ekinakyurek's picture
Upload folder using huggingface_hub
0bfc910 verified
raw
history blame
26.7 kB
Step 1 | loss:0.029540225863456726 lr:4.000000000000001e-06 tokens_per_second_per_gpu:7114.746095435348
Step 2 | loss:0.054938316345214844 lr:8.000000000000001e-06 tokens_per_second_per_gpu:7172.623498126431
Step 3 | loss:0.10439801961183548 lr:1.2e-05 tokens_per_second_per_gpu:6754.20056252678
Step 4 | loss:0.04550715908408165 lr:1.6000000000000003e-05 tokens_per_second_per_gpu:7154.277473480419
Step 5 | loss:0.03319788724184036 lr:2e-05 tokens_per_second_per_gpu:7104.606274517272
Step 6 | loss:0.02870815061032772 lr:2.4e-05 tokens_per_second_per_gpu:7073.182005367511
Step 7 | loss:0.12112876027822495 lr:2.8000000000000003e-05 tokens_per_second_per_gpu:6710.125022370693
Step 8 | loss:0.035006776452064514 lr:3.2000000000000005e-05 tokens_per_second_per_gpu:7091.131313437556
Step 9 | loss:0.04666886851191521 lr:3.6e-05 tokens_per_second_per_gpu:7107.41062598703
Step 10 | loss:0.09492333978414536 lr:4e-05 tokens_per_second_per_gpu:6885.647885873007
Step 11 | loss:0.10706596076488495 lr:4.4000000000000006e-05 tokens_per_second_per_gpu:6543.562241673616
Step 12 | loss:0.02137569710612297 lr:4.8e-05 tokens_per_second_per_gpu:7097.925566626606
Step 13 | loss:0.02656949870288372 lr:5.2000000000000004e-05 tokens_per_second_per_gpu:7036.2454866288235
Step 14 | loss:0.04016675427556038 lr:5.6000000000000006e-05 tokens_per_second_per_gpu:7124.482847804156
Step 15 | loss:0.01376822404563427 lr:6e-05 tokens_per_second_per_gpu:7000.628332578698
Step 16 | loss:0.0112454229965806 lr:6.400000000000001e-05 tokens_per_second_per_gpu:7040.754973080417
Step 17 | loss:0.0598704069852829 lr:6.800000000000001e-05 tokens_per_second_per_gpu:6862.126890936521
Step 18 | loss:0.01084582507610321 lr:7.2e-05 tokens_per_second_per_gpu:7106.651793203107
Step 19 | loss:0.028979798778891563 lr:7.6e-05 tokens_per_second_per_gpu:7139.729799441104
Step 20 | loss:0.024652546271681786 lr:8e-05 tokens_per_second_per_gpu:7157.923151355867
Step 21 | loss:0.010876902379095554 lr:8.4e-05 tokens_per_second_per_gpu:7110.646006524665
Step 22 | loss:0.012989507988095284 lr:8.800000000000001e-05 tokens_per_second_per_gpu:7091.682474910741
Step 23 | loss:0.013232446275651455 lr:9.200000000000001e-05 tokens_per_second_per_gpu:7102.943089778945
Step 24 | loss:0.005407996941357851 lr:9.6e-05 tokens_per_second_per_gpu:7108.696162906358
Step 25 | loss:0.010473412461578846 lr:0.0001 tokens_per_second_per_gpu:7121.906570216937
Step 26 | loss:0.02576451003551483 lr:9.999512620046522e-05 tokens_per_second_per_gpu:6679.591709400005
Step 27 | loss:0.0068130651488900185 lr:9.998050575201771e-05 tokens_per_second_per_gpu:6986.792091005637
Step 28 | loss:0.015450399369001389 lr:9.995614150494293e-05 tokens_per_second_per_gpu:6719.65140869916
Step 29 | loss:0.007353500928729773 lr:9.992203820909906e-05 tokens_per_second_per_gpu:7048.478086242976
Step 30 | loss:0.002062559127807617 lr:9.987820251299122e-05 tokens_per_second_per_gpu:7064.967769989714
Step 31 | loss:0.005398543085902929 lr:9.982464296247522e-05 tokens_per_second_per_gpu:7047.243445511115
Step 32 | loss:0.015898820012807846 lr:9.976136999909156e-05 tokens_per_second_per_gpu:6513.638608552851
Step 33 | loss:0.03684702143073082 lr:9.968839595802982e-05 tokens_per_second_per_gpu:7184.7771430175
