ekinakyurek's picture
Upload folder using huggingface_hub
0bfc910 verified
raw
history blame
26.8 kB
Step 1 | loss:0.095920130610466 lr:4.000000000000001e-06 tokens_per_second_per_gpu:6556.856319066329
Step 2 | loss:0.011275455355644226 lr:8.000000000000001e-06 tokens_per_second_per_gpu:7067.614503725045
Step 3 | loss:0.02797607332468033 lr:1.2e-05 tokens_per_second_per_gpu:7125.295324674653
Step 4 | loss:0.006133408285677433 lr:1.6000000000000003e-05 tokens_per_second_per_gpu:7066.554089866459
Step 5 | loss:0.025178268551826477 lr:2e-05 tokens_per_second_per_gpu:6763.903727921412
Step 6 | loss:0.01040574535727501 lr:2.4e-05 tokens_per_second_per_gpu:7102.968276299749
Step 7 | loss:0.007350593339651823 lr:2.8000000000000003e-05 tokens_per_second_per_gpu:6983.895796037691
Step 8 | loss:0.005881750024855137 lr:3.2000000000000005e-05 tokens_per_second_per_gpu:7095.502823207143
Step 9 | loss:0.017233092337846756 lr:3.6e-05 tokens_per_second_per_gpu:7039.832255525476
Step 10 | loss:0.01895858906209469 lr:4e-05 tokens_per_second_per_gpu:7044.460698499007
Step 11 | loss:0.03846563771367073 lr:4.4000000000000006e-05 tokens_per_second_per_gpu:6954.633524446355
Step 12 | loss:0.02557559311389923 lr:4.8e-05 tokens_per_second_per_gpu:7087.286732082519
Step 13 | loss:0.007976368069648743 lr:5.2000000000000004e-05 tokens_per_second_per_gpu:7087.607460928441
Step 14 | loss:0.01716320589184761 lr:5.6000000000000006e-05 tokens_per_second_per_gpu:7077.492847624228
Step 15 | loss:0.012465793639421463 lr:6e-05 tokens_per_second_per_gpu:7045.463132018335
Step 16 | loss:0.007910924032330513 lr:6.400000000000001e-05 tokens_per_second_per_gpu:7126.890030033927
Step 17 | loss:0.011759893968701363 lr:6.800000000000001e-05 tokens_per_second_per_gpu:6928.14359316902
Step 18 | loss:0.0061362688429653645 lr:7.2e-05 tokens_per_second_per_gpu:7136.8955556179435
Step 19 | loss:0.0020642681047320366 lr:7.6e-05 tokens_per_second_per_gpu:7012.360505470083
Step 20 | loss:0.0017075837822631001 lr:8e-05 tokens_per_second_per_gpu:7105.400955617253
Step 21 | loss:0.003554040566086769 lr:8.4e-05 tokens_per_second_per_gpu:7112.751193049365
Step 22 | loss:0.0050487820990383625 lr:8.800000000000001e-05 tokens_per_second_per_gpu:6722.451839325025
Step 23 | loss:0.0066717686131596565 lr:9.200000000000001e-05 tokens_per_second_per_gpu:6750.501703324968
Step 24 | loss:0.004712450318038464 lr:9.6e-05 tokens_per_second_per_gpu:6948.183914544187
Step 25 | loss:0.0004461197822820395 lr:0.0001 tokens_per_second_per_gpu:7158.423351301243
Step 26 | loss:0.010683871805667877 lr:9.999512620046522e-05 tokens_per_second_per_gpu:7071.022299474951
Step 27 | loss:0.00013994208711665124 lr:9.998050575201771e-05 tokens_per_second_per_gpu:6988.915103393356
Step 28 | loss:0.0001019828996504657 lr:9.995614150494293e-05 tokens_per_second_per_gpu:7095.128708321274
Step 29 | loss:0.003132760524749756 lr:9.992203820909906e-05 tokens_per_second_per_gpu:7198.909712834217
Step 30 | loss:0.003380765672773123 lr:9.987820251299122e-05 tokens_per_second_per_gpu:7113.494643359176
Step 31 | loss:0.0016515518072992563 lr:9.982464296247522e-05 tokens_per_second_per_gpu:7121.983511402419
Step 32 | loss:0.0027374140918254852 lr:9.976136999909156e-05 tokens_per_second_per_gpu:6913.815729790802
Step 33 | loss:0.00037197332130745053 lr:9.968839595802982e-05 tokens_per_second_per_gpu:7112.895489557705
