| Step 1 | loss:0.11346574872732162 lr:7.142857142857143e-06 tokens_per_second_per_gpu:2972.0191647566767 | |
| Step 2 | loss:0.07889757305383682 lr:1.4285714285714285e-05 tokens_per_second_per_gpu:7177.5571122817155 | |
| Step 3 | loss:0.05025334656238556 lr:2.1428571428571428e-05 tokens_per_second_per_gpu:2993.782996932647 | |
| Step 4 | loss:0.07228319346904755 lr:2.857142857142857e-05 tokens_per_second_per_gpu:2186.5355685119766 | |
| Step 5 | loss:0.04655948653817177 lr:3.571428571428572e-05 tokens_per_second_per_gpu:6854.719727963997 | |
| Step 6 | loss:0.03788962587714195 lr:4.2857142857142856e-05 tokens_per_second_per_gpu:2521.6255587728597 | |
| Step 7 | loss:0.06608358025550842 lr:5e-05 tokens_per_second_per_gpu:7197.850502959648 | |
| Step 8 | loss:0.2159593105316162 lr:5.714285714285714e-05 tokens_per_second_per_gpu:6921.345901090375 | |
| Step 9 | loss:0.1369064301252365 lr:6.428571428571429e-05 tokens_per_second_per_gpu:7176.276612071919 | |
| Step 10 | loss:0.15427464246749878 lr:7.142857142857143e-05 tokens_per_second_per_gpu:6948.846774232478 | |
| Step 11 | loss:0.13343018293380737 lr:7.857142857142858e-05 tokens_per_second_per_gpu:6935.190459377111 | |
| Step 12 | loss:0.035034410655498505 lr:8.571428571428571e-05 tokens_per_second_per_gpu:6868.206840590692 | |
| Step 13 | loss:0.03599270433187485 lr:9.285714285714286e-05 tokens_per_second_per_gpu:6838.625115141094 | |
| Step 14 | loss:0.05177108943462372 lr:0.0001 tokens_per_second_per_gpu:7126.619678011884 | |
| Step 15 | loss:0.21989037096500397 lr:9.998540070400966e-05 tokens_per_second_per_gpu:6817.999878521229 | |
| Step 16 | loss:0.008901139721274376 lr:9.994161134161634e-05 tokens_per_second_per_gpu:2519.6241741386166 | |
| Step 17 | loss:0.036226995289325714 lr:9.986865748457457e-05 tokens_per_second_per_gpu:6955.057506813304 | |
| Step 18 | loss:0.09318801015615463 lr:9.976658173588244e-05 tokens_per_second_per_gpu:7203.949158260739 | |
| Step 19 | loss:0.02981800213456154 lr:9.96354437049027e-05 tokens_per_second_per_gpu:7143.589806371735 | |
| Step 20 | loss:0.10015814751386642 lr:9.947531997255256e-05 tokens_per_second_per_gpu:6925.869330396556 | |
| Step 21 | loss:0.005274234339594841 lr:9.928630404658255e-05 tokens_per_second_per_gpu:6897.022333342156 | |
| Step 22 | loss:0.003310987027361989 lr:9.906850630697068e-05 tokens_per_second_per_gpu:6871.592030201317 | |
| Step 23 | loss:0.018725872039794922 lr:9.882205394146361e-05 tokens_per_second_per_gpu:7137.9436633853675 | |
| Step 24 | loss:0.004897508304566145 lr:9.85470908713026e-05 tokens_per_second_per_gpu:6937.5434541781115 | |
| Step 25 | loss:0.04525185003876686 lr:9.824377766717759e-05 tokens_per_second_per_gpu:7166.07345208534 | |
| Step 26 | loss:0.010056343860924244 lr:9.791229145545831e-05 tokens_per_second_per_gpu:7178.674286165042 | |
| Step 27 | loss:0.015235690400004387 lr:9.755282581475769e-05 tokens_per_second_per_gpu:6442.9467783421505 | |
| Step 28 | loss:0.005478620063513517 lr:9.716559066288715e-05 tokens_per_second_per_gpu:6895.180925771291 | |
| Step 29 | loss:0.014502967707812786 lr:9.675081213427076e-05 tokens_per_second_per_gpu:6971.493613254307 | |
