ekinakyurek's picture
Upload folder using huggingface_hub
0bfc910 verified
Step 1 | loss:0.18009191751480103 lr:4.000000000000001e-06 tokens_per_second_per_gpu:6998.8300058015775
Step 2 | loss:0.31317728757858276 lr:8.000000000000001e-06 tokens_per_second_per_gpu:7039.5685086748
Step 3 | loss:0.02819315902888775 lr:1.2e-05 tokens_per_second_per_gpu:7133.427462899775
Step 4 | loss:0.031229889020323753 lr:1.6000000000000003e-05 tokens_per_second_per_gpu:3892.0327521990534
Step 5 | loss:0.026115207001566887 lr:2e-05 tokens_per_second_per_gpu:7036.794323260246
Step 6 | loss:0.030171455815434456 lr:2.4e-05 tokens_per_second_per_gpu:7066.3219467495355
Step 7 | loss:0.03461410850286484 lr:2.8000000000000003e-05 tokens_per_second_per_gpu:7068.271195486485
Step 8 | loss:0.11270493268966675 lr:3.2000000000000005e-05 tokens_per_second_per_gpu:7070.3867709613605
Step 9 | loss:0.027376271784305573 lr:3.6e-05 tokens_per_second_per_gpu:7013.8664913981565
Step 10 | loss:0.1806798279285431 lr:4e-05 tokens_per_second_per_gpu:3145.3571955533453
Step 11 | loss:0.030545877292752266 lr:4.4000000000000006e-05 tokens_per_second_per_gpu:7081.558613521713
Step 12 | loss:0.02777668833732605 lr:4.8e-05 tokens_per_second_per_gpu:7139.241329113979
Step 13 | loss:0.033755384385585785 lr:5.2000000000000004e-05 tokens_per_second_per_gpu:7081.43925623093
Step 14 | loss:0.15714439749717712 lr:5.6000000000000006e-05 tokens_per_second_per_gpu:3283.577131169415
Step 15 | loss:0.028676647692918777 lr:6e-05 tokens_per_second_per_gpu:6958.617510758428
Step 16 | loss:0.1457669585943222 lr:6.400000000000001e-05 tokens_per_second_per_gpu:7079.148691683309
Step 17 | loss:0.025622490793466568 lr:6.800000000000001e-05 tokens_per_second_per_gpu:7063.271420689791
Step 18 | loss:0.025395670905709267 lr:7.2e-05 tokens_per_second_per_gpu:7052.237363156325
Step 19 | loss:0.02016039751470089 lr:7.6e-05 tokens_per_second_per_gpu:7023.17738043994
Step 20 | loss:0.017484331503510475 lr:8e-05 tokens_per_second_per_gpu:7153.5917054411275
Step 21 | loss:0.021080292761325836 lr:8.4e-05 tokens_per_second_per_gpu:7091.134536816941
Step 22 | loss:0.01708146743476391 lr:8.800000000000001e-05 tokens_per_second_per_gpu:7110.172007981684
Step 23 | loss:0.017242437228560448 lr:9.200000000000001e-05 tokens_per_second_per_gpu:7042.155975568982
Step 24 | loss:0.021529387682676315 lr:9.6e-05 tokens_per_second_per_gpu:7116.972182588817
Step 25 | loss:0.012584959156811237 lr:0.0001 tokens_per_second_per_gpu:7086.794941516708
Step 26 | loss:0.014612418599426746 lr:9.999512620046522e-05 tokens_per_second_per_gpu:7173.246288351139
Step 27 | loss:0.010515368543565273 lr:9.998050575201771e-05 tokens_per_second_per_gpu:6851.108909449922
Step 28 | loss:0.009127353318035603 lr:9.995614150494293e-05 tokens_per_second_per_gpu:7037.752870465287
Step 29 | loss:0.13754822313785553 lr:9.992203820909906e-05 tokens_per_second_per_gpu:7059.027468826925
Step 30 | loss:0.007806963752955198 lr:9.987820251299122e-05 tokens_per_second_per_gpu:7040.201307200682
Step 31 | loss:0.12668229639530182 lr:9.982464296247522e-05 tokens_per_second_per_gpu:7125.643131809696
Step 32 | loss:0.006576175801455975 lr:9.976136999909156e-05 tokens_per_second_per_gpu:7120.9471875789295
Step 33 | loss:0.006318070460110903 lr:9.968839595802982e-05 tokens_per_second_per_gpu:7179.174106520034
