5398 | loss:1.3715518712997437 lr:7.839544191458229e-06 tokens_per_second_per_gpu:3586.7385936060764 mfu:16.91925790674732 Step 5399 | loss:1.2784634828567505 lr:7.831599989926889e-06 tokens_per_second_per_gpu:4776.576462205093 mfu:22.53192614020271 Step 5400 | loss:1.204101800918579 lr:7.823659067939271e-06 tokens_per_second_per_gpu:4768.068943975678 mfu:22.491794725182274 Step 5401 | loss:1.138450026512146 lr:7.815721427012264e-06 tokens_per_second_per_gpu:5348.129651587351 mfu:25.22804005154857 Step 5402 | loss:1.1605677604675293 lr:7.807787068662137e-06 tokens_per_second_per_gpu:5319.333497686664 mfu:25.092203680468547 Step 5403 | loss:1.3044270277023315 lr:7.799855994404523e-06 tokens_per_second_per_gpu:4477.526585364502 mfu:21.121256847975314 Step 5404 | loss:1.2737939357757568 lr:7.791928205754437e-06 tokens_per_second_per_gpu:4276.454815866746 mfu:20.17276700487296 Step 5405 | loss:1.2241439819335938 lr:7.784003704226259e-06 tokens_per_second_per_gpu:4670.4242721697965 mfu:22.031188148375005 Step 5406 | loss:1.3043062686920166 lr:7.776082491333742e-06 tokens_per_second_per_gpu:5330.70428934051 mfu:25.145841644756846 Step 5407 | loss:1.248373031616211 lr:7.768164568590017e-06 tokens_per_second_per_gpu:5323.208443494372 mfu:25.110482460977433 Step 5408 | loss:1.3131890296936035 lr:7.76024993750758e-06 tokens_per_second_per_gpu:3885.7174943436557 mfu:18.329592392587042 Step 5409 | loss:1.3072535991668701 lr:7.7523385995983e-06 tokens_per_second_per_gpu:5336.717647504023 mfu:25.17420768119884 Step 5410 | loss:1.219738245010376 lr:7.744430556373417e-06 tokens_per_second_per_gpu:5335.262889689294 mfu:25.167345340379484 Step 5411 | loss:1.2587590217590332 lr:7.736525809343545e-06 tokens_per_second_per_gpu:4139.648309517432 mfu:19.52742737282635 Step 5412 | loss:1.275649905204773 lr:7.72862436001866e-06 tokens_per_second_per_gpu:4066.032082434358 mfu:19.180167069451983 Step 5413 | loss:1.1963738203048706 lr:7.720726209908119e-06 tokens_per_second_per_gpu:5336.042579927076 mfu:25.171023272259973 Step 5414 | loss:1.3950831890106201 lr:7.71283136052064e-06 tokens_per_second_per_gpu:5273.680683617703 mfu:24.876851567331983 Step 5415 | loss:1.3328667879104614 lr:7.704939813364314e-06 tokens_per_second_per_gpu:5279.414526780917 mfu:24.903899083827387 Step 5416 | loss:1.265699028968811 lr:7.697051569946604e-06 tokens_per_second_per_gpu:4798.108399122565 mfu:22.633495960369686 Step 5417 | loss:1.337044358253479 lr:7.689166631774333e-06 tokens_per_second_per_gpu:5341.395114952816 mfu:25.196272093213032 Step 5418 | loss:1.3878206014633179 lr:7.681285000353702e-06 tokens_per_second_per_gpu:4884.777287148047 mfu:23.042327892422996 Step 5419 | loss:1.2849129438400269 lr:7.673406677190276e-06 tokens_per_second_per_gpu:4232.9239776575105 mfu:19.967424613913135 Step 5420 | loss:1.1496187448501587 lr:7.665531663788992e-06 tokens_per_second_per_gpu:4976.878356486142 mfu:23.4767843505536 Step 5421 | loss:1.2710710763931274 lr:7.657659961654146e-06 tokens_per_second_per_gpu:4353.224281026436 mfu:20.53490167025262 Step 5422 | loss:1.4519119262695312 lr:7.649791572289408e-06 tokens_per_second_per_gpu:3214.232634962358 mfu:15.162083743754664 Step 5423 | loss:1.2294785976409912 lr:7.641926497197818e-06 tokens_per_second_per_gpu:5296.546430732286 mfu:24.98471319777022 Step 5424 | loss:1.379063367843628 lr:7.634064737881775e-06 tokens_per_second_per_gpu:4130.271372538228 mfu:19.48319476122503 Step 5425 | loss:1.2585914134979248 lr:7.626206295843052e-06 tokens_per_second_per_gpu:4689.535979074144 mfu:22.121341330636255 Step 5426 | loss:1.246599555015564 lr:7.6183511725827825e-06 tokens_per_second_per_gpu:3856.050139116478 mfu:18.18964641620769 Step 5427 | loss:1.1921972036361694 lr:7.610499369601473e-06 tokens_per_second_per_gpu:5304.387304974543 mfu:25.021699939362044 Step 5428 | loss:1.236840844154358 lr:7.602650888398985e-06 tokens_per_second_per_gpu:5340.566421119459 mfu:25.19236300301134 Step 5429 | loss:1.1950665712356567 lr:7.594805730474555e-06 tokens_per_second_per_gpu:5337.4472898722015 mfu:25.177649528739362 Step 5430 | loss:1.2535209655761719 lr:7.586963897326782e-06 tokens_per_second_per_gpu:4734.505240580408 mfu:22.33346900970848 Step 5431 | loss:1.2810808420181274 lr:7.579125390453631e-06 tokens_per_second_per_gpu:5308.767721268375 mfu:25.042363110396128 Step 5432 | loss:1.420137643814087 lr:7.571290211352425e-06 tokens_per_second_per_gpu:3597.9673066607606 mfu:16.972225662042266 Step 5433 | loss:1.3858877420425415 lr:7.563458361519859e-06 tokens_per_second_per_gpu:3858.0433409509965 mfu:18.19904868933641 Step 5434 | loss:1.2366611957550049 lr:7.555629842451992e-06 tokens_per_second_per_gpu:4713.508135725822 mfu:22.234422083633902 Step 5435 | loss:1.0620996952056885 lr:7.547804655644239e-06 tokens_per_second_per_gpu:3913.172034336436 mfu:18.45910014196053 Step 5436 | loss:1.2748030424118042 lr:7.539982802591386e-06 tokens_per_second_per_gpu:4650.82237284749 mfu:21.938722644842798 Step 5437 | loss:1.1634560823440552 lr:7.532164284787582e-06 tokens_per_second_per_gpu:4589.263428983108 mfu:21.64833860359564 Step 5438 | loss:1.4158118963241577 lr:7.524349103726333e-06 tokens_per_second_per_gpu:4980.572169506672 mfu:23.49420869680093 Step 5439 | loss:1.0757532119750977 lr:7.516537260900514e-06 tokens_per_second_per_gpu:4258.502957093179 mfu:20.0880850241351 Step 5440 | loss:1.4556156396865845 lr:7.508728757802358e-06 tokens_per_second_per_gpu:3269.789126359046 mfu:15.424153192587704 Step 5441 | loss:1.2117220163345337 lr:7.500923595923462e-06 tokens_per_second_per_gpu:4110.7903672663615 mfu:19.391299535555394 Step 5442 | loss:1.1600661277770996 lr:7.493121776754783e-06 tokens_per_second_per_gpu:5295.617602844018 mfu:24.980331758146875 Step 5443 | loss:1.3748118877410889 lr:7.485323301786643e-06 tokens_per_second_per_gpu:5323.318730355189 mfu:25.111002702916785 Step 5444 | loss:1.4052892923355103 lr:7.477528172508721e-06 tokens_per_second_per_gpu:3867.773175144278 mfu:18.24494597730702 Step 5445 | loss:1.2817360162734985 lr:7.469736390410062e-06 tokens_per_second_per_gpu:3836.9862187930903 mfu:18.09971865140206 Step 5446 | loss:1.271647334098816 lr:7.461947956979068e-06 tokens_per_second_per_gpu:4396.933335761609 mfu:20.741084738972162 Step 5447 | loss:1.2840033769607544 lr:7.454162873703499e-06 tokens_per_second_per_gpu:4384.735931946152 mfu:20.68354750408297 Step 5448 | loss:1.1800459623336792 lr:7.446381142070477e-06 tokens_per_second_per_gpu:4608.646912730872 mfu:21.739773803597195 Step 5449 | loss:1.1126575469970703 lr:7.438602763566491e-06 tokens_per_second_per_gpu:5264.2472691531175 mfu:24.832352541796062 Step 5450 | loss:1.0980793237686157 lr:7.4308277396773765e-06 tokens_per_second_per_gpu:5337.734802691567 mfu:25.179005775763052 Step 5451 | loss:1.209410548210144 lr:7.423056071888337e-06 tokens_per_second_per_gpu:4799.671493641885 mfu:22.640869343908744 Step 5452 | loss:1.4222313165664673 lr:7.415287761683937e-06 tokens_per_second_per_gpu:3850.816394559389 mfu:18.164957950163 Step 5453 | loss:1.2877299785614014 lr:7.40752281054809e-06 tokens_per_second_per_gpu:4732.759919915853 mfu:22.325236034351366 Step 5454 | loss:1.5200080871582031 lr:7.399761219964074e-06 tokens_per_second_per_gpu:5354.060483716597 mfu:25.256016798606527 Step 5455 | loss:1.398726463317871 lr:7.392002991414526e-06 tokens_per_second_per_gpu:5328.163441747063 mfu:25.133856033145257 Step 5456 | loss:1.3556474447250366 lr:7.384248126381437e-06 tokens_per_second_per_gpu:5312.8990995141985 mfu:25.061851526467496 Step 5457 | loss:1.2852797508239746 lr:7.37649662634616e-06 tokens_per_second_per_gpu:4457.228897273305 mfu:21.02550919010644 Step 5458 | loss:1.326061725616455 lr:7.368748492789401e-06 tokens_per_second_per_gpu:4608.046508840902 mfu:21.73694159600874 Step 5459 | loss:1.189421534538269 lr:7.361003727191226e-06 tokens_per_second_per_gpu:5336.308186229154 mfu:25.17227618250398 Step 5460 | loss:1.344893455505371 lr:7.353262331031055e-06 tokens_per_second_per_gpu:5303.606674757905 mfu:25.01801757344091 Step 5461 | loss:1.1434690952301025 lr:7.345524305787668e-06 tokens_per_second_per_gpu:4630.235302625101 mfu:21.84160992208741 Step 5462 | loss:1.2680957317352295 lr:7.337789652939195e-06 tokens_per_second_per_gpu:4550.230064061743 mfu:21.464211561482774 Step 5463 | loss:1.2901932001113892 lr:7.330058373963131e-06 tokens_per_second_per_gpu:4702.045144555275 mfu:22.18034919849446 Step 5464 | loss:1.2443971633911133 lr:7.3223304703363135e-06 tokens_per_second_per_gpu:4027.9874651065625 mfu:19.000704118435717 Step 5465 | loss:1.2935786247253418 lr:7.31460594353495e-06 tokens_per_second_per_gpu:4299.666852666418 mfu:20.28226214283887 Step 5466 | loss:1.3034095764160156 lr:7.306884795034591e-06 tokens_per_second_per_gpu:5360.120926442279 mfu:25.284604940961724 Step 5467 | loss:1.156531572341919 lr:7.2991670263101495e-06 tokens_per_second_per_gpu:4711.133585563702 mfu:22.22322092537914 Step 5468 | loss:1.2243318557739258 lr:7.291452638835891e-06 tokens_per_second_per_gpu:4640.440298985204 mfu:21.889748631069935 Step 5469 | loss:1.290789008140564 lr:7.283741634085428e-06 tokens_per_second_per_gpu:4145.018407352018 mfu:19.55275904054526 Step 5470 | loss:1.0907801389694214 lr:7.2760340135317375e-06 tokens_per_second_per_gpu:5325.463167184978 mfu:25.121118377321555 Step 5471 | loss:1.2888574600219727 lr:7.268329778647146e-06 tokens_per_second_per_gpu:4999.256349087236 mfu:23.582345159732206 Step 5472 | loss:1.2583330869674683 lr:7.260628930903329e-06 tokens_per_second_per_gpu:5324.816376507581 mfu:25.118067355342397 Step 5473 | loss:1.5166653394699097 lr:7.252931471771321e-06 tokens_per_second_per_gpu:4169.8299807750245 mfu:19.669799465672533 Step 5474 | loss:1.196714162826538 lr:7.245237402721508e-06 tokens_per_second_per_gpu:5051.995786745431 mfu:23.831126085441852 Step 5475 | loss:1.3459761142730713 lr:7.237546725223623e-06 tokens_per_second_per_gpu:4374.766510932338 mfu:20.636520044202182 Step 5476 | loss:1.2108452320098877 lr:7.229859440746758e-06 tokens_per_second_per_gpu:3906.028412392503 mfu:18.425402458423413 Step 5477 | loss:1.1617870330810547 lr:7.222175550759355e-06 tokens_per_second_per_gpu:4252.786368772738 mfu:20.061118901677034 Step 5478 | loss:1.2848231792449951 lr:7.214495056729204e-06 tokens_per_second_per_gpu:5307.737118332767 mfu:25.037501580509876 Step 5479 | loss:1.3625669479370117 lr:7.206817960123452e-06 tokens_per_second_per_gpu:5351.7031229990835 mfu:25.244896725894804 Step 5480 | loss:1.4405766725540161 lr:7.199144262408592e-06 tokens_per_second_per_gpu:3269.8118695077083 mfu:15.424260475900327 Step 5481 | loss:1.2025893926620483 lr:7.191473965050471e-06 tokens_per_second_per_gpu:4240.48466236374 mfu:20.003089653658254 Step 5482 | loss:1.3522400856018066 lr:7.183807069514287e-06 tokens_per_second_per_gpu:3571.261537043865 mfu:16.846249990285223 Step 5483 | loss:1.1244961023330688 lr:7.17614357726458e-06 tokens_per_second_per_gpu:4069.7334475120565 mfu:19.19762704004149 Step 5484 | loss:1.2788822650909424 lr:7.168483489765254e-06 tokens_per_second_per_gpu:5331.56530464539 mfu:25.149903200854325 Step 5485 | loss:1.1720006465911865 lr:7.1608268084795485e-06 tokens_per_second_per_gpu:5111.768013795476 mfu:24.11308187863045 Step 5486 | loss:1.231018304824829 lr:7.153173534870064e-06 tokens_per_second_per_gpu:5336.746516457956 mfu:25.174343860980088 Step 5487 | loss:1.0713469982147217 lr:7.1455236703987434e-06 tokens_per_second_per_gpu:4259.0086326163455 mfu:20.090470381855017 Step 5488 | loss:1.2807036638259888 lr:7.1378772165268784e-06 tokens_per_second_per_gpu:3870.112185449619 mfu:18.25597948799362 Step 5489 | loss:1.3159288167953491 lr:7.130234174715111e-06 tokens_per_second_per_gpu:4618.2053369327305 mfu:21.7848625213927 Step 5490 | loss:1.1461843252182007 lr:7.122594546423431e-06 tokens_per_second_per_gpu:5320.165802271043 mfu:25.096129803198867 Step 5491 | loss:1.263121247291565 lr:7.1149583331111765e-06 tokens_per_second_per_gpu:3782.5153390382716 mfu:17.84277021790816 Step 5492 | loss:1.261381983757019 lr:7.107325536237034e-06 tokens_per_second_per_gpu:5230.725577925518 mfu:24.674225004885184 Step 5493 | loss:1.4482593536376953 lr:7.099696157259034e-06 tokens_per_second_per_gpu:4006.534697700815 mfu:18.899507754363256 Step 5494 | loss:1.308526635169983 lr:7.092070197634559e-06 tokens_per_second_per_gpu:5073.389162076909 mfu:23.93204228696665 Step 5495 | loss:1.172208547592163 lr:7.084447658820334e-06 tokens_per_second_per_gpu:4690.863873206612 mfu:22.127605233821207 Step 5496 | loss:1.4007402658462524 lr:7.076828542272435e-06 tokens_per_second_per_gpu:4710.044969639894 mfu:22.218085738329513 Step 5497 | loss:1.4635735750198364 lr:7.0692128494462774e-06 tokens_per_second_per_gpu:3951.8083232315103 mfu:18.64135410870923 Step 5498 | loss:1.1139419078826904 lr:7.061600581796629e-06 tokens_per_second_per_gpu:5311.581119896413 mfu:25.05563439173989 Step 5499 | loss:0.9626551866531372 lr:7.0539917407776015e-06 tokens_per_second_per_gpu:5095.611175842306 mfu:24.03686731736454 Step 5500 | loss:1.430657982826233 lr:7.046386327842652e-06 tokens_per_second_per_gpu:5089.533029642532 mfu:24.008195664701525 Step 5501 | loss:1.3889826536178589 lr:7.038784344444582e-06 tokens_per_second_per_gpu:5344.494787715667 mfu:25.21089377849411 Step 5502 | loss:1.1617928743362427 lr:7.031185792035535e-06 tokens_per_second_per_gpu:5073.365112758132 mfu:23.931928842226743 Step 5503 | loss:1.3922553062438965 lr:7.02359067206701e-06 tokens_per_second_per_gpu:4589.092371205275 mfu:21.647531694872143 Step 5504 | loss:1.0832282304763794 lr:7.015998985989833e-06 tokens_per_second_per_gpu:4935.040271244639 mfu:23.279426964156013 Step 5505 | loss:1.0878634452819824 lr:7.008410735254192e-06 tokens_per_second_per_gpu:4282.57570508073 mfu:20.201640283626705 Step 5506 | loss:1.168531894683838 lr:7.000825921309606e-06 tokens_per_second_per_gpu:3980.8465713772493 mfu:18.7783324796487 Step 5507 | loss:1.2529127597808838 lr:6.993244545604944e-06 tokens_per_second_per_gpu:4639.641006798962 mfu:21.885978233454118 Step 5508 | loss:1.2016483545303345 lr:6.9856666095884145e-06 tokens_per_second_per_gpu:5335.360815850194 mfu:25.167807274788373 Step 5509 | loss:1.2223360538482666 lr:6.978092114707574e-06 tokens_per_second_per_gpu:3838.342976734083 mfu:18.1061187100965 Step 5510 | loss:1.3445124626159668 lr:6.970521062409313e-06 tokens_per_second_per_gpu:5341.878167525654 mfu:25.198550734616376 Step 5511 | loss:1.2108179330825806 lr:6.962953454139876e-06 tokens_per_second_per_gpu:5316.860764430693 mfu:25.080539375808335 Step 5512 | loss:1.2932820320129395 lr:6.955389291344838e-06 tokens_per_second_per_gpu:5311.1270757667935 mfu:25.053492588112558 Step 5513 | loss:1.2529091835021973 lr:6.947828575469126e-06 tokens_per_second_per_gpu:5317.440856895637 mfu:25.083275770939455 Step 5514 | loss:1.270411729812622 lr:6.9402713079569995e-06 tokens_per_second_per_gpu:4670.036395327949 mfu:22.0293584671334 Step 5515 | loss:1.3687690496444702 lr:6.932717490252066e-06 tokens_per_second_per_gpu:3297.2734548922563 mfu:15.553801459588854 Step 5516 | loss:1.506993055343628 lr:6.925167123797271e-06 tokens_per_second_per_gpu:3107.616573945811 mfu:14.65915759336385 Step 5517 | loss:1.1948314905166626 lr:6.9176202100349e-06 tokens_per_second_per_gpu:5313.506817468855 mfu:25.064718235746984 Step 5518 | loss:1.234322428703308 lr:6.9100767504065824e-06 tokens_per_second_per_gpu:4824.090423160979 mfu:22.756057600749305 Step 5519 | loss:1.2809525728225708 lr:6.902536746353286e-06 tokens_per_second_per_gpu:3729.0984151970774 mfu:17.590793474282247 Step 5520 | loss:1.2738116979599 lr:6.895000199315316e-06 tokens_per_second_per_gpu:5010.292462864463 mfu:23.634404391374563 Step 5521 | loss:1.2583225965499878 lr:6.887467110732321e-06 tokens_per_second_per_gpu:5303.560938969309 mfu:25.01780182992277 Step 5522 | loss:1.312434434890747 lr:6.879937482043286e-06 tokens_per_second_per_gpu:5294.041103477873 mfu:24.972895141658245 Step 5523 | loss:1.266028881072998 lr:6.872411314686539e-06 tokens_per_second_per_gpu:3667.0167981096174 mfu:17.297943894264588 Step 5524 | loss:1.1691720485687256 lr:6.86488861009974e-06 tokens_per_second_per_gpu:5305.696384761809 mfu:25.027875092070616 Step 5525 | loss:1.2334073781967163 lr:6.857369369719896e-06 tokens_per_second_per_gpu:5240.119310683583 mfu:24.71853684504105 Step 5526 | loss:1.3541085720062256 lr:6.849853594983344e-06 tokens_per_second_per_gpu:4073.5647435071414 mfu:19.21569991693681 Step 5527 | loss:1.2386376857757568 lr:6.842341287325768e-06 tokens_per_second_per_gpu:5343.086074184799 mfu:25.20424863641769 Step 5528 | loss:1.3557997941970825 lr:6.83483244818218e-06 tokens_per_second_per_gpu:3581.563078550924 mfu:16.894844119198243 Step 5529 | loss:1.432039499282837 lr:6.8273270789869366e-06 tokens_per_second_per_gpu:4463.055162395845 mfu:21.052992676752798 Step 5530 | loss:1.1303966045379639 lr:6.819825181173731e-06 tokens_per_second_per_gpu:4477.898789184678 mfu:21.123012596899603 Step 5531 | loss:1.182861328125 lr:6.812326756175586e-06 tokens_per_second_per_gpu:4493.177669650777 mfu:21.195085682904008 Step 5532 | loss:1.0851149559020996 lr:6.8048318054248714e-06 tokens_per_second_per_gpu:5337.28222886005 mfu:25.17687090778273 Step 5533 | loss:1.1944645643234253 lr:6.797340330353285e-06 tokens_per_second_per_gpu:5313.385754468834 mfu:25.06414716092041 Step 5534 | loss:1.1179478168487549 lr:6.7898523323918665e-06 tokens_per_second_per_gpu:4107.961745254299 mfu:19.37795644291181 Step 5535 | loss:1.3745726346969604 lr:6.782367812970988e-06 tokens_per_second_per_gpu:4838.523672426005 mfu:22.824141700098686 Step 5536 | loss:1.1432794332504272 lr:6.774886773520359e-06 tokens_per_second_per_gpu:5337.478375572796 mfu:25.17779616529283 Step 5537 | loss:1.1349608898162842 lr:6.767409215469022e-06 tokens_per_second_per_gpu:4379.140915606812 mfu:20.65715485740208 Step 5538 | loss:1.1029020547866821 lr:6.759935140245358e-06 tokens_per_second_per_gpu:5260.034608966284 mfu:24.812480704940825 Step 5539 | loss:1.2733019590377808 lr:6.7524645492770765e-06 tokens_per_second_per_gpu:5311.506490354373 mfu:25.055282351456974 Step 5540 | loss:1.1086957454681396 lr:6.7449974439912275e-06 tokens_per_second_per_gpu:5330.514551702383 mfu:25.144946619945223 Step 5541 | loss:1.3636443614959717 lr:6.737533825814193e-06 tokens_per_second_per_gpu:5334.6630555269285 mfu:25.164515820293342 Step 5542 | loss:1.2105739116668701 lr:6.730073696171691e-06 tokens_per_second_per_gpu:3770.794281535544 mfu:17.787479989849167 Step 5543 | loss:1.2172749042510986 lr:6.72261705648877e-06 tokens_per_second_per_gpu:5327.595082828558 mfu:25.131174987154633 Step 5544 | loss:1.2363123893737793 lr:6.715163908189811e-06 tokens_per_second_per_gpu:4554.221430860435 mfu:21.483039519669607 Step 5545 | loss:1.3452155590057373 lr:6.70771425269853e-06 tokens_per_second_per_gpu:5004.497390176136 mfu:23.607068044762364 Step 5546 | loss:1.396276593208313 lr:6.700268091437981e-06 tokens_per_second_per_gpu:5335.419126664354 mfu:25.168082336847615 Step 5547 | loss:1.4590381383895874 lr:6.692825425830537e-06 tokens_per_second_per_gpu:3398.201978550879 mfu:16.029898525868404 Step 5548 | loss:1.1839338541030884 lr:6.685386257297918e-06 tokens_per_second_per_gpu:4246.035396979084 mfu:20.02927341589181 Step 5549 | loss:1.4818482398986816 lr:6.677950587261167e-06 tokens_per_second_per_gpu:5361.1211963832475 mfu:25.28932338493692 Step 5550 | loss:1.2632408142089844 lr:6.670518417140664e-06 tokens_per_second_per_gpu:5299.136586279515 mfu:24.996931403412603 Step 5551 | loss:1.2153750658035278 lr:6.663089748356113e-06 tokens_per_second_per_gpu:3202.988720585863 mfu:15.109044281231123 Step 5552 | loss:1.2052185535430908 lr:6.655664582326557e-06 tokens_per_second_per_gpu:4027.124146085093 mfu:18.99663169531403 Step 5553 | loss:1.2213962078094482 lr:6.648242920470366e-06 tokens_per_second_per_gpu:4705.1704761514075 mfu:22.195091920869974 Step 5554 | loss:1.2298587560653687 lr:6.640824764205242e-06 tokens_per_second_per_gpu:5294.099642578144 mfu:24.973171280582022 Step 5555 | loss:1.212485671043396 lr:6.633410114948216e-06 tokens_per_second_per_gpu:4768.57388805291 mfu:22.49417663254692 Step 5556 | loss:1.366385817527771 lr:6.625998974115649e-06 tokens_per_second_per_gpu:4295.917438379572 mfu:20.264575515931774 Step 5557 | loss:1.294426679611206 lr:6.618591343123234e-06 tokens_per_second_per_gpu:4275.263900849016 mfu:20.167149255543272 Step 5558 | loss:1.2088934183120728 lr:6.611187223385995e-06 tokens_per_second_per_gpu:4793.329945779259 mfu:22.610955180661104 Step 5559 | loss:1.1953295469284058 lr:6.603786616318278e-06 tokens_per_second_per_gpu:5249.836295595808 mfu:24.764373520760603 Step 5560 | loss:1.348913550376892 lr:6.596389523333763e-06 tokens_per_second_per_gpu:4381.694444420879 mfu:20.669200288494974 Step 5561 | loss:1.2758821249008179 lr:6.588995945845458e-06 tokens_per_second_per_gpu:5344.632451148492 mfu:25.211543160394548 Step 5562 | loss:1.286954402923584 lr:6.581605885265701e-06 tokens_per_second_per_gpu:4525.017051942842 mfu:21.345277481534467 Step 5563 | loss:1.2339320182800293 lr:6.574219343006158e-06 tokens_per_second_per_gpu:4804.961130757002 mfu:22.66582146468591 Step 5564 | loss:1.1455172300338745 lr:6.566836320477818e-06 tokens_per_second_per_gpu:4391.2545805977625 mfu:20.71429708196876 Step 5565 | loss:1.2980378866195679 lr:6.559456819091006e-06 tokens_per_second_per_gpu:4800.924562004914 mfu:22.646780281172664 Step 5566 | loss:1.3599721193313599 lr:6.552080840255359e-06 tokens_per_second_per_gpu:5350.2893707758485 mfu:25.238227815446802 Step 5567 | loss:1.3603179454803467 lr:6.544708385379874e-06 tokens_per_second_per_gpu:3492.561391909151 mfu:16.475007978055405 Step 5568 | loss:1.3423084020614624 lr:6.537339455872835e-06 tokens_per_second_per_gpu:5354.242625705671 mfu:25.256875993445618 Step 5569 | loss:1.2865642309188843 lr:6.529974053141863e-06 tokens_per_second_per_gpu:5316.565643402362 mfu:25.079147239564858 Step 5570 | loss:1.2724870443344116 lr:6.522612178593943e-06 tokens_per_second_per_gpu:5325.835732771537 mfu:25.122875832759597 Step 5571 | loss:1.492586612701416 lr:6.515253833635326e-06 tokens_per_second_per_gpu:3572.7603675755836 mfu:16.8533202296302 Step 5572 | loss:1.2008435726165771 lr:6.507899019671626e-06 tokens_per_second_per_gpu:4650.261699946087 mfu:21.936077855106216 Step 5573 | loss:1.1420402526855469 lr:6.50054773810779e-06 tokens_per_second_per_gpu:5316.614628262426 mfu:25.079378309507458 Step 5574 | loss:1.0421572923660278 lr:6.493199990348056e-06 tokens_per_second_per_gpu:3761.2866515428186 mfu:17.742630877004533 Step 5575 | loss:1.2240227460861206 lr:6.485855777796007e-06 tokens_per_second_per_gpu:5325.065731649147 mfu:25.119243606089544 Step 5576 | loss:1.2046724557876587 lr:6.478515101854574e-06 tokens_per_second_per_gpu:5067.483723344949 mfu:23.904185324896247 Step 5577 | loss:1.334801197052002 lr:6.471177963925959e-06 tokens_per_second_per_gpu:4251.44035752472 mfu:20.054769536966937 Step 5578 | loss:1.4226086139678955 lr:6.4638443654117255e-06 tokens_per_second_per_gpu:3754.165593542542 mfu:17.70903963143945 Step 5579 | loss:1.258241891860962 lr:6.456514307712769e-06 tokens_per_second_per_gpu:4559.371104001753 mfu:21.50733140650204 Step 5580 | loss:1.1050018072128296 lr:6.449187792229275e-06 tokens_per_second_per_gpu:5347.870735626921 mfu:25.2268187007876 Step 5581 | loss:1.4044357538223267 lr:6.441864820360766e-06 tokens_per_second_per_gpu:4565.598347656363 mfu:21.536706377298163 Step 5582 | loss:1.1735121011734009 lr:6.434545393506114e-06 tokens_per_second_per_gpu:5317.9375587893865 mfu:25.085618798518354 Step 5583 | loss:1.317845344543457 lr:6.427229513063471e-06 tokens_per_second_per_gpu:4714.400398920152 mfu:22.23863104135735 Step 5584 | loss:1.1619634628295898 lr:6.419917180430332e-06 tokens_per_second_per_gpu:5249.426943453317 mfu:24.762442536861794 Step 5585 | loss:1.1909550428390503 lr:6.4126083970035365e-06 tokens_per_second_per_gpu:4887.818464292911 mfu:23.056673643893646 Step 5586 | loss:1.1068836450576782 lr:6.405303164179197e-06 tokens_per_second_per_gpu:4587.858952750053 mfu:21.641713449575967 Step 5587 | loss:1.46360182762146 lr:6.398001483352781e-06 tokens_per_second_per_gpu:5335.920818014557 mfu:25.170448900543896 Step 5588 | loss:1.2160695791244507 lr:6.390703355919087e-06 tokens_per_second_per_gpu:5287.998817451687 mfu:24.94439264755242 Step 5589 | loss:1.4412243366241455 lr:6.383408783272199e-06 tokens_per_second_per_gpu:4269.404867441962 mfu:20.139511195308017 Step 5590 | loss:1.4591948986053467 lr:6.376117766805542e-06 tokens_per_second_per_gpu:3902.414045679128 mfu:18.408352873961874 Step 5591 | loss:1.1995718479156494 lr:6.3688303079118825e-06 tokens_per_second_per_gpu:4780.534908016767 mfu:22.550598804476877 Step 5592 | loss:1.311774492263794 lr:6.361546407983266e-06 tokens_per_second_per_gpu:4802.590517786575 mfu:22.654638878836124 Step 5593 | loss:1.2219077348709106 lr:6.354266068411077e-06 tokens_per_second_per_gpu:4056.136949825377 mfu:19.133490040651704 Step 5594 | loss:1.3045896291732788 lr:6.346989290586042e-06 tokens_per_second_per_gpu:4260.851065342866 mfu:20.09916145137745 Step 5595 | loss:1.1194988489151 lr:6.339716075898164e-06 tokens_per_second_per_gpu:4214.804071622403 mfu:19.88194992557077 Step 5596 | loss:1.4927927255630493 lr:6.332446425736791e-06 tokens_per_second_per_gpu:4821.397846647878 mfu:22.74335625793608 Step 5597 | loss:1.3064236640930176 lr:6.325180341490608e-06 tokens_per_second_per_gpu:5308.4398338824 mfu:25.040816409653132 Step 5598 | loss:1.27577543258667 lr:6.3179178245475725e-06 tokens_per_second_per_gpu:5368.147128991605 mfu:25.32246590779826 Step 5599 | loss:1.1194831132888794 lr:6.310658876294989e-06 tokens_per_second_per_gpu:5347.3203542547435 mfu:25.224222457950297 Step 5600 | loss:1.199695110321045 lr:6.3034034981194954e-06 tokens_per_second_per_gpu:4378.745173469528 mfu:20.655288074219936 Step 5601 | loss:1.3636094331741333 lr:6.296151691407012e-06 tokens_per_second_per_gpu:3273.7856492692435 mfu:15.443005473032228 Step 5602 | loss:1.4366086721420288 lr:6.288903457542792e-06 tokens_per_second_per_gpu:4273.478463484767 mfu:20.158727042869085 Step 5603 | loss:1.2358869314193726 lr:6.281658797911427e-06 tokens_per_second_per_gpu:4194.510500337241 mfu:19.786221687378365 Step 5604 | loss:1.2680696249008179 lr:6.274417713896791e-06 tokens_per_second_per_gpu:3921.791495402498 mfu:18.49975961044085 Step 5605 | loss:1.233713150024414 lr:6.267180206882084e-06 tokens_per_second_per_gpu:3960.2954769773864 mfu:18.681389460986278 Step 5606 | loss:1.3613263368606567 lr:6.259946278249859e-06 tokens_per_second_per_gpu:4484.389729687514 mfu:21.15363147072013 Step 5607 | loss:1.2055373191833496 lr:6.2527159293819305e-06 tokens_per_second_per_gpu:4593.213624330575 mfu:21.666972349022465 Step 5608 | loss:1.2231907844543457 lr:6.245489161659454e-06 tokens_per_second_per_gpu:3953.2168038919745 mfu:18.64799815229622 Step 5609 | loss:1.409285306930542 lr:6.238265976462926e-06 tokens_per_second_per_gpu:4284.2894928313735 mfu:20.209724512848837 Step 5610 | loss:1.2322670221328735 lr:6.2310463751721115e-06 tokens_per_second_per_gpu:4576.229991061138 mfu:21.5868576531839 Step 5611 | loss:1.223902940750122 lr:6.2238303591661135e-06 tokens_per_second_per_gpu:4480.3887001358935 mfu:21.1347579316791 Step 5612 | loss:1.3139152526855469 lr:6.216617929823374e-06 tokens_per_second_per_gpu:5322.903843032513 mfu:25.109045608628648 Step 5613 | loss:1.2745130062103271 lr:6.209409088521603e-06 tokens_per_second_per_gpu:4940.246926303899 mfu:23.303987644417496 Step 5614 | loss:1.4519798755645752 lr:6.202203836637846e-06 tokens_per_second_per_gpu:4733.061324372633 mfu:22.3266578105989 Step 5615 | loss:1.3329813480377197 lr:6.195002175548492e-06 tokens_per_second_per_gpu:4464.974835055576 mfu:21.062048100218675 Step 5616 | loss:1.1351338624954224 lr:6.1878041066291944e-06 tokens_per_second_per_gpu:4781.250158862463 mfu:22.5539727647504 Step 5617 | loss:1.3898004293441772 lr:6.180609631254941e-06 tokens_per_second_per_gpu:5304.073097333264 mfu:25.020217768308772 Step 5618 | loss:1.2608717679977417 lr:6.173418750800059e-06 tokens_per_second_per_gpu:5319.754797294284 mfu:25.094191022598814 Step 5619 | loss:1.3458393812179565 lr:6.166231466638145e-06 tokens_per_second_per_gpu:4714.9666802253505 mfu:22.24130228689153 Step 5620 | loss:1.2731741666793823 lr:6.1590477801421244e-06 tokens_per_second_per_gpu:3861.027770485866 mfu:18.213126752648577 Step 5621 | loss:1.2800344228744507 lr:6.151867692684268e-06 tokens_per_second_per_gpu:5314.98083387061 mfu:25.071671422607196 Step 5622 | loss:1.088208556175232 lr:6.144691205636105e-06 tokens_per_second_per_gpu:4157.575427231426 mfu:19.611992645764946 Step 5623 | loss:1.1863913536071777 lr:6.137518320368505e-06 tokens_per_second_per_gpu:4343.228629096574 mfu:20.487750474665383 Step 5624 | loss:1.2731726169586182 lr:6.130349038251668e-06 tokens_per_second_per_gpu:4718.284787222478 mfu:22.256954363724407 Step 5625 | loss:1.3520774841308594 lr:6.123183360655063e-06 tokens_per_second_per_gpu:4000.0183750666333 mfu:18.868769148698536 Step 5626 | loss:1.330655813217163 lr:6.116021288947493e-06 tokens_per_second_per_gpu:4079.8136200501876 mfu:19.245176933758632 Step 5627 | loss:1.3607743978500366 lr:6.108862824497097e-06 tokens_per_second_per_gpu:4306.31481382683 mfu:20.313621709891667 Step 5628 | loss:1.1838823556900024 lr:6.101707968671275e-06 tokens_per_second_per_gpu:5328.71425093954 mfu:25.136454294083908 Step 5629 | loss:1.364231824874878 lr:6.094556722836764e-06 tokens_per_second_per_gpu:3747.6420998607523 mfu:17.678267198719656 Step 5630 | loss:1.198303461074829 lr:6.08740908835963e-06 tokens_per_second_per_gpu:4749.346797549837 mfu:22.40347916616401 Step 5631 | loss:1.2664834260940552 lr:6.080265066605201e-06 