| Step 30 | loss:0.11518469452857971 lr:9.630873244788883e-05 tokens_per_second_per_gpu:6848.292022744467 | |
| Step 31 | loss:0.1646685153245926 lr:9.583960976582913e-05 tokens_per_second_per_gpu:2038.6841880600477 | |
| Step 32 | loss:0.016328683122992516 lr:9.534371804252728e-05 tokens_per_second_per_gpu:6850.151801163364 | |
| Step 33 | loss:0.004173299763351679 lr:9.482134686478519e-05 tokens_per_second_per_gpu:7138.483952825901 | |
| Step 34 | loss:0.12218522280454636 lr:9.42728012826605e-05 tokens_per_second_per_gpu:6946.798440145836 | |
| Step 35 | loss:0.010880785062909126 lr:9.36984016313259e-05 tokens_per_second_per_gpu:6978.924539841603 | |
| Step 36 | loss:0.1453608274459839 lr:9.309848334400246e-05 tokens_per_second_per_gpu:7153.520544522646 | |
| Step 37 | loss:0.044476769864559174 lr:9.247339675607605e-05 tokens_per_second_per_gpu:7144.100981973014 | |
| Step 38 | loss:0.05347314104437828 lr:9.182350690051133e-05 tokens_per_second_per_gpu:6938.792094828048 | |
| Step 39 | loss:0.005342620890587568 lr:9.114919329468282e-05 tokens_per_second_per_gpu:6973.986105976239 | |
| Step 40 | loss:0.00919003039598465 lr:9.045084971874738e-05 tokens_per_second_per_gpu:7110.25646288862 | |
| Step 41 | loss:0.005706812255084515 lr:8.972888398568772e-05 tokens_per_second_per_gpu:6925.833377422499 | |
| Step 42 | loss:0.006096248980611563 lr:8.898371770316111e-05 tokens_per_second_per_gpu:7089.225261523368 | |
| Step 43 | loss:0.0057297078892588615 lr:8.821578602729242e-05 tokens_per_second_per_gpu:7136.646665907186 | |
| Step 44 | loss:0.011234967969357967 lr:8.742553740855506e-05 tokens_per_second_per_gpu:7099.767980528127 | |
| Step 45 | loss:0.07386242598295212 lr:8.661343332988869e-05 tokens_per_second_per_gpu:7115.82881401822 | |
| Step 46 | loss:0.008051897399127483 lr:8.577994803720606e-05 tokens_per_second_per_gpu:6884.145323461232 | |
| Step 47 | loss:0.0015358994714915752 lr:8.492556826244687e-05 tokens_per_second_per_gpu:6960.614414546227 | |
| Step 48 | loss:0.03645475208759308 lr:8.405079293933986e-05 tokens_per_second_per_gpu:6972.211196309202 | |
| Step 49 | loss:0.011261802166700363 lr:8.315613291203976e-05 tokens_per_second_per_gpu:6845.063230297769 | |
| Step 50 | loss:0.001811921945773065 lr:8.224211063680853e-05 tokens_per_second_per_gpu:7122.640698995134 | |
| Step 51 | loss:0.00268059060908854 lr:8.130925987691569e-05 tokens_per_second_per_gpu:6954.99146905551 | |
| Step 52 | loss:0.002204248448833823 lr:8.035812539093557e-05 tokens_per_second_per_gpu:7161.809108882757 | |
| Step 53 | loss:0.0005680735921487212 lr:7.938926261462366e-05 tokens_per_second_per_gpu:6801.895635128145 | |
| Step 54 | loss:0.0016335092950612307 lr:7.840323733655778e-05 tokens_per_second_per_gpu:7178.984894024924 | |
| Step 55 | loss:0.0013489145785570145 lr:7.740062536773352e-05 tokens_per_second_per_gpu:7128.682562332135 | |
| Step 56 | loss:0.0010575939668342471 lr:7.638201220530665e-05 tokens_per_second_per_gpu:5943.836685822171 | |
| Step 57 | loss:0.02951529435813427 lr:7.534799269067953e-05 tokens_per_second_per_gpu:6822.880329848946 | |
| Step 58 | loss:0.001098968437872827 lr:7.42991706621303e-05 tokens_per_second_per_gpu:7141.43660851316 | |
