Step 1 | loss:0.007433821447193623 lr:7.142857142857143e-06 tokens_per_second_per_gpu:4278.922304346791 Step 2 | loss:0.009891935624182224 lr:1.4285714285714285e-05 tokens_per_second_per_gpu:6974.604100065492 Step 3 | loss:0.008527606725692749 lr:2.1428571428571428e-05 tokens_per_second_per_gpu:4327.3065714434815 Step 4 | loss:0.009289908222854137 lr:2.857142857142857e-05 tokens_per_second_per_gpu:7027.680338809943 Step 5 | loss:0.008530417457222939 lr:3.571428571428572e-05 tokens_per_second_per_gpu:3504.3657781305515 Step 6 | loss:0.012702836655080318 lr:4.2857142857142856e-05 tokens_per_second_per_gpu:3598.8280133135977 Step 7 | loss:0.01713400147855282 lr:5e-05 tokens_per_second_per_gpu:6943.563048075219 Step 8 | loss:0.03756745904684067 lr:5.714285714285714e-05 tokens_per_second_per_gpu:7149.598148689258 Step 9 | loss:0.008962743915617466 lr:6.428571428571429e-05 tokens_per_second_per_gpu:6990.288691106839 Step 10 | loss:0.008733885362744331 lr:7.142857142857143e-05 tokens_per_second_per_gpu:7018.914175375169 Step 11 | loss:0.005553539376705885 lr:7.857142857142858e-05 tokens_per_second_per_gpu:7033.228014280872 Step 12 | loss:0.006694405805319548 lr:8.571428571428571e-05 tokens_per_second_per_gpu:7058.441853717412 Step 13 | loss:0.007489765528589487 lr:9.285714285714286e-05 tokens_per_second_per_gpu:7014.026902201876 Step 14 | loss:0.006205238401889801 lr:0.0001 tokens_per_second_per_gpu:6928.086956917003 Step 15 | loss:0.005077727138996124 lr:9.998540070400966e-05 tokens_per_second_per_gpu:7043.869152921344 Step 16 | loss:0.0065876999869942665 lr:9.994161134161634e-05 tokens_per_second_per_gpu:3507.1039445214155 Step 17 | loss:0.004523609299212694 lr:9.986865748457457e-05 tokens_per_second_per_gpu:7043.662047614013 Step 18 | loss:0.004424856044352055 lr:9.976658173588244e-05 tokens_per_second_per_gpu:6981.378854962374 Step 19 | loss:0.0131758414208889 lr:9.96354437049027e-05 tokens_per_second_per_gpu:7002.246077976707 Step 20 | loss:0.01182754896581173 lr:9.947531997255256e-05 tokens_per_second_per_gpu:3429.603139159148 Step 21 | loss:0.0047209737822413445 lr:9.928630404658255e-05 tokens_per_second_per_gpu:7121.710362831032 Step 22 | loss:0.004698405973613262 lr:9.906850630697068e-05 tokens_per_second_per_gpu:7052.891366261295 Step 23 | loss:0.007808104623109102 lr:9.882205394146361e-05 tokens_per_second_per_gpu:6915.455008094548 Step 24 | loss:0.0032391438726335764 lr:9.85470908713026e-05 tokens_per_second_per_gpu:7055.742223440795 Step 25 | loss:0.004487615544348955 lr:9.824377766717759e-05 tokens_per_second_per_gpu:6969.508743168209 Step 26 | loss:0.003022173885256052 lr:9.791229145545831e-05 tokens_per_second_per_gpu:6987.882614507493 Step 27 | loss:0.004331974312663078 lr:9.755282581475769e-05 tokens_per_second_per_gpu:6868.12351044032 Step 28 | loss:0.005120791029185057 lr:9.716559066288715e-05 tokens_per_second_per_gpu:7051.8927705139595 Step 29 | loss:0.00606536353006959 lr:9.675081213427076e-05 tokens_per_second_per_gpu:7092.632816066926 Step 30 | loss:0.007662759628146887 