Step 34 | loss:0.0033198196906596422 lr:9.96057350657239e-05 tokens_per_second_per_gpu:7071.703579527923
Step 35 | loss:0.008529623970389366 lr:9.951340343707852e-05 tokens_per_second_per_gpu:7087.0412134962435
Step 36 | loss:0.056784238666296005 lr:9.941141907232765e-05 tokens_per_second_per_gpu:6730.77085918304
Step 37 | loss:0.002416824223473668 lr:9.929980185352526e-05 tokens_per_second_per_gpu:7090.260945936238
Step 38 | loss:0.0034335372038185596 lr:9.917857354066931e-05 tokens_per_second_per_gpu:7048.015724052929
Step 39 | loss:0.002490300452336669 lr:9.904775776745958e-05 tokens_per_second_per_gpu:7077.7227467430475
Step 40 | loss:0.004477814771234989 lr:9.890738003669029e-05 tokens_per_second_per_gpu:6521.965534406548
Step 41 | loss:0.003761568106710911 lr:9.875746771527816e-05 tokens_per_second_per_gpu:7133.717442112903
Step 42 | loss:0.0022928102407604456 lr:9.859805002892732e-05 tokens_per_second_per_gpu:7134.078778061631
Step 43 | loss:0.0016421062173321843 lr:9.842915805643155e-05 tokens_per_second_per_gpu:7038.829386645042
Step 44 | loss:0.0026522090192884207 lr:9.825082472361557e-05 tokens_per_second_per_gpu:6981.211226988865
Step 45 | loss:0.005578839685767889 lr:9.806308479691595e-05 tokens_per_second_per_gpu:7095.841085653481
Step 46 | loss:0.0014538329560309649 lr:9.786597487660337e-05 tokens_per_second_per_gpu:7049.182594010485
Step 47 | loss:0.0018974957056343555 lr:9.765953338964735e-05 tokens_per_second_per_gpu:7060.384098548698
Step 48 | loss:0.0003907567006535828 lr:9.744380058222483e-05 tokens_per_second_per_gpu:7148.412884038914
Step 49 | loss:0.0001827648957259953 lr:9.721881851187406e-05 tokens_per_second_per_gpu:6945.958679970432
Step 50 | loss:0.016895955428481102 lr:9.698463103929542e-05 tokens_per_second_per_gpu:7148.366572503492
Step 51 | loss:0.0008212547982111573 lr:9.674128381980072e-05 tokens_per_second_per_gpu:6742.105049582061
Step 52 | loss:0.002156355418264866 lr:9.648882429441257e-05 tokens_per_second_per_gpu:7097.205298823339
Step 53 | loss:0.005788710433989763 lr:9.622730168061567e-05 tokens_per_second_per_gpu:6939.106594167151
Step 54 | loss:0.0004166981962043792 lr:9.595676696276172e-05 tokens_per_second_per_gpu:7076.91238264064
Step 55 | loss:0.0002549587225075811 lr:9.567727288213005e-05 tokens_per_second_per_gpu:6510.2329808698205
Step 56 | loss:0.0005680440226569772 lr:9.538887392664544e-05 tokens_per_second_per_gpu:6396.897707649098
Step 57 | loss:0.0010496220784261823 lr:9.50916263202557e-05 tokens_per_second_per_gpu:7002.356213224929
Step 58 | loss:0.00011234038538532332 lr:9.478558801197065e-05 tokens_per_second_per_gpu:6909.040589932731
Step 59 | loss:0.0014891921309754252 lr:9.447081866456489e-05 tokens_per_second_per_gpu:7150.294368169828
Step 60 | loss:0.008352180942893028 lr:9.414737964294636e-05 tokens_per_second_per_gpu:6920.823480383532
Step 61 | loss:0.0009430976351723075 lr:9.381533400219318e-05 tokens_per_second_per_gpu:7099.099349917173
Step 62 | loss:6.173684232635424e-05 lr:9.347474647526095e-05 tokens_per_second_per_gpu:7087.209033763686
Step 63 | loss:0.008832256309688091 lr:9.312568346036288e-05 tokens_per_second_per_gpu:6789.179895062969
Step 64 | loss:6.935551209608093e-05 lr:9.276821300802534e-05 tokens_per_second_per_gpu:6922.522859786644