tokens_per_second_per_gpu:5029.281314798871 mfu:23.723978045781383 Step 5632 | loss:1.2361794710159302 lr:6.073124658938165e-06 tokens_per_second_per_gpu:4117.691967929361 mfu:19.42385556341726 Step 5633 | loss:1.326370120048523 lr:6.065987866722497e-06 tokens_per_second_per_gpu:4972.085717974992 mfu:23.454176656988057 Step 5634 | loss:1.258726716041565 lr:6.0588546913214615e-06 tokens_per_second_per_gpu:4877.412250962137 mfu:23.007585760129306 Step 5635 | loss:1.1866340637207031 lr:6.051725134097675e-06 tokens_per_second_per_gpu:5328.83994554177 mfu:25.13704721696834 Step 5636 | loss:1.1681413650512695 lr:6.044599196413034e-06 tokens_per_second_per_gpu:5327.6557797059095 mfu:25.13146130468106 Step 5637 | loss:1.1316442489624023 lr:6.037476879628736e-06 tokens_per_second_per_gpu:5013.375443616624 mfu:23.648947337593263 Step 5638 | loss:1.141477346420288 lr:6.030358185105323e-06 tokens_per_second_per_gpu:4106.662129192199 mfu:19.37182593220952 Step 5639 | loss:1.2364436388015747 lr:6.023243114202615e-06 tokens_per_second_per_gpu:5221.1265492286375 mfu:24.628944748758823 Step 5640 | loss:1.252665400505066 lr:6.016131668279732e-06 tokens_per_second_per_gpu:5305.550549661107 mfu:25.027187163018567 Step 5641 | loss:1.1311490535736084 lr:6.009023848695139e-06 tokens_per_second_per_gpu:4351.9458446308 mfu:20.528871067650662 Step 5642 | loss:1.2943040132522583 lr:6.001919656806585e-06 tokens_per_second_per_gpu:4086.406720326397 mfu:19.276277712660416 Step 5643 | loss:1.2562510967254639 lr:5.994819093971105e-06 tokens_per_second_per_gpu:4775.037928361489 mfu:22.52466861356149 Step 5644 | loss:1.1352840662002563 lr:5.9877221615450866e-06 tokens_per_second_per_gpu:5244.25505648778 mfu:24.738045863630447 Step 5645 | loss:1.2785613536834717 lr:5.980628860884202e-06 tokens_per_second_per_gpu:4067.6264208084817 mfu:19.187687835584903 Step 5646 | loss:1.0342613458633423 lr:5.973539193343406e-06 tokens_per_second_per_gpu:5338.525182035229 mfu:25.182734129979725 Step 5647 | loss:1.2608082294464111 lr:5.966453160277e-06 tokens_per_second_per_gpu:4689.342140999625 mfu:22.120426963366565 Step 5648 | loss:1.186396598815918 lr:5.959370763038577e-06 tokens_per_second_per_gpu:4083.0736431876244 mfu:19.260555019115227 Step 5649 | loss:1.2168686389923096 lr:5.952292002981005e-06 tokens_per_second_per_gpu:5138.933938714758 mfu:24.24122818145944 Step 5650 | loss:1.1693590879440308 lr:5.945216881456511e-06 tokens_per_second_per_gpu:4104.937238225472 mfu:19.363689327222726 Step 5651 | loss:1.132033109664917 lr:5.938145399816597e-06 tokens_per_second_per_gpu:5292.735403154539 mfu:24.966735930457634 Step 5652 | loss:1.3062365055084229 lr:5.931077559412051e-06 tokens_per_second_per_gpu:3786.7953071383845 mfu:17.86295955767425 Step 5653 | loss:1.1890615224838257 lr:5.924013361593006e-06 tokens_per_second_per_gpu:4746.845700735961 mfu:22.39168106576184 Step 5654 | loss:1.4317744970321655 lr:5.9169528077088834e-06 tokens_per_second_per_gpu:3507.549322005969 mfu:16.54570860152666 Step 5655 | loss:1.2846524715423584 lr:5.909895899108381e-06 tokens_per_second_per_gpu:5342.173769471739 mfu:25.199945139430955 Step 5656 | loss:1.1677900552749634 lr:5.902842637139547e-06 tokens_per_second_per_gpu:3419.169332641226 mfu:16.128805112512065 Step 5657 | loss:1.2338181734085083 lr:5.8957930231497065e-06 tokens_per_second_per_gpu:4357.247054931446 mfu:20.55387778111855 Step 5658 | loss:1.367089867591858 lr:5.888747058485477e-06 tokens_per_second_per_gpu:4877.8944357332075 mfu:23.009860307963653 Step 5659 | loss:1.3510465621948242 lr:5.881704744492808e-06 tokens_per_second_per_gpu:5332.584130287363 mfu:25.15470917523709 Step 5660 | loss:1.1664254665374756 lr:5.874666082516941e-06 tokens_per_second_per_gpu:5319.524524812764 mfu:25.093104788014948 Step 5661 | loss:1.1628187894821167 lr:5.867631073902397e-06 tokens_per_second_per_gpu:5146.7130443863625 mfu:24.277923550164687 Step 5662 | loss:1.199103593826294 lr:5.8605997199930316e-06 tokens_per_second_per_gpu:4345.619361787359 mfu:20.49902796866887 Step 5663 | loss:1.2510088682174683 lr:5.853572022131998e-06 tokens_per_second_per_gpu:5333.144856034162 mfu:25.157354214254422 Step 5664 | loss:1.249595284461975 lr:5.8465479816617124e-06 tokens_per_second_per_gpu:4979.1701211756335 mfu:23.48759499560931 Step 5665 | loss:1.3428033590316772 lr:5.8395275999239465e-06 tokens_per_second_per_gpu:4843.979012483982 mfu:22.849875469929156 Step 5666 | loss:1.1776447296142578 lr:5.832510878259751e-06 tokens_per_second_per_gpu:5330.274483525498 mfu:25.143814177395 Step 5667 | loss:1.1824212074279785 lr:5.825497818009445e-06 tokens_per_second_per_gpu:5308.085989576736 mfu:25.039147265691252 Step 5668 | loss:1.250901460647583 lr:5.81848842051271e-06 tokens_per_second_per_gpu:4959.643446988393 mfu:23.39548434187394 Step 5669 | loss:1.2728219032287598 lr:5.8114826871084886e-06 tokens_per_second_per_gpu:3917.0956917331036 mfu:18.477608703345595 Step 5670 | loss:1.210994839668274 lr:5.804480619135014e-06 tokens_per_second_per_gpu:4978.931783921203 mfu:23.486470718115626 Step 5671 | loss:1.2343064546585083 lr:5.79748221792985e-06 tokens_per_second_per_gpu:4019.2857013262565 mfu:18.95965641401002 Step 5672 | loss:1.3053267002105713 lr:5.790487484829854e-06 tokens_per_second_per_gpu:4998.3973207578965 mfu:23.578292976537366 Step 5673 | loss:1.3423665761947632 lr:5.78349642117115e-06 tokens_per_second_per_gpu:4281.267277127374 mfu:20.195468205729902 Step 5674 | loss:1.2886862754821777 lr:5.7765090282892065e-06 tokens_per_second_per_gpu:5374.52226416418 mfu:25.352538508117515 Step 5675 | loss:1.296268343925476 lr:5.7695253075187696e-06 tokens_per_second_per_gpu:3773.9618555946304 mfu:17.802421977129743 Step 5676 | loss:1.1969656944274902 lr:5.7625452601938636e-06 tokens_per_second_per_gpu:5310.585693090516 mfu:25.050938793659146 Step 5677 | loss:1.32137930393219 lr:5.755568887647852e-06 tokens_per_second_per_gpu:5328.666707023398 mfu:25.136230021319637 Step 5678 | loss:1.3338719606399536 lr:5.748596191213376e-06 tokens_per_second_per_gpu:3857.8157057930266 mfu:18.19797489545771 Step 5679 | loss:1.2433706521987915 lr:5.741627172222358e-06 tokens_per_second_per_gpu:4413.315097133889 mfu:20.81836030238191 Step 5680 | loss:1.2761527299880981 lr:5.7346618320060495e-06 tokens_per_second_per_gpu:5331.671310197368 mfu:25.150403247129418 Step 5681 | loss:1.2978246212005615 lr:5.7277001718949895e-06 tokens_per_second_per_gpu:4678.2081876263255 mfu:22.067906205656374 Step 5682 | loss:1.223104476928711 lr:5.720742193218984e-06 tokens_per_second_per_gpu:5215.767061315604 mfu:24.603663129850116 Step 5683 | loss:1.1984047889709473 lr:5.713787897307182e-06 tokens_per_second_per_gpu:3612.9398781456644 mfu:17.04285383632067 Step 5684 | loss:1.1722736358642578 lr:5.706837285488012e-06 tokens_per_second_per_gpu:5335.053781151298 mfu:25.16635893972816 Step 5685 | loss:1.4540667533874512 lr:5.699890359089166e-06 tokens_per_second_per_gpu:3653.4157778692374 mfu:17.233785561217374 Step 5686 | loss:1.2556239366531372 lr:5.692947119437689e-06 tokens_per_second_per_gpu:5319.8966267005935 mfu:25.09486005610697 Step 5687 | loss:1.3602790832519531 lr:5.686007567859889e-06 tokens_per_second_per_gpu:4235.873097043198 mfu:19.981336113227073 Step 5688 | loss:1.1963810920715332 lr:5.679071705681352e-06 tokens_per_second_per_gpu:4603.080754468375 mfu:21.71351728538847 Step 5689 | loss:1.2877380847930908 lr:5.672139534227006e-06 tokens_per_second_per_gpu:4355.751096494188 mfu:20.54682108993318 Step 5690 | loss:1.1341869831085205 lr:5.665211054821046e-06 tokens_per_second_per_gpu:4967.5379817635085 mfu:23.43272420935468 Step 5691 | loss:1.3518069982528687 lr:5.658286268786941e-06 tokens_per_second_per_gpu:4308.780531732273 mfu:20.3252529219465 Step 5692 | loss:1.1694912910461426 lr:5.6513651774475044e-06 tokens_per_second_per_gpu:4921.289623301737 mfu:23.21456281170688 Step 5693 | loss:1.2412528991699219 lr:5.644447782124815e-06 tokens_per_second_per_gpu:5299.686308286164 mfu:24.99952453591021 Step 5694 | loss:1.2517708539962769 lr:5.637534084140228e-06 tokens_per_second_per_gpu:5320.628982117955 mfu:25.098314701563385 Step 5695 | loss:1.2298825979232788 lr:5.630624084814431e-06 tokens_per_second_per_gpu:5046.36637659313 mfu:23.80457119727703 Step 5696 | loss:1.5715798139572144 lr:5.623717785467392e-06 tokens_per_second_per_gpu:2697.415582821756 mfu:12.72416953072571 Step 5697 | loss:1.324181318283081 lr:5.61681518741834e-06 tokens_per_second_per_gpu:4954.309431480394 mfu:23.370322880645816 Step 5698 | loss:1.1728715896606445 lr:5.609916291985845e-06 tokens_per_second_per_gpu:5157.236469438306 mfu:24.327564341616164 Step 5699 | loss:1.3600959777832031 lr:5.6030211004877456e-06 tokens_per_second_per_gpu:4139.487396289141 mfu:19.526668317673874 Step 5700 | loss:1.1368224620819092 lr:5.5961296142411746e-06 tokens_per_second_per_gpu:4197.389234143834 mfu:19.799801165906697 Step 5701 | loss:1.2668585777282715 lr:5.589241834562556e-06 tokens_per_second_per_gpu:3815.7158518402907 mfu:17.99938270138688 Step 5702 | loss:1.1244231462478638 lr:5.582357762767607e-06 tokens_per_second_per_gpu:4958.623594408673 mfu:23.390673523250605 Step 5703 | loss:1.0692453384399414 lr:5.575477400171342e-06 tokens_per_second_per_gpu:4457.725689095765 mfu:21.02785264189441 Step 5704 | loss:1.2965319156646729 lr:5.568600748088057e-06 tokens_per_second_per_gpu:5320.829352583079 mfu:25.099259883234094 Step 5705 | loss:1.323224663734436 lr:5.561727807831349e-06 tokens_per_second_per_gpu:3867.279179466888 mfu:18.242615715412416 Step 5706 | loss:1.2911109924316406 lr:5.554858580714098e-06 tokens_per_second_per_gpu:5075.671085837611 mfu:23.94280651068222 Step 5707 | loss:1.3868560791015625 lr:5.547993068048482e-06 tokens_per_second_per_gpu:5311.032519198778 mfu:25.053046548648215 Step 5708 | loss:1.310387134552002 lr:5.5411312711459605e-06 tokens_per_second_per_gpu:5315.541101446038 mfu:25.074314300351993 Step 5709 | loss:1.190795660018921 lr:5.534273191317294e-06 tokens_per_second_per_gpu:4897.930105753994 mfu:23.104371981889507 Step 5710 | loss:1.3221715688705444 lr:5.527418829872521e-06 tokens_per_second_per_gpu:4433.994825624727 mfu:20.915910109998705 Step 5711 | loss:1.3582215309143066 lr:5.520568188120984e-06 tokens_per_second_per_gpu:5052.579791895336 mfu:23.833880937375504 Step 5712 | loss:1.26732337474823 lr:5.5137212673713e-06 tokens_per_second_per_gpu:4081.490654966446 mfu:19.253087793590286 Step 5713 | loss:1.0814423561096191 lr:5.50687806893139e-06 tokens_per_second_per_gpu:5332.65899122388 mfu:25.15506230704723 Step 5714 | loss:1.1336742639541626 lr:5.500038594108436e-06 tokens_per_second_per_gpu:5290.761242669647 mfu:24.957423478623884 Step 5715 | loss:1.2166000604629517 lr:5.493202844208953e-06 tokens_per_second_per_gpu:5000.679558280684 mfu:23.589058680322232 Step 5716 | loss:1.4408702850341797 lr:5.4863708205387165e-06 tokens_per_second_per_gpu:4527.876880178663 mfu:21.358767779259843 Step 5717 | loss:1.3144948482513428 lr:5.479542524402773e-06 tokens_per_second_per_gpu:5308.377299526284 mfu:25.040521424425872 Step 5718 | loss:1.1962957382202148 lr:5.472717957105503e-06 tokens_per_second_per_gpu:4305.800449558735 mfu:20.31119536587947 Step 5719 | loss:1.3695716857910156 lr:5.465897119950542e-06 tokens_per_second_per_gpu:5339.947213910002 mfu:25.189442096956686 Step 5720 | loss:1.3358787298202515 lr:5.459080014240809e-06 tokens_per_second_per_gpu:5316.527435668423 mfu:25.078967007164955 Step 5721 | loss:1.2919522523880005 lr:5.452266641278533e-06 tokens_per_second_per_gpu:4647.265394802812 mfu:21.92194377252301 Step 5722 | loss:1.1764743328094482 lr:5.445457002365228e-06 tokens_per_second_per_gpu:4375.841875937267 mfu:20.641592724406625 Step 5723 | loss:1.3337188959121704 lr:5.438651098801659e-06 tokens_per_second_per_gpu:5190.0744311565 mfu:24.482466609774892 Step 5724 | loss:1.35503089427948 lr:5.431848931887926e-06 tokens_per_second_per_gpu:3397.8400655335404 mfu:16.028191320416887 Step 5725 | loss:1.3516899347305298 lr:5.425050502923393e-06 tokens_per_second_per_gpu:4082.10749092996 mfu:19.25599751407325 Step 5726 | loss:1.2253663539886475 lr:5.418255813206688e-06 tokens_per_second_per_gpu:4493.68608033459 mfu:21.197483942843363 Step 5727 | loss:1.2027806043624878 lr:5.411464864035773e-06 tokens_per_second_per_gpu:5338.249370152407 mfu:25.181433078270096 Step 5728 | loss:1.3489917516708374 lr:5.404677656707862e-06 tokens_per_second_per_gpu:5314.917997584756 mfu:25.07137501312585 Step 5729 | loss:1.299382209777832 lr:5.397894192519445e-06 tokens_per_second_per_gpu:5064.724639625335 mfu:23.891170256242603 Step 5730 | loss:1.2079412937164307 lr:5.391114472766337e-06 tokens_per_second_per_gpu:5321.406422467198 mfu:25.101982020335765 Step 5731 | loss:1.1627110242843628 lr:5.384338498743608e-06 tokens_per_second_per_gpu:3530.3819858188513 mfu:16.65341417238618 Step 5732 | loss:1.4065862894058228 lr:5.377566271745602e-06 tokens_per_second_per_gpu:4211.4557498647455 mfu:19.866155320557297 Step 5733 | loss:1.268816590309143 lr:5.370797793065985e-06 tokens_per_second_per_gpu:5316.037923971736 mfu:25.07665789697237 Step 5734 | loss:1.3195250034332275 lr:5.364033063997681e-06 tokens_per_second_per_gpu:4365.214366533845 mfu:20.591460949310605 Step 5735 | loss:1.3450124263763428 lr:5.357272085832887e-06 tokens_per_second_per_gpu:3601.564121034535 mfu:16.989192449123173 Step 5736 | loss:1.1664232015609741 lr:5.35051485986312e-06 tokens_per_second_per_gpu:5351.062039838245 mfu:25.241872627245062 Step 5737 | loss:1.5378988981246948 lr:5.343761387379159e-06 tokens_per_second_per_gpu:3914.3797942091505 mfu:18.464797351345208 Step 5738 | loss:1.2029112577438354 lr:5.337011669671044e-06 tokens_per_second_per_gpu:5333.895231185469 mfu:25.16089386187034 Step 5739 | loss:1.210313081741333 lr:5.3302657080281394e-06 tokens_per_second_per_gpu:4009.178282829228 mfu:18.911977996456113 Step 5740 | loss:1.0703703165054321 lr:5.323523503739078e-06 tokens_per_second_per_gpu:5251.630251113941 mfu:24.772835915020007 Step 5741 | loss:1.2425817251205444 lr:5.316785058091744e-06 tokens_per_second_per_gpu:5332.8412836142725 mfu:25.155922211355005 Step 5742 | loss:1.154390573501587 lr:5.3100503723733545e-06 tokens_per_second_per_gpu:4164.678846268062 mfu:19.64550068532902 Step 5743 | loss:1.224068522453308 lr:5.303319447870378e-06 tokens_per_second_per_gpu:5314.061663298935 mfu:25.067335538193934 Step 5744 | loss:1.3540470600128174 lr:5.2965922858685545e-06 tokens_per_second_per_gpu:4481.944317727364 mfu:21.1420960452738 Step 5745 | loss:1.1771254539489746 lr:5.289868887652941e-06 tokens_per_second_per_gpu:5324.112496271087 mfu:25.11474703217251 Step 5746 | loss:1.2302258014678955 lr:5.283149254507849e-06 tokens_per_second_per_gpu:4807.5305646521465 mfu:22.67794192275993 Step 5747 | loss:1.2547569274902344 lr:5.276433387716864e-06 tokens_per_second_per_gpu:4991.55128867192 mfu:23.545999075134294 Step 5748 | loss:1.365364670753479 lr:5.269721288562879e-06 tokens_per_second_per_gpu:4573.905520448734 mfu:21.575892728709604 Step 5749 | loss:1.2746596336364746 lr:5.263012958328059e-06 tokens_per_second_per_gpu:3813.3092758373446 mfu:17.988030471776778 Step 5750 | loss:1.2970046997070312 lr:5.256308398293816e-06 tokens_per_second_per_gpu:3702.712365004243 mfu:17.46632597359826 Step 5751 | loss:1.2900066375732422 lr:5.249607609740898e-06 tokens_per_second_per_gpu:4875.109968770336 mfu:22.996725502220738 Step 5752 | loss:1.281472086906433 lr:5.242910593949296e-06 tokens_per_second_per_gpu:4680.386762664203 mfu:22.07818291581328 Step 5753 | loss:1.3436729907989502 lr:5.236217352198272e-06 tokens_per_second_per_gpu:4229.754644273607 mfu:19.952474327597226 Step 5754 | loss:1.2453817129135132 lr:5.229527885766403e-06 tokens_per_second_per_gpu:5282.663209652862 mfu:24.919223675216806 Step 5755 | loss:1.4086259603500366 lr:5.222842195931521e-06 tokens_per_second_per_gpu:4346.953334973723 mfu:20.505320547788248 Step 5756 | loss:1.2887043952941895 lr:5.216160283970725e-06 tokens_per_second_per_gpu:3095.1764285035333 mfu:14.600475304804945 Step 5757 | loss:1.3084216117858887 lr:5.209482151160427e-06 tokens_per_second_per_gpu:5334.486235386247 mfu:25.163681729521123 Step 5758 | loss:1.3293582201004028 lr:5.2028077987762965e-06 tokens_per_second_per_gpu:4024.836631071468 mfu:18.98584109670446 Step 5759 | loss:1.2383838891983032 lr:5.196137228093264e-06 tokens_per_second_per_gpu:5306.109970243981 mfu:25.029826045354977 Step 5760 | loss:1.4707626104354858 lr:5.189470440385574e-06 tokens_per_second_per_gpu:5009.468047871478 mfu:23.63051548519295 Step 5761 | loss:1.262017846107483 lr:5.182807436926731e-06 tokens_per_second_per_gpu:4331.546430038551 mfu:20.432643548519994 Step 5762 | loss:1.127925992012024 lr:5.176148218989496e-06 tokens_per_second_per_gpu:5349.745727686 mfu:25.23566335823691 Step 5763 | loss:1.3240461349487305 lr:5.1694927878459475e-06 tokens_per_second_per_gpu:4503.899058317737 mfu:21.245660302503595 Step 5764 | loss:1.3743823766708374 lr:5.162841144767411e-06 tokens_per_second_per_gpu:5309.175216442602 mfu:25.044285334658802 Step 5765 | loss:1.33344566822052 lr:5.156193291024497e-06 tokens_per_second_per_gpu:4769.100680010049 mfu:22.49666160008872 Step 5766 | loss:1.1853432655334473 lr:5.149549227887099e-06 tokens_per_second_per_gpu:5332.039295477412 mfu:25.15213909648015 Step 5767 | loss:1.187840461730957 lr:5.14290895662437e-06 tokens_per_second_per_gpu:4719.778694525102 mfu:22.264001379357754 Step 5768 | loss:1.585193395614624 lr:5.136272478504755e-06 tokens_per_second_per_gpu:4281.226029493473 mfu:20.195273633603218 Step 5769 | loss:1.0733368396759033 lr:5.129639794795968e-06 tokens_per_second_per_gpu:4566.37532771643 mfu:21.540371524807963 Step 5770 | loss:1.177639365196228 lr:5.123010906764996e-06 tokens_per_second_per_gpu:5314.348004243028 mfu:25.06868625728202 Step 5771 | loss:1.2623710632324219 lr:5.116385815678104e-06 tokens_per_second_per_gpu:5130.612415937435 mfu:24.201974138720615 Step 5772 | loss:1.3248332738876343 lr:5.10976452280083e-06 tokens_per_second_per_gpu:4953.153958263155 mfu:23.364872316336037 Step 5773 | loss:1.2640055418014526 lr:5.103147029397987e-06 tokens_per_second_per_gpu:5295.88359351595 mfu:24.98158648152907 Step 5774 | loss:1.264220952987671 lr:5.0965333367336636e-06 tokens_per_second_per_gpu:3590.220358943006 mfu:16.93568198789204 Step 5775 | loss:1.1522201299667358 lr:5.089923446071221e-06 tokens_per_second_per_gpu:5289.443210572925 mfu:24.951206096344183 Step 5776 | loss:1.2147525548934937 lr:5.083317358673293e-06 tokens_per_second_per_gpu:3325.849964030625 mfu:15.68860172884976 Step 5777 | loss:1.2791563272476196 lr:5.076715075801791e-06 tokens_per_second_per_gpu:5332.2867763511385 mfu:25.15330650598611 Step 5778 | loss:1.3057398796081543 lr:5.0701165987178945e-06 tokens_per_second_per_gpu:4684.157242094906 mfu:22.09596891059803 Step 5779 | loss:1.2801932096481323 lr:5.063521928682058e-06 tokens_per_second_per_gpu:4673.289855352128 mfu:22.04470559316497 Step 5780 | loss:1.353580355644226 lr:5.056931066954013e-06 tokens_per_second_per_gpu:4061.8853790688872 mfu:19.16060636217651 Step 5781 | loss:1.067034125328064 lr:5.050344014792755e-06 tokens_per_second_per_gpu:5319.418712194662 mfu:25.092605651841865 Step 5782 | loss:1.2807643413543701 lr:5.043760773456557e-06 tokens_per_second_per_gpu:3946.866119256941 mfu:18.618040889334242 Step 5783 | loss:1.3165194988250732 lr:5.037181344202968e-06 tokens_per_second_per_gpu:5328.448154087457 mfu:25.135199069831828 Step 5784 | loss:1.2914081811904907 lr:5.030605728288801e-06 tokens_per_second_per_gpu:5319.93668469438 mfu:25.095049016498262 Step 5785 | loss:1.2658073902130127 lr:5.0240339269701425e-06 tokens_per_second_per_gpu:5345.892521819192 mfu:25.217487128738462 Step 5786 | loss:1.416496753692627 lr:5.017465941502356e-06 tokens_per_second_per_gpu:4968.236003663063 mfu:23.436016897749695 Step 5787 | loss:1.431130290031433 lr:5.010901773140067e-06 tokens_per_second_per_gpu:4754.062929588357 mfu:22.425725965644812 Step 5788 | loss:1.1404194831848145 lr:5.004341423137179e-06 tokens_per_second_per_gpu:5331.266196653326 mfu:25.148492257422674 Step 5789 | loss:1.180532693862915 lr:4.997784892746865e-06 tokens_per_second_per_gpu:4596.8051916929235 mfu:21.683914385055246 Step 5790 | loss:1.3307034969329834 lr:4.991232183221567e-06 tokens_per_second_per_gpu:3869.0627533099732 mfu:18.251029137539323 Step 5791 | loss:1.1304179430007935 lr:4.9846832958129974e-06 tokens_per_second_per_gpu:4256.035885893355 mfu:20.076447428359778 Step 5792 | loss:1.1731890439987183 lr:4.978138231772133e-06 tokens_per_second_per_gpu:4372.1862809792365 mfu:20.62434865928078 Step 5793 | loss:1.2638328075408936 lr:4.971596992349234e-06 tokens_per_second_per_gpu:5263.088344890072 mfu:24.826885698314406 Step 5794 | loss:1.414559006690979 lr:4.965059578793815e-06 tokens_per_second_per_gpu:4248.669909222656 mfu:20.04170085963888 Step 5795 | loss:1.2235724925994873 lr:4.958525992354671e-06 tokens_per_second_per_gpu:3963.9490206547257 mfu:18.698623849871115 Step 5796 | loss:1.2831281423568726 lr:4.9519962342798596e-06 tokens_per_second_per_gpu:4602.25197240391 mfu:21.70960777898559 Step 5797 | loss:1.153135895729065 lr:4.945470305816707e-06 tokens_per_second_per_gpu:4296.769666029291 mfu:20.268595619160536 Step 5798 | loss:1.352193832397461 lr:4.938948208211813e-06 tokens_per_second_per_gpu:5298.88352861872 mfu:24.995737687250546 Step 5799 | loss:1.2592467069625854 lr:4.932429942711039e-06 tokens_per_second_per_gpu:4812.8891633191815 mfu:22.70321934694355 Step 5800 | loss:1.360321283340454 lr:4.925915510559523e-06 tokens_per_second_per_gpu:3951.7626046454275 mfu:18.641138446338285 Step 5801 | loss:1.2556006908416748 lr:4.919404913001657e-06 tokens_per_second_per_gpu:4800.309672009154 mfu:22.64387974015161 Step 5802 | loss:1.3395048379898071 lr:4.912898151281117e-06 tokens_per_second_per_gpu:4023.6314327096593 mfu:18.980155970403757 Step 5803 | loss:1.3134269714355469 lr:4.906395226640837e-06 tokens_per_second_per_gpu:4459.559884263928 mfu:21.0365048534486 Step 5804 | loss:1.3282865285873413 lr:4.899896140323013e-06 tokens_per_second_per_gpu:3269.9863164796043 mfu:15.425083372030484 Step 5805 | loss:1.2612755298614502 lr:4.8934008935691225e-06 tokens_per_second_per_gpu:4844.708003281868 mfu:22.85331424390144 Step 5806 | loss:1.6882448196411133 lr:4.8869094876198926e-06 tokens_per_second_per_gpu:3975.6757641558274 mfu:18.753940899754568 Step 5807 | loss:1.270439624786377 lr:4.880421923715334e-06 tokens_per_second_per_gpu:4905.345110076981 mfu:23.139349822411226 Step 5808 | loss:1.3843226432800293 lr:4.873938203094707e-06 tokens_per_second_per_gpu:4250.949424924505 mfu:20.052453724129986 Step 5809 | loss:1.3268965482711792 lr:4.867458326996551e-06 tokens_per_second_per_gpu:5333.089970654261 mfu:25.157095310553014 Step 5810 | loss:1.1553345918655396 lr:4.860982296658667e-06 tokens_per_second_per_gpu:4030.3442562950368 mfu:19.011821504581793 Step 5811 | loss:1.2434954643249512 lr:4.854510113318111e-06 tokens_per_second_per_gpu:4888.393353666833 mfu:23.059385495156675 Step 5812 | loss:1.3472288846969604 lr:4.848041778211221e-06 tokens_per_second_per_gpu:3850.1335911066044 mfu:18.16173704977793 Step 5813 | loss:1.2701655626296997 lr:4.84157729257359e-06 tokens_per_second_per_gpu:5321.184492365741 mfu:25.10093513818201 Step 5814 | loss:1.3848577737808228 lr:4.835116657640076e-06 tokens_per_second_per_gpu:2934.727998760404 mfu:13.843612686381634 Step 5815 | loss:1.1287920475006104 lr:4.828659874644803e-06 tokens_per_second_per_gpu:5304.357889409536 mfu:25.02156118112309 Step 5816 | loss:1.2157176733016968 lr:4.822206944821161e-06 tokens_per_second_per_gpu:5217.269883575692 mfu:24.610752198858865 Step 5817 | loss:1.3083171844482422 lr:4.815757869401802e-06 tokens_per_second_per_gpu:5305.64982034624 mfu:25.027655439777668 Step 5818 | loss:1.1386774778366089 lr:4.809312649618641e-06 tokens_per_second_per_gpu:5323.847374361805 mfu:25.113496406891965 Step 5819 | loss:1.3602057695388794 lr:4.802871286702859e-06 tokens_per_second_per_gpu:3113.9051629022715 mfu:14.688821940415385 Step 5820 | loss:1.2244632244110107 lr:4.796433781884896e-06 tokens_per_second_per_gpu:4966.805984893336 mfu:23.429271255226535 Step 5821 | loss:1.2564752101898193 lr:4.790000136394457e-06 tokens_per_second_per_gpu:5305.841799011979 mfu:25.028561035898896 Step 5822 | loss:1.2691478729248047 lr:4.783570351460515e-06 tokens_per_second_per_gpu:4005.340853747036 mfu:18.893876188742496 Step 5823 | loss:1.1163517236709595 lr:4.7771444283112975e-06 tokens_per_second_per_gpu:4509.3417275789725 mfu:21.271334302023973 Step 5824 | loss:1.2821509838104248 lr:4.770722368174296e-06 tokens_per_second_per_gpu:3367.951828811999 mfu:15.887203408342351 Step 5825 | loss:1.2297831773757935 lr:4.764304172276274e-06 tokens_per_second_per_gpu:4730.188889083067 mfu:22.31310804325002 Step 5826 | loss:1.2251842021942139 lr:4.757889841843238e-06 tokens_per_second_per_gpu:4364.315674795201 mfu:20.587221667046794 Step 5827 | loss:1.1460219621658325 lr:4.7514793781004764e-06 tokens_per_second_per_gpu:5065.548362595381 mfu:23.89505589803394 Step 5828 | loss:1.338822603225708 lr:4.745072782272522e-06 tokens_per_second_per_gpu:4536.988952609093 mfu:21.401750979594052 Step 5829 | loss:1.2157126665115356 lr:4.73867005558318e-06 tokens_per_second_per_gpu:5050.574899994973 mfu:23.82442352021166 Step 5830 | loss:1.3144291639328003 lr:4.7322711992555115e-06 tokens_per_second_per_gpu:3445.526483392552 mfu:16.253136289599706 Step 5831 | loss:1.226766586303711 lr:4.72587621451184e-06 tokens_per_second_per_gpu:4267.698785348393 mfu:20.131463314985034 Step 5832 | loss:1.2252289056777954 lr:4.719485102573748e-06 tokens_per_second_per_gpu:5331.79284592451 mfu:25.150976551890484 Step 5833 | loss:1.3167271614074707 lr:4.7130978646620805e-06 tokens_per_second_per_gpu:5257.70972294144 mfu:24.801513820895174 Step 5834 | loss:1.2905793190002441 lr:4.706714501996942e-06 tokens_per_second_per_gpu:5324.197767285324 mfu:25.115149270095397 Step 5835 | loss:1.175013780593872 lr:4.700335015797691e-06 tokens_per_second_per_gpu:4483.29006840022 mfu:21.148444180806397 Step 5836 | loss:1.4283379316329956 lr:4.693959407282955e-06 tokens_per_second_per_gpu:4260.515258501048 mfu:20.09757739321004 Step 5837 | loss:1.2737116813659668 lr:4.687587677670615e-06 tokens_per_second_per_gpu:4892.584755359535 mfu:23.07915705206802 Step 5838 | loss:1.3172122240066528 lr:4.681219828177813e-06 tokens_per_second_per_gpu:4290.628508974934 mfu:20.239626733545695 Step 5839 | loss:1.1826225519180298 lr:4.674855860020947e-06 tokens_per_second_per_gpu:5313.407220457689 mfu:25.064248419652312 Step 5840 | loss:1.1978087425231934 lr:4.668495774415673e-06 tokens_per_second_per_gpu:5258.869402502463 mfu:24.806984227246257 Step 5841 | loss:1.0276528596878052 lr:4.662139572576912e-06 tokens_per_second_per_gpu:5011.405604138296 mfu:23.63965526868472 Step 5842 | loss:1.2718538045883179 lr:4.655787255718841e-06 tokens_per_second_per_gpu:5277.967854598907 mfu:24.89707488431712 Step 5843 | loss:1.2150228023529053 lr:4.649438825054886e-06 tokens_per_second_per_gpu:5310.620891345543 mfu:25.05110482983355 Step 5844 | loss:1.1735981702804565 lr:4.6430942817977445e-06 tokens_per_second_per_gpu:5343.448287834699 mfu:25.20595726000429 Step 5845 | loss:1.382759928703308 lr:4.63675362715936e-06 tokens_per_second_per_gpu:5311.541348003924 mfu:25.05544678093724 Step 5846 | loss:1.1769673824310303 lr:4.6304168623509394e-06 tokens_per_second_per_gpu:5316.080879715584 mfu:25.07686052654511 Step 5847 | loss:1.1802539825439453 lr:4.624083988582942e-06 tokens_per_second_per_gpu:5357.874277776571 mfu:25.27400711588779 Step 5848 | loss:1.4311835765838623 lr:4.617755007065092e-06 tokens_per_second_per_gpu:3870.223565532311 mfu:18.256504886847083 Step 5849 | loss:1.3408913612365723 lr:4.611429919006361e-06 tokens_per_second_per_gpu:4205.26628013097 mfu:19.83695853579065 Step 5850 | loss:1.280596137046814 lr:4.6051087256149785e-06 tokens_per_second_per_gpu:3863.3375517782415 mfu:18.224022385094038 Step 5851 | loss:1.20168137550354 lr:4.598791428098439e-06 tokens_per_second_per_gpu:5278.874654358143 mfu:24.901352413497428 Step 5852 | loss:1.1873204708099365 lr:4.59247802766348e-06 tokens_per_second_per_gpu:5144.342699039915 mfu:24.266742226742874 Step 5853 | loss:1.186208963394165 lr:4.586168525516102e-06 tokens_per_second_per_gpu:3400.879908834387 mfu:16.04253077991773 Step 5854 | loss:1.0827457904815674 lr:4.579862922861558e-06 tokens_per_second_per_gpu:4365.306642866432 mfu:20.59189623251538 Step 5855 | loss:1.2048990726470947 lr:4.57356122090436e-06 tokens_per_second_per_gpu:4175.269405109435 mfu:19.695458158319436 Step 5856 | loss:1.418595552444458 lr:4.567263420848272e-06 tokens_per_second_per_gpu:3928.8431416640906 mfu:18.533023428991697 Step 5857 | loss:1.3118470907211304 lr:4.5609695238963105e-06 tokens_per_second_per_gpu:3841.2221536212273 mfu:18.119700278711388 Step 5858 | loss:1.4577909708023071 lr:4.554679531250752e-06 tokens_per_second_per_gpu:3436.9270445614693 mfu:16.21257126941793 Step 5859 | loss:1.1797125339508057 lr:4.548393444113122e-06 tokens_per_second_per_gpu:5328.296960009149 mfu:25.13448586156808 Step 5860 | loss:1.141448974609375 lr:4.5421112636842036e-06 tokens_per_second_per_gpu:5307.089797335039 mfu:25.034448056919242 Step 5861 | loss:1.292372465133667 lr:4.535832991164029e-06 tokens_per_second_per_gpu:4905.801016570954 mfu:23.141500411128966 Step 5862 | loss:1.292055368423462 lr:4.529558627751892e-06 tokens_per_second_per_gpu:4170.529404682788 mfu:19.67309876757948 Step 5863 | loss:1.3289625644683838 lr:4.523288174646331e-06 tokens_per_second_per_gpu:5331.8380540008475 mfu:25.151189806099858 Step 5864 | loss:1.3953996896743774 lr:4.51702163304514e-06 tokens_per_second_per_gpu:5122.708540136185 mfu:24.164690208025853 