| Step 59 | loss:0.00379947223700583 lr:7.323615860218843e-05 tokens_per_second_per_gpu:7159.267053327752 | |
| Step 60 | loss:0.003029614919796586 lr:7.215957727996207e-05 tokens_per_second_per_gpu:6935.953618594634 | |
| Step 61 | loss:0.0006757461815141141 lr:7.107005538862646e-05 tokens_per_second_per_gpu:7167.048860443881 | |
| Step 62 | loss:0.045060474425554276 lr:6.996822917828477e-05 tokens_per_second_per_gpu:7102.242553716666 | |
| Step 63 | loss:0.05299106240272522 lr:6.885474208441603e-05 tokens_per_second_per_gpu:6875.5008926033215 | |
| Step 64 | loss:0.0006223469390533864 lr:6.773024435212678e-05 tokens_per_second_per_gpu:7054.080709332995 | |
| Step 65 | loss:0.0007855833973735571 lr:6.659539265642643e-05 tokens_per_second_per_gpu:6940.620314678693 | |
| Step 66 | loss:0.0009436701075173914 lr:6.545084971874738e-05 tokens_per_second_per_gpu:7190.005082057359 | |
| Step 67 | loss:0.00027969584334641695 lr:6.429728391993446e-05 tokens_per_second_per_gpu:6964.268752054641 | |
| Step 68 | loss:0.05008869990706444 lr:6.313536890992935e-05 tokens_per_second_per_gpu:7208.630869844277 | |
| Step 69 | loss:0.002126579638570547 lr:6.19657832143779e-05 tokens_per_second_per_gpu:6897.463108390952 | |
| Step 70 | loss:0.0007595796487294137 lr:6.078920983839031e-05 tokens_per_second_per_gpu:7171.329004788599 | |
| Step 71 | loss:0.0006084630731493235 lr:5.960633586768543e-05 tokens_per_second_per_gpu:7137.56891545468 | |
| Step 72 | loss:0.016900092363357544 lr:5.841785206735192e-05 tokens_per_second_per_gpu:7120.660073207742 | |
| Step 73 | loss:0.00041904818499460816 lr:5.7224452478461064e-05 tokens_per_second_per_gpu:6923.43071504541 | |
| Step 74 | loss:0.0010331397643312812 lr:5.602683401276615e-05 tokens_per_second_per_gpu:6937.2015450270055 | |
| Step 75 | loss:0.0007437799358740449 lr:5.482569604572576e-05 tokens_per_second_per_gpu:7121.04438841308 | |
| Step 76 | loss:0.00046076675062067807 lr:5.3621740008088126e-05 tokens_per_second_per_gpu:7110.265710589559 | |
| Step 77 | loss:0.0010380077874287963 lr:5.2415668976275355e-05 tokens_per_second_per_gpu:7169.6430508569 | |
| Step 78 | loss:0.00019121391233056784 lr:5.1208187261806615e-05 tokens_per_second_per_gpu:7150.981486900063 | |
| Step 79 | loss:0.01940959133207798 lr:5e-05 tokens_per_second_per_gpu:7128.39478638199 | |
| Step 80 | loss:0.0004266287724021822 lr:4.87918127381934e-05 tokens_per_second_per_gpu:7188.6661165139585 | |
| Step 81 | loss:0.0007839715108275414 lr:4.758433102372466e-05 tokens_per_second_per_gpu:7108.087014639719 | |
| Step 82 | loss:0.00037887843791395426 lr:4.6378259991911886e-05 tokens_per_second_per_gpu:6913.980809098169 | |
| Step 83 | loss:0.0002763587108347565 lr:4.5174303954274244e-05 tokens_per_second_per_gpu:5575.805299210902 | |
| Step 84 | loss:0.0008857405628077686 lr:4.397316598723385e-05 tokens_per_second_per_gpu:6861.486924190542 | |
| Step 85 | loss:0.0002895248762797564 lr:4.277554752153895e-05 tokens_per_second_per_gpu:7147.5850785828625 | |
| Step 86 | loss:0.00029322714544832706 lr:4.1582147932648074e-05 tokens_per_second_per_gpu:7176.712240982264 | |
| Step 87 | loss:0.00012120822793804109 lr:4.039366413231458e-05 tokens_per_second_per_gpu:6863.554237648201 | |
