diff --git "a/loss_log.txt" "b/loss_log.txt" new file mode 100644--- /dev/null +++ "b/loss_log.txt" @@ -0,0 +1,8064 @@ +h09Step 1 | loss:23.1383056640625 lr:2.5e-06 tokens_per_second_per_gpu:348.9456493001084 +Step 2 | loss:23.049884796142578 lr:5e-06 tokens_per_second_per_gpu:660.1254161613391 +Step 3 | loss:17.224260330200195 lr:7.5e-06 tokens_per_second_per_gpu:748.2571164374905 +Step 4 | loss:13.74847412109375 lr:1e-05 tokens_per_second_per_gpu:773.3043290534115 +Step 5 | loss:12.887229919433594 lr:1.25e-05 tokens_per_second_per_gpu:733.218750550965 +Step 6 | loss:11.686604499816895 lr:1.5e-05 tokens_per_second_per_gpu:763.9361612771563 +Step 7 | loss:10.253026962280273 lr:1.75e-05 tokens_per_second_per_gpu:779.8629481577535 +Step 8 | loss:8.749797821044922 lr:2e-05 tokens_per_second_per_gpu:756.3837224624288 +Step 9 | loss:8.565296173095703 lr:2.25e-05 tokens_per_second_per_gpu:744.2922472274712 +Step 10 | loss:8.157066345214844 lr:2.5e-05 tokens_per_second_per_gpu:755.7553297715766 +Step 11 | loss:7.828578472137451 lr:2.7500000000000004e-05 tokens_per_second_per_gpu:736.9984171022476 +Step 12 | loss:7.450377941131592 lr:3e-05 tokens_per_second_per_gpu:765.2077736446419 +Step 13 | loss:7.128231525421143 lr:3.2500000000000004e-05 tokens_per_second_per_gpu:769.3191290124137 +Step 14 | loss:6.842988967895508 lr:3.5e-05 tokens_per_second_per_gpu:747.5336173144996 +Step 15 | loss:6.607292175292969 lr:3.7500000000000003e-05 tokens_per_second_per_gpu:762.6559027258877 +Step 16 | loss:6.47810173034668 lr:4e-05 tokens_per_second_per_gpu:755.9108392470811 +Step 17 | loss:6.325036525726318 lr:4.25e-05 tokens_per_second_per_gpu:743.7169916038712 +Step 18 | loss:6.317660808563232 lr:4.5e-05 tokens_per_second_per_gpu:766.3330805345191 +Step 19 | loss:6.144715309143066 lr:4.75e-05 tokens_per_second_per_gpu:770.9469450610419 +Step 20 | loss:6.112294673919678 lr:5e-05 tokens_per_second_per_gpu:768.3107567714709 +Step 21 | loss:6.093757629394531 lr:5.25e-05 tokens_per_second_per_gpu:778.2869100050038 +Step 22 | loss:6.106443881988525 lr:5.500000000000001e-05 tokens_per_second_per_gpu:778.7271955368008 +Step 23 | loss:6.014016151428223 lr:5.7499999999999995e-05 tokens_per_second_per_gpu:769.9201050517153 +Step 24 | loss:6.012807846069336 lr:6e-05 tokens_per_second_per_gpu:759.0796364835704 +Step 25 | loss:5.989124774932861 lr:6.25e-05 tokens_per_second_per_gpu:776.8558274178398 +Step 26 | loss:5.969160556793213 lr:6.500000000000001e-05 tokens_per_second_per_gpu:775.8771346861375 +Step 27 | loss:5.936854839324951 lr:6.750000000000001e-05 tokens_per_second_per_gpu:762.9331848338738 +Step 28 | loss:5.930723190307617 lr:7e-05 tokens_per_second_per_gpu:771.517822035583 +Step 29 | loss:5.920095443725586 lr:7.25e-05 tokens_per_second_per_gpu:783.2398757247568 +Step 30 | loss:5.911574840545654 lr:7.500000000000001e-05 tokens_per_second_per_gpu:774.4418216235678 +Step 31 | loss:5.8992204666137695 lr:7.75e-05 tokens_per_second_per_gpu:770.9674395677708 +Step 32 | loss:5.877628326416016 lr:8e-05 tokens_per_second_per_gpu:765.5730370170403 +Step 33 | loss:5.8828444480896 lr:8.25e-05 tokens_per_second_per_gpu:752.8384100208293 +Step 34 | loss:5.875374794006348 lr:8.5e-05 tokens_per_second_per_gpu:764.6930515789617 +Step 35 | loss:5.874391555786133 lr:8.75e-05 tokens_per_second_per_gpu:781.6270261500975 +Step 36 | loss:5.846567153930664 lr:9e-05 tokens_per_second_per_gpu:770.5915436526568 +Step 37 | loss:5.876285076141357 lr:9.250000000000001e-05 tokens_per_second_per_gpu:753.0490234777901 +Step 38 | loss:5.89816427230835 lr:9.5e-05 tokens_per_second_per_gpu:743.0278094634468 +Step 39 | loss:5.8625640869140625 lr:9.75e-05 tokens_per_second_per_gpu:764.1400072779064 +Step 40 | loss:5.917813301086426 lr:0.0001 tokens_per_second_per_gpu:763.6725138022259 +Step 41 | loss:5.809134006500244 lr:0.0001025 tokens_per_second_per_gpu:764.4061352145249 +Step 42 | loss:5.829002857208252 lr:0.000105 tokens_per_second_per_gpu:763.9805978931347 +Step 43 | loss:5.83132266998291 lr:0.0001075 tokens_per_second_per_gpu:744.5537080394244 +Step 44 | loss:5.82648229598999 lr:0.00011000000000000002 tokens_per_second_per_gpu:755.8580527532939 +Step 45 | loss:5.807488918304443 lr:0.00011250000000000001 tokens_per_second_per_gpu:724.3970595315031 +Step 46 | loss:5.8180084228515625 lr:0.00011499999999999999 tokens_per_second_per_gpu:770.7948016227705 +Step 47 | loss:5.83638334274292 lr:0.00011750000000000001 tokens_per_second_per_gpu:780.2555365517849 +Step 48 | loss:5.850699424743652 lr:0.00012 tokens_per_second_per_gpu:758.8877121272371 +Step 49 | loss:5.833136558532715 lr:0.00012250000000000002 tokens_per_second_per_gpu:778.9304718235022 +Step 50 | loss:5.874137878417969 lr:0.000125 tokens_per_second_per_gpu:775.2850844264557 +Step 51 | loss:5.853473663330078 lr:0.0001275 tokens_per_second_per_gpu:730.3688915009245 +Step 52 | loss:5.797051429748535 lr:0.00013000000000000002 tokens_per_second_per_gpu:757.7986338762844 +Step 53 | loss:5.821016311645508 lr:0.0001325 tokens_per_second_per_gpu:768.6025596867266 +Step 54 | loss:5.830788612365723 lr:0.00013500000000000003 tokens_per_second_per_gpu:754.7591502275492 +Step 55 | loss:5.836033821105957 lr:0.0001375 tokens_per_second_per_gpu:774.8101392583828 +Step 56 | loss:5.7846479415893555 lr:0.00014 tokens_per_second_per_gpu:739.5614442034735 +Step 57 | loss:5.779760360717773 lr:0.00014250000000000002 tokens_per_second_per_gpu:712.6364233144413 +Step 58 | loss:5.797586917877197 lr:0.000145 tokens_per_second_per_gpu:749.4025707470981 +Step 59 | loss:5.864298343658447 lr:0.0001475 tokens_per_second_per_gpu:769.3291722214366 +Step 60 | loss:5.820601463317871 lr:0.00015000000000000001 tokens_per_second_per_gpu:742.5475828206775 +Step 61 | loss:5.849066734313965 lr:0.0001525 tokens_per_second_per_gpu:766.2695724621907 +Step 62 | loss:5.810840606689453 lr:0.000155 tokens_per_second_per_gpu:778.7680565805488 +Step 63 | loss:5.84266471862793 lr:0.0001575 tokens_per_second_per_gpu:756.474084465533 +Step 64 | loss:5.75917387008667 lr:0.00016 tokens_per_second_per_gpu:760.9820261716666 +Step 65 | loss:5.798797607421875 lr:0.00016250000000000002 tokens_per_second_per_gpu:732.9686016871017 +Step 66 | loss:5.743879795074463 lr:0.000165 tokens_per_second_per_gpu:743.2667572878006 +Step 67 | loss:5.736098766326904 lr:0.0001675 tokens_per_second_per_gpu:753.9969786642768 +Step 68 | loss:5.692569732666016 lr:0.00017 tokens_per_second_per_gpu:776.1745359482168 +Step 69 | loss:6.0253801345825195 lr:0.00017250000000000002 tokens_per_second_per_gpu:742.2972835752471 +Step 70 | loss:6.076961517333984 lr:0.000175 tokens_per_second_per_gpu:755.6608876105302 +Step 71 | loss:6.232037544250488 lr:0.0001775 tokens_per_second_per_gpu:766.6244796781808 +Step 72 | loss:6.208469390869141 lr:0.00018 tokens_per_second_per_gpu:765.5796426034822 +Step 73 | loss:6.063745498657227 lr:0.0001825 tokens_per_second_per_gpu:743.5401417859918 +Step 74 | loss:6.015668869018555 lr:0.00018500000000000002 tokens_per_second_per_gpu:771.4737347840636 +Step 75 | loss:5.9831366539001465 lr:0.0001875 tokens_per_second_per_gpu:743.2325839558562 +Step 76 | loss:5.856415271759033 lr:0.00019 tokens_per_second_per_gpu:774.6338245310909 +Step 77 | loss:5.7624077796936035 lr:0.00019250000000000002 tokens_per_second_per_gpu:755.7810906883575 +Step 78 | loss:5.735480308532715 lr:0.000195 tokens_per_second_per_gpu:756.0807752963801 +Step 79 | loss:5.732331275939941 lr:0.00019750000000000003 tokens_per_second_per_gpu:760.2396126230831 +Step 80 | loss:6.103208541870117 lr:0.0002 tokens_per_second_per_gpu:733.6033316870584 +Step 81 | loss:6.103653907775879 lr:0.0001999999922584364 tokens_per_second_per_gpu:765.5387679606237 +Step 82 | loss:5.979250431060791 lr:0.0001999999690337467 tokens_per_second_per_gpu:776.9128876724801 +Step 83 | loss:6.022012233734131 lr:0.00019999993032593456 tokens_per_second_per_gpu:757.6755216647093 +Step 84 | loss:5.860971450805664 lr:0.00019999987613500596 tokens_per_second_per_gpu:747.7390831416233 +Step 85 | loss:5.832777976989746 lr:0.00019999980646096926 tokens_per_second_per_gpu:763.8721386225628 +Step 86 | loss:5.7828192710876465 lr:0.00019999972130383528 tokens_per_second_per_gpu:760.5268732681277 +Step 87 | loss:5.5902838706970215 lr:0.0001999996206636172 tokens_per_second_per_gpu:729.3909123174216 +Step 88 | loss:5.557908535003662 lr:0.00019999950454033062 tokens_per_second_per_gpu:770.7527162786611 +Step 89 | loss:5.4701433181762695 lr:0.00019999937293399347 tokens_per_second_per_gpu:757.6017307479311 +Step 90 | loss:5.293154716491699 lr:0.00019999922584462617 tokens_per_second_per_gpu:771.886753312494 +Step 91 | loss:5.659940242767334 lr:0.00019999906327225147 tokens_per_second_per_gpu:730.6711807288755 +Step 92 | loss:6.0928168296813965 lr:0.00019999888521689456 tokens_per_second_per_gpu:764.683037084419 +Step 93 | loss:6.4849324226379395 lr:0.00019999869167858299 tokens_per_second_per_gpu:768.7168465910505 +Step 94 | loss:6.21609354019165 lr:0.00019999848265734677 tokens_per_second_per_gpu:756.2162850733231 +Step 95 | loss:6.251147747039795 lr:0.00019999825815321818 tokens_per_second_per_gpu:750.830700780054 +Step 96 | loss:6.1631975173950195 lr:0.00019999801816623203 tokens_per_second_per_gpu:759.9557222228617 +Step 97 | loss:6.084164619445801 lr:0.0001999977626964255 tokens_per_second_per_gpu:737.0375465652345 +Step 98 | loss:6.087406158447266 lr:0.00019999749174383813 tokens_per_second_per_gpu:776.5817932285671 +Step 99 | loss:6.105776786804199 lr:0.00019999720530851183 tokens_per_second_per_gpu:770.2032913202415 +Step 100 | loss:5.970592498779297 lr:0.00019999690339049097 tokens_per_second_per_gpu:762.3698651761963 +Step 101 | loss:5.910174369812012 lr:0.00019999658598982234 tokens_per_second_per_gpu:765.3142476908807 +Step 102 | loss:5.737716197967529 lr:0.00019999625310655506 tokens_per_second_per_gpu:761.7292528673107 +Step 103 | loss:5.586511611938477 lr:0.00019999590474074067 tokens_per_second_per_gpu:763.7488486649603 +Step 104 | loss:5.457448959350586 lr:0.00019999554089243304 tokens_per_second_per_gpu:780.8451601957105 +Step 105 | loss:5.449234485626221 lr:0.00019999516156168863 tokens_per_second_per_gpu:738.136890218813 +Step 106 | loss:5.579235553741455 lr:0.00019999476674856608 tokens_per_second_per_gpu:763.0665861703468 +Step 107 | loss:5.498909950256348 lr:0.00019999435645312653 tokens_per_second_per_gpu:759.4032761783213 +Step 108 | loss:5.517745018005371 lr:0.00019999393067543354 tokens_per_second_per_gpu:770.7524589689212 +Step 109 | loss:5.81436014175415 lr:0.00019999348941555301 tokens_per_second_per_gpu:776.1956601259196 +Step 110 | loss:5.47047758102417 lr:0.00019999303267355327 tokens_per_second_per_gpu:790.1026975860649 +Step 111 | loss:5.672069549560547 lr:0.00019999256044950502 tokens_per_second_per_gpu:775.1885999207207 +Step 112 | loss:5.362423896789551 lr:0.00019999207274348142 tokens_per_second_per_gpu:743.2798861886008 +Step 113 | loss:5.18189811706543 lr:0.00019999156955555797 tokens_per_second_per_gpu:735.7128431000863 +Step 114 | loss:5.005560398101807 lr:0.00019999105088581252 tokens_per_second_per_gpu:743.0109214311449 +Step 115 | loss:5.045798301696777 lr:0.00019999051673432543 tokens_per_second_per_gpu:764.9434127932277 +Step 116 | loss:4.87407922744751 lr:0.00019998996710117938 tokens_per_second_per_gpu:764.4537231550586 +Step 117 | loss:4.724734306335449 lr:0.00019998940198645953 tokens_per_second_per_gpu:760.0260351929072 +Step 118 | loss:4.634696960449219 lr:0.0001999888213902533 tokens_per_second_per_gpu:756.8316279649423 +Step 119 | loss:4.486621856689453 lr:0.0001999882253126506 tokens_per_second_per_gpu:784.4221516174897 +Step 120 | loss:4.816398620605469 lr:0.00019998761375374376 tokens_per_second_per_gpu:779.3757029367669 +Step 121 | loss:4.955985069274902 lr:0.00019998698671362742 tokens_per_second_per_gpu:765.6264856998101 +Step 122 | loss:4.847987174987793 lr:0.0001999863441923987 tokens_per_second_per_gpu:769.379030628148 +Step 123 | loss:4.7537617683410645 lr:0.00019998568619015704 tokens_per_second_per_gpu:761.9802050722578 +Step 124 | loss:4.731329441070557 lr:0.00019998501270700444 tokens_per_second_per_gpu:767.3266965121828 +Step 125 | loss:4.859186172485352 lr:0.000199984323743045 tokens_per_second_per_gpu:782.1621077115 +Step 126 | loss:4.579174995422363 lr:0.0001999836192983855 tokens_per_second_per_gpu:774.9951235000443 +Step 127 | loss:4.537351608276367 lr:0.00019998289937313502 tokens_per_second_per_gpu:746.2052128920252 +Step 128 | loss:4.4690728187561035 lr:0.00019998216396740497 tokens_per_second_per_gpu:763.9427917687392 +Step 129 | loss:4.371546745300293 lr:0.00019998141308130927 tokens_per_second_per_gpu:763.14280324329 +Step 130 | loss:4.280544281005859 lr:0.00019998064671496413 tokens_per_second_per_gpu:765.521993426596 +Step 131 | loss:4.3425517082214355 lr:0.00019997986486848822 tokens_per_second_per_gpu:773.0930188850735 +Step 132 | loss:4.258113861083984 lr:0.00019997906754200262 tokens_per_second_per_gpu:755.4594641218409 +Step 133 | loss:4.203635215759277 lr:0.00019997825473563077 tokens_per_second_per_gpu:767.0718023489306 +Step 134 | loss:4.238587379455566 lr:0.00019997742644949852 tokens_per_second_per_gpu:781.5555322642506 +Step 135 | loss:4.183294296264648 lr:0.00019997658268373406 tokens_per_second_per_gpu:769.8474470832392 +Step 136 | loss:4.070291042327881 lr:0.00019997572343846814 tokens_per_second_per_gpu:759.5191995545074 +Step 137 | loss:4.035970211029053 lr:0.00019997484871383368 tokens_per_second_per_gpu:733.482258164453 +Step 138 | loss:3.9680047035217285 lr:0.0001999739585099662 tokens_per_second_per_gpu:771.8750851541998 +Step 139 | loss:3.7813758850097656 lr:0.0001999730528270035 tokens_per_second_per_gpu:776.7979043636038 +Step 140 | loss:3.8680999279022217 lr:0.00019997213166508582 tokens_per_second_per_gpu:739.4974503402659 +Step 141 | loss:4.047509670257568 lr:0.00019997119502435578 tokens_per_second_per_gpu:770.0478825264819 +Step 142 | loss:3.966045379638672 lr:0.00019997024290495835 tokens_per_second_per_gpu:766.9644769160518 +Step 143 | loss:3.9110021591186523 lr:0.00019996927530704106 tokens_per_second_per_gpu:767.5140800500957 +Step 144 | loss:4.052016735076904 lr:0.00019996829223075361 tokens_per_second_per_gpu:750.4460082707421 +Step 145 | loss:3.9657654762268066 lr:0.00019996729367624826 tokens_per_second_per_gpu:785.8677824154167 +Step 146 | loss:3.895627975463867 lr:0.00019996627964367965 tokens_per_second_per_gpu:733.1504258654018 +Step 147 | loss:3.9522197246551514 lr:0.00019996525013320473 tokens_per_second_per_gpu:768.7240839201672 +Step 148 | loss:3.958646774291992 lr:0.00019996420514498296 tokens_per_second_per_gpu:737.4237205609792 +Step 149 | loss:3.8525872230529785 lr:0.00019996314467917605 tokens_per_second_per_gpu:779.0642596649184 +Step 150 | loss:3.807493209838867 lr:0.00019996206873594826 tokens_per_second_per_gpu:758.6475609022839 +Step 151 | loss:3.708500623703003 lr:0.00019996097731546616 tokens_per_second_per_gpu:772.376961348271 +Step 152 | loss:3.7774226665496826 lr:0.00019995987041789874 tokens_per_second_per_gpu:752.2759393519676 +Step 153 | loss:3.7926149368286133 lr:0.00019995874804341738 tokens_per_second_per_gpu:746.9630504223317 +Step 154 | loss:3.7640132904052734 lr:0.00019995761019219585 tokens_per_second_per_gpu:762.9005671905738 +Step 155 | loss:3.6782994270324707 lr:0.00019995645686441034 tokens_per_second_per_gpu:771.9009928455071 +Step 156 | loss:3.6368346214294434 lr:0.00019995528806023943 tokens_per_second_per_gpu:749.820050931916 +Step 157 | loss:3.6973540782928467 lr:0.00019995410377986406 tokens_per_second_per_gpu:758.615244049862 +Step 158 | loss:3.653724431991577 lr:0.0001999529040234676 tokens_per_second_per_gpu:739.3098876678735 +Step 159 | loss:3.602363348007202 lr:0.00019995168879123582 tokens_per_second_per_gpu:756.0319122725375 +Step 160 | loss:3.5851492881774902 lr:0.00019995045808335687 tokens_per_second_per_gpu:751.2868941123846 +Step 161 | loss:3.5332820415496826 lr:0.00019994921190002129 tokens_per_second_per_gpu:754.1609446995348 +Step 162 | loss:3.569904088973999 lr:0.00019994795024142208 tokens_per_second_per_gpu:757.4790039737162 +Step 163 | loss:3.6154704093933105 lr:0.0001999466731077545 tokens_per_second_per_gpu:719.0870740969227 +Step 164 | loss:3.493010997772217 lr:0.00019994538049921637 tokens_per_second_per_gpu:748.920784810256 +Step 165 | loss:3.5173020362854004 lr:0.00019994407241600778 tokens_per_second_per_gpu:768.7252379182627 +Step 166 | loss:3.5885753631591797 lr:0.0001999427488583313 tokens_per_second_per_gpu:769.2214576832212 +Step 167 | loss:3.5733158588409424 lr:0.0001999414098263918 tokens_per_second_per_gpu:769.33728667638 +Step 168 | loss:3.5300662517547607 lr:0.00019994005532039663 tokens_per_second_per_gpu:761.4427261063756 +Step 169 | loss:3.5078940391540527 lr:0.00019993868534055556 tokens_per_second_per_gpu:743.9868892815539 +Step 170 | loss:3.501958131790161 lr:0.00019993729988708063 tokens_per_second_per_gpu:786.767161192357 +Step 171 | loss:3.5222995281219482 lr:0.0001999358989601864 tokens_per_second_per_gpu:773.9711543673708 +Step 172 | loss:3.504517078399658 lr:0.00019993448256008973 tokens_per_second_per_gpu:756.2175482380655 +Step 173 | loss:3.427271604537964 lr:0.00019993305068701 tokens_per_second_per_gpu:755.7124044553908 +Step 174 | loss:3.4905078411102295 lr:0.0001999316033411688 tokens_per_second_per_gpu:763.146041790159 +Step 175 | loss:3.421877861022949 lr:0.00019993014052279034 tokens_per_second_per_gpu:754.7366856328839 +Step 176 | loss:3.3634347915649414 lr:0.00019992866223210104 tokens_per_second_per_gpu:737.0129975144586 +Step 177 | loss:3.4008917808532715 lr:0.00019992716846932982 tokens_per_second_per_gpu:772.0365205364191 +Step 178 | loss:3.4232563972473145 lr:0.00019992565923470794 tokens_per_second_per_gpu:771.2057119345562 +Step 179 | loss:3.3585755825042725 lr:0.00019992413452846907 tokens_per_second_per_gpu:780.363994344467 +Step 180 | loss:3.2674124240875244 lr:0.00019992259435084927 tokens_per_second_per_gpu:771.9269032888338 +Step 181 | loss:3.3243346214294434 lr:0.00019992103870208707 tokens_per_second_per_gpu:771.0911361091454 +Step 182 | loss:3.3530328273773193 lr:0.00019991946758242328 tokens_per_second_per_gpu:770.9123835949109 +Step 183 | loss:3.344665050506592 lr:0.0001999178809921012 tokens_per_second_per_gpu:722.5139814296185 +Step 184 | loss:3.275367498397827 lr:0.0001999162789313664 tokens_per_second_per_gpu:720.6384139940574 +Step 185 | loss:3.392603635787964 lr:0.000199914661400467 tokens_per_second_per_gpu:770.0320703397623 +Step 186 | loss:3.2947328090667725 lr:0.00019991302839965347 tokens_per_second_per_gpu:776.0431270580365 +Step 187 | loss:3.33259916305542 lr:0.00019991137992917858 tokens_per_second_per_gpu:772.3320602868548 +Step 188 | loss:3.306861639022827 lr:0.0001999097159892976 tokens_per_second_per_gpu:750.3589187853793 +Step 189 | loss:3.3128697872161865 lr:0.00019990803658026816 tokens_per_second_per_gpu:758.8169990605187 +Step 190 | loss:3.2421443462371826 lr:0.00019990634170235025 tokens_per_second_per_gpu:703.42013075317 +Step 191 | loss:3.3018791675567627 lr:0.00019990463135580636 tokens_per_second_per_gpu:769.9423259056537 +Step 192 | loss:3.226256847381592 lr:0.00019990290554090123 tokens_per_second_per_gpu:745.958954027094 +Step 193 | loss:3.326505422592163 lr:0.00019990116425790212 tokens_per_second_per_gpu:770.1347527419579 +Step 194 | loss:3.248148202896118 lr:0.00019989940750707864 tokens_per_second_per_gpu:754.8006758494574 +Step 195 | loss:3.228278636932373 lr:0.00019989763528870273 tokens_per_second_per_gpu:759.1534407246487 +Step 196 | loss:3.2045350074768066 lr:0.00019989584760304885 tokens_per_second_per_gpu:789.2167375029151 +Step 197 | loss:3.182413339614868 lr:0.00019989404445039374 tokens_per_second_per_gpu:777.5723929512199 +Step 198 | loss:3.17328143119812 lr:0.00019989222583101664 tokens_per_second_per_gpu:738.5726256090576 +Step 199 | loss:3.231567144393921 lr:0.0001998903917451991 tokens_per_second_per_gpu:767.6299728753805 +Step 200 | loss:3.1867623329162598 lr:0.00019988854219322506 tokens_per_second_per_gpu:767.0003365227991 +Step 201 | loss:3.128021001815796 lr:0.00019988667717538093 tokens_per_second_per_gpu:743.9087660873307 +Step 202 | loss:3.1360573768615723 lr:0.0001998847966919555 tokens_per_second_per_gpu:764.2866297507362 +Step 203 | loss:3.0931997299194336 lr:0.0001998829007432398 tokens_per_second_per_gpu:756.7665199321984 +Step 204 | loss:3.173245429992676 lr:0.00019988098932952755 tokens_per_second_per_gpu:782.5765313464639 +Step 205 | loss:3.1238255500793457 lr:0.0001998790624511146 tokens_per_second_per_gpu:751.8333312757464 +Step 206 | loss:3.178152322769165 lr:0.0001998771201082993 tokens_per_second_per_gpu:769.190254414193 +Step 207 | loss:3.168410539627075 lr:0.00019987516230138242 tokens_per_second_per_gpu:780.5619871523211 +Step 208 | loss:3.0982766151428223 lr:0.00019987318903066706 tokens_per_second_per_gpu:780.4046420424371 +Step 209 | loss:3.0406341552734375 lr:0.0001998712002964587 tokens_per_second_per_gpu:741.0381841654158 +Step 210 | loss:3.1832754611968994 lr:0.00019986919609906538 tokens_per_second_per_gpu:783.8839879900667 +Step 211 | loss:3.125009536743164 lr:0.00019986717643879728 tokens_per_second_per_gpu:762.9742775122374 +Step 212 | loss:3.195193290710449 lr:0.0001998651413159672 tokens_per_second_per_gpu:771.8456994786852 +Step 213 | loss:3.0630486011505127 lr:0.00019986309073089022 tokens_per_second_per_gpu:763.4289441558192 +Step 214 | loss:3.0361149311065674 lr:0.0001998610246838838 tokens_per_second_per_gpu:752.8173173011435 +Step 215 | loss:3.167987823486328 lr:0.00019985894317526786 tokens_per_second_per_gpu:754.9063442297988 +Step 216 | loss:3.1127123832702637 lr:0.00019985684620536467 tokens_per_second_per_gpu:748.2002139305717 +Step 217 | loss:3.005049467086792 lr:0.0001998547337744989 tokens_per_second_per_gpu:759.0010383186127 +Step 218 | loss:3.0229852199554443 lr:0.00019985260588299765 tokens_per_second_per_gpu:747.6943742910496 +Step 219 | loss:3.14624285697937 lr:0.00019985046253119033 tokens_per_second_per_gpu:785.5793872031605 +Step 220 | loss:3.021475315093994 lr:0.00019984830371940886 tokens_per_second_per_gpu:765.2121568895321 +Step 221 | loss:3.0711774826049805 lr:0.00019984612944798746 tokens_per_second_per_gpu:761.5842114974259 +Step 222 | loss:3.0104360580444336 lr:0.00019984393971726278 tokens_per_second_per_gpu:731.9348526457668 +Step 223 | loss:2.994818925857544 lr:0.00019984173452757386 tokens_per_second_per_gpu:774.1599322377684 +Step 224 | loss:3.0273406505584717 lr:0.00019983951387926214 tokens_per_second_per_gpu:747.2251366611575 +Step 225 | loss:3.139474391937256 lr:0.0001998372777726714 tokens_per_second_per_gpu:780.5605099255545 +Step 226 | loss:3.0499136447906494 lr:0.00019983502620814792 tokens_per_second_per_gpu:746.565492565852 +Step 227 | loss:3.1046128273010254 lr:0.0001998327591860403 tokens_per_second_per_gpu:759.4190375990827 +Step 228 | loss:3.090927839279175 lr:0.0001998304767066995 tokens_per_second_per_gpu:762.8586041969645 +Step 229 | loss:3.049348831176758 lr:0.00019982817877047898 tokens_per_second_per_gpu:770.4701381642087 +Step 230 | loss:3.12280535697937 lr:0.00019982586537773452 tokens_per_second_per_gpu:757.4418294495266 +Step 231 | loss:3.0515530109405518 lr:0.00019982353652882426 tokens_per_second_per_gpu:754.2395941511561 +Step 232 | loss:3.079690456390381 lr:0.0001998211922241088 tokens_per_second_per_gpu:759.4572049743108 +Step 233 | loss:3.0679287910461426 lr:0.00019981883246395117 tokens_per_second_per_gpu:752.8290034809495 +Step 234 | loss:3.094155788421631 lr:0.00019981645724871663 tokens_per_second_per_gpu:771.2152027335948 +Step 235 | loss:3.0699470043182373 lr:0.00019981406657877302 tokens_per_second_per_gpu:745.3151293768624 +Step 236 | loss:3.0474560260772705 lr:0.00019981166045449046 tokens_per_second_per_gpu:768.5422568040738 +Step 237 | loss:3.0385146141052246 lr:0.0001998092388762415 tokens_per_second_per_gpu:776.5364286434254 +Step 238 | loss:3.0808486938476562 lr:0.0001998068018444011 tokens_per_second_per_gpu:769.5449510064484 +Step 239 | loss:3.0238571166992188 lr:0.00019980434935934653 tokens_per_second_per_gpu:771.8727061168235 +Step 240 | loss:3.0281825065612793 lr:0.00019980188142145754 tokens_per_second_per_gpu:760.3980783457791 +Step 241 | loss:3.080312490463257 lr:0.00019979939803111627 tokens_per_second_per_gpu:756.0557404819314 +Step 242 | loss:2.985811710357666 lr:0.00019979689918870719 tokens_per_second_per_gpu:747.8209474745352 +Step 243 | loss:3.0320262908935547 lr:0.0001997943848946172 tokens_per_second_per_gpu:761.7253719714895 +Step 244 | loss:2.9134554862976074 lr:0.00019979185514923563 tokens_per_second_per_gpu:766.2046447870052 +Step 245 | loss:3.0082879066467285 lr:0.0001997893099529541 tokens_per_second_per_gpu:754.943800454436 +Step 246 | loss:3.0550715923309326 lr:0.00019978674930616676 tokens_per_second_per_gpu:748.0491250765322 +Step 247 | loss:2.9825279712677 lr:0.00019978417320927003 tokens_per_second_per_gpu:770.4594707444899 +Step 248 | loss:2.933588743209839 lr:0.00019978158166266278 tokens_per_second_per_gpu:766.8745310468317 +Step 249 | loss:3.0146403312683105 lr:0.00019977897466674628 tokens_per_second_per_gpu:776.1780500691559 +Step 250 | loss:2.9502811431884766 lr:0.00019977635222192413 tokens_per_second_per_gpu:763.6827449918728 +Step 251 | loss:2.949955940246582 lr:0.00019977371432860244 tokens_per_second_per_gpu:743.4453090474228 +Step 252 | loss:2.886305332183838 lr:0.00019977106098718956 tokens_per_second_per_gpu:787.1853582036794 +Step 253 | loss:2.914462089538574 lr:0.00019976839219809636 tokens_per_second_per_gpu:741.1927005758432 +Step 254 | loss:2.8710808753967285 lr:0.00019976570796173602 tokens_per_second_per_gpu:770.6558733680461 +Step 255 | loss:2.8980305194854736 lr:0.00019976300827852418 tokens_per_second_per_gpu:738.8617238542137 +Step 256 | loss:2.889432668685913 lr:0.00019976029314887881 tokens_per_second_per_gpu:752.9686523333888 +Step 257 | loss:2.8715362548828125 lr:0.0001997575625732203 tokens_per_second_per_gpu:777.705251770573 +Step 258 | loss:2.8425631523132324 lr:0.00019975481655197142 tokens_per_second_per_gpu:740.5222180576536 +Step 259 | loss:2.9411933422088623 lr:0.00019975205508555735 tokens_per_second_per_gpu:771.1378268992364 +Step 260 | loss:2.9488744735717773 lr:0.00019974927817440564 tokens_per_second_per_gpu:779.72459411269 +Step 261 | loss:2.856431007385254 lr:0.0001997464858189463 tokens_per_second_per_gpu:782.2301554301642 +Step 262 | loss:2.8370237350463867 lr:0.0001997436780196116 tokens_per_second_per_gpu:752.910686021452 +Step 263 | loss:2.891678810119629 lr:0.00019974085477683632 tokens_per_second_per_gpu:767.481070612791 +Step 264 | loss:2.895522117614746 lr:0.00019973801609105755 tokens_per_second_per_gpu:779.3212307936141 +Step 265 | loss:2.918071746826172 lr:0.00019973516196271484 tokens_per_second_per_gpu:749.8421601930967 +Step 266 | loss:2.945570707321167 lr:0.00019973229239225008 tokens_per_second_per_gpu:774.334178505331 +Step 267 | loss:2.815294027328491 lr:0.0001997294073801076 tokens_per_second_per_gpu:776.307203683292 +Step 268 | loss:2.8807315826416016 lr:0.00019972650692673405 tokens_per_second_per_gpu:757.8034165959293 +Step 269 | loss:2.7817749977111816 lr:0.0001997235910325785 tokens_per_second_per_gpu:760.672458860291 +Step 270 | loss:2.743204355239868 lr:0.00019972065969809245 tokens_per_second_per_gpu:690.0774543306858 +Step 271 | loss:2.7901721000671387 lr:0.00019971771292372982 tokens_per_second_per_gpu:778.3826569528195 +Step 272 | loss:2.8783786296844482 lr:0.00019971475070994674 tokens_per_second_per_gpu:760.6356661138891 +Step 273 | loss:2.7418761253356934 lr:0.00019971177305720195 tokens_per_second_per_gpu:775.2999224294202 +Step 274 | loss:2.826639175415039 lr:0.00019970877996595645 tokens_per_second_per_gpu:731.5600763544769 +Step 275 | loss:2.8441643714904785 lr:0.00019970577143667363 tokens_per_second_per_gpu:781.404536682863 +Step 276 | loss:2.771372079849243 lr:0.0001997027474698194 tokens_per_second_per_gpu:773.2938787473814 +Step 277 | loss:2.7814104557037354 lr:0.00019969970806586184 tokens_per_second_per_gpu:766.8994187364233 +Step 278 | loss:2.7928671836853027 lr:0.0001996966532252716 tokens_per_second_per_gpu:753.4094517035568 +Step 279 | loss:2.812354326248169 lr:0.00019969358294852173 tokens_per_second_per_gpu:775.1441660560348 +Step 280 | loss:2.8139050006866455 lr:0.00019969049723608752 tokens_per_second_per_gpu:755.7360469935555 +Step 281 | loss:2.8013625144958496 lr:0.00019968739608844678 tokens_per_second_per_gpu:761.5030176173128 +Step 282 | loss:2.7716012001037598 lr:0.00019968427950607965 tokens_per_second_per_gpu:713.1729745762021 +Step 283 | loss:2.848947048187256 lr:0.00019968114748946864 tokens_per_second_per_gpu:749.5541370518472 +Step 284 | loss:2.7624025344848633 lr:0.00019967800003909872 tokens_per_second_per_gpu:758.1821259665496 +Step 285 | loss:2.8047432899475098 lr:0.00019967483715545723 tokens_per_second_per_gpu:776.4556849875983 +Step 286 | loss:2.6309471130371094 lr:0.00019967165883903385 tokens_per_second_per_gpu:746.3704400762114 +Step 287 | loss:2.783865213394165 lr:0.0001996684650903207 tokens_per_second_per_gpu:777.5163348143469 +Step 288 | loss:2.800138473510742 lr:0.00019966525590981227 tokens_per_second_per_gpu:779.190728521944 +Step 289 | loss:2.778599739074707 lr:0.00019966203129800545 tokens_per_second_per_gpu:759.5575470922015 +Step 290 | loss:2.7212154865264893 lr:0.00019965879125539946 tokens_per_second_per_gpu:747.5921565481971 +Step 291 | loss:2.7977747917175293 lr:0.00019965553578249603 tokens_per_second_per_gpu:764.8566174362591 +Step 292 | loss:2.7767653465270996 lr:0.00019965226487979917 tokens_per_second_per_gpu:770.9383539960437 +Step 293 | loss:2.8502063751220703 lr:0.00019964897854781534 tokens_per_second_per_gpu:773.0190312199977 +Step 294 | loss:2.79187273979187 lr:0.00019964567678705335 tokens_per_second_per_gpu:780.2232178238237 +Step 295 | loss:2.772562026977539 lr:0.0001996423595980244 tokens_per_second_per_gpu:779.8623301291292 +Step 296 | loss:2.6801915168762207 lr:0.00019963902698124213 tokens_per_second_per_gpu:748.0298998971771 +Step 297 | loss:2.709527015686035 lr:0.00019963567893722253 tokens_per_second_per_gpu:761.3314987536208 +Step 298 | loss:2.697321891784668 lr:0.00019963231546648395 tokens_per_second_per_gpu:715.3439592332923 +Step 299 | loss:2.6757519245147705 lr:0.00019962893656954718 tokens_per_second_per_gpu:782.9884623753217 +Step 300 | loss:2.7226765155792236 lr:0.00019962554224693538 