Step 5865 | loss:1.1568102836608887 lr:4.51075900414537e-06 tokens_per_second_per_gpu:4061.501349098282 mfu:19.158794827282893 Step 5866 | loss:1.2983397245407104 lr:4.504500289143318e-06 tokens_per_second_per_gpu:5306.221297465224 mfu:25.030351194851967 Step 5867 | loss:1.251441240310669 lr:4.498245489234542e-06 tokens_per_second_per_gpu:4964.7785959386965 mfu:23.41970771561927 Step 5868 | loss:1.1833699941635132 lr:4.4919946056138416e-06 tokens_per_second_per_gpu:4473.652925598589 mfu:21.10298413394499 Step 5869 | loss:1.3313860893249512 lr:4.485747639475279e-06 tokens_per_second_per_gpu:5318.966794423641 mfu:25.09047387861084 Step 5870 | loss:1.2494111061096191 lr:4.479504592012157e-06 tokens_per_second_per_gpu:4251.42639819434 mfu:20.05470368842383 Step 5871 | loss:1.1999235153198242 lr:4.473265464417039e-06 tokens_per_second_per_gpu:4311.578669608297 mfu:20.338452215719254 Step 5872 | loss:1.4102059602737427 lr:4.467030257881738e-06 tokens_per_second_per_gpu:4644.479774393135 mfu:21.90880352577472 Step 5873 | loss:1.1441595554351807 lr:4.460798973597311e-06 tokens_per_second_per_gpu:3726.717986257356 mfu:17.579564584830525 Step 5874 | loss:1.2687900066375732 lr:4.454571612754074e-06 tokens_per_second_per_gpu:5308.706870879572 mfu:25.04207606873 Step 5875 | loss:1.1213274002075195 lr:4.448348176541592e-06 tokens_per_second_per_gpu:4304.652490217537 mfu:20.30578024580498 Step 5876 | loss:1.4390559196472168 lr:4.442128666148676e-06 tokens_per_second_per_gpu:4269.813221881789 mfu:20.141437472873132 Step 5877 | loss:1.2560614347457886 lr:4.43591308276339e-06 tokens_per_second_per_gpu:5339.9267972305515 mfu:25.189345787996274 Step 5878 | loss:1.3107678890228271 lr:4.429701427573052e-06 tokens_per_second_per_gpu:3775.189211328726 mfu:17.808211623535954 Step 5879 | loss:1.2851154804229736 lr:4.423493701764219e-06 tokens_per_second_per_gpu:4990.718998921642 mfu:23.54207302237896 Step 5880 | loss:1.225478172302246 lr:4.417289906522709e-06 tokens_per_second_per_gpu:4586.853158302103 mfu:21.63696894555876 Step 5881 | loss:1.2321020364761353 lr:4.41109004303358e-06 tokens_per_second_per_gpu:4076.288271956841 mfu:19.22854726531591 Step 5882 | loss:1.32013738155365 lr:4.4048941124811475e-06 tokens_per_second_per_gpu:5327.457185696257 mfu:25.13052450285389 Step 5883 | loss:1.2562943696975708 lr:4.3987021160489665e-06 tokens_per_second_per_gpu:5228.011353614872 mfu:24.66142154571745 Step 5884 | loss:1.2632026672363281 lr:4.392514054919847e-06 tokens_per_second_per_gpu:4667.5801057044755 mfu:22.01777172989325 Step 5885 | loss:1.1614859104156494 lr:4.386329930275845e-06 tokens_per_second_per_gpu:5264.980245002352 mfu:24.83581011393547 Step 5886 | loss:1.3970777988433838 lr:4.380149743298268e-06 tokens_per_second_per_gpu:5087.657833397967 mfu:23.999350044074443 Step 5887 | loss:1.2283079624176025 lr:4.3739734951676635e-06 tokens_per_second_per_gpu:4198.578423930645 mfu:19.805410777027785 Step 5888 | loss:1.0404132604599 lr:4.367801187063836e-06 tokens_per_second_per_gpu:4168.743606709469 mfu:19.66467485385078 Step 5889 | loss:1.295283555984497 lr:4.361632820165826e-06 tokens_per_second_per_gpu:3833.2861226786263 mfu:18.08226466672864 Step 5890 | loss:1.238619327545166 lr:4.355468395651935e-06 tokens_per_second_per_gpu:5337.6255011931235 mfu:25.178490181946135 Step 5891 | loss:1.0591187477111816 lr:4.3493079146997014e-06 tokens_per_second_per_gpu:5315.211625292454 mfu:25.072760105121112 Step 5892 | loss:1.2082324028015137 lr:4.343151378485913e-06 tokens_per_second_per_gpu:4158.318036528758 mfu:19.615495660522672 Step 5893 | loss:1.2603942155838013 lr:4.336998788186603e-06 tokens_per_second_per_gpu:5289.930890591126 mfu:24.953506566196825 Step 5894 | loss:1.189259648323059 lr:4.330850144977056e-06 tokens_per_second_per_gpu:5015.739662898646 mfu:23.660099763323963 Step 5895 | loss:1.3383973836898804 lr:4.324705450031794e-06 tokens_per_second_per_gpu:4070.0869702674013 mfu:19.19929466719565 Step 5896 | loss:1.2891143560409546 lr:4.3185647045245915e-06 tokens_per_second_per_gpu:5316.284365077227 mfu:25.077820401714167 Step 5897 | loss:1.2893016338348389 lr:4.312427909628461e-06 tokens_per_second_per_gpu:5293.0532077138605 mfu:24.968235068787003 Step 5898 | loss:1.2075278759002686 lr:4.306295066515684e-06 tokens_per_second_per_gpu:5087.427808749216 mfu:23.998264978560034 Step 5899 | loss:1.2609350681304932 lr:4.30016617635775e-06 tokens_per_second_per_gpu:3927.052478039819 mfu:18.52457656315729 Step 5900 | loss:1.12600576877594 lr:4.294041240325417e-06 tokens_per_second_per_gpu:4149.043396650259 mfu:19.571745601799055 Step 5901 | loss:1.3203003406524658 lr:4.287920259588693e-06 tokens_per_second_per_gpu:5352.907327115458 mfu:25.250577162170153 Step 5902 | loss:1.096726894378662 lr:4.281803235316808e-06 tokens_per_second_per_gpu:4416.26674684793 mfu:20.832283737686414 Step 5903 | loss:1.1774314641952515 lr:4.275690168678248e-06 tokens_per_second_per_gpu:3508.923325688088 mfu:16.552190011324416 Step 5904 | loss:1.4622840881347656 lr:4.269581060840761e-06 tokens_per_second_per_gpu:5347.137694761975 mfu:25.223360821957982 Step 5905 | loss:1.2876328229904175 lr:4.263475912971304e-06 tokens_per_second_per_gpu:4037.7057014656157 mfu:19.04654669744347 Step 5906 | loss:1.033265471458435 lr:4.257374726236094e-06 tokens_per_second_per_gpu:5313.096474820964 mfu:25.06278257946521 Step 5907 | loss:1.4017075300216675 lr:4.251277501800613e-06 tokens_per_second_per_gpu:4671.019332930062 mfu:22.03399515150901 Step 5908 | loss:1.311185598373413 lr:4.245184240829544e-06 tokens_per_second_per_gpu:4109.461036675673 mfu:19.385028856351926 Step 5909 | loss:1.3506383895874023 lr:4.239094944486837e-06 tokens_per_second_per_gpu:4627.822957354294 mfu:21.830230477856464 Step 5910 | loss:1.3515187501907349 lr:4.233009613935704e-06 tokens_per_second_per_gpu:4417.268814307033 mfu:20.83701066086134 Step 5911 | loss:1.2077155113220215 lr:4.226928250338552e-06 tokens_per_second_per_gpu:5322.856873018505 mfu:25.10882404305866 Step 5912 | loss:1.0973870754241943 lr:4.220850854857059e-06 tokens_per_second_per_gpu:5301.945996014898 mfu:25.01018386846913 Step 5913 | loss:1.2770471572875977 lr:4.214777428652158e-06 tokens_per_second_per_gpu:4087.1500076168854 mfu:19.279783925627537 Step 5914 | loss:1.2413896322250366 lr:4.208707972883996e-06 tokens_per_second_per_gpu:4436.5135473449955 mfu:20.92779135009145 Step 5915 | loss:1.2427693605422974 lr:4.202642488711966e-06 tokens_per_second_per_gpu:5033.9627890514985 mfu:23.7460613585729 Step 5916 | loss:1.3369063138961792 lr:4.196580977294732e-06 tokens_per_second_per_gpu:4626.948230164446 mfu:21.826104240458104 Step 5917 | loss:1.4052373170852661 lr:4.190523439790153e-06 tokens_per_second_per_gpu:4750.991524126547 mfu:22.411237622045647 Step 5918 | loss:1.4938513040542603 lr:4.18446987735536e-06 tokens_per_second_per_gpu:5259.632445371798 mfu:24.810583630649447 Step 5919 | loss:1.1378850936889648 lr:4.178420291146729e-06 tokens_per_second_per_gpu:4310.041380810785 mfu:20.331200562172878 Step 5920 | loss:1.2667927742004395 lr:4.172374682319849e-06 tokens_per_second_per_gpu:4402.842879683335 mfu:20.76896106592311 Step 5921 | loss:1.3163641691207886 lr:4.166333052029567e-06 tokens_per_second_per_gpu:4479.1860555623425 mfu:21.129084852033337 Step 5922 | loss:1.1379728317260742 lr:4.160295401429984e-06 tokens_per_second_per_gpu:5100.816024851862 mfu:24.061419478181424 Step 5923 | loss:1.3025171756744385 lr:4.154261731674403e-06 tokens_per_second_per_gpu:4821.452540563214 mfu:22.74361425846646 Step 5924 | loss:1.4073086977005005 lr:4.148232043915395e-06 tokens_per_second_per_gpu:3298.859254817516 mfu:15.561281948401671 Step 5925 | loss:1.2374475002288818 lr:4.142206339304777e-06 tokens_per_second_per_gpu:5089.262283155599 mfu:24.00691850732855 Step 5926 | loss:1.352913737297058 lr:4.136184618993574e-06 tokens_per_second_per_gpu:4835.908685137447 mfu:22.81180635889572 Step 5927 | loss:1.2984634637832642 lr:4.13016688413207e-06 tokens_per_second_per_gpu:4201.1980376576985 mfu:19.817767941930487 Step 5928 | loss:1.4911751747131348 lr:4.124153135869801e-06 tokens_per_second_per_gpu:3853.8488658629217 mfu:18.17926263469472 Step 5929 | loss:1.194594144821167 lr:4.11814337535551e-06 tokens_per_second_per_gpu:3879.597467670656 mfu:18.300723182586278 Step 5930 | loss:1.1809450387954712 lr:4.112137603737193e-06 tokens_per_second_per_gpu:3884.380286255816 mfu:18.323284553885475 Step 5931 | loss:1.2949137687683105 lr:4.106135822162099e-06 tokens_per_second_per_gpu:5204.8862139103085 mfu:24.55233631617533 Step 5932 | loss:1.1987717151641846 lr:4.100138031776691e-06 tokens_per_second_per_gpu:4563.986959425646 mfu:21.529105184082685 Step 5933 | loss:1.2516517639160156 lr:4.094144233726674e-06 tokens_per_second_per_gpu:3756.3369479001694 mfu:17.719282280415634 Step 5934 | loss:1.42074453830719 lr:4.088154429157015e-06 tokens_per_second_per_gpu:3955.0232546272127 mfu:18.656519488626618 Step 5935 | loss:1.294631838798523 lr:4.082168619211879e-06 tokens_per_second_per_gpu:4342.631548994 mfu:20.48493394594917 Step 5936 | loss:1.2611397504806519 lr:4.076186805034693e-06 tokens_per_second_per_gpu:4170.992707066776 mfu:19.675284243972293 Step 5937 | loss:1.1253694295883179 lr:4.0702089877681285e-06 tokens_per_second_per_gpu:4116.393297910343 mfu:19.417729515361593 Step 5938 | loss:1.1793122291564941 lr:4.064235168554065e-06 tokens_per_second_per_gpu:5198.219663609176 mfu:24.52088906097412 Step 5939 | loss:1.379439353942871 lr:4.058265348533636e-06 tokens_per_second_per_gpu:4470.04839238616 mfu:21.085980935785184 Step 5940 | loss:1.357803225517273 lr:4.052299528847223e-06 tokens_per_second_per_gpu:3682.685221073975 mfu:17.371854518696082 Step 5941 | loss:1.161739468574524 lr:4.046337710634413e-06 tokens_per_second_per_gpu:4285.455773604313 mfu:20.215226058242816 Step 5942 | loss:1.3267778158187866 lr:4.040379895034044e-06 tokens_per_second_per_gpu:5119.2925639712585 mfu:24.14857646563026 Step 5943 | loss:1.4320992231369019 lr:4.034426083184212e-06 tokens_per_second_per_gpu:4469.924620792127 mfu:21.085397084058517 Step 5944 | loss:1.2297660112380981 lr:4.028476276222204e-06 tokens_per_second_per_gpu:5336.931672439029 mfu:25.17521727333368 Step 5945 | loss:1.3226789236068726 lr:4.02253047528457e-06 tokens_per_second_per_gpu:4673.4747818456 mfu:22.04557792298639 Step 5946 | loss:1.345781683921814 lr:4.0165886815071e-06 tokens_per_second_per_gpu:4390.752283632402 mfu:20.711927661482456 Step 5947 | loss:1.144538402557373 lr:4.010650896024795e-06 tokens_per_second_per_gpu:5317.0427046765 mfu:25.08139761899001 Step 5948 | loss:1.186303973197937 lr:4.004717119971904e-06 tokens_per_second_per_gpu:5344.009294307657 mfu:25.208603623254806 Step 5949 | loss:0.960875391960144 lr:3.9987873544819256e-06 tokens_per_second_per_gpu:5050.07962498129 mfu:23.822087223469488 Step 5950 | loss:1.1673179864883423 lr:3.992861600687559e-06 tokens_per_second_per_gpu:5246.041173618512 mfu:24.746471282879117 Step 5951 | loss:1.3137774467468262 lr:3.986939859720751e-06 tokens_per_second_per_gpu:5325.83963462908 mfu:25.12289423848735 Step 5952 | loss:1.3387975692749023 lr:3.981022132712703e-06 tokens_per_second_per_gpu:4451.052180480416 mfu:20.996372563137825 Step 5953 | loss:1.279773473739624 lr:3.975108420793819e-06 tokens_per_second_per_gpu:4516.632722207375 mfu:21.3057271676581 Step 5954 | loss:1.1124892234802246 lr:3.969198725093745e-06 tokens_per_second_per_gpu:4755.846129498094 mfu:22.43413762386432 Step 5955 | loss:1.2641232013702393 lr:3.9632930467413785e-06 tokens_per_second_per_gpu:4611.374792905079 mfu:21.75264167980328 Step 5956 | loss:1.2406436204910278 lr:3.957391386864823e-06 tokens_per_second_per_gpu:5324.573920465041 mfu:25.116923648822475 Step 5957 | loss:1.2501697540283203 lr:3.951493746591422e-06 tokens_per_second_per_gpu:5298.814509542855 mfu:24.995412112493824 Step 5958 | loss:1.0608386993408203 lr:3.9456001270477745e-06 tokens_per_second_per_gpu:5054.206939998358 mfu:23.841556472597556 Step 5959 | loss:1.2826319932937622 lr:3.939710529359672e-06 tokens_per_second_per_gpu:5326.642577954284 mfu:25.126681859148597 Step 5960 | loss:1.1913270950317383 lr:3.93382495465216e-06 tokens_per_second_per_gpu:5304.777344751863 mfu:25.023539823539306 Step 5961 | loss:1.218812346458435 lr:3.927943404049531e-06 tokens_per_second_per_gpu:5314.349930710032 mfu:25.068695344755568 Step 5962 | loss:1.3347293138504028 lr:3.922065878675271e-06 tokens_per_second_per_gpu:3518.6424992207394 mfu:16.598037011139933 Step 5963 | loss:1.0641664266586304 lr:3.91619237965212e-06 tokens_per_second_per_gpu:4700.954013416449 mfu:22.175202146746447 Step 5964 | loss:1.2758569717407227 lr:3.91032290810206e-06 tokens_per_second_per_gpu:5331.526027882648 mfu:25.14971792566316 Step 5965 | loss:1.194008708000183 lr:3.904457465146271e-06 tokens_per_second_per_gpu:5087.945849412463 mfu:24.000708664755418 Step 5966 | loss:1.3659911155700684 lr:3.898596051905198e-06 tokens_per_second_per_gpu:5327.9615245484965 mfu:25.132903555268992 Step 5967 | loss:1.1597425937652588 lr:3.8927386694985e-06 tokens_per_second_per_gpu:5324.992485252236 mfu:25.11889809033819 Step 5968 | loss:1.2595422267913818 lr:3.8868853190450475e-06 tokens_per_second_per_gpu:4508.569478736183 mfu:21.267691472473295 Step 5969 | loss:1.2857459783554077 lr:3.88103600166298e-06 tokens_per_second_per_gpu:3894.979728594929 mfu:18.373283931850416 Step 5970 | loss:1.5187201499938965 lr:3.875190718469646e-06 tokens_per_second_per_gpu:4420.806124430954 mfu:20.853696756243217 Step 5971 | loss:1.2768402099609375 lr:3.869349470581604e-06 tokens_per_second_per_gpu:4426.116510424999 mfu:20.878746753022412 Step 5972 | loss:1.450774908065796 lr:3.863512259114679e-06 tokens_per_second_per_gpu:4537.76683408929 mfu:21.40542037925641 Step 5973 | loss:1.3511320352554321 lr:3.85767908518391e-06 tokens_per_second_per_gpu:5322.862809618555 mfu:25.108852047013986 Step 5974 | loss:1.2983661890029907 lr:3.8518499499035435e-06 tokens_per_second_per_gpu:4136.356436080404 mfu:19.511899044172367 Step 5975 | loss:1.1770676374435425 lr:3.84602485438709e-06 tokens_per_second_per_gpu:5201.925151839478 mfu:24.53836848117794 Step 5976 | loss:1.2008116245269775 lr:3.840203799747272e-06 tokens_per_second_per_gpu:4594.646799643353 mfu:21.673732881497767 Step 5977 | loss:1.3096333742141724 lr:3.83438678709602e-06 tokens_per_second_per_gpu:3756.986698337776 mfu:17.72234726408868 Step 5978 | loss:1.0813533067703247 lr:3.828573817544534e-06 tokens_per_second_per_gpu:5301.315908544642 mfu:25.00721163836793 Step 5979 | loss:1.3035500049591064 lr:3.822764892203215e-06 tokens_per_second_per_gpu:5296.890373199389 mfu:24.986335633070176 Step 5980 | loss:1.2029539346694946 lr:3.81696001218168e-06 tokens_per_second_per_gpu:4668.880664039126 mfu:22.023906685455927 Step 5981 | loss:1.2619056701660156 lr:3.811159178588816e-06 tokens_per_second_per_gpu:3746.7432307588656 mfu:17.67402707980317 Step 5982 | loss:1.3088665008544922 lr:3.805362392532688e-06 tokens_per_second_per_gpu:3128.6818588739206 mfu:14.758526136477961 Step 5983 | loss:1.367809534072876 lr:3.7995696551206134e-06 tokens_per_second_per_gpu:5281.400352524504 mfu:24.913266562676696 Step 5984 | loss:1.4575082063674927 lr:3.7937809674591483e-06 tokens_per_second_per_gpu:4003.453922657671 mfu:18.88497521285032 Step 5985 | loss:1.1690523624420166 lr:3.7879963306540424e-06 tokens_per_second_per_gpu:4564.657799858534 mfu:21.5322696528618 Step 5986 | loss:1.1720771789550781 lr:3.7822157458102914e-06 tokens_per_second_per_gpu:5311.43557691269 mfu:25.054947840653472 Step 5987 | loss:1.226155161857605 lr:3.776439214032132e-06 tokens_per_second_per_gpu:4317.688508224858 mfu:20.367273366919534 Step 5988 | loss:1.3147006034851074 lr:3.77066673642299e-06 tokens_per_second_per_gpu:4478.778840600325 mfu:21.12716394957946 Step 5989 | loss:1.136600136756897 lr:3.7648983140855353e-06 tokens_per_second_per_gpu:4989.492150244014 mfu:23.536285767844618 Step 5990 | loss:1.3367114067077637 lr:3.759133948121685e-06 tokens_per_second_per_gpu:4454.35768690088 mfu:21.011965200900708 Step 5991 | loss:1.3644315004348755 lr:3.75337363963254e-06 tokens_per_second_per_gpu:4803.510342993256 mfu:22.658977851274404 Step 5992 | loss:1.4092315435409546 lr:3.7476173897184497e-06 tokens_per_second_per_gpu:4049.1207553118747 mfu:19.10039345404529 Step 5993 | loss:1.1935569047927856 lr:3.741865199479e-06 tokens_per_second_per_gpu:3274.3111223145465 mfu:15.445484219041871 Step 5994 | loss:1.2630447149276733 lr:3.7361170700129676e-06 tokens_per_second_per_gpu:4216.559215627396 mfu:19.89022923930077 Step 5995 | loss:1.3356773853302002 lr:3.7303730024183775e-06 tokens_per_second_per_gpu:4461.52603892178 mfu:21.045779540430264 Step 5996 | loss:1.2810144424438477 lr:3.724632997792485e-06 tokens_per_second_per_gpu:5235.754954502086 mfu:24.697949432296983 Step 5997 | loss:1.261548399925232 lr:3.7188970572317405e-06 tokens_per_second_per_gpu:4921.784546789427 mfu:23.216897450240968 Step 5998 | loss:1.1950807571411133 lr:3.7131651818318402e-06 tokens_per_second_per_gpu:5302.649717018132 mfu:25.013503440508572 Step 5999 | loss:1.221071720123291 lr:3.7074373726877136e-06 tokens_per_second_per_gpu:4538.099203046088 mfu:21.406988220333616 Step 6000 | loss:1.4843788146972656 lr:3.701713630893483e-06 tokens_per_second_per_gpu:5360.178773677899 mfu:25.284877816241895 Step 6001 | loss:1.2506695985794067 lr:3.6959939575425067e-06 tokens_per_second_per_gpu:3393.8127606477947 mfu:16.00919383614176 Step 6002 | loss:1.125226616859436 lr:3.690278353727386e-06 tokens_per_second_per_gpu:5346.665214836699 mfu:25.221132053537072 Step 6003 | loss:1.210040807723999 lr:3.6845668205399142e-06 tokens_per_second_per_gpu:5006.383543506881 mfu:23.615965351834436 Step 6004 | loss:1.1229921579360962 lr:3.6788593590711157e-06 tokens_per_second_per_gpu:5340.098855918503 mfu:25.190157418183585 Step 6005 | loss:1.2101269960403442 lr:3.673155970411263e-06 tokens_per_second_per_gpu:5322.059327494827 mfu:25.105061884748174 Step 6006 | loss:1.1937122344970703 lr:3.667456655649809e-06 tokens_per_second_per_gpu:3530.3488499456944 mfu:16.653257864818936 Step 6007 | loss:1.1805405616760254 lr:3.66176141587545e-06 tokens_per_second_per_gpu:4643.038153038649 mfu:21.902003151879644 Step 6008 | loss:1.213876485824585 lr:3.656070252176119e-06 tokens_per_second_per_gpu:4632.424312387016 mfu:21.85193585461794 Step 6009 | loss:1.149714469909668 lr:3.6503831656389403e-06 tokens_per_second_per_gpu:4640.978171451141 mfu:21.892285867262267 Step 6010 | loss:1.170250654220581 lr:3.6447001573502672e-06 tokens_per_second_per_gpu:5273.2201302587255 mfu:24.874679058559177 Step 6011 | loss:1.3942586183547974 lr:3.639021228395703e-06 tokens_per_second_per_gpu:4702.776970233483 mfu:22.1838013450809 Step 6012 | loss:1.2351012229919434 lr:3.633346379860028e-06 tokens_per_second_per_gpu:4032.7201457786427 mfu:19.023028980644504 Step 6013 | loss:1.2104038000106812 lr:3.6276756128272637e-06 tokens_per_second_per_gpu:4914.499969971676 mfu:23.182534858514675 Step 6014 | loss:1.2780100107192993 lr:3.6220089283806685e-06 tokens_per_second_per_gpu:5319.809723841885 mfu:25.094450120495285 Step 6015 | loss:1.1544899940490723 lr:3.6163463276026877e-06 tokens_per_second_per_gpu:4488.419260880348 mfu:21.172639456865642 Step 6016 | loss:1.191322684288025 lr:3.6106878115750057e-06 tokens_per_second_per_gpu:5314.333253973624 mfu:25.068616677744586 Step 6017 | loss:1.3809341192245483 lr:3.605033381378539e-06 tokens_per_second_per_gpu:3534.0710649840616 mfu:16.670816188230287 Step 6018 | loss:1.2078790664672852 lr:3.599383038093393e-06 tokens_per_second_per_gpu:3738.711388733569 mfu:17.63613951059629 Step 6019 | loss:1.3886358737945557 lr:3.593736782798904e-06 tokens_per_second_per_gpu:4207.256602284325 mfu:19.846347224972 Step 6020 | loss:1.2493760585784912 lr:3.5880946165736534e-06 tokens_per_second_per_gpu:5303.057859260609 mfu:25.015428717102584 Step 6021 | loss:1.2991851568222046 lr:3.582456540495402e-06 tokens_per_second_per_gpu:5363.636626964211 mfu:25.30118910016404 Step 6022 | loss:1.321628451347351 lr:3.5768225556411434e-06 tokens_per_second_per_gpu:4763.471133823765 mfu:22.470106070228397 Step 6023 | loss:1.389455795288086 lr:3.571192663087114e-06 tokens_per_second_per_gpu:4768.794232837275 mfu:22.495216036489463 Step 6024 | loss:1.2322959899902344 lr:3.5655668639087257e-06 tokens_per_second_per_gpu:4400.61423236636 mfu:20.758448156282494 Step 6025 | loss:1.3492616415023804 lr:3.5599451591806387e-06 tokens_per_second_per_gpu:4188.550944162463 mfu:19.7581094440968 Step 6026 | loss:1.2786145210266113 lr:3.5543275499767297e-06 tokens_per_second_per_gpu:4046.507314971769 mfu:19.08806541006211 Step 6027 | loss:1.167256474494934 lr:3.5487140373700793e-06 tokens_per_second_per_gpu:5292.9137462655 mfu:24.967577205340504 Step 6028 | loss:1.2247239351272583 lr:3.5431046224329855e-06 tokens_per_second_per_gpu:4618.731013166125 mfu:21.787342225875236 Step 6029 | loss:1.281213402748108 lr:3.537499306236988e-06 tokens_per_second_per_gpu:4241.115711045618 mfu:20.006066417958678 Step 6030 | loss:1.5040082931518555 lr:3.531898089852806e-06 tokens_per_second_per_gpu:5361.341705853103 mfu:25.290363565729027 Step 6031 | loss:1.2305597066879272 lr:3.5263009743504132e-06 tokens_per_second_per_gpu:3792.7523440001382 mfu:17.891059916926437 Step 6032 | loss:1.3285884857177734 lr:3.5207079607989775e-06 tokens_per_second_per_gpu:3422.107815931402 mfu:16.142666439548776 Step 6033 | loss:1.3704761266708374 lr:3.5151190502668767e-06 tokens_per_second_per_gpu:4969.498324371734 mfu:23.44197147990662 Step 6034 | loss:1.316286563873291 lr:3.50953424382173e-06 tokens_per_second_per_gpu:4583.020619642099 mfu:21.618890206800994 Step 6035 | loss:1.272688865661621 lr:3.5039535425303583e-06 tokens_per_second_per_gpu:5311.182754311628 mfu:25.05375523330828 Step 6036 | loss:1.3201584815979004 lr:3.498376947458784e-06 tokens_per_second_per_gpu:4767.559978759113 mfu:22.489393849417315 Step 6037 | loss:1.3585249185562134 lr:3.492804459672275e-06 tokens_per_second_per_gpu:5307.6460708688255 mfu:25.037072094088167 Step 6038 | loss:1.1389440298080444 lr:3.487236080235301e-06 tokens_per_second_per_gpu:5300.515573701569 mfu:25.00343632236195 Step 6039 | loss:1.1672364473342896 lr:3.4816718102115288e-06 tokens_per_second_per_gpu:4039.826495524597 mfu:19.056550844864464 Step 6040 | loss:1.3520207405090332 lr:3.476111650663871e-06 tokens_per_second_per_gpu:4085.441732783423 mfu:19.271725701776354 Step 6041 | loss:1.2220767736434937 lr:3.470555602654446e-06 tokens_per_second_per_gpu:4171.445940503986 mfu:19.677422223425204 Step 6042 | loss:1.3694730997085571 lr:3.4650036672445597e-06 tokens_per_second_per_gpu:4892.185753603514 mfu:23.07727489270815 Step 6043 | loss:1.1527642011642456 lr:3.4594558454947747e-06 tokens_per_second_per_gpu:4411.50671472326 mfu:20.80982985400912 Step 6044 | loss:1.2129801511764526 lr:3.453912138464846e-06 tokens_per_second_per_gpu:4351.076507156541 mfu:20.524770254460314 Step 6045 | loss:1.1750377416610718 lr:3.4483725472137267e-06 tokens_per_second_per_gpu:5320.975243465072 mfu:25.09994807541601 Step 6046 | loss:1.2767913341522217 lr:3.442837072799621e-06 tokens_per_second_per_gpu:4337.409783883219 mfu:20.460301988996616 Step 6047 | loss:1.2874739170074463 lr:3.4373057162799233e-06 tokens_per_second_per_gpu:4060.4431019145236 mfu:19.153802894761515 Step 6048 | loss:1.2115812301635742 lr:3.4317784787112286e-06 tokens_per_second_per_gpu:4702.607984894517 mfu:22.183004212405134 Step 6049 | loss:1.3111958503723145 lr:3.4262553611493805e-06 tokens_per_second_per_gpu:4137.459922736763 mfu:19.517104379004646 Step 6050 | loss:1.4643421173095703 lr:3.420736364649413e-06 tokens_per_second_per_gpu:3988.64552213909 mfu:18.815121461030515 Step 6051 | loss:1.2772831916809082 lr:3.415221490265563e-06 tokens_per_second_per_gpu:4972.745614657461 mfu:23.45728950222925 Step 6052 | loss:1.259147047996521 lr:3.4097107390513084e-06 tokens_per_second_per_gpu:5309.296940090053 mfu:25.044859525872027 Step 6053 | loss:1.3565642833709717 lr:3.4042041120593254e-06 tokens_per_second_per_gpu:4860.743827227633 mfu:22.92895796144731 Step 6054 | loss:1.1909745931625366 lr:3.398701610341484e-06 tokens_per_second_per_gpu:4014.167484045373 mfu:18.93551290983817 Step 6055 | loss:1.2378647327423096 lr:3.3932032349488997e-06 tokens_per_second_per_gpu:4673.980210417358 mfu:22.047962115794377 Step 6056 | loss:1.2078769207000732 lr:3.3877089869318866e-06 tokens_per_second_per_gpu:4156.613957134171 mfu:19.607457227272477 Step 6057 | loss:1.250044584274292 lr:3.382218867339945e-06 tokens_per_second_per_gpu:3020.798317962844 mfu:14.249621067170283 Step 6058 | loss:1.3245549201965332 lr:3.376732877221833e-06 tokens_per_second_per_gpu:5319.933319156187 mfu:25.095033140680385 Step 6059 | loss:1.0431638956069946 lr:3.37125101762549e-06 tokens_per_second_per_gpu:5355.984929094901 mfu:25.26509473580023 Step 6060 | loss:1.1339397430419922 lr:3.3657732895980565e-06 tokens_per_second_per_gpu:4533.712798949932 mfu:21.38629680381434 Step 6061 | loss:1.2679632902145386 lr:3.36029969418592e-06 tokens_per_second_per_gpu:3844.820107320213 mfu:18.136672440183705 Step 6062 | loss:1.2367572784423828 lr:3.3548302324346554e-06 tokens_per_second_per_gpu:5300.44791746495 mfu:25.00311717635047 Step 6063 | loss:1.076202392578125 lr:3.3493649053890326e-06 tokens_per_second_per_gpu:4332.94734119338 mfu:20.439251885457416 Step 6064 | loss:1.4140945672988892 lr:3.343903714093069e-06 tokens_per_second_per_gpu:4153.463829071575 mfu:19.59259753573394 Step 6065 | loss:1.1206011772155762 lr:3.338446659589975e-06 tokens_per_second_per_gpu:5215.411867064879 mfu:24.601987617967055 Step 6066 | loss:1.3528772592544556 lr:3.332993742922144e-06 tokens_per_second_per_gpu:5331.893999571894 mfu:25.15145371090378 Step 6067 | loss:1.2566275596618652 lr:3.3275449651312294e-06 tokens_per_second_per_gpu:3720.6496954615595 mfu:17.55093942178958 Step 6068 | loss:1.4448260068893433 lr:3.3221003272580625e-06 tokens_per_second_per_gpu:5065.581747248146 mfu:23.895213379137044 Step 6069 | loss:1.349790334701538 lr:3.316659830342672e-06 tokens_per_second_per_gpu:4706.890773270424 mfu:22.203206855893328 Step 6070 | loss:1.1959701776504517 lr:3.3112234754243354e-06 tokens_per_second_per_gpu:4781.851658664574 mfu:22.556810141943405 Step 6071 | loss:1.418357014656067 lr:3.3057912635415106e-06 tokens_per_second_per_gpu:3931.7784576873632 mfu:18.54686981549003 Step 6072 | loss:1.3026554584503174 lr:3.3003631957318566e-06 tokens_per_second_per_gpu:3903.8895171127856 mfu:18.415312924455822 Step 6073 | loss:1.167498230934143 lr:3.2949392730322716e-06 tokens_per_second_per_gpu:4758.011647883114 mfu:22.444352743561993 Step 6074 | loss:1.3855781555175781 lr:3.2895194964788404e-06 tokens_per_second_per_gpu:3685.434211679506 mfu:17.384821976408535 Step 6075 | loss:1.3366682529449463 lr:3.2841038671068496e-06 tokens_per_second_per_gpu:5248.7992444977435 mfu:24.759481573791867 Step 6076 | loss:1.5206959247589111 lr:3.2786923859508155e-06 tokens_per_second_per_gpu:3412.678301385868 mfu:16.098185810596412 Step 6077 | loss:1.3708388805389404 lr:3.273285054044453e-06 tokens_per_second_per_gpu:5338.899739571395 mfu:25.184500981783927 Step 6078 | loss:1.399552345275879 lr:3.267881872420664e-06 tokens_per_second_per_gpu:5309.10865919478 mfu:25.04397137276499 Step 6079 | loss:1.2031961679458618 lr:3.2624828421115944e-06 tokens_per_second_per_gpu:5331.488671222195 mfu:25.149541707922104 Step 6080 | loss:1.2426981925964355 lr:3.257087964148578e-06 tokens_per_second_per_gpu:5314.165676884374 mfu:25.067826188023 Step 6081 | loss:1.2821404933929443 lr:3.2516972395621347e-06 tokens_per_second_per_gpu:5305.390834701558 mfu:25.026433760304194 Step 6082 | loss:1.3087131977081299 lr:3.246310669382033e-06 tokens_per_second_per_gpu:4062.7991898399314 mfu:19.164916963495717 Step 6083 | loss:1.2383404970169067 lr:3.2409282546372267e-06 tokens_per_second_per_gpu:5277.074912918386 mfu:24.89286272605854 Step 6084 | loss:1.2233058214187622 lr:3.235549996355858e-06 tokens_per_second_per_gpu:3784.7103377141693 mfu:17.85312440116776 Step 6085 | loss:1.1141523122787476 lr:3.23017589556531e-06 tokens_per_second_per_gpu:4567.224074674227 mfu:21.54437520901906 Step 6086 | loss:1.2279330492019653 lr:3.224805953292154e-06 tokens_per_second_per_gpu:3972.6095855918006 mfu:18.739477212324047 Step 6087 | loss:1.3708367347717285 lr:3.219440170562152e-06 tokens_per_second_per_gpu:4974.286022342069 mfu:23.464555868098195 Step 6088 | loss:1.1164721250534058 lr:3.214078548400304e-06 tokens_per_second_per_gpu:5093.856788915095 mfu:24.02859157489961 Step 6089 | loss:1.1820807456970215 lr:3.208721087830799e-06 tokens_per_second_per_gpu:4643.29634913405 mfu:21.903221106914444 Step 6090 | loss:1.357180118560791 lr:3.20336778987701e-06 tokens_per_second_per_gpu:3049.9356459441938 mfu:14.38706681459909 Step 6091 | loss:1.3656947612762451 lr:3.198018655561555e-06 tokens_per_second_per_gpu:4796.389531886685 mfu:22.62538777034905 Step 6092 | loss:1.118536353111267 lr:3.192673685906236e-06 tokens_per_second_per_gpu:4383.833335215913 mfu:20.67928980130755 Step 6093 | loss:1.245186448097229 lr:3.1873328819320426e-06 tokens_per_second_per_gpu:4253.3961959551325 mfu:20.06399556054364 Step 6094 | loss:1.267404556274414 lr:3.1819962446592048e-06 tokens_per_second_per_gpu:4863.219793230937 mfu:22.940637515528255 Step 6095 | loss:1.2080379724502563 lr:3.1766637751071387e-06 tokens_per_second_per_gpu:5053.589720361389 mfu:23.83864494226144 Step 6096 | loss:1.1838622093200684 lr:3.171335474294443e-06 tokens_per_second_per_gpu:4428.92963014369 mfu:20.892016718703186 Step 6097 | loss:1.2209731340408325 lr:3.166011343238964e-06 tokens_per_second_per_gpu:4390.596063024023 mfu:20.71119074221875 Step 6098 | loss:1.232081413269043 