| Step 88 | loss:8.458917000098154e-05 lr:3.92107901616097e-05 tokens_per_second_per_gpu:7227.1895264208015 | |
| Step 89 | loss:9.201384818879887e-05 lr:3.803421678562213e-05 tokens_per_second_per_gpu:2031.110524620846 | |
| Step 90 | loss:0.015644844621419907 lr:3.6864631090070655e-05 tokens_per_second_per_gpu:6864.6759935678865 | |
| Step 91 | loss:8.025140414247289e-05 lr:3.570271608006555e-05 tokens_per_second_per_gpu:6893.624886862714 | |
| Step 92 | loss:0.00033437059028074145 lr:3.4549150281252636e-05 tokens_per_second_per_gpu:7161.939299868398 | |
| Step 93 | loss:0.0002588052302598953 lr:3.340460734357359e-05 tokens_per_second_per_gpu:6903.426846461385 | |
| Step 94 | loss:0.0002588576462585479 lr:3.226975564787322e-05 tokens_per_second_per_gpu:6972.470590505708 | |
| Step 95 | loss:0.017733996734023094 lr:3.114525791558398e-05 tokens_per_second_per_gpu:7125.052097315373 | |
| Step 96 | loss:0.0036655820440500975 lr:3.003177082171523e-05 tokens_per_second_per_gpu:6965.4403306990125 | |
| Step 97 | loss:6.619201303692535e-05 lr:2.8929944611373554e-05 tokens_per_second_per_gpu:6969.752933679744 | |
| Step 98 | loss:0.00019116754992865026 lr:2.784042272003794e-05 tokens_per_second_per_gpu:7148.33585488109 | |
| Step 99 | loss:0.00015488200006075203 lr:2.6763841397811573e-05 tokens_per_second_per_gpu:6975.506692967312 | |
| Step 100 | loss:0.0002998733543790877 lr:2.57008293378697e-05 tokens_per_second_per_gpu:7207.112664339563 | |
| Step 101 | loss:0.00046510566608048975 lr:2.4652007309320498e-05 tokens_per_second_per_gpu:7181.07322662876 | |
| Step 102 | loss:0.00511598726734519 lr:2.361798779469336e-05 tokens_per_second_per_gpu:6929.688393636525 | |
| Step 103 | loss:0.00011235496640438214 lr:2.259937463226651e-05 tokens_per_second_per_gpu:6947.758904999339 | |
| Step 104 | loss:0.003750794567167759 lr:2.1596762663442218e-05 tokens_per_second_per_gpu:6896.99048926509 | |
| Step 105 | loss:0.0005654390552081168 lr:2.061073738537635e-05 tokens_per_second_per_gpu:7152.722181169863 | |
| Step 106 | loss:0.00024903216399252415 lr:1.9641874609064443e-05 tokens_per_second_per_gpu:7197.284226662888 | |
| Step 107 | loss:0.006168627645820379 lr:1.8690740123084316e-05 tokens_per_second_per_gpu:7187.7976354976745 | |
| Step 108 | loss:0.00837626401335001 lr:1.7757889363191483e-05 tokens_per_second_per_gpu:7150.894305974971 | |
| Step 109 | loss:0.004128227476030588 lr:1.684386708796025e-05 tokens_per_second_per_gpu:7132.927671440402 | |
| Step 110 | loss:0.000286786729702726 lr:1.5949207060660138e-05 tokens_per_second_per_gpu:7092.845415606344 | |
| Step 111 | loss:0.0004157178627792746 lr:1.5074431737553157e-05 tokens_per_second_per_gpu:5559.297595461058 | |
| Step 112 | loss:0.014690784737467766 lr:1.422005196279395e-05 tokens_per_second_per_gpu:7192.945910934856 | |
| Step 113 | loss:0.02255910448729992 lr:1.338656667011134e-05 tokens_per_second_per_gpu:6894.269128858172 | |
| Step 114 | loss:8.325742237502709e-05 lr:1.257446259144494e-05 tokens_per_second_per_gpu:6845.4782744098175 | |
| Step 115 | loss:0.0001966281997738406 lr:1.178421397270758e-05 tokens_per_second_per_gpu:7172.565095230581 | |
| Step 116 | loss:0.000696010363753885 lr:1.1016282296838887e-05 tokens_per_second_per_gpu:6918.243246315934 | |