Step 34 | loss:0.008536187931895256 lr:9.96057350657239e-05 tokens_per_second_per_gpu:7057.293347921651
Step 35 | loss:0.005036395043134689 lr:9.951340343707852e-05 tokens_per_second_per_gpu:7112.93600533267
Step 36 | loss:0.00768124358728528 lr:9.941141907232765e-05 tokens_per_second_per_gpu:7114.622975323564
Step 37 | loss:0.008800892159342766 lr:9.929980185352526e-05 tokens_per_second_per_gpu:7042.614547288561
Step 38 | loss:0.004721419885754585 lr:9.917857354066931e-05 tokens_per_second_per_gpu:7064.378561217177
Step 39 | loss:0.0027123871259391308 lr:9.904775776745958e-05 tokens_per_second_per_gpu:7046.647556979512
Step 40 | loss:0.008982259780168533 lr:9.890738003669029e-05 tokens_per_second_per_gpu:7118.806059276934
Step 41 | loss:0.005215343553572893 lr:9.875746771527816e-05 tokens_per_second_per_gpu:7022.924309678752
Step 42 | loss:0.006462646182626486 lr:9.859805002892732e-05 tokens_per_second_per_gpu:7121.921034580305
Step 43 | loss:0.0667555034160614 lr:9.842915805643155e-05 tokens_per_second_per_gpu:7163.63477324463
Step 44 | loss:0.00662742555141449 lr:9.825082472361557e-05 tokens_per_second_per_gpu:7041.180407805876
Step 45 | loss:0.0028068949468433857 lr:9.806308479691595e-05 tokens_per_second_per_gpu:7034.927629114503
Step 46 | loss:0.004663445986807346 lr:9.786597487660337e-05 tokens_per_second_per_gpu:7056.840892903616
Step 47 | loss:0.0029336088337004185 lr:9.765953338964735e-05 tokens_per_second_per_gpu:6998.589509313195
Step 48 | loss:0.05873936787247658 lr:9.744380058222483e-05 tokens_per_second_per_gpu:7078.730968654989
Step 49 | loss:0.002175444969907403 lr:9.721881851187406e-05 tokens_per_second_per_gpu:7144.717443554232
Step 50 | loss:0.004309366457164288 lr:9.698463103929542e-05 tokens_per_second_per_gpu:7008.393022510011
Step 51 | loss:0.002648165449500084 lr:9.674128381980072e-05 tokens_per_second_per_gpu:7058.619566249902
Step 52 | loss:0.004984778352081776 lr:9.648882429441257e-05 tokens_per_second_per_gpu:7037.741204571367
Step 53 | loss:0.006551043130457401 lr:9.622730168061567e-05 tokens_per_second_per_gpu:7148.613131082808
Step 54 | loss:0.001940861577168107 lr:9.595676696276172e-05 tokens_per_second_per_gpu:7043.431606388836
Step 55 | loss:0.002408933360129595 lr:9.567727288213005e-05 tokens_per_second_per_gpu:7146.422280245127
Step 56 | loss:0.04799652099609375 lr:9.538887392664544e-05 tokens_per_second_per_gpu:6129.330401952224
Step 57 | loss:0.041337136179208755 lr:9.50916263202557e-05 tokens_per_second_per_gpu:7118.7031922849055
Step 58 | loss:0.0009219947969540954 lr:9.478558801197065e-05 tokens_per_second_per_gpu:7174.039475686794
Step 59 | loss:0.0015516665298491716 lr:9.447081866456489e-05 tokens_per_second_per_gpu:7037.858375510623
Step 60 | loss:0.030973020941019058 lr:9.414737964294636e-05 tokens_per_second_per_gpu:7026.416668317087
Step 61 | loss:0.0011241307947784662 lr:9.381533400219318e-05 tokens_per_second_per_gpu:7127.626480781194
Step 62 | loss:0.0015523171750828624 lr:9.347474647526095e-05 tokens_per_second_per_gpu:7138.402631378805
Step 63 | loss:0.022126222029328346 lr:9.312568346036288e-05 tokens_per_second_per_gpu:7156.598572368849
Step 64 | loss:0.022150062024593353 lr:9.276821300802534e-05 tokens_per_second_per_gpu:7100.052641113448