Step 65 | loss:0.0004424146900419146 lr:9.24024048078213e-05 tokens_per_second_per_gpu:7036.663169221326
Step 66 | loss:0.0003946302749682218 lr:9.202833017478422e-05 tokens_per_second_per_gpu:7102.20186889871
Step 67 | loss:0.0027314608450978994 lr:9.164606203550497e-05 tokens_per_second_per_gpu:7102.9036682624655
Step 68 | loss:2.278161446156446e-05 lr:9.125567491391476e-05 tokens_per_second_per_gpu:7092.403487613373
Step 69 | loss:0.001611829618923366 lr:9.085724491675642e-05 tokens_per_second_per_gpu:7134.48426494747
Step 70 | loss:0.0008477122173644602 lr:9.045084971874738e-05 tokens_per_second_per_gpu:6711.2157244206655
Step 71 | loss:0.0038024550303816795 lr:9.003656854743667e-05 tokens_per_second_per_gpu:6999.82183774109
Step 72 | loss:0.006400879472494125 lr:8.961448216775954e-05 tokens_per_second_per_gpu:6941.3926163348415
Step 73 | loss:0.0005568875349126756 lr:8.9184672866292e-05 tokens_per_second_per_gpu:7057.59741709092
Step 74 | loss:0.000917714845854789 lr:8.874722443520899e-05 tokens_per_second_per_gpu:7140.130677030925
Step 75 | loss:0.006572643294930458 lr:8.83022221559489e-05 tokens_per_second_per_gpu:7138.41364059637
Step 76 | loss:0.0018299238290637732 lr:8.784975278258783e-05 tokens_per_second_per_gpu:7129.286504526253
Step 77 | loss:0.0021015924867242575 lr:8.73899045249266e-05 tokens_per_second_per_gpu:7042.009662502534
Step 78 | loss:0.0029271224047988653 lr:8.692276703129421e-05 tokens_per_second_per_gpu:6958.323321901262
Step 79 | loss:0.0036449891049414873 lr:8.644843137107059e-05 tokens_per_second_per_gpu:6747.8423111685215
Step 80 | loss:0.00010054302401840687 lr:8.596699001693255e-05 tokens_per_second_per_gpu:7018.643032019039
Step 81 | loss:0.001949609606526792 lr:8.547853682682604e-05 tokens_per_second_per_gpu:7095.352831548751
Step 82 | loss:0.0009813999058678746 lr:8.498316702566828e-05 tokens_per_second_per_gpu:7113.406223508263
Step 83 | loss:0.0005126105970703065 lr:8.44809771867835e-05 tokens_per_second_per_gpu:6599.1335985929
Step 84 | loss:0.000268933130428195 lr:8.397206521307584e-05 tokens_per_second_per_gpu:7077.207415139641
Step 85 | loss:0.00014128700422588736 lr:8.345653031794292e-05 tokens_per_second_per_gpu:7108.624711811209
Step 86 | loss:0.000378004478989169 lr:8.293447300593402e-05 tokens_per_second_per_gpu:7070.931474092836
Step 87 | loss:0.00017564809240866452 lr:8.240599505315655e-05 tokens_per_second_per_gpu:7138.668486506096
Step 88 | loss:0.0010751086520031095 lr:8.18711994874345e-05 tokens_per_second_per_gpu:7126.345569717123
Step 89 | loss:0.0005539911799132824 lr:8.133019056822304e-05 tokens_per_second_per_gpu:6943.229482229822
Step 90 | loss:0.00013185892021283507 lr:8.07830737662829e-05 tokens_per_second_per_gpu:6944.1238942716345
Step 91 | loss:0.00021973412367515266 lr:8.022995574311876e-05 tokens_per_second_per_gpu:7114.000598931125
Step 92 | loss:0.0029335280414670706 lr:7.967094433018508e-05 tokens_per_second_per_gpu:6898.355671180146
Step 93 | loss:3.689749428303912e-05 lr:7.910614850786448e-05 tokens_per_second_per_gpu:7114.49576104938
Step 94 | loss:0.0015608830144628882 lr:7.85356783842216e-05 tokens_per_second_per_gpu:7083.550110739564
Step 95 | loss:0.0014523952268064022 lr:7.795964517353735e-05 tokens_per_second_per_gpu:7035.289082282342
