ekinakyurek's picture
Upload folder using huggingface_hub
0bfc910 verified
raw
history blame
26.7 kB
Step 1 | loss:0.007717160973697901 lr:4.000000000000001e-06 tokens_per_second_per_gpu:4765.6518158286535
Step 2 | loss:0.011798330582678318 lr:8.000000000000001e-06 tokens_per_second_per_gpu:2722.820638790913
Step 3 | loss:0.011066935025155544 lr:1.2e-05 tokens_per_second_per_gpu:4056.300114560815
Step 4 | loss:0.06607521325349808 lr:1.6000000000000003e-05 tokens_per_second_per_gpu:3565.8618690975386
Step 5 | loss:0.053778357803821564 lr:2e-05 tokens_per_second_per_gpu:7015.661621015296
Step 6 | loss:0.010302800685167313 lr:2.4e-05 tokens_per_second_per_gpu:4101.928609756071
Step 7 | loss:0.012550846673548222 lr:2.8000000000000003e-05 tokens_per_second_per_gpu:7027.845267455205
Step 8 | loss:0.011083463206887245 lr:3.2000000000000005e-05 tokens_per_second_per_gpu:6989.951510253902
Step 9 | loss:0.011257014237344265 lr:3.6e-05 tokens_per_second_per_gpu:6994.8623867051865
Step 10 | loss:0.04111339896917343 lr:4e-05 tokens_per_second_per_gpu:6939.367357251662
Step 11 | loss:0.00891095120459795 lr:4.4000000000000006e-05 tokens_per_second_per_gpu:6946.609716996621
Step 12 | loss:0.010376016609370708 lr:4.8e-05 tokens_per_second_per_gpu:6950.545052852816
Step 13 | loss:0.009249729104340076 lr:5.2000000000000004e-05 tokens_per_second_per_gpu:7053.480887775268
Step 14 | loss:0.05037343129515648 lr:5.6000000000000006e-05 tokens_per_second_per_gpu:3525.121483840703
Step 15 | loss:0.010580269619822502 lr:6e-05 tokens_per_second_per_gpu:7012.7399207956205
Step 16 | loss:0.012633295729756355 lr:6.400000000000001e-05 tokens_per_second_per_gpu:7019.985482582019
Step 17 | loss:0.005920320749282837 lr:6.800000000000001e-05 tokens_per_second_per_gpu:6964.055615321013
Step 18 | loss:0.005812352057546377 lr:7.2e-05 tokens_per_second_per_gpu:6951.1716210736995
Step 19 | loss:0.05899326875805855 lr:7.6e-05 tokens_per_second_per_gpu:7042.282406296128
Step 20 | loss:0.009306409396231174 lr:8e-05 tokens_per_second_per_gpu:7028.180372806691
Step 21 | loss:0.0031778800766915083 lr:8.4e-05 tokens_per_second_per_gpu:6932.77122280794
Step 22 | loss:0.008047216571867466 lr:8.800000000000001e-05 tokens_per_second_per_gpu:7069.058549517583
Step 23 | loss:0.04175831377506256 lr:9.200000000000001e-05 tokens_per_second_per_gpu:6995.268503445106
Step 24 | loss:0.010173922404646873 lr:9.6e-05 tokens_per_second_per_gpu:7034.68662550376
Step 25 | loss:0.005207568407058716 lr:0.0001 tokens_per_second_per_gpu:7066.368170865323
Step 26 | loss:0.04262256994843483 lr:9.999512620046522e-05 tokens_per_second_per_gpu:7124.811955181296
Step 27 | loss:0.008702673017978668 lr:9.998050575201771e-05 tokens_per_second_per_gpu:6146.126736621402
Step 28 | loss:0.028031382709741592 lr:9.995614150494293e-05 tokens_per_second_per_gpu:7065.319456493627
Step 29 | loss:0.0038657954428344965 lr:9.992203820909906e-05 tokens_per_second_per_gpu:7058.420631268385
Step 30 | loss:0.003297625109553337 lr:9.987820251299122e-05 tokens_per_second_per_gpu:6947.122708323051
Step 31 | loss:0.005899155046790838 lr:9.982464296247522e-05 tokens_per_second_per_gpu:7069.745735044296
Step 32 | loss:0.0028817513957619667 lr:9.976136999909156e-05 tokens_per_second_per_gpu:6961.5551741102