Step 34 | loss:0.05401809513568878 lr:9.96057350657239e-05 tokens_per_second_per_gpu:6737.663655125681
Step 35 | loss:0.02879168838262558 lr:9.951340343707852e-05 tokens_per_second_per_gpu:6990.194943817553
Step 36 | loss:0.0001365482748951763 lr:9.941141907232765e-05 tokens_per_second_per_gpu:7097.879228937666
Step 37 | loss:8.674233686178923e-05 lr:9.929980185352526e-05 tokens_per_second_per_gpu:6749.126617139935
Step 38 | loss:0.00011085063306381926 lr:9.917857354066931e-05 tokens_per_second_per_gpu:7056.886586329071
Step 39 | loss:0.0011464423732832074 lr:9.904775776745958e-05 tokens_per_second_per_gpu:7075.4079406976225
Step 40 | loss:0.0003272634348832071 lr:9.890738003669029e-05 tokens_per_second_per_gpu:6934.247672693781
Step 41 | loss:0.0007803998305462301 lr:9.875746771527816e-05 tokens_per_second_per_gpu:7090.02169677753
Step 42 | loss:0.001429117051884532 lr:9.859805002892732e-05 tokens_per_second_per_gpu:6907.384217480435
Step 43 | loss:0.0019045633962377906 lr:9.842915805643155e-05 tokens_per_second_per_gpu:7124.613918264794
Step 44 | loss:0.00013557741476688534 lr:9.825082472361557e-05 tokens_per_second_per_gpu:7032.515103109555
Step 45 | loss:0.00023527612211182714 lr:9.806308479691595e-05 tokens_per_second_per_gpu:7083.146734444354
Step 46 | loss:0.00022388831712305546 lr:9.786597487660337e-05 tokens_per_second_per_gpu:7126.807798501739
Step 47 | loss:9.057059651240706e-05 lr:9.765953338964735e-05 tokens_per_second_per_gpu:7004.006151805449
Step 48 | loss:0.0007530518341809511 lr:9.744380058222483e-05 tokens_per_second_per_gpu:6756.393996151731
Step 49 | loss:0.0005137891857884824 lr:9.721881851187406e-05 tokens_per_second_per_gpu:6917.165238818346
Step 50 | loss:0.00025636813370510936 lr:9.698463103929542e-05 tokens_per_second_per_gpu:7123.511195363611
Step 51 | loss:0.0007551180315203965 lr:9.674128381980072e-05 tokens_per_second_per_gpu:7010.932911697327
Step 52 | loss:7.878890755819157e-05 lr:9.648882429441257e-05 tokens_per_second_per_gpu:7083.529623357655
Step 53 | loss:6.05294517299626e-05 lr:9.622730168061567e-05 tokens_per_second_per_gpu:6949.443749267703
Step 54 | loss:0.0001629233593121171 lr:9.595676696276172e-05 tokens_per_second_per_gpu:7126.317389661889
Step 55 | loss:7.254988304339349e-05 lr:9.567727288213005e-05 tokens_per_second_per_gpu:7130.296837355082
Step 56 | loss:0.005167370196431875 lr:9.538887392664544e-05 tokens_per_second_per_gpu:6413.1116055051425
Step 57 | loss:2.9441485821735114e-05 lr:9.50916263202557e-05 tokens_per_second_per_gpu:7141.798590552635
Step 58 | loss:0.005892408080399036 lr:9.478558801197065e-05 tokens_per_second_per_gpu:6945.995637428901
Step 59 | loss:0.00014601480506826192 lr:9.447081866456489e-05 tokens_per_second_per_gpu:7156.845908940097
Step 60 | loss:3.0792492907494307e-05 lr:9.414737964294636e-05 tokens_per_second_per_gpu:7149.460078809537
Step 61 | loss:0.004181995987892151 lr:9.381533400219318e-05 tokens_per_second_per_gpu:7063.689467419139
Step 62 | loss:0.0013692781794816256 lr:9.347474647526095e-05 tokens_per_second_per_gpu:7014.979453202723
Step 63 | loss:0.0001953955361386761 lr:9.312568346036288e-05 tokens_per_second_per_gpu:6773.588566811737
Step 64 | loss:0.0003141107445117086 lr:9.276821300802534e-05 tokens_per_second_per_gpu:7073.6155690059195