Step 96 | loss:0.00014356619794853032 lr:7.737816117462752e-05 tokens_per_second_per_gpu:7040.6662554562645
Step 97 | loss:0.0010892453137785196 lr:7.679133974894983e-05 tokens_per_second_per_gpu:7093.842887876512
Step 98 | loss:0.0011676530120894313 lr:7.619929529850397e-05 tokens_per_second_per_gpu:7054.614679817557
Step 99 | loss:0.00389692559838295 lr:7.560214324352858e-05 tokens_per_second_per_gpu:7153.13332801413
Step 100 | loss:0.0007687279721722007 lr:7.500000000000001e-05 tokens_per_second_per_gpu:7103.528147956955
Step 101 | loss:0.0008042973349802196 lr:7.439298295693665e-05 tokens_per_second_per_gpu:7052.223244730633
Step 102 | loss:0.0014940457185730338 lr:7.378121045351378e-05 tokens_per_second_per_gpu:6962.88295373816
Step 103 | loss:0.000645704916678369 lr:7.316480175599309e-05 tokens_per_second_per_gpu:7069.303280368251
Step 104 | loss:0.0007343633333221078 lr:7.254387703447154e-05 tokens_per_second_per_gpu:7122.14874010463
Step 105 | loss:3.910697705578059e-05 lr:7.191855733945387e-05 tokens_per_second_per_gpu:7150.0494042643895
Step 106 | loss:0.0005806538392789662 lr:7.128896457825364e-05 tokens_per_second_per_gpu:7035.400381827787
Step 107 | loss:0.0007767953793518245 lr:7.06552214912271e-05 tokens_per_second_per_gpu:7146.16824806903
Step 108 | loss:5.9072448493679985e-05 lr:7.001745162784477e-05 tokens_per_second_per_gpu:6927.755084586071
Step 109 | loss:0.0011609528446570039 lr:6.937577932260515e-05 tokens_per_second_per_gpu:7109.375213092769
Step 110 | loss:0.011143789626657963 lr:6.873032967079561e-05 tokens_per_second_per_gpu:7089.813670826421
Step 111 | loss:2.9558248570538126e-05 lr:6.808122850410461e-05 tokens_per_second_per_gpu:6250.42902816199
Step 112 | loss:0.004367121960967779 lr:6.742860236609077e-05 tokens_per_second_per_gpu:6886.481298400715
Step 113 | loss:0.0001906528341351077 lr:6.677257848751277e-05 tokens_per_second_per_gpu:6948.856293013826
Step 114 | loss:0.00036189169622957706 lr:6.611328476152557e-05 tokens_per_second_per_gpu:7050.796684735588
Step 115 | loss:0.00034651599708013237 lr:6.545084971874738e-05 tokens_per_second_per_gpu:7000.562835258956
Step 116 | loss:0.0004136743664275855 lr:6.478540250220234e-05 tokens_per_second_per_gpu:7147.977350440332
Step 117 | loss:0.003798292251303792 lr:6.411707284214384e-05 tokens_per_second_per_gpu:7087.5832480361705
Step 118 | loss:0.006392097566276789 lr:6.344599103076329e-05 tokens_per_second_per_gpu:6799.183304443337
Step 119 | loss:0.0013543276581913233 lr:6.277228789678953e-05 tokens_per_second_per_gpu:6921.211954806336
Step 120 | loss:0.0002928821195382625 lr:6.209609477998338e-05 tokens_per_second_per_gpu:7117.199422392905
Step 121 | loss:0.0005018142401240766 lr:6.141754350553279e-05 tokens_per_second_per_gpu:7106.606368097013
Step 122 | loss:6.97396244504489e-05 lr:6.073676635835317e-05 tokens_per_second_per_gpu:7076.701997253973
Step 123 | loss:0.0008127280743792653 lr:6.005389605729824e-05 tokens_per_second_per_gpu:6774.044475265982
Step 124 | loss:8.059457172748807e-07 lr:5.9369065729286245e-05 tokens_per_second_per_gpu:7069.022594436617
Step 125 | loss:0.0006907738279551268 lr:5.868240888334653e-05 tokens_per_second_per_gpu:7101.833364445445
Step 126 | loss:0.00037604503449983895 lr:5.799405938459175e-05 tokens_per_second_per_gpu:6779.740501122109
Step 127 | loss:9.945348210749216e-06 lr:5.730415142812059e-05 tokens_per_second_per_gpu:7109.808695930745
