|
Step 1 | loss:0.009997181594371796 lr:6.25e-06 tokens_per_second_per_gpu:3372.705913347604 |
|
Step 2 | loss:0.021949084475636482 lr:1.25e-05 tokens_per_second_per_gpu:2848.59548092494 |
|
Step 3 | loss:0.010684763081371784 lr:1.8750000000000002e-05 tokens_per_second_per_gpu:7013.173968638842 |
|
Step 4 | loss:0.020580904558300972 lr:2.5e-05 tokens_per_second_per_gpu:3379.9597802059843 |
|
Step 5 | loss:0.05869036540389061 lr:3.125e-05 tokens_per_second_per_gpu:7065.67096566462 |
|
Step 6 | loss:0.007317163050174713 lr:3.7500000000000003e-05 tokens_per_second_per_gpu:3332.737972225316 |
|
Step 7 | loss:0.007715300656855106 lr:4.375e-05 tokens_per_second_per_gpu:2779.750272032225 |
|
Step 8 | loss:0.011293564923107624 lr:5e-05 tokens_per_second_per_gpu:7168.749036913079 |
|
Step 9 | loss:0.01255835685878992 lr:5.6250000000000005e-05 tokens_per_second_per_gpu:7076.983001247736 |
|
Step 10 | loss:0.03429204970598221 lr:6.25e-05 tokens_per_second_per_gpu:7119.751345710415 |
|
Step 11 | loss:0.009982830844819546 lr:6.875e-05 tokens_per_second_per_gpu:7097.94320672013 |
|
Step 12 | loss:0.11489806324243546 lr:7.500000000000001e-05 tokens_per_second_per_gpu:2109.6550407007776 |
|
Step 13 | loss:0.014137938618659973 lr:8.125000000000001e-05 tokens_per_second_per_gpu:7075.637220235884 |
|
Step 14 | loss:0.005503526423126459 lr:8.75e-05 tokens_per_second_per_gpu:6998.834569066252 |
|
Step 15 | loss:0.08129885792732239 lr:9.375e-05 tokens_per_second_per_gpu:7188.082632584315 |
|
Step 16 | loss:0.015760665759444237 lr:0.0001 tokens_per_second_per_gpu:7156.96524205046 |
|
Step 17 | loss:0.06739290058612823 lr:9.998810135399546e-05 tokens_per_second_per_gpu:7150.214994895175 |
|
Step 18 | loss:0.00899391807615757 lr:9.99524110790929e-05 tokens_per_second_per_gpu:7195.905616203375 |
|
Step 19 | loss:0.010397745296359062 lr:9.989294616193017e-05 tokens_per_second_per_gpu:6967.615446705353 |
|
Step 20 | loss:0.0081868227571249 lr:9.980973490458728e-05 tokens_per_second_per_gpu:7167.318770492032 |
|
Step 21 | loss:0.005446585360914469 lr:9.970281691111598e-05 tokens_per_second_per_gpu:7102.262716741796 |
|
Step 22 | loss:0.035525448620319366 lr:9.957224306869053e-05 tokens_per_second_per_gpu:7098.023167887444 |
|
Step 23 | loss:0.008133026771247387 lr:9.941807552338804e-05 tokens_per_second_per_gpu:7161.555116188592 |
|
Step 24 | loss:0.020106256008148193 lr:9.924038765061042e-05 tokens_per_second_per_gpu:7216.97972691087 |
|
Step 25 | loss:0.0035311037208884954 lr:9.903926402016153e-05 tokens_per_second_per_gpu:2858.67710883746 |
|
Step 26 | loss:0.004498583264648914 lr:9.881480035599667e-05 tokens_per_second_per_gpu:7147.294482277971 |
|
Step 27 | loss:0.004862579051405191 lr:9.856710349066307e-05 tokens_per_second_per_gpu:6167.093307691695 |
|
Step 28 | loss:0.004098123870790005 lr:9.829629131445342e-05 tokens_per_second_per_gpu:7123.997349757315 |
|