Step 65 | loss:0.027976224198937416 lr:9.24024048078213e-05 tokens_per_second_per_gpu:7138.89620030133
Step 66 | loss:0.0009740146924741566 lr:9.202833017478422e-05 tokens_per_second_per_gpu:7107.351838050351
Step 67 | loss:0.0015151966363191605 lr:9.164606203550497e-05 tokens_per_second_per_gpu:7160.809358507925
Step 68 | loss:0.0005838324432261288 lr:9.125567491391476e-05 tokens_per_second_per_gpu:7134.361606310554
Step 69 | loss:0.0010164560517296195 lr:9.085724491675642e-05 tokens_per_second_per_gpu:7033.287451967064
Step 70 | loss:0.0033495104871690273 lr:9.045084971874738e-05 tokens_per_second_per_gpu:7025.411970399057
Step 71 | loss:0.013386349193751812 lr:9.003656854743667e-05 tokens_per_second_per_gpu:7033.207015591838
Step 72 | loss:0.002241686685010791 lr:8.961448216775954e-05 tokens_per_second_per_gpu:7124.188362618499
Step 73 | loss:0.00034153315937146544 lr:8.9184672866292e-05 tokens_per_second_per_gpu:7059.203112506652
Step 74 | loss:0.0011084728175774217 lr:8.874722443520899e-05 tokens_per_second_per_gpu:7024.0544207207295
Step 75 | loss:0.0015735337510704994 lr:8.83022221559489e-05 tokens_per_second_per_gpu:7025.344250386632
Step 76 | loss:0.004906295333057642 lr:8.784975278258783e-05 tokens_per_second_per_gpu:7058.942646927155
Step 77 | loss:0.0018294390756636858 lr:8.73899045249266e-05 tokens_per_second_per_gpu:7068.491941716468
Step 78 | loss:0.002055485500022769 lr:8.692276703129421e-05 tokens_per_second_per_gpu:7048.901579529997
Step 79 | loss:0.01685016229748726 lr:8.644843137107059e-05 tokens_per_second_per_gpu:7045.666725052401
Step 80 | loss:0.0010193786583840847 lr:8.596699001693255e-05 tokens_per_second_per_gpu:7045.673459074597
Step 81 | loss:0.000156522830366157 lr:8.547853682682604e-05 tokens_per_second_per_gpu:7105.716080985385
Step 82 | loss:0.000824958726298064 lr:8.498316702566828e-05 tokens_per_second_per_gpu:7152.078552814536
Step 83 | loss:0.0002650362439453602 lr:8.44809771867835e-05 tokens_per_second_per_gpu:6667.018071243688
Step 84 | loss:0.0020614636596292257 lr:8.397206521307584e-05 tokens_per_second_per_gpu:7028.034833329362
Step 85 | loss:0.00029351533157750964 lr:8.345653031794292e-05 tokens_per_second_per_gpu:7118.4900685002385
Step 86 | loss:0.0073922546580433846 lr:8.293447300593402e-05 tokens_per_second_per_gpu:7096.867913950279
Step 87 | loss:0.0002778662892524153 lr:8.240599505315655e-05 tokens_per_second_per_gpu:7141.678809741712
Step 88 | loss:0.0014240993186831474 lr:8.18711994874345e-05 tokens_per_second_per_gpu:7054.4010096696975
Step 89 | loss:0.00030431090272031724 lr:8.133019056822304e-05 tokens_per_second_per_gpu:7104.95405364002
Step 90 | loss:0.008484740741550922 lr:8.07830737662829e-05 tokens_per_second_per_gpu:7136.812448858259
Step 91 | loss:0.012649844400584698 lr:8.022995574311876e-05 tokens_per_second_per_gpu:7024.400632550346
Step 92 | loss:0.0003517992445267737 lr:7.967094433018508e-05 tokens_per_second_per_gpu:7172.619833980229
Step 93 | loss:0.001214964664541185 lr:7.910614850786448e-05 tokens_per_second_per_gpu:7035.730127125673
Step 94 | loss:0.0017081943806260824 lr:7.85356783842216e-05 tokens_per_second_per_gpu:7134.070661573219
Step 95 | loss:0.0014139094855636358 lr:7.795964517353735e-05 tokens_per_second_per_gpu:7025.017143267173
Step 96 | loss:0.0005821334780193865 lr:7.737816117462752e-05 tokens_per_second_per_gpu:7060.116095294863