Step 128 | loss:0.00012900243746116757 lr:5.661281951285613e-05 tokens_per_second_per_gpu:7039.066588151866
Step 129 | loss:0.00016375807172153145 lr:5.5920198415325064e-05 tokens_per_second_per_gpu:7141.2358125670025
Step 130 | loss:0.0001228506152983755 lr:5.522642316338268e-05 tokens_per_second_per_gpu:7142.419123815858
Step 131 | loss:0.0002603944740258157 lr:5.453162900988902e-05 tokens_per_second_per_gpu:7135.263776904627
Step 132 | loss:0.0003201049694325775 lr:5.383595140634093e-05 tokens_per_second_per_gpu:7152.176449087222
Step 133 | loss:0.0013340616133064032 lr:5.313952597646568e-05 tokens_per_second_per_gpu:6702.287681050857
Step 134 | loss:0.0002762512012850493 lr:5.244248848978067e-05 tokens_per_second_per_gpu:7137.499682925023
Step 135 | loss:0.0016978979110717773 lr:5.174497483512506e-05 tokens_per_second_per_gpu:7124.628603122485
Step 136 | loss:0.0017529870383441448 lr:5.104712099416785e-05 tokens_per_second_per_gpu:7042.4077723729515
Step 137 | loss:2.2168194846017286e-05 lr:5.034906301489808e-05 tokens_per_second_per_gpu:7084.378231011098
Step 138 | loss:7.494900728488574e-06 lr:4.965093698510193e-05 tokens_per_second_per_gpu:7129.266331002967
Step 139 | loss:5.585084727499634e-05 lr:4.895287900583216e-05 tokens_per_second_per_gpu:7101.5656576992515
Step 140 | loss:0.0049140602350234985 lr:4.825502516487497e-05 tokens_per_second_per_gpu:5018.098205716435
Step 141 | loss:0.0005131249781697989 lr:4.755751151021934e-05 tokens_per_second_per_gpu:6552.865287249257
Step 142 | loss:0.0006004064343869686 lr:4.6860474023534335e-05 tokens_per_second_per_gpu:7146.902395727425
Step 143 | loss:1.010658252198482e-06 lr:4.616404859365907e-05 tokens_per_second_per_gpu:6927.0566561457335
Step 144 | loss:8.545256378056365e-07 lr:4.5468370990111006e-05 tokens_per_second_per_gpu:7089.467995213895
Step 145 | loss:2.602529821160715e-05 lr:4.477357683661734e-05 tokens_per_second_per_gpu:7129.857203949524
Step 146 | loss:5.337346465239534e-06 lr:4.407980158467495e-05 tokens_per_second_per_gpu:7020.970161563771
Step 147 | loss:0.0004508928395807743 lr:4.3387180487143876e-05 tokens_per_second_per_gpu:7015.105932470174
Step 148 | loss:3.850179200526327e-05 lr:4.269584857187943e-05 tokens_per_second_per_gpu:7012.490981952906
Step 149 | loss:1.451329126211931e-06 lr:4.2005940615408264e-05 tokens_per_second_per_gpu:7104.00318261242
Step 150 | loss:0.00010721285798354074 lr:4.131759111665349e-05 tokens_per_second_per_gpu:7108.4876664486865
Step 151 | loss:0.0007373376865871251 lr:4.063093427071376e-05 tokens_per_second_per_gpu:6535.2846846574685
Step 152 | loss:5.14740440848982e-06 lr:3.9946103942701777e-05 tokens_per_second_per_gpu:7126.005172757417
Step 153 | loss:8.383424574276432e-05 lr:3.926323364164684e-05 tokens_per_second_per_gpu:6896.807243251913
Step 154 | loss:3.6446053854888305e-05 lr:3.858245649446721e-05 tokens_per_second_per_gpu:7093.179324822906
Step 155 | loss:3.7222223909338936e-05 lr:3.790390522001662e-05 tokens_per_second_per_gpu:7000.223882064014
Step 156 | loss:3.218203573851497e-06 lr:3.7227712103210486e-05 tokens_per_second_per_gpu:7083.678222674595
Step 157 | loss:5.593284004135057e-05 lr:3.655400896923672e-05 tokens_per_second_per_gpu:7112.309190279061
