Step 1 | loss:0.07063907384872437 lr:4.000000000000001e-06 tokens_per_second_per_gpu:6874.656102643277 Step 2 | loss:0.0801808312535286 lr:8.000000000000001e-06 tokens_per_second_per_gpu:7040.87632743559 Step 3 | loss:0.18747851252555847 lr:1.2e-05 tokens_per_second_per_gpu:3186.9423827760543 Step 4 | loss:0.14734072983264923 lr:1.6000000000000003e-05 tokens_per_second_per_gpu:7149.974895165396 Step 5 | loss:0.09741008281707764 lr:2e-05 tokens_per_second_per_gpu:7109.304788123487 Step 6 | loss:0.10051535069942474 lr:2.4e-05 tokens_per_second_per_gpu:7015.2990605024 Step 7 | loss:0.13897164165973663 lr:2.8000000000000003e-05 tokens_per_second_per_gpu:7124.769030604155 Step 8 | loss:0.16769015789031982 lr:3.2000000000000005e-05 tokens_per_second_per_gpu:7109.926632995434 Step 9 | loss:0.181987926363945 lr:3.6e-05 tokens_per_second_per_gpu:7115.557099855561 Step 10 | loss:0.19342440366744995 lr:4e-05 tokens_per_second_per_gpu:2124.339851387587 Step 11 | loss:0.12921205163002014 lr:4.4000000000000006e-05 tokens_per_second_per_gpu:7169.923170422217 Step 12 | loss:0.12405280768871307 lr:4.8e-05 tokens_per_second_per_gpu:7036.785208993393 Step 13 | loss:0.058394528925418854 lr:5.2000000000000004e-05 tokens_per_second_per_gpu:6944.286481421125 Step 14 | loss:0.1284671276807785 lr:5.6000000000000006e-05 tokens_per_second_per_gpu:3373.7156544541085 Step 15 | loss:0.08543194085359573 lr:6e-05 tokens_per_second_per_gpu:6962.833606290957 Step 16 | loss:0.07577818632125854 lr:6.400000000000001e-05 tokens_per_second_per_gpu:7000.616392438358 Step 17 | loss:0.18764404952526093 lr:6.800000000000001e-05 tokens_per_second_per_gpu:1643.9103007736385 Step 18 | loss:0.15422891080379486 lr:7.2e-05 tokens_per_second_per_gpu:2737.3548980002533 Step 19 | loss:0.04734514281153679 lr:7.6e-05 tokens_per_second_per_gpu:6961.301939059951 Step 20 | loss:0.08785419911146164 lr:8e-05 tokens_per_second_per_gpu:7147.650217778977 Step 21 | loss:0.056579429656267166 lr:8.4e-05 tokens_per_second_per_gpu:7054.4020226612865 Step 22 | loss:0.13737070560455322 lr:8.800000000000001e-05 tokens_per_second_per_gpu:7130.856677718144 Step 23 | loss:0.11649675667285919 lr:9.200000000000001e-05 tokens_per_second_per_gpu:7208.407111006576 Step 24 | loss:0.08172506093978882 lr:9.6e-05 tokens_per_second_per_gpu:4095.196265210999 Step 25 | loss:0.06308437138795853 lr:0.0001 tokens_per_second_per_gpu:7075.103438153463 Step 26 | loss:0.05569309741258621 lr:9.999512620046522e-05 tokens_per_second_per_gpu:7019.954552067832 Step 27 | loss:0.06308113783597946 lr:9.998050575201771e-05 tokens_per_second_per_gpu:7015.077046884144 Step 28 | loss:0.06458757072687149 lr:9.995614150494293e-05 tokens_per_second_per_gpu:6997.510785261277 Step 29 | loss:0.049056120216846466 lr:9.992203820909906e-05 tokens_per_second_per_gpu:4051.891213685837 Step 30 | loss:0.05089724808931351 lr:9.987820251299122e-05 tokens_per_second_per_gpu:7013.5034641783395 Step 31 | loss:0.07861800491809845 lr:9.982464296247522e-05 tokens_per_second_per_gpu:7159.549849942247 Step 32 | loss:0.0440584160387516 lr:9.976136999909156e-05 tokens_per_second_per_gpu:7112.941740550761 Step 33 | loss:0.057619404047727585 lr:9.968839595802982e-05 tokens_per_second_per_gpu:7161.256829241712 Step 34 | loss:0.03416652977466583 