tokens_per_second_per_gpu:757.8123930356305 +Step 301 | loss:2.7302231788635254 lr:0.00019962213249917412 tokens_per_second_per_gpu:760.9006442019854 +Step 302 | loss:2.7558517456054688 lr:0.00019961870732679128 tokens_per_second_per_gpu:762.4811332093597 +Step 303 | loss:2.7094550132751465 lr:0.00019961526673031724 tokens_per_second_per_gpu:762.3075190003286 +Step 304 | loss:2.8253042697906494 lr:0.00019961181071028467 tokens_per_second_per_gpu:743.8098918020843 +Step 305 | loss:2.7515573501586914 lr:0.0001996083392672287 tokens_per_second_per_gpu:766.8976874431631 +Step 306 | loss:2.793705463409424 lr:0.00019960485240168681 tokens_per_second_per_gpu:766.3873370103919 +Step 307 | loss:2.689953565597534 lr:0.00019960135011419885 tokens_per_second_per_gpu:759.1228791499543 +Step 308 | loss:2.715536594390869 lr:0.00019959783240530712 tokens_per_second_per_gpu:773.4779302863222 +Step 309 | loss:2.729647636413574 lr:0.00019959429927555626 tokens_per_second_per_gpu:749.9124642642311 +Step 310 | loss:2.7426464557647705 lr:0.0001995907507254933 tokens_per_second_per_gpu:734.9230207552228 +Step 311 | loss:2.73752498626709 lr:0.00019958718675566766 tokens_per_second_per_gpu:740.9277191549265 +Step 312 | loss:2.663421154022217 lr:0.00019958360736663117 tokens_per_second_per_gpu:779.5667862347127 +Step 313 | loss:2.7191617488861084 lr:0.00019958001255893803 tokens_per_second_per_gpu:786.2598790806626 +Step 314 | loss:2.829979419708252 lr:0.00019957640233314483 tokens_per_second_per_gpu:772.5271513023552 +Step 315 | loss:2.7300775051116943 lr:0.00019957277668981055 tokens_per_second_per_gpu:762.7743603354909 +Step 316 | loss:2.7128825187683105 lr:0.0001995691356294965 tokens_per_second_per_gpu:782.183072613801 +Step 317 | loss:2.6822023391723633 lr:0.00019956547915276653 tokens_per_second_per_gpu:771.2768586074392 +Step 318 | loss:2.7120447158813477 lr:0.00019956180726018668 tokens_per_second_per_gpu:764.9998693662978 +Step 319 | loss:2.7186625003814697 lr:0.00019955811995232554 tokens_per_second_per_gpu:771.7259585932464 +Step 320 | loss:2.7090582847595215 lr:0.000199554417229754 tokens_per_second_per_gpu:744.7432674309666 +Step 321 | loss:2.6821069717407227 lr:0.00019955069909304536 tokens_per_second_per_gpu:748.4417696145806 +Step 322 | loss:2.681222915649414 lr:0.00019954696554277525 tokens_per_second_per_gpu:775.7446050236587 +Step 323 | loss:2.6649577617645264 lr:0.00019954321657952184 tokens_per_second_per_gpu:776.5639550420904 +Step 324 | loss:2.6118178367614746 lr:0.00019953945220386551 tokens_per_second_per_gpu:747.6955587402525 +Step 325 | loss:2.6544761657714844 lr:0.00019953567241638912 tokens_per_second_per_gpu:754.1666189744841 +Step 326 | loss:2.720073938369751 lr:0.00019953187721767792 tokens_per_second_per_gpu:759.1029429985578 +Step 327 | loss:2.588958263397217 lr:0.0001995280666083195 tokens_per_second_per_gpu:761.9590378190996 +Step 328 | loss:2.648573398590088 lr:0.00019952424058890388 tokens_per_second_per_gpu:746.4860005541815 +Step 329 | loss:2.656616687774658 lr:0.00019952039916002346 tokens_per_second_per_gpu:760.5612591777585 +Step 330 | loss:2.7785534858703613 lr:0.00019951654232227298 tokens_per_second_per_gpu:748.4582582906993 +Step 331 | loss:2.9133455753326416 lr:0.0001995126700762496 tokens_per_second_per_gpu:714.2272674056152 +Step 332 | loss:2.917120933532715 lr:0.0001995087824225529 tokens_per_second_per_gpu:789.7515405508597 +Step 333 | loss:3.0076255798339844 lr:0.00019950487936178476 tokens_per_second_per_gpu:770.7938771301066 +Step 334 | loss:3.058406352996826 lr:0.00019950096089454955 tokens_per_second_per_gpu:760.7861695843212 +Step 335 | loss:2.971101999282837 lr:0.00019949702702145393 tokens_per_second_per_gpu:779.2019546457186 +Step 336 | loss:2.962874412536621 lr:0.000199493077743107 tokens_per_second_per_gpu:775.2858333954907 +Step 337 | loss:2.973937749862671 lr:0.00019948911306012023 tokens_per_second_per_gpu:757.4951213822725 +Step 338 | loss:2.953063488006592 lr:0.00019948513297310752 tokens_per_second_per_gpu:763.9100091597361 +Step 339 | loss:2.912864923477173 lr:0.000199481137482685 tokens_per_second_per_gpu:758.2990272580511 +Step 340 | loss:2.8480732440948486 lr:0.00019947712658947145 tokens_per_second_per_gpu:752.6166676675771 +Step 341 | loss:2.7902636528015137 lr:0.00019947310029408777 tokens_per_second_per_gpu:760.3878351054551 +Step 342 | loss:2.926133155822754 lr:0.00019946905859715737 tokens_per_second_per_gpu:762.9551273186959 +Step 343 | loss:2.8400282859802246 lr:0.00019946500149930607 tokens_per_second_per_gpu:766.3014480305608 +Step 344 | loss:2.8354716300964355 lr:0.000199460929001162 tokens_per_second_per_gpu:718.2313672115486 +Step 345 | loss:2.7306761741638184 lr:0.00019945684110335573 tokens_per_second_per_gpu:774.8666773318464 +Step 346 | loss:2.744534730911255 lr:0.00019945273780652017 tokens_per_second_per_gpu:769.4162605707365 +Step 347 | loss:2.6889681816101074 lr:0.00019944861911129068 tokens_per_second_per_gpu:766.9133639261008 +Step 348 | loss:2.7902774810791016 lr:0.00019944448501830496 tokens_per_second_per_gpu:746.7044726808349 +Step 349 | loss:2.6608355045318604 lr:0.00019944033552820304 tokens_per_second_per_gpu:767.1757018240214 +Step 350 | loss:2.7917025089263916 lr:0.00019943617064162745 tokens_per_second_per_gpu:746.2716378752528 +Step 351 | loss:2.7103428840637207 lr:0.000199431990359223 tokens_per_second_per_gpu:757.1834831238156 +Step 352 | loss:2.695491075515747 lr:0.00019942779468163697 tokens_per_second_per_gpu:771.1324067944666 +Step 353 | loss:2.722940444946289 lr:0.00019942358360951898 tokens_per_second_per_gpu:748.4603490598627 +Step 354 | loss:2.8127076625823975 lr:0.000199419357143521 tokens_per_second_per_gpu:773.9017956294684 +Step 355 | loss:2.7085671424865723 lr:0.00019941511528429745 tokens_per_second_per_gpu:753.9179062298275 +Step 356 | loss:2.7640676498413086 lr:0.00019941085803250506 tokens_per_second_per_gpu:766.4956787124676 +Step 357 | loss:2.6612491607666016 lr:0.00019940658538880303 tokens_per_second_per_gpu:750.7445081472484 +Step 358 | loss:2.7131736278533936 lr:0.00019940229735385288 tokens_per_second_per_gpu:772.0173589564752 +Step 359 | loss:2.5957908630371094 lr:0.00019939799392831856 tokens_per_second_per_gpu:762.8711890974826 +Step 360 | loss:2.7612831592559814 lr:0.00019939367511286635 tokens_per_second_per_gpu:769.9844742166979 +Step 361 | loss:2.6780154705047607 lr:0.0001993893409081649 tokens_per_second_per_gpu:770.7115933226647 +Step 362 | loss:2.671326160430908 lr:0.00019938499131488534 tokens_per_second_per_gpu:784.4056142624356 +Step 363 | loss:2.6861608028411865 lr:0.00019938062633370114 tokens_per_second_per_gpu:738.3939365471224 +Step 364 | loss:2.7053990364074707 lr:0.00019937624596528806 tokens_per_second_per_gpu:748.9260372177602 +Step 365 | loss:2.6781773567199707 lr:0.0001993718502103244 tokens_per_second_per_gpu:760.7666281651893 +Step 366 | loss:2.6133761405944824 lr:0.00019936743906949066 tokens_per_second_per_gpu:755.1891750212501 +Step 367 | loss:2.7082340717315674 lr:0.0001993630125434699 tokens_per_second_per_gpu:765.4980666250144 +Step 368 | loss:2.7004387378692627 lr:0.00019935857063294748 tokens_per_second_per_gpu:782.9857983725242 +Step 369 | loss:2.6116762161254883 lr:0.00019935411333861112 tokens_per_second_per_gpu:750.1384744156505 +Step 370 | loss:2.6298108100891113 lr:0.00019934964066115093 tokens_per_second_per_gpu:772.736202011277 +Step 371 | loss:2.6670279502868652 lr:0.0001993451526012595 tokens_per_second_per_gpu:755.9897673596328 +Step 372 | loss:2.703042984008789 lr:0.00019934064915963165 tokens_per_second_per_gpu:780.0043019771649 +Step 373 | loss:2.6537060737609863 lr:0.00019933613033696465 tokens_per_second_per_gpu:771.126674054002 +Step 374 | loss:2.6857213973999023 lr:0.00019933159613395822 tokens_per_second_per_gpu:759.907794242541 +Step 375 | loss:2.694671154022217 lr:0.00019932704655131436 tokens_per_second_per_gpu:775.8882229622756 +Step 376 | loss:2.606468677520752 lr:0.00019932248158973745 tokens_per_second_per_gpu:782.7271093402298 +Step 377 | loss:2.628127098083496 lr:0.00019931790124993434 tokens_per_second_per_gpu:755.2403974645629 +Step 378 | loss:2.6005048751831055 lr:0.0001993133055326142 tokens_per_second_per_gpu:772.1729245049094 +Step 379 | loss:2.6720521450042725 lr:0.00019930869443848858 tokens_per_second_per_gpu:731.3106743422652 +Step 380 | loss:2.630767822265625 lr:0.00019930406796827145 tokens_per_second_per_gpu:760.4584093993379 +Step 381 | loss:2.640923261642456 lr:0.00019929942612267906 tokens_per_second_per_gpu:783.9552441561616 +Step 382 | loss:2.620248317718506 lr:0.00019929476890243018 tokens_per_second_per_gpu:757.7770825575648 +Step 383 | loss:2.608546733856201 lr:0.00019929009630824585 tokens_per_second_per_gpu:780.894637237299 +Step 384 | loss:2.550848960876465 lr:0.0001992854083408496 tokens_per_second_per_gpu:765.8237866934509 +Step 385 | loss:2.6026978492736816 lr:0.0001992807050009672 tokens_per_second_per_gpu:721.8863034037025 +Step 386 | loss:2.532592535018921 lr:0.00019927598628932694 tokens_per_second_per_gpu:751.3781521299778 +Step 387 | loss:2.598527669906616 lr:0.00019927125220665936 tokens_per_second_per_gpu:768.3395204279633 +Step 388 | loss:2.5704424381256104 lr:0.0001992665027536975 tokens_per_second_per_gpu:761.9465316269309 +Step 389 | loss:2.6388607025146484 lr:0.0001992617379311767 tokens_per_second_per_gpu:747.164626437257 +Step 390 | loss:2.6182775497436523 lr:0.00019925695773983466 tokens_per_second_per_gpu:764.3973296331558 +Step 391 | loss:2.5473945140838623 lr:0.0001992521621804116 tokens_per_second_per_gpu:779.3045330074682 +Step 392 | loss:2.573843002319336 lr:0.00019924735125364992 tokens_per_second_per_gpu:761.9121276044568 +Step 393 | loss:2.580709218978882 lr:0.00019924252496029453 tokens_per_second_per_gpu:762.1428820193997 +Step 394 | loss:2.63076114654541 lr:0.00019923768330109277 tokens_per_second_per_gpu:781.7482514077449 +Step 395 | loss:2.6092114448547363 lr:0.00019923282627679417 tokens_per_second_per_gpu:768.3828579641477 +Step 396 | loss:2.6342148780822754 lr:0.00019922795388815085 tokens_per_second_per_gpu:745.7578630559807 +Step 397 | loss:2.5932180881500244 lr:0.00019922306613591714 tokens_per_second_per_gpu:776.4377378260635 +Step 398 | loss:2.5392825603485107 lr:0.00019921816302084983 tokens_per_second_per_gpu:777.0483530093346 +Step 399 | loss:2.5286924839019775 lr:0.00019921324454370807 tokens_per_second_per_gpu:744.9213197856243 +Step 400 | loss:2.6296725273132324 lr:0.00019920831070525342 tokens_per_second_per_gpu:778.3063785704456 +Step 401 | loss:2.599215269088745 lr:0.00019920336150624975 tokens_per_second_per_gpu:744.4914250790994 +Step 402 | loss:2.544064998626709 lr:0.0001991983969474634 tokens_per_second_per_gpu:761.557450555814 +Step 403 | loss:2.5841875076293945 lr:0.00019919341702966302 tokens_per_second_per_gpu:760.2207321849456 +Step 404 | loss:2.573845863342285 lr:0.00019918842175361965 tokens_per_second_per_gpu:776.1105278248165 +Step 405 | loss:2.631944417953491 lr:0.0001991834111201067 tokens_per_second_per_gpu:786.458876822693 +Step 406 | loss:2.608039140701294 lr:0.00019917838512990003 tokens_per_second_per_gpu:778.3067083829334 +Step 407 | loss:2.5903406143188477 lr:0.00019917334378377773 tokens_per_second_per_gpu:754.0781680413787 +Step 408 | loss:2.5842294692993164 lr:0.00019916828708252044 tokens_per_second_per_gpu:757.3018200323015 +Step 409 | loss:2.563265800476074 lr:0.00019916321502691108 tokens_per_second_per_gpu:771.9899318139562 +Step 410 | loss:2.5728650093078613 lr:0.0001991581276177349 tokens_per_second_per_gpu:764.890641510398 +Step 411 | loss:2.5884692668914795 lr:0.00019915302485577966 tokens_per_second_per_gpu:771.49514572567 +Step 412 | loss:2.4774274826049805 lr:0.00019914790674183542 tokens_per_second_per_gpu:748.0998260242067 +Step 413 | loss:2.573162317276001 lr:0.00019914277327669463 tokens_per_second_per_gpu:736.4584507973957 +Step 414 | loss:2.530273199081421 lr:0.00019913762446115206 tokens_per_second_per_gpu:745.1531537996433 +Step 415 | loss:2.5748281478881836 lr:0.00019913246029600493 tokens_per_second_per_gpu:740.3695377058455 +Step 416 | loss:2.5064377784729004 lr:0.00019912728078205283 tokens_per_second_per_gpu:778.2928705108618 +Step 417 | loss:2.581268787384033 lr:0.0001991220859200977 tokens_per_second_per_gpu:749.6843795645503 +Step 418 | loss:2.541278600692749 lr:0.0001991168757109439 tokens_per_second_per_gpu:767.1355768469436 +Step 419 | loss:2.5685105323791504 lr:0.00019911165015539805 tokens_per_second_per_gpu:741.614993997008 +Step 420 | loss:2.5650014877319336 lr:0.00019910640925426934 tokens_per_second_per_gpu:736.7294070781992 +Step 421 | loss:2.5097053050994873 lr:0.0001991011530083691 tokens_per_second_per_gpu:749.3354532219146 +Step 422 | loss:2.467871904373169 lr:0.00019909588141851128 tokens_per_second_per_gpu:768.1220125384414 +Step 423 | loss:2.5715925693511963 lr:0.00019909059448551203 tokens_per_second_per_gpu:771.5880576251812 +Step 424 | loss:2.53450608253479 lr:0.00019908529221018993 tokens_per_second_per_gpu:754.8942449211345 +Step 425 | loss:2.5837268829345703 lr:0.00019907997459336595 tokens_per_second_per_gpu:776.9977348002168 +Step 426 | loss:2.574031114578247 lr:0.00019907464163586346 tokens_per_second_per_gpu:759.108584382302 +Step 427 | loss:2.5332345962524414 lr:0.00019906929333850807 tokens_per_second_per_gpu:716.1194788523463 +Step 428 | loss:2.533526659011841 lr:0.00019906392970212792 tokens_per_second_per_gpu:756.2789573026984 +Step 429 | loss:2.5428009033203125 lr:0.00019905855072755352 tokens_per_second_per_gpu:771.34116832586 +Step 430 | loss:2.6256492137908936 lr:0.0001990531564156176 tokens_per_second_per_gpu:743.0221310963266 +Step 431 | loss:2.5088083744049072 lr:0.00019904774676715548 tokens_per_second_per_gpu:759.2953467231315 +Step 432 | loss:2.5578134059906006 lr:0.00019904232178300464 tokens_per_second_per_gpu:727.0236513360747 +Step 433 | loss:2.5540285110473633 lr:0.0001990368814640051 tokens_per_second_per_gpu:743.2929645866149 +Step 434 | loss:2.502814769744873 lr:0.00019903142581099918 tokens_per_second_per_gpu:759.3774100648852 +Step 435 | loss:2.5089640617370605 lr:0.00019902595482483159 tokens_per_second_per_gpu:768.86225147708 +Step 436 | loss:2.542786121368408 lr:0.00019902046850634933 tokens_per_second_per_gpu:760.8839667866584 +Step 437 | loss:2.5703511238098145 lr:0.000199014966856402 tokens_per_second_per_gpu:736.7549118436214 +Step 438 | loss:2.5509016513824463 lr:0.00019900944987584132 tokens_per_second_per_gpu:767.5089331449675 +Step 439 | loss:2.5261318683624268 lr:0.00019900391756552153 tokens_per_second_per_gpu:781.2466010637448 +Step 440 | loss:2.561877965927124 lr:0.0001989983699262992 tokens_per_second_per_gpu:771.8061988563402 +Step 441 | loss:2.5176491737365723 lr:0.00019899280695903325 tokens_per_second_per_gpu:779.7101249620209 +Step 442 | loss:2.600525379180908 lr:0.00019898722866458507 tokens_per_second_per_gpu:779.8763837613482 +Step 443 | loss:2.4476077556610107 lr:0.00019898163504381827 tokens_per_second_per_gpu:756.5792667672345 +Step 444 | loss:2.4417343139648438 lr:0.000198976026097599 tokens_per_second_per_gpu:717.6040441029103 +Step 445 | loss:2.6120622158050537 lr:0.00019897040182679563 tokens_per_second_per_gpu:776.4799908798165 +Step 446 | loss:2.5790393352508545 lr:0.000198964762232279 tokens_per_second_per_gpu:744.5066575278998 +Step 447 | loss:2.517124652862549 lr:0.00019895910731492232 tokens_per_second_per_gpu:759.2637038678998 +Step 448 | loss:2.523362398147583 lr:0.00019895343707560108 tokens_per_second_per_gpu:760.3899052037849 +Step 449 | loss:2.5253334045410156 lr:0.0001989477515151933 tokens_per_second_per_gpu:788.2894262366203 +Step 450 | loss:2.5425562858581543 lr:0.0001989420506345792 tokens_per_second_per_gpu:746.8019370727698 +Step 451 | loss:2.5802290439605713 lr:0.00019893633443464153 tokens_per_second_per_gpu:784.5984199843745 +Step 452 | loss:2.523271322250366 lr:0.00019893060291626527 tokens_per_second_per_gpu:770.2670638477064 +Step 453 | loss:2.4645767211914062 lr:0.0001989248560803379 tokens_per_second_per_gpu:765.6777773850733 +Step 454 | loss:2.532602310180664 lr:0.00019891909392774913 tokens_per_second_per_gpu:769.54667318995 +Step 455 | loss:2.5298023223876953 lr:0.0001989133164593912 tokens_per_second_per_gpu:752.7215197819268 +Step 456 | loss:2.4923806190490723 lr:0.0001989075236761586 tokens_per_second_per_gpu:788.4413508873191 +Step 457 | loss:2.5133094787597656 lr:0.00019890171557894823 tokens_per_second_per_gpu:763.6968832098529 +Step 458 | loss:2.560171127319336 lr:0.0001988958921686594 tokens_per_second_per_gpu:762.0715534867264 +Step 459 | loss:2.498594284057617 lr:0.00019889005344619375 tokens_per_second_per_gpu:766.2131928598859 +Step 460 | loss:2.496729850769043 lr:0.00019888419941245527 tokens_per_second_per_gpu:788.6862989896135 +Step 461 | loss:2.5381178855895996 lr:0.00019887833006835038 tokens_per_second_per_gpu:776.0677077809994 +Step 462 | loss:2.5955348014831543 lr:0.00019887244541478777 tokens_per_second_per_gpu:750.2783797819844 +Step 463 | loss:2.509014368057251 lr:0.00019886654545267867 tokens_per_second_per_gpu:746.3390214317012 +Step 464 | loss:2.558289051055908 lr:0.0001988606301829365 tokens_per_second_per_gpu:762.9899251722884 +Step 465 | loss:2.5052261352539062 lr:0.00019885469960647712 tokens_per_second_per_gpu:762.7724184551513 +Step 466 | loss:2.5147387981414795 lr:0.00019884875372421884 tokens_per_second_per_gpu:766.7578300841238 +Step 467 | loss:2.468503475189209 lr:0.00019884279253708226 tokens_per_second_per_gpu:761.6749396080723 +Step 468 | loss:2.485184669494629 lr:0.00019883681604599028 tokens_per_second_per_gpu:753.488467202516 +Step 469 | loss:2.4842309951782227 lr:0.00019883082425186833 tokens_per_second_per_gpu:765.3083106220893 +Step 470 | loss:2.5536015033721924 lr:0.00019882481715564407 tokens_per_second_per_gpu:751.6348684661102 +Step 471 | loss:2.478111743927002 lr:0.00019881879475824762 tokens_per_second_per_gpu:751.2728757178157 +Step 472 | loss:2.50495982170105 lr:0.00019881275706061145 tokens_per_second_per_gpu:775.5689750564285 +Step 473 | loss:2.5065975189208984 lr:0.00019880670406367031 tokens_per_second_per_gpu:765.0298474799862 +Step 474 | loss:2.4612255096435547 lr:0.00019880063576836147 tokens_per_second_per_gpu:774.1804239209845 +Step 475 | loss:2.508157730102539 lr:0.00019879455217562447 tokens_per_second_per_gpu:754.5809005877891 +Step 476 | loss:2.536269187927246 lr:0.00019878845328640126 tokens_per_second_per_gpu:765.0282889405115 +Step 477 | loss:2.512253761291504 lr:0.0001987823391016361 tokens_per_second_per_gpu:765.1654873479271 +Step 478 | loss:2.5867297649383545 lr:0.00019877620962227566 tokens_per_second_per_gpu:767.6265648591711 +Step 479 | loss:2.5054569244384766 lr:0.00019877006484926896 tokens_per_second_per_gpu:768.6348999699057 +Step 480 | loss:2.5135066509246826 lr:0.00019876390478356748 tokens_per_second_per_gpu:762.8115410507254 +Step 481 | loss:2.5377566814422607 lr:0.00019875772942612492 tokens_per_second_per_gpu:755.0774583566034 +Step 482 | loss:2.4262890815734863 lr:0.00019875153877789745 tokens_per_second_per_gpu:744.4288480146048 +Step 483 | loss:2.465970993041992 lr:0.00019874533283984356 tokens_per_second_per_gpu:706.1079636499597 +Step 484 | loss:2.5237576961517334 lr:0.0001987391116129241 tokens_per_second_per_gpu:761.8109970826774 +Step 485 | loss:2.5267863273620605 lr:0.0001987328750981024 tokens_per_second_per_gpu:772.1128281375074 +Step 486 | loss:2.4683690071105957 lr:0.00019872662329634396 tokens_per_second_per_gpu:788.2456016109677 +Step 487 | loss:2.5002663135528564 lr:0.00019872035620861682 tokens_per_second_per_gpu:770.3702517494065 +Step 488 | loss:2.4262542724609375 lr:0.0001987140738358913 tokens_per_second_per_gpu:727.8319781641085 +Step 489 | loss:2.546877384185791 lr:0.0001987077761791401 tokens_per_second_per_gpu:757.9351005511147 +Step 490 | loss:2.4287567138671875 lr:0.0001987014632393383 tokens_per_second_per_gpu:787.1742398885295 +Step 491 | loss:2.4722940921783447 lr:0.00019869513501746336 tokens_per_second_per_gpu:777.4398956497695 +Step 492 | loss:2.4320662021636963 lr:0.0001986887915144951 tokens_per_second_per_gpu:780.0185657469211 +Step 493 | loss:2.4503731727600098 lr:0.0001986824327314156 tokens_per_second_per_gpu:771.7047577119432 +Step 494 | loss:2.5431957244873047 lr:0.0001986760586692095 tokens_per_second_per_gpu:768.9553234702232 +Step 495 | loss:2.492011070251465 lr:0.00019866966932886366 tokens_per_second_per_gpu:760.8127890885767 +Step 496 | loss:2.501220941543579 lr:0.00019866326471136735 tokens_per_second_per_gpu:750.6743864138978 +Step 497 | loss:2.4578850269317627 lr:0.00019865684481771222 tokens_per_second_per_gpu:759.7904152846017 +Step 498 | loss:2.498952865600586 lr:0.00019865040964889229 tokens_per_second_per_gpu:786.8832745514839 +Step 499 | loss:2.544529676437378 lr:0.00019864395920590384 tokens_per_second_per_gpu:775.1191863225932 +Step 500 | loss:2.4481773376464844 lr:0.0001986374934897457 tokens_per_second_per_gpu:744.3987603405333 +Step 501 | loss:2.498131513595581 lr:0.0001986310125014189 tokens_per_second_per_gpu:746.1167137978083 +Step 502 | loss:2.4945387840270996 lr:0.00019862451624192692 tokens_per_second_per_gpu:769.509632264327 +Step 503 | loss:2.5746042728424072 lr:0.00019861800471227562 tokens_per_second_per_gpu:760.9614380869301 +Step 504 | loss:2.4594242572784424 lr:0.00019861147791347313 tokens_per_second_per_gpu:779.9327042007103 +Step 505 | loss:2.486844062805176 lr:0.00019860493584653003 tokens_per_second_per_gpu:777.1877964369604 +Step 506 | loss:2.440779685974121 lr:0.00019859837851245922 tokens_per_second_per_gpu:773.9697954540247 +Step 507 | loss:2.414855718612671 lr:0.00019859180591227598 tokens_per_second_per_gpu:774.3700596275748 +Step 508 | loss:2.4425454139709473 lr:0.000198585218046998 tokens_per_second_per_gpu:772.5936845513263 +Step 509 | loss:2.499605417251587 lr:0.00019857861491764527 tokens_per_second_per_gpu:771.4288779656308 +Step 510 | loss:2.436037540435791 lr:0.00019857199652524013 tokens_per_second_per_gpu:762.5578940799157 +Step 511 | loss:2.4756317138671875 lr:0.00019856536287080734 tokens_per_second_per_gpu:758.2761945674357 +Step 512 | loss:2.4160585403442383 lr:0.00019855871395537395 tokens_per_second_per_gpu:761.3042436081003 +Step 513 | loss:2.501163959503174 lr:0.0001985520497799695 tokens_per_second_per_gpu:761.38387384259 +Step 514 | loss:2.471482753753662 lr:0.00019854537034562575 tokens_per_second_per_gpu:752.8655160059484 +Step 515 | loss:2.5558485984802246 lr:0.00019853867565337692 tokens_per_second_per_gpu:758.6233168647673 +Step 516 | loss:2.425302028656006 lr:0.0001985319657042595 tokens_per_second_per_gpu:734.1364334733335 +Step 517 | loss:2.3563356399536133 lr:0.0001985252404993125 tokens_per_second_per_gpu:770.2618637074266 +Step 518 | loss:2.489306688308716 lr:0.0001985185000395771 tokens_per_second_per_gpu:768.2578494067238 +Step 519 | loss:2.4644579887390137 lr:0.000198511744326097 tokens_per_second_per_gpu:771.7016897098795 +Step 520 | loss:2.397264003753662 lr:0.00019850497335991815 tokens_per_second_per_gpu:745.8679491082175 +Step 521 | loss:2.4419519901275635 lr:0.00019849818714208893 tokens_per_second_per_gpu:783.1744806408457 +Step 522 | loss:2.482513904571533 lr:0.00019849138567366005 tokens_per_second_per_gpu:774.4012067818462 +Step 523 | loss:2.4737133979797363 lr:0.0001984845689556846 tokens_per_second_per_gpu:740.9334317329242 +Step 524 | loss:2.455349922180176 lr:0.000198477736989218 tokens_per_second_per_gpu:781.81738627888 +Step 525 | loss:2.493114948272705 lr:0.00019847088977531806 tokens_per_second_per_gpu:765.3616553242995 +Step 526 | loss:2.410449981689453 lr:0.00019846402731504498 tokens_per_second_per_gpu:771.0507571994106 +Step 527 | loss:2.4613940715789795 lr:0.00019845714960946121 tokens_per_second_per_gpu:786.1850490926116 +Step 528 | loss:2.459024429321289 lr:0.00019845025665963167 tokens_per_second_per_gpu:753.6599771938784 +Step 529 | loss:2.487898588180542 lr:0.00019844334846662364 tokens_per_second_per_gpu:773.423013906168 +Step 530 | loss:2.485103130340576 lr:0.00019843642503150668 tokens_per_second_per_gpu:772.9036510686356 +Step 531 | loss:2.4384102821350098 lr:0.00019842948635535277 tokens_per_second_per_gpu:780.4649157067618 +Step 532 | loss:2.4618618488311768 lr:0.00019842253243923622 tokens_per_second_per_gpu:780.3913021565438 +Step 533 | loss:2.466658353805542 lr:0.00019841556328423375 tokens_per_second_per_gpu:713.8600459880996 +Step 534 | loss:2.4044747352600098 lr:0.00019840857889142437 tokens_per_second_per_gpu:767.6722794018758 +Step 535 | loss:2.451612710952759 lr:0.0001984015792618895 tokens_per_second_per_gpu:772.073695014447 +Step 536 | loss:2.427015781402588 lr:0.00019839456439671286 tokens_per_second_per_gpu:779.9202086620364 +Step 537 | loss:2.4834938049316406 lr:0.00019838753429698064 tokens_per_second_per_gpu:757.9623142225487 +Step 538 | loss:2.396328926086426 lr:0.00019838048896378126 tokens_per_second_per_gpu:723.9848012149762 +Step 539 | loss:2.4397716522216797 lr:0.0001983734283982056 tokens_per_second_per_gpu:767.3156343530235 +Step 540 | loss:2.418447971343994 lr:0.0001983663526013468 tokens_per_second_per_gpu:767.3159890566429 +Step 541 | loss:2.41723370552063 lr:0.0001983592615743005 tokens_per_second_per_gpu:769.6829332951424 +Step 542 | loss:2.466120481491089 lr:0.0001983521553181645 tokens_per_second_per_gpu:764.4568597929779 +Step 543 | loss:2.406615972518921 lr:0.0001983450338340392 tokens_per_second_per_gpu:775.099031878689 +Step 544 | loss:2.4259564876556396 lr:0.00019833789712302713 tokens_per_second_per_gpu:739.4295337692373 +Step 545 | loss:2.4536983966827393 lr:0.0001983307451862333 tokens_per_second_per_gpu:757.1790411437128 +Step 546 | loss:2.474520683288574 lr:0.0001983235780247651 tokens_per_second_per_gpu:729.8325745809814 +Step 547 | loss:2.4876034259796143 lr:0.00019831639563973216 tokens_per_second_per_gpu:731.9094794520961 +Step 548 | loss:2.472146511077881 lr:0.00019830919803224658 tokens_per_second_per_gpu:777.7908820684536 +Step 549 | loss:2.5104494094848633 lr:0.0001983019852034228 tokens_per_second_per_gpu:757.9068341499964 +Step 550 | loss:2.4458162784576416 lr:0.0001982947571543775 tokens_per_second_per_gpu:766.0709587928247 +Step 551 | loss:2.396406650543213 lr:0.0001982875138862299 tokens_per_second_per_gpu:746.6320449125633 +Step 552 | loss:2.4322924613952637 lr:0.00019828025540010144 tokens_per_second_per_gpu:776.4893006607604 +Step 553 | loss:2.469381093978882 lr:0.00019827298169711597 tokens_per_second_per_gpu:765.1812155228034 +Step 554 | loss:2.441577672958374 lr:0.00019826569277839968 tokens_per_second_per_gpu:765.4410783707068 +Step 555 | loss:2.513364315032959 lr:0.00019825838864508116 tokens_per_second_per_gpu:730.7929450495838 +Step 556 | loss:2.453188419342041 lr:0.00019825106929829126 tokens_per_second_per_gpu:778.3133988998651 +Step 557 | loss:2.446780204772949 lr:0.0001982437347391633 tokens_per_second_per_gpu:780.7298020576974 +Step 558 | loss:2.4243855476379395 lr:0.00019823638496883284 tokens_per_second_per_gpu:734.8682458488056 +Step 559 | loss:2.4363157749176025 lr:0.00019822901998843787 tokens_per_second_per_gpu:782.3590627434959 +Step 560 | loss:2.4513211250305176 lr:0.0001982216397991188 tokens_per_second_per_gpu:765.1418650416254 +Step 561 | loss:2.3542981147766113 lr:0.0001982142444020182 tokens_per_second_per_gpu:770.3898791087555 +Step 562 | loss:2.4422240257263184 lr:0.00019820683379828116 tokens_per_second_per_gpu:774.1003067560866 +Step 563 | loss:2.339937686920166 lr:0.0001981994079890551 tokens_per_second_per_gpu:757.1237718823012 +Step 564 | loss:2.538360357284546 lr:0.00019819196697548968 tokens_per_second_per_gpu:780.6730865301121 +Step 565 | loss:2.435138702392578 lr:0.00019818451075873713 tokens_per_second_per_gpu:747.1308615283259 +Step 566 | loss:2.5130584239959717 lr:0.0001981770393399518 tokens_per_second_per_gpu:770.0510877979573 +Step 567 | loss:2.3910908699035645 lr:0.0001981695527202905 tokens_per_second_per_gpu:756.3910573182374 +Step 568 | loss:2.4492859840393066 lr:0.0001981620509009125 tokens_per_second_per_gpu:765.4732382659314 +Step 569 | loss:2.4141628742218018 lr:0.0001981545338829792 tokens_per_second_per_gpu:778.7278626760689 +Step 570 | loss:2.4166407585144043 lr:0.0001981470016676545 tokens_per_second_per_gpu:730.4788378172271 +Step 571 | loss:2.429579019546509 lr:0.00019813945425610466 tokens_per_second_per_gpu:765.6676073487779 +Step 572 | loss:2.4518704414367676 lr:0.00019813189164949823 tokens_per_second_per_gpu:769.2451517373936 +Step 573 | loss:2.476107597351074 lr:0.00019812431384900613 tokens_per_second_per_gpu:760.7455687906513 +Step 574 | loss:2.428269863128662 lr:0.0001981167208558017 tokens_per_second_per_gpu:740.3611071046059 +Step 575 | loss:2.43211030960083 lr:0.00019810911267106044 tokens_per_second_per_gpu:754.4949606204808 +Step 576 | loss:2.45876407623291 lr:0.00019810148929596047 tokens_per_second_per_gpu:749.156059544481 +Step 577 | loss:2.4119997024536133 lr:0.00019809385073168206 tokens_per_second_per_gpu:735.3876763659466 +Step 578 | loss:2.4215989112854004 lr:0.0001980861969794079 tokens_per_second_per_gpu:785.4633994195945 +Step 579 | loss:2.401789903640747 lr:0.00019807852804032305 tokens_per_second_per_gpu:759.8626345637476 +Step 580 | loss:2.4510769844055176 lr:0.0001980708439156149 tokens_per_second_per_gpu:729.5010636120614 +Step 581 | loss:2.4441187381744385 lr:0.00019806314460647318 tokens_per_second_per_gpu:763.2676007994716 +Step 582 | loss:2.451589345932007 lr:0.00019805543011409 tokens_per_second_per_gpu:763.3290588853042 +Step 583 | loss:2.421757221221924 lr:0.0001980477004396598 tokens_per_second_per_gpu:766.2029185292824 +Step 584 | loss:2.4877772331237793 lr:0.00019803995558437934 tokens_per_second_per_gpu:718.6577071395094 +Step 585 | loss:2.4209790229797363 lr:0.00019803219554944784 tokens_per_second_per_gpu:765.1706870436138 +Step 586 | loss:2.5134685039520264 lr:0.00019802442033606675 tokens_per_second_per_gpu:749.9259812614865 +Step 587 | loss:2.371755838394165 lr:0.00019801662994543988 tokens_per_second_per_gpu:780.5038197379465 +Step 588 | loss:2.4167041778564453 lr:0.00019800882437877348 tokens_per_second_per_gpu:746.5266598175693 +Step 589 | loss:2.5334911346435547 lr:0.00019800100363727609 tokens_per_second_per_gpu:754.2884390764602 +Step 590 | loss:2.45893931388855 lr:0.0001979931677221586 tokens_per_second_per_gpu:758.491714993041 +Step 591 | loss:2.398630142211914 lr:0.00019798531663463425 tokens_per_second_per_gpu:758.3751253731505 +Step 592 | loss:2.4665679931640625 lr:0.00019797745037591864 tokens_per_second_per_gpu:776.9743031887233 +Step 593 | loss:2.424042224884033 lr:0.0001979695689472297 tokens_per_second_per_gpu:770.6961992320129 +Step 594 | loss:2.4377729892730713 lr:0.00019796167234978774 tokens_per_second_per_gpu:746.1618163926493 +Step 595 | loss:2.390347480773926 lr:0.00019795376058481535 tokens_per_second_per_gpu:758.6937313525484 +Step 596 | loss:2.3694915771484375 lr:0.0001979458336535376 tokens_per_second_per_gpu:780.279131994546 +Step 597 | loss:2.432352066040039 lr:0.00019793789155718176 tokens_per_second_per_gpu:771.5189896334623 +Step 598 | loss:2.422189235687256 lr:0.00019792993429697755 tokens_per_second_per_gpu:771.6632711915968 +Step 599 | loss:2.403676986694336 lr:0.000197921961874157 tokens_per_second_per_gpu:788.6803574049313 +Step 600 | loss:2.4200642108917236 lr:0.0001979139742899545 tokens_per_second_per_gpu:777.9770240318188 +Step 601 | loss:2.4142520427703857 lr:0.00019790597154560672 tokens_per_second_per_gpu:761.6967911005349 +Step 602 | loss:2.3899459838867188 lr:0.0001978979536423528 tokens_per_second_per_gpu:749.8219506819484 +Step 603 | loss:2.3534045219421387 lr:0.00019788992058143414 tokens_per_second_per_gpu:785.1221673390374 +Step 604 | loss:2.4168238639831543 lr:0.0001978818723640945 tokens_per_second_per_gpu:783.8314757046505 +Step 605 | loss:2.382155656814575 lr:0.00019787380899158002 tokens_per_second_per_gpu:783.7939295027043 +Step 606 | loss:2.447300672531128 lr:0.0001978657304651391 tokens_per_second_per_gpu:771.317431514004 +Step 607 | loss:2.4244635105133057 lr:0.00019785763678602263 tokens_per_second_per_gpu:766.024135321283 +Step 608 | loss:2.4363372325897217 lr:0.00019784952795548372 tokens_per_second_per_gpu:783.6767552265063 +Step 609 | loss:2.4129762649536133 lr:0.0001978414039747779 tokens_per_second_per_gpu:773.4475984405618 +Step 610 | loss:2.4013617038726807 lr:0.00019783326484516296 tokens_per_second_per_gpu:782.2162065981546 +Step 611 | loss:2.3750803470611572 lr:0.00019782511056789915 tokens_per_second_per_gpu:783.333668297695 +Step 612 | loss:2.492417812347412 lr:0.00019781694114424898 tokens_per_second_per_gpu:757.1975359022193 +Step 613 | loss:2.402592658996582 lr:0.00019780875657547732 tokens_per_second_per_gpu:781.2102640004214 +Step 614 | loss:2.4235103130340576 lr:0.00019780055686285141 tokens_per_second_per_gpu:774.4327417871865 +Step 615 | loss:2.4506170749664307 lr:0.00019779234200764084 tokens_per_second_per_gpu:752.3408805172041 +Step 616 | loss:2.3564023971557617 lr:0.00019778411201111753 tokens_per_second_per_gpu:729.790966923671 +Step 617 | loss:2.4119415283203125 lr:0.0001977758668745557 tokens_per_second_per_gpu:754.7887503618639 +Step 618 | loss:2.442474842071533 lr:0.000197767606599232 tokens_per_second_per_gpu:786.3955453151054 +Step 619 | loss:2.4980692863464355 lr:0.00019775933118642533 tokens_per_second_per_gpu:771.7775754805272 +Step 620 | loss:2.345029830932617 lr:0.00019775104063741704 tokens_per_second_per_gpu:751.8416111743595 +Step 621 | loss:2.4506192207336426 lr:0.0001977427349534907 tokens_per_second_per_gpu:776.1741481015322 +Step 622 | loss:2.456653594970703 lr:0.00019773441413593234 tokens_per_second_per_gpu:747.5779158764992 +Step 623 | loss:2.413968563079834 lr:0.00019772607818603025 tokens_per_second_per_gpu:751.1514913428583 +Step 624 | loss:2.3899364471435547 lr:0.00019771772710507516 tokens_per_second_per_gpu:783.9954587535608 +Step 625 | loss:2.4092907905578613 lr:0.00019770936089436 tokens_per_second_per_gpu:766.7816863180087 +Step 626 | loss:2.418036699295044 lr:0.00019770097955518017 tokens_per_second_per_gpu:774.5563560951396 +Step 627 | loss:2.4173879623413086 lr:0.00019769258308883334 tokens_per_second_per_gpu:743.4426629985974 +Step 628 | loss:2.400012493133545 lr:0.00019768417149661956 tokens_per_second_per_gpu:754.6078667604945 +Step 629 | loss:2.4452004432678223 lr:0.0001976757447798412 tokens_per_second_per_gpu:767.0976169409267 +Step 630 | loss:2.308042526245117 lr:0.00019766730293980294 tokens_per_second_per_gpu:764.9380461497757 +Step 631 | loss:2.4666812419891357 lr:0.00019765884597781192 tokens_per_second_per_gpu:771.9833304769309 +Step 632 | loss:2.354780673980713 lr:0.0001976503738951775 tokens_per_second_per_gpu:761.9002747965133 +Step 633 | loss:2.3639934062957764 lr:0.0001976418866932114 tokens_per_second_per_gpu:765.6815683712481 +Step 634 | loss:2.3867452144622803 lr:0.00019763338437322773 tokens_per_second_per_gpu:779.3101499710558 +Step 635 | loss:2.397683620452881 lr:0.00019762486693654293 tokens_per_second_per_gpu:768.9973492349865 +Step 636 | loss:2.356179714202881 lr:0.00019761633438447577 tokens_per_second_per_gpu:773.6774101933792 +Step 637 | loss:2.3647871017456055 lr:0.00019760778671834732 tokens_per_second_per_gpu:768.6508259264494 +Step 638 | loss:2.41987943649292 lr:0.00019759922393948104 tokens_per_second_per_gpu:778.8140333733769 +Step 639 | loss:2.463637351989746 lr:0.00019759064604920273 tokens_per_second_per_gpu:773.7039968421165 +Step 640 | loss:2.4450976848602295 lr:0.0001975820530488405 tokens_per_second_per_gpu:765.6155792228649 +Step 641 | loss:2.4280033111572266 lr:0.0001975734449397248 tokens_per_second_per_gpu:776.3435960246251 +Step 642 | loss:2.4469213485717773 lr:0.00019756482172318847 tokens_per_second_per_gpu:754.9254672269454 +Step 643 | loss:2.410402297973633 lr:0.00019755618340056664 tokens_per_second_per_gpu:775.2890418095965 +Step 644 | loss:2.360546350479126 lr:0.00019754752997319677 tokens_per_second_per_gpu:741.2214780443588 +Step 645 | loss:2.3516459465026855 lr:0.0001975388614424187 tokens_per_second_per_gpu:780.5252477568995 +Step 646 | loss:2.3636579513549805 lr:0.00019753017780957461 tokens_per_second_per_gpu:764.471645920771 +Step 647 | loss:2.418457508087158 lr:0.000197521479076009 tokens_per_second_per_gpu:753.8625066025406 +Step 648 | loss:2.4253406524658203 lr:0.00019751276524306862 tokens_per_second_per_gpu:775.3210350466478 +Step 649 | loss:2.3898627758026123 lr:0.00019750403631210275 tokens_per_second_per_gpu:744.4174701235238 +Step 650 | loss:2.3840107917785645 lr:0.00019749529228446286 tokens_per_second_per_gpu:749.3394532133975 +Step 651 | loss:2.3258728981018066 lr:0.0001974865331615028 tokens_per_second_per_gpu:772.7088765036053 +Step 652 | loss:2.370147705078125 lr:0.00019747775894457875 tokens_per_second_per_gpu:780.8761889038306 +Step 653 | loss:2.40622878074646 lr:0.00019746896963504921 tokens_per_second_per_gpu:742.8808103548439 +Step 654 | loss:2.363130569458008 lr:0.00019746016523427513 tokens_per_second_per_gpu:759.1909430484604 +Step 655 | loss:2.365795373916626 lr:0.0001974513457436196 tokens_per_second_per_gpu:731.204365544566 +Step 656 | loss:2.4137370586395264 lr:0.00019744251116444818 tokens_per_second_per_gpu:732.737681031509 +Step 657 | loss:2.401412010192871 lr:0.00019743366149812882 tokens_per_second_per_gpu:750.8946402410362 +Step 658 | loss:2.3923988342285156 lr:0.00019742479674603162 tokens_per_second_per_gpu:769.6383160467064 +Step 659 | loss:2.3780710697174072 lr:0.00019741591690952914 tokens_per_second_per_gpu:765.8478431144187 +Step 660 | loss:2.450706958770752 lr:0.00019740702198999633 tokens_per_second_per_gpu:762.1666877555967 +Step 661 | loss:2.4492290019989014 lr:0.00019739811198881034 tokens_per_second_per_gpu:758.6613568913623 +Step 662 | loss:2.439422845840454 lr:0.0001973891869073507 tokens_per_second_per_gpu:763.2961823381427 +Step 663 | loss:2.411776542663574 lr:0.00019738024674699934 tokens_per_second_per_gpu:754.0732296997342 +Step 664 | loss:2.3210768699645996 lr:0.00019737129150914045 tokens_per_second_per_gpu:768.282415109941 +Step 665 | loss:2.4330289363861084 lr:0.00019736232119516058 tokens_per_second_per_gpu:782.1526858412869 +Step 666 | loss:2.4041569232940674 lr:0.00019735333580644864 tokens_per_second_per_gpu:767.5640281712027 +Step 667 | loss:2.3690292835235596 lr:0.0001973443353443958 tokens_per_second_per_gpu:733.4615812775332 +Step 668 | loss:2.390540361404419 lr:0.00019733531981039568 tokens_per_second_per_gpu:751.2122948356216 +Step 669 | loss:2.375462532043457 lr:0.00019732628920584412 tokens_per_second_per_gpu:775.27733860476 +Step 670 | loss:2.4206833839416504 lr:0.00019731724353213933 tokens_per_second_per_gpu:744.3345863129821 +Step 671 | loss:2.344639539718628 lr:0.00019730818279068188 tokens_per_second_per_gpu:784.4175552583887 +Step 672 | loss:2.396432876586914 lr:0.0001972991069828747 tokens_per_second_per_gpu:776.8255630727691 +Step 673 | loss:2.3853747844696045 lr:0.00019729001611012295 tokens_per_second_per_gpu:762.579579388684 +Step 674 | loss:2.3527755737304688 lr:0.00019728091017383418 tokens_per_second_per_gpu:777.7742560426733 +Step 675 | loss:2.4132461547851562 lr:0.00019727178917541832 tokens_per_second_per_gpu:769.284313214718 +Step 676 | loss:2.450355052947998 lr:0.00019726265311628756 tokens_per_second_per_gpu:742.4737076674637 +Step 677 | loss:2.3927969932556152 lr:0.00019725350199785641 tokens_per_second_per_gpu:770.06341688127 +Step 678 | loss:2.358333110809326 lr:0.0001972443358215418 tokens_per_second_per_gpu:753.111519145383 +Step 679 | loss:2.3910417556762695 lr:0.00019723515458876297 tokens_per_second_per_gpu:782.683815003858 +Step 680 | loss:2.335081100463867 lr:0.00019722595830094138 tokens_per_second_per_gpu:757.2196175613064 +Step 681 | loss:2.4212701320648193 lr:0.00019721674695950093 tokens_per_second_per_gpu:778.6130316869458 +Step 682 | loss:2.360908031463623 lr:0.0001972075205658679 tokens_per_second_per_gpu:760.2081809272053 +Step 683 | loss:2.3589072227478027 lr:0.0001971982791214707 tokens_per_second_per_gpu:778.8522739625215 +Step 684 | loss:2.3979854583740234 lr:0.00019718902262774027 tokens_per_second_per_gpu:777.0581615152264 +Step 685 | loss:2.373786449432373 lr:0.0001971797510861098 tokens_per_second_per_gpu:775.1488817496394 +Step 686 | loss:2.33540678024292 lr:0.00019717046449801477 tokens_per_second_per_gpu:732.9080658460691 +Step 687 | loss:2.3790078163146973 lr:0.0001971611628648931 tokens_per_second_per_gpu:777.0604065942102 +Step 688 | loss:2.369414806365967 lr:0.00019715184618818493 tokens_per_second_per_gpu:768.0901976998763 +Step 689 | loss:2.3574609756469727 lr:0.0001971425144693328 tokens_per_second_per_gpu:773.0892286192477 +Step 690 | loss:2.3486037254333496 lr:0.00019713316770978155 tokens_per_second_per_gpu:766.6193079025657 +Step 691 | loss:2.331268548965454 lr:0.0001971238059109783 tokens_per_second_per_gpu:788.9565794340954 +Step 692 | loss:2.3779940605163574 lr:0.00019711442907437257 tokens_per_second_per_gpu:767.4558408596297 +Step 693 | loss:2.4356651306152344 lr:0.00019710503720141625 tokens_per_second_per_gpu:741.4278159249659 +Step 694 | loss:2.375797986984253 lr:0.00019709563029356343 tokens_per_second_per_gpu:773.4089517329094 +Step 695 | loss:2.4117462635040283 lr:0.00019708620835227062 tokens_per_second_per_gpu:754.3992149602454 +Step 696 | loss:2.3297760486602783 lr:0.00019707677137899662 tokens_per_second_per_gpu:770.6801013706447 +Step 697 | loss:2.3823955059051514 lr:0.00019706731937520257 tokens_per_second_per_gpu:793.8603966534531 +Step 698 | loss:2.3920772075653076 lr:0.00019705785234235197 tokens_per_second_per_gpu:781.6961334578403 +Step 699 | loss:2.431595802307129 lr:0.00019704837028191054 tokens_per_second_per_gpu:752.1668053101018 +Step 700 | loss:2.331024169921875 lr:0.00019703887319534645 tokens_per_second_per_gpu:751.0519708642528 +Step 701 | loss:2.4390063285827637 lr:0.00019702936108413014 tokens_per_second_per_gpu:727.6041978163461 +Step 702 | loss:2.371272325515747 lr:0.0001970198339497344 tokens_per_second_per_gpu:769.8209514095217 +Step 703 | loss:2.3384056091308594 lr:0.00019701029179363427 tokens_per_second_per_gpu:771.0595872452955 +Step 704 | loss:2.366889476776123 lr:0.00019700073461730727 tokens_per_second_per_gpu:758.989987591134 +Step 705 | loss:2.341641426086426 lr:0.00019699116242223306 tokens_per_second_per_gpu:761.0187686024738 +Step 706 | loss:2.389730215072632 lr:0.00019698157520989373 tokens_per_second_per_gpu:756.7243451904384 +Step 707 | loss:2.305236339569092 lr:0.0001969719729817737 tokens_per_second_per_gpu:768.2825196138909 +Step 708 | loss:2.376462936401367 lr:0.0001969623557393597 tokens_per_second_per_gpu:755.0965589682587 +Step 709 | loss:2.3159708976745605 lr:0.00019695272348414078 tokens_per_second_per_gpu:772.5654027980654 +Step 710 | loss:2.4032554626464844 lr:0.0001969430762176083 tokens_per_second_per_gpu:700.7518321880075 +Step 711 | loss:2.284937620162964 lr:0.00019693341394125597 tokens_per_second_per_gpu:764.1543351074984 +Step 712 | loss:2.3165576457977295 lr:0.00019692373665657978 tokens_per_second_per_gpu:757.5136277999059 +Step 713 | loss:2.3726236820220947 lr:0.00019691404436507815 tokens_per_second_per_gpu:763.4297811372032 +Step 714 | loss:2.4289097785949707 lr:0.0001969043370682517 tokens_per_second_per_gpu:767.7139262724885 +Step 715 | loss:2.3590359687805176 lr:0.0001968946147676034 tokens_per_second_per_gpu:765.2260977378304 +Step 716 | loss:2.365464210510254 lr:0.00019688487746463858 tokens_per_second_per_gpu:713.8969194208983 +Step 717 | loss:2.364250659942627 lr:0.00019687512516086494 tokens_per_second_per_gpu:763.7479881033313 +Step 718 | loss:2.33764386177063 lr:0.00019686535785779234 tokens_per_second_per_gpu:736.2452922893721 +Step 719 | loss:2.3020131587982178 lr:0.00019685557555693315 tokens_per_second_per_gpu:764.70095806907 +Step 720 | loss:2.2993788719177246 lr:0.00019684577825980192 tokens_per_second_per_gpu:770.5289319127877 +Step 721 | loss:2.44343900680542 lr:0.00019683596596791562 tokens_per_second_per_gpu:780.7526113947639 +Step 722 | loss:2.3822312355041504 lr:0.00019682613868279348 tokens_per_second_per_gpu:790.163224576154 +Step 723 | loss:2.365201473236084 lr:0.0001968162964059571 tokens_per_second_per_gpu:763.4533874402025 +Step 724 | loss:2.3961615562438965 lr:0.0001968064391389303 tokens_per_second_per_gpu:774.6037281860775 +Step 725 | loss:2.272441864013672 lr:0.00019679656688323936 tokens_per_second_per_gpu:760.9964487624394 +Step 726 | loss:2.371168613433838 lr:0.0001967866796404128 tokens_per_second_per_gpu:778.1259039005181 +Step 727 | loss:2.4099555015563965 lr:0.00019677677741198143 tokens_per_second_per_gpu:782.6601143263155 +Step 728 | loss:2.385671377182007 lr:0.0001967668601994785 tokens_per_second_per_gpu:768.5819180958134 +Step 729 | loss:2.350717782974243 lr:0.00019675692800443943 tokens_per_second_per_gpu:756.5663224878043 +Step 730 | loss:2.3895316123962402 lr:0.00019674698082840212 tokens_per_second_per_gpu:750.0950937225934 +Step 731 | loss:2.3745598793029785 lr:0.0001967370186729066 tokens_per_second_per_gpu:772.8726642696959 +Step 732 | loss:2.3276851177215576 lr:0.0001967270415394954 tokens_per_second_per_gpu:751.320862900664 +Step 733 | loss:2.3495469093322754 lr:0.00019671704942971326 tokens_per_second_per_gpu:759.6522606015343 +Step 734 | loss:2.3070812225341797 lr:0.0001967070423451073 tokens_per_second_per_gpu:767.9517201245641 +Step 735 | loss:2.3096871376037598 lr:0.00019669702028722689 tokens_per_second_per_gpu:747.7494788125521 +Step 736 | loss:2.3427462577819824 lr:0.0001966869832576238 tokens_per_second_per_gpu:743.4845040606596 +Step 737 | loss:2.3268752098083496 lr:0.000196676931257852 tokens_per_second_per_gpu:750.4724875027421 +Step 738 | loss:2.3972933292388916 lr:0.00019666686428946797 tokens_per_second_per_gpu:762.1137136442251 +Step 739 | loss:2.324653387069702 lr:0.00019665678235403032 tokens_per_second_per_gpu:761.5629070365745 +Step 740 | loss:2.3343636989593506 lr:0.00019664668545310004 tokens_per_second_per_gpu:713.8512800610605 +Step 741 | loss:2.3180246353149414 lr:0.00019663657358824047 tokens_per_second_per_gpu:771.6500921379717 +Step 742 | loss:2.340178966522217 lr:0.00019662644676101724 tokens_per_second_per_gpu:784.7907548054376 +Step 743 | loss:2.343088150024414 lr:0.0001966163049729983 tokens_per_second_per_gpu:755.8167804796512 +Step 744 | loss:2.3603692054748535 lr:0.0001966061482257539 tokens_per_second_per_gpu:777.0507322270689 +Step 745 | loss:2.3916678428649902 lr:0.00019659597652085665 tokens_per_second_per_gpu:772.6938835132376 +Step 746 | loss:2.308454751968384 lr:0.00019658578985988143 tokens_per_second_per_gpu:763.5632075105286 +Step 747 | loss:2.3088531494140625 lr:0.00019657558824440546 tokens_per_second_per_gpu:748.4846833147209 +Step 748 | loss:2.393507957458496 lr:0.00019656537167600825 tokens_per_second_per_gpu:754.3141545211835 +Step 749 | loss:2.404245615005493 lr:0.00019655514015627166 tokens_per_second_per_gpu:775.5047602822088 +Step 750 | loss:2.4019277095794678 lr:0.00019654489368677985 tokens_per_second_per_gpu:758.6412455911238 +Step 751 | loss:2.2970147132873535 lr:0.0001965346322691193 tokens_per_second_per_gpu:768.2679596299259 +Step 752 | loss:2.411153793334961 lr:0.0001965243559048788 tokens_per_second_per_gpu:756.4973518126667 +Step 753 | loss:2.3492462635040283 lr:0.00019651406459564942 tokens_per_second_per_gpu:772.1063303529502 +Step 754 | loss:2.2831928730010986 lr:0.0001965037583430246 tokens_per_second_per_gpu:781.3234131902586 +Step 755 | loss:2.354154109954834 lr:0.00019649343714860012 tokens_per_second_per_gpu:771.2603441533003 +Step 756 | loss:2.348889112472534 lr:0.00019648310101397391 tokens_per_second_per_gpu:768.4345494768031 +Step 757 | loss:2.364622116088867 lr:0.00019647274994074644 tokens_per_second_per_gpu:768.2282671107585 +Step 758 | loss:2.3935441970825195 lr:0.0001964623839305203 tokens_per_second_per_gpu:759.7754181573097 +Step 759 | loss:2.336353063583374 lr:0.00019645200298490053 tokens_per_second_per_gpu:759.8016943025333 +Step 760 | loss:2.3516125679016113 lr:0.00019644160710549437 tokens_per_second_per_gpu:756.042591998824 +Step 761 | loss:2.3202757835388184 lr:0.00019643119629391147 tokens_per_second_per_gpu:747.2519399097013 +Step 762 | loss:2.3703484535217285 lr:0.00019642077055176375 tokens_per_second_per_gpu:756.1921800430043 +Step 763 | loss:2.2909488677978516 lr:0.0001964103298806654 tokens_per_second_per_gpu:769.4254547670645 +Step 764 | loss:2.3743515014648438 lr:0.000196399874282233 tokens_per_second_per_gpu:784.8732695279264 +Step 765 | loss:2.3134684562683105 lr:0.0001963894037580854 tokens_per_second_per_gpu:770.1385862605604 +Step 766 | loss:2.318207263946533 lr:0.00019637891830984373 tokens_per_second_per_gpu:776.208124960101 +Step 767 | loss:2.299042224884033 lr:0.0001963684179391315 tokens_per_second_per_gpu:781.7831391404235 +Step 768 | loss:2.409562587738037 lr:0.0001963579026475745 tokens_per_second_per_gpu:777.8365473033215 +Step 769 | loss:2.3658194541931152 lr:0.00019634737243680084 tokens_per_second_per_gpu:767.9301977916417 +Step 770 | loss:2.326323986053467 lr:0.00019633682730844086 tokens_per_second_per_gpu:771.5688475908837 +Step 771 | loss:2.330620527267456 lr:0.00019632626726412734 tokens_per_second_per_gpu:771.2800322228079 +Step 772 | loss:2.2489635944366455 lr:0.00019631569230549523 tokens_per_second_per_gpu:776.8158792698422 +Step 773 | loss:2.319251298904419 lr:0.00019630510243418196 tokens_per_second_per_gpu:748.0807701794402 +Step 774 | loss:2.323969602584839 lr:0.0001962944976518271 tokens_per_second_per_gpu:784.9860029085359 +Step 775 | loss:2.3664519786834717 lr:0.00019628387796007265 tokens_per_second_per_gpu:764.92324061431 +Step 776 | loss:2.395073890686035 lr:0.00019627324336056289 tokens_per_second_per_gpu:763.553493825304 +Step 777 | loss:2.3335819244384766 lr:0.00019626259385494428 tokens_per_second_per_gpu:757.2844955769131 +Step 778 | loss:2.3227596282958984 lr:0.00019625192944486579 tokens_per_second_per_gpu:772.4240081747151 +Step 779 | loss:2.363837480545044 lr:0.00019624125013197857 tokens_per_second_per_gpu:746.731746286383 +Step 780 | loss:2.3234450817108154 lr:0.00019623055591793613 tokens_per_second_per_gpu:759.1195622780734 +Step 781 | loss:2.3558685779571533 lr:0.00019621984680439426 tokens_per_second_per_gpu:760.9313627877359 +Step 782 | loss:2.277423143386841 lr:0.0001962091227930111 tokens_per_second_per_gpu:758.7051448012554 +Step 783 | loss:2.3218672275543213 lr:0.00019619838388544697 tokens_per_second_per_gpu:764.3324227990785 +Step 784 | loss:2.3797266483306885 lr:0.00019618763008336467 tokens_per_second_per_gpu:774.0548218774 +Step 785 | loss:2.354106903076172 lr:0.0001961768613884292 tokens_per_second_per_gpu:767.1570765878058 +Step 786 | loss:2.381396532058716 lr:0.00019616607780230792 tokens_per_second_per_gpu:773.5394559634617 +Step 787 | loss:2.3442044258117676 lr:0.0001961552793266704 tokens_per_second_per_gpu:765.4966755791451 +Step 788 | loss:2.3845887184143066 lr:0.00019614446596318862 tokens_per_second_per_gpu:760.2991439752761 +Step 789 | loss:2.3584611415863037 lr:0.00019613363771353684 tokens_per_second_per_gpu:767.5533748225122 +Step 790 | loss:2.38875150680542 lr:0.0001961227945793916 tokens_per_second_per_gpu:731.6787627962907 +Step 791 | loss:2.3360252380371094 lr:0.00019611193656243175 tokens_per_second_per_gpu:750.107262566252 +Step 792 | loss:2.2763724327087402 lr:0.00019610106366433846 tokens_per_second_per_gpu:753.196656768276 +Step 793 | loss:2.370382785797119 lr:0.0001960901758867952 tokens_per_second_per_gpu:759.2520023659673 +Step 794 | loss:2.3159408569335938 lr:0.00019607927323148772 tokens_per_second_per_gpu:757.7978460621274 +Step 795 | loss:2.3117449283599854 lr:0.0001960683557001041 tokens_per_second_per_gpu:761.662630295307 +Step 796 | loss:2.3971500396728516 lr:0.00019605742329433472 tokens_per_second_per_gpu:759.5735519567866 +Step 797 | loss:2.2911252975463867 lr:0.0001960464760158722 tokens_per_second_per_gpu:757.182701353264 +Step 798 | loss:2.386842966079712 lr:0.00019603551386641166 tokens_per_second_per_gpu:768.1797741160473 +Step 799 | loss:2.334754467010498 lr:0.00019602453684765028 tokens_per_second_per_gpu:761.4608090615693 +Step 800 | loss:2.3207476139068604 lr:0.00019601354496128764 tokens_per_second_per_gpu:764.1504670785939 +Step 801 | loss:2.2830092906951904 lr:0.00019600253820902566 tokens_per_second_per_gpu:770.6632713121897 +Step 802 | loss:2.3167617321014404 lr:0.00019599151659256854 tokens_per_second_per_gpu:770.6201983242973 +Step 803 | loss:2.3405113220214844 lr:0.00019598048011362272 tokens_per_second_per_gpu:755.379137245764 +Step 804 | loss:2.3565309047698975 lr:0.00019596942877389702 tokens_per_second_per_gpu:784.3703942404624 +Step 805 | loss:2.3406553268432617 lr:0.00019595836257510257 tokens_per_second_per_gpu:758.1375687201386 +Step 806 | loss:2.3099637031555176 lr:0.0001959472815189527 tokens_per_second_per_gpu:749.4480440957335 +Step 807 | loss:2.292611598968506 lr:0.00019593618560716317 tokens_per_second_per_gpu:748.3413542957617 +Step 808 | loss:2.265230655670166 lr:0.00019592507484145192 tokens_per_second_per_gpu:770.4309332410598 +Step 809 | loss:2.35286021232605 lr:0.00019591394922353927 tokens_per_second_per_gpu:758.2976868347661 +Step 810 | loss:2.2187652587890625 lr:0.0001959028087551478 tokens_per_second_per_gpu:759.4074140457578 +Step 811 | loss:2.395329713821411 lr:0.00019589165343800242 tokens_per_second_per_gpu:772.7649360390823 +Step 812 | loss:2.2951998710632324 lr:0.0001958804832738303 tokens_per_second_per_gpu:763.3403723048928 +Step 813 | loss:2.2789981365203857 lr:0.00019586929826436095 tokens_per_second_per_gpu:729.8578995348639 +Step 814 | loss:2.3506627082824707 lr:0.00019585809841132616 tokens_per_second_per_gpu:735.2280279054977 +Step 815 | loss:2.3955190181732178 lr:0.00019584688371646 tokens_per_second_per_gpu:761.0589546849245 +Step 816 | loss:2.3439321517944336 lr:0.00019583565418149887 tokens_per_second_per_gpu:778.1836364216713 +Step 817 | loss:2.227856159210205 lr:0.00019582440980818144 tokens_per_second_per_gpu:779.9414202808008 +Step 818 | loss:2.3521125316619873 lr:0.0001958131505982487 tokens_per_second_per_gpu:777.7080377192195 +Step 819 | loss:2.3556244373321533 lr:0.00019580187655344393 tokens_per_second_per_gpu:748.3540361129653 +Step 820 | loss:2.346911668777466 lr:0.0001957905876755127 tokens_per_second_per_gpu:788.913867221492 +Step 821 | loss:2.360015869140625 lr:0.00019577928396620288 tokens_per_second_per_gpu:783.1821304872531 +Step 822 | loss:2.339773654937744 lr:0.00019576796542726465 tokens_per_second_per_gpu:785.3319776347537 +Step 823 | loss:2.3213770389556885 lr:0.00019575663206045045 tokens_per_second_per_gpu:777.6739794895581 +Step 824 | loss:2.3340635299682617 lr:0.00019574528386751507 tokens_per_second_per_gpu:773.0039903450333 +Step 825 | loss:2.3329482078552246 lr:0.00019573392085021554 tokens_per_second_per_gpu:771.8055340783123 +Step 826 | loss:2.3217198848724365 lr:0.0001957225430103112 tokens_per_second_per_gpu:759.2972687611785 +Step 827 | loss:2.3425536155700684 lr:0.00019571115034956374 tokens_per_second_per_gpu:752.9344837611259 +Step 828 | loss:2.3882691860198975 lr:0.0001956997428697371 tokens_per_second_per_gpu:787.8370252258325 +Step 829 | loss:2.293199062347412 lr:0.00019568832057259743 tokens_per_second_per_gpu:780.4314419470019 +Step 830 | loss:2.3377935886383057 lr:0.00019567688345991334 tokens_per_second_per_gpu:782.278967019405 +Step 831 | loss:2.321979522705078 lr:0.00019566543153345565 tokens_per_second_per_gpu:753.7102908428461 +Step 832 | loss:2.363440990447998 lr:0.00019565396479499745 tokens_per_second_per_gpu:733.9508810516087 +Step 833 | loss:2.31331729888916 lr:0.00019564248324631413 tokens_per_second_per_gpu:732.2512753518382 +Step 834 | loss:2.2949776649475098 lr:0.00019563098688918346 tokens_per_second_per_gpu:765.4958843851588 +Step 835 | loss:2.327450752258301 lr:0.00019561947572538537 tokens_per_second_per_gpu:770.0980839359315 +Step 836 | loss:2.367093563079834 lr:0.00019560794975670217 tokens_per_second_per_gpu:729.465503001203 +Step 837 | loss:2.314481019973755 lr:0.00019559640898491847 tokens_per_second_per_gpu:756.368526995876 +Step 838 | loss:2.275618076324463 lr:0.0001955848534118211 tokens_per_second_per_gpu:772.460057672859 +Step 839 | loss:2.360841751098633 lr:0.00019557328303919925 tokens_per_second_per_gpu:778.6179854867715 +Step 840 | loss:2.3497490882873535 lr:0.00019556169786884436 tokens_per_second_per_gpu:776.467420133115 +Step 841 | loss:2.3651392459869385 lr:0.00019555009790255017 tokens_per_second_per_gpu:771.589490776401 +Step 842 | loss:2.2990550994873047 lr:0.00019553848314211273 tokens_per_second_per_gpu:784.3346125210925 +Step 843 | loss:2.3046844005584717 lr:0.0001955268535893304 tokens_per_second_per_gpu:736.8403228099894 +Step 844 | loss:2.321274757385254 lr:0.00019551520924600374 tokens_per_second_per_gpu:784.4396456345688 +Step 845 | loss:2.2782793045043945 lr:0.0001955035501139357 tokens_per_second_per_gpu:749.3473712323879 +Step 846 | loss:2.303853988647461 lr:0.00019549187619493144 tokens_per_second_per_gpu:713.9929022504507 +Step 847 | loss:2.314385414123535 lr:0.00019548018749079849 tokens_per_second_per_gpu:752.7257297433042 +Step 848 | loss:2.3027045726776123 lr:0.0001954684840033466 tokens_per_second_per_gpu:742.1768216414641 +Step 849 | loss:2.2995524406433105 lr:0.00019545676573438784 tokens_per_second_per_gpu:730.5416267562097 +Step 850 | loss:2.2937028408050537 lr:0.00019544503268573656 tokens_per_second_per_gpu:767.0205071149451 +Step 851 | loss:2.294471025466919 lr:0.00019543328485920945 tokens_per_second_per_gpu:760.2728549473258 +Step 852 | loss:2.256350517272949 lr:0.0001954215222566254 tokens_per_second_per_gpu:760.7220501281644 +Step 853 | loss:2.291131019592285 lr:0.0001954097448798056 tokens_per_second_per_gpu:764.5417199801091 +Step 854 | loss:2.2735185623168945 lr:0.0001953979527305736 tokens_per_second_per_gpu:780.9932254546867 +Step 855 | loss:2.3311173915863037 lr:0.00019538614581075518 tokens_per_second_per_gpu:767.4771733744783 +Step 856 | loss:2.3129565715789795 lr:0.00019537432412217843 tokens_per_second_per_gpu:773.7107618612428 +Step 857 | loss:2.3788251876831055 lr:0.00019536248766667368 tokens_per_second_per_gpu:755.954644881367 +Step 858 | loss:2.299720287322998 lr:0.00019535063644607364 tokens_per_second_per_gpu:745.0052152712182 +Step 859 | loss:2.3335678577423096 lr:0.0001953387704622132 tokens_per_second_per_gpu:682.8502740551054 +Step 860 | loss:2.3585495948791504 lr:0.00019532688971692964 tokens_per_second_per_gpu:761.6667266213607 +Step 861 | loss:2.3436036109924316 lr:0.0001953149942120624 tokens_per_second_per_gpu:774.8408179991732 +Step 862 | loss:2.2936317920684814 lr:0.00019530308394945334 tokens_per_second_per_gpu:778.0785015044814 +Step 863 | loss:2.3367786407470703 lr:0.00019529115893094653 tokens_per_second_per_gpu:769.108046275922 +Step 864 | loss:2.321990966796875 lr:0.00019527921915838827 tokens_per_second_per_gpu:793.6714960625496 +Step 865 | loss:2.3893885612487793 lr:0.00019526726463362727 tokens_per_second_per_gpu:768.599331637727 +Step 866 | loss:2.2750229835510254 lr:0.0001952552953585145 tokens_per_second_per_gpu:778.7573376322333 +Step 867 | loss:2.300424098968506 lr:0.0001952433113349031 tokens_per_second_per_gpu:766.682202032202 +Step 868 | loss:2.347425937652588 lr:0.0001952313125646486 tokens_per_second_per_gpu:771.1122756111456 +Step 869 | loss:2.2793962955474854 lr:0.0001952192990496088 tokens_per_second_per_gpu:754.430296743274 +Step 870 | loss:2.267852783203125 lr:0.00019520727079164375 tokens_per_second_per_gpu:783.9552799673528 +Step 871 | loss:2.2728443145751953 lr:0.0001951952277926158 tokens_per_second_per_gpu:775.3977200688875 +Step 872 | loss:2.269590377807617 lr:0.00019518317005438963 tokens_per_second_per_gpu:763.5350133967486 +Step 873 | loss:2.32387113571167 lr:0.0001951710975788321 tokens_per_second_per_gpu:764.0905770380216 +Step 874 | loss:2.303929328918457 lr:0.0001951590103678124 tokens_per_second_per_gpu:721.2261536434983 +Step 875 | loss:2.289675712585449 lr:0.00019514690842320205 tokens_per_second_per_gpu:795.3598568575472 +Step 876 | loss:2.3097176551818848 lr:0.0001951347917468748 tokens_per_second_per_gpu:750.7665424766556 +Step 877 | loss:2.240342378616333 lr:0.00019512266034070664 tokens_per_second_per_gpu:760.7742312767706 +Step 878 | loss:2.291762113571167 lr:0.00019511051420657597 tokens_per_second_per_gpu:754.5832221134636 +Step 879 | loss:2.3054423332214355 lr:0.00019509835334636334 tokens_per_second_per_gpu:755.3711294381113 +Step 880 | loss:2.3367459774017334 lr:0.00019508617776195167 tokens_per_second_per_gpu:769.9866777691074 +Step 881 | loss:2.3489160537719727 lr:0.00019507398745522605 tokens_per_second_per_gpu:741.4177683847929 +Step 882 | loss:2.3186304569244385 lr:0.000195061782428074 tokens_per_second_per_gpu:785.8612956010909 +Step 883 | loss:2.307267189025879 lr:0.00019504956268238518 tokens_per_second_per_gpu:740.5173377608376 +Step 884 | loss:2.234661102294922 lr:0.00019503732822005162 tokens_per_second_per_gpu:771.7067604072926 +Step 885 | loss:2.3220772743225098 lr:0.00019502507904296763 tokens_per_second_per_gpu:778.5607821234804 +Step 886 | loss:2.304987907409668 lr:0.00019501281515302968 tokens_per_second_per_gpu:756.1561687456092 +Step 887 | loss:2.295732259750366 lr:0.0001950005365521367 tokens_per_second_per_gpu:795.8500498361578 +Step 888 | loss:2.27004075050354 lr:0.0001949882432421897 tokens_per_second_per_gpu:794.1190275401422 +Step 889 | loss:2.308877944946289 lr:0.00019497593522509218 tokens_per_second_per_gpu:781.6109808830594 +Step 890 | loss:2.283750057220459 lr:0.0001949636125027497 tokens_per_second_per_gpu:788.3980444898609 +Step 891 | loss:2.3056914806365967 lr:0.00019495127507707026 tokens_per_second_per_gpu:786.6307277360975 +Step 892 | loss:2.2516331672668457 lr:0.0001949389229499641 tokens_per_second_per_gpu:764.3294542717341 +Step 893 | loss:2.298147678375244 lr:0.00019492655612334366 tokens_per_second_per_gpu:777.4848831433154 +Step 894 | loss:2.3097572326660156 lr:0.00019491417459912373 tokens_per_second_per_gpu:754.258413388758 +Step 895 | loss:2.3684821128845215 lr:0.00019490177837922138 tokens_per_second_per_gpu:789.6118473971343 +Step 896 | loss:2.3361215591430664 lr:0.00019488936746555593 tokens_per_second_per_gpu:759.4832206652025 +Step 897 | loss:2.276930570602417 lr:0.00019487694186004893 tokens_per_second_per_gpu:764.4816549445377 +Step 898 | loss:2.287428855895996 lr:0.0001948645015646243 tokens_per_second_per_gpu:752.5288064168907 +Step 899 | loss:2.3098511695861816 lr:0.00019485204658120818 tokens_per_second_per_gpu:766.6171672471315 +Step 900 | loss:2.2979977130889893 lr:0.000194839576911729 tokens_per_second_per_gpu:743.8134770658296 +Step 901 | loss:2.3184781074523926 lr:0.00019482709255811743 tokens_per_second_per_gpu:786.1307044377922 +Step 902 | loss:2.291576862335205 lr:0.0001948145935223064 tokens_per_second_per_gpu:770.5066650337419 +Step 903 | loss:2.341022491455078 lr:0.00019480207980623128 tokens_per_second_per_gpu:771.9695821383731 +Step 904 | loss:2.286900520324707 lr:0.00019478955141182945 tokens_per_second_per_gpu:768.32582688694 +Step 905 | loss:2.3418917655944824 lr:0.00019477700834104078 tokens_per_second_per_gpu:756.029584698352 +Step 906 | loss:2.2531983852386475 lr:0.00019476445059580727 tokens_per_second_per_gpu:755.2123584310239 +Step 907 | loss:2.262805461883545 lr:0.00019475187817807332 tokens_per_second_per_gpu:758.5026893349042 +Step 908 | loss:2.367476224899292 lr:0.00019473929108978545 tokens_per_second_per_gpu:765.900541005292 +Step 909 | loss:2.3353095054626465 lr:0.00019472668933289263 tokens_per_second_per_gpu:757.9526129230862 +Step 910 | loss:2.2484724521636963 lr:0.00019471407290934593 tokens_per_second_per_gpu:777.8336791366374 +Step 911 | loss:2.3122458457946777 lr:0.0001947014418210988 tokens_per_second_per_gpu:763.7502363938607 +Step 912 | loss:2.3135733604431152 lr:0.0001946887960701069 tokens_per_second_per_gpu:758.9708939089675 +Step 913 | loss:2.2689387798309326 lr:0.00019467613565832823 tokens_per_second_per_gpu:767.1358983753643 +Step 914 | loss:2.279184341430664 lr:0.00019466346058772297 tokens_per_second_per_gpu:784.3500857693062 +Step 915 | loss:2.2438488006591797 lr:0.00019465077086025368 tokens_per_second_per_gpu:773.5352439691554 +Step 916 | loss:2.318974256515503 lr:0.00019463806647788506 tokens_per_second_per_gpu:788.7332748151259 +Step 917 | loss:2.298102378845215 lr:0.00019462534744258423 tokens_per_second_per_gpu:795.3607215828537 +Step 918 | loss:2.312831401824951 lr:0.0001946126137563204 tokens_per_second_per_gpu:761.4669977313525 +Step 919 | loss:2.3086979389190674 lr:0.00019459986542106519 tokens_per_second_per_gpu:751.4387125706252 +Step 920 | loss:2.3075952529907227 lr:0.00019458710243879242 tokens_per_second_per_gpu:769.0542344434773 +Step 921 | loss:2.277533769607544 lr:0.00019457432481147823 tokens_per_second_per_gpu:762.5824048706825 +Step 922 | loss:2.3360188007354736 lr:0.00019456153254110098 tokens_per_second_per_gpu:783.3221139903485 +Step 923 | loss:2.34651780128479 lr:0.00019454872562964132 tokens_per_second_per_gpu:748.53695653157 +Step 924 | loss:2.2692532539367676 lr:0.00019453590407908213 tokens_per_second_per_gpu:750.6914638933596 +Step 925 | loss:2.329252243041992 lr:0.0001945230678914086 tokens_per_second_per_gpu:776.9514409421087 +Step 926 | loss:2.3744025230407715 lr:0.0001945102170686082 tokens_per_second_per_gpu:783.5760754453984 +Step 927 | loss:2.2824676036834717 lr:0.00019449735161267064 tokens_per_second_per_gpu:754.8793186059281 +Step 928 | loss:2.2423548698425293 lr:0.0001944844715255879 tokens_per_second_per_gpu:780.8413294882914 +Step 929 | loss:2.324033260345459 lr:0.00019447157680935412 tokens_per_second_per_gpu:785.8484011120592 +Step 930 | loss:2.2948408126831055 lr:0.00019445866746596596 tokens_per_second_per_gpu:768.3901534331776 +Step 931 | loss:2.3434436321258545 lr:0.00019444574349742206 tokens_per_second_per_gpu:749.8676519408488 +Step 932 | loss:2.2742693424224854 lr:0.00019443280490572353 tokens_per_second_per_gpu:778.763558387215 +Step 933 | loss:2.2809793949127197 lr:0.00019441985169287368 tokens_per_second_per_gpu:771.9026117660482 +Step 934 | loss:2.3143439292907715 lr:0.000194406883860878 tokens_per_second_per_gpu:748.4749480419949 +Step 935 | loss:2.301267147064209 lr:0.00019439390141174435 tokens_per_second_per_gpu:773.9889978812463 +Step 936 | loss:2.3614301681518555 lr:0.00019438090434748285 tokens_per_second_per_gpu:766.454854078324 +Step 937 | loss:2.2904179096221924 lr:0.0001943678926701058 tokens_per_second_per_gpu:769.575423189009 +Step 938 | loss:2.28709077835083 lr:0.00019435486638162786 tokens_per_second_per_gpu:754.8786658182119 +Step 939 | loss:2.3071494102478027 lr:0.00019434182548406587 tokens_per_second_per_gpu:771.7191466427513 +Step 940 | loss:2.282656192779541 lr:0.00019432876997943897 tokens_per_second_per_gpu:747.1541332968733 +Step 941 | loss:2.22468900680542 lr:0.00019431569986976864 tokens_per_second_per_gpu:784.7107803365793 +Step 942 | loss:2.2473392486572266 lr:0.00019430261515707842 tokens_per_second_per_gpu:744.3111354342288 +Step 943 | loss:2.308397054672241 lr:0.0001942895158433943 tokens_per_second_per_gpu:763.200704080427 +Step 944 | loss:2.256816864013672 lr:0.0001942764019307445 tokens_per_second_per_gpu:754.4920568858986 +Step 945 | loss:2.222979784011841 lr:0.00019426327342115938 tokens_per_second_per_gpu:763.1188644312807 +Step 946 | loss:2.279392719268799 lr:0.00019425013031667168 tokens_per_second_per_gpu:769.1233213585598 +Step 947 | loss:2.279275894165039 lr:0.00019423697261931636 tokens_per_second_per_gpu:790.2363838467237 +Step 948 | loss:2.2979276180267334 lr:0.00019422380033113067 tokens_per_second_per_gpu:784.306914444581 +Step 949 | loss:2.308518409729004 lr:0.00019421061345415406 tokens_per_second_per_gpu:774.3908293853525 +Step 950 | loss:2.280893325805664 lr:0.0001941974119904283 tokens_per_second_per_gpu:766.7182328174645 +Step 951 | loss:2.210759401321411 lr:0.00019418419594199735 tokens_per_second_per_gpu:740.9222862986184 +Step 952 | loss:2.240543842315674 lr:0.0001941709653109075 tokens_per_second_per_gpu:760.4019993852162 +Step 953 | loss:2.300313949584961 lr:0.00019415772009920726 tokens_per_second_per_gpu:757.1800589952537 +Step 954 | loss:2.3867709636688232 lr:0.00019414446030894736 tokens_per_second_per_gpu:745.440105412995 +Step 955 | loss:2.3156323432922363 lr:0.00019413118594218093 tokens_per_second_per_gpu:768.6510381194935 +Step 956 | loss:2.2219223976135254 lr:0.00019411789700096314 tokens_per_second_per_gpu:789.8370425495988 +Step 957 | loss:2.358928680419922 lr:0.00019410459348735159 tokens_per_second_per_gpu:747.93748561298 +Step 958 | loss:2.2391648292541504 lr:0.0001940912754034061 tokens_per_second_per_gpu:787.161057805393 +Step 959 | loss:2.301881790161133 lr:0.0001940779427511887 tokens_per_second_per_gpu:759.464085408854 +Step 960 | loss:2.3195581436157227 lr:0.0001940645955327637 tokens_per_second_per_gpu:772.8577145886914 +Step 961 | loss:2.3436412811279297 lr:0.0001940512337501977 tokens_per_second_per_gpu:770.6126671602109 +Step 962 | loss:2.2384989261627197 lr:0.00019403785740555946 tokens_per_second_per_gpu:739.021897036734 +Step 963 | loss:2.3066155910491943 lr:0.0001940244665009201 tokens_per_second_per_gpu:740.6416184033143 +Step 964 | loss:2.246460437774658 lr:0.00019401106103835296 tokens_per_second_per_gpu:770.8263414853109 +Step 965 | loss:2.3125882148742676 lr:0.0001939976410199336 tokens_per_second_per_gpu:750.6983467093623 +Step 966 | loss:2.239960193634033 lr:0.00019398420644773984 tokens_per_second_per_gpu:781.7953279955163 +Step 967 | loss:2.3091626167297363 lr:0.0001939707573238518 tokens_per_second_per_gpu:751.4245697689131 +Step 968 | loss:2.2272040843963623 lr:0.00019395729365035184 tokens_per_second_per_gpu:785.2958658311397 +Step 969 | loss:2.353494882583618 lr:0.00019394381542932454 tokens_per_second_per_gpu:775.530224851918 +Step 970 | loss:2.229590654373169 lr:0.00019393032266285676 tokens_per_second_per_gpu:792.8204986249473 +Step 971 | loss:2.282667636871338 lr:0.00019391681535303756 tokens_per_second_per_gpu:764.0590621164265 +Step 972 | loss:2.272721529006958 lr:0.00019390329350195835 tokens_per_second_per_gpu:795.1386291041462 +Step 973 | loss:2.2452046871185303 lr:0.0001938897571117127 tokens_per_second_per_gpu:760.9456297718086 +Step 974 | loss:2.3401236534118652 lr:0.00019387620618439649 tokens_per_second_per_gpu:794.5732934362943 +Step 975 | loss:2.2552454471588135 lr:0.0001938626407221078 tokens_per_second_per_gpu:762.4717524686928 +Step 976 | loss:2.2953073978424072 lr:0.00019384906072694702 tokens_per_second_per_gpu:777.4422947773021 +Step 977 | loss:2.286909580230713 lr:0.0001938354662010167 tokens_per_second_per_gpu:775.0659931231237 +Step 978 | loss:2.362438440322876 lr:0.0001938218571464218 tokens_per_second_per_gpu:766.5501284866639 +Step 979 | loss:2.2104833126068115 lr:0.00019380823356526932 tokens_per_second_per_gpu:749.4280240044085 +Step 980 | loss:2.242814540863037 lr:0.00019379459545966867 tokens_per_second_per_gpu:771.5880701374256 +Step 981 | loss:2.3630900382995605 lr:0.00019378094283173145 tokens_per_second_per_gpu:761.8814257156463 +Step 982 | loss:2.326061725616455 lr:0.0001937672756835715 tokens_per_second_per_gpu:768.0831310194352 +Step 983 | loss:2.2600607872009277 lr:0.00019375359401730498 tokens_per_second_per_gpu:751.5580074267842 +Step 984 | loss:2.372116804122925 lr:0.00019373989783505016 tokens_per_second_per_gpu:741.563592589047 +Step 985 | loss:2.3367297649383545 lr:0.00019372618713892764 tokens_per_second_per_gpu:791.7093585985838 +Step 986 | loss:2.2618322372436523 lr:0.00019371246193106032 tokens_per_second_per_gpu:779.3243592148065 +Step 987 | loss:2.2376348972320557 lr:0.00019369872221357328 tokens_per_second_per_gpu:759.4615783877971 +Step 988 | loss:2.239485502243042 lr:0.00019368496798859383 tokens_per_second_per_gpu:764.7970633166475 +Step 989 | loss:2.255749464035034 lr:0.00019367119925825158 tokens_per_second_per_gpu:750.609370616666 +Step 990 | loss:2.249358892440796 lr:0.00019365741602467835 tokens_per_second_per_gpu:763.8228581122023 +Step 991 | loss:2.219820261001587 lr:0.00019364361829000818 tokens_per_second_per_gpu:786.0250715010897 +Step 992 | loss:2.251595973968506 lr:0.00019362980605637747 tokens_per_second_per_gpu:768.6196763889803 +Step 993 | loss:2.291360855102539 lr:0.00019361597932592473 tokens_per_second_per_gpu:768.7735140016132 +Step 994 | loss:2.239687442779541 lr:0.00019360213810079078 tokens_per_second_per_gpu:762.678127301235 +Step 995 | loss:2.2066798210144043 lr:0.00019358828238311864 tokens_per_second_per_gpu:752.0591835604238 +Step 996 | loss:2.3098793029785156 lr:0.00019357441217505368 tokens_per_second_per_gpu:745.8328505206347 +Step 997 | loss:2.2350964546203613 lr:0.0001935605274787434 tokens_per_second_per_gpu:787.0994382498848 +Step 998 | loss:2.345595359802246 lr:0.00019354662829633757 tokens_per_second_per_gpu:754.9632635752774 +Step 999 | loss:2.2784833908081055 lr:0.00019353271462998825 tokens_per_second_per_gpu:752.7711052815342 +Step 1000 | loss:2.273494243621826 lr:0.00019351878648184972 tokens_per_second_per_gpu:789.5479180137534 +Step 1001 | loss:2.227482557296753 lr:0.00019350484385407846 tokens_per_second_per_gpu:790.4051766171871 +Step 1002 | loss:2.2576606273651123 lr:0.00019349088674883324 tokens_per_second_per_gpu:783.5375143022792 +Step 1003 | loss:2.3107213973999023 lr:0.00019347691516827505 tokens_per_second_per_gpu:779.5948733475024 +Step 1004 | loss:2.341087818145752 lr:0.00019346292911456711 tokens_per_second_per_gpu:761.948587246191 +Step 1005 | loss:2.2758898735046387 lr:0.00019344892858987492 tokens_per_second_per_gpu:778.174158782886 +Step 1006 | loss:2.2495458126068115 lr:0.00019343491359636623 tokens_per_second_per_gpu:766.0989109378447 +Step 1007 | loss:2.284386157989502 lr:0.00019342088413621097 tokens_per_second_per_gpu:762.1641173151538 +Step 1008 | loss:2.3138880729675293 lr:0.0001934068402115813 tokens_per_second_per_gpu:786.5617164519482 +Step 1009 | loss:2.2628018856048584 lr:0.00019339278182465175 tokens_per_second_per_gpu:774.1668383016004 +Step 1010 | loss:2.3129334449768066 lr:0.00019337870897759892 tokens_per_second_per_gpu:765.6789125089092 +Step 1011 | loss:2.2290916442871094 lr:0.00019336462167260173 tokens_per_second_per_gpu:776.3740320900702 +Step 1012 | loss:2.3036723136901855 lr:0.00019335051991184137 tokens_per_second_per_gpu:780.4640985064607 +Step 1013 | loss:2.2271080017089844 lr:0.00019333640369750122 tokens_per_second_per_gpu:757.468406078718 +Step 1014 | loss:2.2708592414855957 lr:0.00019332227303176688 tokens_per_second_per_gpu:782.4431304848392 +Step 1015 | loss:2.3258392810821533 lr:0.00019330812791682627 tokens_per_second_per_gpu:763.6569196394585 +Step 1016 | loss:2.2513723373413086 lr:0.0001932939683548695 tokens_per_second_per_gpu:759.5629188935128 +Step 1017 | loss:2.289374828338623 lr:0.00019327979434808888 tokens_per_second_per_gpu:778.2944315625346 +Step 1018 | loss:2.2833807468414307 lr:0.000193265605898679 tokens_per_second_per_gpu:751.8822032623509 +Step 1019 | loss:2.2233564853668213 lr:0.00019325140300883667 tokens_per_second_per_gpu:772.3370584816292 +Step 1020 | loss:2.277658462524414 lr:0.00019323718568076093 tokens_per_second_per_gpu:772.7319951439023 +Step 1021 | loss:2.3092360496520996 lr:0.0001932229539166531 tokens_per_second_per_gpu:759.7665509209645 +Step 1022 | loss:2.3164968490600586 lr:0.0001932087077187167 tokens_per_second_per_gpu:764.3208559689892 +Step 1023 | loss:2.302814483642578 lr:0.00019319444708915744 tokens_per_second_per_gpu:777.4831334586004 +Step 1024 | loss:2.3044540882110596 lr:0.00019318017203018336 tokens_per_second_per_gpu:751.089248975666 +Step 1025 | loss:2.2432117462158203 lr:0.00019316588254400464 tokens_per_second_per_gpu:769.2171976443079 +Step 1026 | loss:2.3009231090545654 lr:0.0001931515786328338 tokens_per_second_per_gpu:774.5745419331914 +Step 1027 | loss:2.269476890563965 lr:0.0001931372602988855 tokens_per_second_per_gpu:772.2944795300197 +Step 1028 | loss:2.2493057250976562 lr:0.00019312292754437667 tokens_per_second_per_gpu:777.8175703864308 +Step 1029 | loss:2.2810769081115723 lr:0.00019310858037152647 tokens_per_second_per_gpu:779.6631786930927 +Step 1030 | loss:2.2846133708953857 lr:0.00019309421878255624 tokens_per_second_per_gpu:778.7468045657852 +Step 1031 | loss:2.236706018447876 lr:0.0001930798427796897 tokens_per_second_per_gpu:736.3650266523705 +Step 1032 | loss:2.2280569076538086 lr:0.00019306545236515263 tokens_per_second_per_gpu:765.3822494981373 +Step 1033 | loss:2.2525441646575928 lr:0.00019305104754117314 tokens_per_second_per_gpu:790.1702002129914 +Step 1034 | loss:2.3077609539031982 lr:0.00019303662830998154 tokens_per_second_per_gpu:781.3898112876119 +Step 1035 | loss:2.310326099395752 lr:0.0001930221946738104 tokens_per_second_per_gpu:768.9164666548127 +Step 1036 | loss:2.2716314792633057 lr:0.0001930077466348945 tokens_per_second_per_gpu:790.0801663038931 +Step 1037 | loss:2.249903678894043 lr:0.0001929932841954708 tokens_per_second_per_gpu:769.1860511869024 +Step 1038 | loss:2.2979066371917725 lr:0.0001929788073577786 tokens_per_second_per_gpu:757.8409816418605 +Step 1039 | loss:2.2342429161071777 lr:0.00019296431612405933 tokens_per_second_per_gpu:762.8179542584322 +Step 1040 | loss:2.238295555114746 lr:0.00019294981049655668 tokens_per_second_per_gpu:761.9949457539451 +Step 1041 | loss:2.251011848449707 lr:0.00019293529047751661 tokens_per_second_per_gpu:791.5794806662626 +Step 1042 | loss:2.211798667907715 lr:0.00019292075606918725 tokens_per_second_per_gpu:773.3098668981188 +Step 1043 | loss:2.2878122329711914 lr:0.00019290620727381894 tokens_per_second_per_gpu:782.9904079857663 +Step 1044 | loss:2.290400981903076 lr:0.00019289164409366438 tokens_per_second_per_gpu:778.5850260864845 +Step 1045 | loss:2.2952725887298584 lr:0.00019287706653097833 tokens_per_second_per_gpu:769.1020444908545 +Step 1046 | loss:2.2736620903015137 lr:0.00019286247458801786 tokens_per_second_per_gpu:784.966970491095 +Step 1047 | loss:2.231437921524048 lr:0.0001928478682670423 tokens_per_second_per_gpu:788.0672823208043 +Step 1048 | loss:2.3506367206573486 lr:0.00019283324757031318 tokens_per_second_per_gpu:781.7007937150024 +Step 1049 | loss:2.2756311893463135 lr:0.00019281861250009416 tokens_per_second_per_gpu:759.770161544942 +Step 1050 | loss:2.2596542835235596 lr:0.00019280396305865126 tokens_per_second_per_gpu:768.7230064645598 +Step 1051 | loss:2.3502461910247803 lr:0.00019278929924825268 tokens_per_second_per_gpu:762.7617989172811 +Step 1052 | loss:2.3341004848480225 lr:0.0001927746210711688 tokens_per_second_per_gpu:764.1373245790452 +Step 1053 | loss:2.214618444442749 lr:0.00019275992852967226 tokens_per_second_per_gpu:725.4348237427595 +Step 1054 | loss:2.22799015045166 lr:0.000192745221626038 tokens_per_second_per_gpu:762.8572405816337 +Step 1055 | loss:2.224668502807617 lr:0.00019273050036254302 tokens_per_second_per_gpu:779.6679936059103 +Step 1056 | loss:2.223031520843506 lr:0.00019271576474146667 tokens_per_second_per_gpu:787.5210987286835 +Step 1057 | loss:2.20503568649292 lr:0.00019270101476509045 tokens_per_second_per_gpu:767.6227395118124 +Step 1058 | loss:2.2365546226501465 lr:0.00019268625043569818 tokens_per_second_per_gpu:769.0786407286224 +Step 1059 | loss:2.226761817932129 lr:0.0001926714717555758 tokens_per_second_per_gpu:781.264410972508 +Step 1060 | loss:2.308448314666748 lr:0.00019265667872701153 tokens_per_second_per_gpu:759.1098494758148 +Step 1061 | loss:2.3124489784240723 lr:0.00019264187135229578 tokens_per_second_per_gpu:788.6809507537894 +Step 1062 | loss:2.2365732192993164 lr:0.0001926270496337212 tokens_per_second_per_gpu:737.4025980955059 +Step 1063 | loss:2.2388219833374023 lr:0.00019261221357358267 tokens_per_second_per_gpu:787.1324685103867 +Step 1064 | loss:2.2821946144104004 lr:0.00019259736317417723 tokens_per_second_per_gpu:784.5441716548464 +Step 1065 | loss:2.247361898422241 lr:0.0001925824984378042 tokens_per_second_per_gpu:740.0538212873888 +Step 1066 | loss:2.2503836154937744 lr:0.00019256761936676514 tokens_per_second_per_gpu:759.233265388185 +Step 1067 | loss:2.283695697784424 lr:0.0001925527259633638 tokens_per_second_per_gpu:771.2906061480656 +Step 1068 | loss:2.2850661277770996 lr:0.00019253781822990612 tokens_per_second_per_gpu:762.9673654244713 +Step 1069 | loss:2.264451265335083 lr:0.00019252289616870024 tokens_per_second_per_gpu:753.9723334582691 +Step 1070 | loss:2.312628984451294 lr:0.00019250795978205664 tokens_per_second_per_gpu:763.8060737008274 +Step 1071 | loss:2.326709032058716 lr:0.00019249300907228789 tokens_per_second_per_gpu:783.1481354433696 +Step 1072 | loss:2.2756354808807373 lr:0.0001924780440417089 tokens_per_second_per_gpu:770.8010509379595 +Step 1073 | loss:2.3031556606292725 lr:0.0001924630646926366 tokens_per_second_per_gpu:785.452522305298 +Step 1074 | loss:2.2513811588287354 lr:0.00019244807102739036 tokens_per_second_per_gpu:756.6523154390297 +Step 1075 | loss:2.2172138690948486 lr:0.00019243306304829162 tokens_per_second_per_gpu:790.2352968898264 +Step 1076 | loss:2.1809215545654297 lr:0.00019241804075766412 tokens_per_second_per_gpu:767.9606356052815 +Step 1077 | loss:2.257845401763916 lr:0.00019240300415783375 tokens_per_second_per_gpu:784.7728877756601 +Step 1078 | loss:2.243802309036255 lr:0.0001923879532511287 tokens_per_second_per_gpu:768.1774702264153 +Step 1079 | loss:2.2762255668640137 lr:0.00019237288803987922 tokens_per_second_per_gpu:754.2422156956357 +Step 1080 | loss:2.3132848739624023 lr:0.00019235780852641798 tokens_per_second_per_gpu:757.3396077861224 +Step 1081 | loss:2.298861503601074 lr:0.00019234271471307973 tokens_per_second_per_gpu:748.4358756694904 +Step 1082 | loss:2.2716803550720215 lr:0.00019232760660220142 tokens_per_second_per_gpu:751.5727944090454 +Step 1083 | loss:2.214811086654663 lr:0.00019231248419612225 tokens_per_second_per_gpu:787.8692949500872 +Step 1084 | loss:2.3075661659240723 lr:0.00019229734749718374 tokens_per_second_per_gpu:734.964509944937 +Step 1085 | loss:2.29616641998291 lr:0.00019228219650772944 tokens_per_second_per_gpu:789.2249248052431 +Step 1086 | loss:2.249483346939087 lr:0.00019226703123010526 tokens_per_second_per_gpu:753.2490330449527 +Step 1087 | loss:2.2558059692382812 lr:0.0001922518516666592 tokens_per_second_per_gpu:748.2628923964758 +Step 1088 | loss:2.2501087188720703 lr:0.00019223665781974153 tokens_per_second_per_gpu:774.6992636891234 +Step 1089 | loss:2.272510528564453 lr:0.00019222144969170476 tokens_per_second_per_gpu:779.6655753924007 +Step 1090 | loss:2.2248902320861816 lr:0.0001922062272849036 tokens_per_second_per_gpu:791.2039208742344 +Step 1091 | loss:2.2590556144714355 lr:0.00019219099060169493 tokens_per_second_per_gpu:763.0499475645819 +Step 1092 | loss:2.3011908531188965 lr:0.00019217573964443784 tokens_per_second_per_gpu:763.6415158041763 +Step 1093 | loss:2.3196728229522705 lr:0.0001921604744154937 tokens_per_second_per_gpu:788.4015799332315 +Step 1094 | loss:2.3345792293548584 lr:0.00019214519491722603 tokens_per_second_per_gpu:748.2663570507075 +Step 1095 | loss:2.219212770462036 lr:0.00019212990115200057 tokens_per_second_per_gpu:779.4288298144969 +Step 1096 | loss:2.2560760974884033 lr:0.0001921145931221853 tokens_per_second_per_gpu:783.996295019701 +Step 1097 | loss:2.2567451000213623 lr:0.00019209927083015034 tokens_per_second_per_gpu:776.4132140598134 +Step 1098 | loss:2.239813804626465 lr:0.00019208393427826804 tokens_per_second_per_gpu:769.6077767741915 +Step 1099 | loss:2.242039918899536 lr:0.00019206858346891304 tokens_per_second_per_gpu:781.0877641331142 +Step 1100 | loss:2.2575058937072754 lr:0.00019205321840446213 tokens_per_second_per_gpu:781.4299171667144 +Step 1101 | loss:2.2509350776672363 lr:0.00019203783908729424 tokens_per_second_per_gpu:772.8560679757375 +Step 1102 | loss:2.2053871154785156 lr:0.00019202244551979063 tokens_per_second_per_gpu:765.6443910354222 +Step 1103 | loss:2.255664110183716 lr:0.00019200703770433464 tokens_per_second_per_gpu:784.6245405348772 +Step 1104 | loss:2.245981216430664 lr:0.00019199161564331196 tokens_per_second_per_gpu:788.4529069720153 +Step 1105 | loss:2.24609637260437 lr:0.00019197617933911033 tokens_per_second_per_gpu:766.8820349686121 +Step 1106 | loss:2.2789041996002197 lr:0.00019196072879411983 tokens_per_second_per_gpu:774.3593206027748 +Step 1107 | loss:2.2733521461486816 lr:0.00019194526401073266 tokens_per_second_per_gpu:761.0791621969096 +Step 1108 | loss:2.2911763191223145 lr:0.00019192978499134327 tokens_per_second_per_gpu:765.0619853971942 +Step 1109 | loss:2.182476282119751 lr:0.00019191429173834827 tokens_per_second_per_gpu:739.5577985926882 +Step 1110 | loss:2.2980830669403076 lr:0.0001918987842541465 tokens_per_second_per_gpu:735.0031185788379 +Step 1111 | loss:2.221776008605957 lr:0.00019188326254113906 tokens_per_second_per_gpu:779.281826789344 +Step 1112 | loss:2.280059576034546 lr:0.00019186772660172917 tokens_per_second_per_gpu:779.0119854208199 +Step 1113 | loss:2.283189296722412 lr:0.0001918521764383222 tokens_per_second_per_gpu:763.2689427503742 +Step 1114 | loss:2.2584009170532227 lr:0.0001918366120533259 tokens_per_second_per_gpu:774.8090285652883 +Step 1115 | loss:2.257438898086548 lr:0.0001918210334491501 tokens_per_second_per_gpu:781.4610017451097 +Step 1116 | loss:2.239182710647583 lr:0.00019180544062820682 tokens_per_second_per_gpu:758.3914228881205 +Step 1117 | loss:2.2065646648406982 lr:0.00019178983359291035 tokens_per_second_per_gpu:731.7177810358861 +Step 1118 | loss:2.161081075668335 lr:0.00019177421234567714 tokens_per_second_per_gpu:776.0499963731916 +Step 1119 | loss:2.2547693252563477 lr:0.00019175857688892583 tokens_per_second_per_gpu:775.2521927946896 +Step 1120 | loss:2.279369354248047 lr:0.00019174292722507735 tokens_per_second_per_gpu:797.2993539726816 +Step 1121 | loss:2.2813501358032227 lr:0.00019172726335655465 tokens_per_second_per_gpu:784.5137751623502 +Step 1122 | loss:2.2040140628814697 lr:0.00019171158528578306 tokens_per_second_per_gpu:770.3005774041419 +Step 1123 | loss:2.1762118339538574 lr:0.00019169589301518998 tokens_per_second_per_gpu:770.1249818598766 +Step 1124 | loss:2.259539842605591 lr:0.00019168018654720515 tokens_per_second_per_gpu:759.5158794893243 +Step 1125 | loss:2.24619722366333 lr:0.00019166446588426031 tokens_per_second_per_gpu:760.8145856601105 +Step 1126 | loss:2.2271907329559326 lr:0.0001916487310287896 tokens_per_second_per_gpu:776.9165862433797 +Step 1127 | loss:2.291963815689087 lr:0.00019163298198322925 tokens_per_second_per_gpu:770.0043387690547 +Step 1128 | loss:2.263935089111328 lr:0.00019161721875001768 tokens_per_second_per_gpu:759.4941843296181 +Step 1129 | loss:2.2612926959991455 lr:0.00019160144133159555 tokens_per_second_per_gpu:740.7159814025478 +Step 1130 | loss:2.2401702404022217 lr:0.00019158564973040568 tokens_per_second_per_gpu:763.6061874371508 +Step 1131 | loss:2.2506604194641113 lr:0.00019156984394889313 tokens_per_second_per_gpu:788.5181595563716 +Step 1132 | loss:2.219693899154663 lr:0.0001915540239895051 tokens_per_second_per_gpu:780.0276774859864 +Step 1133 | loss:2.274604558944702 lr:0.00019153818985469102 tokens_per_second_per_gpu:786.4028198913902 +Step 1134 | loss:2.2547364234924316 lr:0.00019152234154690256 tokens_per_second_per_gpu:800.0798782391525 +Step 1135 | loss:2.24106502532959 lr:0.00019150647906859348 tokens_per_second_per_gpu:759.3603480384384 +Step 1136 | loss:2.2142438888549805 lr:0.0001914906024222198 tokens_per_second_per_gpu:772.2986805912727 +Step 1137 | loss:2.3454337120056152 lr:0.0001914747116102397 tokens_per_second_per_gpu:750.0666488927694 +Step 1138 | loss:2.2323453426361084 lr:0.00019145880663511358 tokens_per_second_per_gpu:773.4989178671151 +Step 1139 | loss:2.226520538330078 lr:0.00019144288749930408 tokens_per_second_per_gpu:746.3328272145983 +Step 1140 | loss:2.271510601043701 lr:0.00019142695420527593 tokens_per_second_per_gpu:757.106625125801 +Step 1141 | loss:2.200575351715088 lr:0.00019141100675549612 tokens_per_second_per_gpu:752.1440683495931 +Step 1142 | loss:2.2197039127349854 lr:0.00019139504515243381 tokens_per_second_per_gpu:755.7515360181376 +Step 1143 | loss:2.264885187149048 lr:0.00019137906939856034 tokens_per_second_per_gpu:767.1381185549806 +Step 1144 | loss:2.2082369327545166 lr:0.00019136307949634929 tokens_per_second_per_gpu:774.9890948410126 +Step 1145 | loss:2.2500429153442383 lr:0.00019134707544827637 tokens_per_second_per_gpu:770.347226469695 +Step 1146 | loss:2.243603229522705 lr:0.00019133105725681953 tokens_per_second_per_gpu:761.5511430584605 +Step 1147 | loss:2.216479778289795 lr:0.00019131502492445885 tokens_per_second_per_gpu:769.753909624366 +Step 1148 | loss:2.2256603240966797 lr:0.00019129897845367668 tokens_per_second_per_gpu:776.1509791698619 +Step 1149 | loss:2.253044605255127 lr:0.00019128291784695746 tokens_per_second_per_gpu:747.6639675392018 +Step 1150 | loss:2.2265095710754395 lr:0.00019126684310678794 tokens_per_second_per_gpu:759.8394712345843 +Step 1151 | loss:2.1638693809509277 lr:0.00019125075423565696 tokens_per_second_per_gpu:784.0975581158759 +Step 1152 | loss:2.260871171951294 lr:0.00019123465123605557 tokens_per_second_per_gpu:788.5548120349754 +Step 1153 | loss:2.268308401107788 lr:0.00019121853411047704 tokens_per_second_per_gpu:770.3051337634329 +Step 1154 | loss:2.2894811630249023 lr:0.00019120240286141677 tokens_per_second_per_gpu:773.3587858553101 +Step 1155 | loss:2.2387986183166504 lr:0.00019118625749137244 tokens_per_second_per_gpu:773.7414766508111 +Step 1156 | loss:2.2598800659179688 lr:0.0001911700980028438 tokens_per_second_per_gpu:711.8568838798359 +Step 1157 | loss:2.2572073936462402 lr:0.00019115392439833287 tokens_per_second_per_gpu:773.7353058876469 +Step 1158 | loss:2.227130889892578 lr:0.00019113773668034384 tokens_per_second_per_gpu:764.861499420128 +Step 1159 | loss:2.171191453933716 lr:0.00019112153485138306 tokens_per_second_per_gpu:764.6051476024185 +Step 1160 | loss:2.2318525314331055 lr:0.00019110531891395905 tokens_per_second_per_gpu:767.202725862527 +Step 1161 | loss:2.2074851989746094 lr:0.00019108908887058263 tokens_per_second_per_gpu:793.7904843434177 +Step 1162 | loss:2.1945724487304688 lr:0.00019107284472376663 tokens_per_second_per_gpu:779.40279283224 +Step 1163 | loss:2.2216107845306396 lr:0.0001910565864760262 tokens_per_second_per_gpu:778.0595601821732 +Step 1164 | loss:2.278773069381714 lr:0.00019104031412987862 tokens_per_second_per_gpu:755.2185972347178 +Step 1165 | loss:2.2673521041870117 lr:0.00019102402768784334 tokens_per_second_per_gpu:758.5542453717848 +Step 1166 | loss:2.2691495418548584 lr:0.00019100772715244203 tokens_per_second_per_gpu:779.360442704322 +Step 1167 | loss:2.25062894821167 lr:0.0001909914125261985 tokens_per_second_per_gpu:747.8699645550649 +Step 1168 | loss:2.234467029571533 lr:0.00019097508381163877 tokens_per_second_per_gpu:790.0331456311006 +Step 1169 | loss:2.2337756156921387 lr:0.0001909587410112911 tokens_per_second_per_gpu:765.14191247779 +Step 1170 | loss:2.2534918785095215 lr:0.00019094238412768576 tokens_per_second_per_gpu:770.5003023608175 +Step 1171 | loss:2.2865657806396484 lr:0.00019092601316335537 tokens_per_second_per_gpu:752.8727878692835 +Step 1172 | loss:2.2067198753356934 lr:0.00019090962812083463 tokens_per_second_per_gpu:780.0693063738433 +Step 1173 | loss:2.2629880905151367 lr:0.0001908932290026605 