lr:9.630873244788883e-05 tokens_per_second_per_gpu:7111.006380872096 Step 31 | loss:0.0033766624983400106 lr:9.583960976582913e-05 tokens_per_second_per_gpu:7043.106157384212 Step 32 | loss:0.003239640034735203 lr:9.534371804252728e-05 tokens_per_second_per_gpu:7122.967151716612 Step 33 | loss:0.0075318035669624805 lr:9.482134686478519e-05 tokens_per_second_per_gpu:6968.109709952053 Step 34 | loss:0.006072061602026224 lr:9.42728012826605e-05 tokens_per_second_per_gpu:7104.322457313338 Step 35 | loss:0.005512516479939222 lr:9.36984016313259e-05 tokens_per_second_per_gpu:7148.292070833934 Step 36 | loss:0.003978733438998461 lr:9.309848334400246e-05 tokens_per_second_per_gpu:6975.852230531516 Step 37 | loss:0.0038091831374913454 lr:9.247339675607605e-05 tokens_per_second_per_gpu:6935.001766276717 Step 38 | loss:0.003959219437092543 lr:9.182350690051133e-05 tokens_per_second_per_gpu:7047.514829436099 Step 39 | loss:0.002670063404366374 lr:9.114919329468282e-05 tokens_per_second_per_gpu:7103.653239028144 Step 40 | loss:0.0025509214028716087 lr:9.045084971874738e-05 tokens_per_second_per_gpu:6924.062441522704 Step 41 | loss:0.0033416671212762594 lr:8.972888398568772e-05 tokens_per_second_per_gpu:7032.931220590678 Step 42 | loss:0.002726883627474308 lr:8.898371770316111e-05 tokens_per_second_per_gpu:6922.580068664329 Step 43 | loss:0.003601265838369727 lr:8.821578602729242e-05 tokens_per_second_per_gpu:6998.505679747708 Step 44 | loss:0.0025357180275022984 lr:8.742553740855506e-05 tokens_per_second_per_gpu:6920.093841971782 Step 45 | loss:0.00259264069609344 lr:8.661343332988869e-05 tokens_per_second_per_gpu:6958.522087471687 Step 46 | loss:0.0017771099228411913 lr:8.577994803720606e-05 tokens_per_second_per_gpu:7055.234261746467 Step 47 | loss:0.0030695602763444185 lr:8.492556826244687e-05 tokens_per_second_per_gpu:7115.696357106142 Step 48 | loss:0.002117033116519451 lr:8.405079293933986e-05 tokens_per_second_per_gpu:3445.4926993823374 Step 49 | loss:0.006632229313254356 lr:8.315613291203976e-05 tokens_per_second_per_gpu:7005.54770636426 Step 50 | loss:0.0010640522232279181 lr:8.224211063680853e-05 tokens_per_second_per_gpu:6983.02899748714 Step 51 | loss:0.0028867260552942753 lr:8.130925987691569e-05 tokens_per_second_per_gpu:7058.8216296737655 Step 52 | loss:0.0012619802728295326 lr:8.035812539093557e-05 tokens_per_second_per_gpu:6963.2794344963495 Step 53 | loss:0.002152219647541642 lr:7.938926261462366e-05 tokens_per_second_per_gpu:7098.155556019047 Step 54 | loss:0.0011904919520020485 lr:7.840323733655778e-05 tokens_per_second_per_gpu:6970.425986279287 Step 55 | loss:0.002649707952514291 lr:7.740062536773352e-05 tokens_per_second_per_gpu:6926.415840684613 Step 56 | loss:0.0009792173514142632 lr:7.638201220530665e-05 tokens_per_second_per_gpu:6372.985792017077 Step 57 | loss:0.0013906939420849085 lr:7.534799269067953e-05 tokens_per_second_per_gpu:7100.866245314832 Step 58 | loss:0.0007890767883509398 lr:7.42991706621303e-05 tokens_per_second_per_gpu:6998.043670887341 Step 59 | loss:0.0013064939994364977 