Step 97 | loss:0.0029627722688019276 lr:7.679133974894983e-05 tokens_per_second_per_gpu:7159.147456351612
Step 98 | loss:0.004898642189800739 lr:7.619929529850397e-05 tokens_per_second_per_gpu:7100.198744376425
Step 99 | loss:0.0008355341269634664 lr:7.560214324352858e-05 tokens_per_second_per_gpu:7138.565268589664
Step 100 | loss:0.00043121943599544466 lr:7.500000000000001e-05 tokens_per_second_per_gpu:7114.549823079954
Step 101 | loss:0.009044676087796688 lr:7.439298295693665e-05 tokens_per_second_per_gpu:7051.332682931595
Step 102 | loss:0.0009635205497033894 lr:7.378121045351378e-05 tokens_per_second_per_gpu:7007.988804765756
Step 103 | loss:0.00047722429735586047 lr:7.316480175599309e-05 tokens_per_second_per_gpu:7114.842340773173
Step 104 | loss:0.0008138161501847208 lr:7.254387703447154e-05 tokens_per_second_per_gpu:7041.582550827874
Step 105 | loss:0.00068050337722525 lr:7.191855733945387e-05 tokens_per_second_per_gpu:7176.040058500955
Step 106 | loss:0.0015233673620969057 lr:7.128896457825364e-05 tokens_per_second_per_gpu:6983.179985121488
Step 107 | loss:0.0014511581975966692 lr:7.06552214912271e-05 tokens_per_second_per_gpu:7020.985842102759
Step 108 | loss:0.0008598329732194543 lr:7.001745162784477e-05 tokens_per_second_per_gpu:7141.8323450023645
Step 109 | loss:0.0009696594788692892 lr:6.937577932260515e-05 tokens_per_second_per_gpu:7029.003024019798
Step 110 | loss:0.00519518693909049 lr:6.873032967079561e-05 tokens_per_second_per_gpu:6978.080645584017
Step 111 | loss:0.0009848929475992918 lr:6.808122850410461e-05 tokens_per_second_per_gpu:6827.774930830296
Step 112 | loss:0.00018184393411502242 lr:6.742860236609077e-05 tokens_per_second_per_gpu:7081.719459194123
Step 113 | loss:0.0002707761886995286 lr:6.677257848751277e-05 tokens_per_second_per_gpu:7124.995583820943
Step 114 | loss:0.002485088538378477 lr:6.611328476152557e-05 tokens_per_second_per_gpu:7004.069227825291
Step 115 | loss:0.0018826309824362397 lr:6.545084971874738e-05 tokens_per_second_per_gpu:7022.231231898059
Step 116 | loss:0.003785816254094243 lr:6.478540250220234e-05 tokens_per_second_per_gpu:7066.358771892953
Step 117 | loss:0.0002744268567766994 lr:6.411707284214384e-05 tokens_per_second_per_gpu:7071.201498354699
Step 118 | loss:0.005153376143425703 lr:6.344599103076329e-05 tokens_per_second_per_gpu:7012.476265793883
Step 119 | loss:0.0007771875243633986 lr:6.277228789678953e-05 tokens_per_second_per_gpu:7032.256105879901
Step 120 | loss:0.0007396205328404903 lr:6.209609477998338e-05 tokens_per_second_per_gpu:7032.492832991018
Step 121 | loss:0.0007155280909501016 lr:6.141754350553279e-05 tokens_per_second_per_gpu:7022.969826397278
Step 122 | loss:0.0006300503155216575 lr:6.073676635835317e-05 tokens_per_second_per_gpu:7033.230212542472
Step 123 | loss:0.0012443548766896129 lr:6.005389605729824e-05 tokens_per_second_per_gpu:7018.194002988244
Step 124 | loss:0.0015270340954884887 lr:5.9369065729286245e-05 tokens_per_second_per_gpu:7025.749134362398
Step 125 | loss:0.00043346776510588825 lr:5.868240888334653e-05 tokens_per_second_per_gpu:7106.96797620578
Step 126 | loss:0.0003676552732940763 lr:5.799405938459175e-05 tokens_per_second_per_gpu:7041.384620041042
Step 127 | loss:0.0006526146898977458 lr:5.730415142812059e-05 tokens_per_second_per_gpu:7046.072139857756