Step 33 | loss:0.004295954015105963 lr:9.968839595802982e-05 tokens_per_second_per_gpu:7103.369008962014
Step 34 | loss:0.005332204047590494 lr:9.96057350657239e-05 tokens_per_second_per_gpu:7005.220142799756
Step 35 | loss:0.003418134991079569 lr:9.951340343707852e-05 tokens_per_second_per_gpu:6897.249632875057
Step 36 | loss:0.020042426884174347 lr:9.941141907232765e-05 tokens_per_second_per_gpu:7054.494705356733
Step 37 | loss:0.003379473928362131 lr:9.929980185352526e-05 tokens_per_second_per_gpu:6961.176478229203
Step 38 | loss:0.0021382393315434456 lr:9.917857354066931e-05 tokens_per_second_per_gpu:7047.64959657671
Step 39 | loss:0.0038591136690229177 lr:9.904775776745958e-05 tokens_per_second_per_gpu:6992.0235838981025
Step 40 | loss:0.0006594560109078884 lr:9.890738003669029e-05 tokens_per_second_per_gpu:6832.64037110896
Step 41 | loss:0.002047021174803376 lr:9.875746771527816e-05 tokens_per_second_per_gpu:6995.09956514717
Step 42 | loss:0.002400354715064168 lr:9.859805002892732e-05 tokens_per_second_per_gpu:6922.314916762286
Step 43 | loss:0.0018328193109482527 lr:9.842915805643155e-05 tokens_per_second_per_gpu:7004.4820837316565
Step 44 | loss:0.0022636449430137873 lr:9.825082472361557e-05 tokens_per_second_per_gpu:7034.754658534583
Step 45 | loss:0.004316433798521757 lr:9.806308479691595e-05 tokens_per_second_per_gpu:7053.901109078756
Step 46 | loss:0.002044723369181156 lr:9.786597487660337e-05 tokens_per_second_per_gpu:7056.789357443406
Step 47 | loss:0.0008138153934851289 lr:9.765953338964735e-05 tokens_per_second_per_gpu:6977.268744496381
Step 48 | loss:0.0010715450625866652 lr:9.744380058222483e-05 tokens_per_second_per_gpu:6902.672751290089
Step 49 | loss:0.00913983304053545 lr:9.721881851187406e-05 tokens_per_second_per_gpu:7193.891981183207
Step 50 | loss:0.0015367832966148853 lr:9.698463103929542e-05 tokens_per_second_per_gpu:7053.041625973136
Step 51 | loss:0.00047497867490164936 lr:9.674128381980072e-05 tokens_per_second_per_gpu:7026.80633212007
Step 52 | loss:0.001315409317612648 lr:9.648882429441257e-05 tokens_per_second_per_gpu:7091.336283223388
Step 53 | loss:0.0014841972151771188 lr:9.622730168061567e-05 tokens_per_second_per_gpu:7143.061318996444
Step 54 | loss:0.002150429179891944 lr:9.595676696276172e-05 tokens_per_second_per_gpu:7038.171620555715
Step 55 | loss:0.001224601292051375 lr:9.567727288213005e-05 tokens_per_second_per_gpu:6959.093764045569
Step 56 | loss:0.0011078715324401855 lr:9.538887392664544e-05 tokens_per_second_per_gpu:6319.63465286324
Step 57 | loss:0.0009197339531965554 lr:9.50916263202557e-05 tokens_per_second_per_gpu:6927.637051389944
Step 58 | loss:0.0019169397419318557 lr:9.478558801197065e-05 tokens_per_second_per_gpu:2249.27942692595
Step 59 | loss:0.0007976124761626124 lr:9.447081866456489e-05 tokens_per_second_per_gpu:7000.47676062355
Step 60 | loss:0.0034662303514778614 lr:9.414737964294636e-05 tokens_per_second_per_gpu:7084.366053806596
Step 61 | loss:0.024144982919096947 lr:9.381533400219318e-05 tokens_per_second_per_gpu:6861.788758917914
Step 62 | loss:0.0018489802023395896 lr:9.347474647526095e-05 tokens_per_second_per_gpu:6901.5655044149835
Step 63 | loss:0.0005814200267195702 lr:9.312568346036288e-05 tokens_per_second_per_gpu:7014.696323506923
Step 64 | loss:0.000357311888365075 lr:9.276821300802534e-05 tokens_per_second_per_gpu:7093.578148356162