lr:3.1606913829577172e-06 tokens_per_second_per_gpu:4940.779583817523 mfu:23.306500280790004 Step 6099 | loss:1.2719757556915283 lr:3.155375594466936e-06 tokens_per_second_per_gpu:3991.154203226094 mfu:18.82695533774304 Step 6100 | loss:1.1818064451217651 lr:3.15006397878205e-06 tokens_per_second_per_gpu:4975.048593456579 mfu:23.468153046153386 Step 6101 | loss:1.2114415168762207 lr:3.1447565369176978e-06 tokens_per_second_per_gpu:4711.741392425495 mfu:22.22608805404877 Step 6102 | loss:1.3002009391784668 lr:3.1394532698877184e-06 tokens_per_second_per_gpu:4828.529311634357 mfu:22.7769965950307 Step 6103 | loss:1.2582383155822754 lr:3.1341541787051537e-06 tokens_per_second_per_gpu:3913.0563252704533 mfu:18.45855432255429 Step 6104 | loss:1.3084993362426758 lr:3.1288592643822417e-06 tokens_per_second_per_gpu:5292.17981343521 mfu:24.964115118958176 Step 6105 | loss:1.1877148151397705 lr:3.1235685279304343e-06 tokens_per_second_per_gpu:5347.219979706554 mfu:25.22374897408082 Step 6106 | loss:1.2005763053894043 lr:3.118281970360376e-06 tokens_per_second_per_gpu:5342.263305870515 mfu:25.200367497900466 Step 6107 | loss:1.1674602031707764 lr:3.1129995926819173e-06 tokens_per_second_per_gpu:5202.345595030464 mfu:24.54035178344483 Step 6108 | loss:1.205839991569519 lr:3.107721395904109e-06 tokens_per_second_per_gpu:3916.4741467061804 mfu:18.474676769407083 Step 6109 | loss:1.2602883577346802 lr:3.1024473810352035e-06 tokens_per_second_per_gpu:4088.8692971631326 mfu:19.287894107758234 Step 6110 | loss:1.2387948036193848 lr:3.09717754908265e-06 tokens_per_second_per_gpu:4422.29381833381 mfu:20.860714462209742 Step 6111 | loss:1.1907391548156738 lr:3.09191190105311e-06 tokens_per_second_per_gpu:5300.775029117555 mfu:25.004660217826814 Step 6112 | loss:1.1855741739273071 lr:3.086650437952432e-06 tokens_per_second_per_gpu:4373.425570210679 mfu:20.63019459803004 Step 6113 | loss:1.3242583274841309 lr:3.0813931607856756e-06 tokens_per_second_per_gpu:5247.876366424319 mfu:24.755128200460288 Step 6114 | loss:1.2086753845214844 lr:3.076140070557096e-06 tokens_per_second_per_gpu:5317.003885855773 mfu:25.081214503989468 Step 6115 | loss:1.2207168340682983 lr:3.0708911682701513e-06 tokens_per_second_per_gpu:4459.332929426291 mfu:21.03543426875698 Step 6116 | loss:1.3838934898376465 lr:3.0656464549274927e-06 tokens_per_second_per_gpu:3857.8442246819423 mfu:18.198109423922546 Step 6117 | loss:1.0728685855865479 lr:3.0604059315309825e-06 tokens_per_second_per_gpu:4170.026603995224 mfu:19.670726970949598 Step 6118 | loss:1.1282846927642822 lr:3.0551695990816696e-06 tokens_per_second_per_gpu:4398.4819418689385 mfu:20.748389778199883 Step 6119 | loss:1.1700013875961304 lr:3.0499374585798156e-06 tokens_per_second_per_gpu:4143.042607977303 mfu:19.543438857788598 Step 6120 | loss:1.139696478843689 lr:3.0447095110248737e-06 tokens_per_second_per_gpu:3722.2639036075584 mfu:17.558553917026565 Step 6121 | loss:1.4272998571395874 lr:3.0394857574154944e-06 tokens_per_second_per_gpu:2997.8146303569515 mfu:14.141203091311818 Step 6122 | loss:1.5381546020507812 lr:3.034266198749533e-06 tokens_per_second_per_gpu:4772.975910316108 mfu:22.51494172262487 Step 6123 | loss:1.153287410736084 lr:3.029050836024036e-06 tokens_per_second_per_gpu:4524.887005164995 mfu:21.34466402869509 Step 6124 | loss:1.0501500368118286 lr:3.0238396702352595e-06 tokens_per_second_per_gpu:4924.882463555472 mfu:23.231510852185504 Step 6125 | loss:1.2702653408050537 lr:3.0186327023786458e-06 tokens_per_second_per_gpu:5339.979949648528 mfu:25.18959651702061 Step 6126 | loss:1.3129019737243652 lr:3.0134299334488443e-06 tokens_per_second_per_gpu:4197.565514072443 mfu:19.800632708406404 Step 6127 | loss:1.232715368270874 lr:3.0082313644396983e-06 tokens_per_second_per_gpu:5237.0724863046 mfu:24.704164454603546 Step 6128 | loss:1.413426399230957 lr:3.0030369963442467e-06 tokens_per_second_per_gpu:4870.141467619085 mfu:22.973288234576575 Step 6129 | loss:1.3012137413024902 lr:2.9978468301547323e-06 tokens_per_second_per_gpu:4960.998143234507 mfu:23.401874675201867 Step 6130 | loss:1.292284369468689 lr:2.99266086686259e-06 tokens_per_second_per_gpu:3265.3128707430096 mfu:15.403037931118902 Step 6131 | loss:1.1596343517303467 lr:2.987479107458449e-06 tokens_per_second_per_gpu:3605.48886443674 mfu:17.00770613338165 Step 6132 | loss:1.2372853755950928 lr:2.9823015529321487e-06 tokens_per_second_per_gpu:4733.255646495808 mfu:22.327574461208687 Step 6133 | loss:1.3016680479049683 lr:2.9771282042727083e-06 tokens_per_second_per_gpu:4944.847645481398 mfu:23.325690021741394 Step 6134 | loss:1.2315658330917358 lr:2.9719590624683546e-06 tokens_per_second_per_gpu:4704.999585487922 mfu:22.194285800453354 Step 6135 | loss:1.293495774269104 lr:2.9667941285065113e-06 tokens_per_second_per_gpu:4155.973038898367 mfu:19.604433906602264 Step 6136 | loss:1.2741299867630005 lr:2.9616334033737896e-06 tokens_per_second_per_gpu:4246.616314742301 mfu:20.032013704095696 Step 6137 | loss:1.2905243635177612 lr:2.9564768880560033e-06 tokens_per_second_per_gpu:5351.085061373334 mfu:25.241981223753953 Step 6138 | loss:1.2731010913848877 lr:2.951324583538165e-06 tokens_per_second_per_gpu:4085.5682277958445 mfu:19.27232240033222 Step 6139 | loss:1.2966883182525635 lr:2.9461764908044724e-06 tokens_per_second_per_gpu:4719.778994539351 mfu:22.264002794576154 Step 6140 | loss:1.2938618659973145 lr:2.941032610838329e-06 tokens_per_second_per_gpu:4171.387106252326 mfu:19.677144692221965 Step 6141 | loss:1.2580204010009766 lr:2.9358929446223286e-06 tokens_per_second_per_gpu:5311.889532649623 mfu:25.057089227317423 Step 6142 | loss:1.1021050214767456 lr:2.9307574931382614e-06 tokens_per_second_per_gpu:3359.0261776065136 mfu:15.845099588732948 Step 6143 | loss:1.0158730745315552 lr:2.9256262573671115e-06 tokens_per_second_per_gpu:4637.13947862266 mfu:21.87417809824179 Step 6144 | loss:1.3023277521133423 lr:2.9204992382890566e-06 tokens_per_second_per_gpu:4507.817567943059 mfu:21.264144580972918 Step 6145 | loss:1.2764182090759277 lr:2.915376436883474e-06 tokens_per_second_per_gpu:5330.19902415026 mfu:25.143458222647304 Step 6146 | loss:1.1677639484405518 lr:2.9102578541289312e-06 tokens_per_second_per_gpu:5299.754692282446 mfu:24.999847114888187 Step 6147 | loss:1.2946865558624268 lr:2.9051434910031872e-06 tokens_per_second_per_gpu:4836.172932197175 mfu:22.813052857361654 Step 6148 | loss:1.3320614099502563 lr:2.9000333484832027e-06 tokens_per_second_per_gpu:4305.020551154524 mfu:20.307516452042417 Step 6149 | loss:1.2464569807052612 lr:2.8949274275451242e-06 tokens_per_second_per_gpu:5090.6048787717245 mfu:24.013251759920248 Step 6150 | loss:1.3573415279388428 lr:2.8898257291643e-06 tokens_per_second_per_gpu:4211.703288227205 mfu:19.86732300124742 Step 6151 | loss:1.3211593627929688 lr:2.884728254315264e-06 tokens_per_second_per_gpu:4401.405984283586 mfu:20.762182985162855 Step 6152 | loss:1.2812508344650269 lr:2.879635003971745e-06 tokens_per_second_per_gpu:5328.376083904476 mfu:25.134859102482263 Step 6153 | loss:1.2624843120574951 lr:2.8745459791066688e-06 tokens_per_second_per_gpu:5054.540193742591 mfu:23.843128487368052 Step 6154 | loss:1.3896290063858032 lr:2.8694611806921513e-06 tokens_per_second_per_gpu:3336.897996312424 mfu:15.740717182111684 Step 6155 | loss:1.3478319644927979 lr:2.8643806096995017e-06 tokens_per_second_per_gpu:4527.393908168584 mfu:21.356489517884782 Step 6156 | loss:1.1344976425170898 lr:2.859304267099222e-06 tokens_per_second_per_gpu:3531.483861657655 mfu:16.65861190871722 Step 6157 | loss:1.3060142993927002 lr:2.854232153861003e-06 tokens_per_second_per_gpu:4877.937099252805 mfu:23.01006155906474 Step 6158 | loss:1.3389374017715454 lr:2.8491642709537303e-06 tokens_per_second_per_gpu:5317.055824396163 mfu:25.081459506946118 Step 6159 | loss:1.2846771478652954 lr:2.8441006193454855e-06 tokens_per_second_per_gpu:5260.795591981106 mfu:24.816070391658826 Step 6160 | loss:1.3318095207214355 lr:2.8390412000035336e-06 tokens_per_second_per_gpu:5287.7935028651955 mfu:24.943424143617662 Step 6161 | loss:1.1482540369033813 lr:2.833986013894341e-06 tokens_per_second_per_gpu:5287.626968119344 mfu:24.942638570807723 Step 6162 | loss:1.2599035501480103 lr:2.8289350619835536e-06 tokens_per_second_per_gpu:3649.170376540668 mfu:17.21375927881035 Step 6163 | loss:1.3426074981689453 lr:2.823888345236017e-06 tokens_per_second_per_gpu:5339.396089662634 mfu:25.186842349850362 Step 6164 | loss:1.1455869674682617 lr:2.8188458646157683e-06 tokens_per_second_per_gpu:5091.774026383785 mfu:24.018766828683486 Step 6165 | loss:1.4686850309371948 lr:2.8138076210860286e-06 tokens_per_second_per_gpu:3696.847215516505 mfu:17.43865906276691 Step 6166 | loss:1.2515002489089966 lr:2.8087736156092172e-06 tokens_per_second_per_gpu:5336.834640580269 mfu:25.17475955750056 Step 6167 | loss:1.2030609846115112 lr:2.8037438491469366e-06 tokens_per_second_per_gpu:3832.047956800769 mfu:18.076424027029905 Step 6168 | loss:1.4439845085144043 lr:2.798718322659988e-06 tokens_per_second_per_gpu:3424.7046431875774 mfu:16.15491611678057 Step 6169 | loss:1.357673168182373 lr:2.793697037108356e-06 tokens_per_second_per_gpu:4785.831612504898 mfu:22.575584263258364 Step 6170 | loss:1.3701106309890747 lr:2.7886799934512155e-06 tokens_per_second_per_gpu:4482.860249466003 mfu:21.146416651559026 Step 6171 | loss:1.390358805656433 lr:2.7836671926469326e-06 tokens_per_second_per_gpu:4691.1313284628 mfu:22.128866865897223 Step 6172 | loss:1.2310993671417236 lr:2.778658635653067e-06 tokens_per_second_per_gpu:4671.155315946574 mfu:22.034636606598998 Step 6173 | loss:1.2045035362243652 lr:2.7736543234263585e-06 tokens_per_second_per_gpu:4999.670415180215 mfu:23.58429838013975 Step 6174 | loss:1.3886464834213257 lr:2.7686542569227453e-06 tokens_per_second_per_gpu:5102.140275890062 mfu:24.06766619626914 Step 6175 | loss:1.2994680404663086 lr:2.7636584370973497e-06 tokens_per_second_per_gpu:5330.977990956783 mfu:25.147132741979117 Step 6176 | loss:1.1150580644607544 lr:2.758666864904483e-06 tokens_per_second_per_gpu:4112.22995255484 mfu:19.39809030497972 Step 6177 | loss:1.185813307762146 lr:2.7536795412976434e-06 tokens_per_second_per_gpu:5328.7000664422985 mfu:25.136387383390296 Step 6178 | loss:1.2818046808242798 lr:2.7486964672295252e-06 tokens_per_second_per_gpu:5298.604022360297 mfu:24.99441920854088 Step 6179 | loss:1.347602128982544 lr:2.743717643652002e-06 tokens_per_second_per_gpu:3964.503311028762 mfu:18.701238532137133 Step 6180 | loss:1.1501920223236084 lr:2.7387430715161393e-06 tokens_per_second_per_gpu:5350.808744415736 mfu:25.240677789520433 Step 6181 | loss:1.2807340621948242 lr:2.73377275177219e-06 tokens_per_second_per_gpu:4091.3900040574604 mfu:19.299784712255722 Step 6182 | loss:1.3024672269821167 lr:2.7288066853695978e-06 tokens_per_second_per_gpu:5346.977494403665 mfu:25.222605129534838 Step 6183 | loss:1.2834718227386475 lr:2.7238448732569895e-06 tokens_per_second_per_gpu:5310.304976613902 mfu:25.04961460614379 Step 6184 | loss:1.2582389116287231 lr:2.7188873163821792e-06 tokens_per_second_per_gpu:4163.858587874532 mfu:19.641631386536222 Step 6185 | loss:1.1900219917297363 lr:2.713934015692171e-06 tokens_per_second_per_gpu:4058.8760261296316 mfu:19.14641073091348 Step 6186 | loss:1.2768546342849731 lr:2.708984972133155e-06 tokens_per_second_per_gpu:4540.455633045437 mfu:21.418103902688962 Step 6187 | loss:1.2735368013381958 lr:2.7040401866505083e-06 tokens_per_second_per_gpu:3577.0466615711734 mfu:16.87353940972456 Step 6188 | loss:1.2024263143539429 lr:2.699099660188792e-06 tokens_per_second_per_gpu:4334.703170898986 mfu:20.4475344337542 Step 6189 | loss:1.4397200345993042 lr:2.694163393691759e-06 tokens_per_second_per_gpu:5307.171578001189 mfu:25.034833830274692 Step 6190 | loss:1.251838207244873 lr:2.6892313881023423e-06 tokens_per_second_per_gpu:5333.8043449598445 mfu:25.160465136037278 Step 6191 | loss:1.3294677734375 lr:2.6843036443626677e-06 tokens_per_second_per_gpu:4851.4782261785895 mfu:22.885250540424412 Step 6192 | loss:1.333768367767334 lr:2.6793801634140385e-06 tokens_per_second_per_gpu:4484.597734208371 mfu:21.15461266353424 Step 6193 | loss:1.3500388860702515 lr:2.674460946196952e-06 tokens_per_second_per_gpu:4061.630397433132 mfu:19.1594035702963 Step 6194 | loss:1.2913157939910889 lr:2.669545993651085e-06 tokens_per_second_per_gpu:5341.484949617462 mfu:25.19669585865354 Step 6195 | loss:1.248368263244629 lr:2.6646353067153018e-06 tokens_per_second_per_gpu:5315.245991997333 mfu:25.072922218731588 Step 6196 | loss:1.259641170501709 lr:2.6597288863276557e-06 tokens_per_second_per_gpu:5240.549188702393 mfu:24.720564653000533 Step 6197 | loss:1.1441892385482788 lr:2.654826733425378e-06 tokens_per_second_per_gpu:4808.5337457659625 mfu:22.682674099234152 Step 6198 | loss:1.138451099395752 lr:2.649928848944891e-06 tokens_per_second_per_gpu:5069.046085135506 mfu:23.911555252028712 Step 6199 | loss:1.469103455543518 lr:2.645035233821794e-06 tokens_per_second_per_gpu:5316.838499219368 mfu:25.080434347007678 Step 6200 | loss:1.2075576782226562 lr:2.6401458889908803e-06 tokens_per_second_per_gpu:4680.50386694589 mfu:22.078735316690043 Step 6201 | loss:1.429635763168335 lr:2.6352608153861202e-06 tokens_per_second_per_gpu:4149.379372203584 mfu:19.57333045580743 Step 6202 | loss:1.2178664207458496 lr:2.6303800139406725e-06 tokens_per_second_per_gpu:4851.7532076615225 mfu:22.886547674996088 Step 6203 | loss:1.3859801292419434 lr:2.6255034855868777e-06 tokens_per_second_per_gpu:4316.982534535827 mfu:20.363943168576842 Step 6204 | loss:1.2385327816009521 lr:2.62063123125626e-06 tokens_per_second_per_gpu:4444.349545639986 mfu:20.964755091008094 Step 6205 | loss:1.277089238166809 lr:2.615763251879527e-06 tokens_per_second_per_gpu:3940.947720558016 mfu:18.590122792888465 Step 6206 | loss:1.1529991626739502 lr:2.6108995483865697e-06 tokens_per_second_per_gpu:4279.448460209564 mfu:20.18688853600642 Step 6207 | loss:1.4057466983795166 lr:2.6060401217064656e-06 tokens_per_second_per_gpu:3117.502826827841 mfu:14.70579273497706 Step 6208 | loss:1.1992130279541016 lr:2.60118497276747e-06 tokens_per_second_per_gpu:4992.188926687516 mfu:23.54900692244613 Step 6209 | loss:1.377201795578003 lr:2.5963341024970278e-06 tokens_per_second_per_gpu:3692.729544980437 mfu:17.41923530830124 Step 6210 | loss:1.2892156839370728 lr:2.591487511821758e-06 tokens_per_second_per_gpu:5039.938724587288 mfu:23.774250866094956 Step 6211 | loss:1.2682783603668213 lr:2.586645201667465e-06 tokens_per_second_per_gpu:4292.68876282099 mfu:20.249345302453087 Step 6212 | loss:1.4025003910064697 lr:2.5818071729591443e-06 tokens_per_second_per_gpu:3781.478864913353 mfu:17.8378809926202 Step 6213 | loss:1.365342140197754 lr:2.5769734266209573e-06 tokens_per_second_per_gpu:4615.596052677757 mfu:21.77255408237219 Step 6214 | loss:1.1656920909881592 lr:2.572143963576265e-06 tokens_per_second_per_gpu:5354.450972643995 mfu:25.257858801501342 Step 6215 | loss:1.4579319953918457 lr:2.5673187847475937e-06 tokens_per_second_per_gpu:4501.066229061077 mfu:21.232297363569415 Step 6216 | loss:1.1928282976150513 lr:2.5624978910566645e-06 tokens_per_second_per_gpu:4391.1525813764365 mfu:20.713815934238905 Step 6217 | loss:1.2343348264694214 lr:2.5576812834243733e-06 tokens_per_second_per_gpu:3813.9952239969316 mfu:17.991266206280375 Step 6218 | loss:1.2409840822219849 lr:2.552868962770799e-06 tokens_per_second_per_gpu:4451.877948820984 mfu:21.000267853290893 Step 6219 | loss:1.314634919166565 lr:2.5480609300152e-06 tokens_per_second_per_gpu:4703.575828599516 mfu:22.187569696292773 Step 6220 | loss:1.2836217880249023 lr:2.543257186076017e-06 tokens_per_second_per_gpu:4313.818438002943 mfu:20.349017585380697 Step 6221 | loss:1.3419427871704102 lr:2.538457731870872e-06 tokens_per_second_per_gpu:4310.436192324407 mfu:20.333062955444422 Step 6222 | loss:1.1913942098617554 lr:2.5336625683165664e-06 tokens_per_second_per_gpu:4395.384271064941 mfu:20.733777536500288 Step 6223 | loss:1.278071641921997 lr:2.5288716963290798e-06 tokens_per_second_per_gpu:5309.014084760777 mfu:25.043525249023737 Step 6224 | loss:1.237114667892456 lr:2.5240851168235798e-06 tokens_per_second_per_gpu:3695.3264606675625 mfu:17.431485402676913 Step 6225 | loss:1.1689432859420776 lr:2.519302830714404e-06 tokens_per_second_per_gpu:4597.142005879921 mfu:21.685503195041743 Step 6226 | loss:1.1444493532180786 lr:2.5145248389150776e-06 tokens_per_second_per_gpu:4414.99458305535 mfu:20.826282724023287 Step 6227 | loss:1.208178997039795 lr:2.5097511423383042e-06 tokens_per_second_per_gpu:5352.7159274776195 mfu:25.24967429742232 Step 6228 | loss:1.1261628866195679 lr:2.504981741895959e-06 tokens_per_second_per_gpu:4934.032100340718 mfu:23.27467124999052 Step 6229 | loss:1.2464171648025513 lr:2.500216638499109e-06 tokens_per_second_per_gpu:3956.384461756253 mfu:18.662940534900187 Step 6230 | loss:1.3582032918930054 lr:2.4954558330579915e-06 tokens_per_second_per_gpu:4831.060678977848 mfu:22.788937486685747 Step 6231 | loss:1.1736053228378296 lr:2.490699326482021e-06 tokens_per_second_per_gpu:4496.123681519969 mfu:21.208982523532445 Step 6232 | loss:1.402559518814087 lr:2.48594711967981e-06 tokens_per_second_per_gpu:4527.853169707926 mfu:21.358655932923956 Step 6233 | loss:1.3046088218688965 lr:2.481199213559121e-06 tokens_per_second_per_gpu:5024.302957229956 mfu:23.700494283733423 Step 6234 | loss:1.2569475173950195 lr:2.476455609026909e-06 tokens_per_second_per_gpu:5312.107781570525 mfu:25.058118744714424 Step 6235 | loss:1.2086679935455322 lr:2.471716306989319e-06 tokens_per_second_per_gpu:5162.037992234467 mfu:24.35021394386992 Step 6236 | loss:1.1227794885635376 lr:2.4669813083516515e-06 tokens_per_second_per_gpu:4396.180944470373 mfu:20.737535580880213 Step 6237 | loss:1.1840423345565796 lr:2.4622506140183966e-06 tokens_per_second_per_gpu:4706.111877024594 mfu:22.199532669408345 Step 6238 | loss:1.1829313039779663 lr:2.4575242248932318e-06 tokens_per_second_per_gpu:3731.2309495895865 mfu:17.6008530028596 Step 6239 | loss:1.2382107973098755 lr:2.4528021418789878e-06 tokens_per_second_per_gpu:3579.6691636718183 mfu:16.8859101995783 Step 6240 | loss:1.321544885635376 lr:2.44808436587769e-06 tokens_per_second_per_gpu:3886.749536719076 mfu:18.334460712556485 Step 6241 | loss:1.3454087972640991 lr:2.4433708977905506e-06 tokens_per_second_per_gpu:5044.754465160266 mfu:23.79696753602776 Step 6242 | loss:1.37696373462677 lr:2.4386617385179335e-06 tokens_per_second_per_gpu:5306.903491560949 mfu:25.03356922079582 Step 6243 | loss:1.1581394672393799 lr:2.433956888959388e-06 tokens_per_second_per_gpu:4609.330648462828 mfu:21.74299910170218 Step 6244 | loss:1.2650681734085083 lr:2.429256350013662e-06 tokens_per_second_per_gpu:3800.5505434771776 mfu:17.92784535436966 Step 6245 | loss:1.205483317375183 lr:2.424560122578648e-06 tokens_per_second_per_gpu:5320.436955273782 mfu:25.09740887817626 Step 6246 | loss:1.1267818212509155 lr:2.419868207551429e-06 tokens_per_second_per_gpu:4048.7836564495165 mfu:19.09880330119655 Step 6247 | loss:1.1845589876174927 lr:2.4151806058282767e-06 tokens_per_second_per_gpu:4801.319681425226 mfu:22.6486441268926 Step 6248 | loss:1.3973909616470337 lr:2.4104973183046136e-06 tokens_per_second_per_gpu:3689.354450855872 mfu:17.40331441346523 Step 6249 | loss:1.1956422328948975 lr:2.4058183458750548e-06 tokens_per_second_per_gpu:4171.906052995093 mfu:19.679592652549044 Step 6250 | loss:1.3163466453552246 lr:2.401143689433391e-06 tokens_per_second_per_gpu:4429.044451165665 mfu:20.892558349054333 Step 6251 | loss:1.2103466987609863 lr:2.39647334987258e-06 tokens_per_second_per_gpu:4643.0671712813755 mfu:21.902140035881605 Step 6252 | loss:1.4155651330947876 lr:2.3918073280847635e-06 tokens_per_second_per_gpu:4392.011225782769 mfu:20.717866306403412 Step 6253 | loss:1.325725793838501 lr:2.387145624961254e-06 tokens_per_second_per_gpu:3684.9835269476416 mfu:17.38269601963359 Step 6254 | loss:1.460964322090149 lr:2.382488241392539e-06 tokens_per_second_per_gpu:5318.251950191952 mfu:25.087101836404962 Step 6255 | loss:1.134925127029419 lr:2.377835178268281e-06 tokens_per_second_per_gpu:5297.497107729062 mfu:24.989197703366234 Step 6256 | loss:1.276092767715454 lr:2.373186436477318e-06 tokens_per_second_per_gpu:4202.3732099453355 mfu:19.82331143011634 Step 6257 | loss:1.3408211469650269 lr:2.3685420169076655e-06 tokens_per_second_per_gpu:5314.505118636607 mfu:25.069427392683014 Step 6258 | loss:1.4242937564849854 lr:2.3639019204465068e-06 tokens_per_second_per_gpu:4187.911161131589 mfu:19.75509147838193 Step 6259 | loss:1.4609572887420654 lr:2.359266147980205e-06 tokens_per_second_per_gpu:4216.096895980592 mfu:19.888048398646934 Step 6260 | loss:1.4905997514724731 lr:2.3546347003942925e-06 tokens_per_second_per_gpu:3740.2220062855895 mfu:17.643265351327102 Step 6261 | loss:1.1610356569290161 lr:2.350007578573479e-06 tokens_per_second_per_gpu:5318.297000906183 mfu:25.087314348310432 Step 6262 | loss:1.2104350328445435 lr:2.3453847834016495e-06 tokens_per_second_per_gpu:3866.2980112181417 mfu:18.237987377378516 Step 6263 | loss:1.181789517402649 lr:2.3407663157618583e-06 tokens_per_second_per_gpu:4647.052612775743 mfu:21.920940043396975 Step 6264 | loss:1.3980605602264404 lr:2.3361521765363327e-06 tokens_per_second_per_gpu:5306.556574901689 mfu:25.031932755724 Step 6265 | loss:1.3076530694961548 lr:2.3315423666064788e-06 tokens_per_second_per_gpu:5304.916776951299 mfu:25.02419754901363 Step 6266 | loss:1.3480736017227173 lr:2.3269368868528706e-06 tokens_per_second_per_gpu:3879.143972798815 mfu:18.298583969901603 Step 6267 | loss:1.3553427457809448 lr:2.322335738155257e-06 tokens_per_second_per_gpu:3782.8410048363744 mfu:17.844306439042125 Step 6268 | loss:1.098541259765625 lr:2.3177389213925565e-06 tokens_per_second_per_gpu:5140.858092360346 mfu:24.25030474250014 Step 6269 | loss:1.3427032232284546 lr:2.3131464374428645e-06 tokens_per_second_per_gpu:5311.076099590343 mfu:25.053252124790806 Step 6270 | loss:1.4693925380706787 lr:2.308558287183449e-06 tokens_per_second_per_gpu:5145.739791427442 mfu:24.27333254990338 Step 6271 | loss:1.2853999137878418 lr:2.303974471490747e-06 tokens_per_second_per_gpu:4420.983641550759 mfu:20.85453413478488 Step 6272 | loss:1.3999112844467163 lr:2.299394991240364e-06 tokens_per_second_per_gpu:4105.755729133493 mfu:19.367550288484807 Step 6273 | loss:1.4658795595169067 lr:2.2948198473070894e-06 tokens_per_second_per_gpu:3503.3452725441584 mfu:16.5258773829305 Step 6274 | loss:1.371407151222229 lr:2.2902490405648707e-06 tokens_per_second_per_gpu:3003.377774888558 mfu:14.16744539323774 Step 6275 | loss:1.300264596939087 lr:2.2856825718868354e-06 tokens_per_second_per_gpu:4451.904976594326 mfu:21.000395347909166 Step 6276 | loss:1.1676596403121948 lr:2.281120442145279e-06 tokens_per_second_per_gpu:5302.805686510006 mfu:25.014239175212882 Step 6277 | loss:1.268966794013977 lr:2.2765626522116697e-06 tokens_per_second_per_gpu:5304.667543294516 mfu:25.023021871330936 Step 6278 | loss:1.1891417503356934 lr:2.2720092029566485e-06 tokens_per_second_per_gpu:4390.976146067882 mfu:20.712983658785486 Step 6279 | loss:1.19472336769104 lr:2.267460095250021e-06 tokens_per_second_per_gpu:3813.1834726190364 mfu:17.987437036531777 Step 6280 | loss:1.106977105140686 lr:2.2629153299607687e-06 tokens_per_second_per_gpu:5101.815535018032 mfu:24.06613433816927 Step 6281 | loss:1.4622223377227783 lr:2.258374907957042e-06 tokens_per_second_per_gpu:3466.800802347646 mfu:16.353490881883985 Step 6282 | loss:1.3935790061950684 lr:2.253838830106164e-06 tokens_per_second_per_gpu:3949.467738839974 mfu:18.63031317278948 Step 6283 | loss:1.1430062055587769 lr:2.249307097274622e-06 tokens_per_second_per_gpu:5358.975037706199 mfu:25.279199588284857 Step 6284 | loss:1.2547674179077148 lr:2.244779710328079e-06 tokens_per_second_per_gpu:4946.843343717406 mfu:23.335104070821874 Step 6285 | loss:1.3644382953643799 lr:2.240256670131366e-06 tokens_per_second_per_gpu:5359.749976016043 mfu:25.282855104510496 Step 6286 | loss:1.1719378232955933 lr:2.2357379775484857e-06 tokens_per_second_per_gpu:5275.396780919354 mfu:24.884946691100264 Step 6287 | loss:1.4013140201568604 lr:2.231223633442603e-06 tokens_per_second_per_gpu:5018.182038761479 mfu:23.671620866981236 Step 6288 | loss:1.1018447875976562 lr:2.226713638676062e-06 tokens_per_second_per_gpu:5066.367664188506 mfu:23.89892068343598 Step 6289 | loss:1.2973979711532593 lr:2.22220799411037e-06 tokens_per_second_per_gpu:3923.3627379376817 mfu:18.50717142956093 Step 6290 | loss:1.334026575088501 lr:2.2177067006062034e-06 tokens_per_second_per_gpu:4314.82438390426 mfu:20.353762803829273 Step 6291 | loss:1.3046154975891113 lr:2.21320975902341e-06 tokens_per_second_per_gpu:5214.846325458207 mfu:24.59931986171703 Step 6292 | loss:1.5310944318771362 lr:2.208717170221003e-06 tokens_per_second_per_gpu:5337.005625739053 mfu:25.17556612366763 Step 6293 | loss:1.4146857261657715 lr:2.2042289350571705e-06 tokens_per_second_per_gpu:2848.6540715719366 mfu:13.437587286107313 Step 6294 | loss:1.3598886728286743 lr:2.199745054389263e-06 tokens_per_second_per_gpu:4758.659950940517 mfu:22.44741089969567 Step 6295 | loss:1.1773267984390259 lr:2.195265529073795e-06 tokens_per_second_per_gpu:5334.955452087708 mfu:25.16589510475854 Step 6296 | loss:1.3165186643600464 lr:2.1907903599664605e-06 tokens_per_second_per_gpu:5301.352690206738 mfu:25.007385143743633 Step 6297 | loss:1.2347081899642944 lr:2.1863195479221195e-06 tokens_per_second_per_gpu:4321.774141121597 mfu:20.386545994374305 Step 6298 | loss:1.0759997367858887 lr:2.181853093794789e-06 tokens_per_second_per_gpu:5241.680483053898 mfu:24.7259011614753 Step 6299 | loss:1.2482340335845947 lr:2.1773909984376563e-06 tokens_per_second_per_gpu:5308.434496620113 mfu:25.040791232876295 Step 6300 | loss:1.5940964221954346 lr:2.1729332627030947e-06 tokens_per_second_per_gpu:4958.160399437898 mfu:23.388488553544246 Step 6301 | loss:1.410019040107727 lr:2.1684798874426205e-06 tokens_per_second_per_gpu:4243.983946223197 mfu:20.019596372662697 Step 6302 | loss:1.1614747047424316 lr:2.1640308735069196e-06 tokens_per_second_per_gpu:5022.361109487477 mfu:23.691334256618763 Step 6303 | loss:1.3695735931396484 lr:2.159586221745874e-06 tokens_per_second_per_gpu:4496.707874900363 mfu:21.21173826338143 Step 6304 | loss:1.205779790878296 lr:2.15514593300849e-06 tokens_per_second_per_gpu:5316.845436446567 mfu:25.080467071091988 Step 6305 | loss:1.017334222793579 lr:2.1507100081429617e-06 tokens_per_second_per_gpu:5297.5944692233925 mfu:24.989656974146573 Step 6306 | loss:1.4202415943145752 lr:2.1462784479966664e-06 tokens_per_second_per_gpu:4617.431367746052 mfu:21.781211576686378 Step 6307 | loss:1.3461346626281738 lr:2.1418512534161133e-06 tokens_per_second_per_gpu:4973.627046111537 mfu:23.46144736478584 Step 6308 | loss:1.42127525806427 lr:2.137428425246993e-06 tokens_per_second_per_gpu:5324.248808740376 mfu:25.11539004134745 Step 6309 | loss:1.1071150302886963 lr:2.1330099643341815e-06 tokens_per_second_per_gpu:5315.723529624175 mfu:25.07517484519372 Step 6310 | loss:1.3543223142623901 lr:2.1285958715216853e-06 tokens_per_second_per_gpu:5298.684411781933 mfu:24.994798419158585 Step 6311 | loss:1.2378476858139038 lr:2.124186147652696e-06 tokens_per_second_per_gpu:5021.709865940364 mfu:23.688262229693425 Step 6312 | loss:1.2871372699737549 lr:2.1197807935695785e-06 tokens_per_second_per_gpu:4558.516619179627 mfu:21.503300655805926 Step 6313 | loss:1.185813069343567 lr:2.1153798101138407e-06 tokens_per_second_per_gpu:5314.332361382674 mfu:25.068612467240786 Step 6314 | loss:1.214668869972229 lr:2.1109831981261707e-06 tokens_per_second_per_gpu:4608.70616060145 mfu:21.740053285911447 Step 6315 | loss:1.2873470783233643 lr:2.1065909584464278e-06 tokens_per_second_per_gpu:5330.188701220628 mfu:25.14340952762696 Step 6316 | loss:1.1921205520629883 lr:2.1022030919136155e-06 tokens_per_second_per_gpu:4033.5959718198706 mfu:19.027160401512308 Step 6317 | loss:1.1758577823638916 lr:2.0978195993659133e-06 tokens_per_second_per_gpu:3745.1283906261733 mfu:17.666409603377126 Step 6318 | loss:1.2013881206512451 lr:2.0934404816406766e-06 tokens_per_second_per_gpu:5337.240328837127 mfu:25.17667325822572 Step 6319 | loss:1.1806612014770508 lr:2.089065739574403e-06 tokens_per_second_per_gpu:5310.14323138136 mfu:25.048851626285305 Step 6320 | loss:1.3004342317581177 lr:2.0846953740027627e-06 tokens_per_second_per_gpu:4863.850291904544 mfu:22.943611685345825 Step 6321 | loss:1.2678216695785522 lr:2.080329385760607e-06 tokens_per_second_per_gpu:4503.552108286969 mfu:21.24402368001268 Step 6322 | loss:1.3397586345672607 lr:2.0759677756819223e-06 tokens_per_second_per_gpu:4415.19111338087 mfu:20.827209791100298 Step 6323 | loss:1.2522567510604858 lr:2.0716105445998725e-06 tokens_per_second_per_gpu:3723.2075721027854 mfu:17.563005362325 Step 6324 | loss:1.3387870788574219 lr:2.0672576933467967e-06 tokens_per_second_per_gpu:4224.0597805482585 mfu:19.925610683760812 Step 6325 | loss:1.2544573545455933 lr:2.0629092227541752e-06 tokens_per_second_per_gpu:5251.330298818967 mfu:24.77142098886748 Step 6326 | loss:1.3427609205245972 lr:2.0585651336526623e-06 tokens_per_second_per_gpu:5353.659872307092 mfu:25.254127046236537 Step 6327 | loss:1.4135011434555054 lr:2.0542254268720834e-06 tokens_per_second_per_gpu:3923.1406039027743 mfu:18.5061235854183 Step 6328 | loss:1.3116843700408936 lr:2.0498901032414085e-06 tokens_per_second_per_gpu:5276.132271321276 mfu:24.88841612481373 Step 6329 | loss:1.2520625591278076 lr:2.0455591635887812e-06 tokens_per_second_per_gpu:5078.183782849333 mfu:23.95465933119683 Step 6330 | loss:1.1848727464675903 lr:2.0412326087415195e-06 tokens_per_second_per_gpu:4115.965647562185 mfu:19.41571221570466 