Step 1 | loss:0.012119091115891933 lr:7.142857142857143e-06 tokens_per_second_per_gpu:3814.109546763372 Step 2 | loss:0.011553052812814713 lr:1.4285714285714285e-05 tokens_per_second_per_gpu:7130.831568945052 Step 3 | loss:0.013801290653645992 lr:2.1428571428571428e-05 tokens_per_second_per_gpu:7113.181224988439 Step 4 | loss:0.005418441724032164 lr:2.857142857142857e-05 tokens_per_second_per_gpu:3188.668215092602 Step 5 | loss:0.015122749842703342 lr:3.571428571428572e-05 tokens_per_second_per_gpu:3059.1521828712052 Step 6 | loss:0.011049823835492134 lr:4.2857142857142856e-05 tokens_per_second_per_gpu:3179.891303178817 Step 7 | loss:0.009920629672706127 lr:5e-05 tokens_per_second_per_gpu:3888.907696427405 Step 8 | loss:0.013433997519314289 lr:5.714285714285714e-05 tokens_per_second_per_gpu:7014.599863074784 Step 9 | loss:0.018506748601794243 lr:6.428571428571429e-05 tokens_per_second_per_gpu:7146.785686591416 Step 10 | loss:0.014613879844546318 lr:7.142857142857143e-05 tokens_per_second_per_gpu:7051.710815895897 Step 11 | loss:0.01269792951643467 lr:7.857142857142858e-05 tokens_per_second_per_gpu:7037.967735856792 Step 12 | loss:0.01168736256659031 lr:8.571428571428571e-05 tokens_per_second_per_gpu:2960.2812415149438 Step 13 | loss:0.03740984573960304 lr:9.285714285714286e-05 tokens_per_second_per_gpu:7032.041561919136 Step 14 | loss:0.003825670573860407 lr:0.0001 tokens_per_second_per_gpu:7089.788949455485 Step 15 | loss:0.005892462097108364 lr:9.998540070400966e-05 tokens_per_second_per_gpu:3027.176952210542 Step 16 | loss:0.007911288179457188 lr:9.994161134161634e-05 tokens_per_second_per_gpu:7106.673870408529 Step 17 | loss:0.013042236678302288 lr:9.986865748457457e-05 tokens_per_second_per_gpu:2954.675082186942 Step 18 | loss:0.0027721712831407785 lr:9.976658173588244e-05 tokens_per_second_per_gpu:7118.7396724283435 Step 19 | loss:0.0026670177467167377 lr:9.96354437049027e-05 tokens_per_second_per_gpu:7107.164009287921 Step 20 | loss:0.024779273197054863 lr:9.947531997255256e-05 tokens_per_second_per_gpu:7025.857667503761 Step 21 | loss:0.001324935001321137 lr:9.928630404658255e-05 tokens_per_second_per_gpu:7066.354651963818 Step 22 | loss:0.0027123300824314356 lr:9.906850630697068e-05 tokens_per_second_per_gpu:7025.817106423312 Step 23 | loss:0.002099835081025958 lr:9.882205394146361e-05 tokens_per_second_per_gpu:7085.985540528094 Step 24 | loss:0.0011380024952813983 lr:9.85470908713026e-05 tokens_per_second_per_gpu:7075.358689544146 Step 25 | loss:0.0019947304390370846 lr:9.824377766717759e-05 tokens_per_second_per_gpu:7142.851979973636 Step 26 | loss:0.0019393203547224402 lr:9.791229145545831e-05 tokens_per_second_per_gpu:7123.975629155879 Step 27 | loss:0.00910987239331007 lr:9.755282581475769e-05 tokens_per_second_per_gpu:6837.143454714966 Step 28 | loss:0.00015504243492614478 lr:9.716559066288715e-05 tokens_per_second_per_gpu:7075.826288146152 Step 29 | loss:0.0016415498685091734 lr:9.675081213427076e-05 tokens_per_second_per_gpu:7097.2785193999625 Step 30 | loss:0.0007980477530509233 