lr:9.96057350657239e-05 tokens_per_second_per_gpu:6907.507205051308 Step 35 | loss:0.030809275805950165 lr:9.951340343707852e-05 tokens_per_second_per_gpu:6988.132664730387 Step 36 | loss:0.05112010985612869 lr:9.941141907232765e-05 tokens_per_second_per_gpu:6966.615614290823 Step 37 | loss:0.04565148428082466 lr:9.929980185352526e-05 tokens_per_second_per_gpu:6992.704513402796 Step 38 | loss:0.09623751044273376 lr:9.917857354066931e-05 tokens_per_second_per_gpu:6969.982584695734 Step 39 | loss:0.05947336554527283 lr:9.904775776745958e-05 tokens_per_second_per_gpu:7249.376449779968 Step 40 | loss:0.06903963536024094 lr:9.890738003669029e-05 tokens_per_second_per_gpu:6930.954856631288 Step 41 | loss:0.13243110477924347 lr:9.875746771527816e-05 tokens_per_second_per_gpu:1990.9927148418933 Step 42 | loss:0.10677917301654816 lr:9.859805002892732e-05 tokens_per_second_per_gpu:6742.789282935288 Step 43 | loss:0.04582388326525688 lr:9.842915805643155e-05 tokens_per_second_per_gpu:7223.249478331776 Step 44 | loss:0.024604585021734238 lr:9.825082472361557e-05 tokens_per_second_per_gpu:6933.468997760702 Step 45 | loss:0.05129252001643181 lr:9.806308479691595e-05 tokens_per_second_per_gpu:7223.143264031078 Step 46 | loss:0.033024005591869354 lr:9.786597487660337e-05 tokens_per_second_per_gpu:7255.351485112446 Step 47 | loss:0.028983477503061295 lr:9.765953338964735e-05 tokens_per_second_per_gpu:7195.533760004664 Step 48 | loss:0.08475819230079651 lr:9.744380058222483e-05 tokens_per_second_per_gpu:6993.179607055751 Step 49 | loss:0.02869809977710247 lr:9.721881851187406e-05 tokens_per_second_per_gpu:6968.396567560355 Step 50 | loss:0.022100280970335007 lr:9.698463103929542e-05 tokens_per_second_per_gpu:6984.446124294531 Step 51 | loss:0.03306233510375023 lr:9.674128381980072e-05 tokens_per_second_per_gpu:6999.808265372898 Step 52 | loss:0.027357473969459534 lr:9.648882429441257e-05 tokens_per_second_per_gpu:7176.235873220122 Step 53 | loss:0.05449387803673744 lr:9.622730168061567e-05 tokens_per_second_per_gpu:2716.3226509879382 Step 54 | loss:0.0439644530415535 lr:9.595676696276172e-05 tokens_per_second_per_gpu:7020.539535387841 Step 55 | loss:0.016017036512494087 lr:9.567727288213005e-05 tokens_per_second_per_gpu:7103.516234557724 Step 56 | loss:0.01826702244579792 lr:9.538887392664544e-05 tokens_per_second_per_gpu:6475.349432874782 Step 57 | loss:0.04756738245487213 lr:9.50916263202557e-05 tokens_per_second_per_gpu:1661.8197865833567 Step 58 | loss:0.03192819282412529 lr:9.478558801197065e-05 tokens_per_second_per_gpu:7003.36726634201 Step 59 | loss:0.037976015359163284 lr:9.447081866456489e-05 tokens_per_second_per_gpu:7059.25945828456 Step 60 | loss:0.0204075388610363 lr:9.414737964294636e-05 tokens_per_second_per_gpu:7110.810797601217 Step 61 | loss:0.041492998600006104 lr:9.381533400219318e-05 tokens_per_second_per_gpu:7224.9900590973975 Step 62 | loss:0.06012221425771713 lr:9.347474647526095e-05 tokens_per_second_per_gpu:6787.804759421025 Step 63 | loss:0.03672964125871658 lr:9.312568346036288e-05 tokens_per_second_per_gpu:7190.684445382621 Step 64 | loss:0.039721887558698654 lr:9.276821300802534e-05 tokens_per_second_per_gpu:6955.830833713987 Step 65 | loss:0.022996515035629272 lr:9.24024048078213e-05 tokens_per_second_per_gpu:6987.613756250589 