Step 65 | loss:0.001708107185550034 lr:9.24024048078213e-05 tokens_per_second_per_gpu:6994.082814622964
Step 66 | loss:0.0017755840672180057 lr:9.202833017478422e-05 tokens_per_second_per_gpu:7024.385701974433
Step 67 | loss:0.00190495525021106 lr:9.164606203550497e-05 tokens_per_second_per_gpu:7097.723189157454
Step 68 | loss:0.011792528443038464 lr:9.125567491391476e-05 tokens_per_second_per_gpu:7106.688386272463
Step 69 | loss:0.003977603279054165 lr:9.085724491675642e-05 tokens_per_second_per_gpu:7068.951470483102
Step 70 | loss:0.0009017084375955164 lr:9.045084971874738e-05 tokens_per_second_per_gpu:7105.678202016724
Step 71 | loss:0.0005989113124087453 lr:9.003656854743667e-05 tokens_per_second_per_gpu:7007.479565377195
Step 72 | loss:0.000268982897978276 lr:8.961448216775954e-05 tokens_per_second_per_gpu:7031.1712322055155
Step 73 | loss:0.0006750575848855078 lr:8.9184672866292e-05 tokens_per_second_per_gpu:7016.751017472591
Step 74 | loss:0.0012515854323282838 lr:8.874722443520899e-05 tokens_per_second_per_gpu:7052.296701931459
Step 75 | loss:0.0008598480490036309 lr:8.83022221559489e-05 tokens_per_second_per_gpu:7066.758385747782
Step 76 | loss:0.007910097017884254 lr:8.784975278258783e-05 tokens_per_second_per_gpu:7038.203427188493
Step 77 | loss:0.0015292213065549731 lr:8.73899045249266e-05 tokens_per_second_per_gpu:7078.881444846515
Step 78 | loss:0.0013078140327706933 lr:8.692276703129421e-05 tokens_per_second_per_gpu:7073.333751719733
Step 79 | loss:0.0008622295572422445 lr:8.644843137107059e-05 tokens_per_second_per_gpu:6973.422302729589
Step 80 | loss:0.0012173989089205861 lr:8.596699001693255e-05 tokens_per_second_per_gpu:6894.731064051415
Step 81 | loss:0.0005852589965797961 lr:8.547853682682604e-05 tokens_per_second_per_gpu:7016.940775906466
Step 82 | loss:0.0011112464126199484 lr:8.498316702566828e-05 tokens_per_second_per_gpu:7108.480735009908
Step 83 | loss:0.010315882042050362 lr:8.44809771867835e-05 tokens_per_second_per_gpu:5999.991684493117
Step 84 | loss:0.00032650414505042136 lr:8.397206521307584e-05 tokens_per_second_per_gpu:6887.135146499313
Step 85 | loss:0.0012548055965453386 lr:8.345653031794292e-05 tokens_per_second_per_gpu:7068.668257849253
Step 86 | loss:0.0010378140723332763 lr:8.293447300593402e-05 tokens_per_second_per_gpu:7012.566152998574
Step 87 | loss:0.0007717790431343019 lr:8.240599505315655e-05 tokens_per_second_per_gpu:7063.584999273401
Step 88 | loss:0.0017850336153060198 lr:8.18711994874345e-05 tokens_per_second_per_gpu:7027.059050791612
Step 89 | loss:0.0010677101090550423 lr:8.133019056822304e-05 tokens_per_second_per_gpu:7053.296250202947
Step 90 | loss:0.00047878079931251705 lr:8.07830737662829e-05 tokens_per_second_per_gpu:6926.863854910874
Step 91 | loss:0.0033548439387232065 lr:8.022995574311876e-05 tokens_per_second_per_gpu:6929.333567741733
Step 92 | loss:0.0005516879609785974 lr:7.967094433018508e-05 tokens_per_second_per_gpu:7017.187416697672
Step 93 | loss:0.0004544590483419597 lr:7.910614850786448e-05 tokens_per_second_per_gpu:6887.175013483203
Step 94 | loss:0.00036337380879558623 lr:7.85356783842216e-05 tokens_per_second_per_gpu:6956.541088898766
Step 95 | loss:0.0009806951275095344 lr:7.795964517353735e-05 tokens_per_second_per_gpu:6943.185504923191