Step 65 | loss:0.0052342661656439304 lr:9.24024048078213e-05 tokens_per_second_per_gpu:6779.324399314853
Step 66 | loss:0.0026232542004436255 lr:9.202833017478422e-05 tokens_per_second_per_gpu:7154.2732373434255
Step 67 | loss:0.00011536344391060993 lr:9.164606203550497e-05 tokens_per_second_per_gpu:6763.7901342951445
Step 68 | loss:0.00037219212390482426 lr:9.125567491391476e-05 tokens_per_second_per_gpu:7142.497390016467
Step 69 | loss:0.000342419371008873 lr:9.085724491675642e-05 tokens_per_second_per_gpu:7103.38879687949
Step 70 | loss:7.268437911989167e-05 lr:9.045084971874738e-05 tokens_per_second_per_gpu:7022.266092528667
Step 71 | loss:0.00012057813728461042 lr:9.003656854743667e-05 tokens_per_second_per_gpu:7111.043193266059
Step 72 | loss:0.0002662487095221877 lr:8.961448216775954e-05 tokens_per_second_per_gpu:7172.772361224292
Step 73 | loss:8.909632742870599e-05 lr:8.9184672866292e-05 tokens_per_second_per_gpu:7127.361689929295
Step 74 | loss:7.305494364118204e-05 lr:8.874722443520899e-05 tokens_per_second_per_gpu:6751.502002947895
Step 75 | loss:4.4741289457306266e-05 lr:8.83022221559489e-05 tokens_per_second_per_gpu:7128.328549895998
Step 76 | loss:0.00013019990001339465 lr:8.784975278258783e-05 tokens_per_second_per_gpu:7088.33270470313
Step 77 | loss:2.7271093131275848e-05 lr:8.73899045249266e-05 tokens_per_second_per_gpu:7115.858493448846
Step 78 | loss:1.837199852161575e-05 lr:8.692276703129421e-05 tokens_per_second_per_gpu:7123.630146977778
Step 79 | loss:7.973476022016257e-05 lr:8.644843137107059e-05 tokens_per_second_per_gpu:7100.583468941698
Step 80 | loss:0.00010700645361794159 lr:8.596699001693255e-05 tokens_per_second_per_gpu:7126.0436215618465
Step 81 | loss:1.440356754756067e-05 lr:8.547853682682604e-05 tokens_per_second_per_gpu:7082.0900242070575
Step 82 | loss:2.2106645701569505e-05 lr:8.498316702566828e-05 tokens_per_second_per_gpu:6945.334028898965
Step 83 | loss:4.912256190436892e-05 lr:8.44809771867835e-05 tokens_per_second_per_gpu:6275.915836697447
Step 84 | loss:7.857841410441324e-05 lr:8.397206521307584e-05 tokens_per_second_per_gpu:7035.829306153114
Step 85 | loss:2.9898668799432926e-05 lr:8.345653031794292e-05 tokens_per_second_per_gpu:7137.511845786461
Step 86 | loss:4.0803966840030625e-05 lr:8.293447300593402e-05 tokens_per_second_per_gpu:7113.763041118208
Step 87 | loss:9.09728532860754e-06 lr:8.240599505315655e-05 tokens_per_second_per_gpu:7069.413052337877
Step 88 | loss:1.4241628377931193e-05 lr:8.18711994874345e-05 tokens_per_second_per_gpu:7092.692539870378
Step 89 | loss:3.1743966246722266e-05 lr:8.133019056822304e-05 tokens_per_second_per_gpu:6988.007699999395
Step 90 | loss:1.4580432434740942e-05 lr:8.07830737662829e-05 tokens_per_second_per_gpu:6970.96289460495
Step 91 | loss:2.946998029074166e-05 lr:8.022995574311876e-05 tokens_per_second_per_gpu:7145.502672665943
Step 92 | loss:1.5837116734473966e-05 lr:7.967094433018508e-05 tokens_per_second_per_gpu:7097.314311508971
Step 93 | loss:5.219048398430459e-05 lr:7.910614850786448e-05 tokens_per_second_per_gpu:6752.270476519438
Step 94 | loss:0.00028034168644808233 lr:7.85356783842216e-05 tokens_per_second_per_gpu:7136.634101033642
Step 95 | loss:2.693287024158053e-05 lr:7.795964517353735e-05 tokens_per_second_per_gpu:7001.703145273083