Step 158 | loss:2.6721032554632984e-05 lr:3.588292715785617e-05 tokens_per_second_per_gpu:7091.2245456931
Step 159 | loss:1.354797677777242e-05 lr:3.5214597497797684e-05 tokens_per_second_per_gpu:7130.752068613852
Step 160 | loss:1.3690589639736572e-06 lr:3.4549150281252636e-05 tokens_per_second_per_gpu:7115.874812395864
Step 161 | loss:5.960013368166983e-06 lr:3.388671523847445e-05 tokens_per_second_per_gpu:7094.786361910792
Step 162 | loss:0.0002312444121344015 lr:3.322742151248725e-05 tokens_per_second_per_gpu:7137.45632514496
Step 163 | loss:1.306535614276072e-05 lr:3.257139763390925e-05 tokens_per_second_per_gpu:7076.969880099401
Step 164 | loss:0.0001672924408921972 lr:3.1918771495895396e-05 tokens_per_second_per_gpu:7099.99930816563
Step 165 | loss:0.0004270974895916879 lr:3.12696703292044e-05 tokens_per_second_per_gpu:6765.795972492016
Step 166 | loss:0.00010257727262796834 lr:3.062422067739485e-05 tokens_per_second_per_gpu:6951.635382732522
Step 167 | loss:1.8149994502891786e-05 lr:2.9982548372155263e-05 tokens_per_second_per_gpu:7053.0046418293805
Step 168 | loss:2.7050325002164755e-07 lr:2.934477850877292e-05 tokens_per_second_per_gpu:7103.832362306278
Step 169 | loss:9.294653864344582e-07 lr:2.8711035421746367e-05 tokens_per_second_per_gpu:6250.8035816249685
Step 170 | loss:2.286300514242612e-06 lr:2.8081442660546125e-05 tokens_per_second_per_gpu:7104.427696841558
Step 171 | loss:8.693018003214092e-07 lr:2.7456122965528475e-05 tokens_per_second_per_gpu:7059.973123310374
Step 172 | loss:0.003066105069592595 lr:2.6835198244006927e-05 tokens_per_second_per_gpu:6947.710119689123
Step 173 | loss:1.5188087672868278e-05 lr:2.6218789546486234e-05 tokens_per_second_per_gpu:7133.940397975158
Step 174 | loss:0.00011609125067479908 lr:2.560701704306336e-05 tokens_per_second_per_gpu:7063.19691770947
Step 175 | loss:3.440136424615048e-05 lr:2.500000000000001e-05 tokens_per_second_per_gpu:7066.5953070761
Step 176 | loss:1.0009518973674858e-06 lr:2.4397856756471432e-05 tokens_per_second_per_gpu:7110.735142656809
Step 177 | loss:5.258223154669395e-07 lr:2.3800704701496053e-05 tokens_per_second_per_gpu:7130.324251444125
Step 178 | loss:6.0575775933102705e-06 lr:2.3208660251050158e-05 tokens_per_second_per_gpu:7130.477702020835
Step 179 | loss:2.9760263714706525e-05 lr:2.2621838825372493e-05 tokens_per_second_per_gpu:7150.117451680757
Step 180 | loss:4.3399703031354875e-07 lr:2.2040354826462668e-05 tokens_per_second_per_gpu:6767.427748085995
Step 181 | loss:2.2780863218940794e-05 lr:2.1464321615778422e-05 tokens_per_second_per_gpu:7121.546398020273
Step 182 | loss:5.162895604371442e-07 lr:2.0893851492135537e-05 tokens_per_second_per_gpu:7087.361838909138
Step 183 | loss:1.6758610854594735e-06 lr:2.0329055669814934e-05 tokens_per_second_per_gpu:7099.691794932654
Step 184 | loss:2.825595402100589e-06 lr:1.977004425688126e-05 tokens_per_second_per_gpu:7036.941974192973
Step 185 | loss:3.6735873436555266e-05 lr:1.9216926233717085e-05 tokens_per_second_per_gpu:7132.623569023027
Step 186 | loss:1.4281424228101969e-05 lr:1.866980943177699e-05 tokens_per_second_per_gpu:7131.625336676355
Step 187 | loss:4.954384280608792e-07 lr:1.8128800512565513e-05 tokens_per_second_per_gpu:6890.551615830013
Step 188 | loss:6.580243621101545e-07 lr:1.7594004946843456e-05 tokens_per_second_per_gpu:7051.364126186731