Step 96 | loss:0.00042983677121810615 lr:7.737816117462752e-05 tokens_per_second_per_gpu:6959.7838939324065
Step 97 | loss:0.00016360022709704936 lr:7.679133974894983e-05 tokens_per_second_per_gpu:6848.079083911749
Step 98 | loss:0.0004620795079972595 lr:7.619929529850397e-05 tokens_per_second_per_gpu:7052.956459314436
Step 99 | loss:0.0010959854116663337 lr:7.560214324352858e-05 tokens_per_second_per_gpu:7069.624651352907
Step 100 | loss:0.0012994559947401285 lr:7.500000000000001e-05 tokens_per_second_per_gpu:7114.983598191908
Step 101 | loss:0.0005256670410744846 lr:7.439298295693665e-05 tokens_per_second_per_gpu:7026.276884945681
Step 102 | loss:0.0008625894552096725 lr:7.378121045351378e-05 tokens_per_second_per_gpu:7039.880528695378
Step 103 | loss:0.0008110045455396175 lr:7.316480175599309e-05 tokens_per_second_per_gpu:7110.794216943635
Step 104 | loss:0.0015763400588184595 lr:7.254387703447154e-05 tokens_per_second_per_gpu:7018.44046393014
Step 105 | loss:0.006749422755092382 lr:7.191855733945387e-05 tokens_per_second_per_gpu:6907.90121259572
Step 106 | loss:0.0019243033602833748 lr:7.128896457825364e-05 tokens_per_second_per_gpu:7060.991291836118
Step 107 | loss:0.0008425582200288773 lr:7.06552214912271e-05 tokens_per_second_per_gpu:7081.431736037115
Step 108 | loss:0.0020393154118210077 lr:7.001745162784477e-05 tokens_per_second_per_gpu:6960.18413112291
Step 109 | loss:0.0012784764403477311 lr:6.937577932260515e-05 tokens_per_second_per_gpu:7056.259769902966
Step 110 | loss:0.0009409835911355913 lr:6.873032967079561e-05 tokens_per_second_per_gpu:7032.736224567334
Step 111 | loss:0.0006828506593592465 lr:6.808122850410461e-05 tokens_per_second_per_gpu:6937.748514293419
Step 112 | loss:0.0008516262751072645 lr:6.742860236609077e-05 tokens_per_second_per_gpu:6910.140939230035
Step 113 | loss:0.00039492733776569366 lr:6.677257848751277e-05 tokens_per_second_per_gpu:7139.141835905823
Step 114 | loss:0.0007230450864881277 lr:6.611328476152557e-05 tokens_per_second_per_gpu:6945.434025869618
Step 115 | loss:0.0010181547841057181 lr:6.545084971874738e-05 tokens_per_second_per_gpu:6988.8500883261
Step 116 | loss:0.0009589443798176944 lr:6.478540250220234e-05 tokens_per_second_per_gpu:6966.342477007727
Step 117 | loss:0.001450462150387466 lr:6.411707284214384e-05 tokens_per_second_per_gpu:7070.795143284753
Step 118 | loss:0.0007019777549430728 lr:6.344599103076329e-05 tokens_per_second_per_gpu:7067.196077169587
Step 119 | loss:0.0007328979554586112 lr:6.277228789678953e-05 tokens_per_second_per_gpu:7043.518273539388
Step 120 | loss:0.0007088769343681633 lr:6.209609477998338e-05 tokens_per_second_per_gpu:6969.941577374882
Step 121 | loss:0.0010005782824009657 lr:6.141754350553279e-05 tokens_per_second_per_gpu:7010.299326556531
Step 122 | loss:0.00033581157913431525 lr:6.073676635835317e-05 tokens_per_second_per_gpu:6906.187538521414
Step 123 | loss:0.0011525978334248066 lr:6.005389605729824e-05 tokens_per_second_per_gpu:7032.928390592858
Step 124 | loss:0.0002751214778982103 lr:5.9369065729286245e-05 tokens_per_second_per_gpu:6895.075351656819
Step 125 | loss:0.0002782866940833628 lr:5.868240888334653e-05 tokens_per_second_per_gpu:6929.222405460703
Step 126 | loss:0.0006654362077824771 lr:5.799405938459175e-05 tokens_per_second_per_gpu:7092.492836261331