Step 29 | loss:0.002603575587272644 lr:9.800249271929645e-05 tokens_per_second_per_gpu:7045.300338719556 |
|
Step 30 | loss:0.0013945404207333922 lr:9.768584753741134e-05 tokens_per_second_per_gpu:7067.138374954247 |
|
Step 31 | loss:0.05925104022026062 lr:9.73465064747553e-05 tokens_per_second_per_gpu:7082.565805201056 |
|
Step 32 | loss:0.002120282733812928 lr:9.698463103929542e-05 tokens_per_second_per_gpu:7105.650303541457 |
|
Step 33 | loss:0.03873215243220329 lr:9.660039346413994e-05 tokens_per_second_per_gpu:7105.1411825276755 |
|
Step 34 | loss:0.0006570927216671407 lr:9.619397662556435e-05 tokens_per_second_per_gpu:7102.120274411826 |
|
Step 35 | loss:0.0017919926904141903 lr:9.576557395597236e-05 tokens_per_second_per_gpu:7162.902280094276 |
|
Step 36 | loss:0.0027609618846327066 lr:9.53153893518325e-05 tokens_per_second_per_gpu:7061.351086949896 |
|
Step 37 | loss:0.027153493836522102 lr:9.484363707663442e-05 tokens_per_second_per_gpu:2773.821345120831 |
|
Step 38 | loss:0.002410727785900235 lr:9.435054165891109e-05 tokens_per_second_per_gpu:7016.13300098825 |
|
Step 39 | loss:0.0016071751015260816 lr:9.38363377853754e-05 tokens_per_second_per_gpu:7148.912515817933 |
|
Step 40 | loss:0.00035109053715132177 lr:9.330127018922194e-05 tokens_per_second_per_gpu:2086.0854942129004 |
|
Step 41 | loss:0.0014272419502958655 lr:9.274559353364734e-05 tokens_per_second_per_gpu:7097.051510516715 |
|
Step 42 | loss:0.00024285937251988798 lr:9.21695722906443e-05 tokens_per_second_per_gpu:7147.713950314072 |
|
Step 43 | loss:0.000505373755004257 lr:9.157348061512727e-05 tokens_per_second_per_gpu:7042.664674624356 |
|
Step 44 | loss:0.00148515566252172 lr:9.09576022144496e-05 tokens_per_second_per_gpu:7046.928591073811 |
|
Step 45 | loss:0.0006293951300904155 lr:9.032223021337414e-05 tokens_per_second_per_gpu:7081.450126961496 |
|
Step 46 | loss:0.018910076469182968 lr:8.966766701456177e-05 tokens_per_second_per_gpu:6997.775888881761 |
|
Step 47 | loss:9.049645450431854e-05 lr:8.899422415464409e-05 tokens_per_second_per_gpu:7137.270329134368 |
|
Step 48 | loss:0.0009823214495554566 lr:8.83022221559489e-05 tokens_per_second_per_gpu:7171.8402892611 |
|
Step 49 | loss:0.017887184396386147 lr:8.759199037394887e-05 tokens_per_second_per_gpu:7087.445499893975 |
|
Step 50 | loss:0.0007029801490716636 lr:8.68638668405062e-05 tokens_per_second_per_gpu:7090.680472754882 |
|
Step 51 | loss:0.011756590567529202 lr:8.611819810298778e-05 tokens_per_second_per_gpu:6923.598973090227 |
|
Step 52 | loss:2.78255593002541e-05 lr:8.535533905932738e-05 tokens_per_second_per_gpu:7104.163509298331 |
|
Step 53 | loss:0.00183262606151402 lr:8.457565278911348e-05 tokens_per_second_per_gpu:7156.501516026363 |
|
Step 54 | loss:0.00013829753152094781 lr:8.377951038078302e-05 tokens_per_second_per_gpu:6915.48577795003 |
|
Step 55 | loss:8.604916365584359e-05 lr:8.296729075500344e-05 tokens_per_second_per_gpu:6975.600041206586 |