Step 128 | loss:0.000701254466548562 lr:5.661281951285613e-05 tokens_per_second_per_gpu:7061.0591809210355
Step 129 | loss:0.0009863324230536819 lr:5.5920198415325064e-05 tokens_per_second_per_gpu:7036.855633164163
Step 130 | loss:0.0006370892515406013 lr:5.522642316338268e-05 tokens_per_second_per_gpu:7055.533058414875
Step 131 | loss:0.0004070046416018158 lr:5.453162900988902e-05 tokens_per_second_per_gpu:7040.815030356561
Step 132 | loss:0.0005063162534497678 lr:5.383595140634093e-05 tokens_per_second_per_gpu:7138.983023034665
Step 133 | loss:0.0006398994592018425 lr:5.313952597646568e-05 tokens_per_second_per_gpu:7019.4249221270275
Step 134 | loss:0.0008908756426535547 lr:5.244248848978067e-05 tokens_per_second_per_gpu:7016.97676544365
Step 135 | loss:0.0006675228360109031 lr:5.174497483512506e-05 tokens_per_second_per_gpu:7051.529137090155
Step 136 | loss:0.0008693868294358253 lr:5.104712099416785e-05 tokens_per_second_per_gpu:7137.408558091586
Step 137 | loss:0.00037806888576596975 lr:5.034906301489808e-05 tokens_per_second_per_gpu:7122.237248510047
Step 138 | loss:0.002103759441524744 lr:4.965093698510193e-05 tokens_per_second_per_gpu:7180.652020438039
Step 139 | loss:0.00037591473665088415 lr:4.895287900583216e-05 tokens_per_second_per_gpu:7145.234709153499
Step 140 | loss:0.001704183523543179 lr:4.825502516487497e-05 tokens_per_second_per_gpu:6851.470756064882
Step 141 | loss:0.0003409053897485137 lr:4.755751151021934e-05 tokens_per_second_per_gpu:7117.442756291861
Step 142 | loss:0.00033879821421578526 lr:4.6860474023534335e-05 tokens_per_second_per_gpu:7125.024031877995
Step 143 | loss:0.0007233016658574343 lr:4.616404859365907e-05 tokens_per_second_per_gpu:7122.250134682994
Step 144 | loss:0.00036300442297942936 lr:4.5468370990111006e-05 tokens_per_second_per_gpu:7121.57131194985
Step 145 | loss:0.00032935250783339143 lr:4.477357683661734e-05 tokens_per_second_per_gpu:7072.104734917796
Step 146 | loss:0.0003314189671073109 lr:4.407980158467495e-05 tokens_per_second_per_gpu:7073.74962277476
Step 147 | loss:0.0006408370099961758 lr:4.3387180487143876e-05 tokens_per_second_per_gpu:7038.737500027444
Step 148 | loss:0.0014450637390837073 lr:4.269584857187943e-05 tokens_per_second_per_gpu:7016.850117392364
Step 149 | loss:0.0005955788074061275 lr:4.2005940615408264e-05 tokens_per_second_per_gpu:7127.356908351542
Step 150 | loss:0.0007133231847546995 lr:4.131759111665349e-05 tokens_per_second_per_gpu:7074.09868337433
Step 151 | loss:0.00043020996963605285 lr:4.063093427071376e-05 tokens_per_second_per_gpu:7163.40957559151
Step 152 | loss:0.0006772220367565751 lr:3.9946103942701777e-05 tokens_per_second_per_gpu:7003.949911207916
Step 153 | loss:0.00019764102762565017 lr:3.926323364164684e-05 tokens_per_second_per_gpu:7143.618035103577
Step 154 | loss:0.0006879244465380907 lr:3.858245649446721e-05 tokens_per_second_per_gpu:7005.935001205516
Step 155 | loss:0.0011113440850749612 lr:3.790390522001662e-05 tokens_per_second_per_gpu:6998.681319133657
Step 156 | loss:0.0007065472891554236 lr:3.7227712103210486e-05 tokens_per_second_per_gpu:7022.317351713778
Step 157 | loss:0.00025754832313396037 lr:3.655400896923672e-05 tokens_per_second_per_gpu:7124.476362864454
Step 158 | loss:0.0008550232741981745 lr:3.588292715785617e-05 tokens_per_second_per_gpu:7065.07147202258