Step 127 | loss:0.00023203201999422163 lr:5.730415142812059e-05 tokens_per_second_per_gpu:6870.927068929936
Step 128 | loss:0.0006327247247099876 lr:5.661281951285613e-05 tokens_per_second_per_gpu:7070.060981448554
Step 129 | loss:0.0007003758219070733 lr:5.5920198415325064e-05 tokens_per_second_per_gpu:7085.242681818933
Step 130 | loss:0.00023260695161297917 lr:5.522642316338268e-05 tokens_per_second_per_gpu:6949.826296919135
Step 131 | loss:0.0009756020735949278 lr:5.453162900988902e-05 tokens_per_second_per_gpu:7025.853198876617
Step 132 | loss:0.009996986016631126 lr:5.383595140634093e-05 tokens_per_second_per_gpu:6922.384548990233
Step 133 | loss:0.0008823410607874393 lr:5.313952597646568e-05 tokens_per_second_per_gpu:7043.5405694536485
Step 134 | loss:0.00024395894433837384 lr:5.244248848978067e-05 tokens_per_second_per_gpu:6937.249267998909
Step 135 | loss:0.00041148331365548074 lr:5.174497483512506e-05 tokens_per_second_per_gpu:6977.57768128664
Step 136 | loss:0.0006792456260882318 lr:5.104712099416785e-05 tokens_per_second_per_gpu:7065.466449058593
Step 137 | loss:0.0007075682515278459 lr:5.034906301489808e-05 tokens_per_second_per_gpu:7002.62486715798
Step 138 | loss:0.0010140225058421493 lr:4.965093698510193e-05 tokens_per_second_per_gpu:7115.667266438031
Step 139 | loss:0.0004998283111490309 lr:4.895287900583216e-05 tokens_per_second_per_gpu:7030.733843395433
Step 140 | loss:0.0003585314843803644 lr:4.825502516487497e-05 tokens_per_second_per_gpu:6937.9420345162325
Step 141 | loss:0.00025047105737030506 lr:4.755751151021934e-05 tokens_per_second_per_gpu:6913.199615851978
Step 142 | loss:0.0006239487556740642 lr:4.6860474023534335e-05 tokens_per_second_per_gpu:7020.802912949245
Step 143 | loss:0.0006782030686736107 lr:4.616404859365907e-05 tokens_per_second_per_gpu:7033.100719523972
Step 144 | loss:0.001430873991921544 lr:4.5468370990111006e-05 tokens_per_second_per_gpu:6912.094759999119
Step 145 | loss:0.0005458036321215332 lr:4.477357683661734e-05 tokens_per_second_per_gpu:6949.209078897781
Step 146 | loss:0.0005880115204490721 lr:4.407980158467495e-05 tokens_per_second_per_gpu:7046.057797266081
Step 147 | loss:0.0008938790415413678 lr:4.3387180487143876e-05 tokens_per_second_per_gpu:7059.918039037532
Step 148 | loss:0.0005998093984089792 lr:4.269584857187943e-05 tokens_per_second_per_gpu:6944.960149527041
Step 149 | loss:0.0004189919272903353 lr:4.2005940615408264e-05 tokens_per_second_per_gpu:6968.576445352629
Step 150 | loss:0.000480139278806746 lr:4.131759111665349e-05 tokens_per_second_per_gpu:7003.209240823344
Step 151 | loss:0.0005850403103977442 lr:4.063093427071376e-05 tokens_per_second_per_gpu:7058.738398083008
Step 152 | loss:0.0007663979195058346 lr:3.9946103942701777e-05 tokens_per_second_per_gpu:6965.575904499519
Step 153 | loss:0.0005060759140178561 lr:3.926323364164684e-05 tokens_per_second_per_gpu:7000.413316707364
Step 154 | loss:0.0008425578707829118 lr:3.858245649446721e-05 tokens_per_second_per_gpu:6984.915378783536
Step 155 | loss:0.0004016058810520917 lr:3.790390522001662e-05 tokens_per_second_per_gpu:6983.495712518545
Step 156 | loss:0.0001922405353980139 lr:3.7227712103210486e-05 tokens_per_second_per_gpu:6942.199558890534
Step 157 | loss:0.0013894123258069158 lr:3.655400896923672e-05 tokens_per_second_per_gpu:7073.449779659054