tokens_per_second_per_gpu:763.2002449478471 +Step 1174 | loss:2.242105007171631 lr:0.00019087681581137208 tokens_per_second_per_gpu:784.4688297313107 +Step 1175 | loss:2.2671995162963867 lr:0.0001908603885495106 tokens_per_second_per_gpu:785.8820242666138 +Step 1176 | loss:2.2475688457489014 lr:0.00019084394721961956 tokens_per_second_per_gpu:773.6723125199528 +Step 1177 | loss:2.276135206222534 lr:0.00019082749182424452 tokens_per_second_per_gpu:778.3775897744047 +Step 1178 | loss:2.2464466094970703 lr:0.0001908110223659334 tokens_per_second_per_gpu:773.8051684065229 +Step 1179 | loss:2.2417595386505127 lr:0.00019079453884723608 tokens_per_second_per_gpu:743.116784350682 +Step 1180 | loss:2.2806687355041504 lr:0.0001907780412707048 tokens_per_second_per_gpu:772.1696464491368 +Step 1181 | loss:2.2634286880493164 lr:0.00019076152963889384 tokens_per_second_per_gpu:747.4128747491583 +Step 1182 | loss:2.237196445465088 lr:0.00019074500395435977 tokens_per_second_per_gpu:773.8650316561909 +Step 1183 | loss:2.2207422256469727 lr:0.00019072846421966125 tokens_per_second_per_gpu:774.9628179871511 +Step 1184 | loss:2.2808165550231934 lr:0.0001907119104373592 tokens_per_second_per_gpu:773.3547313527557 +Step 1185 | loss:2.272620439529419 lr:0.00019069534261001656 tokens_per_second_per_gpu:764.1621377177325 +Step 1186 | loss:2.2589669227600098 lr:0.00019067876074019865 tokens_per_second_per_gpu:770.4220273269036 +Step 1187 | loss:2.2548675537109375 lr:0.0001906621648304728 tokens_per_second_per_gpu:784.3987757564855 +Step 1188 | loss:2.184309720993042 lr:0.00019064555488340862 tokens_per_second_per_gpu:744.4690754077144 +Step 1189 | loss:2.1986243724823 lr:0.0001906289309015778 tokens_per_second_per_gpu:768.4959887142093 +Step 1190 | loss:2.2712697982788086 lr:0.00019061229288755432 tokens_per_second_per_gpu:752.5809226342843 +Step 1191 | loss:2.1596479415893555 lr:0.0001905956408439142 tokens_per_second_per_gpu:750.2963713399829 +Step 1192 | loss:2.247283697128296 lr:0.00019057897477323568 tokens_per_second_per_gpu:750.3204341154143 +Step 1193 | loss:2.307523250579834 lr:0.0001905622946780993 tokens_per_second_per_gpu:768.4303872446133 +Step 1194 | loss:2.2024054527282715 lr:0.00019054560056108754 tokens_per_second_per_gpu:763.0655848229185 +Step 1195 | loss:2.241393804550171 lr:0.00019052889242478528 tokens_per_second_per_gpu:765.7852195066569 +Step 1196 | loss:2.180332660675049 lr:0.00019051217027177934 tokens_per_second_per_gpu:757.17237155696 +Step 1197 | loss:2.2361690998077393 lr:0.00019049543410465893 tokens_per_second_per_gpu:767.4063182477913 +Step 1198 | loss:2.2114312648773193 lr:0.00019047868392601532 tokens_per_second_per_gpu:786.5192331667452 +Step 1199 | loss:2.236851692199707 lr:0.0001904619197384419 tokens_per_second_per_gpu:770.1270027915989 +Step 1200 | loss:2.232950210571289 lr:0.00019044514154453434 tokens_per_second_per_gpu:782.0777565861408 +Step 1201 | loss:2.303670883178711 lr:0.0001904283493468904 tokens_per_second_per_gpu:779.894820757563 +Step 1202 | loss:2.2399981021881104 lr:0.0001904115431481101 tokens_per_second_per_gpu:770.1898965921511 +Step 1203 | loss:2.2754769325256348 lr:0.0001903947229507955 tokens_per_second_per_gpu:784.5809689107716 +Step 1204 | loss:2.2002322673797607 lr:0.0001903778887575509 tokens_per_second_per_gpu:781.1073276472885 +Step 1205 | loss:2.23160982131958 lr:0.0001903610405709828 tokens_per_second_per_gpu:767.9182492560866 +Step 1206 | loss:2.2606418132781982 lr:0.00019034417839369977 tokens_per_second_per_gpu:781.6667641609586 +Step 1207 | loss:2.206765651702881 lr:0.00019032730222831264 tokens_per_second_per_gpu:739.5255084259392 +Step 1208 | loss:2.264894962310791 lr:0.0001903104120774344 tokens_per_second_per_gpu:790.5876575769339 +Step 1209 | loss:2.185576915740967 lr:0.0001902935079436801 tokens_per_second_per_gpu:740.898111985049 +Step 1210 | loss:2.2286529541015625 lr:0.00019027658982966706 tokens_per_second_per_gpu:771.0853512233805 +Step 1211 | loss:2.229745388031006 lr:0.00019025965773801476 tokens_per_second_per_gpu:750.5781650001358 +Step 1212 | loss:2.2497506141662598 lr:0.00019024271167134477 tokens_per_second_per_gpu:777.7559664346986 +Step 1213 | loss:2.2259976863861084 lr:0.0001902257516322809 tokens_per_second_per_gpu:766.2601039378733 +Step 1214 | loss:2.234422206878662 lr:0.0001902087776234491 tokens_per_second_per_gpu:777.6160744886824 +Step 1215 | loss:2.277059316635132 lr:0.00019019178964747746 tokens_per_second_per_gpu:790.1325077830788 +Step 1216 | loss:2.2587060928344727 lr:0.00019017478770699624 tokens_per_second_per_gpu:737.0164437517286 +Step 1217 | loss:2.247840166091919 lr:0.0001901577718046379 tokens_per_second_per_gpu:788.7101762016352 +Step 1218 | loss:2.2780635356903076 lr:0.00019014074194303703 tokens_per_second_per_gpu:774.1618492454146 +Step 1219 | loss:2.152980089187622 lr:0.00019012369812483035 tokens_per_second_per_gpu:748.3487358977886 +Step 1220 | loss:2.196967840194702 lr:0.00019010664035265683 tokens_per_second_per_gpu:787.7209962789836 +Step 1221 | loss:2.272585868835449 lr:0.00019008956862915752 tokens_per_second_per_gpu:763.0764680934898 +Step 1222 | loss:2.2404842376708984 lr:0.00019007248295697563 tokens_per_second_per_gpu:775.4215534028166 +Step 1223 | loss:2.2460904121398926 lr:0.0001900553833387566 tokens_per_second_per_gpu:779.8919432034868 +Step 1224 | loss:2.259199380874634 lr:0.00019003826977714798 tokens_per_second_per_gpu:738.5270070876819 +Step 1225 | loss:2.218163013458252 lr:0.0001900211422747995 tokens_per_second_per_gpu:759.7270255453319 +Step 1226 | loss:2.191521644592285 lr:0.00019000400083436295 tokens_per_second_per_gpu:748.7646852569745 +Step 1227 | loss:2.235185384750366 lr:0.00018998684545849245 tokens_per_second_per_gpu:791.4333519024177 +Step 1228 | loss:2.2340705394744873 lr:0.00018996967614984413 tokens_per_second_per_gpu:768.4189466028054 +Step 1229 | loss:2.25239896774292 lr:0.00018995249291107636 tokens_per_second_per_gpu:749.2427081686508 +Step 1230 | loss:2.268254041671753 lr:0.00018993529574484966 tokens_per_second_per_gpu:750.4932549986808 +Step 1231 | loss:2.2697975635528564 lr:0.00018991808465382667 tokens_per_second_per_gpu:750.5063214584287 +Step 1232 | loss:2.228133201599121 lr:0.0001899008596406722 tokens_per_second_per_gpu:755.5735078910304 +Step 1233 | loss:2.2870945930480957 lr:0.00018988362070805325 tokens_per_second_per_gpu:756.6173881896163 +Step 1234 | loss:2.2782106399536133 lr:0.0001898663678586389 tokens_per_second_per_gpu:772.4162354724477 +Step 1235 | loss:2.18054461479187 lr:0.0001898491010951005 tokens_per_second_per_gpu:711.1726910937354 +Step 1236 | loss:2.198805093765259 lr:0.0001898318204201114 tokens_per_second_per_gpu:749.6829906521979 +Step 1237 | loss:2.202205181121826 lr:0.00018981452583634724 tokens_per_second_per_gpu:742.8098006264687 +Step 1238 | loss:2.1593258380889893 lr:0.00018979721734648574 tokens_per_second_per_gpu:739.9519455498274 +Step 1239 | loss:2.263359785079956 lr:0.00018977989495320684 tokens_per_second_per_gpu:758.1688949694895 +Step 1240 | loss:2.311871290206909 lr:0.0001897625586591925 tokens_per_second_per_gpu:773.8999803686299 +Step 1241 | loss:2.268575429916382 lr:0.00018974520846712703 tokens_per_second_per_gpu:781.2902996498889 +Step 1242 | loss:2.290813446044922 lr:0.00018972784437969672 tokens_per_second_per_gpu:760.8904582243684 +Step 1243 | loss:2.193373918533325 lr:0.00018971046639959006 tokens_per_second_per_gpu:761.8905825316297 +Step 1244 | loss:2.226311445236206 lr:0.00018969307452949773 tokens_per_second_per_gpu:773.4483917220679 +Step 1245 | loss:2.2072601318359375 lr:0.00018967566877211255 tokens_per_second_per_gpu:770.9323377785374 +Step 1246 | loss:2.1906328201293945 lr:0.00018965824913012944 tokens_per_second_per_gpu:748.6782801812235 +Step 1247 | loss:2.2630646228790283 lr:0.00018964081560624553 tokens_per_second_per_gpu:758.9482757542897 +Step 1248 | loss:2.2352957725524902 lr:0.00018962336820316006 tokens_per_second_per_gpu:778.9905513859098 +Step 1249 | loss:2.2579708099365234 lr:0.00018960590692357446 tokens_per_second_per_gpu:780.7998271109212 +Step 1250 | loss:2.2474489212036133 lr:0.00018958843177019227 tokens_per_second_per_gpu:750.6579152937945 +Step 1251 | loss:2.2313714027404785 lr:0.00018957094274571915 tokens_per_second_per_gpu:770.1250322196694 +Step 1252 | loss:2.234496831893921 lr:0.00018955343985286303 tokens_per_second_per_gpu:772.4827303174036 +Step 1253 | loss:2.236453056335449 lr:0.0001895359230943338 tokens_per_second_per_gpu:770.0818395290459 +Step 1254 | loss:2.162402868270874 lr:0.00018951839247284368 tokens_per_second_per_gpu:752.098556849459 +Step 1255 | loss:2.2085814476013184 lr:0.00018950084799110694 tokens_per_second_per_gpu:777.2333006328836 +Step 1256 | loss:2.257572889328003 lr:0.00018948328965184003 tokens_per_second_per_gpu:781.6251185678342 +Step 1257 | loss:2.2246766090393066 lr:0.0001894657174577615 tokens_per_second_per_gpu:757.9204620090708 +Step 1258 | loss:2.2039730548858643 lr:0.00018944813141159208 tokens_per_second_per_gpu:757.5623775876619 +Step 1259 | loss:2.217834711074829 lr:0.00018943053151605467 tokens_per_second_per_gpu:779.009005153979 +Step 1260 | loss:2.2583446502685547 lr:0.00018941291777387425 tokens_per_second_per_gpu:757.3898046138645 +Step 1261 | loss:2.2247586250305176 lr:0.00018939529018777797 tokens_per_second_per_gpu:745.3581339937265 +Step 1262 | loss:2.284027099609375 lr:0.00018937764876049515 tokens_per_second_per_gpu:762.2457495896194 +Step 1263 | loss:2.2846012115478516 lr:0.00018935999349475725 tokens_per_second_per_gpu:775.8215857246156 +Step 1264 | loss:2.152127742767334 lr:0.00018934232439329787 tokens_per_second_per_gpu:788.1590004924071 +Step 1265 | loss:2.2185556888580322 lr:0.00018932464145885266 tokens_per_second_per_gpu:789.943476316647 +Step 1266 | loss:2.2653026580810547 lr:0.00018930694469415958 tokens_per_second_per_gpu:792.3847684732275 +Step 1267 | loss:2.2258801460266113 lr:0.00018928923410195859 tokens_per_second_per_gpu:777.7558928517784 +Step 1268 | loss:2.2481775283813477 lr:0.00018927150968499188 tokens_per_second_per_gpu:784.4870625150132 +Step 1269 | loss:2.233360528945923 lr:0.0001892537714460037 tokens_per_second_per_gpu:780.8786873106388 +Step 1270 | loss:2.204989194869995 lr:0.0001892360193877405 tokens_per_second_per_gpu:771.7518834862377 +Step 1271 | loss:2.1393961906433105 lr:0.00018921825351295087 tokens_per_second_per_gpu:712.6695158700104 +Step 1272 | loss:2.187652587890625 lr:0.00018920047382438553 tokens_per_second_per_gpu:758.6079660478146 +Step 1273 | loss:2.188796281814575 lr:0.00018918268032479732 tokens_per_second_per_gpu:764.8913487814004 +Step 1274 | loss:2.2628183364868164 lr:0.0001891648730169412 tokens_per_second_per_gpu:774.1641161568524 +Step 1275 | loss:2.205648422241211 lr:0.00018914705190357434 tokens_per_second_per_gpu:789.2107833419218 +Step 1276 | loss:2.2139999866485596 lr:0.00018912921698745598 tokens_per_second_per_gpu:791.3288593544225 +Step 1277 | loss:2.205436944961548 lr:0.00018911136827134755 tokens_per_second_per_gpu:763.0517987858685 +Step 1278 | loss:2.278517723083496 lr:0.00018909350575801258 tokens_per_second_per_gpu:732.2146715138567 +Step 1279 | loss:2.1624622344970703 lr:0.00018907562945021672 tokens_per_second_per_gpu:728.1146023617797 +Step 1280 | loss:2.2060976028442383 lr:0.0001890577393507278 tokens_per_second_per_gpu:792.5898642501785 +Step 1281 | loss:2.168699264526367 lr:0.0001890398354623158 tokens_per_second_per_gpu:754.6136349800651 +Step 1282 | loss:2.2250235080718994 lr:0.00018902191778775272 tokens_per_second_per_gpu:766.70099492352 +Step 1283 | loss:2.1956355571746826 lr:0.00018900398632981283 tokens_per_second_per_gpu:774.4637003714033 +Step 1284 | loss:2.2218029499053955 lr:0.00018898604109127248 tokens_per_second_per_gpu:781.696013256847 +Step 1285 | loss:2.2272255420684814 lr:0.00018896808207491018 tokens_per_second_per_gpu:769.5933039280517 +Step 1286 | loss:2.227010726928711 lr:0.00018895010928350646 tokens_per_second_per_gpu:795.7217721445816 +Step 1287 | loss:2.2648680210113525 lr:0.00018893212271984416 tokens_per_second_per_gpu:784.1291535143598 +Step 1288 | loss:2.1703057289123535 lr:0.00018891412238670815 tokens_per_second_per_gpu:773.567421474284 +Step 1289 | loss:2.2501182556152344 lr:0.00018889610828688543 tokens_per_second_per_gpu:750.6126018148927 +Step 1290 | loss:2.222513198852539 lr:0.00018887808042316508 tokens_per_second_per_gpu:759.5878585579803 +Step 1291 | loss:2.1686134338378906 lr:0.0001888600387983385 tokens_per_second_per_gpu:776.5060874287681 +Step 1292 | loss:2.128702163696289 lr:0.000188841983415199 tokens_per_second_per_gpu:773.4579114096005 +Step 1293 | loss:2.173417806625366 lr:0.00018882391427654213 tokens_per_second_per_gpu:778.2369405162503 +Step 1294 | loss:2.1709461212158203 lr:0.00018880583138516563 tokens_per_second_per_gpu:759.2827288328716 +Step 1295 | loss:2.1510496139526367 lr:0.00018878773474386923 tokens_per_second_per_gpu:742.7189651316858 +Step 1296 | loss:2.129093885421753 lr:0.00018876962435545488 tokens_per_second_per_gpu:789.3040293397822 +Step 1297 | loss:2.242877960205078 lr:0.0001887515002227266 tokens_per_second_per_gpu:744.6483802333416 +Step 1298 | loss:2.1677632331848145 lr:0.0001887333623484906 tokens_per_second_per_gpu:779.9593036092782 +Step 1299 | loss:2.256413698196411 lr:0.0001887152107355552 tokens_per_second_per_gpu:774.9893954530302 +Step 1300 | loss:2.1956892013549805 lr:0.00018869704538673084 tokens_per_second_per_gpu:751.5528998814593 +Step 1301 | loss:2.271066188812256 lr:0.0001886788663048301 tokens_per_second_per_gpu:783.2813907346456 +Step 1302 | loss:2.2659664154052734 lr:0.00018866067349266761 tokens_per_second_per_gpu:786.8463912712807 +Step 1303 | loss:2.2663540840148926 lr:0.00018864246695306022 tokens_per_second_per_gpu:789.7259794156541 +Step 1304 | loss:2.2468934059143066 lr:0.00018862424668882687 tokens_per_second_per_gpu:778.2726978031382 +Step 1305 | loss:2.1872899532318115 lr:0.00018860601270278863 tokens_per_second_per_gpu:713.7044319402582 +Step 1306 | loss:2.2232680320739746 lr:0.00018858776499776868 tokens_per_second_per_gpu:759.1085414524068 +Step 1307 | loss:2.221665859222412 lr:0.00018856950357659232 tokens_per_second_per_gpu:725.1872512485475 +Step 1308 | loss:2.179903030395508 lr:0.00018855122844208707 tokens_per_second_per_gpu:778.9138269602088 +Step 1309 | loss:2.157745599746704 lr:0.0001885329395970824 tokens_per_second_per_gpu:764.0426347016188 +Step 1310 | loss:2.162334680557251 lr:0.00018851463704441004 tokens_per_second_per_gpu:740.110504566805 +Step 1311 | loss:2.195136070251465 lr:0.0001884963207869038 tokens_per_second_per_gpu:787.9047153883827 +Step 1312 | loss:2.297775983810425 lr:0.00018847799082739956 tokens_per_second_per_gpu:767.848405752772 +Step 1313 | loss:2.2375924587249756 lr:0.00018845964716873544 tokens_per_second_per_gpu:766.1567531198307 +Step 1314 | loss:2.2373814582824707 lr:0.00018844128981375158 tokens_per_second_per_gpu:758.3784446218515 +Step 1315 | loss:2.138761281967163 lr:0.00018842291876529027 tokens_per_second_per_gpu:759.4992779241252 +Step 1316 | loss:2.2094368934631348 lr:0.0001884045340261959 tokens_per_second_per_gpu:782.8067806332778 +Step 1317 | loss:2.1623246669769287 lr:0.00018838613559931506 tokens_per_second_per_gpu:764.0348552934128 +Step 1318 | loss:2.205038547515869 lr:0.00018836772348749633 tokens_per_second_per_gpu:768.7061501668887 +Step 1319 | loss:2.213677406311035 lr:0.00018834929769359054 tokens_per_second_per_gpu:778.0656114975791 +Step 1320 | loss:2.158996105194092 lr:0.0001883308582204506 tokens_per_second_per_gpu:742.7686955565786 +Step 1321 | loss:2.199734926223755 lr:0.0001883124050709314 tokens_per_second_per_gpu:760.3334506576283 +Step 1322 | loss:2.2753803730010986 lr:0.00018829393824789024 tokens_per_second_per_gpu:779.0108177647943 +Step 1323 | loss:2.206008195877075 lr:0.00018827545775418618 tokens_per_second_per_gpu:778.4472499261915 +Step 1324 | loss:2.158109426498413 lr:0.0001882569635926807 tokens_per_second_per_gpu:781.4066582252555 +Step 1325 | loss:2.244694232940674 lr:0.00018823845576623725 tokens_per_second_per_gpu:753.4246218561907 +Step 1326 | loss:2.212876081466675 lr:0.00018821993427772137 tokens_per_second_per_gpu:792.1824075790877 +Step 1327 | loss:2.246450424194336 lr:0.00018820139913000082 tokens_per_second_per_gpu:789.9825147846263 +Step 1328 | loss:2.1714324951171875 lr:0.00018818285032594538 tokens_per_second_per_gpu:745.4318947889751 +Step 1329 | loss:2.220059394836426 lr:0.00018816428786842704 tokens_per_second_per_gpu:777.4434570914187 +Step 1330 | loss:2.2527618408203125 lr:0.0001881457117603198 tokens_per_second_per_gpu:727.3630797800848 +Step 1331 | loss:2.235119342803955 lr:0.00018812712200449986 tokens_per_second_per_gpu:766.9744543020337 +Step 1332 | loss:2.2424559593200684 lr:0.00018810851860384545 tokens_per_second_per_gpu:793.8350472111877 +Step 1333 | loss:2.287656307220459 lr:0.00018808990156123697 tokens_per_second_per_gpu:777.4750214102596 +Step 1334 | loss:2.240877628326416 lr:0.00018807127087955695 tokens_per_second_per_gpu:754.4150940236278 +Step 1335 | loss:2.220655918121338 lr:0.00018805262656169 tokens_per_second_per_gpu:776.7762290687533 +Step 1336 | loss:2.231844186782837 lr:0.00018803396861052284 tokens_per_second_per_gpu:772.4655371055355 +Step 1337 | loss:2.206840991973877 lr:0.00018801529702894425 tokens_per_second_per_gpu:788.6072537130686 +Step 1338 | loss:2.2195487022399902 lr:0.00018799661181984525 tokens_per_second_per_gpu:791.1363125313186 +Step 1339 | loss:2.2951459884643555 lr:0.00018797791298611881 tokens_per_second_per_gpu:739.5518444651946 +Step 1340 | loss:2.2212939262390137 lr:0.0001879592005306602 tokens_per_second_per_gpu:779.8995137915418 +Step 1341 | loss:2.2037055492401123 lr:0.00018794047445636666 tokens_per_second_per_gpu:786.7858620266064 +Step 1342 | loss:2.2601418495178223 lr:0.0001879217347661375 tokens_per_second_per_gpu:764.6883085542909 +Step 1343 | loss:2.2431342601776123 lr:0.0001879029814628743 tokens_per_second_per_gpu:768.5869902906011 +Step 1344 | loss:2.2093379497528076 lr:0.00018788421454948056 tokens_per_second_per_gpu:764.1638059460031 +Step 1345 | loss:2.177793264389038 lr:0.0001878654340288621 tokens_per_second_per_gpu:788.5972984611552 +Step 1346 | loss:2.1702587604522705 lr:0.00018784663990392667 tokens_per_second_per_gpu:780.5075577489941 +Step 1347 | loss:2.1859169006347656 lr:0.0001878278321775842 tokens_per_second_per_gpu:773.9001638194246 +Step 1348 | loss:2.2228479385375977 lr:0.0001878090108527467 tokens_per_second_per_gpu:785.9628120820986 +Step 1349 | loss:2.2992758750915527 lr:0.0001877901759323283 tokens_per_second_per_gpu:788.4257852413331 +Step 1350 | loss:2.1717419624328613 lr:0.00018777132741924524 tokens_per_second_per_gpu:766.7790923047737 +Step 1351 | loss:2.1518073081970215 lr:0.00018775246531641587 tokens_per_second_per_gpu:779.5220293025357 +Step 1352 | loss:2.2285876274108887 lr:0.00018773358962676065 tokens_per_second_per_gpu:778.8266176766216 +Step 1353 | loss:2.204768419265747 lr:0.00018771470035320207 tokens_per_second_per_gpu:778.1248487049068 +Step 1354 | loss:2.262335777282715 lr:0.00018769579749866483 tokens_per_second_per_gpu:755.6859873625706 +Step 1355 | loss:2.2171077728271484 lr:0.00018767688106607566 tokens_per_second_per_gpu:798.7201605630147 +Step 1356 | loss:2.20253324508667 lr:0.00018765795105836342 tokens_per_second_per_gpu:756.1913696398605 +Step 1357 | loss:2.217987298965454 lr:0.0001876390074784591 tokens_per_second_per_gpu:769.3610058264936 +Step 1358 | loss:2.2179999351501465 lr:0.00018762005032929566 tokens_per_second_per_gpu:800.3021568116868 +Step 1359 | loss:2.2131848335266113 lr:0.0001876010796138084 tokens_per_second_per_gpu:745.4900002065225 +Step 1360 | loss:2.1790685653686523 lr:0.00018758209533493444 tokens_per_second_per_gpu:774.3286993597316 +Step 1361 | loss:2.197960615158081 lr:0.00018756309749561327 tokens_per_second_per_gpu:750.9236788640934 +Step 1362 | loss:2.1989951133728027 lr:0.00018754408609878627 tokens_per_second_per_gpu:764.3350870325902 +Step 1363 | loss:2.234766721725464 lr:0.000187525061147397 tokens_per_second_per_gpu:791.699782523652 +Step 1364 | loss:2.157200336456299 lr:0.00018750602264439113 tokens_per_second_per_gpu:770.8839604526612 +Step 1365 | loss:2.2222607135772705 lr:0.00018748697059271641 tokens_per_second_per_gpu:780.3786035408117 +Step 1366 | loss:2.214057445526123 lr:0.00018746790499532274 tokens_per_second_per_gpu:786.5632754382362 +Step 1367 | loss:2.180849075317383 lr:0.000187448825855162 tokens_per_second_per_gpu:770.0837600961111 +Step 1368 | loss:2.1433417797088623 lr:0.0001874297331751883 tokens_per_second_per_gpu:796.2969180834891 +Step 1369 | loss:2.241917610168457 lr:0.00018741062695835773 tokens_per_second_per_gpu:787.5800450299457 +Step 1370 | loss:2.2008159160614014 lr:0.00018739150720762857 tokens_per_second_per_gpu:798.9984872524356 +Step 1371 | loss:2.250575065612793 lr:0.00018737237392596115 tokens_per_second_per_gpu:789.4967907767302 +Step 1372 | loss:2.2566585540771484 lr:0.00018735322711631785 tokens_per_second_per_gpu:784.7784200590279 +Step 1373 | loss:2.170247793197632 lr:0.00018733406678166325 tokens_per_second_per_gpu:779.8647750359735 +Step 1374 | loss:2.223599433898926 lr:0.00018731489292496395 tokens_per_second_per_gpu:758.5563762182655 +Step 1375 | loss:2.2178151607513428 lr:0.0001872957055491887 tokens_per_second_per_gpu:778.6387510024063 +Step 1376 | loss:2.189049243927002 lr:0.00018727650465730827 tokens_per_second_per_gpu:780.0169072588491 +Step 1377 | loss:2.2907207012176514 lr:0.00018725729025229553 tokens_per_second_per_gpu:784.1787004989806 +Step 1378 | loss:2.2076711654663086 lr:0.00018723806233712548 tokens_per_second_per_gpu:792.5343759546726 +Step 1379 | loss:2.167188882827759 lr:0.0001872188209147753 tokens_per_second_per_gpu:790.7669098396864 +Step 1380 | loss:2.214000701904297 lr:0.00018719956598822402 tokens_per_second_per_gpu:775.7254910983577 +Step 1381 | loss:2.194580316543579 lr:0.00018718029756045298 tokens_per_second_per_gpu:777.9154128759413 +Step 1382 | loss:2.278698682785034 lr:0.00018716101563444557 tokens_per_second_per_gpu:778.1880501952779 +Step 1383 | loss:2.1874446868896484 lr:0.0001871417202131872 tokens_per_second_per_gpu:779.5251704850044 +Step 1384 | loss:2.2307944297790527 lr:0.00018712241129966532 tokens_per_second_per_gpu:774.8835894120898 +Step 1385 | loss:2.2113170623779297 lr:0.0001871030888968697 tokens_per_second_per_gpu:782.0822470618135 +Step 1386 | loss:2.170663356781006 lr:0.00018708375300779197 tokens_per_second_per_gpu:764.0661255616299 +Step 1387 | loss:2.20688796043396 lr:0.00018706440363542591 tokens_per_second_per_gpu:806.2514651580093 +Step 1388 | loss:2.23665714263916 lr:0.00018704504078276749 tokens_per_second_per_gpu:743.940752107419 +Step 1389 | loss:2.2144086360931396 lr:0.0001870256644528146 tokens_per_second_per_gpu:743.0402071316009 +Step 1390 | loss:2.212688446044922 lr:0.00018700627464856738 tokens_per_second_per_gpu:721.9798193668527 +Step 1391 | loss:2.2150444984436035 lr:0.0001869868713730279 tokens_per_second_per_gpu:782.5265782119017 +Step 1392 | loss:2.2453293800354004 lr:0.00018696745462920046 tokens_per_second_per_gpu:774.2389560425471 +Step 1393 | loss:2.223686695098877 lr:0.00018694802442009132 tokens_per_second_per_gpu:779.5434138723069 +Step 1394 | loss:2.158726453781128 lr:0.0001869285807487089 tokens_per_second_per_gpu:760.5824362682823 +Step 1395 | loss:2.253784418106079 lr:0.00018690912361806375 tokens_per_second_per_gpu:747.8323046363183 +Step 1396 | loss:2.1474952697753906 lr:0.00018688965303116837 tokens_per_second_per_gpu:768.7311003952507 +Step 1397 | loss:2.1936683654785156 lr:0.00018687016899103745 tokens_per_second_per_gpu:765.7375813036949 +Step 1398 | loss:2.177457332611084 lr:0.0001868506715006877 tokens_per_second_per_gpu:770.6264239577608 +Step 1399 | loss:2.2393224239349365 lr:0.00018683116056313797 tokens_per_second_per_gpu:794.9538793545522 +Step 1400 | loss:2.2286577224731445 lr:0.00018681163618140917 tokens_per_second_per_gpu:774.4853700694639 +Step 1401 | loss:2.1528611183166504 lr:0.00018679209835852426 tokens_per_second_per_gpu:767.696404628632 +Step 1402 | loss:2.1605172157287598 lr:0.0001867725470975083 tokens_per_second_per_gpu:774.3909798454316 +Step 1403 | loss:2.2016730308532715 lr:0.00018675298240138845 tokens_per_second_per_gpu:779.0107646234841 +Step 1404 | loss:2.2602312564849854 lr:0.00018673340427319396 tokens_per_second_per_gpu:755.9243763623551 +Step 1405 | loss:2.2358450889587402 lr:0.00018671381271595608 tokens_per_second_per_gpu:761.9704541280068 +Step 1406 | loss:2.197415351867676 lr:0.00018669420773270828 tokens_per_second_per_gpu:760.5201483005185 +Step 1407 | loss:2.2042925357818604 lr:0.00018667458932648595 tokens_per_second_per_gpu:768.1040493153143 +Step 1408 | loss:2.1793899536132812 lr:0.00018665495750032663 tokens_per_second_per_gpu:752.4730146365648 +Step 1409 | loss:2.2106168270111084 lr:0.00018663531225727003 tokens_per_second_per_gpu:782.6954382570021 +Step 1410 | loss:2.232268810272217 lr:0.00018661565360035773 tokens_per_second_per_gpu:763.1105664425853 +Step 1411 | loss:2.2016096115112305 lr:0.0001865959815326336 tokens_per_second_per_gpu:782.1065302454044 +Step 1412 | loss:2.158966541290283 lr:0.0001865762960571434 tokens_per_second_per_gpu:766.9472556545936 +Step 1413 | loss:2.240614891052246 lr:0.00018655659717693517 tokens_per_second_per_gpu:789.240957079508 +Step 1414 | loss:2.249345541000366 lr:0.00018653688489505882 tokens_per_second_per_gpu:772.5401230559032 +Step 1415 | loss:2.2118186950683594 lr:0.00018651715921456647 tokens_per_second_per_gpu:753.3888940369131 +Step 1416 | loss:2.2427501678466797 lr:0.00018649742013851226 tokens_per_second_per_gpu:793.7594385619417 +Step 1417 | loss:2.1794283390045166 lr:0.00018647766766995242 tokens_per_second_per_gpu:781.1694943684151 +Step 1418 | loss:2.187227249145508 lr:0.00018645790181194522 tokens_per_second_per_gpu:780.1517903929916 +Step 1419 | loss:2.150850534439087 lr:0.0001864381225675511 tokens_per_second_per_gpu:792.931564328616 +Step 1420 | loss:2.209444522857666 lr:0.00018641832993983247 tokens_per_second_per_gpu:766.3906707875187 +Step 1421 | loss:2.221363067626953 lr:0.0001863985239318538 tokens_per_second_per_gpu:794.0694556698252 +Step 1422 | loss:2.1930065155029297 lr:0.00018637870454668175 tokens_per_second_per_gpu:738.8715335207191 +Step 1423 | loss:2.1092641353607178 lr:0.00018635887178738495 tokens_per_second_per_gpu:798.4764295999138 +Step 1424 | loss:2.1861116886138916 lr:0.00018633902565703413 tokens_per_second_per_gpu:785.0277434783745 +Step 1425 | loss:2.1968226432800293 lr:0.00018631916615870214 tokens_per_second_per_gpu:775.9851516880948 +Step 1426 | loss:2.190917491912842 lr:0.00018629929329546375 tokens_per_second_per_gpu:790.5822978479188 +Step 1427 | loss:2.1346840858459473 lr:0.000186279407070396 tokens_per_second_per_gpu:764.1586446595352 +Step 1428 | loss:2.143122673034668 lr:0.00018625950748657783 tokens_per_second_per_gpu:771.3038519466835 +Step 1429 | loss:2.181483268737793 lr:0.00018623959454709037 tokens_per_second_per_gpu:783.907390856788 +Step 1430 | loss:2.179826021194458 lr:0.00018621966825501675 tokens_per_second_per_gpu:763.7999668233225 +Step 1431 | loss:2.2472708225250244 lr:0.00018619972861344216 tokens_per_second_per_gpu:779.0133539968626 +Step 1432 | loss:2.138807535171509 lr:0.00018617977562545389 tokens_per_second_per_gpu:795.9433244310216 +Step 1433 | loss:2.199580430984497 lr:0.0001861598092941413 tokens_per_second_per_gpu:791.1039214561873 +Step 1434 | loss:2.22875714302063 lr:0.0001861398296225958 tokens_per_second_per_gpu:750.3699481432498 +Step 1435 | loss:2.148664951324463 lr:0.00018611983661391082 tokens_per_second_per_gpu:792.3779184482836 +Step 1436 | loss:2.121870279312134 lr:0.000186099830271182 tokens_per_second_per_gpu:781.1420798070743 +Step 1437 | loss:2.1707301139831543 lr:0.0001860798105975069 tokens_per_second_per_gpu:754.7927704222815 +Step 1438 | loss:2.213902711868286 lr:0.00018605977759598514 tokens_per_second_per_gpu:755.1149515868517 +Step 1439 | loss:2.2896065711975098 lr:0.00018603973126971854 tokens_per_second_per_gpu:784.5997000071462 +Step 1440 | loss:2.189748764038086 lr:0.00018601967162181081 tokens_per_second_per_gpu:781.8163189680774 +Step 1441 | loss:2.162914991378784 lr:0.00018599959865536788 tokens_per_second_per_gpu:785.6931807448314 +Step 1442 | loss:2.222165107727051 lr:0.00018597951237349768 tokens_per_second_per_gpu:783.3577989019417 +Step 1443 | loss:2.1993539333343506 lr:0.00018595941277931016 tokens_per_second_per_gpu:775.3582419405707 +Step 1444 | loss:2.2116003036499023 lr:0.00018593929987591735 tokens_per_second_per_gpu:769.071918110841 +Step 1445 | loss:2.2229669094085693 lr:0.00018591917366643339 tokens_per_second_per_gpu:785.280222947851 +Step 1446 | loss:2.1912872791290283 lr:0.00018589903415397444 tokens_per_second_per_gpu:753.9916730661826 +Step 1447 | loss:2.223947048187256 lr:0.00018587888134165872 tokens_per_second_per_gpu:774.1937077668299 +Step 1448 | loss:2.2080330848693848 lr:0.00018585871523260652 tokens_per_second_per_gpu:767.0220768372957 +Step 1449 | loss:2.17447829246521 lr:0.00018583853582994014 tokens_per_second_per_gpu:782.7751595104663 +Step 1450 | loss:2.207200527191162 lr:0.00018581834313678407 tokens_per_second_per_gpu:768.474364804956 +Step 1451 | loss:2.1596415042877197 lr:0.0001857981371562647 tokens_per_second_per_gpu:799.2466542406883 +Step 1452 | loss:2.262547492980957 lr:0.0001857779178915106 tokens_per_second_per_gpu:783.1174850772669 +Step 1453 | loss:2.1754517555236816 lr:0.00018575768534565232 tokens_per_second_per_gpu:788.1010327646751 +Step 1454 | loss:2.24054217338562 lr:0.00018573743952182245 tokens_per_second_per_gpu:775.8405774866221 +Step 1455 | loss:2.237025737762451 lr:0.00018571718042315576 tokens_per_second_per_gpu:777.7951233495718 +Step 1456 | loss:2.264125347137451 lr:0.00018569690805278892 tokens_per_second_per_gpu:747.1435932358709 +Step 1457 | loss:2.1389708518981934 lr:0.00018567662241386073 tokens_per_second_per_gpu:762.4462020061264 +Step 1458 | loss:2.1409945487976074 lr:0.0001856563235095121 tokens_per_second_per_gpu:778.0825619093225 +Step 1459 | loss:2.1967737674713135 lr:0.0001856360113428859 tokens_per_second_per_gpu:726.7704366109889 +Step 1460 | loss:2.2012970447540283 lr:0.00018561568591712706 tokens_per_second_per_gpu:775.8005356417009 +Step 1461 | loss:2.2173421382904053 lr:0.00018559534723538263 tokens_per_second_per_gpu:774.9537726674574 +Step 1462 | loss:2.2206037044525146 