lr:9.630873244788883e-05 tokens_per_second_per_gpu:7107.204682113286 Step 31 | loss:0.0009702115203253925 lr:9.583960976582913e-05 tokens_per_second_per_gpu:7095.832528468289 Step 32 | loss:0.0011159790446981788 lr:9.534371804252728e-05 tokens_per_second_per_gpu:7066.424419792196 Step 33 | loss:0.002856888808310032 lr:9.482134686478519e-05 tokens_per_second_per_gpu:7126.9597307011345 Step 34 | loss:0.006425188388675451 lr:9.42728012826605e-05 tokens_per_second_per_gpu:7070.4921363577005 Step 35 | loss:0.0036817521322518587 lr:9.36984016313259e-05 tokens_per_second_per_gpu:7068.711595543263 Step 36 | loss:2.0803146981052123e-05 lr:9.309848334400246e-05 tokens_per_second_per_gpu:7147.826367380491 Step 37 | loss:0.0007794692064635456 lr:9.247339675607605e-05 tokens_per_second_per_gpu:7088.854658050239 Step 38 | loss:7.533848111052066e-05 lr:9.182350690051133e-05 tokens_per_second_per_gpu:7052.107284074701 Step 39 | loss:0.0030352130997925997 lr:9.114919329468282e-05 tokens_per_second_per_gpu:7048.952398291872 Step 40 | loss:0.0007049605483189225 lr:9.045084971874738e-05 tokens_per_second_per_gpu:7077.549912030579 Step 41 | loss:0.0022499251645058393 lr:8.972888398568772e-05 tokens_per_second_per_gpu:7039.392920819287 Step 42 | loss:0.0003144382790196687 lr:8.898371770316111e-05 tokens_per_second_per_gpu:7087.037891781897 Step 43 | loss:0.0019024431239813566 lr:8.821578602729242e-05 tokens_per_second_per_gpu:7127.876518453258 Step 44 | loss:7.544802065240219e-05 lr:8.742553740855506e-05 tokens_per_second_per_gpu:7084.6675484921 Step 45 | loss:0.0005483488203026354 lr:8.661343332988869e-05 tokens_per_second_per_gpu:7079.429377242723 Step 46 | loss:9.948270189852337e-07 lr:8.577994803720606e-05 tokens_per_second_per_gpu:7055.490275491626 Step 47 | loss:0.0008776985923759639 lr:8.492556826244687e-05 tokens_per_second_per_gpu:7043.101220416072 Step 48 | loss:1.042959979713487e-06 lr:8.405079293933986e-05 tokens_per_second_per_gpu:7091.349099645261 Step 49 | loss:0.009083736687898636 lr:8.315613291203976e-05 tokens_per_second_per_gpu:7088.966769066027 Step 50 | loss:4.483600150706479e-06 lr:8.224211063680853e-05 tokens_per_second_per_gpu:7128.708147538198 Step 51 | loss:1.1333786460454576e-05 lr:8.130925987691569e-05 tokens_per_second_per_gpu:7061.544795524407 Step 52 | loss:0.0031913018319755793 lr:8.035812539093557e-05 tokens_per_second_per_gpu:7082.614770476553 Step 53 | loss:6.899006984895095e-05 lr:7.938926261462366e-05 tokens_per_second_per_gpu:7045.338035960297 Step 54 | loss:0.0005698605673387647 lr:7.840323733655778e-05 tokens_per_second_per_gpu:7135.3689963852 Step 55 | loss:4.603382876666728e-06 lr:7.740062536773352e-05 tokens_per_second_per_gpu:7069.541494261048 Step 56 | loss:8.128891204250976e-05 lr:7.638201220530665e-05 tokens_per_second_per_gpu:6317.910539457231 Step 57 | loss:0.0007562857354059815 lr:7.534799269067953e-05 tokens_per_second_per_gpu:7061.878165643703 Step 58 | loss:8.829722355585545e-05 lr:7.42991706621303e-05 tokens_per_second_per_gpu:7121.8050482426925 Step 59 | loss:0.000968162261415273 lr:7.323615860218843e-05 tokens_per_second_per_gpu:7099.128115295508 Step 60 | loss:0.000641241145785898 lr:7.215957727996207e-05 tokens_per_second_per_gpu:7046.899127564777 Step 61 | loss:6.959816528251395e-05 lr:7.107005538862646e-05 tokens_per_second_per_gpu:7114.4496236746745 Step 62 | loss:2.526294792914996e-06 lr:6.996822917828477e-05 tokens_per_second_per_gpu:7106.531241379665 Step 63 | loss:2.5891662517096847e-05 lr:6.885474208441603e-05 tokens_per_second_per_gpu:7054.33745453767 Step 64 | loss:0.003994029946625233 lr:6.773024435212678e-05 tokens_per_second_per_gpu:7066.339275084743 Step 65 | loss:3.336900408612564e-05 lr:6.659539265642643e-05 tokens_per_second_per_gpu:7046.200797255235 Step 66 | loss:8.527242243872024e-06 lr:6.545084971874738e-05 tokens_per_second_per_gpu:7120.182407914635 Step 67 | loss:0.0026279750745743513 lr:6.429728391993446e-05 tokens_per_second_per_gpu:7081.230194660598 Step 68 | loss:0.0001791453832993284 lr:6.313536890992935e-05 tokens_per_second_per_gpu:7114.908020569847 Step 69 | loss:0.0008048127638176084 lr:6.19657832143779e-05 tokens_per_second_per_gpu:7041.518085241422 Step 70 | loss:9.759585373103619e-05 lr:6.078920983839031e-05 tokens_per_second_per_gpu:7149.829872651354 Step 71 | loss:0.00104529841337353 lr:5.960633586768543e-05 tokens_per_second_per_gpu:7068.948261459653 Step 72 | loss:1.738629725878127e-05 lr:5.841785206735192e-05 tokens_per_second_per_gpu:7116.368722034808 Step 73 | loss:6.24505992163904e-06 lr:5.7224452478461064e-05 tokens_per_second_per_gpu:7049.132040607147 Step 74 | loss:2.332511257918668e-06 lr:5.602683401276615e-05 tokens_per_second_per_gpu:7015.825530892338 Step 75 | loss:0.00013803700858261436 lr:5.482569604572576e-05 tokens_per_second_per_gpu:7070.1066095285005 Step 76 | loss:0.0006583340582437813 lr:5.3621740008088126e-05 tokens_per_second_per_gpu:7125.108712325812 Step 77 | loss:2.839632361428812e-05 lr:5.2415668976275355e-05 tokens_per_second_per_gpu:7137.525929801437 Step 78 | loss:0.0005978906410746276 lr:5.1208187261806615e-05 tokens_per_second_per_gpu:7125.720671135523 Step 79 | loss:0.00010161939280806109 lr:5e-05 tokens_per_second_per_gpu:7156.515659113592 Step 80 | loss:8.680938481120393e-05 lr:4.87918127381934e-05 tokens_per_second_per_gpu:7147.903387680116 Step 81 | loss:0.00015696053742431104 lr:4.758433102372466e-05 tokens_per_second_per_gpu:7081.615832937164 Step 82 | loss:5.956782842986286e-05 lr:4.6378259991911886e-05 tokens_per_second_per_gpu:7033.076717911305 Step 83 | loss:9.936579772329424e-07 lr:4.5174303954274244e-05 tokens_per_second_per_gpu:6474.560371564301 Step 84 | loss:1.4979253819547012e-06 lr:4.397316598723385e-05 tokens_per_second_per_gpu:7046.8145984523135 Step 85 | loss:1.0097635822603479e-05 lr:4.277554752153895e-05 tokens_per_second_per_gpu:7089.426175115935 Step 86 | loss:2.935175143647939e-05 lr:4.1582147932648074e-05 tokens_per_second_per_gpu:7124.629024127328 Step 87 | loss:3.4928029890579637e-07 lr:4.039366413231458e-05 tokens_per_second_per_gpu:7104.853837097104 Step 