Step 159 | loss:0.0002527768665459007 lr:3.5214597497797684e-05 tokens_per_second_per_gpu:7124.839546043385
Step 160 | loss:0.0007664287113584578 lr:3.4549150281252636e-05 tokens_per_second_per_gpu:7039.988019701066
Step 161 | loss:0.0006537258741445839 lr:3.388671523847445e-05 tokens_per_second_per_gpu:6918.702526234304
Step 162 | loss:0.0011308350367471576 lr:3.322742151248725e-05 tokens_per_second_per_gpu:7019.255659790205
Step 163 | loss:0.001258939621038735 lr:3.257139763390925e-05 tokens_per_second_per_gpu:7004.455540226454
Step 164 | loss:0.00271209585480392 lr:3.1918771495895396e-05 tokens_per_second_per_gpu:7005.430793716794
Step 165 | loss:0.00024858888355083764 lr:3.12696703292044e-05 tokens_per_second_per_gpu:7136.9828190646895
Step 166 | loss:0.0002619593287818134 lr:3.062422067739485e-05 tokens_per_second_per_gpu:7125.118444573215
Step 167 | loss:0.00028346330509521067 lr:2.9982548372155263e-05 tokens_per_second_per_gpu:7139.1893634175885
Step 168 | loss:0.0007056072936393321 lr:2.934477850877292e-05 tokens_per_second_per_gpu:7077.2885650490925
Step 169 | loss:0.00028484969516284764 lr:2.8711035421746367e-05 tokens_per_second_per_gpu:6670.208541229388
Step 170 | loss:0.00027982069877907634 lr:2.8081442660546125e-05 tokens_per_second_per_gpu:7040.775734171608
Step 171 | loss:0.0005876333452761173 lr:2.7456122965528475e-05 tokens_per_second_per_gpu:7066.097307967806
Step 172 | loss:0.00029774103313684464 lr:2.6835198244006927e-05 tokens_per_second_per_gpu:7154.3978415272
Step 173 | loss:0.0010719196870923042 lr:2.6218789546486234e-05 tokens_per_second_per_gpu:7001.899912818018
Step 174 | loss:0.0003181182546541095 lr:2.560701704306336e-05 tokens_per_second_per_gpu:7136.528642012222
Step 175 | loss:0.0006655407487414777 lr:2.500000000000001e-05 tokens_per_second_per_gpu:7036.958450057089
Step 176 | loss:0.0003917997528333217 lr:2.4397856756471432e-05 tokens_per_second_per_gpu:7141.678749102416
Step 177 | loss:0.00029523391276597977 lr:2.3800704701496053e-05 tokens_per_second_per_gpu:7115.8917105890305
Step 178 | loss:0.0003119556640740484 lr:2.3208660251050158e-05 tokens_per_second_per_gpu:7065.577966980239
Step 179 | loss:0.0002892749907914549 lr:2.2621838825372493e-05 tokens_per_second_per_gpu:7125.095327382073
Step 180 | loss:0.0007699046982452273 lr:2.2040354826462668e-05 tokens_per_second_per_gpu:7048.2783168583255
Step 181 | loss:0.0006299299420788884 lr:2.1464321615778422e-05 tokens_per_second_per_gpu:7030.089852120068
Step 182 | loss:0.00037335994420573115 lr:2.0893851492135537e-05 tokens_per_second_per_gpu:7161.413196071
Step 183 | loss:0.00025024396018125117 lr:2.0329055669814934e-05 tokens_per_second_per_gpu:7125.636531659093
Step 184 | loss:0.0009829809423536062 lr:1.977004425688126e-05 tokens_per_second_per_gpu:6998.280639524545
Step 185 | loss:0.0007007549284026027 lr:1.9216926233717085e-05 tokens_per_second_per_gpu:7025.966100445012
Step 186 | loss:0.0002503481227904558 lr:1.866980943177699e-05 tokens_per_second_per_gpu:7162.342451925611
Step 187 | loss:0.00026103167328983545 lr:1.8128800512565513e-05 tokens_per_second_per_gpu:7154.730317228906
Step 188 | loss:0.0008618187275715172 lr:1.7594004946843456e-05 tokens_per_second_per_gpu:7047.605480516829