lr:0.0001855749953008017 tokens_per_second_per_gpu:768.3458867350827 +Step 1463 | loss:2.153799295425415 lr:0.0001855546301165353 tokens_per_second_per_gpu:785.9603149040031 +Step 1464 | loss:2.197273015975952 lr:0.00018553425168573665 tokens_per_second_per_gpu:779.7080954828441 +Step 1465 | loss:2.171505928039551 lr:0.000185513860011561 tokens_per_second_per_gpu:759.7847069760232 +Step 1466 | loss:2.194828987121582 lr:0.00018549345509716558 tokens_per_second_per_gpu:747.2345974909289 +Step 1467 | loss:2.1843929290771484 lr:0.0001854730369457097 tokens_per_second_per_gpu:788.3280234329784 +Step 1468 | loss:2.19692063331604 lr:0.00018545260556035475 tokens_per_second_per_gpu:797.9180476306313 +Step 1469 | loss:2.142072916030884 lr:0.00018543216094426412 tokens_per_second_per_gpu:770.0920254065776 +Step 1470 | loss:2.172682285308838 lr:0.00018541170310060328 tokens_per_second_per_gpu:791.4525018282759 +Step 1471 | loss:2.1923906803131104 lr:0.0001853912320325398 tokens_per_second_per_gpu:749.2158251090134 +Step 1472 | loss:2.2233755588531494 lr:0.0001853707477432432 tokens_per_second_per_gpu:773.9242549217929 +Step 1473 | loss:2.150635242462158 lr:0.00018535025023588508 tokens_per_second_per_gpu:773.1388726949488 +Step 1474 | loss:2.2458620071411133 lr:0.00018532973951363907 tokens_per_second_per_gpu:782.9219402544189 +Step 1475 | loss:2.192455530166626 lr:0.00018530921557968096 tokens_per_second_per_gpu:786.1098008117367 +Step 1476 | loss:2.2244386672973633 lr:0.00018528867843718843 tokens_per_second_per_gpu:776.2299537987166 +Step 1477 | loss:2.2271804809570312 lr:0.00018526812808934126 tokens_per_second_per_gpu:744.5712562882104 +Step 1478 | loss:2.2156357765197754 lr:0.00018524756453932133 tokens_per_second_per_gpu:773.4519044423249 +Step 1479 | loss:2.1953179836273193 lr:0.00018522698779031247 tokens_per_second_per_gpu:779.4007264553943 +Step 1480 | loss:2.1423041820526123 lr:0.00018520639784550067 tokens_per_second_per_gpu:771.2783339851944 +Step 1481 | loss:2.1920199394226074 lr:0.00018518579470807385 tokens_per_second_per_gpu:784.2395522521451 +Step 1482 | loss:2.209103584289551 lr:0.00018516517838122203 tokens_per_second_per_gpu:762.6975865323468 +Step 1483 | loss:2.1259541511535645 lr:0.0001851445488681373 tokens_per_second_per_gpu:784.5062255725059 +Step 1484 | loss:2.1816279888153076 lr:0.00018512390617201366 tokens_per_second_per_gpu:773.3150608580107 +Step 1485 | loss:2.2265305519104004 lr:0.00018510325029604734 tokens_per_second_per_gpu:789.0065549493211 +Step 1486 | loss:2.1589419841766357 lr:0.00018508258124343648 tokens_per_second_per_gpu:798.724513061067 +Step 1487 | loss:2.2211222648620605 lr:0.00018506189901738127 tokens_per_second_per_gpu:789.4521386756895 +Step 1488 | loss:2.2016441822052 lr:0.000185041203621084 tokens_per_second_per_gpu:768.1180243581023 +Step 1489 | loss:2.1709401607513428 lr:0.00018502049505774893 tokens_per_second_per_gpu:754.3959405872331 +Step 1490 | loss:2.183195114135742 lr:0.00018499977333058247 tokens_per_second_per_gpu:763.9358756771251 +Step 1491 | loss:2.1783525943756104 lr:0.0001849790384427929 tokens_per_second_per_gpu:797.9001569547333 +Step 1492 | loss:2.187178373336792 lr:0.0001849582903975907 tokens_per_second_per_gpu:754.090540444503 +Step 1493 | loss:2.2119452953338623 lr:0.0001849375291981883 tokens_per_second_per_gpu:775.8070355570336 +Step 1494 | loss:2.2052206993103027 lr:0.00018491675484780013 tokens_per_second_per_gpu:785.0437997086718 +Step 1495 | loss:2.2211215496063232 lr:0.00018489596734964274 tokens_per_second_per_gpu:800.7964760031081 +Step 1496 | loss:2.188875675201416 lr:0.0001848751667069347 tokens_per_second_per_gpu:766.1933577174493 +Step 1497 | loss:2.2376511096954346 lr:0.0001848543529228966 tokens_per_second_per_gpu:740.4118422885639 +Step 1498 | loss:2.236269950866699 lr:0.0001848335260007511 tokens_per_second_per_gpu:783.5995413648894 +Step 1499 | loss:2.1426877975463867 lr:0.00018481268594372274 tokens_per_second_per_gpu:747.0219212307077 +Step 1500 | loss:2.227449893951416 lr:0.0001847918327550383 tokens_per_second_per_gpu:777.7641978913949 +Step 1501 | loss:2.2081446647644043 lr:0.00018477096643792652 tokens_per_second_per_gpu:766.047905177081 +Step 1502 | loss:2.1831419467926025 lr:0.0001847500869956181 tokens_per_second_per_gpu:742.5964174310798 +Step 1503 | loss:2.144792079925537 lr:0.0001847291944313459 tokens_per_second_per_gpu:744.7638953187027 +Step 1504 | loss:2.2205731868743896 lr:0.0001847082887483447 tokens_per_second_per_gpu:748.463738356644 +Step 1505 | loss:2.217041254043579 lr:0.00018468736994985135 tokens_per_second_per_gpu:780.8828317293065 +Step 1506 | loss:2.1662943363189697 lr:0.00018466643803910471 tokens_per_second_per_gpu:783.5314290531544 +Step 1507 | loss:2.228966474533081 lr:0.0001846454930193458 tokens_per_second_per_gpu:773.7023117039471 +Step 1508 | loss:2.171210527420044 lr:0.0001846245348938174 tokens_per_second_per_gpu:772.0252560809521 +Step 1509 | loss:2.178079843521118 lr:0.00018460356366576462 tokens_per_second_per_gpu:762.3555613929161 +Step 1510 | loss:2.1634509563446045 lr:0.00018458257933843446 tokens_per_second_per_gpu:748.3976821793987 +Step 1511 | loss:2.262467384338379 lr:0.00018456158191507586 tokens_per_second_per_gpu:762.5686906900352 +Step 1512 | loss:2.1049485206604004 lr:0.00018454057139893993 tokens_per_second_per_gpu:750.4768701149942 +Step 1513 | loss:2.204519510269165 lr:0.00018451954779327974 tokens_per_second_per_gpu:765.6447575836587 +Step 1514 | loss:2.135538339614868 lr:0.0001844985111013504 tokens_per_second_per_gpu:768.3818748991746 +Step 1515 | loss:2.135261297225952 lr:0.0001844774613264091 tokens_per_second_per_gpu:794.4836801518622 +Step 1516 | loss:2.1699790954589844 lr:0.00018445639847171493 tokens_per_second_per_gpu:785.6479911021582 +Step 1517 | loss:2.1594669818878174 lr:0.0001844353225405291 tokens_per_second_per_gpu:768.4241094515215 +Step 1518 | loss:2.20957088470459 lr:0.00018441423353611486 tokens_per_second_per_gpu:745.4652383629236 +Step 1519 | loss:2.208277463912964 lr:0.0001843931314617374 tokens_per_second_per_gpu:775.3720913423 +Step 1520 | loss:2.2146787643432617 lr:0.000184372016320664 tokens_per_second_per_gpu:779.8644714601729 +Step 1521 | loss:2.1545629501342773 lr:0.00018435088811616398 tokens_per_second_per_gpu:787.9555984328756 +Step 1522 | loss:2.246565341949463 lr:0.00018432974685150862 tokens_per_second_per_gpu:781.5289047262497 +Step 1523 | loss:2.2493529319763184 lr:0.00018430859252997119 tokens_per_second_per_gpu:787.9724183247674 +Step 1524 | loss:2.1225452423095703 lr:0.00018428742515482713 tokens_per_second_per_gpu:756.055742596189 +Step 1525 | loss:2.252362012863159 lr:0.00018426624472935377 tokens_per_second_per_gpu:756.7789684824561 +Step 1526 | loss:2.198676109313965 lr:0.00018424505125683047 tokens_per_second_per_gpu:774.3824803120972 +Step 1527 | loss:2.189258098602295 lr:0.0001842238447405387 tokens_per_second_per_gpu:769.4136519589684 +Step 1528 | loss:2.199772357940674 lr:0.0001842026251837619 tokens_per_second_per_gpu:744.1202868198252 +Step 1529 | loss:2.1830525398254395 lr:0.00018418139258978547 tokens_per_second_per_gpu:782.7554075925058 +Step 1530 | loss:2.167212963104248 lr:0.0001841601469618969 tokens_per_second_per_gpu:799.1075470649243 +Step 1531 | loss:2.1534910202026367 lr:0.00018413888830338566 tokens_per_second_per_gpu:764.6760754946683 +Step 1532 | loss:2.1606242656707764 lr:0.0001841176166175433 tokens_per_second_per_gpu:780.9248753568481 +Step 1533 | loss:2.2085955142974854 lr:0.00018409633190766332 tokens_per_second_per_gpu:781.7970933435921 +Step 1534 | loss:2.1857824325561523 lr:0.0001840750341770412 tokens_per_second_per_gpu:766.8176620553395 +Step 1535 | loss:2.1627607345581055 lr:0.00018405372342897462 tokens_per_second_per_gpu:742.3812667029626 +Step 1536 | loss:2.182384967803955 lr:0.00018403239966676305 tokens_per_second_per_gpu:784.1233522632642 +Step 1537 | loss:2.1152775287628174 lr:0.00018401106289370807 tokens_per_second_per_gpu:745.0227849523526 +Step 1538 | loss:2.1586852073669434 lr:0.00018398971311311336 tokens_per_second_per_gpu:752.2237534935726 +Step 1539 | loss:2.199087381362915 lr:0.0001839683503282845 tokens_per_second_per_gpu:791.8906834318495 +Step 1540 | loss:2.144031047821045 lr:0.00018394697454252908 tokens_per_second_per_gpu:782.6158091602814 +Step 1541 | loss:2.1580896377563477 lr:0.00018392558575915677 tokens_per_second_per_gpu:766.5596844507011 +Step 1542 | loss:2.2192280292510986 lr:0.0001839041839814792 tokens_per_second_per_gpu:769.1018951812343 +Step 1543 | loss:2.2664220333099365 lr:0.00018388276921281008 tokens_per_second_per_gpu:768.427904537229 +Step 1544 | loss:2.2211854457855225 lr:0.00018386134145646503 tokens_per_second_per_gpu:789.5873642609124 +Step 1545 | loss:2.1649248600006104 lr:0.0001838399007157618 tokens_per_second_per_gpu:770.5147091205298 +Step 1546 | loss:2.1880035400390625 lr:0.00018381844699402 tokens_per_second_per_gpu:774.918828782411 +Step 1547 | loss:2.1748385429382324 lr:0.00018379698029456144 tokens_per_second_per_gpu:734.2983893336544 +Step 1548 | loss:2.216407299041748 lr:0.00018377550062070977 tokens_per_second_per_gpu:791.0215200608203 +Step 1549 | loss:2.166769504547119 lr:0.00018375400797579074 tokens_per_second_per_gpu:793.495374700035 +Step 1550 | loss:2.130742073059082 lr:0.00018373250236313206 tokens_per_second_per_gpu:796.089318161683 +Step 1551 | loss:2.235206127166748 lr:0.0001837109837860635 tokens_per_second_per_gpu:751.7581483103797 +Step 1552 | loss:2.1337077617645264 lr:0.0001836894522479168 tokens_per_second_per_gpu:776.1800593831375 +Step 1553 | loss:2.2141377925872803 lr:0.00018366790775202566 tokens_per_second_per_gpu:779.4453598919638 +Step 1554 | loss:2.2555320262908936 lr:0.00018364635030172595 tokens_per_second_per_gpu:801.8794365003719 +Step 1555 | loss:2.220393657684326 lr:0.00018362477990035536 tokens_per_second_per_gpu:788.2295587137596 +Step 1556 | loss:2.215911626815796 lr:0.0001836031965512537 tokens_per_second_per_gpu:768.9679452950056 +Step 1557 | loss:2.2158799171447754 lr:0.0001835816002577627 tokens_per_second_per_gpu:773.2756239665622 +Step 1558 | loss:2.1161041259765625 lr:0.00018355999102322615 tokens_per_second_per_gpu:745.6237959111819 +Step 1559 | loss:2.1359620094299316 lr:0.0001835383688509899 tokens_per_second_per_gpu:780.8317805245537 +Step 1560 | loss:2.1850602626800537 lr:0.00018351673374440169 tokens_per_second_per_gpu:745.2961804114377 +Step 1561 | loss:2.157956123352051 lr:0.00018349508570681132 tokens_per_second_per_gpu:777.3024770776728 +Step 1562 | loss:2.22577166557312 lr:0.00018347342474157055 tokens_per_second_per_gpu:755.0248829510433 +Step 1563 | loss:2.2135443687438965 lr:0.00018345175085203322 tokens_per_second_per_gpu:781.0968584800979 +Step 1564 | loss:2.2126998901367188 lr:0.00018343006404155512 tokens_per_second_per_gpu:795.6022764062247 +Step 1565 | loss:2.248084783554077 lr:0.000183408364313494 tokens_per_second_per_gpu:794.489808194882 +Step 1566 | loss:2.1970386505126953 lr:0.0001833866516712097 tokens_per_second_per_gpu:773.0581907387473 +Step 1567 | loss:2.173258066177368 lr:0.00018336492611806406 tokens_per_second_per_gpu:785.0866302606951 +Step 1568 | loss:2.1970205307006836 lr:0.00018334318765742078 tokens_per_second_per_gpu:790.4551370354033 +Step 1569 | loss:2.1131093502044678 lr:0.0001833214362926457 tokens_per_second_per_gpu:777.0099274821233 +Step 1570 | loss:2.133509635925293 lr:0.00018329967202710662 tokens_per_second_per_gpu:781.5826824224982 +Step 1571 | loss:2.2173967361450195 lr:0.0001832778948641733 tokens_per_second_per_gpu:749.8100888046492 +Step 1572 | loss:2.1940691471099854 lr:0.0001832561048072176 tokens_per_second_per_gpu:776.7100866760551 +Step 1573 | loss:2.1391115188598633 lr:0.00018323430185961318 tokens_per_second_per_gpu:739.6223745374025 +Step 1574 | loss:2.236342668533325 lr:0.0001832124860247359 tokens_per_second_per_gpu:790.9934589628705 +Step 1575 | loss:2.1748032569885254 lr:0.00018319065730596352 tokens_per_second_per_gpu:770.8989195489369 +Step 1576 | loss:2.1794588565826416 lr:0.0001831688157066758 tokens_per_second_per_gpu:795.604622752417 +Step 1577 | loss:2.1552114486694336 lr:0.00018314696123025454 tokens_per_second_per_gpu:779.623202562279 +Step 1578 | loss:2.210597038269043 lr:0.00018312509388008344 tokens_per_second_per_gpu:759.2387436131786 +Step 1579 | loss:2.125028133392334 lr:0.00018310321365954828 tokens_per_second_per_gpu:785.349406411067 +Step 1580 | loss:2.2063159942626953 lr:0.0001830813205720368 tokens_per_second_per_gpu:788.2706712445942 +Step 1581 | loss:2.215954065322876 lr:0.0001830594146209387 tokens_per_second_per_gpu:787.0399032742079 +Step 1582 | loss:2.1886656284332275 lr:0.00018303749580964577 tokens_per_second_per_gpu:753.838326331058 +Step 1583 | loss:2.2022836208343506 lr:0.0001830155641415517 tokens_per_second_per_gpu:738.0102512722167 +Step 1584 | loss:2.1981377601623535 lr:0.00018299361962005218 tokens_per_second_per_gpu:768.7895226822071 +Step 1585 | loss:2.1909139156341553 lr:0.0001829716622485449 tokens_per_second_per_gpu:786.9525432404761 +Step 1586 | loss:2.2209439277648926 lr:0.0001829496920304296 tokens_per_second_per_gpu:786.3798761912434 +Step 1587 | loss:2.147092342376709 lr:0.00018292770896910794 tokens_per_second_per_gpu:793.0738884622497 +Step 1588 | loss:2.1833951473236084 lr:0.00018290571306798354 tokens_per_second_per_gpu:769.7487250114868 +Step 1589 | loss:2.1828746795654297 lr:0.0001828837043304621 tokens_per_second_per_gpu:772.0915523385643 +Step 1590 | loss:2.218766212463379 lr:0.00018286168275995123 tokens_per_second_per_gpu:767.0944161003307 +Step 1591 | loss:2.1285243034362793 lr:0.00018283964835986058 tokens_per_second_per_gpu:759.4664011425541 +Step 1592 | loss:2.2002315521240234 lr:0.00018281760113360177 tokens_per_second_per_gpu:777.0119616659175 +Step 1593 | loss:2.2170002460479736 lr:0.00018279554108458835 tokens_per_second_per_gpu:775.6494331904746 +Step 1594 | loss:2.253387212753296 lr:0.000182773468216236 tokens_per_second_per_gpu:765.5672073948483 +Step 1595 | loss:2.1981823444366455 lr:0.00018275138253196217 tokens_per_second_per_gpu:784.373828974027 +Step 1596 | loss:2.192487955093384 lr:0.00018272928403518653 tokens_per_second_per_gpu:801.0071114776028 +Step 1597 | loss:2.148275852203369 lr:0.00018270717272933056 tokens_per_second_per_gpu:789.327974939989 +Step 1598 | loss:2.187516450881958 lr:0.00018268504861781776 tokens_per_second_per_gpu:782.4177259526025 +Step 1599 | loss:2.2030210494995117 lr:0.0001826629117040737 tokens_per_second_per_gpu:786.1494612440325 +Step 1600 | loss:2.181056022644043 lr:0.0001826407619915258 tokens_per_second_per_gpu:787.5413587767533 +Step 1601 | loss:2.226638078689575 lr:0.00018261859948360355 tokens_per_second_per_gpu:780.2345370929987 +Step 1602 | loss:2.2350525856018066 lr:0.00018259642418373844 tokens_per_second_per_gpu:739.4783287289016 +Step 1603 | loss:2.213266611099243 lr:0.00018257423609536384 tokens_per_second_per_gpu:772.5723105546284 +Step 1604 | loss:2.230494737625122 lr:0.00018255203522191517 tokens_per_second_per_gpu:761.4611671769721 +Step 1605 | loss:2.1601569652557373 lr:0.00018252982156682988 tokens_per_second_per_gpu:777.3375168450951 +Step 1606 | loss:2.1396851539611816 lr:0.00018250759513354728 tokens_per_second_per_gpu:781.5569281416925 +Step 1607 | loss:2.153315544128418 lr:0.0001824853559255087 tokens_per_second_per_gpu:766.7684339748346 +Step 1608 | loss:2.154634714126587 lr:0.0001824631039461575 tokens_per_second_per_gpu:791.9997789415354 +Step 1609 | loss:2.1984856128692627 lr:0.00018244083919893904 tokens_per_second_per_gpu:778.3485190516881 +Step 1610 | loss:2.1812331676483154 lr:0.00018241856168730046 tokens_per_second_per_gpu:796.9370614919794 +Step 1611 | loss:2.190495014190674 lr:0.00018239627141469113 tokens_per_second_per_gpu:798.6327152327135 +Step 1612 | loss:2.1589393615722656 lr:0.00018237396838456226 tokens_per_second_per_gpu:765.3263550325104 +Step 1613 | loss:2.172886848449707 lr:0.000182351652600367 tokens_per_second_per_gpu:774.5660417549623 +Step 1614 | loss:2.1769609451293945 lr:0.00018232932406556064 tokens_per_second_per_gpu:756.2551812098365 +Step 1615 | loss:2.130687713623047 lr:0.0001823069827836002 tokens_per_second_per_gpu:777.2273079788429 +Step 1616 | loss:2.20511531829834 lr:0.00018228462875794488 tokens_per_second_per_gpu:792.4476482099419 +Step 1617 | loss:2.2044129371643066 lr:0.0001822622619920558 tokens_per_second_per_gpu:762.0757090188447 +Step 1618 | loss:2.167173385620117 lr:0.000182239882489396 tokens_per_second_per_gpu:750.0868441509051 +Step 1619 | loss:2.209676742553711 lr:0.00018221749025343058 tokens_per_second_per_gpu:758.4103828063568 +Step 1620 | loss:2.1945998668670654 lr:0.00018219508528762648 tokens_per_second_per_gpu:757.5868085633175 +Step 1621 | loss:2.164459228515625 lr:0.00018217266759545275 tokens_per_second_per_gpu:800.9977107438707 +Step 1622 | loss:2.2100424766540527 lr:0.0001821502371803803 tokens_per_second_per_gpu:762.8859359407667 +Step 1623 | loss:2.109588623046875 lr:0.0001821277940458821 tokens_per_second_per_gpu:787.6926780352934 +Step 1624 | loss:2.21860408782959 lr:0.00018210533819543306 tokens_per_second_per_gpu:802.6413756608832 +Step 1625 | loss:2.147778034210205 lr:0.00018208286963251 tokens_per_second_per_gpu:775.4526592890678 +Step 1626 | loss:2.202235460281372 lr:0.00018206038836059176 tokens_per_second_per_gpu:779.4965431181596 +Step 1627 | loss:2.2087807655334473 lr:0.00018203789438315921 tokens_per_second_per_gpu:772.1253821814364 +Step 1628 | loss:2.1118483543395996 lr:0.00018201538770369507 tokens_per_second_per_gpu:764.1813150869676 +Step 1629 | loss:2.2223007678985596 lr:0.00018199286832568405 tokens_per_second_per_gpu:767.476966335136 +Step 1630 | loss:2.1668856143951416 lr:0.00018197033625261293 tokens_per_second_per_gpu:787.7016818747684 +Step 1631 | loss:2.2012851238250732 lr:0.0001819477914879703 tokens_per_second_per_gpu:769.4620068375646 +Step 1632 | loss:2.151322364807129 lr:0.00018192523403524685 tokens_per_second_per_gpu:794.5720633544727 +Step 1633 | loss:2.1875011920928955 lr:0.00018190266389793514 tokens_per_second_per_gpu:771.6210522339878 +Step 1634 | loss:2.1491289138793945 lr:0.0001818800810795298 tokens_per_second_per_gpu:784.8933053074198 +Step 1635 | loss:2.1783015727996826 lr:0.00018185748558352728 tokens_per_second_per_gpu:752.7907385647238 +Step 1636 | loss:2.2079131603240967 lr:0.00018183487741342612 tokens_per_second_per_gpu:757.7706484164636 +Step 1637 | loss:2.1792678833007812 lr:0.00018181225657272671 tokens_per_second_per_gpu:773.937414298653 +Step 1638 | loss:2.179708480834961 lr:0.00018178962306493153 tokens_per_second_per_gpu:803.4800647991686 +Step 1639 | loss:2.2548329830169678 lr:0.00018176697689354493 tokens_per_second_per_gpu:764.9727187252366 +Step 1640 | loss:2.1622793674468994 lr:0.00018174431806207325 tokens_per_second_per_gpu:761.4439686766243 +Step 1641 | loss:2.2061045169830322 lr:0.00018172164657402477 tokens_per_second_per_gpu:774.1047315139804 +Step 1642 | loss:2.1528046131134033 lr:0.00018169896243290978 tokens_per_second_per_gpu:767.365468219282 +Step 1643 | loss:2.210585117340088 lr:0.00018167626564224044 tokens_per_second_per_gpu:770.5558110047723 +Step 1644 | loss:2.2134432792663574 lr:0.00018165355620553098 tokens_per_second_per_gpu:726.6112712699754 +Step 1645 | loss:2.1635806560516357 lr:0.0001816308341262975 tokens_per_second_per_gpu:776.600614886746 +Step 1646 | loss:2.171525478363037 lr:0.00018160809940805808 tokens_per_second_per_gpu:793.7679933201294 +Step 1647 | loss:2.126110792160034 lr:0.0001815853520543328 tokens_per_second_per_gpu:757.1213346930809 +Step 1648 | loss:2.128884792327881 lr:0.00018156259206864362 tokens_per_second_per_gpu:759.7381338622554 +Step 1649 | loss:2.1445703506469727 lr:0.0001815398194545145 tokens_per_second_per_gpu:784.6129467322061 +Step 1650 | loss:2.134953498840332 lr:0.0001815170342154714 tokens_per_second_per_gpu:804.4024770411313 +Step 1651 | loss:2.1532809734344482 lr:0.00018149423635504218 tokens_per_second_per_gpu:751.7616869661384 +Step 1652 | loss:2.142611503601074 lr:0.0001814714258767566 tokens_per_second_per_gpu:783.6294073657439 +Step 1653 | loss:2.205109119415283 lr:0.00018144860278414648 tokens_per_second_per_gpu:799.6469579257315 +Step 1654 | loss:2.16104793548584 lr:0.00018142576708074558 tokens_per_second_per_gpu:760.6336582938051 +Step 1655 | loss:2.2256081104278564 lr:0.0001814029187700895 tokens_per_second_per_gpu:782.5369748436556 +Step 1656 | loss:2.1310839653015137 lr:0.00018138005785571593 tokens_per_second_per_gpu:750.5659224743052 +Step 1657 | loss:2.1730029582977295 lr:0.00018135718434116448 tokens_per_second_per_gpu:785.9849745919073 +Step 1658 | loss:2.1807985305786133 lr:0.0001813342982299766 tokens_per_second_per_gpu:787.8424574218883 +Step 1659 | loss:2.085780620574951 lr:0.00018131139952569584 tokens_per_second_per_gpu:784.5366573054029 +Step 1660 | loss:2.276970624923706 lr:0.00018128848823186763 tokens_per_second_per_gpu:761.1563424189861 +Step 1661 | loss:2.204864025115967 lr:0.00018126556435203934 tokens_per_second_per_gpu:785.1020283121877 +Step 1662 | loss:2.151837110519409 lr:0.0001812426278897603 tokens_per_second_per_gpu:770.6741300007861 +Step 1663 | loss:2.1903886795043945 lr:0.0001812196788485818 tokens_per_second_per_gpu:770.2914767893828 +Step 1664 | loss:2.1899197101593018 lr:0.00018119671723205706 tokens_per_second_per_gpu:778.7866335994971 +Step 1665 | loss:2.1770143508911133 lr:0.00018117374304374128 tokens_per_second_per_gpu:772.0166921920974 +Step 1666 | loss:2.2431154251098633 lr:0.00018115075628719155 tokens_per_second_per_gpu:754.4337077721433 +Step 1667 | loss:2.163694143295288 lr:0.000181127756965967 tokens_per_second_per_gpu:777.7841541422902 +Step 1668 | loss:2.173945665359497 lr:0.00018110474508362855 tokens_per_second_per_gpu:764.9702473759226 +Step 1669 | loss:2.2002975940704346 lr:0.00018108172064373922 tokens_per_second_per_gpu:768.142645725055 +Step 1670 | loss:2.175377130508423 lr:0.00018105868364986393 tokens_per_second_per_gpu:774.3747943285471 +Step 1671 | loss:2.1066677570343018 lr:0.00018103563410556948 tokens_per_second_per_gpu:776.8277327340875 +Step 1672 | loss:2.1556262969970703 lr:0.00018101257201442469 tokens_per_second_per_gpu:782.1256303131239 +Step 1673 | loss:2.18526291847229 lr:0.00018098949738000025 tokens_per_second_per_gpu:774.0012156096545 +Step 1674 | loss:2.2467713356018066 lr:0.0001809664102058689 tokens_per_second_per_gpu:790.3061247441669 +Step 1675 | loss:2.159998893737793 lr:0.00018094331049560523 tokens_per_second_per_gpu:747.9886660232189 +Step 1676 | loss:2.136963367462158 lr:0.00018092019825278577 tokens_per_second_per_gpu:782.4426964017231 +Step 1677 | loss:2.246269702911377 lr:0.00018089707348098907 tokens_per_second_per_gpu:754.989033189206 +Step 1678 | loss:2.15986704826355 lr:0.0001808739361837955 tokens_per_second_per_gpu:762.6703329609342 +Step 1679 | loss:2.129934310913086 lr:0.00018085078636478753 tokens_per_second_per_gpu:757.4026386326768 +Step 1680 | loss:2.1695282459259033 lr:0.00018082762402754936 tokens_per_second_per_gpu:796.8385315819598 +Step 1681 | loss:2.1419081687927246 lr:0.00018080444917566732 tokens_per_second_per_gpu:800.7498271075551 +Step 1682 | loss:2.1439220905303955 lr:0.00018078126181272962 tokens_per_second_per_gpu:761.813745428317 +Step 1683 | loss:2.1397085189819336 lr:0.00018075806194232632 tokens_per_second_per_gpu:775.0857490055699 +Step 1684 | loss:2.1928553581237793 lr:0.0001807348495680495 tokens_per_second_per_gpu:774.9135621223234 +Step 1685 | loss:2.137155055999756 lr:0.00018071162469349324 tokens_per_second_per_gpu:761.0753521686723 +Step 1686 | loss:2.2168571949005127 lr:0.0001806883873222534 tokens_per_second_per_gpu:768.0942835916659 +Step 1687 | loss:2.1445178985595703 lr:0.00018066513745792787 tokens_per_second_per_gpu:776.6073464024308 +Step 1688 | loss:2.1676383018493652 lr:0.00018064187510411644 tokens_per_second_per_gpu:765.9668167867278 +Step 1689 | loss:2.1500048637390137 lr:0.0001806186002644209 tokens_per_second_per_gpu:722.4948339420164 +Step 1690 | loss:2.2013394832611084 lr:0.00018059531294244488 tokens_per_second_per_gpu:786.9641470219175 +Step 1691 | loss:2.2049365043640137 lr:0.00018057201314179396 tokens_per_second_per_gpu:753.0065951067891 +Step 1692 | loss:2.227017879486084 lr:0.00018054870086607578 tokens_per_second_per_gpu:749.5987105867473 +Step 1693 | loss:2.145347833633423 lr:0.0001805253761188997 tokens_per_second_per_gpu:783.5500973119637 +Step 1694 | loss:2.174683094024658 lr:0.0001805020389038772 tokens_per_second_per_gpu:799.8859499972755 +Step 1695 | loss:2.163102626800537 lr:0.00018047868922462152 tokens_per_second_per_gpu:738.0134948215814 +Step 1696 | loss:2.207271099090576 lr:0.000180455327084748 tokens_per_second_per_gpu:779.2556042879119 +Step 1697 | loss:2.10650634765625 lr:0.00018043195248787378 tokens_per_second_per_gpu:770.0634090104915 +Step 1698 | loss:2.2061967849731445 lr:0.00018040856543761804 tokens_per_second_per_gpu:733.1976853889477 +Step 1699 | loss:2.134303331375122 lr:0.00018038516593760177 tokens_per_second_per_gpu:785.5340094520479 +Step 1700 | loss:2.120108127593994 lr:0.000180361753991448 tokens_per_second_per_gpu:775.9171361106893 +Step 1701 | loss:2.189301013946533 lr:0.00018033832960278153 tokens_per_second_per_gpu:788.023128383959 +Step 1702 | loss:2.192547559738159 lr:0.0001803148927752293 tokens_per_second_per_gpu:753.6566655231567 +Step 1703 | loss:2.129016399383545 lr:0.00018029144351242003 tokens_per_second_per_gpu:752.5324991389415 +Step 1704 | loss:2.2213568687438965 lr:0.00018026798181798435 tokens_per_second_per_gpu:789.5813787341209 +Step 1705 | loss:2.1617932319641113 lr:0.00018024450769555493 tokens_per_second_per_gpu:770.6234601213737 +Step 1706 | loss:2.132951498031616 lr:0.00018022102114876625 tokens_per_second_per_gpu:795.5295032989485 +Step 1707 | loss:2.2139854431152344 lr:0.00018019752218125478 tokens_per_second_per_gpu:775.2281043406136 +Step 1708 | loss:2.2728633880615234 lr:0.0001801740107966589 tokens_per_second_per_gpu:752.1958480797301 +Step 1709 | loss:2.16402268409729 lr:0.0001801504869986189 tokens_per_second_per_gpu:756.0611410728341 +Step 1710 | loss:2.186807155609131 lr:0.00018012695079077702 tokens_per_second_per_gpu:776.4445432000223 +Step 1711 | loss:2.1420841217041016 lr:0.00018010340217677737 tokens_per_second_per_gpu:780.1491492836259 +Step 1712 | loss:2.1221375465393066 lr:0.00018007984116026604 tokens_per_second_per_gpu:793.1275586724206 +Step 1713 | loss:2.1668686866760254 lr:0.00018005626774489098 tokens_per_second_per_gpu:796.2650319140139 +Step 1714 | loss:2.1280517578125 lr:0.0001800326819343021 tokens_per_second_per_gpu:770.453617637399 +Step 1715 | loss:2.216301679611206 lr:0.00018000908373215128 tokens_per_second_per_gpu:726.7089654046199 +Step 1716 | loss:2.1977226734161377 lr:0.00017998547314209215 tokens_per_second_per_gpu:777.7141551428289 +Step 1717 | loss:2.1706576347351074 lr:0.0001799618501677805 tokens_per_second_per_gpu:766.0294350212309 +Step 1718 | loss:2.2021591663360596 lr:0.00017993821481287377 tokens_per_second_per_gpu:764.3437342696036 +Step 1719 | loss:2.080523729324341 lr:0.00017991456708103153 tokens_per_second_per_gpu:784.3517369060772 +Step 1720 | loss:2.1812777519226074 lr:0.00017989090697591518 tokens_per_second_per_gpu:785.1498063221236 +Step 1721 | loss:2.227375030517578 lr:0.00017986723450118803 tokens_per_second_per_gpu:753.7851641795311 +Step 1722 | loss:2.2092854976654053 lr:0.00017984354966051535 tokens_per_second_per_gpu:789.7393058606158 +Step 1723 | loss:2.153367042541504 lr:0.00017981985245756426 tokens_per_second_per_gpu:791.8957771999172 +Step 1724 | loss:2.2169101238250732 lr:0.0001797961428960038 tokens_per_second_per_gpu:781.7994001749181 +Step 1725 | loss:2.108968496322632 lr:0.00017977242097950505 tokens_per_second_per_gpu:781.566114004997 +Step 1726 | loss:2.152749538421631 lr:0.00017974868671174083 tokens_per_second_per_gpu:792.1316478420899 +Step 1727 | loss:2.1548640727996826 lr:0.000179724940096386 tokens_per_second_per_gpu:774.3633157371445 +Step 1728 | loss:2.1748781204223633 lr:0.00017970118113711715 tokens_per_second_per_gpu:767.6459703386967 +Step 1729 | loss:2.1698789596557617 lr:0.0001796774098376131 tokens_per_second_per_gpu:777.3064457985582 +Step 1730 | loss:2.174992322921753 lr:0.0001796536262015542 tokens_per_second_per_gpu:788.2873000016929 +Step 1731 | loss:2.143770694732666 lr:0.00017962983023262304 tokens_per_second_per_gpu:781.3534938077397 +Step 1732 | loss:2.1661922931671143 lr:0.00017960602193450392 tokens_per_second_per_gpu:794.1770236393652 +Step 1733 | loss:2.1410365104675293 lr:0.00017958220131088318 tokens_per_second_per_gpu:767.6351292062471 +Step 1734 | loss:2.117069721221924 lr:0.0001795583683654489 tokens_per_second_per_gpu:787.4902608716814 +Step 1735 | loss:2.21628475189209 lr:0.00017953452310189117 tokens_per_second_per_gpu:780.3239942431688 +Step 1736 | loss:2.1579296588897705 lr:0.00017951066552390204 tokens_per_second_per_gpu:778.9335827815767 +Step 1737 | loss:2.1457765102386475 lr:0.0001794867956351754 tokens_per_second_per_gpu:805.1004084312195 +Step 1738 | loss:2.1142594814300537 lr:0.000179462913439407 tokens_per_second_per_gpu:770.2312709892026 +Step 1739 | loss:2.1587581634521484 lr:0.00017943901894029463 tokens_per_second_per_gpu:788.1053216124096 +Step 1740 | loss:2.1722304821014404 lr:0.00017941511214153785 tokens_per_second_per_gpu:763.770612660125 +Step 1741 | loss:2.196712017059326 lr:0.00017939119304683822 tokens_per_second_per_gpu:776.8008491031035 +Step 1742 | loss:2.2157132625579834 lr:0.00017936726165989914 tokens_per_second_per_gpu:758.9955697771147 +Step 1743 | loss:2.1810455322265625 lr:0.00017934331798442595 tokens_per_second_per_gpu:763.7378391003705 +Step 1744 | loss:2.194027900695801 lr:0.00017931936202412581 tokens_per_second_per_gpu:743.4837644962548 +Step 1745 | loss:2.147613286972046 lr:0.00017929539378270794 tokens_per_second_per_gpu:750.8750872652888 +Step 1746 | loss:2.1211700439453125 lr:0.00017927141326388337 tokens_per_second_per_gpu:769.7268529089771 +Step 1747 | loss:2.129279136657715 lr:0.000179247420471365 tokens_per_second_per_gpu:764.8572032698748 +Step 1748 | loss:2.213557720184326 lr:0.00017922341540886768 tokens_per_second_per_gpu:756.3720979474639 +Step 1749 | loss:2.163790702819824 lr:0.0001791993980801081 tokens_per_second_per_gpu:769.0732974382632 +Step 1750 | loss:2.2435426712036133 lr:0.00017917536848880493 tokens_per_second_per_gpu:774.661759768178 +Step 1751 | loss:2.1840100288391113 