Step 96 | loss:0.00027029935154132545 lr:7.737816117462752e-05 tokens_per_second_per_gpu:6942.2237979372685
Step 97 | loss:6.184071935422253e-06 lr:7.679133974894983e-05 tokens_per_second_per_gpu:7086.061398679753
Step 98 | loss:0.010054090060293674 lr:7.619929529850397e-05 tokens_per_second_per_gpu:7141.101535395458
Step 99 | loss:5.9453604990267195e-06 lr:7.560214324352858e-05 tokens_per_second_per_gpu:6926.217210492452
Step 100 | loss:2.3493716071243398e-05 lr:7.500000000000001e-05 tokens_per_second_per_gpu:7144.601392397747
Step 101 | loss:1.703025736787822e-05 lr:7.439298295693665e-05 tokens_per_second_per_gpu:6770.243036810235
Step 102 | loss:1.1920383258257061e-05 lr:7.378121045351378e-05 tokens_per_second_per_gpu:6897.147880415645
Step 103 | loss:1.5763087503728457e-05 lr:7.316480175599309e-05 tokens_per_second_per_gpu:6923.1631612930805
Step 104 | loss:1.5658185930078616e-06 lr:7.254387703447154e-05 tokens_per_second_per_gpu:7075.10253888922
Step 105 | loss:0.010088295675814152 lr:7.191855733945387e-05 tokens_per_second_per_gpu:6938.130705407873
Step 106 | loss:2.7563125968299573e-06 lr:7.128896457825364e-05 tokens_per_second_per_gpu:7101.828144676874
Step 107 | loss:0.001394405378960073 lr:7.06552214912271e-05 tokens_per_second_per_gpu:7099.555864887245
Step 108 | loss:1.549895023345016e-05 lr:7.001745162784477e-05 tokens_per_second_per_gpu:7048.084219031862
Step 109 | loss:6.027940344210947e-06 lr:6.937577932260515e-05 tokens_per_second_per_gpu:7091.785008005878
Step 110 | loss:5.082295047031948e-06 lr:6.873032967079561e-05 tokens_per_second_per_gpu:7105.683177465976
Step 111 | loss:5.4094048209663015e-06 lr:6.808122850410461e-05 tokens_per_second_per_gpu:6971.306698211071
Step 112 | loss:4.127318243263289e-05 lr:6.742860236609077e-05 tokens_per_second_per_gpu:6764.929941485346
Step 113 | loss:1.5480782167287543e-06 lr:6.677257848751277e-05 tokens_per_second_per_gpu:6930.561901657678
Step 114 | loss:1.0831701729330234e-05 lr:6.611328476152557e-05 tokens_per_second_per_gpu:7094.6843903692825
Step 115 | loss:8.86739871930331e-06 lr:6.545084971874738e-05 tokens_per_second_per_gpu:7074.760688318036
Step 116 | loss:0.00014212621317710727 lr:6.478540250220234e-05 tokens_per_second_per_gpu:7171.942317164167
Step 117 | loss:5.5098298616940156e-06 lr:6.411707284214384e-05 tokens_per_second_per_gpu:7090.519599585456
Step 118 | loss:5.033820343669504e-06 lr:6.344599103076329e-05 tokens_per_second_per_gpu:7089.8361782271
Step 119 | loss:1.8586304122436559e-06 lr:6.277228789678953e-05 tokens_per_second_per_gpu:7023.746577217382
Step 120 | loss:5.22351683684974e-06 lr:6.209609477998338e-05 tokens_per_second_per_gpu:7100.137314331823
Step 121 | loss:1.0904846021730918e-05 lr:6.141754350553279e-05 tokens_per_second_per_gpu:7083.725366831435
Step 122 | loss:7.427526270475937e-06 lr:6.073676635835317e-05 tokens_per_second_per_gpu:7083.34520016218
Step 123 | loss:4.169386556895915e-06 lr:6.005389605729824e-05 tokens_per_second_per_gpu:7154.672474656313
Step 124 | loss:2.3857876385591226e-06 lr:5.9369065729286245e-05 tokens_per_second_per_gpu:7085.866604330056
Step 125 | loss:0.022122755646705627 lr:5.868240888334653e-05 tokens_per_second_per_gpu:6518.412144651196
Step 126 | loss:0.00023554684594273567 lr:5.799405938459175e-05 tokens_per_second_per_gpu:7111.080369052329