Step 189 | loss:0.00015473697567358613 lr:1.7065526994065973e-05 tokens_per_second_per_gpu:7134.771681422758
Step 190 | loss:3.909034660409816e-07 lr:1.6543469682057106e-05 tokens_per_second_per_gpu:7031.272342340671
Step 191 | loss:2.0180352294119075e-05 lr:1.602793478692419e-05 tokens_per_second_per_gpu:7136.978755764452
Step 192 | loss:0.0004492579319048673 lr:1.551902281321651e-05 tokens_per_second_per_gpu:7128.081822162232
Step 193 | loss:5.233718184172176e-05 lr:1.5016832974331724e-05 tokens_per_second_per_gpu:6872.525950451789
Step 194 | loss:3.097840817645192e-05 lr:1.4521463173173965e-05 tokens_per_second_per_gpu:6516.579197346292
Step 195 | loss:2.6365127268945798e-05 lr:1.4033009983067452e-05 tokens_per_second_per_gpu:7088.149406346664
Step 196 | loss:9.954388224286959e-05 lr:1.3551568628929434e-05 tokens_per_second_per_gpu:7128.120347656343
Step 197 | loss:3.1318388664658414e-06 lr:1.3077232968705805e-05 tokens_per_second_per_gpu:7105.864897783129
Step 198 | loss:4.1833050090644974e-06 lr:1.2610095475073414e-05 tokens_per_second_per_gpu:6922.724799305372
Step 199 | loss:7.337460556300357e-05 lr:1.2150247217412186e-05 tokens_per_second_per_gpu:7096.869639855486
Step 200 | loss:0.0017239877488464117 lr:1.1697777844051105e-05 tokens_per_second_per_gpu:7107.996106494593
Step 201 | loss:5.964072897768347e-06 lr:1.1252775564791024e-05 tokens_per_second_per_gpu:7095.227079785615
Step 202 | loss:3.506623033899814e-05 lr:1.0815327133708015e-05 tokens_per_second_per_gpu:7094.343396430226
Step 203 | loss:0.0005673199193552136 lr:1.0385517832240471e-05 tokens_per_second_per_gpu:7069.464966995054
Step 204 | loss:5.540213533095084e-05 lr:9.963431452563332e-06 tokens_per_second_per_gpu:7124.329036816601
Step 205 | loss:2.1596085844066693e-06 lr:9.549150281252633e-06 tokens_per_second_per_gpu:7068.644972083886
Step 206 | loss:5.073594593341113e-07 lr:9.142755083243576e-06 tokens_per_second_per_gpu:6944.314216279912
Step 207 | loss:0.0003969993849750608 lr:8.744325086085248e-06 tokens_per_second_per_gpu:7121.647709600391
Step 208 | loss:9.875832802208606e-06 lr:8.353937964495029e-06 tokens_per_second_per_gpu:6887.346677501267
Step 209 | loss:9.690284059615806e-06 lr:7.971669825215788e-06 tokens_per_second_per_gpu:6758.478040258444
Step 210 | loss:0.00015706694102846086 lr:7.597595192178702e-06 tokens_per_second_per_gpu:7010.525745470163
Step 211 | loss:0.00021768909937236458 lr:7.2317869919746705e-06 tokens_per_second_per_gpu:7092.36181905593
Step 212 | loss:0.0001115861814469099 lr:6.874316539637127e-06 tokens_per_second_per_gpu:7077.555591184393
Step 213 | loss:7.169802120188251e-05 lr:6.52525352473905e-06 tokens_per_second_per_gpu:7179.012902552189
Step 214 | loss:8.646498827147298e-06 lr:6.184665997806832e-06 tokens_per_second_per_gpu:7120.979923391178
Step 215 | loss:8.888794695849356e-07 lr:5.852620357053651e-06 tokens_per_second_per_gpu:7104.622489562669
Step 216 | loss:7.221656687761424e-06 lr:5.529181335435124e-06 tokens_per_second_per_gpu:7147.679813147273
Step 217 | loss:3.10497016471345e-05 lr:5.214411988029355e-06 tokens_per_second_per_gpu:7174.778327216255
Step 218 | loss:0.0001612574269529432 lr:4.908373679744316e-06 tokens_per_second_per_gpu:7119.068931005513
Step 219 | loss:3.326678051962517e-05 lr:4.611126073354571e-06 tokens_per_second_per_gpu:7038.944161703609