lr:0.00017915132663867876 tokens_per_second_per_gpu:789.5856176358969 +Step 1752 | loss:2.1594104766845703 lr:0.0001791272725334519 tokens_per_second_per_gpu:764.5358198172103 +Step 1753 | loss:2.1447551250457764 lr:0.00017910320617684877 tokens_per_second_per_gpu:791.2784918750466 +Step 1754 | loss:2.1809804439544678 lr:0.00017907912757259554 tokens_per_second_per_gpu:789.8252040755424 +Step 1755 | loss:2.181722640991211 lr:0.00017905503672442042 tokens_per_second_per_gpu:752.2802717131465 +Step 1756 | loss:2.176436185836792 lr:0.0001790309336360533 tokens_per_second_per_gpu:766.2502611973074 +Step 1757 | loss:2.1485753059387207 lr:0.00017900681831122618 tokens_per_second_per_gpu:802.2107262856249 +Step 1758 | loss:2.17166805267334 lr:0.00017898269075367285 tokens_per_second_per_gpu:769.2140733452165 +Step 1759 | loss:2.1554818153381348 lr:0.000178958550967129 tokens_per_second_per_gpu:780.9423195402691 +Step 1760 | loss:2.165006637573242 lr:0.0001789343989553322 tokens_per_second_per_gpu:751.3756715849352 +Step 1761 | loss:2.0938854217529297 lr:0.000178910234722022 tokens_per_second_per_gpu:782.0609481736559 +Step 1762 | loss:2.1919736862182617 lr:0.0001788860582709397 tokens_per_second_per_gpu:776.7118482241654 +Step 1763 | loss:2.110663414001465 lr:0.00017886186960582864 tokens_per_second_per_gpu:772.2790112149257 +Step 1764 | loss:2.20405912399292 lr:0.00017883766873043393 tokens_per_second_per_gpu:718.1605152043157 +Step 1765 | loss:2.1775941848754883 lr:0.00017881345564850268 tokens_per_second_per_gpu:743.5858068295672 +Step 1766 | loss:2.110867500305176 lr:0.00017878923036378377 tokens_per_second_per_gpu:790.8747905757666 +Step 1767 | loss:2.152371883392334 lr:0.00017876499288002807 tokens_per_second_per_gpu:799.715054218026 +Step 1768 | loss:2.1479804515838623 lr:0.0001787407432009883 tokens_per_second_per_gpu:764.4310731287748 +Step 1769 | loss:2.198939800262451 lr:0.00017871648133041906 tokens_per_second_per_gpu:772.346059506776 +Step 1770 | loss:2.143235206604004 lr:0.00017869220727207682 tokens_per_second_per_gpu:737.5444027285282 +Step 1771 | loss:2.1878836154937744 lr:0.00017866792102972 tokens_per_second_per_gpu:780.0865293036612 +Step 1772 | loss:2.1199357509613037 lr:0.00017864362260710888 tokens_per_second_per_gpu:768.570007744447 +Step 1773 | loss:2.2001092433929443 lr:0.00017861931200800556 tokens_per_second_per_gpu:778.5365101983931 +Step 1774 | loss:2.1057772636413574 lr:0.00017859498923617414 tokens_per_second_per_gpu:763.8401949232671 +Step 1775 | loss:2.146273374557495 lr:0.0001785706542953805 tokens_per_second_per_gpu:797.576397179754 +Step 1776 | loss:2.173008918762207 lr:0.00017854630718939252 tokens_per_second_per_gpu:744.3130692300114 +Step 1777 | loss:2.191490650177002 lr:0.00017852194792197977 tokens_per_second_per_gpu:787.4853076626421 +Step 1778 | loss:2.1207714080810547 lr:0.00017849757649691396 tokens_per_second_per_gpu:757.685552803055 +Step 1779 | loss:2.1321444511413574 lr:0.00017847319291796848 tokens_per_second_per_gpu:740.0865930911348 +Step 1780 | loss:2.1621623039245605 lr:0.00017844879718891866 tokens_per_second_per_gpu:791.795235280683 +Step 1781 | loss:2.129514217376709 lr:0.00017842438931354177 tokens_per_second_per_gpu:780.8162984991184 +Step 1782 | loss:2.227804183959961 lr:0.00017839996929561687 tokens_per_second_per_gpu:784.6232192956572 +Step 1783 | loss:2.183985471725464 lr:0.00017837553713892493 tokens_per_second_per_gpu:793.1623921277103 +Step 1784 | loss:2.1254663467407227 lr:0.00017835109284724886 tokens_per_second_per_gpu:780.0668559124427 +Step 1785 | loss:2.226356029510498 lr:0.0001783266364243734 tokens_per_second_per_gpu:781.5762791582474 +Step 1786 | loss:2.1524698734283447 lr:0.00017830216787408513 tokens_per_second_per_gpu:771.469653990369 +Step 1787 | loss:2.153935432434082 lr:0.00017827768720017254 tokens_per_second_per_gpu:790.3175912153181 +Step 1788 | loss:2.0892558097839355 lr:0.00017825319440642606 tokens_per_second_per_gpu:782.4189508651127 +Step 1789 | loss:2.1646032333374023 lr:0.0001782286894966379 tokens_per_second_per_gpu:752.9738129649162 +Step 1790 | loss:2.229789972305298 lr:0.0001782041724746022 tokens_per_second_per_gpu:762.4635376319287 +Step 1791 | loss:2.1437156200408936 lr:0.00017817964334411498 tokens_per_second_per_gpu:770.8462587377197 +Step 1792 | loss:2.1055469512939453 lr:0.00017815510210897407 tokens_per_second_per_gpu:752.610107935644 +Step 1793 | loss:2.1124467849731445 lr:0.00017813054877297924 tokens_per_second_per_gpu:760.9740129398738 +Step 1794 | loss:2.145932674407959 lr:0.00017810598333993212 tokens_per_second_per_gpu:782.4149754770076 +Step 1795 | loss:2.0906965732574463 lr:0.00017808140581363619 tokens_per_second_per_gpu:772.6513303210677 +Step 1796 | loss:2.079119920730591 lr:0.00017805681619789687 tokens_per_second_per_gpu:763.8758174701566 +Step 1797 | loss:2.103870391845703 lr:0.00017803221449652135 tokens_per_second_per_gpu:789.7368932586115 +Step 1798 | loss:2.1804733276367188 lr:0.00017800760071331876 tokens_per_second_per_gpu:789.4380345718691 +Step 1799 | loss:2.1761550903320312 lr:0.00017798297485210012 tokens_per_second_per_gpu:791.1032141698912 +Step 1800 | loss:2.195474147796631 lr:0.0001779583369166782 tokens_per_second_per_gpu:770.5730984572313 +Step 1801 | loss:2.1754226684570312 lr:0.00017793368691086778 tokens_per_second_per_gpu:778.8440733931885 +Step 1802 | loss:2.1442313194274902 lr:0.00017790902483848546 tokens_per_second_per_gpu:777.9697220663668 +Step 1803 | loss:2.129847526550293 lr:0.00017788435070334967 tokens_per_second_per_gpu:783.7051095211477 +Step 1804 | loss:2.0716543197631836 lr:0.00017785966450928076 tokens_per_second_per_gpu:798.6017518601735 +Step 1805 | loss:2.209963083267212 lr:0.00017783496626010088 tokens_per_second_per_gpu:770.8268225657606 +Step 1806 | loss:2.1096484661102295 lr:0.00017781025595963414 tokens_per_second_per_gpu:761.9370820563369 +Step 1807 | loss:2.1875925064086914 lr:0.00017778553361170646 tokens_per_second_per_gpu:771.0397809492638 +Step 1808 | loss:2.161475658416748 lr:0.00017776079922014564 tokens_per_second_per_gpu:761.9820167856907 +Step 1809 | loss:2.1430225372314453 lr:0.00017773605278878133 tokens_per_second_per_gpu:769.1701905287208 +Step 1810 | loss:2.1372060775756836 lr:0.000177711294321445 tokens_per_second_per_gpu:741.2483260762616 +Step 1811 | loss:2.085787773132324 lr:0.0001776865238219701 tokens_per_second_per_gpu:787.3782793411341 +Step 1812 | loss:2.1250979900360107 lr:0.00017766174129419188 tokens_per_second_per_gpu:801.4016549453469 +Step 1813 | loss:2.141716480255127 lr:0.0001776369467419474 tokens_per_second_per_gpu:748.8778532157961 +Step 1814 | loss:2.126020908355713 lr:0.00017761214016907565 tokens_per_second_per_gpu:779.9903793178141 +Step 1815 | loss:2.136413097381592 lr:0.00017758732157941752 tokens_per_second_per_gpu:780.1833611278615 +Step 1816 | loss:2.1037282943725586 lr:0.0001775624909768156 tokens_per_second_per_gpu:780.971858913506 +Step 1817 | loss:2.1731371879577637 lr:0.00017753764836511455 tokens_per_second_per_gpu:770.8436183865242 +Step 1818 | loss:2.0936033725738525 lr:0.0001775127937481607 tokens_per_second_per_gpu:747.7051867099317 +Step 1819 | loss:2.1959569454193115 lr:0.00017748792712980236 tokens_per_second_per_gpu:801.3717040390287 +Step 1820 | loss:2.1317028999328613 lr:0.00017746304851388967 tokens_per_second_per_gpu:760.7606956532727 +Step 1821 | loss:2.1522109508514404 lr:0.0001774381579042746 tokens_per_second_per_gpu:787.0543222515868 +Step 1822 | loss:2.143148183822632 lr:0.000177413255304811 tokens_per_second_per_gpu:793.7419742098757 +Step 1823 | loss:2.1474194526672363 lr:0.00017738834071935456 tokens_per_second_per_gpu:742.3513818101202 +Step 1824 | loss:2.1273322105407715 lr:0.00017736341415176284 tokens_per_second_per_gpu:791.769058952551 +Step 1825 | loss:2.1425137519836426 lr:0.00017733847560589527 tokens_per_second_per_gpu:752.5937158906469 +Step 1826 | loss:2.1067118644714355 lr:0.0001773135250856131 tokens_per_second_per_gpu:797.9807139405383 +Step 1827 | loss:2.1081933975219727 lr:0.00017728856259477947 tokens_per_second_per_gpu:770.953180388241 +Step 1828 | loss:2.178821325302124 lr:0.00017726358813725934 tokens_per_second_per_gpu:789.3611883740141 +Step 1829 | loss:2.2126681804656982 lr:0.0001772386017169195 tokens_per_second_per_gpu:761.4226164645976 +Step 1830 | loss:2.1892027854919434 lr:0.00017721360333762873 tokens_per_second_per_gpu:779.9006743519001 +Step 1831 | loss:2.110623359680176 lr:0.00017718859300325745 tokens_per_second_per_gpu:781.8290801631153 +Step 1832 | loss:2.12593150138855 lr:0.0001771635707176781 tokens_per_second_per_gpu:766.4076633377895 +Step 1833 | loss:2.064627170562744 lr:0.0001771385364847649 tokens_per_second_per_gpu:795.311998959706 +Step 1834 | loss:2.1665282249450684 lr:0.00017711349030839394 tokens_per_second_per_gpu:793.0958042519795 +Step 1835 | loss:2.182039260864258 lr:0.00017708843219244315 tokens_per_second_per_gpu:778.4408208659837 +Step 1836 | loss:2.20255184173584 lr:0.0001770633621407923 tokens_per_second_per_gpu:801.4365010290046 +Step 1837 | loss:2.1385200023651123 lr:0.00017703828015732303 tokens_per_second_per_gpu:791.4584686264368 +Step 1838 | loss:2.0966460704803467 lr:0.0001770131862459188 tokens_per_second_per_gpu:783.4318498346586 +Step 1839 | loss:2.1578330993652344 lr:0.00017698808041046493 tokens_per_second_per_gpu:776.0610292958412 +Step 1840 | loss:2.176535129547119 lr:0.00017696296265484862 tokens_per_second_per_gpu:803.8219978031659 +Step 1841 | loss:2.1191258430480957 lr:0.00017693783298295884 tokens_per_second_per_gpu:778.1601362181465 +Step 1842 | loss:2.139927625656128 lr:0.0001769126913986865 tokens_per_second_per_gpu:771.5713399934854 +Step 1843 | loss:2.133014678955078 lr:0.00017688753790592426 tokens_per_second_per_gpu:794.2894339147584 +Step 1844 | loss:2.175126314163208 lr:0.0001768623725085667 tokens_per_second_per_gpu:765.0388517963592 +Step 1845 | loss:2.228067398071289 lr:0.00017683719521051017 tokens_per_second_per_gpu:725.6284595591767 +Step 1846 | loss:2.227698564529419 lr:0.00017681200601565294 tokens_per_second_per_gpu:784.7041826487708 +Step 1847 | loss:2.145364999771118 lr:0.00017678680492789507 tokens_per_second_per_gpu:746.3944540283613 +Step 1848 | loss:2.1488218307495117 lr:0.0001767615919511385 tokens_per_second_per_gpu:760.7247890352215 +Step 1849 | loss:2.1056032180786133 lr:0.00017673636708928693 tokens_per_second_per_gpu:775.9844937526206 +Step 1850 | loss:2.120415449142456 lr:0.000176711130346246 tokens_per_second_per_gpu:766.7697677988197 +Step 1851 | loss:2.187556266784668 lr:0.00017668588172592314 tokens_per_second_per_gpu:779.7077795389199 +Step 1852 | loss:2.1943891048431396 lr:0.00017666062123222767 tokens_per_second_per_gpu:791.6169738235016 +Step 1853 | loss:2.1425673961639404 lr:0.00017663534886907061 tokens_per_second_per_gpu:768.5384563642585 +Step 1854 | loss:2.154341697692871 lr:0.00017661006464036498 tokens_per_second_per_gpu:758.9611454796619 +Step 1855 | loss:2.1525373458862305 lr:0.00017658476855002554 tokens_per_second_per_gpu:740.0274764648269 +Step 1856 | loss:2.119772434234619 lr:0.00017655946060196896 tokens_per_second_per_gpu:776.2911809750123 +Step 1857 | loss:2.1212642192840576 lr:0.00017653414080011362 tokens_per_second_per_gpu:759.2621676895694 +Step 1858 | loss:2.1579368114471436 lr:0.00017650880914837992 tokens_per_second_per_gpu:760.3767941310196 +Step 1859 | loss:2.1153550148010254 lr:0.00017648346565068992 tokens_per_second_per_gpu:778.768416969553 +Step 1860 | loss:2.2003278732299805 lr:0.0001764581103109676 tokens_per_second_per_gpu:754.9423543472242 +Step 1861 | loss:2.1406824588775635 lr:0.00017643274313313873 tokens_per_second_per_gpu:768.5223018685208 +Step 1862 | loss:2.191899299621582 lr:0.00017640736412113104 tokens_per_second_per_gpu:780.8300175059594 +Step 1863 | loss:2.1403350830078125 lr:0.0001763819732788739 tokens_per_second_per_gpu:757.6914737718555 +Step 1864 | loss:2.240431547164917 lr:0.0001763565706102986 tokens_per_second_per_gpu:721.2423195897945 +Step 1865 | loss:2.1778311729431152 lr:0.00017633115611933838 tokens_per_second_per_gpu:784.4684833310389 +Step 1866 | loss:2.1658425331115723 lr:0.0001763057298099281 tokens_per_second_per_gpu:779.3115411208187 +Step 1867 | loss:2.0957088470458984 lr:0.00017628029168600455 tokens_per_second_per_gpu:748.0520987118967 +Step 1868 | loss:2.176870107650757 lr:0.00017625484175150637 tokens_per_second_per_gpu:785.371765119823 +Step 1869 | loss:2.147615909576416 lr:0.00017622938001037402 tokens_per_second_per_gpu:793.7919642983967 +Step 1870 | loss:2.1513187885284424 lr:0.00017620390646654976 tokens_per_second_per_gpu:757.879648365076 +Step 1871 | loss:2.1964213848114014 lr:0.00017617842112397766 tokens_per_second_per_gpu:745.3000033058853 +Step 1872 | loss:2.1474456787109375 lr:0.00017615292398660373 tokens_per_second_per_gpu:775.608899993171 +Step 1873 | loss:2.181460380554199 lr:0.0001761274150583756 tokens_per_second_per_gpu:794.9368345201575 +Step 1874 | loss:2.1668570041656494 lr:0.00017610189434324298 tokens_per_second_per_gpu:776.9221887366648 +Step 1875 | loss:2.1768736839294434 lr:0.0001760763618451572 tokens_per_second_per_gpu:743.2633358381415 +Step 1876 | loss:2.1859562397003174 lr:0.00017605081756807148 tokens_per_second_per_gpu:778.8125456673195 +Step 1877 | loss:2.114443063735962 lr:0.0001760252615159409 tokens_per_second_per_gpu:754.0820248661242 +Step 1878 | loss:2.203958749771118 lr:0.0001759996936927224 tokens_per_second_per_gpu:768.4168325031411 +Step 1879 | loss:2.106367588043213 lr:0.00017597411410237454 tokens_per_second_per_gpu:788.4973458381927 +Step 1880 | loss:2.177201747894287 lr:0.00017594852274885794 tokens_per_second_per_gpu:767.9415135223463 +Step 1881 | loss:2.147838830947876 lr:0.00017592291963613492 tokens_per_second_per_gpu:773.364672547632 +Step 1882 | loss:2.1735305786132812 lr:0.00017589730476816963 tokens_per_second_per_gpu:794.979102635986 +Step 1883 | loss:2.158500909805298 lr:0.00017587167814892807 tokens_per_second_per_gpu:772.3039716462904 +Step 1884 | loss:2.161503791809082 lr:0.000175846039782378 tokens_per_second_per_gpu:778.362374290015 +Step 1885 | loss:2.121274948120117 lr:0.0001758203896724891 tokens_per_second_per_gpu:771.8912740131284 +Step 1886 | loss:2.147374153137207 lr:0.00017579472782323278 tokens_per_second_per_gpu:778.934802784318 +Step 1887 | loss:2.1603431701660156 lr:0.0001757690542385823 tokens_per_second_per_gpu:774.5930284056296 +Step 1888 | loss:2.222291946411133 lr:0.00017574336892251275 tokens_per_second_per_gpu:791.847560551664 +Step 1889 | loss:2.2149412631988525 lr:0.00017571767187900096 tokens_per_second_per_gpu:794.6701211020437 +Step 1890 | loss:2.1793484687805176 lr:0.00017569196311202571 tokens_per_second_per_gpu:788.8482194464638 +Step 1891 | loss:2.1731958389282227 lr:0.00017566624262556747 tokens_per_second_per_gpu:792.4780121919177 +Step 1892 | loss:2.136094808578491 lr:0.00017564051042360862 tokens_per_second_per_gpu:797.7814069979089 +Step 1893 | loss:2.1844425201416016 lr:0.00017561476651013327 tokens_per_second_per_gpu:779.2975793653062 +Step 1894 | loss:2.1425368785858154 lr:0.00017558901088912744 tokens_per_second_per_gpu:765.9914595241145 +Step 1895 | loss:2.1070363521575928 lr:0.00017556324356457877 tokens_per_second_per_gpu:765.280637354013 +Step 1896 | loss:2.136559009552002 lr:0.00017553746454047705 tokens_per_second_per_gpu:799.9392156650116 +Step 1897 | loss:2.160010576248169 lr:0.00017551167382081348 tokens_per_second_per_gpu:764.9072138326587 +Step 1898 | loss:2.1519856452941895 lr:0.00017548587140958142 tokens_per_second_per_gpu:759.9712916785942 +Step 1899 | loss:2.1136183738708496 lr:0.0001754600573107758 tokens_per_second_per_gpu:767.3684526278392 +Step 1900 | loss:2.183500289916992 lr:0.0001754342315283935 tokens_per_second_per_gpu:795.3196714052349 +Step 1901 | loss:2.1983375549316406 lr:0.00017540839406643313 tokens_per_second_per_gpu:784.233893673124 +Step 1902 | loss:2.1095943450927734 lr:0.00017538254492889513 tokens_per_second_per_gpu:787.558462313421 +Step 1903 | loss:2.1919844150543213 lr:0.00017535668411978179 tokens_per_second_per_gpu:780.0207289983463 +Step 1904 | loss:2.1650726795196533 lr:0.00017533081164309718 tokens_per_second_per_gpu:797.4796556291204 +Step 1905 | loss:2.1748623847961426 lr:0.0001753049275028471 tokens_per_second_per_gpu:791.3553174544578 +Step 1906 | loss:2.1994011402130127 lr:0.00017527903170303928 tokens_per_second_per_gpu:754.6424698037192 +Step 1907 | loss:2.1913766860961914 lr:0.00017525312424768318 tokens_per_second_per_gpu:765.9837051122473 +Step 1908 | loss:2.156646251678467 lr:0.00017522720514079006 tokens_per_second_per_gpu:753.2513788585927 +Step 1909 | loss:2.1608638763427734 lr:0.00017520127438637307 tokens_per_second_per_gpu:767.9183813092076 +Step 1910 | loss:2.2633056640625 lr:0.00017517533198844708 tokens_per_second_per_gpu:787.3473571982198 +Step 1911 | loss:2.174973487854004 lr:0.0001751493779510288 tokens_per_second_per_gpu:790.5500141989872 +Step 1912 | loss:2.128359794616699 lr:0.00017512341227813666 tokens_per_second_per_gpu:751.6169327513534 +Step 1913 | loss:2.0940897464752197 lr:0.00017509743497379102 tokens_per_second_per_gpu:788.3617712191257 +Step 1914 | loss:2.1407814025878906 lr:0.00017507144604201393 tokens_per_second_per_gpu:761.5679117430726 +Step 1915 | loss:2.141974687576294 lr:0.00017504544548682934 tokens_per_second_per_gpu:795.2256536586596 +Step 1916 | loss:2.199387788772583 lr:0.00017501943331226291 tokens_per_second_per_gpu:756.0545453557851 +Step 1917 | loss:2.1073412895202637 lr:0.00017499340952234217 tokens_per_second_per_gpu:789.3838394687533 +Step 1918 | loss:2.2038543224334717 lr:0.00017496737412109637 tokens_per_second_per_gpu:750.8306664538301 +Step 1919 | loss:2.1497185230255127 lr:0.00017494132711255665 tokens_per_second_per_gpu:775.8302854056305 +Step 1920 | loss:2.1709461212158203 lr:0.00017491526850075593 tokens_per_second_per_gpu:767.622183231874 +Step 1921 | loss:2.1353507041931152 lr:0.0001748891982897288 tokens_per_second_per_gpu:801.7318581596242 +Step 1922 | loss:2.120943069458008 lr:0.00017486311648351184 tokens_per_second_per_gpu:758.5219554187015 +Step 1923 | loss:2.141274929046631 lr:0.00017483702308614327 tokens_per_second_per_gpu:783.3324991264578 +Step 1924 | loss:2.136824131011963 lr:0.00017481091810166318 tokens_per_second_per_gpu:767.8057412631664 +Step 1925 | loss:2.160090446472168 lr:0.00017478480153411345 tokens_per_second_per_gpu:787.9522246697716 +Step 1926 | loss:2.120706081390381 lr:0.00017475867338753774 tokens_per_second_per_gpu:776.7851252478438 +Step 1927 | loss:2.079374313354492 lr:0.00017473253366598148 tokens_per_second_per_gpu:796.9381658108815 +Step 1928 | loss:2.1723906993865967 lr:0.00017470638237349192 tokens_per_second_per_gpu:786.1751628381612 +Step 1929 | loss:2.161489248275757 lr:0.00017468021951411812 tokens_per_second_per_gpu:758.732701482068 +Step 1930 | loss:2.1672024726867676 lr:0.0001746540450919109 tokens_per_second_per_gpu:777.0803499014269 +Step 1931 | loss:2.1282005310058594 lr:0.00017462785911092287 tokens_per_second_per_gpu:769.9687975380386 +Step 1932 | loss:2.194932699203491 lr:0.00017460166157520847 tokens_per_second_per_gpu:793.5798117876068 +Step 1933 | loss:2.075712203979492 lr:0.00017457545248882386 tokens_per_second_per_gpu:747.8722607167894 +Step 1934 | loss:2.1192057132720947 lr:0.00017454923185582704 tokens_per_second_per_gpu:789.4912377327882 +Step 1935 | loss:2.0836355686187744 lr:0.0001745229996802778 tokens_per_second_per_gpu:782.45618895226 +Step 1936 | loss:2.157823324203491 lr:0.00017449675596623764 tokens_per_second_per_gpu:771.7140810400995 +Step 1937 | loss:2.2096846103668213 lr:0.00017447050071777 tokens_per_second_per_gpu:767.2687544495627 +Step 1938 | loss:2.1222991943359375 lr:0.00017444423393893997 tokens_per_second_per_gpu:773.235020201216 +Step 1939 | loss:2.079867362976074 lr:0.00017441795563381444 tokens_per_second_per_gpu:779.3258896404466 +Step 1940 | loss:2.1260159015655518 lr:0.00017439166580646216 tokens_per_second_per_gpu:773.3232466769865 +Step 1941 | loss:2.076641798019409 lr:0.00017436536446095358 tokens_per_second_per_gpu:785.9259712671261 +Step 1942 | loss:2.1382365226745605 lr:0.000174339051601361 tokens_per_second_per_gpu:773.6552941993809 +Step 1943 | loss:2.1961424350738525 lr:0.00017431272723175844 tokens_per_second_per_gpu:777.1592219225049 +Step 1944 | loss:2.1637508869171143 lr:0.00017428639135622177 tokens_per_second_per_gpu:772.8381590173308 +Step 1945 | loss:2.2305071353912354 lr:0.00017426004397882858 tokens_per_second_per_gpu:758.1313923289546 +Step 1946 | loss:2.1212828159332275 lr:0.0001742336851036583 tokens_per_second_per_gpu:765.2186383437743 +Step 1947 | loss:2.1520936489105225 lr:0.0001742073147347921 tokens_per_second_per_gpu:784.4630532036109 +Step 1948 | loss:2.2089476585388184 lr:0.00017418093287631292 tokens_per_second_per_gpu:787.4452370564073 +Step 1949 | loss:2.1768269538879395 lr:0.00017415453953230548 tokens_per_second_per_gpu:778.1662689424797 +Step 1950 | loss:2.1348116397857666 lr:0.00017412813470685633 tokens_per_second_per_gpu:767.0224527955553 +Step 1951 | loss:2.1519479751586914 lr:0.0001741017184040538 tokens_per_second_per_gpu:771.9356787396139 +Step 1952 | loss:2.1337032318115234 lr:0.00017407529062798784 tokens_per_second_per_gpu:792.5402186844032 +Step 1953 | loss:2.1493706703186035 lr:0.0001740488513827504 tokens_per_second_per_gpu:791.9895646451354 +Step 1954 | loss:2.142716407775879 lr:0.00017402240067243506 tokens_per_second_per_gpu:782.6851158321056 +Step 1955 | loss:2.176612138748169 lr:0.00017399593850113724 tokens_per_second_per_gpu:783.3036259784703 +Step 1956 | loss:2.0853476524353027 lr:0.0001739694648729541 tokens_per_second_per_gpu:752.471649180397 +Step 1957 | loss:2.1614208221435547 lr:0.00017394297979198456 tokens_per_second_per_gpu:744.7744628330822 +Step 1958 | loss:2.1724021434783936 lr:0.0001739164832623294 tokens_per_second_per_gpu:740.3065091722864 +Step 1959 | loss:2.0799107551574707 lr:0.00017388997528809105 tokens_per_second_per_gpu:776.8273845613601 +Step 1960 | loss:2.1588895320892334 lr:0.0001738634558733738 tokens_per_second_per_gpu:772.9962688564129 +Step 1961 | loss:2.2280101776123047 lr:0.0001738369250222837 tokens_per_second_per_gpu:770.6348630076161 +Step 1962 | loss:2.1968884468078613 lr:0.00017381038273892854 tokens_per_second_per_gpu:789.1635281345164 +Step 1963 | loss:2.143312692642212 lr:0.00017378382902741787 tokens_per_second_per_gpu:767.1578223338877 +Step 1964 | loss:2.0800437927246094 lr:0.00017375726389186306 tokens_per_second_per_gpu:757.9803080560544 +Step 1965 | loss:2.1472368240356445 lr:0.00017373068733637722 tokens_per_second_per_gpu:728.9735736309627 +Step 1966 | loss:2.0982813835144043 lr:0.00017370409936507525 tokens_per_second_per_gpu:763.3312162748757 +Step 1967 | loss:2.167506694793701 lr:0.0001736774999820738 tokens_per_second_per_gpu:787.9490729123388 +Step 1968 | loss:2.1720056533813477 lr:0.00017365088919149124 tokens_per_second_per_gpu:742.6372075676179 +Step 1969 | loss:2.185698986053467 lr:0.0001736242669974478 tokens_per_second_per_gpu:787.1402702515697 +Step 1970 | loss:2.1455726623535156 lr:0.0001735976334040654 tokens_per_second_per_gpu:725.9077865141305 +Step 1971 | loss:2.144998788833618 lr:0.00017357098841546775 tokens_per_second_per_gpu:780.2179604398289 +Step 1972 | loss:2.0812692642211914 lr:0.00017354433203578038 tokens_per_second_per_gpu:767.8627776185266 +Step 1973 | loss:2.15535044670105 lr:0.00017351766426913046 tokens_per_second_per_gpu:753.82959679236 +Step 1974 | loss:2.1603455543518066 lr:0.00017349098511964704 tokens_per_second_per_gpu:776.1861868831033 +Step 1975 | loss:2.152400016784668 lr:0.00017346429459146086 tokens_per_second_per_gpu:756.0607686302 +Step 1976 | loss:2.0700626373291016 lr:0.00017343759268870448 tokens_per_second_per_gpu:779.8735406449874 +Step 1977 | loss:2.120967388153076 lr:0.00017341087941551218 tokens_per_second_per_gpu:769.2791170126013 +Step 1978 | loss:2.1715073585510254 lr:0.00017338415477601997 tokens_per_second_per_gpu:781.0019745374904 +Step 1979 | loss:2.0806896686553955 lr:0.0001733574187743657 tokens_per_second_per_gpu:789.1814703662612 +Step 1980 | loss:2.125150680541992 lr:0.00017333067141468895 tokens_per_second_per_gpu:777.554218201723 +Step 1981 | loss:2.0662810802459717 lr:0.000173303912701131 tokens_per_second_per_gpu:791.7453904552563 +Step 1982 | loss:2.1054935455322266 lr:0.000173277142637835 tokens_per_second_per_gpu:780.0001176084038 +Step 1983 | loss:2.121666669845581 lr:0.00017325036122894575 tokens_per_second_per_gpu:788.9595712636569 +Step 1984 | loss:2.1473019123077393 lr:0.00017322356847860983 tokens_per_second_per_gpu:792.3428477428708 +Step 1985 | loss:2.1357882022857666 lr:0.00017319676439097562 tokens_per_second_per_gpu:782.7819826216698 +Step 1986 | loss:2.093486785888672 lr:0.0001731699489701933 tokens_per_second_per_gpu:753.7375724190002 +Step 1987 | loss:2.120307445526123 lr:0.00017314312222041457 tokens_per_second_per_gpu:768.0852340715485 +Step 1988 | loss:2.1669540405273438 lr:0.00017311628414579323 tokens_per_second_per_gpu:784.7656979348977 +Step 1989 | loss:2.1288764476776123 lr:0.00017308943475048452 tokens_per_second_per_gpu:770.3927701140593 +Step 1990 | loss:2.168311595916748 lr:0.00017306257403864564 tokens_per_second_per_gpu:762.4866075573185 +Step 1991 | loss:2.113903522491455 lr:0.00017303570201443545 tokens_per_second_per_gpu:776.4256854388705 +Step 1992 | loss:2.112511396408081 lr:0.00017300881868201456 tokens_per_second_per_gpu:776.0647249275631 +Step 1993 | loss:2.166853189468384 lr:0.00017298192404554538 tokens_per_second_per_gpu:772.3401644129204 +Step 1994 | loss:2.1520543098449707 lr:0.00017295501810919204 tokens_per_second_per_gpu:795.6457265557729 +Step 1995 | loss:2.1957130432128906 lr:0.00017292810087712036 tokens_per_second_per_gpu:750.8471106097903 +Step 1996 | loss:2.099222421646118 lr:0.00017290117235349808 tokens_per_second_per_gpu:759.2590227241066 +Step 1997 | loss:2.122197389602661 lr:0.00017287423254249448 tokens_per_second_per_gpu:773.0123380077051 +Step 1998 | loss:2.1182854175567627 lr:0.00017284728144828073 tokens_per_second_per_gpu:762.135795742261 +Step 1999 | loss:2.1152846813201904 lr:0.00017282031907502968 tokens_per_second_per_gpu:799.6286282436889 +Step 2000 | loss:2.169203042984009 lr:0.00017279334542691596 tokens_per_second_per_gpu:773.8952830876066 +Step 2001 | loss:2.1534152030944824 lr:0.00017276636050811596 tokens_per_second_per_gpu:784.1192539127402 +Step 2002 | loss:2.0623626708984375 lr:0.00017273936432280772 tokens_per_second_per_gpu:796.5703025345973 +Step 2003 | loss:2.1953914165496826 lr:0.00017271235687517117 tokens_per_second_per_gpu:778.718649298146 +Step 2004 | loss:2.160065174102783 lr:0.0001726853381693879 tokens_per_second_per_gpu:790.4993672223225 +Step 2005 | loss:2.12064266204834 lr:0.00017265830820964117 tokens_per_second_per_gpu:750.5251071069094 +Step 2006 | loss:2.1040375232696533 lr:0.00017263126700011616 tokens_per_second_per_gpu:780.8205217132625 +Step 2007 | loss:2.154275417327881 lr:0.0001726042145449996 tokens_per_second_per_gpu:755.0966726639591 +Step 2008 | loss:2.1057655811309814 lr:0.00017257715084848018 tokens_per_second_per_gpu:779.4229848695616 +Step 2009 | loss:2.1482200622558594 lr:0.0001725500759147481 tokens_per_second_per_gpu:768.9293392172582 +Step 2010 | loss:2.084778308868408 lr:0.00017252298974799546 tokens_per_second_per_gpu:736.5495953034772 +Step 2011 | loss:2.1197800636291504 lr:0.00017249589235241602 tokens_per_second_per_gpu:793.8470895223918 +Step 2012 | loss:2.142225503921509 lr:0.00017246878373220533 tokens_per_second_per_gpu:743.527184052465 +Step 2013 | loss:2.120694160461426 lr:0.0001724416638915606 tokens_per_second_per_gpu:753.3097350997803 +Step 2014 | loss:2.119723320007324 lr:0.00017241453283468088 tokens_per_second_per_gpu:780.5929168624957 +Step 2015 | loss:2.106759548187256 lr:0.0001723873905657669 tokens_per_second_per_gpu:782.3319683883326 +Step 2016 | loss:2.115054130554199 lr:0.00017236023708902111 tokens_per_second_per_gpu:768.3898626270877 +Step 2017 | loss:2.119861125946045 lr:0.00017233307240864773 tokens_per_second_per_gpu:767.5435311614921 +Step 2018 | loss:2.0938258171081543 lr:0.0001723058965288527 tokens_per_second_per_gpu:765.581646167967 +Step 2019 | loss:2.176523208618164 lr:0.0001722787094538437 tokens_per_second_per_gpu:798.2326812554605 +Step 2020 | loss:2.138667345046997 lr:0.00017225151118783013 tokens_per_second_per_gpu:729.0885903007236 +Step 2021 | loss:2.0880637168884277 lr:0.00017222430173502318 tokens_per_second_per_gpu:776.203721848255 +Step 2022 | loss:2.1204733848571777 lr:0.00017219708109963565 tokens_per_second_per_gpu:742.5337543367978 +Step 2023 | loss:2.2061915397644043 lr:0.0001721698492858822 tokens_per_second_per_gpu:768.3067219765728 +Step 2024 | loss:2.116586923599243 lr:0.00017214260629797913 tokens_per_second_per_gpu:761.3079200535801 +Step 2025 | loss:2.175044536590576 lr:0.0001721153521401445 tokens_per_second_per_gpu:747.6493604028714 +Step 2026 | loss:2.120455741882324 lr:0.00017208808681659816 tokens_per_second_per_gpu:746.1675953131158 +Step 2027 | loss:2.0894553661346436 lr:0.0001720608103315616 tokens_per_second_per_gpu:767.8569157764272 +Step 2028 | loss:2.170593023300171 lr:0.00017203352268925807 tokens_per_second_per_gpu:772.1836688392815 +Step 2029 | loss:2.1705775260925293 lr:0.00017200622389391254 tokens_per_second_per_gpu:775.8104115112519 +Step 2030 | loss:2.086906671524048 lr:0.00017197891394975178 tokens_per_second_per_gpu:734.5132626342144 +Step 2031 | loss:2.171926736831665 lr:0.00017195159286100413 tokens_per_second_per_gpu:799.674321939709 +Step 2032 | loss:2.125962257385254 lr:0.00017192426063189983 tokens_per_second_per_gpu:763.7601374680123 +Step 2033 | loss:2.1065008640289307 lr:0.0001718969172666707 tokens_per_second_per_gpu:787.3828171729915 +Step 2034 | loss:2.13621187210083 lr:0.0001718695627695504 tokens_per_second_per_gpu:747.4118315835221 +Step 2035 | loss:2.126697063446045 lr:0.0001718421971447742 tokens_per_second_per_gpu:729.1844033650079 +Step 2036 | loss:2.094298839569092 lr:0.00017181482039657926 tokens_per_second_per_gpu:752.4275447332153 +Step 2037 | loss:2.164825439453125 lr:0.00017178743252920425 tokens_per_second_per_gpu:779.2390570858614 +Step 2038 | loss:2.133889675140381 lr:0.00017176003354688968 tokens_per_second_per_gpu:782.7141061625184 +Step 2039 | loss:2.1515560150146484 lr:0.00017173262345387787 tokens_per_second_per_gpu:782.9020996349723 +Step 2040 | loss:2.142646074295044 