|
Step 56 | loss:0.009762349538505077 lr:8.213938048432697e-05 tokens_per_second_per_gpu:5693.927032288762 |
|
Step 57 | loss:0.007210435811430216 lr:8.129617360920296e-05 tokens_per_second_per_gpu:7166.714352686408 |
|
Step 58 | loss:0.00032512645702809095 lr:8.043807145043604e-05 tokens_per_second_per_gpu:7087.433824372898 |
|
Step 59 | loss:0.006775844842195511 lr:7.956548241817912e-05 tokens_per_second_per_gpu:7097.341666038665 |
|
Step 60 | loss:2.61833756667329e-05 lr:7.86788218175523e-05 tokens_per_second_per_gpu:7032.81256551942 |
|
Step 61 | loss:0.0008728350512683392 lr:7.777851165098012e-05 tokens_per_second_per_gpu:7130.180190536882 |
|
Step 62 | loss:0.010676969774067402 lr:7.68649804173412e-05 tokens_per_second_per_gpu:7067.902852659584 |
|
Step 63 | loss:0.004638221114873886 lr:7.593866290802608e-05 tokens_per_second_per_gpu:6981.736862792104 |
|
Step 64 | loss:3.200213177478872e-05 lr:7.500000000000001e-05 tokens_per_second_per_gpu:7041.3299373183445 |
|
Step 65 | loss:0.0003437605337239802 lr:7.404943844596939e-05 tokens_per_second_per_gpu:7078.467262569241 |
|
Step 66 | loss:0.00030483005684800446 lr:7.308743066175172e-05 tokens_per_second_per_gpu:6951.721104824099 |
|
Step 67 | loss:0.0006182598299346864 lr:7.211443451095007e-05 tokens_per_second_per_gpu:6909.817585706816 |
|
Step 68 | loss:8.372263255296275e-05 lr:7.113091308703498e-05 tokens_per_second_per_gpu:7095.972687470338 |
|
Step 69 | loss:1.691787110758014e-05 lr:7.013733449293687e-05 tokens_per_second_per_gpu:7055.554147006013 |
|
Step 70 | loss:0.0003262369427829981 lr:6.91341716182545e-05 tokens_per_second_per_gpu:7060.717008718582 |
|
Step 71 | loss:0.0004152959445491433 lr:6.812190191418508e-05 tokens_per_second_per_gpu:7136.898978662728 |
|
Step 72 | loss:0.0022777309641242027 lr:6.710100716628344e-05 tokens_per_second_per_gpu:7121.129097759808 |
|
Step 73 | loss:0.0002521690621506423 lr:6.607197326515808e-05 tokens_per_second_per_gpu:6999.949946905635 |
|
Step 74 | loss:0.0009332244517281651 lr:6.503528997521366e-05 tokens_per_second_per_gpu:7052.241083839877 |
|
Step 75 | loss:0.0011186192277818918 lr:6.399145070154961e-05 tokens_per_second_per_gpu:7045.02258863669 |
|
Step 76 | loss:0.0004538046196103096 lr:6.294095225512603e-05 tokens_per_second_per_gpu:7063.881305510846 |
|
Step 77 | loss:0.00033995576086454093 lr:6.188429461630866e-05 tokens_per_second_per_gpu:7068.3279193801645 |
|
Step 78 | loss:0.0008291475824080408 lr:6.0821980696905146e-05 tokens_per_second_per_gpu:7123.905385719763 |
|
Step 79 | loss:0.0001460303319618106 lr:5.9754516100806423e-05 tokens_per_second_per_gpu:6929.057007669713 |
|
Step 80 | loss:0.0005933518405072391 lr:5.868240888334653e-05 tokens_per_second_per_gpu:7073.115883032806 |
|
Step 81 | loss:9.139863686868921e-05 lr:5.7606169309495836e-05 tokens_per_second_per_gpu:7107.2094339346295 |
|