Step 189 | loss:0.0007558311917819083 lr:1.7065526994065973e-05 tokens_per_second_per_gpu:7120.896853297243
Step 190 | loss:0.0010207828599959612 lr:1.6543469682057106e-05 tokens_per_second_per_gpu:6957.009169192686
Step 191 | loss:0.00027848954778164625 lr:1.602793478692419e-05 tokens_per_second_per_gpu:7170.7738203734025
Step 192 | loss:0.0002675694995559752 lr:1.551902281321651e-05 tokens_per_second_per_gpu:7099.916878819052
Step 193 | loss:0.0006355201476253569 lr:1.5016832974331724e-05 tokens_per_second_per_gpu:7025.848033592398
Step 194 | loss:0.0002644614432938397 lr:1.4521463173173965e-05 tokens_per_second_per_gpu:7131.996814797787
Step 195 | loss:0.0002673679846338928 lr:1.4033009983067452e-05 tokens_per_second_per_gpu:7148.99887853943
Step 196 | loss:0.0006207852275110781 lr:1.3551568628929434e-05 tokens_per_second_per_gpu:7113.048274405078
Step 197 | loss:0.000341347127687186 lr:1.3077232968705805e-05 tokens_per_second_per_gpu:7145.939798957357
Step 198 | loss:0.0009464792092330754 lr:1.2610095475073414e-05 tokens_per_second_per_gpu:6838.824131123209
Step 199 | loss:0.0003995377628598362 lr:1.2150247217412186e-05 tokens_per_second_per_gpu:7014.223369803345
Step 200 | loss:0.0006975099095143378 lr:1.1697777844051105e-05 tokens_per_second_per_gpu:7002.905549783597
Step 201 | loss:0.0006910972879268229 lr:1.1252775564791024e-05 tokens_per_second_per_gpu:6991.977232224365
Step 202 | loss:0.00023246681666933 lr:1.0815327133708015e-05 tokens_per_second_per_gpu:7147.997782034568
Step 203 | loss:0.00033091907971538603 lr:1.0385517832240471e-05 tokens_per_second_per_gpu:7100.0738446599225
Step 204 | loss:0.00029859691858291626 lr:9.963431452563332e-06 tokens_per_second_per_gpu:7136.584540832816
Step 205 | loss:0.0006699927034787834 lr:9.549150281252633e-06 tokens_per_second_per_gpu:7145.047529681284
Step 206 | loss:0.0007827170775271952 lr:9.142755083243576e-06 tokens_per_second_per_gpu:7122.327008571006
Step 207 | loss:0.0003841849393211305 lr:8.744325086085248e-06 tokens_per_second_per_gpu:7149.507391831032
Step 208 | loss:0.00023412569134961814 lr:8.353937964495029e-06 tokens_per_second_per_gpu:7107.666788242874
Step 209 | loss:0.0002605087647680193 lr:7.971669825215788e-06 tokens_per_second_per_gpu:7145.941168343222
Step 210 | loss:0.0009123857016675174 lr:7.597595192178702e-06 tokens_per_second_per_gpu:6996.99724970942
Step 211 | loss:0.0006150244735181332 lr:7.2317869919746705e-06 tokens_per_second_per_gpu:7016.041355975994
Step 212 | loss:0.0006129314424470067 lr:6.874316539637127e-06 tokens_per_second_per_gpu:7039.008242714278
Step 213 | loss:0.0002814212639350444 lr:6.52525352473905e-06 tokens_per_second_per_gpu:7136.406378836952
Step 214 | loss:0.00023078726371750236 lr:6.184665997806832e-06 tokens_per_second_per_gpu:7137.004654223023
Step 215 | loss:0.00026544686988927424 lr:5.852620357053651e-06 tokens_per_second_per_gpu:7177.206065842668
Step 216 | loss:0.0002672270347829908 lr:5.529181335435124e-06 tokens_per_second_per_gpu:7116.31118498451
Step 217 | loss:0.00028155584004707634 lr:5.214411988029355e-06 tokens_per_second_per_gpu:7128.1356564464995
Step 218 | loss:0.0007024541846476495 lr:4.908373679744316e-06 tokens_per_second_per_gpu:7068.698440091773
Step 219 | loss:0.001129309181123972 lr:4.611126073354571e-06 tokens_per_second_per_gpu:6987.012561392061