Step 158 | loss:0.0004884747322648764 lr:3.588292715785617e-05 tokens_per_second_per_gpu:6997.870856851499
Step 159 | loss:0.004077289253473282 lr:3.5214597497797684e-05 tokens_per_second_per_gpu:6952.293474888752
Step 160 | loss:0.00035840197233483195 lr:3.4549150281252636e-05 tokens_per_second_per_gpu:6990.043170427167
Step 161 | loss:0.0006912366370670497 lr:3.388671523847445e-05 tokens_per_second_per_gpu:7041.030222829318
Step 162 | loss:0.0004366366483736783 lr:3.322742151248725e-05 tokens_per_second_per_gpu:7053.829120321156
Step 163 | loss:0.0005419852677732706 lr:3.257139763390925e-05 tokens_per_second_per_gpu:7035.411308425318
Step 164 | loss:0.00048665684880688787 lr:3.1918771495895396e-05 tokens_per_second_per_gpu:7022.495950442873
Step 165 | loss:0.0006985372747294605 lr:3.12696703292044e-05 tokens_per_second_per_gpu:7047.185481148683
Step 166 | loss:0.0003955260035581887 lr:3.062422067739485e-05 tokens_per_second_per_gpu:6957.394322730902
Step 167 | loss:0.0002128683845512569 lr:2.9982548372155263e-05 tokens_per_second_per_gpu:6893.874790446583
Step 168 | loss:0.0006919001461938024 lr:2.934477850877292e-05 tokens_per_second_per_gpu:7078.097644011101
Step 169 | loss:0.004682112019509077 lr:2.8711035421746367e-05 tokens_per_second_per_gpu:6087.436806365002
Step 170 | loss:0.002017313614487648 lr:2.8081442660546125e-05 tokens_per_second_per_gpu:6937.307444642746
Step 171 | loss:0.0007102281088009477 lr:2.7456122965528475e-05 tokens_per_second_per_gpu:7094.395009428558
Step 172 | loss:0.000651624402962625 lr:2.6835198244006927e-05 tokens_per_second_per_gpu:7046.522124717501
Step 173 | loss:0.0006114460993558168 lr:2.6218789546486234e-05 tokens_per_second_per_gpu:6985.433777139989
Step 174 | loss:0.0005350064020603895 lr:2.560701704306336e-05 tokens_per_second_per_gpu:7022.5454173424805
Step 175 | loss:0.0007083043456077576 lr:2.500000000000001e-05 tokens_per_second_per_gpu:7102.870775576876
Step 176 | loss:0.005003070924431086 lr:2.4397856756471432e-05 tokens_per_second_per_gpu:7032.311504023939
Step 177 | loss:0.0003096727596130222 lr:2.3800704701496053e-05 tokens_per_second_per_gpu:6919.153299954087
Step 178 | loss:0.0017927672015503049 lr:2.3208660251050158e-05 tokens_per_second_per_gpu:7074.962422164824
Step 179 | loss:0.00044130691094323993 lr:2.2621838825372493e-05 tokens_per_second_per_gpu:7048.084112071555
Step 180 | loss:0.0010046741226688027 lr:2.2040354826462668e-05 tokens_per_second_per_gpu:6994.931293278433
Step 181 | loss:0.00036933235242031515 lr:2.1464321615778422e-05 tokens_per_second_per_gpu:6974.1972940677215
Step 182 | loss:0.001002048491500318 lr:2.0893851492135537e-05 tokens_per_second_per_gpu:7101.597518115631
Step 183 | loss:0.0010289422934874892 lr:2.0329055669814934e-05 tokens_per_second_per_gpu:7068.136111127554
Step 184 | loss:0.0006893848767504096 lr:1.977004425688126e-05 tokens_per_second_per_gpu:6959.682595829497
Step 185 | loss:0.0005450312164612114 lr:1.9216926233717085e-05 tokens_per_second_per_gpu:7024.659058198706
Step 186 | loss:0.0009888313943520188 lr:1.866980943177699e-05 tokens_per_second_per_gpu:7015.7765368712035
Step 187 | loss:0.000688783940859139 lr:1.8128800512565513e-05 tokens_per_second_per_gpu:7070.006080875613
Step 188 | loss:0.00022755961981602013 lr:1.7594004946843456e-05 tokens_per_second_per_gpu:6888.823673728325