Step 66 | loss:0.014616144821047783 lr:9.202833017478422e-05 tokens_per_second_per_gpu:6956.195324933145 Step 67 | loss:0.007812967523932457 lr:9.164606203550497e-05 tokens_per_second_per_gpu:7000.076814768658 Step 68 | loss:0.05152742564678192 lr:9.125567491391476e-05 tokens_per_second_per_gpu:7189.962188274474 Step 69 | loss:0.04107976704835892 lr:9.085724491675642e-05 tokens_per_second_per_gpu:7213.391586424291 Step 70 | loss:0.018142802640795708 lr:9.045084971874738e-05 tokens_per_second_per_gpu:6989.7483845139905 Step 71 | loss:0.005483413580805063 lr:9.003656854743667e-05 tokens_per_second_per_gpu:7031.708683154948 Step 72 | loss:0.019375596195459366 lr:8.961448216775954e-05 tokens_per_second_per_gpu:7172.140571204813 Step 73 | loss:0.02874992974102497 lr:8.9184672866292e-05 tokens_per_second_per_gpu:7203.2787493556325 Step 74 | loss:0.08470457047224045 lr:8.874722443520899e-05 tokens_per_second_per_gpu:6829.690206698028 Step 75 | loss:0.033761534839868546 lr:8.83022221559489e-05 tokens_per_second_per_gpu:7147.934038100673 Step 76 | loss:0.017343897372484207 lr:8.784975278258783e-05 tokens_per_second_per_gpu:6985.970729210988 Step 77 | loss:0.02107246033847332 lr:8.73899045249266e-05 tokens_per_second_per_gpu:7027.6138671478775 Step 78 | loss:0.03424762934446335 lr:8.692276703129421e-05 tokens_per_second_per_gpu:7082.152550400412 Step 79 | loss:0.012075426988303661 lr:8.644843137107059e-05 tokens_per_second_per_gpu:6990.831519686031 Step 80 | loss:0.022634262219071388 lr:8.596699001693255e-05 tokens_per_second_per_gpu:7009.5455881110865 Step 81 | loss:0.028386667370796204 lr:8.547853682682604e-05 tokens_per_second_per_gpu:7089.106619266408 Step 82 | loss:0.013626204803586006 lr:8.498316702566828e-05 tokens_per_second_per_gpu:7000.292624454872 Step 83 | loss:0.055497635155916214 lr:8.44809771867835e-05 tokens_per_second_per_gpu:5292.2406143199205 Step 84 | loss:0.0751265212893486 lr:8.397206521307584e-05 tokens_per_second_per_gpu:7162.51432423115 Step 85 | loss:0.018934698775410652 lr:8.345653031794292e-05 tokens_per_second_per_gpu:7195.182336038 Step 86 | loss:0.017791179940104485 lr:8.293447300593402e-05 tokens_per_second_per_gpu:7110.710134820632 Step 87 | loss:0.016670145094394684 lr:8.240599505315655e-05 tokens_per_second_per_gpu:2087.762137775601 Step 88 | loss:0.009953480213880539 lr:8.18711994874345e-05 tokens_per_second_per_gpu:6984.968127068907 Step 89 | loss:0.07367828488349915 lr:8.133019056822304e-05 tokens_per_second_per_gpu:6718.355551127921 Step 90 | loss:0.03196815773844719 lr:8.07830737662829e-05 tokens_per_second_per_gpu:7108.768514639519 Step 91 | loss:0.0030364873819053173 lr:8.022995574311876e-05 tokens_per_second_per_gpu:7253.974145905998 Step 92 | loss:0.004121152684092522 lr:7.967094433018508e-05 tokens_per_second_per_gpu:7182.574466584476 Step 93 | loss:0.040841128677129745 lr:7.910614850786448e-05 tokens_per_second_per_gpu:6831.986022682465 Step 94 | loss:0.015266194008290768 lr:7.85356783842216e-05 tokens_per_second_per_gpu:7028.814409322565 Step 95 | loss:0.033349648118019104 lr:7.795964517353735e-05 tokens_per_second_per_gpu:7028.87237787936 Step 96 | loss:0.015786247327923775 lr:7.737816117462752e-05 tokens_per_second_per_gpu:7215.017325826529 Step 97 | loss:0.009660692885518074 lr:7.679133974894983e-05 tokens_per_second_per_gpu:7123.306742980729 Step 98 | loss:0.017200682312250137 lr:7.619929529850397e-05 tokens_per_second_per_gpu:6969.782176146097 Step 99 | loss:0.005454447120428085 lr:7.560214324352858e-05 tokens_per_second_per_gpu:6939.296325812087 Step 100 | loss:0.002147262217476964 lr:7.500000000000001e-05 tokens_per_second_per_gpu:3360.9421144850553 Step 101 | loss:0.018170207738876343 lr:7.439298295693665e-05 tokens_per_second_per_gpu:6910.697119977575 Step 102 | loss:0.010048959404230118 lr:7.378121045351378e-05 tokens_per_second_per_gpu:7035.344903759731 Step 103 | loss:0.00815110094845295 lr:7.316480175599309e-05 tokens_per_second_per_gpu:7140.4584283936665 Step 104 | loss:0.019582513719797134 lr:7.254387703447154e-05 tokens_per_second_per_gpu:6964.962200679986 Step 105 | loss:0.018017824739217758 lr:7.191855733945387e-05 tokens_per_second_per_gpu:7182.3637444095075 Step 106 | loss:0.04724618047475815 lr:7.128896457825364e-05 tokens_per_second_per_gpu:6758.968341945895 Step 107 | loss:0.014389678835868835 lr:7.06552214912271e-05 tokens_per_second_per_gpu:7124.011786273908 Step 108 | loss:0.011526512913405895 lr:7.001745162784477e-05 tokens_per_second_per_gpu:7116.612408459206 Step 109 | loss:0.012480936013162136 lr:6.937577932260515e-05 tokens_per_second_per_gpu:6878.61704506187 Step 110 | loss:0.0010600752430036664 lr:6.873032967079561e-05 tokens_per_second_per_gpu:7045.064667747545 Step 111 | loss:0.004784375429153442 lr:6.808122850410461e-05 tokens_per_second_per_gpu:6557.657502312459 Step 112 | loss:0.019856467843055725 lr:6.742860236609077e-05 tokens_per_second_per_gpu:6904.895863504724 Step 113 | loss:0.012991903349757195 lr:6.677257848751277e-05 tokens_per_second_per_gpu:7107.539875150528 Step 114 | loss:0.017099305987358093 lr:6.611328476152557e-05 tokens_per_second_per_gpu:7009.891193030596 Step 115 | loss:0.0074644009582698345 lr:6.545084971874738e-05 tokens_per_second_per_gpu:6988.578857436012 Step 116 | loss:0.012278374284505844 lr:6.478540250220234e-05 tokens_per_second_per_gpu:7139.085077860883 Step 117 | loss:0.016715947538614273 lr:6.411707284214384e-05 tokens_per_second_per_gpu:7115.862815901796 Step 118 | loss:0.016424275934696198 lr:6.344599103076329e-05 tokens_per_second_per_gpu:7044.058939789999 Step 119 | loss:0.00811388622969389 lr:6.277228789678953e-05 tokens_per_second_per_gpu:7128.45682789137 Step 120 | loss:0.014147808775305748 lr:6.209609477998338e-05 tokens_per_second_per_gpu:6894.745653805377 Step 121 | loss:0.012508543208241463 lr:6.141754350553279e-05 tokens_per_second_per_gpu:7027.752226569821 Step 122 | loss:0.01612221822142601 lr:6.073676635835317e-05 tokens_per_second_per_gpu:7044.995891064397 Step 123 | loss:0.019603030756115913 lr:6.005389605729824e-05 tokens_per_second_per_gpu:7226.967313265143 Step 124 | loss:0.02100265398621559 lr:5.9369065729286245e-05 tokens_per_second_per_gpu:7143.211426518775 Step 125 | loss:0.03236541897058487 lr:5.868240888334653e-05 tokens_per_second_per_gpu:6737.403093158592 Step 126 | loss:0.006584942806512117 lr:5.799405938459175e-05 tokens_per_second_per_gpu:6922.574621228511 Step 127 | loss:0.015065480954945087 lr:5.730415142812059e-05 tokens_per_second_per_gpu:7197.399924402272 Step 128 | loss:0.0009548875386826694 lr:5.661281951285613e-05 tokens_per_second_per_gpu:7026.773806074188 Step 129 | loss:0.002279198495671153 lr:5.5920198415325064e-05 tokens_per_second_per_gpu:7208.295339441702 Step 130 | loss:0.009627713821828365 lr:5.522642316338268e-05 tokens_per_second_per_gpu:7119.05394248697 Step 131 | loss:0.010664137080311775 lr:5.453162900988902e-05 tokens_per_second_per_gpu:6787.040976369206 Step 132 | loss:0.010823951102793217 lr:5.383595140634093e-05 tokens_per_second_per_gpu:7021.228900091697 Step 133 | loss:0.014284318313002586 lr:5.313952597646568e-05 tokens_per_second_per_gpu:7112.193418774278 Step 134 | loss:0.004829243291169405 lr:5.244248848978067e-05 tokens_per_second_per_gpu:7101.96843883215 Step 135 | loss:0.004080287180840969 lr:5.174497483512506e-05 tokens_per_second_per_gpu:7040.648785848527 Step 136 | loss:0.001923154341056943 lr:5.104712099416785e-05 tokens_per_second_per_gpu:7215.3713299672845 Step 137 | loss:0.009909180924296379 lr:5.034906301489808e-05 tokens_per_second_per_gpu:7012.110589334023 Step 138 | loss:0.02050059847533703 lr:4.965093698510193e-05 tokens_per_second_per_gpu:7041.78982555831 Step 139 | loss:0.0006666003027930856 lr:4.895287900583216e-05 tokens_per_second_per_gpu:6800.806688591347 Step 140 | loss:0.010814529843628407 lr:4.825502516487497e-05 tokens_per_second_per_gpu:6894.92458160544 Step 141 | loss:0.00033450269256718457 lr:4.755751151021934e-05 tokens_per_second_per_gpu:7142.120036027396 Step 142 | loss:0.012067615985870361 lr:4.6860474023534335e-05 tokens_per_second_per_gpu:7045.197366836282 Step 143 | loss:0.011188394390046597 lr:4.616404859365907e-05 tokens_per_second_per_gpu:7186.801855174912 Step 144 | loss:0.015594147145748138 lr:4.5468370990111006e-05 tokens_per_second_per_gpu:6804.129352638988 Step 145 | loss:0.011915506795048714 lr:4.477357683661734e-05 tokens_per_second_per_gpu:7156.8018199332155 Step 146 | loss:0.002682578284293413 lr:4.407980158467495e-05 tokens_per_second_per_gpu:6905.504588717535 Step 147 | loss:0.00039805861888453364 lr:4.3387180487143876e-05 tokens_per_second_per_gpu:7052.611802413409 Step 148 | loss:0.014465893618762493 lr:4.269584857187943e-05 tokens_per_second_per_gpu:7027.082463740024 Step 149 | loss:0.00042478408431634307 lr:4.2005940615408264e-05 tokens_per_second_per_gpu:7035.461219507918 Step 150 | loss:0.0019500120542943478 lr:4.131759111665349e-05 tokens_per_second_per_gpu:6978.6129166687615 Step 151 | loss:0.004563114605844021 lr:4.063093427071376e-05 tokens_per_second_per_gpu:7210.454708109026 Step 152 | loss:0.003091028891503811 lr:3.9946103942701777e-05 tokens_per_second_per_gpu:7014.003263540132 Step 153 | loss:0.004101311322301626 lr:3.926323364164684e-05 tokens_per_second_per_gpu:6975.072555853579 Step 154 | loss:0.004162991885095835 lr:3.858245649446721e-05 tokens_per_second_per_gpu:6979.778282938446 Step 155 | loss:0.0015350731555372477 lr:3.790390522001662e-05 tokens_per_second_per_gpu:7069.98795377558 Step 156 | loss:0.002492140047252178 lr:3.7227712103210486e-05 tokens_per_second_per_gpu:6845.7780673897805 Step 157 | loss:0.0028862059116363525 lr:3.655400896923672e-05 tokens_per_second_per_gpu:7019.565364987398 Step 158 | loss:0.005928779486566782 lr:3.588292715785617e-05 tokens_per_second_per_gpu:7039.880383322011 