lr:7.323615860218843e-05 tokens_per_second_per_gpu:7003.748127137316 Step 60 | loss:0.00041067946585826576 lr:7.215957727996207e-05 tokens_per_second_per_gpu:7149.6469152758955 Step 61 | loss:0.0003053396358154714 lr:7.107005538862646e-05 tokens_per_second_per_gpu:6992.945597104522 Step 62 | loss:5.691653132089414e-05 lr:6.996822917828477e-05 tokens_per_second_per_gpu:6982.882816856271 Step 63 | loss:0.00010506136459298432 lr:6.885474208441603e-05 tokens_per_second_per_gpu:7058.189456188242 Step 64 | loss:0.0020791818387806416 lr:6.773024435212678e-05 tokens_per_second_per_gpu:6925.501586639763 Step 65 | loss:0.0006732754991389811 lr:6.659539265642643e-05 tokens_per_second_per_gpu:7048.991828636306 Step 66 | loss:0.0003678801003843546 lr:6.545084971874738e-05 tokens_per_second_per_gpu:6975.751397093809 Step 67 | loss:0.001088025514036417 lr:6.429728391993446e-05 tokens_per_second_per_gpu:7004.793971291558 Step 68 | loss:0.0030143701005727053 lr:6.313536890992935e-05 tokens_per_second_per_gpu:6983.377231507687 Step 69 | loss:0.0037152341101318598 lr:6.19657832143779e-05 tokens_per_second_per_gpu:7018.294546005699 Step 70 | loss:0.0021930625662207603 lr:6.078920983839031e-05 tokens_per_second_per_gpu:6984.40499827036 Step 71 | loss:0.0003924686461687088 lr:5.960633586768543e-05 tokens_per_second_per_gpu:6929.974046006379 Step 72 | loss:0.001744943205267191 lr:5.841785206735192e-05 tokens_per_second_per_gpu:6980.908240043891 Step 73 | loss:1.0667107744666282e-05 lr:5.7224452478461064e-05 tokens_per_second_per_gpu:7105.3612620296135 Step 74 | loss:0.0012537252623587847 lr:5.602683401276615e-05 tokens_per_second_per_gpu:7067.58740176584 Step 75 | loss:0.00013631217007059604 lr:5.482569604572576e-05 tokens_per_second_per_gpu:6937.379832491852 Step 76 | loss:0.0001166909423773177 lr:5.3621740008088126e-05 tokens_per_second_per_gpu:6973.155972329299 Step 77 | loss:0.0004904019297100604 lr:5.2415668976275355e-05 tokens_per_second_per_gpu:6996.278106616286 Step 78 | loss:0.0016770692309364676 lr:5.1208187261806615e-05 tokens_per_second_per_gpu:6988.819234024851 Step 79 | loss:7.578815711895004e-05 lr:5e-05 tokens_per_second_per_gpu:6988.433506726889 Step 80 | loss:0.0012541806790977716 lr:4.87918127381934e-05 tokens_per_second_per_gpu:6998.655360824805 Step 81 | loss:2.1093062969157472e-05 lr:4.758433102372466e-05 tokens_per_second_per_gpu:6930.654130690276 Step 82 | loss:0.0005921487463638186 lr:4.6378259991911886e-05 tokens_per_second_per_gpu:7071.023959780366 Step 83 | loss:3.908562121068826e-06 lr:4.5174303954274244e-05 tokens_per_second_per_gpu:6689.530558079383 Step 84 | loss:0.0010617291554808617 lr:4.397316598723385e-05 tokens_per_second_per_gpu:7111.477704450716 Step 85 | loss:3.4798293199855834e-05 lr:4.277554752153895e-05 tokens_per_second_per_gpu:6928.00968860458 Step 86 | loss:0.0013808298390358686 lr:4.1582147932648074e-05 tokens_per_second_per_gpu:7013.316919632038 Step 87 | loss:0.00014939576794859022 lr:4.039366413231458e-05 tokens_per_second_per_gpu:7153.457603804454 Step 88 | loss:0.002904578810557723 lr:3.92107901616097e-05 tokens_per_second_per_gpu:6987.01755147715 Step 89 | loss:0.0006003532907925546 lr:3.803421678562213e-05 tokens_per_second_per_gpu:7074.776805006512 Step 90 | loss:0.00020944999414496124 lr:3.6864631090070655e-05 tokens_per_second_per_gpu:7043.195232137626 Step 91 | loss:0.00017395871691405773 lr:3.570271608006555e-05 tokens_per_second_per_gpu:7127.343857180667 Step 92 | loss:0.00042717327596619725 lr:3.4549150281252636e-05 tokens_per_second_per_gpu:7012.066188187324 Step 93 | loss:0.000494409236125648 lr:3.340460734357359e-05 tokens_per_second_per_gpu:7134.3016727290415 Step 94 | loss:0.0005546956090256572 lr:3.226975564787322e-05 tokens_per_second_per_gpu:7011.500459000753 Step 95 | loss:0.0017987475730478764 lr:3.114525791558398e-05 tokens_per_second_per_gpu:6999.896345089642 Step 96 | loss:0.0011261141626164317 lr:3.003177082171523e-05 tokens_per_second_per_gpu:7077.341163618078 Step 97 | loss:0.0004435337905306369 lr:2.8929944611373554e-05 tokens_per_second_per_gpu:7122.704829785961 Step 98 | loss:0.0009541191975586116 lr:2.784042272003794e-05 tokens_per_second_per_gpu:6955.576629783077 Step 99 | loss:0.0009608229156583548 lr:2.6763841397811573e-05 tokens_per_second_per_gpu:7075.3705976328165 Step 100 | loss:2.0330769984866492e-05 lr:2.57008293378697e-05 tokens_per_second_per_gpu:7010.808486802995 Step 101 | loss:0.0005670612445101142 lr:2.4652007309320498e-05 tokens_per_second_per_gpu:7014.871680008315 Step 102 | loss:0.0001822103513404727 lr:2.361798779469336e-05 tokens_per_second_per_gpu:7069.874465547109 Step 103 | loss:6.067636422812939e-05 lr:2.259937463226651e-05 tokens_per_second_per_gpu:7143.434842292193 Step 104 | loss:0.0012350025353953242 lr:2.1596762663442218e-05 tokens_per_second_per_gpu:7150.560104214427 Step 105 | loss:0.000328391557559371 lr:2.061073738537635e-05 tokens_per_second_per_gpu:7007.861876700001 Step 106 | loss:4.4648459152085707e-05 lr:1.9641874609064443e-05 tokens_per_second_per_gpu:7002.365320066603 Step 107 | loss:0.0001899336202768609 lr:1.8690740123084316e-05 tokens_per_second_per_gpu:6989.01028776302 Step 108 | loss:0.000711357977706939 lr:1.7757889363191483e-05 tokens_per_second_per_gpu:7013.800885625218 Step 109 | loss:0.0002103261067532003 lr:1.684386708796025e-05 tokens_per_second_per_gpu:6971.90193408231 Step 110 | loss:0.0012856239918619394 lr:1.5949207060660138e-05 tokens_per_second_per_gpu:6936.0839574955135 Step 111 | loss:0.00028884742641821504 lr:1.5074431737553157e-05 tokens_per_second_per_gpu:6682.076651498819 Step 112 | loss:0.00048056442756205797 lr:1.422005196279395e-05 tokens_per_second_per_gpu:6959.37920253326 Step 113 | loss:0.00016194285126402974 lr:1.338656667011134e-05 tokens_per_second_per_gpu:7062.701177701973 Step 114 | loss:1.003764191409573e-05 lr:1.257446259144494e-05 tokens_per_second_per_gpu:7133.668802917962 Step 115 | loss:1.5516627172473818e-05 lr:1.178421397270758e-05 tokens_per_second_per_gpu:6997.867152606685 Step 116 | loss:7.718747838225681e-06 lr:1.1016282296838887e-05 