Step 127 | loss:2.3868202333687805e-05 lr:5.730415142812059e-05 tokens_per_second_per_gpu:7119.866771705771
Step 128 | loss:2.593579665699508e-06 lr:5.661281951285613e-05 tokens_per_second_per_gpu:7081.817000989164
Step 129 | loss:1.546436942589935e-05 lr:5.5920198415325064e-05 tokens_per_second_per_gpu:7104.365096993394
Step 130 | loss:4.6952482080087066e-06 lr:5.522642316338268e-05 tokens_per_second_per_gpu:7069.877335741978
Step 131 | loss:4.957473720423877e-06 lr:5.453162900988902e-05 tokens_per_second_per_gpu:7026.959434628656
Step 132 | loss:1.1660313248285092e-05 lr:5.383595140634093e-05 tokens_per_second_per_gpu:7106.335876256085
Step 133 | loss:5.8714545048133004e-06 lr:5.313952597646568e-05 tokens_per_second_per_gpu:7076.445453409441
Step 134 | loss:3.589453990571201e-05 lr:5.244248848978067e-05 tokens_per_second_per_gpu:7004.775120240859
Step 135 | loss:0.0007721065194346011 lr:5.174497483512506e-05 tokens_per_second_per_gpu:7083.072697082917
Step 136 | loss:1.050534592650365e-05 lr:5.104712099416785e-05 tokens_per_second_per_gpu:7037.22815254605
Step 137 | loss:7.053890385577688e-06 lr:5.034906301489808e-05 tokens_per_second_per_gpu:7091.932317901008
Step 138 | loss:7.2755865403451025e-06 lr:4.965093698510193e-05 tokens_per_second_per_gpu:7162.6675799979175
Step 139 | loss:3.0469589091808302e-06 lr:4.895287900583216e-05 tokens_per_second_per_gpu:7132.907026293549
Step 140 | loss:5.9093326854053885e-06 lr:4.825502516487497e-05 tokens_per_second_per_gpu:6957.665147967468
Step 141 | loss:0.0026946004945784807 lr:4.755751151021934e-05 tokens_per_second_per_gpu:6994.636738544895
Step 142 | loss:0.00568818487226963 lr:4.6860474023534335e-05 tokens_per_second_per_gpu:7068.517297926472
Step 143 | loss:1.4650881894340273e-05 lr:4.616404859365907e-05 tokens_per_second_per_gpu:6974.188603109633
Step 144 | loss:8.280513611680362e-06 lr:4.5468370990111006e-05 tokens_per_second_per_gpu:7118.150525572311
Step 145 | loss:1.2850611710746307e-05 lr:4.477357683661734e-05 tokens_per_second_per_gpu:6923.364321947428
Step 146 | loss:9.733505066833459e-06 lr:4.407980158467495e-05 tokens_per_second_per_gpu:7090.836254363847
Step 147 | loss:2.712718014663551e-06 lr:4.3387180487143876e-05 tokens_per_second_per_gpu:7111.314223927678
Step 148 | loss:0.004740750417113304 lr:4.269584857187943e-05 tokens_per_second_per_gpu:6709.068384877169
Step 149 | loss:9.103751835937146e-06 lr:4.2005940615408264e-05 tokens_per_second_per_gpu:7142.5069534336635
Step 150 | loss:1.116573275794508e-05 lr:4.131759111665349e-05 tokens_per_second_per_gpu:7120.102535413326
Step 151 | loss:1.39646172101493e-05 lr:4.063093427071376e-05 tokens_per_second_per_gpu:7168.456233290528
Step 152 | loss:5.1016868383158e-06 lr:3.9946103942701777e-05 tokens_per_second_per_gpu:7005.718959893138
Step 153 | loss:1.5659970813430846e-05 lr:3.926323364164684e-05 tokens_per_second_per_gpu:6767.837722511169
Step 154 | loss:8.122730832837988e-06 lr:3.858245649446721e-05 tokens_per_second_per_gpu:7128.275868255587
Step 155 | loss:7.804651431797538e-06 lr:3.790390522001662e-05 tokens_per_second_per_gpu:7070.774330591048
Step 156 | loss:6.383683739841217e-06 lr:3.7227712103210486e-05 tokens_per_second_per_gpu:7067.696476280637
Step 157 | loss:1.3327877240953967e-05 lr:3.655400896923672e-05 tokens_per_second_per_gpu:7135.401622008483