Step 6331 | loss:1.235613465309143 lr:2.036910439526074e-06 tokens_per_second_per_gpu:4490.519877208475 mfu:21.182548422487518 Step 6332 | loss:1.2451037168502808 lr:2.0325926567680787e-06 tokens_per_second_per_gpu:5147.349351881804 mfu:24.28092512118594 Step 6333 | loss:1.2524387836456299 lr:2.02827926129234e-06 tokens_per_second_per_gpu:5149.240826821308 mfu:24.28984753119448 Step 6334 | loss:1.3707737922668457 lr:2.023970253922794e-06 tokens_per_second_per_gpu:4595.841426146718 mfu:21.67936813853844 Step 6335 | loss:1.4270492792129517 lr:2.0196656354825567e-06 tokens_per_second_per_gpu:4292.805668435874 mfu:20.249896766184655 Step 6336 | loss:1.1011773347854614 lr:2.0153654067939205e-06 tokens_per_second_per_gpu:3806.598049551595 mfu:17.95637247233362 Step 6337 | loss:1.4550316333770752 lr:2.0110695686783114e-06 tokens_per_second_per_gpu:4316.730482285045 mfu:20.362754195105357 Step 6338 | loss:1.3680367469787598 lr:2.006778121956329e-06 tokens_per_second_per_gpu:5362.087413321761 mfu:25.2938811950895 Step 6339 | loss:1.167726993560791 lr:2.002491067447745e-06 tokens_per_second_per_gpu:5338.003609588322 mfu:25.18027378375823 Step 6340 | loss:1.1626112461090088 lr:1.998208405971472e-06 tokens_per_second_per_gpu:3998.6719787696898 mfu:18.862417967646955 Step 6341 | loss:1.2457278966903687 lr:1.9939301383455928e-06 tokens_per_second_per_gpu:5310.492598075207 mfu:25.050499648588286 Step 6342 | loss:1.2720248699188232 lr:1.9896562653873603e-06 tokens_per_second_per_gpu:4350.435203666762 mfu:20.52174511648137 Step 6343 | loss:1.4642099142074585 lr:1.985386787913168e-06 tokens_per_second_per_gpu:4746.59706831678 mfu:22.3905082242195 Step 6344 | loss:1.3105568885803223 lr:1.981121706738581e-06 tokens_per_second_per_gpu:3130.9863344450955 mfu:14.76939674093127 Step 6345 | loss:1.1512494087219238 lr:1.976861022678339e-06 tokens_per_second_per_gpu:4979.7529618921135 mfu:23.490344354711826 Step 6346 | loss:1.2910722494125366 lr:1.9726047365463072e-06 tokens_per_second_per_gpu:3863.3364127120303 mfu:18.224017011924378 Step 6347 | loss:1.1338773965835571 lr:1.9683528491555386e-06 tokens_per_second_per_gpu:4761.154811980678 mfu:22.459179584889295 Step 6348 | loss:1.3185126781463623 lr:1.964105361318244e-06 tokens_per_second_per_gpu:3659.640540937125 mfu:17.263148830662693 Step 6349 | loss:1.3847243785858154 lr:1.959862273845778e-06 tokens_per_second_per_gpu:5370.392474503431 mfu:25.33305758567299 Step 6350 | loss:1.177498459815979 lr:1.9556235875486606e-06 tokens_per_second_per_gpu:5219.010625323526 mfu:24.618963574684567 Step 6351 | loss:1.2649413347244263 lr:1.951389303236592e-06 tokens_per_second_per_gpu:3279.1025186802294 mfu:15.468086053195314 Step 6352 | loss:1.2172555923461914 lr:1.9471594217183977e-06 tokens_per_second_per_gpu:5321.091276942513 mfu:25.100495425126454 Step 6353 | loss:1.1972368955612183 lr:1.9429339438020805e-06 tokens_per_second_per_gpu:4615.544955016179 mfu:21.77231304598437 Step 6354 | loss:1.335261583328247 lr:1.938712870294812e-06 tokens_per_second_per_gpu:5218.16762878862 mfu:24.61498701619938 Step 6355 | loss:1.2850991487503052 lr:1.934496202002897e-06 tokens_per_second_per_gpu:3768.4223485986463 mfu:17.776291177492332 Step 6356 | loss:1.3230798244476318 lr:1.930283939731814e-06 tokens_per_second_per_gpu:3970.842909305505 mfu:18.731143498855534 Step 6357 | loss:1.2993087768554688 lr:1.92607608428621e-06 tokens_per_second_per_gpu:4616.510150349853 mfu:21.77686603705261 Step 6358 | loss:1.3058205842971802 lr:1.9218726364698653e-06 tokens_per_second_per_gpu:5309.638163942677 mfu:25.046469137003648 Step 6359 | loss:1.1914348602294922 lr:1.917673597085734e-06 tokens_per_second_per_gpu:3984.7220652905285 mfu:18.796613845665085 Step 6360 | loss:1.1386933326721191 lr:1.9134789669359334e-06 tokens_per_second_per_gpu:5331.629343102909 mfu:25.15020528118453 Step 6361 | loss:1.506730318069458 lr:1.909288746821722e-06 tokens_per_second_per_gpu:4058.9306774565375 mfu:19.146668530546975 Step 6362 | loss:1.1780834197998047 lr:1.9051029375435209e-06 tokens_per_second_per_gpu:5145.631211347289 mfu:24.27282035913963 Step 6363 | loss:1.3714931011199951 lr:1.9009215399009267e-06 tokens_per_second_per_gpu:4579.177416957498 mfu:21.60076116401974 Step 6364 | loss:1.3618836402893066 lr:1.8967445546926616e-06 tokens_per_second_per_gpu:3768.9567832868242 mfu:17.77881219710043 Step 6365 | loss:1.2132484912872314 lr:1.8925719827166345e-06 tokens_per_second_per_gpu:5311.047802718982 mfu:25.053118643620657 Step 6366 | loss:1.2668853998184204 lr:1.888403824769902e-06 tokens_per_second_per_gpu:4313.050793056992 mfu:20.34539647319691 Step 6367 | loss:1.2415401935577393 lr:1.8842400816486554e-06 tokens_per_second_per_gpu:4876.654191107218 mfu:23.00400986245531 Step 6368 | loss:1.409129023551941 lr:1.8800807541482806e-06 tokens_per_second_per_gpu:5301.674941371846 mfu:25.008905257471167 Step 6369 | loss:1.2308452129364014 lr:1.8759258430632947e-06 tokens_per_second_per_gpu:4163.356544773935 mfu:19.63926316357332 Step 6370 | loss:1.1682803630828857 lr:1.8717753491873714e-06 tokens_per_second_per_gpu:3859.5185557635514 mfu:18.206007529304834 Step 6371 | loss:1.2201566696166992 lr:1.8676292733133566e-06 tokens_per_second_per_gpu:4973.723155223771 mfu:23.46190072786615 Step 6372 | loss:1.2872368097305298 lr:1.8634876162332392e-06 tokens_per_second_per_gpu:5032.242973200592 mfu:23.737948693773333 Step 6373 | loss:1.2657372951507568 lr:1.8593503787381616e-06 tokens_per_second_per_gpu:3638.3627505500726 mfu:17.162777863041576 Step 6374 | loss:1.1638787984848022 lr:1.855217561618433e-06 tokens_per_second_per_gpu:5244.681738166309 mfu:24.74005859390747 Step 6375 | loss:1.2304339408874512 lr:1.8510891656635166e-06 tokens_per_second_per_gpu:3937.9195887394594 mfu:18.57583857844777 Step 6376 | loss:1.2638918161392212 lr:1.8469651916620146e-06 tokens_per_second_per_gpu:4291.876529519391 mfu:20.245513859388154 Step 6377 | loss:1.237026333808899 lr:1.842845640401708e-06 tokens_per_second_per_gpu:5341.537834637233 mfu:25.196945326314918 Step 6378 | loss:1.3852964639663696 lr:1.838730512669526e-06 tokens_per_second_per_gpu:4010.276556483451 mfu:18.91715874066789 Step 6379 | loss:1.3006151914596558 lr:1.834619809251531e-06 tokens_per_second_per_gpu:4259.960662057421 mfu:20.094961267161544 Step 6380 | loss:1.1984063386917114 lr:1.830513530932973e-06 tokens_per_second_per_gpu:5016.910514154399 mfu:23.665622868465174 Step 6381 | loss:1.3239667415618896 lr:1.8264116784982438e-06 tokens_per_second_per_gpu:4726.271268605114 mfu:22.294627959040533 Step 6382 | loss:1.184001088142395 lr:1.8223142527308723e-06 tokens_per_second_per_gpu:4764.150076100928 mfu:22.473308756789272 Step 6383 | loss:1.4942322969436646 lr:1.8182212544135713e-06 tokens_per_second_per_gpu:3742.6885242457124 mfu:17.65490033737636 Step 6384 | loss:1.3335908651351929 lr:1.8141326843281957e-06 tokens_per_second_per_gpu:4768.962568689449 mfu:22.49601010542523 Step 6385 | loss:1.355987310409546 lr:1.8100485432557352e-06 tokens_per_second_per_gpu:4411.282093951831 mfu:20.80877027950603 Step 6386 | loss:1.1417351961135864 lr:1.805968831976368e-06 tokens_per_second_per_gpu:5043.284310821838 mfu:23.790032567179203 Step 6387 | loss:1.1682759523391724 lr:1.8018935512694097e-06 tokens_per_second_per_gpu:5302.189700419287 mfu:25.011333463724895 Step 6388 | loss:1.2305124998092651 lr:1.7978227019133127e-06 tokens_per_second_per_gpu:4928.00413307138 mfu:23.246236299903785 Step 6389 | loss:1.349656581878662 lr:1.793756284685713e-06 tokens_per_second_per_gpu:4008.3832804927365 mfu:18.908227834793497 Step 6390 | loss:1.1136994361877441 lr:1.789694300363387e-06 tokens_per_second_per_gpu:4220.704741215083 mfu:19.909784390797487 Step 6391 | loss:1.2921944856643677 lr:1.7856367497222526e-06 tokens_per_second_per_gpu:5286.373582673426 mfu:24.936726137809725 Step 6392 | loss:1.3298641443252563 lr:1.781583633537401e-06 tokens_per_second_per_gpu:5340.3093976482605 mfu:25.191150579444972 Step 6393 | loss:1.2088491916656494 lr:1.7775349525830654e-06 tokens_per_second_per_gpu:5327.996133781341 mfu:25.13306681292526 Step 6394 | loss:1.4484965801239014 lr:1.7734907076326247e-06 tokens_per_second_per_gpu:4126.534465411245 mfu:19.465567132724946 Step 6395 | loss:1.3160544633865356 lr:1.7694508994586328e-06 tokens_per_second_per_gpu:5301.036423585845 mfu:25.00589326013223 Step 6396 | loss:1.3078210353851318 lr:1.7654155288327783e-06 tokens_per_second_per_gpu:4248.509496691213 mfu:20.04094416635886 Step 6397 | loss:1.1705385446548462 lr:1.7613845965258946e-06 tokens_per_second_per_gpu:5322.053074064366 mfu:25.105032386249743 Step 6398 | loss:1.348742961883545 lr:1.7573581033079906e-06 tokens_per_second_per_gpu:5326.76909742011 mfu:25.12727867305534 Step 6399 | loss:1.2567750215530396 lr:1.7533360499482176e-06 tokens_per_second_per_gpu:3507.9031727641564 mfu:16.547377775926194 Step 6400 | loss:1.2796282768249512 lr:1.749318437214864e-06 tokens_per_second_per_gpu:5360.274389305297 mfu:25.28532885147004 Step 6401 | loss:1.3205022811889648 lr:1.7453052658753937e-06 tokens_per_second_per_gpu:4474.534206184499 mfu:21.107141284830707 Step 6402 | loss:1.5222116708755493 lr:1.741296536696413e-06 tokens_per_second_per_gpu:5321.559749830096 mfu:25.102705291666897 Step 6403 | loss:1.1758484840393066 lr:1.7372922504436646e-06 tokens_per_second_per_gpu:5308.240972048518 mfu:25.039878344453385 Step 6404 | loss:1.20540452003479 lr:1.7332924078820644e-06 tokens_per_second_per_gpu:3687.7096853623007 mfu:17.395555774006123 Step 6405 | loss:1.467500925064087 lr:1.7292970097756767e-06 tokens_per_second_per_gpu:3441.6587976541946 mfu:16.23489175607664 Step 6406 | loss:1.313920021057129 lr:1.7253060568876933e-06 tokens_per_second_per_gpu:5332.612359687151 mfu:25.154842338132323 Step 6407 | loss:1.1354533433914185 lr:1.7213195499804906e-06 tokens_per_second_per_gpu:5316.10653783062 mfu:25.07698156025146 Step 6408 | loss:1.2304229736328125 lr:1.7173374898155765e-06 tokens_per_second_per_gpu:4830.053631571965 mfu:22.78418707225219 Step 6409 | loss:1.4111199378967285 lr:1.713359877153603e-06 tokens_per_second_per_gpu:4180.240355087343 mfu:19.718906977496758 Step 6410 | loss:1.3146191835403442 lr:1.7093867127543933e-06 tokens_per_second_per_gpu:4531.180874744505 mfu:21.37435328534652 Step 6411 | loss:1.0973163843154907 lr:1.705417997376907e-06 tokens_per_second_per_gpu:4732.227797653886 mfu:22.322725922852246 Step 6412 | loss:1.3680479526519775 lr:1.7014537317792484e-06 tokens_per_second_per_gpu:4287.2462624109685 mfu:20.223672099432697 Step 6413 | loss:1.363951325416565 lr:1.6974939167186899e-06 tokens_per_second_per_gpu:3752.517037272705 mfu:17.701263110241925 Step 6414 | loss:1.2280941009521484 lr:1.6935385529516428e-06 tokens_per_second_per_gpu:3618.4115041813793 mfu:17.068664429886805 Step 6415 | loss:1.2212265729904175 lr:1.6895876412336558e-06 tokens_per_second_per_gpu:4677.133053414267 mfu:22.062834614141288 Step 6416 | loss:1.2973500490188599 lr:1.6856411823194584e-06 tokens_per_second_per_gpu:4984.411691049026 mfu:23.51232037500614 Step 6417 | loss:1.2099171876907349 lr:1.6816991769629031e-06 tokens_per_second_per_gpu:4926.094510879036 mfu:23.23722828620735 Step 6418 | loss:1.103479266166687 lr:1.6777616259169958e-06 tokens_per_second_per_gpu:5294.3490313560005 mfu:24.974347689997288 Step 6419 | loss:1.2120552062988281 lr:1.673828529933902e-06 tokens_per_second_per_gpu:4242.923321260365 mfu:20.014593223751742 Step 6420 | loss:1.1112853288650513 lr:1.6698998897649337e-06 tokens_per_second_per_gpu:4461.62404327036 mfu:21.046241843663783 Step 6421 | loss:1.2097219228744507 lr:1.665975706160533e-06 tokens_per_second_per_gpu:4101.217907862416 mfu:19.34614461131699 Step 6422 | loss:1.1538944244384766 lr:1.6620559798703194e-06 tokens_per_second_per_gpu:4756.721768660109 mfu:22.43826816319099 Step 6423 | loss:1.2254855632781982 lr:1.6581407116430497e-06 tokens_per_second_per_gpu:4217.065609594091 mfu:19.89261798604139 Step 6424 | loss:1.2585258483886719 lr:1.6542299022266089e-06 tokens_per_second_per_gpu:4682.703175228046 mfu:22.089109829097662 Step 6425 | loss:1.447026252746582 lr:1.6503235523680633e-06 tokens_per_second_per_gpu:4404.456240274054 mfu:20.776571563097228 Step 6426 | loss:1.3318933248519897 lr:1.646421662813613e-06 tokens_per_second_per_gpu:5352.783133061663 mfu:25.24999131762871 Step 6427 | loss:1.23149573802948 lr:1.64252423430859e-06 tokens_per_second_per_gpu:5301.59702045215 mfu:25.00853769119828 Step 6428 | loss:1.4182837009429932 lr:1.6386312675975041e-06 tokens_per_second_per_gpu:5225.685883898031 mfu:24.65045190829706 Step 6429 | loss:1.2732514142990112 lr:1.6347427634239965e-06 tokens_per_second_per_gpu:3665.1700263097746 mfu:17.28923235659297 Step 6430 | loss:1.3117882013320923 lr:1.6308587225308452e-06 tokens_per_second_per_gpu:4386.757111037527 mfu:20.693081750705694 Step 6431 | loss:1.2488276958465576 lr:1.6269791456600014e-06 tokens_per_second_per_gpu:4110.787269763683 mfu:19.39128492410677 Step 6432 | loss:1.2647737264633179 lr:1.6231040335525472e-06 tokens_per_second_per_gpu:5264.639131659111 mfu:24.834201024095467 Step 6433 | loss:1.2727864980697632 lr:1.6192333869487098e-06 tokens_per_second_per_gpu:4017.2849337547505 mfu:18.950218452009075 Step 6434 | loss:1.2788673639297485 lr:1.61536720658787e-06 tokens_per_second_per_gpu:5298.569889671725 mfu:24.994258198825246 Step 6435 | loss:1.0976554155349731 lr:1.6115054932085565e-06 tokens_per_second_per_gpu:3630.372238012876 mfu:17.1250852520816 Step 6436 | loss:1.3647946119308472 lr:1.6076482475484406e-06 tokens_per_second_per_gpu:3839.1310013585066 mfu:18.10983595670077 Step 6437 | loss:1.3587173223495483 lr:1.6037954703443408e-06 tokens_per_second_per_gpu:4733.744161285807 mfu:22.329878868822334 Step 6438 | loss:1.3909457921981812 lr:1.5999471623322215e-06 tokens_per_second_per_gpu:4991.8878525899 mfu:23.547586704559134 Step 6439 | loss:1.2204835414886475 lr:1.5961033242471945e-06 tokens_per_second_per_gpu:5317.360484104807 mfu:25.082896638772098 Step 6440 | loss:1.2824571132659912 lr:1.5922639568235198e-06 tokens_per_second_per_gpu:3570.6318207841996 mfu:16.843279511247708 Step 6441 | loss:1.290225625038147 lr:1.5884290607946023e-06 tokens_per_second_per_gpu:5345.223816901608 mfu:25.214332733549398 Step 6442 | loss:1.496867299079895 lr:1.5845986368929893e-06 tokens_per_second_per_gpu:5230.22545327951 mfu:24.6718658315999 Step 6443 | loss:1.3331807851791382 lr:1.5807726858503763e-06 tokens_per_second_per_gpu:5103.097549019087 mfu:24.07218181694639 Step 6444 | loss:1.2971229553222656 lr:1.5769512083976063e-06 tokens_per_second_per_gpu:3987.033887305246 mfu:18.807519104546014 Step 6445 | loss:1.302323579788208 lr:1.5731342052646647e-06 tokens_per_second_per_gpu:4294.350572015 mfu:20.257184339955117 Step 6446 | loss:1.3053011894226074 lr:1.5693216771806852e-06 tokens_per_second_per_gpu:3912.923253672845 mfu:18.457926601124015 Step 6447 | loss:1.260285496711731 lr:1.5655136248739434e-06 tokens_per_second_per_gpu:4125.407711709274 mfu:19.46025204326874 Step 6448 | loss:1.2741364240646362 lr:1.56171004907186e-06 tokens_per_second_per_gpu:4811.20112511471 mfu:22.695256582724035 Step 6449 | loss:1.2668133974075317 lr:1.5579109505010042e-06 tokens_per_second_per_gpu:4318.923139828996 mfu:20.37309733484613 Step 6450 | loss:1.2616559267044067 lr:1.554116329887087e-06 tokens_per_second_per_gpu:4607.739888227016 mfu:21.735495214258172 Step 6451 | loss:1.2744861841201782 lr:1.5503261879549647e-06 tokens_per_second_per_gpu:4234.1377169138095 mfu:19.97315002907037 Step 6452 | loss:1.3959964513778687 lr:1.5465405254286386e-06 tokens_per_second_per_gpu:5318.959924286096 mfu:25.09044147099987 Step 6453 | loss:1.2757192850112915 lr:1.5427593430312526e-06 tokens_per_second_per_gpu:5162.613707528839 mfu:24.35292969114063 Step 6454 | loss:1.324497103691101 lr:1.5389826414850983e-06 tokens_per_second_per_gpu:5320.291042420141 mfu:25.096720582350333 Step 6455 | loss:1.2378013134002686 lr:1.5352104215116097e-06 tokens_per_second_per_gpu:5169.711159201423 mfu:24.386409581630332 Step 6456 | loss:1.242855191230774 lr:1.5314426838313605e-06 tokens_per_second_per_gpu:5345.675821843933 mfu:25.21646491798234 Step 6457 | loss:1.3731341361999512 lr:1.5276794291640722e-06 tokens_per_second_per_gpu:4459.320085960909 mfu:21.035373683939447 Step 6458 | loss:1.221807837486267 lr:1.523920658228614e-06 tokens_per_second_per_gpu:4526.033355687687 mfu:21.350071559698197 Step 6459 | loss:1.1960772275924683 lr:1.5201663717429897e-06 tokens_per_second_per_gpu:3245.1160305411927 mfu:15.30776598995066 Step 6460 | loss:1.2786332368850708 lr:1.5164165704243533e-06 tokens_per_second_per_gpu:4061.20703543309 mfu:19.157406499509094 Step 6461 | loss:1.1260440349578857 lr:1.5126712549889983e-06 tokens_per_second_per_gpu:3663.0217250420696 mfu:17.279098452975212 Step 6462 | loss:1.1126703023910522 lr:1.5089304261523663e-06 tokens_per_second_per_gpu:5370.254215296965 mfu:25.33240539340664 Step 6463 | loss:1.1317882537841797 lr:1.505194084629033e-06 tokens_per_second_per_gpu:4017.2986512815232 mfu:18.950283159923313 Step 6464 | loss:1.2082935571670532 lr:1.501462231132722e-06 tokens_per_second_per_gpu:5329.160943054051 mfu:25.13856141700159 Step 6465 | loss:1.1379770040512085 lr:1.4977348663763074e-06 tokens_per_second_per_gpu:4745.98341662022 mfu:22.38761352446705 Step 6466 | loss:1.382743000984192 lr:1.4940119910717892e-06 tokens_per_second_per_gpu:3741.8295586777085 mfu:17.650848450237447 Step 6467 | loss:1.1809698343276978 lr:1.4902936059303235e-06 tokens_per_second_per_gpu:4572.720898048132 mfu:21.570304662728542 Step 6468 | loss:1.254390835762024 lr:1.486579711662206e-06 tokens_per_second_per_gpu:3354.3840249219834 mfu:15.8232017624871 Step 6469 | loss:1.3085498809814453 lr:1.4828703089768665e-06 tokens_per_second_per_gpu:5324.733670793902 mfu:25.117677218379928 Step 6470 | loss:1.3358064889907837 lr:1.4791653985828879e-06 tokens_per_second_per_gpu:4703.862848936336 mfu:22.188923620192273 Step 6471 | loss:1.3598237037658691 lr:1.4754649811879878e-06 tokens_per_second_per_gpu:4774.216421801082 mfu:22.52079342695258 Step 6472 | loss:1.528839349746704 lr:1.4717690574990283e-06 tokens_per_second_per_gpu:5308.697605030787 mfu:25.042032360140364 Step 6473 | loss:1.2722729444503784 lr:1.4680776282220115e-06 tokens_per_second_per_gpu:4322.562529913112 mfu:20.39026495881688 Step 6474 | loss:1.2111315727233887 lr:1.4643906940620844e-06 tokens_per_second_per_gpu:5317.1987827549465 mfu:25.082133865915708 Step 6475 | loss:1.397275447845459 lr:1.4607082557235307e-06 tokens_per_second_per_gpu:4798.703593446292 mfu:22.636303593545332 Step 6476 | loss:1.307230830192566 lr:1.4570303139097768e-06 tokens_per_second_per_gpu:5314.307657923349 mfu:25.068495936808308 Step 6477 | loss:1.1274625062942505 lr:1.4533568693233913e-06 tokens_per_second_per_gpu:4881.383177826105 mfu:23.026317299656625 Step 6478 | loss:1.3742085695266724 lr:1.4496879226660875e-06 tokens_per_second_per_gpu:3455.7845610014365 mfu:16.301525391889328 Step 6479 | loss:1.1656008958816528 lr:1.4460234746387135e-06 tokens_per_second_per_gpu:4582.299774191999 mfu:21.61548985582396 Step 6480 | loss:1.1396335363388062 lr:1.442363525941251e-06 tokens_per_second_per_gpu:5307.063701059347 mfu:25.03432495633432 Step 6481 | loss:1.2056008577346802 lr:1.4387080772728406e-06 tokens_per_second_per_gpu:5303.994328958807 mfu:25.01984620444719 Step 6482 | loss:1.1515613794326782 lr:1.4350571293317572e-06 tokens_per_second_per_gpu:3646.1615852861055 mfu:17.199566297109858 Step 6483 | loss:1.1956626176834106 lr:1.4314106828153983e-06 tokens_per_second_per_gpu:4855.985239294221 mfu:22.90651089026658 Step 6484 | loss:1.200233817100525 lr:1.4277687384203293e-06 tokens_per_second_per_gpu:4350.898385146674 mfu:20.523930022549024 Step 6485 | loss:1.25252103805542 lr:1.4241312968422378e-06 tokens_per_second_per_gpu:4131.035210264504 mfu:19.486797914104024 Step 6486 | loss:1.1886200904846191 lr:1.4204983587759484e-06 tokens_per_second_per_gpu:4858.89915900197 mfu:22.920256346693996 Step 6487 | loss:1.359860897064209 lr:1.4168699249154426e-06 tokens_per_second_per_gpu:3670.07539534861 mfu:17.312371819291418 Step 6488 | loss:1.3739434480667114 lr:1.4132459959538325e-06 tokens_per_second_per_gpu:4362.409800034762 mfu:20.578231330626043 Step 6489 | loss:1.2839292287826538 lr:1.4096265725833557e-06 tokens_per_second_per_gpu:5280.916202403735 mfu:24.910982743952502 Step 6490 | loss:1.4432144165039062 lr:1.4060116554954122e-06 tokens_per_second_per_gpu:3388.7022971374417 mfu:15.985086907828437 Step 6491 | loss:1.1518555879592896 lr:1.4024012453805358e-06 tokens_per_second_per_gpu:5313.913653702038 mfu:25.066637351672327 Step 6492 | loss:1.2135035991668701 lr:1.3987953429283772e-06 tokens_per_second_per_gpu:3939.5574520680957 mfu:18.58356465921725 Step 6493 | loss:1.2738062143325806 lr:1.3951939488277581e-06 tokens_per_second_per_gpu:3942.6029703434288 mfu:18.597930888540994 Step 6494 | loss:1.2834330797195435 lr:1.3915970637666254e-06 tokens_per_second_per_gpu:4286.378715169166 mfu:20.21957973107429 Step 6495 | loss:1.257135033607483 lr:1.3880046884320486e-06 tokens_per_second_per_gpu:4455.970326834501 mfu:21.019572298612342 Step 6496 | loss:1.2726855278015137 lr:1.3844168235102651e-06 tokens_per_second_per_gpu:4099.4713821793885 mfu:19.337905951682142 Step 6497 | loss:1.1598931550979614 lr:1.3808334696866322e-06 tokens_per_second_per_gpu:5338.019547606293 mfu:25.180348966108305 Step 6498 | loss:1.355098843574524 lr:1.3772546276456494e-06 tokens_per_second_per_gpu:3599.499562494079 mfu:16.97945357423783 Step 6499 | loss:1.2608381509780884 lr:1.3736802980709534e-06 tokens_per_second_per_gpu:4952.737071361866 mfu:23.36290578969442 Step 6500 | loss:1.3846402168273926 lr:1.370110481645323e-06 tokens_per_second_per_gpu:4680.405884098924 mfu:22.078273114883306 Step 6501 | loss:1.208885908126831 lr:1.3665451790506683e-06 tokens_per_second_per_gpu:4931.830844036319 mfu:23.264287548429618 Step 6502 | loss:1.2697468996047974 lr:1.3629843909680446e-06 tokens_per_second_per_gpu:4195.40623615805 mfu:19.790447026073412 Step 6503 | loss:1.2048187255859375 lr:1.359428118077638e-06 tokens_per_second_per_gpu:4200.199550606594 mfu:19.81305790815097 Step 6504 | loss:1.2447937726974487 lr:1.355876361058775e-06 tokens_per_second_per_gpu:5327.737621034428 mfu:25.131847364191252 Step 6505 | loss:1.4019973278045654 lr:1.3523291205899236e-06 tokens_per_second_per_gpu:4116.170239987293 mfu:19.416677313080964 Step 6506 | loss:1.3436118364334106 lr:1.348786397348681e-06 tokens_per_second_per_gpu:5329.255319662324 mfu:25.139006607565126 Step 6507 | loss:1.446669101715088 lr:1.3452481920117888e-06 tokens_per_second_per_gpu:4948.64813266604 mfu:23.343617568221326 Step 6508 | loss:1.2855052947998047 lr:1.3417145052551179e-06 tokens_per_second_per_gpu:4383.465731976489 mfu:20.677555754107605 Step 6509 | loss:1.4566205739974976 lr:1.3381853377536863e-06 tokens_per_second_per_gpu:5308.548170452845 mfu:25.041327451740045 Step 6510 | loss:1.2565405368804932 lr:1.3346606901816384e-06 tokens_per_second_per_gpu:4018.3394795890363 mfu:18.955192924633472 Step 6511 | loss:1.1314826011657715 lr:1.3311405632122632e-06 tokens_per_second_per_gpu:3898.3647117947894 mfu:18.389251475141844 Step 6512 | loss:1.4522802829742432 lr:1.3276249575179782e-06 tokens_per_second_per_gpu:4985.238854530267 mfu:23.5162222462758 Step 6513 | loss:1.1126267910003662 lr:1.3241138737703468e-06 tokens_per_second_per_gpu:5189.785529168893 mfu:24.48110380980759 Step 6514 | loss:1.3674646615982056 lr:1.3206073126400625e-06 tokens_per_second_per_gpu:4028.208184311914 mfu:19.001745288585937 Step 6515 | loss:1.275407075881958 lr:1.317105274796951e-06 tokens_per_second_per_gpu:4858.884439503537 mfu:22.920186912308484 Step 6516 | loss:1.2281527519226074 lr:1.313607760909985e-06 tokens_per_second_per_gpu:5334.388923633814 mfu:25.163222693381798 Step 6517 | loss:1.3362982273101807 lr:1.310114771647264e-06 tokens_per_second_per_gpu:4151.758412246935 mfu:19.584552793598004 Step 6518 | loss:1.3216702938079834 lr:1.306626307676026e-06 tokens_per_second_per_gpu:3154.6374166435226 mfu:14.88096293095198 Step 6519 | loss:1.1558012962341309 lr:1.3031423696626465e-06 tokens_per_second_per_gpu:5298.239871534052 mfu:24.992701446962943 Step 6520 | loss:1.3061269521713257 lr:1.299662958272635e-06 tokens_per_second_per_gpu:3405.5957882408115 mfu:16.06477638768983 Step 6521 | loss:1.3906928300857544 lr:1.2961880741706317e-06 tokens_per_second_per_gpu:5319.603227527113 mfu:25.0934760421466 Step 6522 | loss:1.1924022436141968 lr:1.2927177180204197e-06 tokens_per_second_per_gpu:4421.977478398303 mfu:20.859222232760796 Step 6523 | loss:1.1511445045471191 lr:1.2892518904849133e-06 tokens_per_second_per_gpu:3875.7236658944844 mfu:18.28244979866934 Step 6524 | loss:1.1231591701507568 lr:1.285790592226163e-06 tokens_per_second_per_gpu:3564.183291699781 mfu:16.81286069932399 Step 6525 | loss:1.355104684829712 lr:1.2823338239053518e-06 tokens_per_second_per_gpu:4248.532767358388 mfu:20.04105393806631 Step 6526 | loss:1.2105857133865356 lr:1.278881586182798e-06 tokens_per_second_per_gpu:4868.149484283123 mfu:22.963891709313437 Step 6527 | loss:1.5091089010238647 lr:1.2754338797179577e-06 tokens_per_second_per_gpu:4433.493793959328 mfu:20.913546658148203 Step 6528 | loss:1.1882747411727905 lr:1.2719907051694152e-06 tokens_per_second_per_gpu:5350.226705678304 mfu:25.237932213489916 Step 6529 | loss:1.4162893295288086 lr:1.268552063194897e-06 tokens_per_second_per_gpu:5064.192155802573 mfu:23.88865843919953 Step 6530 | loss:1.3096003532409668 lr:1.2651179544512588e-06 tokens_per_second_per_gpu:3747.703733204958 mfu:17.678557933720008 Step 6531 | loss:1.1284124851226807 lr:1.2616883795944918e-06 tokens_per_second_per_gpu:4097.181166095886 mfu:19.327102611665104 Step 6532 | loss:1.377998948097229 lr:1.2582633392797165e-06 tokens_per_second_per_gpu:3772.467348908659 mfu:17.79537213410288 Step 6533 | loss:1.2570422887802124 lr:1.2548428341611933e-06 tokens_per_second_per_gpu:4718.6439283065665 mfu:22.25864849349384 Step 6534 | loss:1.1908982992172241 lr:1.251426864892319e-06 tokens_per_second_per_gpu:4318.345807515692 mfu:20.370373959821226 Step 6535 | loss:1.400371789932251 lr:1.2480154321256127e-06 tokens_per_second_per_gpu:5327.703002252211 mfu:25.13168406148896 Step 6536 | loss:1.2868410348892212 lr:1.244608536512737e-06 tokens_per_second_per_gpu:4153.4522146717145 mfu:19.592542748628183 Step 6537 | loss:1.2232295274734497 lr:1.241206178704482e-06 tokens_per_second_per_gpu:5334.039309988889 mfu:25.16157350616845 Step 6538 | loss:1.2609961032867432 lr:1.2378083593507756e-06 tokens_per_second_per_gpu:5325.798842764588 mfu:25.12270181630273 Step 6539 | loss:1.2526490688323975 lr:1.2344150791006732e-06 tokens_per_second_per_gpu:3419.600501850269 mfu:16.130839011236176 Step 6540 | loss:1.2681001424789429 lr:1.2310263386023702e-06 tokens_per_second_per_gpu:5034.173066255023 mfu:23.747053272018913 Step 6541 | loss:1.185215711593628 lr:1.2276421385031878e-06 tokens_per_second_per_gpu:3181.856938308858 mfu:15.009362058776649 Step 6542 | loss:1.4417611360549927 lr:1.2242624794495867e-06 tokens_per_second_per_gpu:3643.544422211282 mfu:17.18722069235185 Step 6543 | loss:1.2224280834197998 lr:1.2208873620871503e-06 tokens_per_second_per_gpu:5173.281319858558 mfu:24.40325063858226 Step 6544 | loss:1.373203158378601 lr:1.2175167870606075e-06 tokens_per_second_per_gpu:3730.197359525757 mfu:17.595977382179864 Step 6545 | loss:1.1771749258041382 lr:1.214150755013807e-06 tokens_per_second_per_gpu:4407.576749190441 mfu:20.79129153606955 Step 6546 | loss:1.3060951232910156 lr:1.2107892665897375e-06 tokens_per_second_per_gpu:3613.7022724099006 mfu:17.046450180142948 Step 6547 | loss:1.1625760793685913 lr:1.2074323224305212e-06 tokens_per_second_per_gpu:5302.563964879067 mfu:25.013098933037774 Step 6548 | loss:1.2702417373657227 lr:1.2040799231774008e-06 tokens_per_second_per_gpu:5320.879235124948 mfu:25.09949518769493 Step 6549 | loss:1.2465229034423828 lr:1.2007320694707642e-06 tokens_per_second_per_gpu:4757.367292577719 mfu:22.441313209648094 Step 6550 | loss:1.2167227268218994 lr:1.1973887619501244e-06 tokens_per_second_per_gpu:5145.9320897186335 mfu:24.274239653752403 Step 6551 | loss:1.230027198791504 lr:1.1940500012541295e-06 tokens_per_second_per_gpu:5316.660634900388 mfu:25.079595330668266 Step 6552 | loss:1.158936858177185 lr:1.1907157880205494e-06 tokens_per_second_per_gpu:5166.412848661176 mfu:24.370850888062183 Step 6553 | loss:1.2171655893325806 lr:1.1873861228862998e-06 tokens_per_second_per_gpu:4352.079589373565 mfu:20.52950196442149 Step 6554 | loss:1.1801984310150146 lr:1.1840610064874165e-06 tokens_per_second_per_gpu:5350.009218150866 mfu:25.236906287715794 Step 6555 | loss:1.276411533355713 lr:1.1807404394590716e-06 tokens_per_second_per_gpu:4257.872615732831 mfu:20.085111596391013 Step 6556 | loss:1.3519070148468018 lr:1.1774244224355634e-06 tokens_per_second_per_gpu:4874.506213390181 mfu:22.993877485081253 Step 6557 | loss:1.188035249710083 lr:1.17411295605033e-06 tokens_per_second_per_gpu:4388.004759483179 mfu:20.69896712129461 Step 6558 | loss:1.1993389129638672 lr:1.1708060409359318e-06 tokens_per_second_per_gpu:5241.464145772239 mfu:24.724880661606772 Step 6559 | loss:1.2017886638641357 lr:1.1675036777240634e-06 tokens_per_second_per_gpu:5238.396146487292 mfu:24.71040838552502 Step 6560 | loss:1.3284237384796143 lr:1.1642058670455452e-06 tokens_per_second_per_gpu:3419.8224540017486 mfu:16.131885997403646 Step 6561 | loss:1.2843416929244995 lr:1.1609126095303401e-06 tokens_per_second_per_gpu:4926.148099306586 mfu:23.237481071963234 Step 6562 | loss:1.1051357984542847 lr:1.1576239058075256e-06 tokens_per_second_per_gpu:3884.7135784290017 mfu:18.324856749931904 Step 6563 | loss:1.2572674751281738 