Step 189 | loss:0.0014005395350977778 lr:1.7065526994065973e-05 tokens_per_second_per_gpu:6912.165675400079
Step 190 | loss:0.0022951557766646147 lr:1.6543469682057106e-05 tokens_per_second_per_gpu:6980.394889404463
Step 191 | loss:0.00045024571591056883 lr:1.602793478692419e-05 tokens_per_second_per_gpu:7036.436459662827
Step 192 | loss:0.0006360564148053527 lr:1.551902281321651e-05 tokens_per_second_per_gpu:7048.19405828195
Step 193 | loss:0.0007029520929791033 lr:1.5016832974331724e-05 tokens_per_second_per_gpu:7054.503817613241
Step 194 | loss:0.0008534158696420491 lr:1.4521463173173965e-05 tokens_per_second_per_gpu:7059.044748122176
Step 195 | loss:0.00021115591516718268 lr:1.4033009983067452e-05 tokens_per_second_per_gpu:6939.515954161051
Step 196 | loss:0.0015203531365841627 lr:1.3551568628929434e-05 tokens_per_second_per_gpu:6948.058100425101
Step 197 | loss:0.002487808233126998 lr:1.3077232968705805e-05 tokens_per_second_per_gpu:7069.317094869838
Step 198 | loss:0.002162965014576912 lr:1.2610095475073414e-05 tokens_per_second_per_gpu:6728.6887674913605
Step 199 | loss:0.0006113103008829057 lr:1.2150247217412186e-05 tokens_per_second_per_gpu:7008.400014096715
Step 200 | loss:0.0007048815605230629 lr:1.1697777844051105e-05 tokens_per_second_per_gpu:7033.563886176666
Step 201 | loss:0.0003906804195139557 lr:1.1252775564791024e-05 tokens_per_second_per_gpu:6982.291468532644
Step 202 | loss:4.599908788804896e-05 lr:1.0815327133708015e-05 tokens_per_second_per_gpu:6826.001454252012
Step 203 | loss:0.0005897274822928011 lr:1.0385517832240471e-05 tokens_per_second_per_gpu:7043.910731773956
Step 204 | loss:0.000618042191490531 lr:9.963431452563332e-06 tokens_per_second_per_gpu:7080.759744602586
Step 205 | loss:0.0003493254189379513 lr:9.549150281252633e-06 tokens_per_second_per_gpu:6883.641000116994
Step 206 | loss:0.00022350235667545348 lr:9.142755083243576e-06 tokens_per_second_per_gpu:6922.743047267518
Step 207 | loss:0.0002449267194606364 lr:8.744325086085248e-06 tokens_per_second_per_gpu:6912.966963063889
Step 208 | loss:0.0005361480871215463 lr:8.353937964495029e-06 tokens_per_second_per_gpu:7013.2727621643135
Step 209 | loss:0.0005851382156834006 lr:7.971669825215788e-06 tokens_per_second_per_gpu:7003.412445068256
Step 210 | loss:0.0007421344635076821 lr:7.597595192178702e-06 tokens_per_second_per_gpu:6975.349563364538
Step 211 | loss:0.0009937129216268659 lr:7.2317869919746705e-06 tokens_per_second_per_gpu:6981.684793351161
Step 212 | loss:0.0005268529057502747 lr:6.874316539637127e-06 tokens_per_second_per_gpu:7064.740823991437
Step 213 | loss:0.0008532798965461552 lr:6.52525352473905e-06 tokens_per_second_per_gpu:7072.510591117289
Step 214 | loss:0.0001894011948024854 lr:6.184665997806832e-06 tokens_per_second_per_gpu:6886.083278368206
Step 215 | loss:0.0004504088428802788 lr:5.852620357053651e-06 tokens_per_second_per_gpu:7003.6066512499
Step 216 | loss:0.0021212417632341385 lr:5.529181335435124e-06 tokens_per_second_per_gpu:7105.646434305893
Step 217 | loss:0.0002717859752010554 lr:5.214411988029355e-06 tokens_per_second_per_gpu:6918.71299524638
Step 218 | loss:0.0007365220808424056 lr:4.908373679744316e-06 tokens_per_second_per_gpu:6985.169240413218
Step 219 | loss:0.0007599032833240926 lr:4.611126073354571e-06 tokens_per_second_per_gpu:7003.10335104368