Step 82 | loss:0.0001686795731075108 lr:5.6526309611002594e-05 tokens_per_second_per_gpu:6957.6179283348165 |
|
Step 83 | loss:0.00014402142551261932 lr:5.544334374259823e-05 tokens_per_second_per_gpu:6602.064733007465 |
|
Step 84 | loss:6.965803186176345e-05 lr:5.435778713738292e-05 tokens_per_second_per_gpu:7004.015823423515 |
|
Step 85 | loss:0.0018404150614514947 lr:5.327015646150716e-05 tokens_per_second_per_gpu:7028.947528338376 |
|
Step 86 | loss:0.0005550393252633512 lr:5.218096936826681e-05 tokens_per_second_per_gpu:7109.594458915911 |
|
Step 87 | loss:0.000405809172661975 lr:5.1090744251728064e-05 tokens_per_second_per_gpu:7098.833863968738 |
|
Step 88 | loss:9.01833045645617e-05 lr:5e-05 tokens_per_second_per_gpu:6920.056586896812 |
|
Step 89 | loss:7.839003956178203e-05 lr:4.890925574827195e-05 tokens_per_second_per_gpu:7055.172161870381 |
|
Step 90 | loss:6.532456609420478e-05 lr:4.781903063173321e-05 tokens_per_second_per_gpu:6995.9081284011 |
|
Step 91 | loss:0.00010183212725678459 lr:4.6729843538492847e-05 tokens_per_second_per_gpu:7101.630992536746 |
|
Step 92 | loss:6.422708975151181e-05 lr:4.564221286261709e-05 tokens_per_second_per_gpu:7106.595125684978 |
|
Step 93 | loss:6.365286390064284e-05 lr:4.4556656257401786e-05 tokens_per_second_per_gpu:6976.719693025743 |
|
Step 94 | loss:0.003811969654634595 lr:4.347369038899744e-05 tokens_per_second_per_gpu:7141.247991955458 |
|
Step 95 | loss:8.100510603981093e-05 lr:4.239383069050417e-05 tokens_per_second_per_gpu:7033.624069684615 |
|
Step 96 | loss:0.00010646203736541793 lr:4.131759111665349e-05 tokens_per_second_per_gpu:6979.61651866507 |
|
Step 97 | loss:2.809865509334486e-05 lr:4.0245483899193595e-05 tokens_per_second_per_gpu:7101.06465794309 |
|
Step 98 | loss:0.0023935327772051096 lr:3.917801930309486e-05 tokens_per_second_per_gpu:7140.749321168664 |
|
Step 99 | loss:2.7313937607686967e-05 lr:3.8115705383691355e-05 tokens_per_second_per_gpu:7089.455392595614 |
|
Step 100 | loss:0.00010507470869924873 lr:3.705904774487396e-05 tokens_per_second_per_gpu:7039.410068525895 |
|
Step 101 | loss:0.0003270615707151592 lr:3.60085492984504e-05 tokens_per_second_per_gpu:7058.745892574937 |
|
Step 102 | loss:0.00012109412637073547 lr:3.4964710024786354e-05 tokens_per_second_per_gpu:7073.332581479545 |
|
Step 103 | loss:4.2960131395375356e-05 lr:3.392802673484193e-05 tokens_per_second_per_gpu:7097.904900457584 |
|
Step 104 | loss:6.459934957092628e-05 lr:3.289899283371657e-05 tokens_per_second_per_gpu:7170.728697531819 |
|
Step 105 | loss:0.00018898703274317086 lr:3.1878098085814924e-05 tokens_per_second_per_gpu:7133.585881739942 |
|
Step 106 | loss:1.8494472897145897e-05 lr:3.086582838174551e-05 tokens_per_second_per_gpu:7055.511186132851 |
|
Step 107 | loss:1.894942943181377e-05 lr:2.9862665507063147e-05 tokens_per_second_per_gpu:7113.58009339812 |
|
Step 108 | loss:1.2594631698448211e-05 lr:2.886908691296504e-05 tokens_per_second_per_gpu:6933.506583125082 |