88 | loss:0.00021305543486960232 lr:3.92107901616097e-05 tokens_per_second_per_gpu:7140.022650768426 Step 89 | loss:7.218774953798857e-06 lr:3.803421678562213e-05 tokens_per_second_per_gpu:7059.525547093815 Step 90 | loss:0.00028346473118290305 lr:3.6864631090070655e-05 tokens_per_second_per_gpu:7043.072002634934 Step 91 | loss:0.0015356699004769325 lr:3.570271608006555e-05 tokens_per_second_per_gpu:7056.09113411922 Step 92 | loss:6.349744126055157e-06 lr:3.4549150281252636e-05 tokens_per_second_per_gpu:7121.561914040893 Step 93 | loss:7.992779501364566e-06 lr:3.340460734357359e-05 tokens_per_second_per_gpu:7093.439091614007 Step 94 | loss:0.0014136090176180005 lr:3.226975564787322e-05 tokens_per_second_per_gpu:7033.490081381828 Step 95 | loss:0.0008577441913075745 lr:3.114525791558398e-05 tokens_per_second_per_gpu:7116.233704952606 Step 96 | loss:2.282523382746149e-06 lr:3.003177082171523e-05 tokens_per_second_per_gpu:7041.083235460897 Step 97 | loss:8.984784653875977e-05 lr:2.8929944611373554e-05 tokens_per_second_per_gpu:7061.95522406775 Step 98 | loss:0.00031662636320106685 lr:2.784042272003794e-05 tokens_per_second_per_gpu:7084.839198324344 Step 99 | loss:1.365731577607221e-06 lr:2.6763841397811573e-05 tokens_per_second_per_gpu:7108.838910275063 Step 100 | loss:3.3512499157950515e-06 lr:2.57008293378697e-05 tokens_per_second_per_gpu:7104.074579502289 Step 101 | loss:3.066375484195305e-06 lr:2.4652007309320498e-05 tokens_per_second_per_gpu:7113.836230909404 Step 102 | loss:1.1841842933790758e-05 lr:2.361798779469336e-05 tokens_per_second_per_gpu:7063.114828764634 Step 103 | loss:2.369401954638306e-05 lr:2.259937463226651e-05 tokens_per_second_per_gpu:7067.3025764319145 Step 104 | loss:0.0004075327597092837 lr:2.1596762663442218e-05 tokens_per_second_per_gpu:7034.967991324606 Step 105 | loss:0.0008435581694357097 lr:2.061073738537635e-05 tokens_per_second_per_gpu:7144.273990744661 Step 106 | loss:5.230464466876583e-06 lr:1.9641874609064443e-05 tokens_per_second_per_gpu:7144.998969591235 Step 107 | loss:0.0005431257886812091 lr:1.8690740123084316e-05 tokens_per_second_per_gpu:7139.374673241931 Step 108 | loss:0.00018714623001869768 lr:1.7757889363191483e-05 tokens_per_second_per_gpu:7132.951369158544 Step 109 | loss:2.9998625450389227e-06 lr:1.684386708796025e-05 tokens_per_second_per_gpu:7074.672841881122 Step 110 | loss:2.7875748855876736e-06 lr:1.5949207060660138e-05 tokens_per_second_per_gpu:7074.658306715045 Step 111 | loss:0.0001888033002614975 lr:1.5074431737553157e-05 tokens_per_second_per_gpu:6354.8216725283955 Step 112 | loss:6.623376248171553e-05 lr:1.422005196279395e-05 tokens_per_second_per_gpu:7100.209156303015 Step 113 | loss:9.848234867604333e-07 lr:1.338656667011134e-05 tokens_per_second_per_gpu:7083.334957950748 Step 114 | loss:0.00021622740314342082 lr:1.257446259144494e-05 tokens_per_second_per_gpu:7014.308838804131 Step 115 | loss:1.919947635542485e-06 lr:1.178421397270758e-05 tokens_per_second_per_gpu:7150.549839110622 Step 116 | loss:4.3732185872613627e-07 lr:1.1016282296838887e-05 