| Step 117 | loss:0.00017549619951751083 lr:1.0271116014312293e-05 tokens_per_second_per_gpu:7161.516229298373 | |
| Step 118 | loss:0.0002540100540500134 lr:9.549150281252633e-06 tokens_per_second_per_gpu:7232.0722732050335 | |
| Step 119 | loss:9.093972767004743e-05 lr:8.850806705317183e-06 tokens_per_second_per_gpu:7164.661700586667 | |
| Step 120 | loss:0.0005339714698493481 lr:8.176493099488663e-06 tokens_per_second_per_gpu:7141.110246612951 | |
| Step 121 | loss:0.0003542705671861768 lr:7.526603243923957e-06 tokens_per_second_per_gpu:7180.744490776651 | |
| Step 122 | loss:0.0019799023866653442 lr:6.901516655997536e-06 tokens_per_second_per_gpu:7206.45415630002 | |
| Step 123 | loss:0.0006128294044174254 lr:6.301598368674105e-06 tokens_per_second_per_gpu:7158.199186505318 | |
| Step 124 | loss:0.00011091229680459946 lr:5.727198717339511e-06 tokens_per_second_per_gpu:7223.984151210271 | |
| Step 125 | loss:0.0029914244078099728 lr:5.178653135214812e-06 tokens_per_second_per_gpu:6873.578950634159 | |
| Step 126 | loss:0.0004038936458528042 lr:4.65628195747273e-06 tokens_per_second_per_gpu:7158.587310119824 | |
| Step 127 | loss:0.00040245719719678164 lr:4.16039023417088e-06 tokens_per_second_per_gpu:6927.879357622875 | |
| Step 128 | loss:0.00028920959448441863 lr:3.691267552111183e-06 tokens_per_second_per_gpu:6915.46615940837 | |
| Step 129 | loss:0.004740703385323286 lr:3.249187865729264e-06 tokens_per_second_per_gpu:7161.141985137788 | |
| Step 130 | loss:0.0007197059458121657 lr:2.8344093371128424e-06 tokens_per_second_per_gpu:7224.815964557556 | |
| Step 131 | loss:0.006197833456099033 lr:2.4471741852423237e-06 tokens_per_second_per_gpu:6937.65221710738 | |
| Step 132 | loss:6.216767360456288e-05 lr:2.087708544541689e-06 tokens_per_second_per_gpu:6811.636384219372 | |
| Step 133 | loss:0.00024436862440779805 lr:1.7562223328224325e-06 tokens_per_second_per_gpu:6886.624144434097 | |
| Step 134 | loss:0.0001290317886741832 lr:1.4529091286973995e-06 tokens_per_second_per_gpu:7111.659400649818 | |
| Step 135 | loss:0.00036069322959519923 lr:1.1779460585363944e-06 tokens_per_second_per_gpu:7103.23218616927 | |
| Step 136 | loss:0.0005095747765153646 lr:9.314936930293283e-07 tokens_per_second_per_gpu:7189.284208457349 | |
| Step 137 | loss:0.0002718658943194896 lr:7.136959534174592e-07 tokens_per_second_per_gpu:7166.451767337445 | |
| Step 138 | loss:0.0002626182103995234 lr:5.246800274474439e-07 tokens_per_second_per_gpu:6945.918728726539 | |
| Step 139 | loss:6.150909030111507e-05 lr:3.6455629509730136e-07 tokens_per_second_per_gpu:6973.895309504627 | |
| Step 140 | loss:4.1929903090931475e-05 lr:2.334182641175686e-07 tokens_per_second_per_gpu:5578.77625491054 | |
| Step 141 | loss:0.00025831200764514506 lr:1.3134251542544774e-07 tokens_per_second_per_gpu:7211.209919549348 | |
| Step 142 | loss:0.00013349638902582228 lr:5.838865838366792e-08 tokens_per_second_per_gpu:6956.274312510406 | |
| Step 143 | loss:0.00015999568859115243 lr:1.4599295990352924e-08 tokens_per_second_per_gpu:6924.927703306033 | |
| Step 144 | loss:0.004884052090346813 lr:0.0 tokens_per_second_per_gpu:6992.451137822864 | |