|
Step 109 | loss:1.4899192137818318e-05 lr:2.7885565489049946e-05 tokens_per_second_per_gpu:7157.170256663477 |
|
Step 110 | loss:0.0009269791771657765 lr:2.6912569338248315e-05 tokens_per_second_per_gpu:7220.323725362026 |
|
Step 111 | loss:0.0006730433669872582 lr:2.595056155403063e-05 tokens_per_second_per_gpu:6081.038547612926 |
|
Step 112 | loss:1.6011554180295207e-05 lr:2.500000000000001e-05 tokens_per_second_per_gpu:7107.442594494505 |
|
Step 113 | loss:0.0014794764574617147 lr:2.4061337091973918e-05 tokens_per_second_per_gpu:7116.405101824958 |
|
Step 114 | loss:2.098037839459721e-05 lr:2.3135019582658802e-05 tokens_per_second_per_gpu:7169.198262003967 |
|
Step 115 | loss:1.175615943793673e-05 lr:2.2221488349019903e-05 tokens_per_second_per_gpu:7110.343258939322 |
|
Step 116 | loss:2.5983064915635623e-05 lr:2.132117818244771e-05 tokens_per_second_per_gpu:7131.807503110347 |
|
Step 117 | loss:0.00041663984302431345 lr:2.0434517581820896e-05 tokens_per_second_per_gpu:7173.803566369658 |
|
Step 118 | loss:6.96275856171269e-06 lr:1.9561928549563968e-05 tokens_per_second_per_gpu:6892.54152664284 |
|
Step 119 | loss:1.8991711840499192e-05 lr:1.8703826390797048e-05 tokens_per_second_per_gpu:7116.1244287985255 |
|
Step 120 | loss:7.888660547905602e-06 lr:1.7860619515673033e-05 tokens_per_second_per_gpu:7199.106174833407 |
|
Step 121 | loss:5.204502031119773e-06 lr:1.703270924499656e-05 tokens_per_second_per_gpu:7107.949533796379 |
|
Step 122 | loss:1.8726495909504592e-05 lr:1.622048961921699e-05 tokens_per_second_per_gpu:7085.514644129928 |
|
Step 123 | loss:0.0002224978234153241 lr:1.5424347210886538e-05 tokens_per_second_per_gpu:7055.194962013016 |
|
Step 124 | loss:0.00020316588052082807 lr:1.4644660940672627e-05 tokens_per_second_per_gpu:6983.794666913756 |
|
Step 125 | loss:0.0006224739481694996 lr:1.3881801897012225e-05 tokens_per_second_per_gpu:7144.961836594143 |
|
Step 126 | loss:1.0587371434667148e-05 lr:1.3136133159493802e-05 tokens_per_second_per_gpu:7086.555739365824 |
|
Step 127 | loss:8.414840522164013e-06 lr:1.2408009626051137e-05 tokens_per_second_per_gpu:7054.586857317468 |
|
Step 128 | loss:1.595690264366567e-05 lr:1.1697777844051105e-05 tokens_per_second_per_gpu:7116.185097970328 |
|
Step 129 | loss:0.0012286374112591147 lr:1.100577584535592e-05 tokens_per_second_per_gpu:7107.726941428794 |
|
Step 130 | loss:6.528756330226315e-06 lr:1.0332332985438248e-05 tokens_per_second_per_gpu:7103.68149198383 |
|
Step 131 | loss:0.0039833965711295605 lr:9.677769786625867e-06 tokens_per_second_per_gpu:6992.181217171735 |
|
Step 132 | loss:1.2281540875846986e-05 lr:9.042397785550405e-06 tokens_per_second_per_gpu:7190.066089111773 |
|
Step 133 | loss:0.0018962608883157372 lr:8.426519384872733e-06 tokens_per_second_per_gpu:7104.999026177273 |
|
Step 134 | loss:8.73971584951505e-05 lr:7.830427709355725e-06 tokens_per_second_per_gpu:7126.641270235755 |