Step 158 | loss:1.1789760719693732e-05 lr:3.588292715785617e-05 tokens_per_second_per_gpu:6756.71219093518
Step 159 | loss:9.950960702553857e-06 lr:3.5214597497797684e-05 tokens_per_second_per_gpu:7088.09888891159
Step 160 | loss:1.3951709661341738e-05 lr:3.4549150281252636e-05 tokens_per_second_per_gpu:6721.710621091984
Step 161 | loss:1.6268433682853356e-05 lr:3.388671523847445e-05 tokens_per_second_per_gpu:7050.197857113174
Step 162 | loss:5.97596590523608e-06 lr:3.322742151248725e-05 tokens_per_second_per_gpu:7064.999097962476
Step 163 | loss:4.166702183283633e-06 lr:3.257139763390925e-05 tokens_per_second_per_gpu:7098.945404265693
Step 164 | loss:2.7706118999049067e-06 lr:3.1918771495895396e-05 tokens_per_second_per_gpu:7120.89803549751
Step 165 | loss:1.6839154568515369e-06 lr:3.12696703292044e-05 tokens_per_second_per_gpu:7110.33802272479
Step 166 | loss:0.005325336009263992 lr:3.062422067739485e-05 tokens_per_second_per_gpu:6747.632702732379
Step 167 | loss:1.6316773326252587e-05 lr:2.9982548372155263e-05 tokens_per_second_per_gpu:7095.015525415171
Step 168 | loss:3.18794127451838e-06 lr:2.934477850877292e-05 tokens_per_second_per_gpu:7166.411742899654
Step 169 | loss:5.900651558476966e-06 lr:2.8711035421746367e-05 tokens_per_second_per_gpu:6254.396085225209
Step 170 | loss:1.0669767107174266e-05 lr:2.8081442660546125e-05 tokens_per_second_per_gpu:6878.428458649318
Step 171 | loss:3.7786774100823095e-06 lr:2.7456122965528475e-05 tokens_per_second_per_gpu:7101.796183028162
Step 172 | loss:9.483410394750535e-06 lr:2.6835198244006927e-05 tokens_per_second_per_gpu:7077.081803745961
Step 173 | loss:3.0907565360394074e-06 lr:2.6218789546486234e-05 tokens_per_second_per_gpu:7061.251531571983
Step 174 | loss:1.3803364709019661e-05 lr:2.560701704306336e-05 tokens_per_second_per_gpu:7033.626539270292
Step 175 | loss:7.721065230725799e-06 lr:2.500000000000001e-05 tokens_per_second_per_gpu:7051.633663043242
Step 176 | loss:0.0005931869964115322 lr:2.4397856756471432e-05 tokens_per_second_per_gpu:6756.7656033637
Step 177 | loss:8.174411777872592e-05 lr:2.3800704701496053e-05 tokens_per_second_per_gpu:6977.721365681852
Step 178 | loss:2.0210839011269854e-06 lr:2.3208660251050158e-05 tokens_per_second_per_gpu:7122.747821928415
Step 179 | loss:4.958463705406757e-06 lr:2.2621838825372493e-05 tokens_per_second_per_gpu:7094.876632261525
Step 180 | loss:4.772512966155773e-06 lr:2.2040354826462668e-05 tokens_per_second_per_gpu:7062.683029301653
Step 181 | loss:2.3513028281740844e-05 lr:2.1464321615778422e-05 tokens_per_second_per_gpu:7098.989386945182
Step 182 | loss:1.4548217222909443e-05 lr:2.0893851492135537e-05 tokens_per_second_per_gpu:6514.957332684294
Step 183 | loss:7.288316282938467e-06 lr:2.0329055669814934e-05 tokens_per_second_per_gpu:6913.485028335978
Step 184 | loss:4.7170276957331225e-05 lr:1.977004425688126e-05 tokens_per_second_per_gpu:7088.946830395968
Step 185 | loss:6.1211981119413394e-06 lr:1.9216926233717085e-05 tokens_per_second_per_gpu:7122.556745776578
Step 186 | loss:1.419593991158763e-05 lr:1.866980943177699e-05 tokens_per_second_per_gpu:7103.548288454274
Step 187 | loss:2.666062573553063e-05 lr:1.8128800512565513e-05 tokens_per_second_per_gpu:7142.940833758842
Step 188 | loss:2.275184669997543e-05 lr:1.7594004946843456e-05 tokens_per_second_per_gpu:6911.982740540522