tokens_per_second_per_gpu:7039.639750488845 Step 117 | loss:0.00021431442291941494 lr:1.0271116014312293e-05 tokens_per_second_per_gpu:7001.9340650009035 Step 118 | loss:0.0001981350069399923 lr:9.549150281252633e-06 tokens_per_second_per_gpu:6990.339489699666 Step 119 | loss:6.18091580690816e-05 lr:8.850806705317183e-06 tokens_per_second_per_gpu:6999.51889505936 Step 120 | loss:0.00038886364200152457 lr:8.176493099488663e-06 tokens_per_second_per_gpu:6939.737712730865 Step 121 | loss:8.600140427006409e-05 lr:7.526603243923957e-06 tokens_per_second_per_gpu:7003.404236477045 Step 122 | loss:0.00013144702825229615 lr:6.901516655997536e-06 tokens_per_second_per_gpu:6999.089598788804 Step 123 | loss:3.786681190831587e-05 lr:6.301598368674105e-06 tokens_per_second_per_gpu:6981.572988647627 Step 124 | loss:0.00044011740828864276 lr:5.727198717339511e-06 tokens_per_second_per_gpu:7006.622121338201 Step 125 | loss:3.4150751162087545e-05 lr:5.178653135214812e-06 tokens_per_second_per_gpu:7162.449520545392 Step 126 | loss:0.0006845332100056112 lr:4.65628195747273e-06 tokens_per_second_per_gpu:7006.547619706399 Step 127 | loss:3.6606450066756224e-06 lr:4.16039023417088e-06 tokens_per_second_per_gpu:7039.269986848858 Step 128 | loss:0.0002642414183355868 lr:3.691267552111183e-06 tokens_per_second_per_gpu:7056.070034248728 Step 129 | loss:0.0005909746396355331 lr:3.249187865729264e-06 tokens_per_second_per_gpu:7003.069895512292 Step 130 | loss:1.7421631127945147e-05 lr:2.8344093371128424e-06 tokens_per_second_per_gpu:7009.171804915963 Step 131 | loss:2.5107539840973914e-05 lr:2.4471741852423237e-06 tokens_per_second_per_gpu:7137.262623329186 Step 132 | loss:0.0004554182814899832 lr:2.087708544541689e-06 tokens_per_second_per_gpu:7146.849907892104 Step 133 | loss:3.2043193641584367e-05 lr:1.7562223328224325e-06 tokens_per_second_per_gpu:7066.764710542235 Step 134 | loss:9.895300172502175e-05 lr:1.4529091286973995e-06 tokens_per_second_per_gpu:6957.800669687655 Step 135 | loss:3.983289934694767e-05 lr:1.1779460585363944e-06 tokens_per_second_per_gpu:6925.743799919971 Step 136 | loss:3.9462127460865304e-05 lr:9.314936930293283e-07 tokens_per_second_per_gpu:7001.080247203092 Step 137 | loss:0.0003175966558046639 lr:7.136959534174592e-07 tokens_per_second_per_gpu:6987.495243582901 Step 138 | loss:0.00010340212611481547 lr:5.246800274474439e-07 tokens_per_second_per_gpu:7046.016421507205 Step 139 | loss:1.5285240806406364e-05 lr:3.6455629509730136e-07 tokens_per_second_per_gpu:7127.06062323452 Step 140 | loss:6.574355938937515e-05 lr:2.334182641175686e-07 tokens_per_second_per_gpu:6782.4490594002555 Step 141 | loss:3.288120569777675e-05 lr:1.3134251542544774e-07 tokens_per_second_per_gpu:6984.0666242827965 Step 142 | loss:2.4724777176743373e-05 lr:5.838865838366792e-08 tokens_per_second_per_gpu:7075.712065137365 Step 143 | loss:3.1426738132722676e-05 lr:1.4599295990352924e-08 tokens_per_second_per_gpu:7128.753672967242 Step 144 | loss:8.870113379089162e-05 lr:0.0 tokens_per_second_per_gpu:7017.73227791866