|
Step 135 | loss:1.81683662958676e-05 lr:7.2544064663526815e-06 tokens_per_second_per_gpu:7157.511720693617 |
|
Step 136 | loss:1.5947720385156572e-05 lr:6.698729810778065e-06 tokens_per_second_per_gpu:7068.014958399452 |
|
Step 137 | loss:3.120024121017195e-05 lr:6.163662214624616e-06 tokens_per_second_per_gpu:7215.606554795167 |
|
Step 138 | loss:2.9728382287430577e-05 lr:5.649458341088915e-06 tokens_per_second_per_gpu:7159.997655543726 |
|
Step 139 | loss:5.4895108405617066e-06 lr:5.156362923365588e-06 tokens_per_second_per_gpu:7112.1876428592595 |
|
Step 140 | loss:5.188698196434416e-06 lr:4.684610648167503e-06 tokens_per_second_per_gpu:6064.432496929655 |
|
Step 141 | loss:0.003997826483100653 lr:4.234426044027645e-06 tokens_per_second_per_gpu:6965.935491456345 |
|
Step 142 | loss:1.1717835150193423e-05 lr:3.8060233744356633e-06 tokens_per_second_per_gpu:7126.053894205312 |
|
Step 143 | loss:1.3120114999765065e-05 lr:3.3996065358600782e-06 tokens_per_second_per_gpu:7094.334302685246 |
|
Step 144 | loss:0.0009180277702398598 lr:3.0153689607045845e-06 tokens_per_second_per_gpu:7058.979668185038 |
|
Step 145 | loss:3.6088571505388245e-05 lr:2.653493525244721e-06 tokens_per_second_per_gpu:7160.575228854824 |
|
Step 146 | loss:6.500137715192977e-06 lr:2.314152462588659e-06 tokens_per_second_per_gpu:7067.746595432052 |
|
Step 147 | loss:0.0002857667859643698 lr:1.99750728070357e-06 tokens_per_second_per_gpu:7130.129825038883 |
|
Step 148 | loss:0.00011650095257209614 lr:1.70370868554659e-06 tokens_per_second_per_gpu:7041.442358317434 |
|
Step 149 | loss:8.784528290561866e-06 lr:1.4328965093369283e-06 tokens_per_second_per_gpu:7133.482270860399 |
|
Step 150 | loss:9.28833833313547e-06 lr:1.1851996440033319e-06 tokens_per_second_per_gpu:7137.065922713905 |
|
Step 151 | loss:0.00042926889727823436 lr:9.607359798384785e-07 tokens_per_second_per_gpu:7133.921261088311 |
|
Step 152 | loss:3.727373950823676e-06 lr:7.596123493895991e-07 tokens_per_second_per_gpu:6957.946126591829 |
|
Step 153 | loss:1.2050382792949677e-05 lr:5.81924476611967e-07 tokens_per_second_per_gpu:7188.6305707630545 |
|
Step 154 | loss:5.231756585999392e-05 lr:4.277569313094809e-07 tokens_per_second_per_gpu:7048.607027183144 |
|
Step 155 | loss:2.7723128823708976e-06 lr:2.971830888840177e-07 tokens_per_second_per_gpu:7093.743981287135 |
|
Step 156 | loss:0.00010837656736839563 lr:1.9026509541272275e-07 tokens_per_second_per_gpu:7097.887013849774 |
|
Step 157 | loss:0.0003977992164436728 lr:1.0705383806982606e-07 tokens_per_second_per_gpu:7144.955456738839 |
|
Step 158 | loss:1.4299096619652119e-05 lr:4.7588920907110094e-08 tokens_per_second_per_gpu:7060.431273418211 |
|
Step 159 | loss:8.44956812215969e-05 lr:1.189864600454338e-08 tokens_per_second_per_gpu:7186.336029947268 |
|
Step 160 | loss:7.621983240824193e-05 lr:0.0 tokens_per_second_per_gpu:7092.863911790079 |
|
|