tokens_per_second_per_gpu:7057.195190189562 Step 117 | loss:2.2028732473700074e-06 lr:1.0271116014312293e-05 tokens_per_second_per_gpu:7131.738978650961 Step 118 | loss:3.6439425912249135e-06 lr:9.549150281252633e-06 tokens_per_second_per_gpu:7136.013774537251 Step 119 | loss:0.00025664237909950316 lr:8.850806705317183e-06 tokens_per_second_per_gpu:7130.744206948473 Step 120 | loss:0.00027411564951762557 lr:8.176493099488663e-06 tokens_per_second_per_gpu:7069.481056649482 Step 121 | loss:2.0956358639523387e-06 lr:7.526603243923957e-06 tokens_per_second_per_gpu:7123.733312009388 Step 122 | loss:3.5969069358543493e-06 lr:6.901516655997536e-06 tokens_per_second_per_gpu:7123.737976002775 Step 123 | loss:3.155369995511137e-06 lr:6.301598368674105e-06 tokens_per_second_per_gpu:7142.972958159509 Step 124 | loss:3.879843006870942e-06 lr:5.727198717339511e-06 tokens_per_second_per_gpu:7123.3185706103095 Step 125 | loss:6.772069127691793e-07 lr:5.178653135214812e-06 tokens_per_second_per_gpu:7097.364057749962 Step 126 | loss:2.418425310679595e-06 lr:4.65628195747273e-06 tokens_per_second_per_gpu:7111.9160391293735 Step 127 | loss:9.285825399274472e-06 lr:4.16039023417088e-06 tokens_per_second_per_gpu:7039.884659902434 Step 128 | loss:7.68833956499293e-07 lr:3.691267552111183e-06 tokens_per_second_per_gpu:7027.790596411767 Step 129 | loss:6.181527623994043e-06 lr:3.249187865729264e-06 tokens_per_second_per_gpu:7118.228702099086 Step 130 | loss:1.626073571969755e-05 lr:2.8344093371128424e-06 tokens_per_second_per_gpu:7125.385171690377 Step 131 | loss:0.00020055565983057022 lr:2.4471741852423237e-06 tokens_per_second_per_gpu:7034.373931685716 Step 132 | loss:1.7251984445465496e-06 lr:2.087708544541689e-06 tokens_per_second_per_gpu:7074.211808874259 Step 133 | loss:1.6027610399760306e-05 lr:1.7562223328224325e-06 tokens_per_second_per_gpu:7039.020086158657 Step 134 | loss:3.0330897970998194e-06 lr:1.4529091286973995e-06 tokens_per_second_per_gpu:7071.142562800441 Step 135 | loss:0.0001658340188441798 lr:1.1779460585363944e-06 tokens_per_second_per_gpu:7083.527818605079 Step 136 | loss:0.0009153854916803539 lr:9.314936930293283e-07 tokens_per_second_per_gpu:7139.686305368988 Step 137 | loss:4.302889919927111e-06 lr:7.136959534174592e-07 tokens_per_second_per_gpu:7124.772545508706 Step 138 | loss:0.00012289360165596008 lr:5.246800274474439e-07 tokens_per_second_per_gpu:7026.661756000606 Step 139 | loss:2.889929419325199e-05 lr:3.6455629509730136e-07 tokens_per_second_per_gpu:7049.279181762225 Step 140 | loss:0.0002541815920267254 lr:2.334182641175686e-07 tokens_per_second_per_gpu:6425.5923814113185 Step 141 | loss:0.00026304752100259066 lr:1.3134251542544774e-07 tokens_per_second_per_gpu:7103.92764922153 Step 142 | loss:1.547430656501092e-06 lr:5.838865838366792e-08 tokens_per_second_per_gpu:7065.314797140473 Step 143 | loss:4.385357442515669e-06 lr:1.4599295990352924e-08 tokens_per_second_per_gpu:7068.63673587248 Step 144 | loss:1.6221850955844275e-06 lr:0.0 tokens_per_second_per_gpu:7043.751456680917