lr:1.1543397565053182e-06 tokens_per_second_per_gpu:3667.5525996963415 mfu:17.300471361766345 Step 6564 | loss:1.1672123670578003 lr:1.1510601622510635e-06 tokens_per_second_per_gpu:5315.234287996722 mfu:25.072867008963797 Step 6565 | loss:1.2599225044250488 lr:1.1477851236712412e-06 tokens_per_second_per_gpu:4099.029682831598 mfu:19.335822380496936 Step 6566 | loss:1.2477388381958008 lr:1.1445146413914477e-06 tokens_per_second_per_gpu:5308.606249081791 mfu:25.04160141854202 Step 6567 | loss:1.294202446937561 lr:1.1412487160364248e-06 tokens_per_second_per_gpu:3991.1778060217366 mfu:18.82706667615714 Step 6568 | loss:1.225562334060669 lr:1.1379873482300296e-06 tokens_per_second_per_gpu:4076.7370419781905 mfu:19.230664190074677 Step 6569 | loss:1.2864208221435547 lr:1.1347305385952634e-06 tokens_per_second_per_gpu:4855.87374121088 mfu:22.905984934783927 Step 6570 | loss:1.1143513917922974 lr:1.1314782877542396e-06 tokens_per_second_per_gpu:5338.71007910564 mfu:25.183606321007552 Step 6571 | loss:1.2651596069335938 lr:1.1282305963282169e-06 tokens_per_second_per_gpu:5329.933877069388 mfu:25.142207478628073 Step 6572 | loss:1.241480827331543 lr:1.124987464937574e-06 tokens_per_second_per_gpu:5209.827697588843 mfu:24.575646137791033 Step 6573 | loss:1.1648024320602417 lr:1.1217488942018212e-06 tokens_per_second_per_gpu:5309.496951494866 mfu:25.045803013793996 Step 6574 | loss:1.1358953714370728 lr:1.1185148847395965e-06 tokens_per_second_per_gpu:4207.977133562028 mfu:19.849746093944237 Step 6575 | loss:1.2008557319641113 lr:1.1152854371686673e-06 tokens_per_second_per_gpu:3796.599632567318 mfu:17.909208233512942 Step 6576 | loss:1.2743995189666748 lr:1.1120605521059284e-06 tokens_per_second_per_gpu:5337.368485778191 mfu:25.177277796382548 Step 6577 | loss:1.4843991994857788 lr:1.1088402301674045e-06 tokens_per_second_per_gpu:4657.254572397725 mfu:21.96906442756766 Step 6578 | loss:1.2963666915893555 lr:1.1056244719682501e-06 tokens_per_second_per_gpu:4983.601716524935 mfu:23.508499586980097 Step 6579 | loss:1.3044328689575195 lr:1.1024132781227437e-06 tokens_per_second_per_gpu:4759.610343477621 mfu:22.45189406344688 Step 6580 | loss:1.277062177658081 lr:1.099206649244297e-06 tokens_per_second_per_gpu:4915.033946265312 mfu:23.1850537157975 Step 6581 | loss:1.1424312591552734 lr:1.0960045859454427e-06 tokens_per_second_per_gpu:3929.6543120019114 mfu:18.53684985787513 Step 6582 | loss:1.1831783056259155 lr:1.0928070888378494e-06 tokens_per_second_per_gpu:3905.4515645088336 mfu:18.42268136853575 Step 6583 | loss:1.1797280311584473 lr:1.0896141585323067e-06 tokens_per_second_per_gpu:4451.180055233362 mfu:20.996975770165154 Step 6584 | loss:1.339802861213684 lr:1.0864257956387403e-06 tokens_per_second_per_gpu:5304.384995476233 mfu:25.02168904506447 Step 6585 | loss:1.3588039875030518 lr:1.0832420007661908e-06 tokens_per_second_per_gpu:5238.783362223556 mfu:24.712234948218796 Step 6586 | loss:1.3694430589675903 lr:1.0800627745228386e-06 tokens_per_second_per_gpu:4400.846244953048 mfu:20.75954259923933 Step 6587 | loss:1.2827885150909424 lr:1.0768881175159839e-06 tokens_per_second_per_gpu:5324.434497288894 mfu:25.116265965912543 Step 6588 | loss:1.3527648448944092 lr:1.0737180303520554e-06 tokens_per_second_per_gpu:4389.025105285035 mfu:20.703780266530913 Step 6589 | loss:1.3371050357818604 lr:1.0705525136366134e-06 tokens_per_second_per_gpu:4662.26332084996 mfu:21.992691548597463 Step 6590 | loss:1.1049087047576904 lr:1.067391567974338e-06 tokens_per_second_per_gpu:3893.975974449638 mfu:18.368549052288962 Step 6591 | loss:1.4102863073349 lr:1.0642351939690404e-06 tokens_per_second_per_gpu:4316.188528530732 mfu:20.360197706779417 Step 6592 | loss:1.298505425453186 lr:1.061083392223658e-06 tokens_per_second_per_gpu:5051.878531860578 mfu:23.83057297414425 Step 6593 | loss:1.3695420026779175 lr:1.0579361633402562e-06 tokens_per_second_per_gpu:5311.5764819498845 mfu:25.0556125137548 Step 6594 | loss:1.236497163772583 lr:1.0547935079200238e-06 tokens_per_second_per_gpu:5088.827428076371 mfu:24.004867221725902 Step 6595 | loss:1.2484476566314697 lr:1.0516554265632777e-06 tokens_per_second_per_gpu:5355.806040490607 mfu:25.26425088773223 Step 6596 | loss:1.3473674058914185 lr:1.0485219198694607e-06 tokens_per_second_per_gpu:5330.783206911616 mfu:25.146213912404477 Step 6597 | loss:1.3592936992645264 lr:1.0453929884371412e-06 tokens_per_second_per_gpu:5117.935054865606 mfu:24.14217286356396 Step 6598 | loss:1.3333522081375122 lr:1.0422686328640158e-06 tokens_per_second_per_gpu:4903.571721990003 mfu:23.130984448233747 Step 6599 | loss:1.3758655786514282 lr:1.0391488537469018e-06 tokens_per_second_per_gpu:5033.083588801291 mfu:23.74191402098564 Step 6600 | loss:1.1940882205963135 lr:1.0360336516817505e-06 tokens_per_second_per_gpu:4865.994864363554 mfu:22.953727999536767 Step 6601 | loss:1.229939579963684 lr:1.0329230272636325e-06 tokens_per_second_per_gpu:5288.919932863175 mfu:24.948737706106908 Step 6602 | loss:1.224225640296936 lr:1.0298169810867452e-06 tokens_per_second_per_gpu:4230.792717023029 mfu:19.957371093869725 Step 6603 | loss:1.2428959608078003 lr:1.026715513744414e-06 tokens_per_second_per_gpu:3722.842674518825 mfu:17.56128407816351 Step 6604 | loss:1.2877020835876465 lr:1.0236186258290843e-06 tokens_per_second_per_gpu:4139.372466282599 mfu:19.526126173223936 Step 6605 | loss:1.251381278038025 lr:1.0205263179323326e-06 tokens_per_second_per_gpu:4363.701812271276 mfu:20.584325972785695 Step 6606 | loss:1.2572435140609741 lr:1.0174385906448564e-06 tokens_per_second_per_gpu:4141.18291929972 mfu:19.534666389000833 Step 6607 | loss:1.209267497062683 lr:1.0143554445564834e-06 tokens_per_second_per_gpu:4721.077848666842 mfu:22.270129711102896 Step 6608 | loss:1.2125076055526733 lr:1.0112768802561567e-06 tokens_per_second_per_gpu:5291.0904252564405 mfu:24.95897628905013 Step 6609 | loss:1.0492011308670044 lr:1.0082028983319559e-06 tokens_per_second_per_gpu:4044.1654651685685 mfu:19.077018504979637 Step 6610 | loss:1.2663519382476807 lr:1.0051334993710775e-06 tokens_per_second_per_gpu:3576.5576651753267 mfu:16.871232730293965 Step 6611 | loss:1.3027018308639526 lr:1.002068683959842e-06 tokens_per_second_per_gpu:5290.927582421659 mfu:24.958208131614615 Step 6612 | loss:1.128218412399292 lr:9.990084526837e-07 tokens_per_second_per_gpu:3820.5481412533763 mfu:18.022177435021998 Step 6613 | loss:1.0849684476852417 lr:9.959528061272233e-07 tokens_per_second_per_gpu:5329.316344975727 mfu:25.13929447438044 Step 6614 | loss:1.4198821783065796 lr:9.929017448741056e-07 tokens_per_second_per_gpu:4585.54384630652 mfu:21.630792697483937 Step 6615 | loss:1.4635390043258667 lr:9.8985526950717e-07 tokens_per_second_per_gpu:3179.138330643551 mfu:14.996537922577101 Step 6616 | loss:1.2723736763000488 lr:9.868133806083563e-07 tokens_per_second_per_gpu:4759.89627561016 mfu:22.453242854101116 Step 6617 | loss:1.3469024896621704 lr:9.837760787587357e-07 tokens_per_second_per_gpu:5328.155644136209 mfu:25.13381925048445 Step 6618 | loss:1.1569933891296387 lr:9.807433645385e-07 tokens_per_second_per_gpu:5327.39813889181 mfu:25.130245969002896 Step 6619 | loss:1.3239747285842896 lr:9.777152385269633e-07 tokens_per_second_per_gpu:3858.895552274608 mfu:18.203068715552135 Step 6620 | loss:1.4339736700057983 lr:9.74691701302566e-07 tokens_per_second_per_gpu:3929.1732716682195 mfu:18.534580708547164 Step 6621 | loss:1.2366067171096802 lr:9.716727534428704e-07 tokens_per_second_per_gpu:5320.623182619311 mfu:25.098287344338782 Step 6622 | loss:1.2316395044326782 lr:9.686583955245604e-07 tokens_per_second_per_gpu:3898.5474910311323 mfu:18.390113675985027 Step 6623 | loss:1.1660441160202026 lr:9.656486281234444e-07 tokens_per_second_per_gpu:5296.740422467932 mfu:24.98562828988566 Step 6624 | loss:1.1737655401229858 lr:9.626434518144572e-07 tokens_per_second_per_gpu:5304.278121003637 mfu:25.021184899942572 Step 6625 | loss:1.212602138519287 lr:9.596428671716534e-07 tokens_per_second_per_gpu:5324.36229714429 mfu:25.11592538551183 Step 6626 | loss:1.2996559143066406 lr:9.566468747682107e-07 tokens_per_second_per_gpu:4195.062841325637 mfu:19.788827174059723 Step 6627 | loss:1.1451616287231445 lr:9.536554751764293e-07 tokens_per_second_per_gpu:4973.062431512465 mfu:23.45878398138883 Step 6628 | loss:1.3200873136520386 lr:9.50668668967733e-07 tokens_per_second_per_gpu:5243.380962504647 mfu:24.733922613176198 Step 6629 | loss:1.2038462162017822 lr:9.47686456712668e-07 tokens_per_second_per_gpu:4514.568746256209 mfu:21.295991040945843 Step 6630 | loss:1.3021447658538818 lr:9.447088389808984e-07 tokens_per_second_per_gpu:5299.326427314047 mfu:24.99782691596271 Step 6631 | loss:1.1432639360427856 lr:9.417358163412271e-07 tokens_per_second_per_gpu:5317.5952789029025 mfu:25.08400420589484 Step 6632 | loss:1.2362990379333496 lr:9.387673893615528e-07 tokens_per_second_per_gpu:3673.286809172797 mfu:17.327520606223807 Step 6633 | loss:1.2548447847366333 lr:9.358035586089164e-07 tokens_per_second_per_gpu:5142.358431413798 mfu:24.257382097799514 Step 6634 | loss:1.3371556997299194 lr:9.328443246494789e-07 tokens_per_second_per_gpu:5126.109173734413 mfu:24.180731576916614 Step 6635 | loss:1.3482410907745361 lr:9.298896880485159e-07 tokens_per_second_per_gpu:5335.010218959415 mfu:25.166153449436575 Step 6636 | loss:1.2187626361846924 lr:9.26939649370423e-07 tokens_per_second_per_gpu:4524.107796193273 mfu:21.34098836702872 Step 6637 | loss:1.1473067998886108 lr:9.239942091787329e-07 tokens_per_second_per_gpu:4459.57035639529 mfu:21.036554252278965 Step 6638 | loss:1.2003854513168335 lr:9.210533680360844e-07 tokens_per_second_per_gpu:5344.1075937561145 mfu:25.209067318524795 Step 6639 | loss:1.1466022729873657 lr:9.181171265042393e-07 tokens_per_second_per_gpu:5338.601577214769 mfu:25.18309449907598 Step 6640 | loss:1.2912664413452148 lr:9.151854851440961e-07 tokens_per_second_per_gpu:5305.054264750203 mfu:25.0248461024189 Step 6641 | loss:1.3019006252288818 lr:9.12258444515654e-07 tokens_per_second_per_gpu:5305.661546181179 mfu:25.027710752541708 Step 6642 | loss:1.2516262531280518 lr:9.09336005178038e-07 tokens_per_second_per_gpu:4576.741141683908 mfu:21.58926883788279 Step 6643 | loss:1.2010371685028076 lr:9.064181676895128e-07 tokens_per_second_per_gpu:4639.197858162127 mfu:21.883887825725218 Step 6644 | loss:1.1955459117889404 lr:9.035049326074407e-07 tokens_per_second_per_gpu:3713.821051046049 mfu:17.51872754099474 Step 6645 | loss:1.3357820510864258 lr:9.0059630048831e-07 tokens_per_second_per_gpu:4036.826316503793 mfu:19.04239848854001 Step 6646 | loss:1.3246848583221436 lr:8.976922718877456e-07 tokens_per_second_per_gpu:4281.031770525557 mfu:20.19435728090756 Step 6647 | loss:1.413044810295105 lr:8.947928473604705e-07 tokens_per_second_per_gpu:4376.76437813972 mfu:20.645944324690703 Step 6648 | loss:1.4576754570007324 lr:8.918980274603389e-07 tokens_per_second_per_gpu:5276.100317049608 mfu:24.888265391062312 Step 6649 | loss:1.2418780326843262 lr:8.890078127403389e-07 tokens_per_second_per_gpu:3765.285173231423 mfu:17.761492586027828 Step 6650 | loss:1.2863271236419678 lr:8.861222037525485e-07 tokens_per_second_per_gpu:4053.450477922032 mfu:19.120817494324253 Step 6651 | loss:1.2964752912521362 lr:8.832412010481905e-07 tokens_per_second_per_gpu:4205.7152494137545 mfu:19.839076400499604 Step 6652 | loss:1.2187445163726807 lr:8.803648051776026e-07 tokens_per_second_per_gpu:2858.5067215367435 mfu:13.484063917026734 Step 6653 | loss:1.4383734464645386 lr:8.774930166902367e-07 tokens_per_second_per_gpu:4547.353409833039 mfu:21.450641892678156 Step 6654 | loss:1.2773630619049072 lr:8.746258361346626e-07 tokens_per_second_per_gpu:3649.6157176905344 mfu:17.21586002899731 Step 6655 | loss:1.1315417289733887 lr:8.717632640585894e-07 tokens_per_second_per_gpu:5312.673957328187 mfu:25.060789492362858 Step 6656 | loss:1.2616099119186401 lr:8.689053010088183e-07 tokens_per_second_per_gpu:4845.829977231808 mfu:22.8586067864518 Step 6657 | loss:1.4155547618865967 lr:8.66051947531285e-07 tokens_per_second_per_gpu:4164.536756722095 mfu:19.644830424697716 Step 6658 | loss:1.2744275331497192 lr:8.632032041710508e-07 tokens_per_second_per_gpu:4473.120874644554 mfu:21.100474358817554 Step 6659 | loss:1.3872053623199463 lr:8.603590714722803e-07 tokens_per_second_per_gpu:3308.221919242293 mfu:15.605447233928617 Step 6660 | loss:1.3329066038131714 lr:8.575195499782695e-07 tokens_per_second_per_gpu:4995.750527884591 mfu:23.565807602964554 Step 6661 | loss:1.2118879556655884 lr:8.546846402314318e-07 tokens_per_second_per_gpu:5295.417101926867 mfu:24.979385961111692 Step 6662 | loss:1.30825674533844 lr:8.51854342773295e-07 tokens_per_second_per_gpu:4899.489929465075 mfu:23.111729936468045 Step 6663 | loss:1.3813101053237915 lr:8.490286581445045e-07 tokens_per_second_per_gpu:4302.559990095216 mfu:20.29590956571066 Step 6664 | loss:1.1550506353378296 lr:8.462075868848396e-07 tokens_per_second_per_gpu:5313.133221160239 mfu:25.062955918217142 Step 6665 | loss:1.3286603689193726 lr:8.433911295331748e-07 tokens_per_second_per_gpu:5260.790570883271 mfu:24.816046706283654 Step 6666 | loss:1.253526210784912 lr:8.405792866275214e-07 tokens_per_second_per_gpu:4751.9270722053225 mfu:22.415650761954193 Step 6667 | loss:1.2710033655166626 lr:8.377720587050053e-07 tokens_per_second_per_gpu:4764.540901773702 mfu:22.475152348169484 Step 6668 | loss:1.1408241987228394 lr:8.34969446301867e-07 tokens_per_second_per_gpu:4615.8485359007855 mfu:21.773745088813293 Step 6669 | loss:1.2089097499847412 lr:8.321714499534644e-07 tokens_per_second_per_gpu:3286.886836722624 mfu:15.504806009542902 Step 6670 | loss:1.2359315156936646 lr:8.293780701942839e-07 tokens_per_second_per_gpu:4709.34996489214 mfu:22.214807282354318 Step 6671 | loss:1.1521610021591187 lr:8.265893075579179e-07 tokens_per_second_per_gpu:4236.5360593846735 mfu:19.984463419704852 Step 6672 | loss:1.2909449338912964 lr:8.238051625770765e-07 tokens_per_second_per_gpu:3527.302014346214 mfu:16.63888542145243 Step 6673 | loss:1.1215388774871826 lr:8.210256357836066e-07 tokens_per_second_per_gpu:4219.264129301184 mfu:19.902988778605888 Step 6674 | loss:1.1131553649902344 lr:8.182507277084472e-07 tokens_per_second_per_gpu:5295.523100421916 mfu:24.979885974098046 Step 6675 | loss:1.4033658504486084 lr:8.154804388816689e-07 tokens_per_second_per_gpu:4195.373845291321 mfu:19.7902942328286 Step 6676 | loss:1.1716678142547607 lr:8.127147698324678e-07 tokens_per_second_per_gpu:3459.2744875480953 mfu:16.317987970852787 Step 6677 | loss:1.1920342445373535 lr:8.09953721089135e-07 tokens_per_second_per_gpu:4601.606671195966 mfu:21.706563783087976 Step 6678 | loss:1.161209225654602 lr:8.071972931790961e-07 tokens_per_second_per_gpu:4578.151521082484 mfu:21.59592183814141 Step 6679 | loss:1.2807387113571167 lr:8.044454866288936e-07 tokens_per_second_per_gpu:3915.8672461962506 mfu:18.47181391615384 Step 6680 | loss:1.3207319974899292 lr:8.016983019641794e-07 tokens_per_second_per_gpu:4938.093275669238 mfu:23.29382850692311 Step 6681 | loss:1.36487877368927 lr:7.989557397097253e-07 tokens_per_second_per_gpu:4781.586304625951 mfu:22.555558421669158 Step 6682 | loss:1.2509938478469849 lr:7.962178003894289e-07 tokens_per_second_per_gpu:5348.9432012686375 mfu:25.231877704201082 Step 6683 | loss:1.3692095279693604 lr:7.934844845262884e-07 tokens_per_second_per_gpu:4024.5223946921965 mfu:18.98435879008918 Step 6684 | loss:1.1601942777633667 lr:7.907557926424308e-07 tokens_per_second_per_gpu:5318.996069899707 mfu:25.090611976026352 Step 6685 | loss:1.2251211404800415 lr:7.880317252591002e-07 tokens_per_second_per_gpu:4074.548999507159 mfu:19.220342820420278 Step 6686 | loss:1.166975736618042 lr:7.85312282896647e-07 tokens_per_second_per_gpu:4803.363745421316 mfu:22.658286325515434 Step 6687 | loss:1.3176782131195068 lr:7.825974660745445e-07 tokens_per_second_per_gpu:5303.90375525632 mfu:25.019418952839093 Step 6688 | loss:1.0392717123031616 lr:7.798872753113917e-07 tokens_per_second_per_gpu:3514.5941153456815 mfu:16.578940093675772 Step 6689 | loss:1.2877992391586304 lr:7.771817111248858e-07 tokens_per_second_per_gpu:4441.871402259073 mfu:20.953065265865465 Step 6690 | loss:1.0545393228530884 lr:7.744807740318521e-07 tokens_per_second_per_gpu:5335.026354265045 mfu:25.166229562426192 Step 6691 | loss:1.3290170431137085 lr:7.717844645482364e-07 tokens_per_second_per_gpu:5319.007224384734 mfu:25.090664593635378 Step 6692 | loss:1.2034510374069214 lr:7.69092783189082e-07 tokens_per_second_per_gpu:5342.294012913238 mfu:25.20051234826015 Step 6693 | loss:1.3481017351150513 lr:7.664057304685613e-07 tokens_per_second_per_gpu:3909.968706759348 mfu:18.443989499235364 Step 6694 | loss:1.2863638401031494 lr:7.637233068999716e-07 tokens_per_second_per_gpu:3844.9123442588084 mfu:18.137107537560304 Step 6695 | loss:1.2940406799316406 lr:7.610455129957034e-07 tokens_per_second_per_gpu:4775.533637207488 mfu:22.527006956764716 Step 6696 | loss:1.320597767829895 lr:7.583723492672751e-07 tokens_per_second_per_gpu:4515.843555691615 mfu:21.30200453455757 Step 6697 | loss:1.3533283472061157 lr:7.557038162253282e-07 tokens_per_second_per_gpu:4431.858752244488 mfu:20.905833887412417 Step 6698 | loss:1.1458266973495483 lr:7.530399143796025e-07 tokens_per_second_per_gpu:5312.777152882899 mfu:25.061276283401416 Step 6699 | loss:1.265459418296814 lr:7.50380644238971e-07 tokens_per_second_per_gpu:5197.410765499834 mfu:24.51707335058011 Step 6700 | loss:1.2509238719940186 lr:7.477260063114083e-07 tokens_per_second_per_gpu:4752.550126973307 mfu:22.418589817598875 Step 6701 | loss:1.370824933052063 lr:7.450760011040031e-07 tokens_per_second_per_gpu:4704.557716262674 mfu:22.1922014279272 Step 6702 | loss:1.3390135765075684 lr:7.424306291229754e-07 tokens_per_second_per_gpu:5320.097836537111 mfu:25.095809197235763 Step 6703 | loss:1.4892334938049316 lr:7.397898908736461e-07 tokens_per_second_per_gpu:4519.242931943382 mfu:21.318039972330556 Step 6704 | loss:1.2192318439483643 lr:7.371537868604506e-07 tokens_per_second_per_gpu:5014.591236497594 mfu:23.654682440048454 Step 6705 | loss:1.4275057315826416 lr:7.34522317586947e-07 tokens_per_second_per_gpu:4193.136862721797 mfu:19.77974200437957 Step 6706 | loss:1.302942156791687 lr:7.318954835558056e-07 tokens_per_second_per_gpu:3568.6765420027127 mfu:16.834056127630475 Step 6707 | loss:1.153287649154663 lr:7.292732852688e-07 tokens_per_second_per_gpu:4162.909187856871 mfu:19.63715290466857 Step 6708 | loss:1.2065742015838623 lr:7.266557232268406e-07 tokens_per_second_per_gpu:3806.899571215247 mfu:17.957794801465965 Step 6709 | loss:1.2143256664276123 lr:7.240427979299358e-07 tokens_per_second_per_gpu:5349.793153924099 mfu:25.235887075893775 Step 6710 | loss:1.2677379846572876 lr:7.214345098772058e-07 tokens_per_second_per_gpu:3627.299349556745 mfu:17.110589912945194 Step 6711 | loss:1.1966588497161865 lr:7.188308595668963e-07 tokens_per_second_per_gpu:4635.029976038632 mfu:21.864227214634674 Step 6712 | loss:1.3846096992492676 lr:7.162318474963681e-07 tokens_per_second_per_gpu:5318.845836281837 mfu:25.089903298418367 Step 6713 | loss:1.2138495445251465 lr:7.136374741620739e-07 tokens_per_second_per_gpu:5048.475622749299 mfu:23.814520871270183 Step 6714 | loss:1.2678484916687012 lr:7.110477400596116e-07 tokens_per_second_per_gpu:4656.269635284124 mfu:21.964418311155207 Step 6715 | loss:1.326354742050171 lr:7.084626456836718e-07 tokens_per_second_per_gpu:3551.5556302407795 mfu:16.75329386572067 Step 6716 | loss:1.2539246082305908 lr:7.058821915280622e-07 tokens_per_second_per_gpu:5145.135624778028 mfu:24.270482592736634 Step 6717 | loss:1.3241363763809204 lr:7.033063780857108e-07 tokens_per_second_per_gpu:5293.470591777396 mfu:24.970203940627762 Step 6718 | loss:1.2389719486236572 lr:7.007352058486544e-07 tokens_per_second_per_gpu:5310.723263271092 mfu:25.05158773567282 Step 6719 | loss:1.1071217060089111 lr:6.981686753080391e-07 tokens_per_second_per_gpu:3741.512931852804 mfu:17.649354867482266 Step 6720 | loss:1.13991117477417 lr:6.956067869541338e-07 tokens_per_second_per_gpu:5296.944101337856 mfu:24.9865890778663 Step 6721 | loss:1.2013206481933594 lr:6.930495412763167e-07 tokens_per_second_per_gpu:5326.246349178914 mfu:25.124812780411574 Step 6722 | loss:1.2852970361709595 lr:6.904969387630689e-07 tokens_per_second_per_gpu:4601.443533339377 mfu:21.70579423398426 Step 6723 | loss:1.0819000005722046 lr:6.879489799020061e-07 tokens_per_second_per_gpu:5202.102143632746 mfu:24.539203381664702 Step 6724 | loss:1.4426634311676025 lr:6.854056651798419e-07 tokens_per_second_per_gpu:3892.546763868549 mfu:18.361807222129496 Step 6725 | loss:1.2575072050094604 lr:6.828669950823957e-07 tokens_per_second_per_gpu:4201.140371921583 mfu:19.817495922814444 Step 6726 | loss:1.3228410482406616 lr:6.803329700946214e-07 tokens_per_second_per_gpu:3955.6108903239146 mfu:18.65929146646895 Step 6727 | loss:1.4260661602020264 lr:6.778035907005709e-07 tokens_per_second_per_gpu:5359.686899693615 mfu:25.282557562735672 Step 6728 | loss:1.3455923795700073 lr:6.752788573834046e-07 tokens_per_second_per_gpu:5299.347537210609 mfu:24.997926494946512 Step 6729 | loss:1.2311716079711914 lr:6.727587706254118e-07 tokens_per_second_per_gpu:3376.1322515823445 mfu:15.925791858274119 Step 6730 | loss:1.2577286958694458 lr:6.702433309079825e-07 tokens_per_second_per_gpu:5355.825789591833 mfu:25.26434404761226 Step 6731 | loss:1.2529855966567993 lr:6.677325387116156e-07 tokens_per_second_per_gpu:5014.7400174318755 mfu:23.655384265100103 Step 6732 | loss:1.3276985883712769 lr:6.652263945159332e-07 tokens_per_second_per_gpu:5355.564308423458 mfu:25.263110596327746 Step 6733 | loss:1.2226144075393677 lr:6.627248987996632e-07 tokens_per_second_per_gpu:4629.134792498469 mfu:21.836418628053696 Step 6734 | loss:1.486603021621704 lr:6.602280520406428e-07 tokens_per_second_per_gpu:3966.498701589858 mfu:18.71065112986256 Step 6735 | loss:1.1777777671813965 lr:6.577358547158324e-07 tokens_per_second_per_gpu:5172.066187203105 mfu:24.397518650523477 Step 6736 | loss:1.2109758853912354 lr:6.552483073012927e-07 tokens_per_second_per_gpu:5307.02199791704 mfu:25.034128235496766 Step 6737 | loss:1.3271090984344482 lr:6.527654102721964e-07 tokens_per_second_per_gpu:3851.0757491724958 mfu:18.166181370123486 Step 6738 | loss:1.2945491075515747 lr:6.502871641028363e-07 tokens_per_second_per_gpu:3825.6889033625134 mfu:18.046427286995257 Step 6739 | loss:1.239766001701355 lr:6.478135692666143e-07 tokens_per_second_per_gpu:5068.351436310865 mfu:23.90827847500357 Step 6740 | loss:1.3631625175476074 lr:6.45344626236033e-07 tokens_per_second_per_gpu:4985.166406113887 mfu:23.51588049473476 Step 6741 | loss:1.5682270526885986 lr:6.428803354827234e-07 tokens_per_second_per_gpu:3123.703291517277 mfu:14.735041384825493 Step 6742 | loss:1.3031975030899048 lr:6.404206974774202e-07 tokens_per_second_per_gpu:5057.779499703848 mfu:23.85840884626989 Step 6743 | loss:1.2763994932174683 lr:6.379657126899613e-07 tokens_per_second_per_gpu:5357.341863378737 mfu:25.27149562633394 Step 6744 | loss:1.469799518585205 lr:6.355153815893078e-07 tokens_per_second_per_gpu:5145.228495328236 mfu:24.270920678967318 Step 6745 | loss:1.2855513095855713 lr:6.330697046435269e-07 tokens_per_second_per_gpu:5215.85317530958 mfu:24.604069344252263 Step 6746 | loss:1.1203118562698364 lr:6.306286823197949e-07 tokens_per_second_per_gpu:4693.142695223482 mfu:22.138354826081912 Step 6747 | loss:1.1803808212280273 lr:6.281923150844026e-07 tokens_per_second_per_gpu:3854.2318701059303 mfu:18.181069331056253 Step 6748 | loss:1.3193299770355225 lr:6.257606034027502e-07 tokens_per_second_per_gpu:5288.152621055853 mfu:24.945118165394877 Step 6749 | loss:1.2001346349716187 lr:6.233335477393465e-07 tokens_per_second_per_gpu:4155.914109853241 mfu:19.604155928242076 Step 6750 | loss:1.1779459714889526 lr:6.209111485578151e-07 tokens_per_second_per_gpu:5155.579435986011 mfu:24.319747832102628 Step 6751 | loss:1.344691276550293 lr:6.184934063208886e-07 tokens_per_second_per_gpu:3452.4413110938917 mfu:16.285754711658186 Step 6752 | loss:1.3522262573242188 lr:6.160803214904032e-07 tokens_per_second_per_gpu:4125.12323842389 mfu:19.45891013424544 Step 6753 | loss:1.1072664260864258 lr:6.136718945273179e-07 tokens_per_second_per_gpu:5314.202604966052 mfu:25.06800038408485 Step 6754 | loss:1.209947109222412 lr:6.112681258916925e-07 tokens_per_second_per_gpu:5060.993735493697 mfu:23.873570944895786 Step 6755 | loss:1.2388217449188232 lr:6.088690160426986e-07 tokens_per_second_per_gpu:5328.698355527162 mfu:25.136379312711686 Step 6756 | loss:1.2693885564804077 lr:6.06474565438625e-07 tokens_per_second_per_gpu:5296.419899330807 mfu:24.984116327560958 Step 6757 | loss:1.3830808401107788 lr:6.040847745368589e-07 tokens_per_second_per_gpu:4116.56768116233 mfu:19.418552110914067 Step 6758 | loss:1.271366834640503 lr:6.016996437939043e-07 tokens_per_second_per_gpu:5340.3572208814585 mfu:25.19137616979545 Step 6759 | loss:1.3702614307403564 lr:5.993191736653775e-07 tokens_per_second_per_gpu:3874.820508286495 mfu:18.278189450137877 Step 6760 | loss:1.2037919759750366 lr:5.969433646059952e-07 tokens_per_second_per_gpu:5305.263735217536 mfu:25.025834210352656 Step 6761 | loss:1.3693228960037231 lr:5.945722170695888e-07 tokens_per_second_per_gpu:4517.36535540504 mfu:21.309183123451604 Step 6762 | loss:1.3419601917266846 lr:5.922057315091101e-07 tokens_per_second_per_gpu:5308.283295733552 mfu:25.040077992496855 Step 6763 | loss:1.2020885944366455 lr:5.898439083765999e-07 tokens_per_second_per_gpu:4550.337681983957 mfu:21.46471921358337 Step 6764 | loss:1.2494345903396606 lr:5.874867481232199e-07 tokens_per_second_per_gpu:4269.186013304028 mfu:20.138478822999016 Step 6765 | loss:1.1658085584640503 lr:5.851342511992486e-07 tokens_per_second_per_gpu:4334.760427838276 mfu:20.44780452450587 Step 6766 | loss:1.324410319328308 lr:5.827864180540515e-07 tokens_per_second_per_gpu:4347.9760474138875 mfu:20.51014485686124 Step 6767 | loss:1.3634400367736816 lr:5.804432491361256e-07 tokens_per_second_per_gpu:5325.239974721593 mfu:25.120065540391206 Step 6768 | loss:1.1999317407608032 lr:5.781047448930682e-07 tokens_per_second_per_gpu:5310.346320140555 mfu:25.04980963061294 Step 6769 | loss:1.218518614768982 lr:5.757709057715776e-07 tokens_per_second_per_gpu:5325.17908967743 mfu:25.11977833524983 Step 6770 | loss:1.3005781173706055 lr:5.734417322174751e-07 tokens_per_second_per_gpu:4620.8379236241035 mfu:21.797280881981514 Step 6771 | loss:1.392833948135376 lr:5.71117224675688e-07 tokens_per_second_per_gpu:4711.306958886464 mfu:22.22403875692315 Step 6772 | loss:1.4019756317138672 lr:5.687973835902361e-07 tokens_per_second_per_gpu:3226.3426881192513 mfu:15.219208930683854 Step 6773 | loss:1.302363395690918 lr:5.664822094042704e-07 tokens_per_second_per_gpu:4748.622727709414 mfu:22.400063605187686 Step 6774 | loss:1.2759007215499878 lr:5.641717025600429e-07 tokens_per_second_per_gpu:3945.3269278116145 mfu:18.610780260673494 Step 6775 | loss:1.2125767469406128 lr:5.618658634988977e-07 tokens_per_second_per_gpu:4278.567908676618 mfu:20.182734824187936 Step 6776 | loss:1.2566124200820923 lr:5.595646926613157e-07 tokens_per_second_per_gpu:5363.7237705372945 mfu:25.3016001712665 Step 6777 | loss:1.2775160074234009 lr:5.572681904868649e-07 tokens_per_second_per_gpu:4570.609842715424 mfu:21.56034645454098 Step 6778 | loss:1.2044909000396729 lr:5.549763574142247e-07 tokens_per_second_per_gpu:4111.716836348512 mfu:19.395669848287817 Step 6779 | loss:1.2571442127227783 lr:5.526891938811895e-07 tokens_per_second_per_gpu:4037.5884310084944 mfu:19.045993512688824 Step 6780 | loss:1.2255401611328125 lr:5.504067003246627e-07 tokens_per_second_per_gpu:4562.292012234324 mfu:21.521109828993406 Step 6781 | loss:1.4570749998092651 lr:5.481288771806398e-07 tokens_per_second_per_gpu:4411.595541807667 mfu:20.810248866521732 Step 6782 | loss:1.3268767595291138 lr:5.45855724884245e-07 tokens_per_second_per_gpu:3888.500829844794 mfu:18.34272186103192 Step 6783 | loss:1.2278677225112915 lr:5.435872438697004e-07 tokens_per_second_per_gpu:4011.5431039243954 mfu:18.923133261042103 Step 6784 | loss:1.0605195760726929 lr:5.413234345703289e-07 tokens_per_second_per_gpu:4783.574288471442 mfu:22.564936080653354 Step 6785 | loss:1.234352946281433 lr:5.390642974185733e-07 tokens_per_second_per_gpu:3912.43888741409 mfu:18.45564176284006 Step 6786 | loss:1.1126374006271362 lr:5.368098328459775e-07 tokens_per_second_per_gpu:3836.280063992165 mfu:18.096387598723663 Step 6787 | loss:1.1789195537567139 lr:5.345600412831942e-07 tokens_per_second_per_gpu:4700.056309890127 mfu:22.170967526048774 Step 6788 | loss:1.1668524742126465 lr:5.323149231599822e-07 tokens_per_second_per_gpu:5117.183130323538 mfu:24.13862590720747 Step 6789 | loss:1.220726490020752 lr:5.300744789052125e-07 tokens_per_second_per_gpu:5346.505387261409 mfu:25.22037811959503 Step 6790 | loss:1.2375692129135132 lr:5.278387089468539e-07 tokens_per_second_per_gpu:5305.977395156296 mfu:25.029200666046727 Step 6791 | loss:1.3143057823181152 lr:5.256076137119925e-07 tokens_per_second_per_gpu:5311.302498245067 mfu:25.054320085872735 Step 6792 | loss:1.2332159280776978 lr:5.233811936268152e-07 tokens_per_second_per_gpu:5193.872354515583 mfu:24.500382062252225 Step 6793 | loss:1.255955696105957 lr:5.21159449116615e-07 tokens_per_second_per_gpu:4995.195536176276 mfu:23.56318961238508 Step 6794 | loss:1.3687149286270142 lr:5.189423806057969e-07 tokens_per_second_per_gpu:5015.668069808449 mfu:23.659762046502465 Step 6795 | loss:1.3516172170639038 lr:5.167299885178722e-07 tokens_per_second_per_gpu:4281.880445529286 mfu:20.198360625699035 Step 6796 | loss:1.212996006011963 lr:5.145222732754473e-07 