Step 220 | loss:0.00047508926945738494 lr:4.322727117869951e-06 tokens_per_second_per_gpu:7044.045002265179
Step 221 | loss:0.0005642809555865824 lr:4.043233037238281e-06 tokens_per_second_per_gpu:7056.110730860521
Step 222 | loss:0.00042012144695036113 lr:3.772698319384349e-06 tokens_per_second_per_gpu:6945.638111020892
Step 223 | loss:0.0008549286285415292 lr:3.511175705587433e-06 tokens_per_second_per_gpu:7073.617767470212
Step 224 | loss:0.0009669017745181918 lr:3.258716180199278e-06 tokens_per_second_per_gpu:7045.666626093695
Step 225 | loss:0.000286176975350827 lr:3.0153689607045845e-06 tokens_per_second_per_gpu:6923.996506388525
Step 226 | loss:0.0009605163941159844 lr:2.7811814881259503e-06 tokens_per_second_per_gpu:7036.433001709479
Step 227 | loss:0.0009142288472503424 lr:2.5561994177751737e-06 tokens_per_second_per_gpu:6084.156655325015
Step 228 | loss:0.0005242257611826062 lr:2.340466610352654e-06 tokens_per_second_per_gpu:7061.7341601012795
Step 229 | loss:0.0008552082581445575 lr:2.134025123396638e-06 tokens_per_second_per_gpu:7089.447884252284
Step 230 | loss:0.0004530947480816394 lr:1.9369152030840556e-06 tokens_per_second_per_gpu:6949.767688804591
Step 231 | loss:0.0004227949830237776 lr:1.7491752763844293e-06 tokens_per_second_per_gpu:6959.831093608465
Step 232 | loss:0.003169838571920991 lr:1.5708419435684462e-06 tokens_per_second_per_gpu:6929.438798102989
Step 233 | loss:0.0006190282292664051 lr:1.4019499710726913e-06 tokens_per_second_per_gpu:7063.779883207605
Step 234 | loss:0.0002394295734120533 lr:1.2425322847218368e-06 tokens_per_second_per_gpu:6899.688264327002
Step 235 | loss:0.000677535543218255 lr:1.0926199633097157e-06 tokens_per_second_per_gpu:7079.295576505652
Step 236 | loss:0.0005709402030333877 lr:9.522422325404235e-07 tokens_per_second_per_gpu:6951.402627736772
Step 237 | loss:0.00178045395296067 lr:8.214264593307098e-07 tokens_per_second_per_gpu:7130.343199080375
Step 238 | loss:0.0016613630577921867 lr:7.001981464747565e-07 tokens_per_second_per_gpu:7055.96738827242
Step 239 | loss:0.0030412583146244287 lr:5.885809276723608e-07 tokens_per_second_per_gpu:6942.834318919953
Step 240 | loss:0.00047537911450490355 lr:4.865965629214819e-07 tokens_per_second_per_gpu:7026.220788003302
Step 241 | loss:0.0006836542161181569 lr:3.9426493427611177e-07 tokens_per_second_per_gpu:7063.567018160837
Step 242 | loss:0.0033634465653449297 lr:3.1160404197018154e-07 tokens_per_second_per_gpu:7023.722040134441
Step 243 | loss:0.0004719410208053887 lr:2.386300009084408e-07 tokens_per_second_per_gpu:7019.520195582725
Step 244 | loss:0.0008831517188809812 lr:1.753570375247815e-07 tokens_per_second_per_gpu:7101.294649489278
Step 245 | loss:0.002968840068206191 lr:1.2179748700879012e-07 tokens_per_second_per_gpu:7071.806049126061
Step 246 | loss:0.0005592398811131716 lr:7.796179090094891e-08 tokens_per_second_per_gpu:7054.492786734295
Step 247 | loss:0.0009493291145190597 lr:4.385849505708084e-08 tokens_per_second_per_gpu:6837.375023433372
Step 248 | loss:0.0006476514390669763 lr:1.949424798228239e-08 tokens_per_second_per_gpu:7162.57712209533
Step 249 | loss:0.0002708960964810103 lr:4.873799534788059e-09 tokens_per_second_per_gpu:6958.8348383308685
Step 250 | loss:0.0019458368187770247 lr:0.0 tokens_per_second_per_gpu:7022.68891283962