Step 159 | loss:0.01123222429305315 lr:3.5214597497797684e-05 tokens_per_second_per_gpu:7010.652651537868 Step 160 | loss:0.003346895333379507 lr:3.4549150281252636e-05 tokens_per_second_per_gpu:7028.334354092652 Step 161 | loss:0.005310109816491604 lr:3.388671523847445e-05 tokens_per_second_per_gpu:7021.74737436789 Step 162 | loss:0.014788877218961716 lr:3.322742151248725e-05 tokens_per_second_per_gpu:7024.122994169179 Step 163 | loss:0.0010468807304278016 lr:3.257139763390925e-05 tokens_per_second_per_gpu:7048.618312592172 Step 164 | loss:0.0032536033540964127 lr:3.1918771495895396e-05 tokens_per_second_per_gpu:7166.094823048589 Step 165 | loss:0.0037119174376130104 lr:3.12696703292044e-05 tokens_per_second_per_gpu:7208.803314222129 Step 166 | loss:0.00967511534690857 lr:3.062422067739485e-05 tokens_per_second_per_gpu:7038.960106910166 Step 167 | loss:0.002417252166196704 lr:2.9982548372155263e-05 tokens_per_second_per_gpu:7149.549958567676 Step 168 | loss:0.0011605611070990562 lr:2.934477850877292e-05 tokens_per_second_per_gpu:7150.224530603905 Step 169 | loss:0.01606067456305027 lr:2.8711035421746367e-05 tokens_per_second_per_gpu:7006.004091914204 Step 170 | loss:0.019335776567459106 lr:2.8081442660546125e-05 tokens_per_second_per_gpu:6743.041273848901 Step 171 | loss:0.013969815336167812 lr:2.7456122965528475e-05 tokens_per_second_per_gpu:7183.238849961411 Step 172 | loss:0.0050972760654985905 lr:2.6835198244006927e-05 tokens_per_second_per_gpu:7121.207868307566 Step 173 | loss:0.00046689348528161645 lr:2.6218789546486234e-05 tokens_per_second_per_gpu:7121.206241497244 Step 174 | loss:0.0037182781379669905 lr:2.560701704306336e-05 tokens_per_second_per_gpu:7005.875624244252 Step 175 | loss:0.0007327563944272697 lr:2.500000000000001e-05 tokens_per_second_per_gpu:7170.744538331616 Step 176 | loss:0.003626345656812191 lr:2.4397856756471432e-05 tokens_per_second_per_gpu:7168.350565385209 Step 177 | loss:0.001262823585420847 lr:2.3800704701496053e-05 tokens_per_second_per_gpu:6971.120566916748 Step 178 | loss:0.0003272329631727189 lr:2.3208660251050158e-05 tokens_per_second_per_gpu:7163.513006174859 Step 179 | loss:0.0006040202570147812 lr:2.2621838825372493e-05 tokens_per_second_per_gpu:7214.273905165422 Step 180 | loss:0.0005639924202114344 lr:2.2040354826462668e-05 tokens_per_second_per_gpu:7027.894572359003 Step 181 | loss:0.010329803451895714 lr:2.1464321615778422e-05 tokens_per_second_per_gpu:7045.308370966834 Step 182 | loss:0.011918301694095135 lr:2.0893851492135537e-05 tokens_per_second_per_gpu:6701.097862359639 Step 183 | loss:0.004067223519086838 lr:2.0329055669814934e-05 tokens_per_second_per_gpu:6947.691392667429 Step 184 | loss:0.005124547053128481 lr:1.977004425688126e-05 tokens_per_second_per_gpu:6982.239855250914 Step 185 | loss:0.009591927751898766 lr:1.9216926233717085e-05 tokens_per_second_per_gpu:6931.2701593074 Step 186 | loss:0.0008653715485706925 lr:1.866980943177699e-05 tokens_per_second_per_gpu:7018.961686708154 Step 187 | loss:8.394992619287223e-05 lr:1.8128800512565513e-05 tokens_per_second_per_gpu:7082.207787093639 Step 188 | loss:0.0031458581797778606 lr:1.7594004946843456e-05 tokens_per_second_per_gpu:6937.696923073706 Step 189 | loss:0.00012177869211882353 lr:1.7065526994065973e-05 