tokens_per_second_per_gpu:5285.569975475515 mfu:24.932935385547648 Step 6797 | loss:1.3370927572250366 lr:5.12319235300257e-07 tokens_per_second_per_gpu:4088.472013326517 mfu:19.2860200521173 Step 6798 | loss:1.2572113275527954 lr:5.101208750131258e-07 tokens_per_second_per_gpu:2989.4903837580864 mfu:14.101936199842049 Step 6799 | loss:1.2916451692581177 lr:5.079271928339819e-07 tokens_per_second_per_gpu:5256.704350457065 mfu:24.79677130735214 Step 6800 | loss:1.2710450887680054 lr:5.057381891818758e-07 tokens_per_second_per_gpu:5301.373196396656 mfu:25.00748187494019 Step 6801 | loss:1.4286580085754395 lr:5.035538644749538e-07 tokens_per_second_per_gpu:3944.162399253634 mfu:18.605286980776437 Step 6802 | loss:1.2228258848190308 lr:5.013742191304655e-07 tokens_per_second_per_gpu:4877.444997963738 mfu:23.007740233323073 Step 6803 | loss:1.1681514978408813 lr:4.991992535647777e-07 tokens_per_second_per_gpu:5308.7013856982385 mfu:25.042050194193784 Step 6804 | loss:1.0799269676208496 lr:4.970289681933526e-07 tokens_per_second_per_gpu:4805.3515290790565 mfu:22.667663040179864 Step 6805 | loss:1.352194905281067 lr:4.948633634307642e-07 tokens_per_second_per_gpu:4779.300172263047 mfu:22.544774345258936 Step 6806 | loss:1.252801537513733 lr:4.927024396906898e-07 tokens_per_second_per_gpu:5320.906902990445 mfu:25.099625701737107 Step 6807 | loss:1.1629414558410645 lr:4.905461973859188e-07 tokens_per_second_per_gpu:4407.132929190457 mfu:20.789197961406124 Step 6808 | loss:1.2299362421035767 lr:4.883946369283299e-07 tokens_per_second_per_gpu:5321.783050657921 mfu:25.1037586397708 Step 6809 | loss:1.1105245351791382 lr:4.862477587289304e-07 tokens_per_second_per_gpu:4776.336447317257 mfu:22.530793949026027 Step 6810 | loss:1.2700117826461792 lr:4.841055631978176e-07 tokens_per_second_per_gpu:4768.117195439504 mfu:22.49202233556969 Step 6811 | loss:1.2346473932266235 lr:4.819680507441915e-07 tokens_per_second_per_gpu:5315.058494816246 mfu:25.072037762538084 Step 6812 | loss:1.5273115634918213 lr:4.798352217763757e-07 tokens_per_second_per_gpu:4414.442480665635 mfu:20.823678362852622 Step 6813 | loss:1.2312158346176147 lr:4.777070767017805e-07 tokens_per_second_per_gpu:5039.722790477984 mfu:23.773232268059214 Step 6814 | loss:1.2681457996368408 lr:4.755836159269278e-07 tokens_per_second_per_gpu:3141.003601988848 mfu:14.816649901057234 Step 6815 | loss:1.3666048049926758 lr:4.7346483985744874e-07 tokens_per_second_per_gpu:4817.950629028594 mfu:22.727095144269946 Step 6816 | loss:1.2714489698410034 lr:4.7135074889807786e-07 tokens_per_second_per_gpu:3806.9054438200633 mfu:17.957822503544854 Step 6817 | loss:1.2257550954818726 lr:4.692413434526449e-07 tokens_per_second_per_gpu:5330.000040252103 mfu:25.142519581649545 Step 6818 | loss:1.3654990196228027 lr:4.6713662392410264e-07 tokens_per_second_per_gpu:3854.0680951549903 mfu:18.18029677666978 Step 6819 | loss:1.2584855556488037 lr:4.65036590714496e-07 tokens_per_second_per_gpu:5328.414965668039 mfu:25.135042514394907 Step 6820 | loss:1.1951655149459839 lr:4.6294124422497365e-07 tokens_per_second_per_gpu:5247.147935366874 mfu:24.751692066879166 Step 6821 | loss:1.3438160419464111 lr:4.608505848557987e-07 tokens_per_second_per_gpu:4508.23876125942 mfu:21.266131421709186 Step 6822 | loss:1.4519325494766235 lr:4.587646130063322e-07 tokens_per_second_per_gpu:4688.96009672715 mfu:22.118624795349824 Step 6823 | loss:1.3763526678085327 lr:4.566833290750361e-07 tokens_per_second_per_gpu:3739.603002763609 mfu:17.640345406101027 Step 6824 | loss:1.1030133962631226 lr:4.5460673345948665e-07 tokens_per_second_per_gpu:5023.623366916271 mfu:23.69728854027371 Step 6825 | loss:1.4210560321807861 lr:4.5253482655635837e-07 tokens_per_second_per_gpu:5315.457328094607 mfu:25.073919127160085 Step 6826 | loss:1.2605767250061035 lr:4.5046760876142903e-07 tokens_per_second_per_gpu:4579.927912072439 mfu:21.604301377524585 Step 6827 | loss:1.2580320835113525 lr:4.484050804695855e-07 tokens_per_second_per_gpu:5039.7881951129475 mfu:23.773540792881516 Step 6828 | loss:1.3723702430725098 lr:4.463472420748155e-07 tokens_per_second_per_gpu:4071.2602148695205 mfu:19.20482906216002 Step 6829 | loss:1.227390170097351 lr:4.4429409397021005e-07 tokens_per_second_per_gpu:4458.8881524517865 mfu:21.033336179881463 Step 6830 | loss:1.1316605806350708 lr:4.4224563654796936e-07 tokens_per_second_per_gpu:4426.276947456384 mfu:20.87950356187283 Step 6831 | loss:1.2542294263839722 lr:4.4020187019938874e-07 tokens_per_second_per_gpu:4304.164508270172 mfu:20.303478351700953 Step 6832 | loss:1.2451286315917969 lr:4.381627953148781e-07 tokens_per_second_per_gpu:5338.289866999201 mfu:25.181624108805895 Step 6833 | loss:1.1359360218048096 lr:4.361284122839454e-07 tokens_per_second_per_gpu:4566.45332494488 mfu:21.54073945104226 Step 6834 | loss:1.3042818307876587 lr:4.3409872149519915e-07 tokens_per_second_per_gpu:4972.452302550311 mfu:23.455905898975615 Step 6835 | loss:1.3261593580245972 lr:4.32073723336357e-07 tokens_per_second_per_gpu:5297.272643714276 mfu:24.988138868310973 Step 6836 | loss:1.1111830472946167 lr:4.300534181942373e-07 tokens_per_second_per_gpu:4718.64082773238 mfu:22.25863386755639 Step 6837 | loss:1.3853318691253662 lr:4.280378064547647e-07 tokens_per_second_per_gpu:3238.82097816072 mfu:15.278071153825282 Step 6838 | loss:1.0995490550994873 lr:4.2602688850296446e-07 tokens_per_second_per_gpu:4801.403807920399 mfu:22.64904096592379 Step 6839 | loss:1.0903873443603516 lr:4.2402066472296833e-07 tokens_per_second_per_gpu:5295.805409092168 mfu:24.98121767226245 Step 6840 | loss:1.3251683712005615 lr:4.2201913549800577e-07 tokens_per_second_per_gpu:4865.0902899309385 mfu:22.949460967601805 Step 6841 | loss:1.2279189825057983 lr:4.2002230121041543e-07 tokens_per_second_per_gpu:5330.643794343446 mfu:25.145556279534183 Step 6842 | loss:1.2609449625015259 lr:4.180301622416366e-07 tokens_per_second_per_gpu:5303.9499436201995 mfu:25.01963683123206 Step 6843 | loss:1.126760721206665 lr:4.1604271897221216e-07 tokens_per_second_per_gpu:4583.035321084075 mfu:21.618959556011124 Step 6844 | loss:1.2519229650497437 lr:4.1405997178178557e-07 tokens_per_second_per_gpu:4563.399451964357 mfu:21.526333811148675 Step 6845 | loss:1.3029283285140991 lr:4.120819210491095e-07 tokens_per_second_per_gpu:4913.7438610504605 mfu:23.17896816372781 Step 6846 | loss:1.1216421127319336 lr:4.101085671520316e-07 tokens_per_second_per_gpu:5341.233844400695 mfu:25.195511352503082 Step 6847 | loss:1.2261409759521484 lr:4.08139910467506e-07 tokens_per_second_per_gpu:3950.441491651693 mfu:18.63490653094172 Step 6848 | loss:1.4120367765426636 lr:4.061759513715929e-07 tokens_per_second_per_gpu:2959.58189200151 mfu:13.960852741311387 Step 6849 | loss:1.362781047821045 lr:4.0421669023944786e-07 tokens_per_second_per_gpu:5108.314756938869 mfu:24.096792276851463 Step 6850 | loss:1.1365851163864136 lr:4.022621274453353e-07 tokens_per_second_per_gpu:4205.921168369037 mfu:19.84004775534507 Step 6851 | loss:1.2693520784378052 lr:4.003122633626205e-07 tokens_per_second_per_gpu:4166.023962021033 mfu:19.651845825836197 Step 6852 | loss:1.2605644464492798 lr:3.983670983637694e-07 tokens_per_second_per_gpu:3160.535916273506 mfu:14.908787160094423 Step 6853 | loss:1.3118338584899902 lr:3.9642663282035143e-07 tokens_per_second_per_gpu:4434.320657744614 mfu:20.917447115700906 Step 6854 | loss:1.3334406614303589 lr:3.944908671030395e-07 tokens_per_second_per_gpu:4863.057814955723 mfu:22.939873436367726 Step 6855 | loss:1.4757112264633179 lr:3.925598015816073e-07 tokens_per_second_per_gpu:5148.588802047039 mfu:24.28677181908736 Step 6856 | loss:1.1925029754638672 lr:3.9063343662492923e-07 tokens_per_second_per_gpu:3308.243021743338 mfu:15.605546778026504 Step 6857 | loss:1.1673544645309448 lr:3.887117726009859e-07 tokens_per_second_per_gpu:3751.6644221011325 mfu:17.69724117900647 Step 6858 | loss:1.334306240081787 lr:3.867948098768559e-07 tokens_per_second_per_gpu:4944.604270001902 mfu:23.324541978080468 Step 6859 | loss:1.3013503551483154 lr:3.848825488187213e-07 tokens_per_second_per_gpu:4077.0804157038483 mfu:19.2322839425242 Step 6860 | loss:1.1869831085205078 lr:3.829749897918705e-07 tokens_per_second_per_gpu:3518.6750384692814 mfu:16.598190504327075 Step 6861 | loss:1.3145177364349365 lr:3.810721331606815e-07 tokens_per_second_per_gpu:4288.003271657468 mfu:20.22724304120753 Step 6862 | loss:1.2491793632507324 lr:3.791739792886495e-07 tokens_per_second_per_gpu:4929.225103804844 mfu:23.251995827172625 Step 6863 | loss:1.12374746799469 lr:3.772805285383596e-07 tokens_per_second_per_gpu:5318.610593468251 mfu:25.088793617930115 Step 6864 | loss:1.1287604570388794 lr:3.7539178127150575e-07 tokens_per_second_per_gpu:4478.048922246182 mfu:21.12372080016606 Step 6865 | loss:1.4672106504440308 lr:3.7350773784887716e-07 tokens_per_second_per_gpu:3196.3033214409543 mfu:15.077508112817874 Step 6866 | loss:1.3039805889129639 lr:3.7162839863036924e-07 tokens_per_second_per_gpu:5040.077516369092 mfu:23.774905570610052 Step 6867 | loss:1.4211444854736328 lr:3.697537639749754e-07 tokens_per_second_per_gpu:4833.898639542757 mfu:22.802324630876427 Step 6868 | loss:1.2863718271255493 lr:3.678838342407981e-07 tokens_per_second_per_gpu:4415.786287435811 mfu:20.830017328664617 Step 6869 | loss:1.2257091999053955 lr:3.6601860978502656e-07 tokens_per_second_per_gpu:4646.412543045734 mfu:21.917920725273365 Step 6870 | loss:1.3066681623458862 lr:3.641580909639675e-07 tokens_per_second_per_gpu:4134.261017765169 mfu:19.50201459846417 Step 6871 | loss:1.2945064306259155 lr:3.623022781330171e-07 tokens_per_second_per_gpu:5293.72472415087 mfu:24.971402726392895 Step 6872 | loss:1.2686102390289307 lr:3.60451171646678e-07 tokens_per_second_per_gpu:5332.635836999226 mfu:25.15495308461902 Step 6873 | loss:1.516478419303894 lr:3.5860477185855333e-07 tokens_per_second_per_gpu:3276.064392880144 mfu:15.4537546954386 Step 6874 | loss:1.1922763586044312 lr:3.5676307912134443e-07 tokens_per_second_per_gpu:5300.394469556515 mfu:25.00286505344723 Step 6875 | loss:1.4272226095199585 lr:3.5492609378685595e-07 tokens_per_second_per_gpu:4351.793835212414 mfu:20.528154013288656 Step 6876 | loss:1.4152992963790894 lr:3.530938162059905e-07 tokens_per_second_per_gpu:5005.379710997012 mfu:23.61123010261389 Step 6877 | loss:1.297552227973938 lr:3.5126624672875695e-07 tokens_per_second_per_gpu:3720.1042321805608 mfu:17.548366378427477 Step 6878 | loss:1.1719884872436523 lr:3.494433857042623e-07 tokens_per_second_per_gpu:3624.7789485734716 mfu:17.098700751482347 Step 6879 | loss:1.274623990058899 lr:3.476252334807084e-07 tokens_per_second_per_gpu:5205.185800023071 mfu:24.5537495149839 Step 6880 | loss:1.2998191118240356 lr:3.4581179040540646e-07 tokens_per_second_per_gpu:3689.92950323664 mfu:17.406027033659363 Step 6881 | loss:1.2602447271347046 lr:3.4400305682476263e-07 tokens_per_second_per_gpu:4609.472945341159 mfu:21.74367034035562 Step 6882 | loss:1.1932135820388794 lr:3.421990330842867e-07 tokens_per_second_per_gpu:4365.465257099074 mfu:20.592644442913134 Step 6883 | loss:1.2069872617721558 lr:3.403997195285835e-07 tokens_per_second_per_gpu:5344.886844502499 mfu:25.21274317724938 Step 6884 | loss:1.2061266899108887 lr:3.3860511650136426e-07 tokens_per_second_per_gpu:5314.780800877637 mfu:25.070727832850196 Step 6885 | loss:1.3363542556762695 lr:3.368152243454381e-07 tokens_per_second_per_gpu:3851.071328885573 mfu:18.16616051887589 Step 6886 | loss:1.2735552787780762 lr:3.3503004340271483e-07 tokens_per_second_per_gpu:4491.361062101248 mfu:21.18651643514767 Step 6887 | loss:1.2873308658599854 lr:3.3324957401419943e-07 tokens_per_second_per_gpu:5199.692869749647 mfu:24.52783842569361 Step 6888 | loss:1.2005654573440552 lr:3.31473816520006e-07 tokens_per_second_per_gpu:4550.204681112683 mfu:21.46409182578128 Step 6889 | loss:1.266385793685913 lr:3.2970277125933813e-07 tokens_per_second_per_gpu:5305.124873513222 mfu:25.025179176001156 Step 6890 | loss:1.1891905069351196 lr:3.279364385705086e-07 tokens_per_second_per_gpu:4355.938295117499 mfu:20.54770413777872 Step 6891 | loss:1.3250153064727783 lr:3.2617481879092524e-07 tokens_per_second_per_gpu:4904.00796450323 mfu:23.133042278599287 Step 6892 | loss:1.1773508787155151 lr:3.2441791225709397e-07 tokens_per_second_per_gpu:4415.971331834096 mfu:20.830890214663164 Step 6893 | loss:1.273832082748413 lr:3.2266571930462677e-07 tokens_per_second_per_gpu:5293.164134237561 mfu:24.96875832812531 Step 6894 | loss:1.1499089002609253 lr:3.209182402682254e-07 tokens_per_second_per_gpu:4818.277945485949 mfu:22.728639151845233 Step 6895 | loss:1.5327873229980469 lr:3.191754754817033e-07 tokens_per_second_per_gpu:5345.0835700556645 mfu:25.213671165248503 Step 6896 | loss:1.195878267288208 lr:3.174374252779638e-07 tokens_per_second_per_gpu:5063.625514171013 mfu:23.885985493944425 Step 6897 | loss:1.3336637020111084 lr:3.1570408998901347e-07 tokens_per_second_per_gpu:5334.84338182529 mfu:25.165366450209554 Step 6898 | loss:1.2209032773971558 lr:3.139754699459596e-07 tokens_per_second_per_gpu:5001.0870622871735 mfu:23.590980946248195 Step 6899 | loss:1.2121082544326782 lr:3.12251565479002e-07 tokens_per_second_per_gpu:5309.75964163491 mfu:25.047042168004143 Step 6900 | loss:1.344380497932434 lr:3.105323769174495e-07 tokens_per_second_per_gpu:4753.023270283186 mfu:22.42082171531815 Step 6901 | loss:1.414900302886963 lr:3.0881790458970053e-07 tokens_per_second_per_gpu:5356.730765107393 mfu:25.2686129715239 Step 6902 | loss:1.2515122890472412 lr:3.0710814882325965e-07 tokens_per_second_per_gpu:5200.736325710344 mfu:24.532760585492166 Step 6903 | loss:1.3315773010253906 lr:3.0540310994472964e-07 tokens_per_second_per_gpu:5299.658509431714 mfu:24.9993934039708 Step 6904 | loss:1.2383114099502563 lr:3.0370278827980823e-07 tokens_per_second_per_gpu:4425.252600025031 mfu:20.874671540267446 Step 6905 | loss:1.075162410736084 lr:3.0200718415329676e-07 tokens_per_second_per_gpu:5362.165719965878 mfu:25.294250580890292 Step 6906 | loss:1.1741244792938232 lr:3.0031629788908887e-07 tokens_per_second_per_gpu:5294.894936494956 mfu:24.97692281767876 Step 6907 | loss:1.381165623664856 lr:2.986301298101846e-07 tokens_per_second_per_gpu:5295.5173072442 mfu:24.979858646690346 Step 6908 | loss:1.3800321817398071 lr:2.9694868023867895e-07 tokens_per_second_per_gpu:3354.5350438572555 mfu:15.823914144571265 Step 6909 | loss:1.1892567873001099 lr:2.952719494957623e-07 tokens_per_second_per_gpu:4988.312371345026 mfu:23.530720549487057 Step 6910 | loss:1.3394885063171387 lr:2.9359993790173404e-07 tokens_per_second_per_gpu:3041.9807949253204 mfu:14.349542425105527 Step 6911 | loss:1.297107458114624 lr:2.9193264577598023e-07 tokens_per_second_per_gpu:5330.64216066011 mfu:25.145548573171155 Step 6912 | loss:1.4015793800354004 lr:2.902700734369934e-07 tokens_per_second_per_gpu:5321.501503321586 mfu:25.102430532948375 Step 6913 | loss:1.3621716499328613 lr:2.8861222120235845e-07 tokens_per_second_per_gpu:5333.563042505047 mfu:25.159326871187552 Step 6914 | loss:1.1959364414215088 lr:2.869590893887636e-07 tokens_per_second_per_gpu:4476.819889604977 mfu:21.117923243502904 Step 6915 | loss:1.3412095308303833 lr:2.8531067831199244e-07 tokens_per_second_per_gpu:5239.587718696387 mfu:24.716029234938503 Step 6916 | loss:1.1727677583694458 lr:2.8366698828692916e-07 tokens_per_second_per_gpu:5279.155800169939 mfu:24.902678626260087 Step 6917 | loss:1.2579272985458374 lr:2.8202801962755597e-07 tokens_per_second_per_gpu:5303.539940751129 mfu:25.01770277774495 Step 6918 | loss:1.388067603111267 lr:2.803937726469502e-07 tokens_per_second_per_gpu:3944.628918719376 mfu:18.607487632692774 Step 6919 | loss:1.2027801275253296 lr:2.7876424765728993e-07 tokens_per_second_per_gpu:3894.8922040145367 mfu:18.372871063471475 Step 6920 | loss:1.2733867168426514 lr:2.7713944496985114e-07 tokens_per_second_per_gpu:4779.446252043477 mfu:22.545463428507006 Step 6921 | loss:1.3752048015594482 lr:2.7551936489500497e-07 tokens_per_second_per_gpu:2916.686194324466 mfu:13.75850641660806 Step 6922 | loss:1.3566644191741943 lr:2.739040077422234e-07 tokens_per_second_per_gpu:5367.583971660628 mfu:25.31980939858349 Step 6923 | loss:1.096874713897705 lr:2.7229337382007334e-07 tokens_per_second_per_gpu:5305.490605023077 mfu:25.02690439393337 Step 6924 | loss:1.4148647785186768 lr:2.706874634362255e-07 tokens_per_second_per_gpu:5034.728072475076 mfu:23.74967133105273 Step 6925 | loss:1.200443983078003 lr:2.690862768974428e-07 tokens_per_second_per_gpu:4787.654385227534 mfu:22.584182593188128 Step 6926 | loss:1.3776687383651733 lr:2.6748981450958887e-07 tokens_per_second_per_gpu:5350.0373264604705 mfu:25.23703887940797 Step 6927 | loss:1.3178207874298096 lr:2.65898076577617e-07 tokens_per_second_per_gpu:5207.750128145736 mfu:24.565845888258004 Step 6928 | loss:1.1984267234802246 lr:2.643110634055923e-07 tokens_per_second_per_gpu:5321.490338372617 mfu:25.102377865979154 Step 6929 | loss:1.4049416780471802 lr:2.6272877529666395e-07 tokens_per_second_per_gpu:5321.767872717001 mfu:25.103687042833858 Step 6930 | loss:1.2824444770812988 lr:2.611512125530846e-07 tokens_per_second_per_gpu:4496.771525293417 mfu:21.21203851314534 Step 6931 | loss:1.1166951656341553 lr:2.5957837547620487e-07 tokens_per_second_per_gpu:4076.2417249693844 mfu:19.22832769523434 Step 6932 | loss:1.2358523607254028 lr:2.5801026436647333e-07 tokens_per_second_per_gpu:4553.616153203422 mfu:21.480184321690455 Step 6933 | loss:1.1794525384902954 lr:2.5644687952342814e-07 tokens_per_second_per_gpu:4868.693528936863 mfu:22.96645806076872 Step 6934 | loss:1.449866533279419 lr:2.5488822124571656e-07 tokens_per_second_per_gpu:4956.884220649904 mfu:23.382468600462726 Step 6935 | loss:1.1285696029663086 lr:2.5333428983107257e-07 tokens_per_second_per_gpu:5330.5741134066975 mfu:25.14522758266675 Step 6936 | loss:1.4354314804077148 lr:2.5178508557633373e-07 tokens_per_second_per_gpu:5307.919831204624 mfu:25.038363468300453 Step 6937 | loss:1.360489010810852 lr:2.502406087774328e-07 tokens_per_second_per_gpu:4506.537982689962 mfu:21.2581085590143 Step 6938 | loss:1.279025673866272 lr:2.4870085972939494e-07 tokens_per_second_per_gpu:5278.174482593486 mfu:24.898049583821916 Step 6939 | loss:1.1582410335540771 lr:2.4716583872635145e-07 tokens_per_second_per_gpu:4384.46753088034 mfu:20.682281410461584 Step 6940 | loss:1.079863429069519 lr:2.456355460615206e-07 tokens_per_second_per_gpu:5255.924688120394 mfu:24.793093507085956 Step 6941 | loss:1.2703396081924438 lr:2.4410998202722414e-07 tokens_per_second_per_gpu:5307.079691802003 mfu:25.034400387395728 Step 6942 | loss:1.2262753248214722 lr:2.425891469148789e-07 tokens_per_second_per_gpu:3741.4472658904538 mfu:17.64904510993409 Step 6943 | loss:1.2441542148590088 lr:2.410730410149969e-07 tokens_per_second_per_gpu:5342.731821341316 mfu:25.202577565313216 Step 6944 | loss:1.1428935527801514 lr:2.395616646171911e-07 tokens_per_second_per_gpu:4530.214500690364 mfu:21.369794734052725 Step 6945 | loss:1.3891066312789917 lr:2.3805501801016372e-07 tokens_per_second_per_gpu:4225.71036849339 mfu:19.933396788717342 Step 6946 | loss:1.191037893295288 lr:2.3655310148171794e-07 tokens_per_second_per_gpu:5165.657889824467 mfu:24.367289618420166 Step 6947 | loss:1.374786376953125 lr:2.350559153187576e-07 tokens_per_second_per_gpu:5092.9470136305 mfu:24.024300009658504 Step 6948 | loss:1.2662858963012695 lr:2.3356345980727056e-07 tokens_per_second_per_gpu:4729.7466859519645 mfu:22.311022095632975 Step 6949 | loss:1.2666785717010498 lr:2.320757352323566e-07 tokens_per_second_per_gpu:5301.799600056865 mfu:25.009493293757362 Step 6950 | loss:1.2190823554992676 lr:2.3059274187819946e-07 tokens_per_second_per_gpu:4408.225454128905 mfu:20.79435158794476 Step 6951 | loss:1.2338652610778809 lr:2.2911448002808366e-07 tokens_per_second_per_gpu:4141.093207883694 mfu:19.534243204945092 Step 6952 | loss:1.2741928100585938 lr:2.2764094996439166e-07 tokens_per_second_per_gpu:4045.6001431620766 mfu:19.083786125856324 Step 6953 | loss:1.416845679283142 lr:2.261721519686011e-07 tokens_per_second_per_gpu:3749.540956923631 mfu:17.687224431463676 Step 6954 | loss:1.254093050956726 lr:2.2470808632128192e-07 tokens_per_second_per_gpu:4843.740308993714 mfu:22.848749464838548 Step 6955 | loss:1.1986196041107178 lr:2.2324875330210216e-07 tokens_per_second_per_gpu:4485.116916737747 mfu:21.157061736106982 Step 6956 | loss:1.2129762172698975 lr:2.2179415318983322e-07 tokens_per_second_per_gpu:5066.022755528269 mfu:23.897293690438154 Step 6957 | loss:1.0842024087905884 lr:2.2034428626232783e-07 tokens_per_second_per_gpu:4845.537349892948 mfu:22.85722641336703 Step 6958 | loss:1.2788492441177368 lr:2.1889915279654783e-07 tokens_per_second_per_gpu:5101.7394797854695 mfu:24.06577557266091 Step 6959 | loss:1.5039880275726318 lr:2.1745875306854457e-07 tokens_per_second_per_gpu:4317.405352792482 mfu:20.36593767443372 Step 6960 | loss:1.1715030670166016 lr:2.1602308735346465e-07 tokens_per_second_per_gpu:4539.0748469178 mfu:21.41159049893849 Step 6961 | loss:1.2759718894958496 lr:2.1459215592555258e-07 tokens_per_second_per_gpu:4428.6212077829705 mfu:20.890561837805397 Step 6962 | loss:1.2887166738510132 lr:2.1316595905815085e-07 tokens_per_second_per_gpu:4568.227601345973 mfu:21.54910901554899 Step 6963 | loss:1.2807915210723877 lr:2.1174449702369148e-07 tokens_per_second_per_gpu:3812.648558859863 mfu:17.984913757064056 Step 6964 | loss:1.3736013174057007 lr:2.1032777009370174e-07 tokens_per_second_per_gpu:4197.118451843238 mfu:19.798523839594566 Step 6965 | loss:1.1376334428787231 lr:2.0891577853881516e-07 tokens_per_second_per_gpu:4081.1074818350617 mfu:19.251280300553468 Step 6966 | loss:1.2116587162017822 lr:2.075085226287521e-07 tokens_per_second_per_gpu:4267.0005926140675 mfu:20.128169820733255 Step 6967 | loss:1.2970201969146729 lr:2.061060026323225e-07 tokens_per_second_per_gpu:5310.944699987919 mfu:25.05263229044709 Step 6968 | loss:1.1382254362106323 lr:2.047082188174454e-07 tokens_per_second_per_gpu:4895.386175009854 mfu:23.092371826530055 Step 6969 | loss:1.3254462480545044 lr:2.0331517145112665e-07 tokens_per_second_per_gpu:3827.129394316735 mfu:18.05322232859942 Step 6970 | loss:1.3771939277648926 lr:2.019268607994701e-07 tokens_per_second_per_gpu:4452.086280473214 mfu:21.001250589239508 Step 6971 | loss:1.1966700553894043 lr:2.005432871276719e-07 tokens_per_second_per_gpu:3552.5976528288675 mfu:16.75820926405607 Step 6972 | loss:1.3988698720932007 lr:1.991644507000262e-07 tokens_per_second_per_gpu:5090.868069056726 mfu:24.014493273399495 Step 6973 | loss:1.2586032152175903 lr:1.9779035177991679e-07 tokens_per_second_per_gpu:5314.153701534253 mfu:25.06776969825327 Step 6974 | loss:1.2479290962219238 lr:1.9642099062983644e-07 tokens_per_second_per_gpu:5342.572942731453 mfu:25.201828107803006 Step 6975 | loss:1.387712001800537 lr:1.9505636751135647e-07 tokens_per_second_per_gpu:4064.2187216384464 mfu:19.171613137186412 Step 6976 | loss:1.502629041671753 lr:1.9369648268514895e-07 tokens_per_second_per_gpu:4438.061087157545 mfu:20.935091359424767 Step 6977 | loss:1.2753617763519287 lr:1.923413364109894e-07 tokens_per_second_per_gpu:4180.828092292772 mfu:19.721679434173073 Step 6978 | loss:1.2437078952789307 lr:1.9099092894773185e-07 tokens_per_second_per_gpu:4611.111775795444 mfu:21.751400983221792 Step 6979 | loss:1.33609139919281 lr:1.8964526055333665e-07 tokens_per_second_per_gpu:5343.6962510902 mfu:25.207126944987387 Step 6980 | loss:1.3286577463150024 lr:1.8830433148486204e-07 tokens_per_second_per_gpu:5271.095339702001 mfu:24.86465605897646 Step 6981 | loss:1.1276153326034546 lr:1.869681419984476e-07 tokens_per_second_per_gpu:5121.440245406664 mfu:24.158707445393308 Step 6982 | loss:1.1329504251480103 lr:1.856366923493391e-07 tokens_per_second_per_gpu:4749.089135310045 mfu:22.4022637294172 Step 6983 | loss:1.296085000038147 lr:1.8430998279187207e-07 tokens_per_second_per_gpu:5339.922848770389 mfu:25.189327162436008 Step 6984 | loss:1.2141013145446777 lr:1.8298801357947704e-07 tokens_per_second_per_gpu:5308.48868346588 mfu:25.041046841473005 Step 6985 | loss:1.3432655334472656 lr:1.8167078496467703e-07 tokens_per_second_per_gpu:4261.294911232268 mfu:20.101255148165677 Step 6986 | loss:1.221185326576233 lr:1.803582971990958e-07 tokens_per_second_per_gpu:4663.682214426657 mfu:21.999384711686947 Step 6987 | loss:1.4172319173812866 lr:1.7905055053344665e-07 tokens_per_second_per_gpu:5312.951137599894 mfu:25.06209699899633 Step 6988 | loss:1.213715672492981 lr:1.7774754521753535e-07 tokens_per_second_per_gpu:4729.568083280151 mfu:22.31017959635727 Step 6989 | loss:1.3464630842208862 lr:1.7644928150026828e-07 tokens_per_second_per_gpu:4236.461647318437 mfu:19.984112405292407 Step 6990 | loss:1.1723194122314453 lr:1.7515575962963883e-07 tokens_per_second_per_gpu:5307.753843375358 mfu:25.037580475389362 Step 6991 | loss:1.2996156215667725 lr:1.7386697985274092e-07 tokens_per_second_per_gpu:3714.0151714925078 mfu:17.51964324026105 Step 6992 | loss:1.2874159812927246 lr:1.7258294241576102e-07 tokens_per_second_per_gpu:5310.495112151484 mfu:25.050511507915033 Step 6993 | loss:1.3584098815917969 lr:1.713036475639751e-07 tokens_per_second_per_gpu:2923.6723075628042 mfu:13.79146110470713 Step 6994 | loss:1.2696503400802612 lr:1.7002909554175716e-07 tokens_per_second_per_gpu:5235.424373531614 mfu:24.696390025456335 Step 6995 | loss:1.3507487773895264 lr:1.687592865925791e-07 tokens_per_second_per_gpu:3769.650223113737 mfu:17.78208327107701 Step 6996 | loss:1.497275710105896 lr:1.6749422095899692e-07 tokens_per_second_per_gpu:3643.952091263378 mfu:17.1891437368261 Step 6997 | loss:1.2803641557693481 lr:1.6623389888267004e-07 tokens_per_second_per_gpu:5007.8076863158085 mfu:23.622683276447965 Step 6998 | loss:1.2000031471252441 lr:1.6497832060434758e-07 tokens_per_second_per_gpu:4904.301388193017 mfu:23.134426408207254 Step 6999 | loss:1.331995964050293 lr:1.6372748636387102e-07 tokens_per_second_per_gpu:4151.154224397451 mfu:19.58170273642691 Step 7000 | loss:1.3041064739227295 lr:1.6248139640017422e-07 tokens_per_second_per_gpu:3464.5432384550486 mfu:16.342841567822486 Step 7001 | loss:1.2998725175857544 lr:1.6124005095129736e-07 tokens_per_second_per_gpu:3951.1652548573843 mfu:18.638320645469697 Step 7002 | loss:1.31162691116333 lr:1.6000345025435626e-07 tokens_per_second_per_gpu:4357.841630366335 mfu:20.55668249488996 Step 7003 | loss:1.1744199991226196 lr:1.5877159454557034e-07 tokens_per_second_per_gpu:4756.38710542652 mfu:22.436689499618716 Step 7004 | loss:1.3080092668533325 lr:1.575444840602569e-07 tokens_per_second_per_gpu:4221.610494291708 mfu:19.914056982597337 Step 7005 | loss:1.334473729133606 lr:1.5632211903281458e-07 tokens_per_second_per_gpu:4290.150452669788 mfu:20.2373716603895 Step 7006 | loss:1.1851004362106323 lr:1.5510449969674545e-07 tokens_per_second_per_gpu:3715.948831864216 mfu:17.528764646150876 Step 7007 | loss:1.1087889671325684 lr:1.5389162628464127e-07 tokens_per_second_per_gpu:5115.697491280352 mfu:24.131617894364602 Step 7008 | loss:1.305004596710205 lr:1.5268349902818613e-07 tokens_per_second_per_gpu:5082.101879967797 mfu:23.973141663800927 Step 7009 | loss:1.371070146560669 lr:1.5148011815815932e-07 tokens_per_second_per_gpu:5305.293680665672 mfu:25.025975468140732 Step 7010 | loss:1.2446750402450562 lr:1.502814839044353e-07 tokens_per_second_per_gpu:5309.511296747111 mfu:25.045870682796387 Step 7011 | loss:1.1753731966018677 lr:1.4908759649597814e-07 tokens_per_second_per_gpu:4531.066311097911 mfu:21.373812869078964 Step 7012 | loss:1.1084853410720825 lr:1.478984561608443e-07 tokens_per_second_per_gpu:3409.620248163008 mfu:16.083760451786496 Step 7013 | loss:1.2899736166000366 lr:1.4671406312619096e-07 tokens_per_second_per_gpu:3293.716676143771 mfu:15.537023527383218 Step 7014 | loss:1.0929241180419922 lr:1.4553441761826215e-07 tokens_per_second_per_gpu:5318.529405341081 mfu:25.08841063968213 Step 7015 | loss:1.3460077047348022 lr:1.4435951986239427e-07 tokens_per_second_per_gpu:5330.690107168961 mfu:25.145774745033922 Step 7016 | loss:1.4165033102035522 lr:1.4318937008301613e-07 tokens_per_second_per_gpu:4302.4248966510595 mfu:20.295272306885252 Step 7017 | loss:1.2904341220855713 lr:1.4202396850366008e-07 tokens_per_second_per_gpu:4672.589018550304 mfu:22.041399626395677 Step 7018 | loss:1.3539721965789795 lr:1.4086331534693687e-07 tokens_per_second_per_gpu:4286.650669020256 mfu:20.220862583789994 Step 7019 | loss:1.153833270072937 lr:1.3970741083455808e-07 tokens_per_second_per_gpu:4440.515681433507 mfu:20.946670099421443 Step 7020 | loss:1.3358327150344849 lr:1.3855625518732762e-07 tokens_per_second_per_gpu:4103.452108669722 mfu:19.356683717719022 Step 7021 | loss:1.182944893836975 lr:1.374098486251446e-07 tokens_per_second_per_gpu:5159.023990526871 mfu:24.335996383573473 Step 7022 | loss:1.2181719541549683 lr:1.36268191366995e-07 tokens_per_second_per_gpu:4091.7564855578303 mfu:19.301513468021156 Step 7023 | loss:1.2391934394836426 lr:1.3513128363095983e-07 tokens_per_second_per_gpu:3897.3302654283784 mfu:18.384371815136735 Step 7024 | loss:1.2877259254455566 lr:1.3399912563421267e-07 tokens_per_second_per_gpu:3797.6440570562454 mfu:17.914134962024406 Step 7025 | loss:1.2053965330123901 lr:1.3287171759302498e-07 tokens_per_second_per_gpu:5329.16018108067 mfu:25.138557822643143 Step 7026 | loss:1.237959623336792 lr:1.3174905972275498e-07 tokens_per_second_per_gpu:4934.7539493921695 mfu:23.278076335126364 Step 7027 | loss:1.4462833404541016 lr:1.3063115223785339e-07 tokens_per_second_per_gpu:4202.438728227217 mfu:19.82362049103055 Step 7028 | loss:1.3645938634872437 lr:1.2951799535186603e-07 tokens_per_second_per_gpu:5330.160329519874 mfu:25.143275693473793 