Step 220 | loss:0.00022116034233476967 lr:4.322727117869951e-06 tokens_per_second_per_gpu:7129.42542509902
Step 221 | loss:0.0009729282464832067 lr:4.043233037238281e-06 tokens_per_second_per_gpu:7046.5654488049195
Step 222 | loss:0.0006586645031347871 lr:3.772698319384349e-06 tokens_per_second_per_gpu:7009.48879868215
Step 223 | loss:0.0003969118697568774 lr:3.511175705587433e-06 tokens_per_second_per_gpu:7071.902659074244
Step 224 | loss:0.0007297380361706018 lr:3.258716180199278e-06 tokens_per_second_per_gpu:7087.341653619772
Step 225 | loss:0.0007303361780941486 lr:3.0153689607045845e-06 tokens_per_second_per_gpu:7034.138986749779
Step 226 | loss:0.0006981865153647959 lr:2.7811814881259503e-06 tokens_per_second_per_gpu:7049.476566183104
Step 227 | loss:0.0005853428738191724 lr:2.5561994177751737e-06 tokens_per_second_per_gpu:6823.870530535876
Step 228 | loss:0.0006600239430554211 lr:2.340466610352654e-06 tokens_per_second_per_gpu:7022.929164675836
Step 229 | loss:0.00027707693516276777 lr:2.134025123396638e-06 tokens_per_second_per_gpu:7123.898267130639
Step 230 | loss:0.00025898890453390777 lr:1.9369152030840556e-06 tokens_per_second_per_gpu:7068.692526036252
Step 231 | loss:0.00028616029885597527 lr:1.7491752763844293e-06 tokens_per_second_per_gpu:7048.774209590382
Step 232 | loss:0.00031490882975049317 lr:1.5708419435684462e-06 tokens_per_second_per_gpu:7057.845754977864
Step 233 | loss:0.0002555155660957098 lr:1.4019499710726913e-06 tokens_per_second_per_gpu:7111.3866590982025
Step 234 | loss:0.0006810750928707421 lr:1.2425322847218368e-06 tokens_per_second_per_gpu:7044.844377800716
Step 235 | loss:0.0002768074336927384 lr:1.0926199633097157e-06 tokens_per_second_per_gpu:7110.498048162201
Step 236 | loss:0.0006561396876350045 lr:9.522422325404235e-07 tokens_per_second_per_gpu:7036.987532300289
Step 237 | loss:0.0002924645086750388 lr:8.214264593307098e-07 tokens_per_second_per_gpu:7144.092206586575
Step 238 | loss:0.0007849468966014683 lr:7.001981464747565e-07 tokens_per_second_per_gpu:7033.290218197609
Step 239 | loss:0.0011009465670213103 lr:5.885809276723608e-07 tokens_per_second_per_gpu:7046.38283375625
Step 240 | loss:0.0007402449264191091 lr:4.865965629214819e-07 tokens_per_second_per_gpu:7060.243276482221
Step 241 | loss:0.0006887661875225604 lr:3.9426493427611177e-07 tokens_per_second_per_gpu:7043.105576422495
Step 242 | loss:0.0002798953792080283 lr:3.1160404197018154e-07 tokens_per_second_per_gpu:7159.385732016831
Step 243 | loss:0.00022904507932253182 lr:2.386300009084408e-07 tokens_per_second_per_gpu:7092.8373979195785
Step 244 | loss:0.0004532588354777545 lr:1.753570375247815e-07 tokens_per_second_per_gpu:7162.130203769207
Step 245 | loss:0.0007026048842817545 lr:1.2179748700879012e-07 tokens_per_second_per_gpu:7010.78407432447
Step 246 | loss:0.00035172488423995674 lr:7.796179090094891e-08 tokens_per_second_per_gpu:7158.2517640751275
Step 247 | loss:0.0005829736473970115 lr:4.385849505708084e-08 tokens_per_second_per_gpu:7121.047713180432
Step 248 | loss:0.0007291529327630997 lr:1.949424798228239e-08 tokens_per_second_per_gpu:7044.96165192736
Step 249 | loss:0.0002654808631632477 lr:4.873799534788059e-09 tokens_per_second_per_gpu:7120.571853566259
Step 250 | loss:0.0016620289534330368 lr:0.0 tokens_per_second_per_gpu:7140.218880309265