tokens_per_second_per_gpu:7185.0293181766465 Step 190 | loss:0.005296279676258564 lr:1.6543469682057106e-05 tokens_per_second_per_gpu:6990.222660072567 Step 191 | loss:0.005614110268652439 lr:1.602793478692419e-05 tokens_per_second_per_gpu:6969.82106686335 Step 192 | loss:0.0014894187916070223 lr:1.551902281321651e-05 tokens_per_second_per_gpu:7050.02946525128 Step 193 | loss:0.0034519382752478123 lr:1.5016832974331724e-05 tokens_per_second_per_gpu:7213.07647180806 Step 194 | loss:0.002049605594947934 lr:1.4521463173173965e-05 tokens_per_second_per_gpu:7151.813732826173 Step 195 | loss:0.0011885460698977113 lr:1.4033009983067452e-05 tokens_per_second_per_gpu:7026.903252778914 Step 196 | loss:0.003957775887101889 lr:1.3551568628929434e-05 tokens_per_second_per_gpu:7190.565433158413 Step 197 | loss:0.0023394194431602955 lr:1.3077232968705805e-05 tokens_per_second_per_gpu:7054.137526989213 Step 198 | loss:0.007406462915241718 lr:1.2610095475073414e-05 tokens_per_second_per_gpu:6237.376227567439 Step 199 | loss:0.0037108855322003365 lr:1.2150247217412186e-05 tokens_per_second_per_gpu:6950.245902729725 Step 200 | loss:0.018784048035740852 lr:1.1697777844051105e-05 tokens_per_second_per_gpu:6828.477154943125 Step 201 | loss:0.006462921388447285 lr:1.1252775564791024e-05 tokens_per_second_per_gpu:7025.751252060694 Step 202 | loss:0.005570678971707821 lr:1.0815327133708015e-05 tokens_per_second_per_gpu:6812.050950850218 Step 203 | loss:0.0007799558225087821 lr:1.0385517832240471e-05 tokens_per_second_per_gpu:7138.269388253908 Step 204 | loss:0.0025837367866188288 lr:9.963431452563332e-06 tokens_per_second_per_gpu:7035.234610379868 Step 205 | loss:0.00010313013626728207 lr:9.549150281252633e-06 tokens_per_second_per_gpu:7224.423153607089 Step 206 | loss:0.003008185653015971 lr:9.142755083243576e-06 tokens_per_second_per_gpu:1410.5091497401224 Step 207 | loss:0.006032952107489109 lr:8.744325086085248e-06 tokens_per_second_per_gpu:7067.212967335043 Step 208 | loss:0.0023580272682011127 lr:8.353937964495029e-06 tokens_per_second_per_gpu:7124.432762405156 Step 209 | loss:8.034864731598645e-05 lr:7.971669825215788e-06 tokens_per_second_per_gpu:7079.666530656051 Step 210 | loss:0.0025893268175423145 lr:7.597595192178702e-06 tokens_per_second_per_gpu:6958.39764720153 Step 211 | loss:0.007696556858718395 lr:7.2317869919746705e-06 tokens_per_second_per_gpu:7153.818508351391 Step 212 | loss:0.0007245623855851591 lr:6.874316539637127e-06 tokens_per_second_per_gpu:7029.0349025828855 Step 213 | loss:0.005148134659975767 lr:6.52525352473905e-06 tokens_per_second_per_gpu:7190.2805032983115 Step 214 | loss:0.008537903428077698 lr:6.184665997806832e-06 tokens_per_second_per_gpu:7192.891443617083 Step 215 | loss:0.0019654566422104836 lr:5.852620357053651e-06 tokens_per_second_per_gpu:7031.497300424668 Step 216 | loss:0.01028459519147873 lr:5.529181335435124e-06 tokens_per_second_per_gpu:6883.236452711541 Step 217 | loss:0.0003279040683992207 lr:5.214411988029355e-06 tokens_per_second_per_gpu:7078.421900459986 Step 218 | loss:0.002245677402243018 lr:4.908373679744316e-06 tokens_per_second_per_gpu:6904.217659031088 Step 219 | loss:0.005061701405793428 lr:4.611126073354571e-06 tokens_per_second_per_gpu:7023.211640585226 Step 220 | loss:0.000236896492424421 lr:4.322727117869951e-06 tokens_per_second_per_gpu:7051.199372121648 Step 221 | loss:0.0027682026848196983 lr:4.043233037238281e-06 tokens_per_second_per_gpu:6899.3369784123615 Step 222 | loss:0.006109646521508694 lr:3.772698319384349e-06 tokens_per_second_per_gpu:7103.04651668349 Step 223 | loss:0.003355335909873247 lr:3.511175705587433e-06 tokens_per_second_per_gpu:6959.742765759275 Step 224 | loss:0.003359878435730934 lr:3.258716180199278e-06 tokens_per_second_per_gpu:6938.877199357771 Step 225 | loss:0.00030958783463574946 lr:3.0153689607045845e-06 tokens_per_second_per_gpu:7180.519549467356 Step 226 | loss:0.004164013545960188 lr:2.7811814881259503e-06 tokens_per_second_per_gpu:6853.822478113319 Step 227 | loss:0.0004354434204287827 lr:2.5561994177751737e-06 tokens_per_second_per_gpu:6473.990984472812 Step 228 | loss:0.007076476234942675 lr:2.340466610352654e-06 tokens_per_second_per_gpu:7009.939464522535 Step 229 | loss:0.004308910574764013 lr:2.134025123396638e-06 tokens_per_second_per_gpu:7193.523587571087 Step 230 | loss:0.001185770845040679 lr:1.9369152030840556e-06 tokens_per_second_per_gpu:6981.264503583417 Step 231 | loss:0.0033934449311345816 lr:1.7491752763844293e-06 tokens_per_second_per_gpu:7153.248875406134 Step 232 | loss:0.003365222131833434 lr:1.5708419435684462e-06 tokens_per_second_per_gpu:6987.8625964724715 Step 233 | loss:0.0022740548010915518 lr:1.4019499710726913e-06 tokens_per_second_per_gpu:7034.043825743859 Step 234 | loss:0.002102212980389595 lr:1.2425322847218368e-06 tokens_per_second_per_gpu:7010.556947094353 Step 235 | loss:0.004940610844641924 lr:1.0926199633097157e-06 tokens_per_second_per_gpu:7061.653426449669 Step 236 | loss:0.0006272595492191613 lr:9.522422325404235e-07 tokens_per_second_per_gpu:6960.9131314601345 Step 237 | loss:5.75081940041855e-05 lr:8.214264593307098e-07 tokens_per_second_per_gpu:7142.926265765877 Step 238 | loss:0.0007656093221157789 lr:7.001981464747565e-07 tokens_per_second_per_gpu:6907.323794327323 Step 239 | loss:0.0046600340865552425 lr:5.885809276723608e-07 tokens_per_second_per_gpu:7015.612619141917 Step 240 | loss:0.0014744503423571587 lr:4.865965629214819e-07 tokens_per_second_per_gpu:7146.955737905755 Step 241 | loss:0.00158807507250458 lr:3.9426493427611177e-07 tokens_per_second_per_gpu:6798.591246831102 Step 242 | loss:0.0003877896233461797 lr:3.1160404197018154e-07 tokens_per_second_per_gpu:7164.8670655455435 Step 243 | loss:0.0011666548671200871 lr:2.386300009084408e-07 tokens_per_second_per_gpu:7115.214635009554 Step 244 | loss:0.001739169587381184 lr:1.753570375247815e-07 tokens_per_second_per_gpu:7061.772227540088 Step 245 | loss:0.00041694685933180153 lr:1.2179748700879012e-07 tokens_per_second_per_gpu:7184.591946713477 Step 246 | loss:0.0017561351414769888 lr:7.796179090094891e-08 tokens_per_second_per_gpu:7017.277191759309 Step 247 | loss:0.002764887409284711 lr:4.385849505708084e-08 tokens_per_second_per_gpu:7024.549347665276 Step 248 | loss:9.420169953955337e-05 lr:1.949424798228239e-08 tokens_per_second_per_gpu:7218.009420305428 Step 249 | loss:0.0017503915587440133 lr:4.873799534788059e-09 tokens_per_second_per_gpu:6997.71327545474 Step 250 | loss:0.0009583075880073011 lr:0.0 tokens_per_second_per_gpu:7115.133492354002