Step 220 | loss:6.26885730525828e-06 lr:4.322727117869951e-06 tokens_per_second_per_gpu:6990.578718299749
Step 221 | loss:2.5699733896544785e-07 lr:4.043233037238281e-06 tokens_per_second_per_gpu:7054.708680369594
Step 222 | loss:2.55863398024303e-07 lr:3.772698319384349e-06 tokens_per_second_per_gpu:7112.095135044306
Step 223 | loss:1.1988352525804657e-05 lr:3.511175705587433e-06 tokens_per_second_per_gpu:7147.361259068542
Step 224 | loss:6.018311978550628e-06 lr:3.258716180199278e-06 tokens_per_second_per_gpu:7117.610773836008
Step 225 | loss:3.592248322092928e-05 lr:3.0153689607045845e-06 tokens_per_second_per_gpu:6785.051930360497
Step 226 | loss:4.513950898399344e-06 lr:2.7811814881259503e-06 tokens_per_second_per_gpu:7082.510620579374
Step 227 | loss:0.0018192669376730919 lr:2.5561994177751737e-06 tokens_per_second_per_gpu:7007.862139311997
Step 228 | loss:4.741022712551057e-05 lr:2.340466610352654e-06 tokens_per_second_per_gpu:6704.357288918235
Step 229 | loss:3.1393567496706964e-06 lr:2.134025123396638e-06 tokens_per_second_per_gpu:7176.755555229882
Step 230 | loss:5.387498731579399e-06 lr:1.9369152030840556e-06 tokens_per_second_per_gpu:7148.161251943011
Step 231 | loss:0.00023710941604804248 lr:1.7491752763844293e-06 tokens_per_second_per_gpu:7129.62413574817
Step 232 | loss:3.06320572462937e-07 lr:1.5708419435684462e-06 tokens_per_second_per_gpu:6932.470868420776
Step 233 | loss:6.29617545655492e-07 lr:1.4019499710726913e-06 tokens_per_second_per_gpu:7107.128615815684
Step 234 | loss:8.09742632554844e-05 lr:1.2425322847218368e-06 tokens_per_second_per_gpu:7122.016118292487
Step 235 | loss:3.1099830266612116e-06 lr:1.0926199633097157e-06 tokens_per_second_per_gpu:7098.876868237267
Step 236 | loss:5.077080913906684e-06 lr:9.522422325404235e-07 tokens_per_second_per_gpu:7134.5409898864455
Step 237 | loss:5.532283103093505e-05 lr:8.214264593307098e-07 tokens_per_second_per_gpu:6935.996182320403
Step 238 | loss:0.00026691146194934845 lr:7.001981464747565e-07 tokens_per_second_per_gpu:6746.282361514014
Step 239 | loss:3.129031483695144e-06 lr:5.885809276723608e-07 tokens_per_second_per_gpu:7113.606457876276
Step 240 | loss:0.00014283997006714344 lr:4.865965629214819e-07 tokens_per_second_per_gpu:7118.527222739295
Step 241 | loss:2.568826857896056e-05 lr:3.9426493427611177e-07 tokens_per_second_per_gpu:7096.173509580145
Step 242 | loss:0.0003508209774736315 lr:3.1160404197018154e-07 tokens_per_second_per_gpu:6929.065717032757
Step 243 | loss:0.0001938796485774219 lr:2.386300009084408e-07 tokens_per_second_per_gpu:7055.001338103328
Step 244 | loss:1.2262429436304956e-06 lr:1.753570375247815e-07 tokens_per_second_per_gpu:6898.12388735376
Step 245 | loss:1.5402747521875426e-05 lr:1.2179748700879012e-07 tokens_per_second_per_gpu:7032.705980046089
Step 246 | loss:1.8149889911001083e-06 lr:7.796179090094891e-08 tokens_per_second_per_gpu:7031.662638005547
Step 247 | loss:0.006206083111464977 lr:4.385849505708084e-08 tokens_per_second_per_gpu:6763.210150792245
Step 248 | loss:1.6148927898029797e-05 lr:1.949424798228239e-08 tokens_per_second_per_gpu:7115.7234867818015
Step 249 | loss:5.711911398975644e-06 lr:4.873799534788059e-09 tokens_per_second_per_gpu:7103.25766793199
Step 250 | loss:8.76625290402444e-06 lr:0.0 tokens_per_second_per_gpu:7097.467031496105