Step 189 | loss:8.638600775157101e-06 lr:1.7065526994065973e-05 tokens_per_second_per_gpu:7045.822788327076
Step 190 | loss:6.441905043175211e-06 lr:1.6543469682057106e-05 tokens_per_second_per_gpu:7002.883558227881
Step 191 | loss:5.2613804655265994e-06 lr:1.602793478692419e-05 tokens_per_second_per_gpu:7061.334606678873
Step 192 | loss:5.115051862958353e-06 lr:1.551902281321651e-05 tokens_per_second_per_gpu:7081.344506649406
Step 193 | loss:4.325819190853508e-06 lr:1.5016832974331724e-05 tokens_per_second_per_gpu:7114.480259402477
Step 194 | loss:2.7898044208995998e-05 lr:1.4521463173173965e-05 tokens_per_second_per_gpu:7155.775083111662
Step 195 | loss:5.0729381655401085e-06 lr:1.4033009983067452e-05 tokens_per_second_per_gpu:7065.154510843982
Step 196 | loss:5.52778146811761e-06 lr:1.3551568628929434e-05 tokens_per_second_per_gpu:7107.916120692827
Step 197 | loss:6.536924956890289e-06 lr:1.3077232968705805e-05 tokens_per_second_per_gpu:6771.164085203082
Step 198 | loss:7.708586963417474e-06 lr:1.2610095475073414e-05 tokens_per_second_per_gpu:7000.249044699692
Step 199 | loss:5.7632182688394096e-06 lr:1.2150247217412186e-05 tokens_per_second_per_gpu:7070.189057783403
Step 200 | loss:8.780374628258869e-06 lr:1.1697777844051105e-05 tokens_per_second_per_gpu:7107.3643583189005
Step 201 | loss:7.296015610336326e-06 lr:1.1252775564791024e-05 tokens_per_second_per_gpu:6967.501888088341
Step 202 | loss:1.9197226720280014e-05 lr:1.0815327133708015e-05 tokens_per_second_per_gpu:7116.710593585159
Step 203 | loss:8.767248800722882e-06 lr:1.0385517832240471e-05 tokens_per_second_per_gpu:7161.0418792240025
Step 204 | loss:0.003306688042357564 lr:9.963431452563332e-06 tokens_per_second_per_gpu:6774.476751603191
Step 205 | loss:3.733004996320233e-05 lr:9.549150281252633e-06 tokens_per_second_per_gpu:7160.624889852235
Step 206 | loss:9.600432349543553e-06 lr:9.142755083243576e-06 tokens_per_second_per_gpu:7061.560215408144
Step 207 | loss:2.108006265189033e-05 lr:8.744325086085248e-06 tokens_per_second_per_gpu:6998.491056264587
Step 208 | loss:8.151075235218741e-06 lr:8.353937964495029e-06 tokens_per_second_per_gpu:7005.877095061543
Step 209 | loss:2.5786323476495454e-06 lr:7.971669825215788e-06 tokens_per_second_per_gpu:7078.701947031986
Step 210 | loss:1.5541034372290596e-05 lr:7.597595192178702e-06 tokens_per_second_per_gpu:7035.752319245688
Step 211 | loss:6.282682988967281e-06 lr:7.2317869919746705e-06 tokens_per_second_per_gpu:6965.551514144136
Step 212 | loss:7.435703992086928e-06 lr:6.874316539637127e-06 tokens_per_second_per_gpu:7105.4871099774355
Step 213 | loss:4.855353836319409e-05 lr:6.52525352473905e-06 tokens_per_second_per_gpu:6904.560617649615
Step 214 | loss:4.628564965969417e-06 lr:6.184665997806832e-06 tokens_per_second_per_gpu:7107.06615237654
Step 215 | loss:9.4095730673871e-06 lr:5.852620357053651e-06 tokens_per_second_per_gpu:7085.834128481069
Step 216 | loss:7.5714237937063444e-06 lr:5.529181335435124e-06 tokens_per_second_per_gpu:7116.435042041076
Step 217 | loss:3.583850048016757e-05 lr:5.214411988029355e-06 tokens_per_second_per_gpu:6532.670553452641
Step 218 | loss:7.1554550231667235e-06 lr:4.908373679744316e-06 tokens_per_second_per_gpu:7080.896741639465
Step 219 | loss:7.304731298063416e-06 lr:4.611126073354571e-06 tokens_per_second_per_gpu:6984.870540337256