Step 7029 | loss:1.19757878780365 lr:1.2840958927743118e-07 tokens_per_second_per_gpu:4346.9935055220085 mfu:20.505510039118313 Step 7030 | loss:1.2357934713363647 lr:1.2730593422627947e-07 tokens_per_second_per_gpu:4442.181131782834 mfu:20.954526312874354 Step 7031 | loss:1.351906657218933 lr:1.2620703040923387e-07 tokens_per_second_per_gpu:4610.3570778962885 mfu:21.747840944466734 Step 7032 | loss:1.418733835220337 lr:1.251128780362043e-07 tokens_per_second_per_gpu:5297.39160172173 mfu:24.988700013528465 Step 7033 | loss:1.4839026927947998 lr:1.2402347731620413e-07 tokens_per_second_per_gpu:3020.884773580876 mfu:14.250028893071388 Step 7034 | loss:1.212975025177002 lr:1.2293882845732796e-07 tokens_per_second_per_gpu:5315.700916519353 mfu:25.075068175320084 Step 7035 | loss:1.1472731828689575 lr:1.218589316667712e-07 tokens_per_second_per_gpu:4443.321245116049 mfu:20.95990442199052 Step 7036 | loss:1.563674807548523 lr:1.2078378715081885e-07 tokens_per_second_per_gpu:2720.2288272813325 mfu:12.831783497182405 Step 7037 | loss:1.1954530477523804 lr:1.197133951148427e-07 tokens_per_second_per_gpu:4556.180106570937 mfu:21.49227892718058 Step 7038 | loss:1.1603397130966187 lr:1.1864775576331532e-07 tokens_per_second_per_gpu:5306.897731742341 mfu:25.033542050748714 Step 7039 | loss:1.3421365022659302 lr:1.1758686929979612e-07 tokens_per_second_per_gpu:3752.884053100647 mfu:17.702994386521684 Step 7040 | loss:1.2542778253555298 lr:1.1653073592693687e-07 tokens_per_second_per_gpu:3762.5330082879764 mfu:17.748510154421833 Step 7041 | loss:1.3753854036331177 lr:1.1547935584648451e-07 tokens_per_second_per_gpu:5340.6790627163655 mfu:25.192894352642586 Step 7042 | loss:1.3127427101135254 lr:1.1443272925927284e-07 tokens_per_second_per_gpu:5338.392712313089 mfu:25.182109247698726 Step 7043 | loss:1.3424404859542847 lr:1.1339085636523361e-07 tokens_per_second_per_gpu:3641.640745605776 mfu:17.178240725002958 Step 7044 | loss:1.219299077987671 lr:1.1235373736338539e-07 tokens_per_second_per_gpu:4755.018525737912 mfu:22.430233675723777 Step 7045 | loss:1.188382625579834 lr:1.113213724518447e-07 tokens_per_second_per_gpu:5311.364011101227 mfu:25.054610252510418 Step 7046 | loss:1.3739029169082642 lr:1.1029376182780938e-07 tokens_per_second_per_gpu:4507.356912136902 mfu:21.261971588939293 Step 7047 | loss:1.3897483348846436 lr:1.0927090568758069e-07 tokens_per_second_per_gpu:4941.424893692672 mfu:23.3095443175723 Step 7048 | loss:1.34882390499115 lr:1.0825280422654682e-07 tokens_per_second_per_gpu:4537.3499454541725 mfu:21.403453844436026 Step 7049 | loss:1.4366344213485718 lr:1.0723945763918553e-07 tokens_per_second_per_gpu:3531.341361742972 mfu:16.657939712306668 Step 7050 | loss:1.248704433441162 lr:1.0623086611906973e-07 tokens_per_second_per_gpu:4113.159206645037 mfu:19.402473755070275 Step 7051 | loss:1.4111448526382446 lr:1.0522702985886202e-07 tokens_per_second_per_gpu:4396.728829394147 mfu:20.740120047544465 Step 7052 | loss:1.0641815662384033 lr:1.042279490503173e-07 tokens_per_second_per_gpu:4422.595954054485 mfu:20.86213968795384 Step 7053 | loss:1.3482935428619385 lr:1.0323362388428292e-07 tokens_per_second_per_gpu:5326.921933930741 mfu:25.12799962895259 Step 7054 | loss:1.3396810293197632 lr:1.0224405455069586e-07 tokens_per_second_per_gpu:4688.479102276725 mfu:22.116355862461052 Step 7055 | loss:1.2426624298095703 lr:1.0125924123858821e-07 tokens_per_second_per_gpu:4618.529489077459 mfu:21.786391602365445 Step 7056 | loss:1.0630521774291992 lr:1.0027918413607617e-07 tokens_per_second_per_gpu:4775.376678410381 mfu:22.526266555338832 Step 7057 | loss:1.1684569120407104 lr:9.930388343037666e-08 tokens_per_second_per_gpu:4035.50137806985 mfu:19.03614852788929 Step 7058 | loss:1.1026545763015747 lr:9.833333930779065e-08 tokens_per_second_per_gpu:5317.355358587385 mfu:25.082872460831915 Step 7059 | loss:1.4420448541641235 lr:9.736755195371427e-08 tokens_per_second_per_gpu:3879.8459026729784 mfu:18.301895092879615 Step 7060 | loss:1.0973321199417114 lr:9.640652155263884e-08 tokens_per_second_per_gpu:5081.843706083043 mfu:23.971923813537533 Step 7061 | loss:1.3436769247055054 lr:9.545024828813698e-08 tokens_per_second_per_gpu:5335.03768610387 mfu:25.166283016643344 Step 7062 | loss:1.1832594871520996 lr:9.44987323428792e-08 tokens_per_second_per_gpu:4789.5061558698135 mfu:22.592917711252415 Step 7063 | loss:1.3138928413391113 lr:9.35519738986257e-08 tokens_per_second_per_gpu:4571.760472349512 mfu:21.565774170842634 Step 7064 | loss:1.387670636177063 lr:9.260997313623176e-08 tokens_per_second_per_gpu:4758.2710668143545 mfu:22.445576466922088 Step 7065 | loss:1.2115200757980347 lr:9.167273023563405e-08 tokens_per_second_per_gpu:3994.2094167883747 mfu:18.841367301389504 Step 7066 | loss:1.1075397729873657 lr:9.074024537587266e-08 tokens_per_second_per_gpu:5339.258144882358 mfu:25.18619164078599 Step 7067 | loss:1.359306812286377 lr:8.981251873506902e-08 tokens_per_second_per_gpu:4955.241875161576 mfu:23.374721376581245 Step 7068 | loss:1.182054042816162 lr:8.888955049044246e-08 tokens_per_second_per_gpu:5315.434284461703 mfu:25.073810426412027 Step 7069 | loss:1.1691001653671265 lr:8.797134081829639e-08 tokens_per_second_per_gpu:3291.8117524042964 mfu:15.52803767709061 Step 7070 | loss:1.2921408414840698 lr:8.705788989403496e-08 tokens_per_second_per_gpu:4084.8383114528897 mfu:19.26887926040593 Step 7071 | loss:1.2514041662216187 lr:8.614919789214083e-08 tokens_per_second_per_gpu:4371.316048743387 mfu:20.62024362534735 Step 7072 | loss:1.1497091054916382 lr:8.524526498619734e-08 tokens_per_second_per_gpu:3352.965945491099 mfu:15.816512439862317 Step 7073 | loss:1.2296806573867798 lr:8.43460913488775e-08 tokens_per_second_per_gpu:5334.503983517522 mfu:25.16376545048449 Step 7074 | loss:1.4246972799301147 lr:8.345167715193835e-08 tokens_per_second_per_gpu:4035.797651579795 mfu:19.03754610058517 Step 7075 | loss:1.1578975915908813 lr:8.256202256624046e-08 tokens_per_second_per_gpu:3718.0924426213833 mfu:17.538876423830143 Step 7076 | loss:1.344089150428772 lr:8.16771277617201e-08 tokens_per_second_per_gpu:3258.48882860919 mfu:15.370847760072026 Step 7077 | loss:1.0770697593688965 lr:8.079699290741428e-08 tokens_per_second_per_gpu:5351.840871482312 mfu:25.245546508992504 Step 7078 | loss:1.0774872303009033 lr:7.99216181714496e-08 tokens_per_second_per_gpu:5338.554362156617 mfu:25.182871777590957 Step 7079 | loss:1.2385936975479126 lr:7.905100372103957e-08 tokens_per_second_per_gpu:5278.165560240311 mfu:24.898007495559682 Step 7080 | loss:1.1272120475769043 lr:7.81851497224928e-08 tokens_per_second_per_gpu:5304.902776452655 mfu:25.0241315062728 Step 7081 | loss:1.256942629814148 lr:7.732405634120755e-08 tokens_per_second_per_gpu:5219.256187401821 mfu:24.620121932905096 Step 7082 | loss:1.0786141157150269 lr:7.646772374166889e-08 tokens_per_second_per_gpu:5067.643456604848 mfu:23.904938813936496 Step 7083 | loss:1.4135316610336304 lr:7.561615208745431e-08 tokens_per_second_per_gpu:3323.805275426249 mfu:15.678956583843068 Step 7084 | loss:1.256776213645935 lr:7.47693415412365e-08 tokens_per_second_per_gpu:4849.985226339706 mfu:22.87820780545236 Step 7085 | loss:1.1774173974990845 lr:7.392729226477213e-08 tokens_per_second_per_gpu:5363.043750370245 mfu:25.298392400115123 Step 7086 | loss:1.240293025970459 lr:7.309000441891312e-08 tokens_per_second_per_gpu:4817.55494747206 mfu:22.725228646857538 Step 7087 | loss:1.1812118291854858 lr:7.225747816360096e-08 tokens_per_second_per_gpu:4118.722131093333 mfu:19.42871501882567 Step 7088 | loss:1.27358877658844 lr:7.1429713657864e-08 tokens_per_second_per_gpu:3360.819066404304 mfu:15.853556951090498 Step 7089 | loss:1.4018869400024414 lr:7.060671105982297e-08 tokens_per_second_per_gpu:4255.366717901502 mfu:20.073290848770373 Step 7090 | loss:1.2814384698867798 lr:6.978847052669102e-08 tokens_per_second_per_gpu:4375.365726016982 mfu:20.63934664399309 Step 7091 | loss:1.3123929500579834 lr:6.897499221477089e-08 tokens_per_second_per_gpu:5330.871987126015 mfu:25.146632703823265 Step 7092 | loss:1.3141059875488281 lr:6.816627627945493e-08 tokens_per_second_per_gpu:4237.716941243571 mfu:19.990033840912492 Step 7093 | loss:1.1972962617874146 lr:6.736232287522515e-08 tokens_per_second_per_gpu:5340.766084505397 mfu:25.1933048492689 Step 7094 | loss:1.4109883308410645 lr:6.656313215565313e-08 tokens_per_second_per_gpu:4422.382713104986 mfu:20.861133794012392 Step 7095 | loss:1.3271727561950684 lr:6.576870427340287e-08 tokens_per_second_per_gpu:5057.982412915953 mfu:23.859366022511956 Step 7096 | loss:1.485442876815796 lr:6.497903938022798e-08 tokens_per_second_per_gpu:3944.602621121068 mfu:18.607363582434722 Step 7097 | loss:1.4684231281280518 lr:6.419413762697169e-08 tokens_per_second_per_gpu:4257.226926928365 mfu:20.082065772134474 Step 7098 | loss:1.2283143997192383 lr:6.341399916356682e-08 tokens_per_second_per_gpu:4356.4882565198295 mfu:20.5502983995466 Step 7099 | loss:1.2730988264083862 lr:6.263862413903865e-08 tokens_per_second_per_gpu:4245.65512541844 mfu:20.02747961005923 Step 7100 | loss:1.1959441900253296 lr:6.186801270149923e-08 tokens_per_second_per_gpu:5318.945289923057 mfu:25.090372438212537 Step 7101 | loss:1.1443318128585815 lr:6.11021649981558e-08 tokens_per_second_per_gpu:4764.1934875504485 mfu:22.473513536003416 Step 7102 | loss:1.2617956399917603 lr:6.034108117529691e-08 tokens_per_second_per_gpu:4650.268300943138 mfu:21.93610899313555 Step 7103 | loss:1.245418667793274 lr:5.9584761378311815e-08 tokens_per_second_per_gpu:3977.324716137213 mfu:18.761719287590985 Step 7104 | loss:1.1229925155639648 lr:5.8833205751668284e-08 tokens_per_second_per_gpu:4225.184980711292 mfu:19.930918444908787 Step 7105 | loss:1.2440598011016846 lr:5.808641443893759e-08 tokens_per_second_per_gpu:4526.572985702269 mfu:21.352617086547358 Step 7106 | loss:1.3760992288589478 lr:5.734438758276672e-08 tokens_per_second_per_gpu:5346.654119543464 mfu:25.221079715145827 Step 7107 | loss:1.398091435432434 lr:5.6607125324900645e-08 tokens_per_second_per_gpu:4164.2111692605295 mfu:19.643294573090564 Step 7108 | loss:1.140461802482605 lr:5.5874627806176696e-08 tokens_per_second_per_gpu:5248.834025215291 mfu:24.759645640370742 Step 7109 | loss:1.2985273599624634 lr:5.514689516651072e-08 tokens_per_second_per_gpu:4884.432646149407 mfu:23.04070216203059 Step 7110 | loss:1.4083915948867798 lr:5.442392754492487e-08 tokens_per_second_per_gpu:5340.999010480494 mfu:25.194403600834697 Step 7111 | loss:1.2754424810409546 lr:5.370572507951421e-08 tokens_per_second_per_gpu:3060.780040276033 mfu:14.438221672906842 Step 7112 | loss:1.4840160608291626 lr:5.299228790747457e-08 tokens_per_second_per_gpu:5036.97914960981 mfu:23.76029004597063 Step 7113 | loss:1.3090851306915283 lr:5.228361616508859e-08 tokens_per_second_per_gpu:3049.3493270507292 mfu:14.3843010483423 Step 7114 | loss:1.3656255006790161 lr:5.157970998772854e-08 tokens_per_second_per_gpu:5350.130641137463 mfu:25.237479060660466 Step 7115 | loss:1.2022395133972168 lr:5.088056950985354e-08 tokens_per_second_per_gpu:5309.114907878408 mfu:25.044000848871804 Step 7116 | loss:1.3427793979644775 lr:5.018619486501786e-08 tokens_per_second_per_gpu:5068.049886391959 mfu:23.90685601258637 Step 7117 | loss:1.3615436553955078 lr:4.9496586185862617e-08 tokens_per_second_per_gpu:5290.056707456829 mfu:24.95410006581892 Step 7118 | loss:1.162956714630127 lr:4.8811743604113005e-08 tokens_per_second_per_gpu:5307.917525035232 mfu:25.038352589705962 Step 7119 | loss:1.3631683588027954 lr:4.813166725059215e-08 tokens_per_second_per_gpu:5289.135859435507 mfu:24.94975626858947 Step 7120 | loss:1.2466751337051392 lr:4.7456357255212803e-08 tokens_per_second_per_gpu:5327.171533924519 mfu:25.129177034709393 Step 7121 | loss:1.0638073682785034 lr:4.678581374697178e-08 tokens_per_second_per_gpu:5350.452405838025 mfu:25.238996879651737 Step 7122 | loss:1.1841881275177002 lr:4.612003685395549e-08 tokens_per_second_per_gpu:4151.614821410985 mfu:19.583875451125706 Step 7123 | loss:1.197980523109436 lr:4.5459026703345566e-08 tokens_per_second_per_gpu:5332.189816345806 mfu:25.152849129097874 Step 7124 | loss:1.3669601678848267 lr:4.480278342140765e-08 tokens_per_second_per_gpu:3554.441216345241 mfu:16.766905667707174 Step 7125 | loss:1.184249997138977 lr:4.4151307133499795e-08 tokens_per_second_per_gpu:3828.1736988414928 mfu:18.058148491219427 Step 7126 | loss:1.3078006505966187 lr:4.350459796406692e-08 tokens_per_second_per_gpu:4809.716350440102 mfu:22.688252647255233 Step 7127 | loss:1.1590893268585205 lr:4.286265603664352e-08 tokens_per_second_per_gpu:4372.91155172061 mfu:20.627769885111785 Step 7128 | loss:1.3682656288146973 lr:4.2225481473859295e-08 tokens_per_second_per_gpu:4475.822964394359 mfu:21.113220577191438 Step 7129 | loss:1.2831779718399048 lr:4.1593074397425216e-08 tokens_per_second_per_gpu:3296.6205790668932 mfu:15.550721732928514 Step 7130 | loss:1.1235036849975586 lr:4.096543492814464e-08 tokens_per_second_per_gpu:5318.388935089603 mfu:25.087748017539216 Step 7131 | loss:1.237573504447937 lr:4.034256318591334e-08 tokens_per_second_per_gpu:5133.42150554649 mfu:24.21522509368664 Step 7132 | loss:1.277313470840454 lr:3.972445928971114e-08 tokens_per_second_per_gpu:5289.733360158932 mfu:24.952574781446 Step 7133 | loss:1.2473490238189697 lr:3.9111123357610244e-08 tokens_per_second_per_gpu:4992.685439971214 mfu:23.551349060319232 Step 7134 | loss:1.2868810892105103 lr:3.850255550676973e-08 tokens_per_second_per_gpu:4042.6539919832812 mfu:19.06988862808072 Step 7135 | loss:1.2549327611923218 lr:3.789875585344382e-08 tokens_per_second_per_gpu:3588.511816240755 mfu:16.927622500458078 Step 7136 | loss:1.4781135320663452 lr:3.729972451296804e-08 tokens_per_second_per_gpu:5338.528013847378 mfu:25.182747488120793 Step 7137 | loss:1.3126137256622314 lr:3.670546159977306e-08 tokens_per_second_per_gpu:4407.119029996775 mfu:20.78913239653808 Step 7138 | loss:1.413703441619873 lr:3.611596722737365e-08 tokens_per_second_per_gpu:4193.341268262442 mfu:19.780706220189973 Step 7139 | loss:1.2968429327011108 lr:3.553124150837694e-08 tokens_per_second_per_gpu:5314.142650870307 mfu:25.067717570385998 Step 7140 | loss:1.2089908123016357 lr:3.4951284554479716e-08 tokens_per_second_per_gpu:5301.3851142147 mfu:25.007538093321294 Step 7141 | loss:1.4314912557601929 lr:3.4376096476465556e-08 tokens_per_second_per_gpu:5219.285821775825 mfu:24.620261723303418 Step 7142 | loss:1.1460293531417847 lr:3.3805677384207704e-08 tokens_per_second_per_gpu:4422.58562521715 mfu:20.862090965065843 Step 7143 | loss:1.147443413734436 lr:3.324002738666898e-08 tokens_per_second_per_gpu:4729.432473913759 mfu:22.309539903838658 Step 7144 | loss:1.1193883419036865 lr:3.267914659190463e-08 tokens_per_second_per_gpu:5252.083623789136 mfu:24.774974551282256 Step 7145 | loss:1.4597432613372803 lr:3.212303510704839e-08 tokens_per_second_per_gpu:3385.0918977945066 mfu:15.968056038130165 Step 7146 | loss:1.1906918287277222 lr:3.157169303833474e-08 tokens_per_second_per_gpu:2793.251946817904 mfu:13.176246011065338 Step 7147 | loss:1.1872516870498657 lr:3.1025120491082194e-08 tokens_per_second_per_gpu:4426.963331341868 mfu:20.882741351769823 Step 7148 | loss:1.1315603256225586 lr:3.048331756969336e-08 tokens_per_second_per_gpu:4197.909881227346 mfu:19.802257147031174 Step 7149 | loss:1.1528183221817017 lr:2.994628437767155e-08 tokens_per_second_per_gpu:4359.225538161236 mfu:20.56321062407752 Step 7150 | loss:1.315858006477356 lr:2.9414021017598603e-08 tokens_per_second_per_gpu:5028.247658847892 mfu:23.71910211430073 Step 7151 | loss:1.4120529890060425 lr:2.8886527591145962e-08 tokens_per_second_per_gpu:4955.563901022305 mfu:23.376240427509583 Step 7152 | loss:1.327854037284851 lr:2.8363804199080247e-08 tokens_per_second_per_gpu:3788.9436064969377 mfu:17.873093452286213 Step 7153 | loss:1.3001151084899902 lr:2.7845850941254916e-08 tokens_per_second_per_gpu:5226.093843788942 mfu:24.65237632470762 Step 7154 | loss:1.2934010028839111 lr:2.7332667916604713e-08 tokens_per_second_per_gpu:5331.882991355778 mfu:25.151401783270167 Step 7155 | loss:1.2681217193603516 lr:2.6824255223162342e-08 tokens_per_second_per_gpu:5354.964627988417 mfu:25.260281801399625 Step 7156 | loss:1.1505920886993408 lr:2.6320612958044556e-08 tokens_per_second_per_gpu:4866.624159322584 mfu:22.9566964912273 Step 7157 | loss:1.2517973184585571 lr:2.5821741217460504e-08 tokens_per_second_per_gpu:5326.575911045796 mfu:25.12636737996671 Step 7158 | loss:1.4057241678237915 lr:2.532764009670341e-08 tokens_per_second_per_gpu:4621.323654652771 mfu:21.799572158117996 Step 7159 | loss:1.3556580543518066 lr:2.4838309690158878e-08 tokens_per_second_per_gpu:5159.616707249882 mfu:24.338792329483812 Step 7160 | loss:1.2063509225845337 lr:2.4353750091299366e-08 tokens_per_second_per_gpu:4212.6683324916385 mfu:19.871875279696283 Step 7161 | loss:1.2187435626983643 lr:2.387396139268694e-08 tokens_per_second_per_gpu:4632.443747672385 mfu:21.852027534175026 Step 7162 | loss:1.2587101459503174 lr:2.3398943685967735e-08 tokens_per_second_per_gpu:5321.006723418938 mfu:25.10009657172943 Step 7163 | loss:1.618689775466919 lr:2.2928697061888604e-08 tokens_per_second_per_gpu:5324.048013088836 mfu:25.114442853999865 Step 7164 | loss:1.289432168006897 lr:2.246322161026937e-08 tokens_per_second_per_gpu:4529.859196039734 mfu:21.36811870139448 Step 7165 | loss:1.4327656030654907 lr:2.2002517420030566e-08 tokens_per_second_per_gpu:4740.201188819662 mfu:22.360337769382028 Step 7166 | loss:1.3200191259384155 lr:2.1546584579176798e-08 tokens_per_second_per_gpu:4518.967251295099 mfu:21.316739539676636 Step 7167 | loss:1.3945900201797485 lr:2.1095423174796737e-08 tokens_per_second_per_gpu:5326.9461676686105 mfu:25.128113943628822 Step 7168 | loss:1.282753586769104 lr:2.0649033293079768e-08 tokens_per_second_per_gpu:5288.838414799071 mfu:24.948353171490115 Step 7169 | loss:1.3667434453964233 lr:2.0207415019288244e-08 tokens_per_second_per_gpu:3972.7159155121303 mfu:18.739978788699997 Step 7170 | loss:1.1594781875610352 lr:1.9770568437788016e-08 tokens_per_second_per_gpu:4802.92545452166 mfu:22.656218832561617 Step 7171 | loss:1.269792079925537 lr:1.933849363202067e-08 tokens_per_second_per_gpu:5099.764752368171 mfu:24.056460446510272 Step 7172 | loss:1.1813714504241943 lr:1.8911190684525736e-08 tokens_per_second_per_gpu:5156.410977631768 mfu:24.323670355921298 Step 7173 | loss:1.2014657258987427 lr:1.8488659676926813e-08 tokens_per_second_per_gpu:5143.4213352845445 mfu:24.262395996707927 Step 7174 | loss:1.2655742168426514 lr:1.8070900689934334e-08 tokens_per_second_per_gpu:5330.927679804762 mfu:25.146895415691066 Step 7175 | loss:1.146934151649475 lr:1.765791380335391e-08 tokens_per_second_per_gpu:5334.691779311016 mfu:25.164651315283667 Step 7176 | loss:1.3209511041641235 lr:1.7249699096069662e-08 tokens_per_second_per_gpu:5069.150549094304 mfu:23.91204802634575 Step 7177 | loss:1.3208309412002563 lr:1.6846256646066426e-08 tokens_per_second_per_gpu:4696.36765764794 mfu:22.153567524073406 Step 7178 | loss:1.316564679145813 lr:1.6447586530404792e-08 tokens_per_second_per_gpu:4759.956544077831 mfu:22.453527150745977 Step 7179 | loss:1.2055487632751465 lr:1.60536888252405e-08 tokens_per_second_per_gpu:5300.700370715107 mfu:25.00430804140443 Step 7180 | loss:1.1751335859298706 lr:1.5664563605818916e-08 tokens_per_second_per_gpu:4621.911869035812 mfu:21.80234686572252 Step 7181 | loss:1.2435556650161743 lr:1.5280210946469476e-08 tokens_per_second_per_gpu:5328.915534317815 mfu:25.13740378212172 Step 7182 | loss:1.2907675504684448 lr:1.4900630920614e-08 tokens_per_second_per_gpu:5001.098647614972 mfu:23.591035596216077 Step 7183 | loss:1.1307004690170288 lr:1.4525823600758381e-08 tokens_per_second_per_gpu:4249.826116924965 mfu:20.047154888640048 Step 7184 | loss:1.2394605875015259 lr:1.4155789058503677e-08 tokens_per_second_per_gpu:4554.707830747425 mfu:21.48533395092491 Step 7185 | loss:1.3136324882507324 lr:1.3790527364526684e-08 tokens_per_second_per_gpu:5349.0865709150285 mfu:25.2325540032845 Step 7186 | loss:1.2148269414901733 lr:1.3430038588607696e-08 tokens_per_second_per_gpu:5283.8091885939475 mfu:24.924629453406073 Step 7187 | loss:1.2344096899032593 lr:1.3074322799605521e-08 tokens_per_second_per_gpu:5324.327980040465 mfu:25.115763505877986 Step 7188 | loss:1.2516374588012695 lr:1.2723380065468582e-08 tokens_per_second_per_gpu:5276.298861115257 mfu:24.88920195729509 Step 7189 | loss:1.2180043458938599 lr:1.2377210453237698e-08 tokens_per_second_per_gpu:5294.859251565425 mfu:24.976754485777686 Step 7190 | loss:1.2789591550827026 lr:1.2035814029034976e-08 tokens_per_second_per_gpu:2891.2898476349355 mfu:13.638707516209989 Step 7191 | loss:1.500810146331787 lr:1.1699190858077692e-08 tokens_per_second_per_gpu:4364.758210135841 mfu:20.58930918175291 Step 7192 | loss:1.341995120048523 lr:1.1367341004667188e-08 tokens_per_second_per_gpu:4086.421373229029 mfu:19.276346832902178 Step 7193 | loss:1.0693259239196777 lr:1.1040264532194422e-08 tokens_per_second_per_gpu:5336.676785969893 mfu:25.17401493037065 Step 7194 | loss:1.3140881061553955 lr:1.0717961503137196e-08 tokens_per_second_per_gpu:5212.099455340464 mfu:24.586362406707273 Step 7195 | loss:1.2281931638717651 lr:1.040043197906293e-08 tokens_per_second_per_gpu:5192.51125875037 mfu:24.493961541300834 Step 7196 | loss:1.3474245071411133 lr:1.0087676020628655e-08 tokens_per_second_per_gpu:3702.4984542783036 mfu:17.465316920207073 Step 7197 | loss:1.3794907331466675 lr:9.779693687575475e-09 tokens_per_second_per_gpu:5246.934703835829 mfu:24.750686217366177 Step 7198 | loss:1.1538540124893188 lr:9.476485038734106e-09 tokens_per_second_per_gpu:4578.621751557122 mfu:21.59813999551987 Step 7199 | loss:1.3346498012542725 lr:9.17805013202766e-09 tokens_per_second_per_gpu:4568.6445743537915 mfu:21.5510759483698 Step 7200 | loss:1.3291103839874268 lr:8.884389024460538e-09 tokens_per_second_per_gpu:5198.022556961304 mfu:24.519959275286247 Step 7201 | loss:1.0920273065567017 lr:8.595501772129532e-09 tokens_per_second_per_gpu:4307.13347607725 mfu:20.317483479405084 Step 7202 | loss:1.1477404832839966 lr:8.311388430221056e-09 tokens_per_second_per_gpu:5338.549041928606 mfu:25.182846681167703 Step 7203 | loss:1.3354343175888062 lr:8.03204905300281e-09 tokens_per_second_per_gpu:4535.509046920647 mfu:21.394770011963704 Step 7204 | loss:1.382547378540039 lr:7.757483693834889e-09 tokens_per_second_per_gpu:4926.909061417721 mfu:23.241070660074985 Step 7205 | loss:1.209149956703186 lr:7.487692405169776e-09 tokens_per_second_per_gpu:4718.744067623414 mfu:22.25912086773694 Step 7206 | loss:1.5264513492584229 lr:7.222675238538479e-09 tokens_per_second_per_gpu:5266.045668676236 mfu:24.84083589918521 Step 7207 | loss:1.286025881767273 lr:6.962432244569938e-09 tokens_per_second_per_gpu:4429.062988191996 mfu:20.892645791370278 Step 7208 | loss:1.3119523525238037 lr:6.706963472971617e-09 tokens_per_second_per_gpu:3668.3347739004394 mfu:17.304161010939755 Step 7209 | loss:1.4225246906280518 lr:6.456268972546142e-09 tokens_per_second_per_gpu:5332.685572599285 mfu:25.15518769593027 Step 7210 | loss:1.4014935493469238 lr:6.210348791182985e-09 tokens_per_second_per_gpu:4101.858618284578 mfu:19.3491669516948 Step 7211 | loss:1.2495847940444946 lr:5.969202975855681e-09 tokens_per_second_per_gpu:3998.045847384276 mfu:18.859464399072927 Step 7212 | loss:1.3196492195129395 lr:5.732831572627384e-09 tokens_per_second_per_gpu:4455.963398069872 mfu:21.019539614447417 Step 7213 | loss:1.350385308265686 lr:5.501234626656415e-09 tokens_per_second_per_gpu:3705.8584555511693 mfu:17.48116661948651 Step 7214 | loss:1.5420093536376953 lr:5.274412182176836e-09 tokens_per_second_per_gpu:3884.1957574656217 mfu:18.322414100098275 Step 7215 | loss:1.3039475679397583 lr:5.052364282517874e-09 tokens_per_second_per_gpu:4120.496127094881 mfu:19.437083260639902 Step 7216 | loss:1.3270792961120605 lr:4.835090970098377e-09 tokens_per_second_per_gpu:5335.177276821144 mfu:25.16694148987336 Step 7217 | loss:1.3704031705856323 lr:4.622592286421256e-09 tokens_per_second_per_gpu:5324.146591458504 mfu:25.114907864988794 Step 7218 | loss:1.3092273473739624 lr:4.414868272076267e-09 tokens_per_second_per_gpu:5316.369873932531 mfu:25.07822376157395 Step 7219 | loss:1.2718172073364258 lr:4.211918966742778e-09 tokens_per_second_per_gpu:4472.33962667619 mfu:21.096789078856137 Step 7220 | loss:1.1441000699996948 lr:4.013744409192555e-09 tokens_per_second_per_gpu:5195.596835258635 mfu:24.50851673214396 Step 7221 | loss:1.454559087753296 lr:3.820344637281426e-09 tokens_per_second_per_gpu:4413.608958278498 mfu:20.81974649553891 Step 7222 | loss:1.1540470123291016 lr:3.631719687946511e-09 tokens_per_second_per_gpu:4345.445707255203 mfu:20.498208810612173 Step 7223 | loss:1.461082935333252 lr:3.4478695972284258e-09 tokens_per_second_per_gpu:3714.7386779783933 mfu:17.523056143797906 Step 7224 | loss:1.1956285238265991 lr:3.2687944002379732e-09 tokens_per_second_per_gpu:5293.297856997134 mfu:24.969389121197672 Step 7225 | loss:1.1652079820632935 lr:3.094494131186676e-09 tokens_per_second_per_gpu:5031.436890590525 mfu:23.734146264569773 Step 7226 | loss:1.2822215557098389 lr:2.924968823372898e-09 tokens_per_second_per_gpu:5237.923153353218 mfu:24.708177196210645 Step 7227 | loss:1.431736707687378 lr:2.760218509173518e-09 tokens_per_second_per_gpu:5302.045393923117 mfu:25.010652745361238 Step 7228 | loss:1.1292353868484497 lr:2.600243220060583e-09 tokens_per_second_per_gpu:5092.88882778771 mfu:24.024025537110536 Step 7229 | loss:1.3826074600219727 lr:2.4450429865985336e-09 tokens_per_second_per_gpu:4920.184961114993 mfu:23.209351931697203 Step 7230 | loss:1.2724201679229736 lr:2.2946178384275487e-09 tokens_per_second_per_gpu:4742.537901787342 mfu:22.371360443134915 Step 7231 | loss:1.4599390029907227 lr:2.148967804285751e-09 tokens_per_second_per_gpu:4553.072768699201 mfu:21.47762108427309 Step 7232 | loss:1.140493392944336 lr:2.008092911992554e-09 tokens_per_second_per_gpu:5329.212615689554 mfu:25.138805165639518 Step 7233 | loss:1.2069896459579468 lr:1.87199318846254e-09 tokens_per_second_per_gpu:5323.990769057853 mfu:25.11417282413888 Step 7234 | loss:1.0921881198883057 lr:1.7406686596888045e-09 tokens_per_second_per_gpu:4034.1989946051754 mfu:19.03000496287689 Step 7235 | loss:1.2133187055587769 lr:1.6141193507623886e-09 tokens_per_second_per_gpu:5334.324579481496 mfu:25.162919171037068 Step 7236 | loss:1.1798408031463623 lr:1.4923452858528475e-09 tokens_per_second_per_gpu:5216.3673416161155 mfu:24.606494754446008 Step 7237 | loss:1.3977121114730835 lr:1.375346488222129e-09 tokens_per_second_per_gpu:3624.0841226292273 mfu:17.095423138953812 Step 7238 | loss:1.4162874221801758 lr:1.263122980221798e-09 tokens_per_second_per_gpu:4386.350725190293 mfu:20.691164759327716 Step 7239 | loss:1.206842303276062 lr:1.1556747832902614e-09 tokens_per_second_per_gpu:3965.753190900817 mfu:18.707134428745118 Step 7240 | loss:1.1877467632293701 lr:1.0530019179472161e-09 tokens_per_second_per_gpu:5150.670448705955 mfu:24.29659130154301 Step 7241 | loss:1.2394752502441406 lr:9.551044038075273e-10 tokens_per_second_per_gpu:4255.66591470349 mfu:20.07470221113359 Step 7242 | loss:1.305548906326294 lr:8.619822595756776e-10 tokens_per_second_per_gpu:4236.965217687384 mfu:19.986487832640698 Step 7243 | loss:1.1662806272506714 lr:7.736355030346642e-10 tokens_per_second_per_gpu:5207.023671170068 mfu:24.562419066757435 Step 7244 | loss:1.2238941192626953 lr:6.900641510626526e-10 tokens_per_second_per_gpu:3676.3669074812587 mfu:17.342049955463782 Step 7245 | loss:1.2172633409500122 lr:6.112682196274256e-10 tokens_per_second_per_gpu:5311.686024327581 mfu:25.056129243840253 Step 7246 | loss:1.1476110219955444 lr:5.372477237725049e-10 tokens_per_second_per_gpu:3872.0705533917403 mfu:18.265217443708632 Step 7247 | loss:1.444239616394043 lr:4.680026776449076e-10 tokens_per_second_per_gpu:5325.936699206415 mfu:25.123352108659567 Step 7248 | loss:1.201582670211792 lr:4.035330944701654e-10 tokens_per_second_per_gpu:4403.6825438504175 mfu:20.772921905060716 Step 7249 | loss:1.3496181964874268 lr:3.4383898656065174e-10 tokens_per_second_per_gpu:5244.7664365969895 mfu:24.740458130856034 Step 7250 | loss:1.2151731252670288 lr:2.8892036532113255e-10 tokens_per_second_per_gpu:3743.2297728946423 mfu:17.657453499599907 Step 7251 | loss:1.2609699964523315 lr:2.3877724124321543e-10 tokens_per_second_per_gpu:5318.512560867831 mfu:25.088331181427847 Step 7252 | loss:1.286165714263916 lr:1.9340962390534955e-10 tokens_per_second_per_gpu:5318.604290253096 mfu:25.08876388458879 Step 7253 | loss:1.344826340675354 lr:1.5281752197005006e-10 tokens_per_second_per_gpu:4028.189271499063 mfu:19.00165607362086 Step 7254 | loss:1.238595724105835 lr:1.1700094319500032e-10 tokens_per_second_per_gpu:4610.514216473246 mfu:21.748582193944845 Step 7255 | loss:1.3263425827026367 lr:8.595989442194974e-11 tokens_per_second_per_gpu:5229.391795174546 mfu:24.667933324082046 Step 7256 | loss:1.4317352771759033 lr:5.969438157948925e-11 tokens_per_second_per_gpu:5004.34575849358 mfu:23.60635277224472 Step 7257 | loss:1.264220952987671 lr:3.820440968305139e-11 tokens_per_second_per_gpu:5349.274081511318 mfu:25.2334385227598 Step 7258 | loss:1.10454261302948 lr:2.148998284323689e-11 tokens_per_second_per_gpu:5010.038099504094 mfu:23.633204516004838 Step 7259 | loss:1.1682989597320557 lr:9.551104246385834e-12 tokens_per_second_per_gpu:3879.3389750701785 mfu:18.299503828886444 Step 7260 | loss:1.2914848327636719 lr:2.387776176782097e-12 tokens_per_second_per_gpu:5315.133502111328 mfu:25.072391584746548 Step 7261 | loss:1.3778202533721924 lr:0.0 tokens_per_second_per_gpu:4921.674263702712 mfu:23.216377226104697