Step 220 | loss:2.7781312383012846e-05 lr:4.322727117869951e-06 tokens_per_second_per_gpu:6731.233219338204
Step 221 | loss:0.0007088644779287279 lr:4.043233037238281e-06 tokens_per_second_per_gpu:7129.58193282312
Step 222 | loss:3.312961780466139e-05 lr:3.772698319384349e-06 tokens_per_second_per_gpu:7095.2521805068145
Step 223 | loss:2.7021096684620716e-06 lr:3.511175705587433e-06 tokens_per_second_per_gpu:6864.301961242415
Step 224 | loss:0.001901702955365181 lr:3.258716180199278e-06 tokens_per_second_per_gpu:6788.171946974151
Step 225 | loss:3.0770095236221096e-06 lr:3.0153689607045845e-06 tokens_per_second_per_gpu:6895.517070845031
Step 226 | loss:8.430745765508618e-06 lr:2.7811814881259503e-06 tokens_per_second_per_gpu:7087.900553203884
Step 227 | loss:0.00010574258340056986 lr:2.5561994177751737e-06 tokens_per_second_per_gpu:6976.646634257064
Step 228 | loss:8.682460247655399e-06 lr:2.340466610352654e-06 tokens_per_second_per_gpu:7088.909212981975
Step 229 | loss:0.0006243855459615588 lr:2.134025123396638e-06 tokens_per_second_per_gpu:7139.335206851824
Step 230 | loss:3.760979097933159e-06 lr:1.9369152030840556e-06 tokens_per_second_per_gpu:7084.487740329673
Step 231 | loss:1.2741875252686441e-05 lr:1.7491752763844293e-06 tokens_per_second_per_gpu:6963.711696422456
Step 232 | loss:4.581038865580922e-06 lr:1.5708419435684462e-06 tokens_per_second_per_gpu:6526.762161433326
Step 233 | loss:1.8185759472544305e-05 lr:1.4019499710726913e-06 tokens_per_second_per_gpu:7111.918666099559
Step 234 | loss:1.0438140634505544e-05 lr:1.2425322847218368e-06 tokens_per_second_per_gpu:7114.716712631283
Step 235 | loss:1.1348466614435893e-05 lr:1.0926199633097157e-06 tokens_per_second_per_gpu:7049.5512658241005
Step 236 | loss:5.334546131052775e-06 lr:9.522422325404235e-07 tokens_per_second_per_gpu:6742.662788642134
Step 237 | loss:7.380192255368456e-05 lr:8.214264593307098e-07 tokens_per_second_per_gpu:7108.23560743566
Step 238 | loss:4.279635959392181e-06 lr:7.001981464747565e-07 tokens_per_second_per_gpu:7088.762848903568
Step 239 | loss:5.737197625421686e-06 lr:5.885809276723608e-07 tokens_per_second_per_gpu:7105.459052216437
Step 240 | loss:1.1795580576290376e-05 lr:4.865965629214819e-07 tokens_per_second_per_gpu:7084.292873590962
Step 241 | loss:2.3643780878046528e-05 lr:3.9426493427611177e-07 tokens_per_second_per_gpu:7097.0686242960755
Step 242 | loss:0.0008697020239196718 lr:3.1160404197018154e-07 tokens_per_second_per_gpu:7095.906863864618
Step 243 | loss:2.1589016796497162e-06 lr:2.386300009084408e-07 tokens_per_second_per_gpu:7093.038580282913
Step 244 | loss:5.686722488462692e-06 lr:1.753570375247815e-07 tokens_per_second_per_gpu:6867.1845597185675
Step 245 | loss:6.3057509578356985e-06 lr:1.2179748700879012e-07 tokens_per_second_per_gpu:7063.526065177536
Step 246 | loss:0.0018674975726753473 lr:7.796179090094891e-08 tokens_per_second_per_gpu:6698.940419700243
Step 247 | loss:0.0035048972349613905 lr:4.385849505708084e-08 tokens_per_second_per_gpu:6764.319707708463
Step 248 | loss:6.948604277567938e-05 lr:1.949424798228239e-08 tokens_per_second_per_gpu:7131.8335767361295
Step 249 | loss:6.5469871515233535e-06 lr:4.873799534788059e-09 tokens_per_second_per_gpu:7065.993113450986
Step 250 | loss:6.990205292822793e-06 lr:0.0 tokens_per_second_per_gpu:7003.521740356228