lr:0.00017170520225441262 tokens_per_second_per_gpu:769.4981140677023 +Step 2041 | loss:2.117527961730957 lr:0.00017167776995273968 tokens_per_second_per_gpu:738.0574984069615 +Step 2042 | loss:2.150880813598633 lr:0.0001716503265531064 tokens_per_second_per_gpu:773.6940721903236 +Step 2043 | loss:2.1789584159851074 lr:0.0001716228720597619 tokens_per_second_per_gpu:776.8738376233522 +Step 2044 | loss:2.1003684997558594 lr:0.00017159540647695696 tokens_per_second_per_gpu:774.4616299616965 +Step 2045 | loss:2.1283586025238037 lr:0.00017156792980894416 tokens_per_second_per_gpu:778.8882177186272 +Step 2046 | loss:2.178682804107666 lr:0.00017154044205997768 tokens_per_second_per_gpu:789.520597279092 +Step 2047 | loss:2.138859987258911 lr:0.00017151294323431354 tokens_per_second_per_gpu:786.334694417935 +Step 2048 | loss:2.0988242626190186 lr:0.0001714854333362094 tokens_per_second_per_gpu:763.0261316543316 +Step 2049 | loss:2.1649320125579834 lr:0.00017145791236992461 tokens_per_second_per_gpu:773.0189428450644 +Step 2050 | loss:2.0998635292053223 lr:0.00017143038033972033 tokens_per_second_per_gpu:792.9688724424221 +Step 2051 | loss:2.1732914447784424 lr:0.0001714028372498594 tokens_per_second_per_gpu:797.4704490425186 +Step 2052 | loss:2.168248414993286 lr:0.00017137528310460628 tokens_per_second_per_gpu:779.4120177787067 +Step 2053 | loss:2.142176628112793 lr:0.00017134771790822722 tokens_per_second_per_gpu:791.8345859030204 +Step 2054 | loss:2.1268181800842285 lr:0.00017132014166499026 tokens_per_second_per_gpu:792.1847929382898 +Step 2055 | loss:2.134136199951172 lr:0.00017129255437916497 tokens_per_second_per_gpu:773.7381202703267 +Step 2056 | loss:2.135298252105713 lr:0.0001712649560550228 tokens_per_second_per_gpu:759.0588684884456 +Step 2057 | loss:2.1075780391693115 lr:0.00017123734669683677 tokens_per_second_per_gpu:768.945658354941 +Step 2058 | loss:2.1527621746063232 lr:0.0001712097263088817 tokens_per_second_per_gpu:749.3794493250955 +Step 2059 | loss:2.1326370239257812 lr:0.0001711820948954341 tokens_per_second_per_gpu:802.6335541483913 +Step 2060 | loss:2.1786229610443115 lr:0.00017115445246077219 tokens_per_second_per_gpu:794.7295998408325 +Step 2061 | loss:2.113797187805176 lr:0.00017112679900917579 tokens_per_second_per_gpu:787.996139346865 +Step 2062 | loss:2.1153645515441895 lr:0.0001710991345449266 tokens_per_second_per_gpu:766.212226476409 +Step 2063 | loss:2.149017095565796 lr:0.00017107145907230796 tokens_per_second_per_gpu:784.5348582528746 +Step 2064 | loss:2.120062828063965 lr:0.00017104377259560488 tokens_per_second_per_gpu:762.1142555501174 +Step 2065 | loss:2.1118690967559814 lr:0.00017101607511910407 tokens_per_second_per_gpu:786.9529103142168 +Step 2066 | loss:2.147029161453247 lr:0.000170988366647094 tokens_per_second_per_gpu:789.510109323886 +Step 2067 | loss:2.123579502105713 lr:0.00017096064718386474 tokens_per_second_per_gpu:734.690503468383 +Step 2068 | loss:2.06933331489563 lr:0.0001709329167337082 tokens_per_second_per_gpu:763.8881996371399 +Step 2069 | loss:2.1651813983917236 lr:0.00017090517530091788 tokens_per_second_per_gpu:786.3012602906083 +Step 2070 | loss:2.1174731254577637 lr:0.00017087742288978905 tokens_per_second_per_gpu:790.9670585197422 +Step 2071 | loss:2.130181312561035 lr:0.00017084965950461866 tokens_per_second_per_gpu:759.7558808463393 +Step 2072 | loss:2.1442596912384033 lr:0.0001708218851497053 tokens_per_second_per_gpu:739.1308974408122 +Step 2073 | loss:2.1419851779937744 lr:0.00017079409982934934 tokens_per_second_per_gpu:781.0889591865589 +Step 2074 | loss:2.0892984867095947 lr:0.00017076630354785283 tokens_per_second_per_gpu:750.6738453909895 +Step 2075 | loss:2.1521944999694824 lr:0.0001707384963095195 tokens_per_second_per_gpu:797.9679738736247 +Step 2076 | loss:2.119217872619629 lr:0.00017071067811865476 tokens_per_second_per_gpu:772.4377212787326 +Step 2077 | loss:2.1481356620788574 lr:0.00017068284897956576 tokens_per_second_per_gpu:763.8929411658404 +Step 2078 | loss:2.1381120681762695 lr:0.00017065500889656127 tokens_per_second_per_gpu:769.1646982842124 +Step 2079 | loss:2.1717114448547363 lr:0.00017062715787395186 tokens_per_second_per_gpu:749.9997843290026 +Step 2080 | loss:2.1341285705566406 lr:0.0001705992959160497 tokens_per_second_per_gpu:786.0297334234805 +Step 2081 | loss:2.118088722229004 lr:0.00017057142302716872 tokens_per_second_per_gpu:733.6773217504052 +Step 2082 | loss:2.1010775566101074 lr:0.00017054353921162454 tokens_per_second_per_gpu:773.5739865313384 +Step 2083 | loss:2.133627414703369 lr:0.00017051564447373438 tokens_per_second_per_gpu:761.6195625448678 +Step 2084 | loss:2.1704468727111816 lr:0.00017048773881781726 tokens_per_second_per_gpu:775.7002093934968 +Step 2085 | loss:2.13667631149292 lr:0.00017045982224819385 tokens_per_second_per_gpu:804.4315505416226 +Step 2086 | loss:2.2078990936279297 lr:0.00017043189476918647 tokens_per_second_per_gpu:743.3512716911698 +Step 2087 | loss:2.1767139434814453 lr:0.00017040395638511923 tokens_per_second_per_gpu:780.7755117694703 +Step 2088 | loss:2.1193172931671143 lr:0.00017037600710031783 tokens_per_second_per_gpu:757.1088836104436 +Step 2089 | loss:2.133855104446411 lr:0.00017034804691910967 tokens_per_second_per_gpu:786.7226402184239 +Step 2090 | loss:2.0957772731781006 lr:0.0001703200758458239 tokens_per_second_per_gpu:773.4349508134179 +Step 2091 | loss:2.123762607574463 lr:0.00017029209388479127 tokens_per_second_per_gpu:782.47784961187 +Step 2092 | loss:2.0984702110290527 lr:0.00017026410104034433 tokens_per_second_per_gpu:762.5710508102133 +Step 2093 | loss:2.1520581245422363 lr:0.00017023609731681722 tokens_per_second_per_gpu:752.1354902246808 +Step 2094 | loss:2.097430467605591 lr:0.00017020808271854575 tokens_per_second_per_gpu:744.8320165107649 +Step 2095 | loss:2.199558734893799 lr:0.00017018005724986753 tokens_per_second_per_gpu:750.0193109997168 +Step 2096 | loss:2.095426082611084 lr:0.0001701520209151217 tokens_per_second_per_gpu:770.664713832215 +Step 2097 | loss:2.0980570316314697 lr:0.00017012397371864922 tokens_per_second_per_gpu:787.08899275885 +Step 2098 | loss:2.1018965244293213 lr:0.00017009591566479265 tokens_per_second_per_gpu:789.2915595832735 +Step 2099 | loss:2.1625475883483887 lr:0.00017006784675789623 tokens_per_second_per_gpu:755.5129124293013 +Step 2100 | loss:2.1584088802337646 lr:0.000170039767002306 tokens_per_second_per_gpu:804.1473305675598 +Step 2101 | loss:2.086784839630127 lr:0.00017001167640236947 tokens_per_second_per_gpu:753.4377209574812 +Step 2102 | loss:2.1458370685577393 lr:0.00016998357496243597 tokens_per_second_per_gpu:779.8728123440295 +Step 2103 | loss:2.136315107345581 lr:0.00016995546268685653 tokens_per_second_per_gpu:749.0428516155197 +Step 2104 | loss:2.1542563438415527 lr:0.0001699273395799838 tokens_per_second_per_gpu:768.6270338009649 +Step 2105 | loss:2.1246962547302246 lr:0.00016989920564617207 tokens_per_second_per_gpu:784.2346703048382 +Step 2106 | loss:2.0650229454040527 lr:0.00016987106088977737 tokens_per_second_per_gpu:774.4017757449656 +Step 2107 | loss:2.135097026824951 lr:0.00016984290531515744 tokens_per_second_per_gpu:784.2491086176125 +Step 2108 | loss:2.0966176986694336 lr:0.00016981473892667154 tokens_per_second_per_gpu:797.2815358049222 +Step 2109 | loss:2.134716510772705 lr:0.00016978656172868083 tokens_per_second_per_gpu:793.4355071218928 +Step 2110 | loss:2.150803565979004 lr:0.00016975837372554793 tokens_per_second_per_gpu:761.1856710596817 +Step 2111 | loss:2.173048496246338 lr:0.00016973017492163725 tokens_per_second_per_gpu:797.6912225015635 +Step 2112 | loss:2.048656940460205 lr:0.00016970196532131487 tokens_per_second_per_gpu:794.1357360217544 +Step 2113 | loss:2.1030313968658447 lr:0.0001696737449289485 tokens_per_second_per_gpu:749.2563698565137 +Step 2114 | loss:2.1025218963623047 lr:0.00016964551374890754 tokens_per_second_per_gpu:782.9362057076994 +Step 2115 | loss:2.119537591934204 lr:0.00016961727178556305 tokens_per_second_per_gpu:801.8609508120911 +Step 2116 | loss:2.093330144882202 lr:0.0001695890190432878 tokens_per_second_per_gpu:796.8377096860485 +Step 2117 | loss:2.083528995513916 lr:0.00016956075552645615 tokens_per_second_per_gpu:789.2899956572293 +Step 2118 | loss:2.1314234733581543 lr:0.0001695324812394442 tokens_per_second_per_gpu:750.9086025840693 +Step 2119 | loss:2.181978940963745 lr:0.00016950419618662972 tokens_per_second_per_gpu:792.8693333364114 +Step 2120 | loss:2.182368755340576 lr:0.00016947590037239208 tokens_per_second_per_gpu:770.1669710304279 +Step 2121 | loss:2.1532912254333496 lr:0.00016944759380111237 tokens_per_second_per_gpu:745.8177103812711 +Step 2122 | loss:2.0993542671203613 lr:0.00016941927647717338 tokens_per_second_per_gpu:746.7493005002324 +Step 2123 | loss:2.0967416763305664 lr:0.00016939094840495941 tokens_per_second_per_gpu:775.5681838511102 +Step 2124 | loss:2.1135008335113525 lr:0.00016936260958885663 tokens_per_second_per_gpu:789.8245122444364 +Step 2125 | loss:2.113990306854248 lr:0.00016933426003325276 tokens_per_second_per_gpu:800.1198283412269 +Step 2126 | loss:2.1745009422302246 lr:0.00016930589974253714 tokens_per_second_per_gpu:737.2199909479457 +Step 2127 | loss:2.1432323455810547 lr:0.0001692775287211009 tokens_per_second_per_gpu:771.0801053196215 +Step 2128 | loss:2.065847158432007 lr:0.0001692491469733367 tokens_per_second_per_gpu:789.8978506084856 +Step 2129 | loss:2.149362564086914 lr:0.00016922075450363897 tokens_per_second_per_gpu:774.7796295939645 +Step 2130 | loss:2.2448623180389404 lr:0.00016919235131640373 tokens_per_second_per_gpu:777.1562103065112 +Step 2131 | loss:2.1124045848846436 lr:0.00016916393741602868 tokens_per_second_per_gpu:757.0760717842427 +Step 2132 | loss:2.1445188522338867 lr:0.0001691355128069132 tokens_per_second_per_gpu:768.853281574731 +Step 2133 | loss:2.099409341812134 lr:0.00016910707749345826 tokens_per_second_per_gpu:791.1991866955292 +Step 2134 | loss:2.1012797355651855 lr:0.0001690786314800666 tokens_per_second_per_gpu:767.8335261915307 +Step 2135 | loss:2.1259348392486572 lr:0.0001690501747711425 tokens_per_second_per_gpu:746.8197587566257 +Step 2136 | loss:2.2203750610351562 lr:0.000169021707371092 tokens_per_second_per_gpu:738.2627476565265 +Step 2137 | loss:2.1231603622436523 lr:0.00016899322928432274 tokens_per_second_per_gpu:789.2829238790246 +Step 2138 | loss:2.190626621246338 lr:0.00016896474051524392 tokens_per_second_per_gpu:777.7207459556766 +Step 2139 | loss:2.1108765602111816 lr:0.00016893624106826662 tokens_per_second_per_gpu:787.4343593256261 +Step 2140 | loss:2.189659595489502 lr:0.00016890773094780336 tokens_per_second_per_gpu:793.8924112425849 +Step 2141 | loss:2.137024402618408 lr:0.00016887921015826845 tokens_per_second_per_gpu:771.6700669278781 +Step 2142 | loss:2.14607572555542 lr:0.00016885067870407776 tokens_per_second_per_gpu:749.013167965168 +Step 2143 | loss:2.0805411338806152 lr:0.00016882213658964888 tokens_per_second_per_gpu:796.835345942392 +Step 2144 | loss:2.1708312034606934 lr:0.00016879358381940103 tokens_per_second_per_gpu:772.675734935073 +Step 2145 | loss:2.091341495513916 lr:0.00016876502039775502 tokens_per_second_per_gpu:772.9120891418971 +Step 2146 | loss:2.1558446884155273 lr:0.00016873644632913343 tokens_per_second_per_gpu:768.8942548640838 +Step 2147 | loss:2.115161418914795 lr:0.0001687078616179604 tokens_per_second_per_gpu:779.8167510214083 +Step 2148 | loss:2.1261630058288574 lr:0.00016867926626866166 tokens_per_second_per_gpu:756.4848413946487 +Step 2149 | loss:2.1792004108428955 lr:0.00016865066028566477 tokens_per_second_per_gpu:780.3729295609354 +Step 2150 | loss:2.0674407482147217 lr:0.00016862204367339875 tokens_per_second_per_gpu:790.8347598430051 +Step 2151 | loss:2.122014045715332 lr:0.00016859341643629441 tokens_per_second_per_gpu:745.9924952218003 +Step 2152 | loss:2.0609688758850098 lr:0.00016856477857878413 tokens_per_second_per_gpu:766.9822895876924 +Step 2153 | loss:2.1782894134521484 lr:0.00016853613010530189 tokens_per_second_per_gpu:780.1890578479388 +Step 2154 | loss:2.060781717300415 lr:0.00016850747102028346 tokens_per_second_per_gpu:790.8054165017435 +Step 2155 | loss:2.1381869316101074 lr:0.0001684788013281661 tokens_per_second_per_gpu:771.9987042730172 +Step 2156 | loss:2.1434969902038574 lr:0.00016845012103338877 tokens_per_second_per_gpu:781.6964129340533 +Step 2157 | loss:2.1151235103607178 lr:0.0001684214301403921 tokens_per_second_per_gpu:793.1334360690502 +Step 2158 | loss:2.1230602264404297 lr:0.00016839272865361833 tokens_per_second_per_gpu:770.3919759348004 +Step 2159 | loss:2.1879305839538574 lr:0.00016836401657751134 tokens_per_second_per_gpu:787.5377944695173 +Step 2160 | loss:2.0750746726989746 lr:0.0001683352939165167 tokens_per_second_per_gpu:776.9531296783215 +Step 2161 | loss:2.083712577819824 lr:0.00016830656067508151 tokens_per_second_per_gpu:777.8380801065236 +Step 2162 | loss:2.1582980155944824 lr:0.00016827781685765464 tokens_per_second_per_gpu:758.9495728047335 +Step 2163 | loss:2.146787166595459 lr:0.00016824906246868648 tokens_per_second_per_gpu:786.5372428628139 +Step 2164 | loss:2.131577253341675 lr:0.0001682202975126291 tokens_per_second_per_gpu:746.4655450950081 +Step 2165 | loss:2.135525703430176 lr:0.0001681915219939363 tokens_per_second_per_gpu:780.2545740382599 +Step 2166 | loss:2.1112468242645264 lr:0.00016816273591706334 tokens_per_second_per_gpu:753.0503733476393 +Step 2167 | loss:2.128204584121704 lr:0.00016813393928646723 tokens_per_second_per_gpu:796.6332945240508 +Step 2168 | loss:2.0796101093292236 lr:0.00016810513210660662 tokens_per_second_per_gpu:786.9003201170434 +Step 2169 | loss:2.1858127117156982 lr:0.00016807631438194173 tokens_per_second_per_gpu:787.0450778004753 +Step 2170 | loss:2.161184072494507 lr:0.00016804748611693447 tokens_per_second_per_gpu:753.2044644266185 +Step 2171 | loss:2.1366143226623535 lr:0.00016801864731604831 tokens_per_second_per_gpu:777.793862952374 +Step 2172 | loss:2.0689609050750732 lr:0.00016798979798374845 tokens_per_second_per_gpu:766.3027611885916 +Step 2173 | loss:2.051987648010254 lr:0.00016796093812450162 tokens_per_second_per_gpu:767.7589608798594 +Step 2174 | loss:2.1232287883758545 lr:0.0001679320677427763 tokens_per_second_per_gpu:746.2263445259807 +Step 2175 | loss:2.1022427082061768 lr:0.00016790318684304246 tokens_per_second_per_gpu:766.9274050398465 +Step 2176 | loss:2.1565299034118652 lr:0.0001678742954297718 tokens_per_second_per_gpu:782.9134778291137 +Step 2177 | loss:2.127584934234619 lr:0.0001678453935074376 tokens_per_second_per_gpu:766.9017063347114 +Step 2178 | loss:2.1013641357421875 lr:0.00016781648108051477 tokens_per_second_per_gpu:761.7923250984302 +Step 2179 | loss:2.1290249824523926 lr:0.00016778755815347992 tokens_per_second_per_gpu:758.2147227918363 +Step 2180 | loss:2.1776719093322754 lr:0.00016775862473081114 tokens_per_second_per_gpu:748.605888362487 +Step 2181 | loss:2.1183338165283203 lr:0.00016772968081698827 tokens_per_second_per_gpu:793.2684466123767 +Step 2182 | loss:2.083097219467163 lr:0.00016770072641649275 tokens_per_second_per_gpu:766.4139102041239 +Step 2183 | loss:2.0998799800872803 lr:0.00016767176153380763 tokens_per_second_per_gpu:762.6863373511543 +Step 2184 | loss:2.1794159412384033 lr:0.0001676427861734175 tokens_per_second_per_gpu:754.5642503736703 +Step 2185 | loss:2.1135497093200684 lr:0.00016761380033980872 tokens_per_second_per_gpu:789.2760272684912 +Step 2186 | loss:2.1163330078125 lr:0.0001675848040374692 tokens_per_second_per_gpu:766.9453308014746 +Step 2187 | loss:2.1619303226470947 lr:0.0001675557972708885 tokens_per_second_per_gpu:763.483795263897 +Step 2188 | loss:2.0812723636627197 lr:0.00016752678004455768 tokens_per_second_per_gpu:785.9526703595349 +Step 2189 | loss:2.1270763874053955 lr:0.00016749775236296963 tokens_per_second_per_gpu:774.6148679301359 +Step 2190 | loss:2.118544816970825 lr:0.00016746871423061865 tokens_per_second_per_gpu:752.3506952176687 +Step 2191 | loss:2.0476016998291016 lr:0.0001674396656520008 tokens_per_second_per_gpu:763.7602885612374 +Step 2192 | loss:2.178569793701172 lr:0.00016741060663161373 tokens_per_second_per_gpu:764.2914751398152 +Step 2193 | loss:2.0885872840881348 lr:0.0001673815371739566 tokens_per_second_per_gpu:777.7104971990109 +Step 2194 | loss:2.1556143760681152 lr:0.00016735245728353036 tokens_per_second_per_gpu:723.0309269330403 +Step 2195 | loss:2.0973198413848877 lr:0.00016732336696483743 tokens_per_second_per_gpu:753.0497304311311 +Step 2196 | loss:2.1500487327575684 lr:0.0001672942662223819 tokens_per_second_per_gpu:775.9120291138868 +Step 2197 | loss:2.124257802963257 lr:0.00016726515506066956 tokens_per_second_per_gpu:747.473161784473 +Step 2198 | loss:2.0885629653930664 lr:0.00016723603348420762 tokens_per_second_per_gpu:760.9475293521963 +Step 2199 | loss:2.1259396076202393 lr:0.00016720690149750508 tokens_per_second_per_gpu:758.6785251111812 +Step 2200 | loss:2.146131992340088 lr:0.0001671777591050724 tokens_per_second_per_gpu:771.2910654773781 +Step 2201 | loss:2.0839004516601562 lr:0.00016714860631142185 tokens_per_second_per_gpu:762.9141727255951 +Step 2202 | loss:2.1325576305389404 lr:0.0001671194431210671 tokens_per_second_per_gpu:794.6023035726299 +Step 2203 | loss:2.1647655963897705 lr:0.0001670902695385236 tokens_per_second_per_gpu:796.1179101172798 +Step 2204 | loss:2.0998382568359375 lr:0.00016706108556830825 tokens_per_second_per_gpu:756.3208953995646 +Step 2205 | loss:2.104659080505371 lr:0.0001670318912149397 tokens_per_second_per_gpu:759.1019970883792 +Step 2206 | loss:2.143609046936035 lr:0.00016700268648293815 tokens_per_second_per_gpu:780.0925622181604 +Step 2207 | loss:2.1174938678741455 lr:0.00016697347137682535 tokens_per_second_per_gpu:784.2935624441078 +Step 2208 | loss:2.085268020629883 lr:0.00016694424590112477 tokens_per_second_per_gpu:739.6704390862018 +Step 2209 | loss:2.138864040374756 lr:0.0001669150100603614 tokens_per_second_per_gpu:732.3278843168811 +Step 2210 | loss:2.101105213165283 lr:0.0001668857638590619 tokens_per_second_per_gpu:795.1559885050943 +Step 2211 | loss:2.1342036724090576 lr:0.00016685650730175445 tokens_per_second_per_gpu:772.5485257377101 +Step 2212 | loss:2.1620097160339355 lr:0.00016682724039296888 tokens_per_second_per_gpu:780.2540552403008 +Step 2213 | loss:2.1420538425445557 lr:0.00016679796313723668 tokens_per_second_per_gpu:785.0007971197083 +Step 2214 | loss:2.1158909797668457 lr:0.00016676867553909078 tokens_per_second_per_gpu:771.0528328230159 +Step 2215 | loss:2.10591983795166 lr:0.00016673937760306595 tokens_per_second_per_gpu:771.4315838270581 +Step 2216 | loss:2.154237747192383 lr:0.0001667100693336983 tokens_per_second_per_gpu:769.4553653743677 +Step 2217 | loss:2.1231424808502197 lr:0.00016668075073552574 tokens_per_second_per_gpu:763.2714105594944 +Step 2218 | loss:2.155219316482544 lr:0.00016665142181308771 tokens_per_second_per_gpu:762.2034042042956 +Step 2219 | loss:2.0720293521881104 lr:0.00016662208257092523 tokens_per_second_per_gpu:765.5097238404787 +Step 2220 | loss:2.110543727874756 lr:0.0001665927330135809 tokens_per_second_per_gpu:792.6864688787363 +Step 2221 | loss:2.1721034049987793 lr:0.00016656337314559897 tokens_per_second_per_gpu:787.8012022723025 +Step 2222 | loss:2.1302382946014404 lr:0.00016653400297152532 tokens_per_second_per_gpu:745.5833745148818 +Step 2223 | loss:2.17319917678833 lr:0.00016650462249590727 tokens_per_second_per_gpu:790.924377417529 +Step 2224 | loss:2.112234115600586 lr:0.0001664752317232939 tokens_per_second_per_gpu:796.6880484775689 +Step 2225 | loss:2.1768174171447754 lr:0.0001664458306582358 tokens_per_second_per_gpu:751.9815402549967 +Step 2226 | loss:2.0312678813934326 lr:0.0001664164193052852 tokens_per_second_per_gpu:760.1846946154282 +Step 2227 | loss:2.089902877807617 lr:0.00016638699766899587 tokens_per_second_per_gpu:762.2306029709082 +Step 2228 | loss:2.1461973190307617 lr:0.00016635756575392324 tokens_per_second_per_gpu:776.2446366044185 +Step 2229 | loss:2.084148645401001 lr:0.00016632812356462423 tokens_per_second_per_gpu:788.3612589822966 +Step 2230 | loss:2.1524877548217773 lr:0.00016629867110565745 tokens_per_second_per_gpu:776.9686097624682 +Step 2231 | loss:2.097721576690674 lr:0.00016626920838158307 tokens_per_second_per_gpu:776.5426215037118 +Step 2232 | loss:2.1421356201171875 lr:0.00016623973539696283 tokens_per_second_per_gpu:764.0542356329614 +Step 2233 | loss:2.1121649742126465 lr:0.00016621025215636002 tokens_per_second_per_gpu:772.8038515612592 +Step 2234 | loss:2.0952842235565186 lr:0.00016618075866433967 tokens_per_second_per_gpu:783.2693820948695 +Step 2235 | loss:2.1815872192382812 lr:0.00016615125492546823 tokens_per_second_per_gpu:791.24651649117 +Step 2236 | loss:2.1171605587005615 lr:0.00016612174094431377 tokens_per_second_per_gpu:757.3506726237898 +Step 2237 | loss:2.12265944480896 lr:0.00016609221672544603 tokens_per_second_per_gpu:776.5399327237703 +Step 2238 | loss:2.0895540714263916 lr:0.0001660626822734363 tokens_per_second_per_gpu:762.495594674242 +Step 2239 | loss:2.175658941268921 lr:0.00016603313759285738 tokens_per_second_per_gpu:755.8711697367464 +Step 2240 | loss:2.0703835487365723 lr:0.00016600358268828376 tokens_per_second_per_gpu:775.8619642136634 +Step 2241 | loss:2.1464591026306152 lr:0.00016597401756429138 tokens_per_second_per_gpu:782.6883704448464 +Step 2242 | loss:2.136406421661377 lr:0.00016594444222545798 tokens_per_second_per_gpu:764.6457818459413 +Step 2243 | loss:2.054914712905884 lr:0.00016591485667636263 tokens_per_second_per_gpu:756.404567828024 +Step 2244 | loss:2.053680419921875 lr:0.00016588526092158615 tokens_per_second_per_gpu:753.6363514707854 +Step 2245 | loss:2.1656718254089355 lr:0.0001658556549657109 tokens_per_second_per_gpu:770.7021645632625 +Step 2246 | loss:2.1275246143341064 lr:0.00016582603881332077 tokens_per_second_per_gpu:785.7778185544278 +Step 2247 | loss:2.1331639289855957 lr:0.0001657964124690013 tokens_per_second_per_gpu:754.6909313690888 +Step 2248 | loss:2.116572618484497 lr:0.00016576677593733953 tokens_per_second_per_gpu:746.2711944159873 +Step 2249 | loss:2.068542957305908 lr:0.00016573712922292417 tokens_per_second_per_gpu:773.3591606945331 +Step 2250 | loss:2.0950846672058105 lr:0.0001657074723303454 tokens_per_second_per_gpu:772.9352828831938 +Step 2251 | loss:2.1417734622955322 lr:0.00016567780526419512 tokens_per_second_per_gpu:757.747497376794 +Step 2252 | loss:2.1079354286193848 lr:0.00016564812802906666 tokens_per_second_per_gpu:781.6374378287932 +Step 2253 | loss:2.1105966567993164 lr:0.00016561844062955498 tokens_per_second_per_gpu:751.7601075064919 +Step 2254 | loss:2.1039774417877197 lr:0.00016558874307025668 tokens_per_second_per_gpu:789.2217467038314 +Step 2255 | loss:2.1410391330718994 lr:0.00016555903535576976 tokens_per_second_per_gpu:770.7017530107078 +Step 2256 | loss:2.1742050647735596 lr:0.00016552931749069403 tokens_per_second_per_gpu:787.6225926775555 +Step 2257 | loss:2.0738868713378906 lr:0.00016549958947963066 tokens_per_second_per_gpu:785.7029582908486 +Step 2258 | loss:2.202247381210327 lr:0.00016546985132718248 tokens_per_second_per_gpu:765.6783737818295 +Step 2259 | loss:2.1329901218414307 lr:0.00016544010303795394 tokens_per_second_per_gpu:781.5762232212315 +Step 2260 | loss:2.169905185699463 lr:0.00016541034461655096 tokens_per_second_per_gpu:767.8517092306124 +Step 2261 | loss:2.0951733589172363 lr:0.00016538057606758108 tokens_per_second_per_gpu:785.0697689371016 +Step 2262 | loss:2.155827522277832 lr:0.00016535079739565342 tokens_per_second_per_gpu:799.3163200507893 +Step 2263 | loss:2.0878798961639404 lr:0.00016532100860537863 tokens_per_second_per_gpu:731.000783723759 +Step 2264 | loss:2.131330966949463 lr:0.00016529120970136893 tokens_per_second_per_gpu:773.9384790721298 +Step 2265 | loss:2.1443142890930176 lr:0.0001652614006882382 tokens_per_second_per_gpu:785.3938598433413 +Step 2266 | loss:2.075765371322632 lr:0.0001652315815706017 tokens_per_second_per_gpu:755.961935785438 +Step 2267 | loss:2.138584852218628 lr:0.00016520175235307645 tokens_per_second_per_gpu:776.6418400964869 +Step 2268 | loss:2.107165813446045 lr:0.00016517191304028087 tokens_per_second_per_gpu:779.5058135074614 +Step 2269 | loss:2.1036975383758545 lr:0.0001651420636368351 tokens_per_second_per_gpu:779.7082423170228 +Step 2270 | loss:2.125897169113159 lr:0.00016511220414736072 tokens_per_second_per_gpu:777.8310862167191 +Step 2271 | loss:2.0617756843566895 lr:0.0001650823345764809 tokens_per_second_per_gpu:769.7944643178644 +Step 2272 | loss:2.1533172130584717 lr:0.00016505245492882042 tokens_per_second_per_gpu:772.7365890592993 +Step 2273 | loss:2.1013214588165283 lr:0.00016502256520900551 tokens_per_second_per_gpu:772.8765469809128 +Step 2274 | loss:2.0809998512268066 lr:0.00016499266542166412 tokens_per_second_per_gpu:765.5393644265754 +Step 2275 | loss:2.12670636177063 lr:0.00016496275557142565 tokens_per_second_per_gpu:790.2784752717893 +Step 2276 | loss:2.1144847869873047 lr:0.00016493283566292104 tokens_per_second_per_gpu:760.7751216191474 +Step 2277 | loss:2.1572537422180176 lr:0.00016490290570078287 tokens_per_second_per_gpu:786.6463445220043 +Step 2278 | loss:2.177063465118408 lr:0.00016487296568964524 tokens_per_second_per_gpu:787.6065428379391 +Step 2279 | loss:2.1356208324432373 lr:0.00016484301563414374 tokens_per_second_per_gpu:741.4552031093931 +Step 2280 | loss:2.1268413066864014 lr:0.00016481305553891563 tokens_per_second_per_gpu:792.7517853570357 +Step 2281 | loss:2.0677664279937744 lr:0.00016478308540859965 tokens_per_second_per_gpu:768.2536335221722 +Step 2282 | loss:2.1166510581970215 lr:0.00016475310524783612 tokens_per_second_per_gpu:782.1579190932604 +Step 2283 | loss:2.120037078857422 lr:0.00016472311506126689 tokens_per_second_per_gpu:735.5829252043433 +Step 2284 | loss:2.135716438293457 lr:0.0001646931148535354 tokens_per_second_per_gpu:764.6938559193279 +Step 2285 | loss:2.092515230178833 lr:0.00016466310462928663 tokens_per_second_per_gpu:782.0991076202862 +Step 2286 | loss:2.1212925910949707 lr:0.00016463308439316706 tokens_per_second_per_gpu:788.254323513911 +Step 2287 | loss:2.0850017070770264 lr:0.00016460305414982477 tokens_per_second_per_gpu:791.2844862130564 +Step 2288 | loss:2.0731801986694336 lr:0.00016457301390390943 tokens_per_second_per_gpu:735.5674277638044 +Step 2289 | loss:2.142714738845825 lr:0.00016454296366007217 tokens_per_second_per_gpu:786.1322539964228 +Step 2290 | loss:2.1164133548736572 lr:0.00016451290342296574 tokens_per_second_per_gpu:724.2015385933787 +Step 2291 | loss:2.1421902179718018 lr:0.00016448283319724433 tokens_per_second_per_gpu:768.0143924788031 +Step 2292 | loss:2.083502769470215 lr:0.00016445275298756378 tokens_per_second_per_gpu:772.7208844770045 +Step 2293 | loss:2.118074655532837 lr:0.00016442266279858151 tokens_per_second_per_gpu:787.1988470577406 +Step 2294 | loss:2.0938096046447754 lr:0.0001643925626349564 tokens_per_second_per_gpu:771.7954339887451 +Step 2295 | loss:2.1322875022888184 lr:0.00016436245250134882 tokens_per_second_per_gpu:783.395842269008 +Step 2296 | loss:2.098266363143921 lr:0.00016433233240242085 tokens_per_second_per_gpu:777.7867325684944 +Step 2297 | loss:2.1272664070129395 lr:0.00016430220234283597 tokens_per_second_per_gpu:782.8692145118682 +Step 2298 | loss:2.1018104553222656 lr:0.0001642720623272593 tokens_per_second_per_gpu:780.2922743230222 +Step 2299 | loss:2.055251359939575 lr:0.0001642419123603574 tokens_per_second_per_gpu:787.1274885517342 +Step 2300 | loss:2.1170198917388916 lr:0.0001642117524467985 tokens_per_second_per_gpu:759.1263213603787 +Step 2301 | loss:2.0968263149261475 lr:0.00016418158259125218 tokens_per_second_per_gpu:749.5948288761429 +Step 2302 | loss:2.144526243209839 lr:0.00016415140279838982 tokens_per_second_per_gpu:790.9089517424679 +Step 2303 | loss:2.070159435272217 lr:0.0001641212130728841 tokens_per_second_per_gpu:789.7164881769193 +Step 2304 | loss:2.078291893005371 lr:0.00016409101341940938 tokens_per_second_per_gpu:787.6841731349837 +Step 2305 | loss:2.1107096672058105 lr:0.00016406080384264148 tokens_per_second_per_gpu:758.3453691908264 +Step 2306 | loss:2.0945708751678467 lr:0.00016403058434725782 tokens_per_second_per_gpu:775.2518277391252 +Step 2307 | loss:2.0930354595184326 lr:0.00016400035493793728 tokens_per_second_per_gpu:768.8996626281205 +Step 2308 | loss:2.1311182975769043 lr:0.00016397011561936035 tokens_per_second_per_gpu:763.9572882944892 +Step 2309 | loss:2.1276330947875977 lr:0.00016393986639620903 tokens_per_second_per_gpu:776.7458454662087 +Step 2310 | loss:2.168919086456299 lr:0.00016390960727316682 tokens_per_second_per_gpu:773.4115022851705 +Step 2311 | loss:2.1214089393615723 lr:0.00016387933825491878 tokens_per_second_per_gpu:786.5521693625121 +Step 2312 | loss:2.051140308380127 lr:0.0001638490593461515 tokens_per_second_per_gpu:782.5879478943563 +Step 2313 | loss:2.2004079818725586 lr:0.00016381877055155316 tokens_per_second_per_gpu:760.708990433087 +Step 2314 | loss:2.111997127532959 lr:0.00016378847187581332 tokens_per_second_per_gpu:766.2432767678655 +Step 2315 | loss:2.1008784770965576 lr:0.00016375816332362322 tokens_per_second_per_gpu:782.5952407107347 +Step 2316 | loss:2.154395580291748 lr:0.00016372784489967557 tokens_per_second_per_gpu:720.412841484076 +Step 2317 | loss:2.1579127311706543 lr:0.00016369751660866454 tokens_per_second_per_gpu:774.5585503502838 +Step 2318 | loss:2.1173081398010254 lr:0.00016366717845528602 tokens_per_second_per_gpu:776.0965893149939 +Step 2319 | loss:2.1313316822052 lr:0.0001636368304442372 tokens_per_second_per_gpu:792.5207443884316 +Step 2320 | loss:2.10483980178833 lr:0.00016360647258021696 tokens_per_second_per_gpu:761.5172461345456 +Step 2321 | loss:2.125856876373291 lr:0.00016357610486792562 tokens_per_second_per_gpu:774.7466446734803 +Step 2322 | loss:2.0508623123168945 lr:0.0001635457273120651 tokens_per_second_per_gpu:781.5074623452674 +Step 2323 | loss:2.0868988037109375 lr:0.00016351533991733872 tokens_per_second_per_gpu:774.5844835749175 +Step 2324 | loss:2.1341395378112793 lr:0.00016348494268845145 tokens_per_second_per_gpu:766.8546838564571 +Step 2325 | loss:2.1221680641174316 lr:0.00016345453563010968 tokens_per_second_per_gpu:752.5418835573865 +Step 2326 | loss:2.1252501010894775 lr:0.00016342411874702142 tokens_per_second_per_gpu:786.9763811256582 +Step 2327 | loss:2.1098647117614746 lr:0.00016339369204389616 tokens_per_second_per_gpu:742.9861434013643 +Step 2328 | loss:2.1554455757141113 lr:0.00016336325552544488 tokens_per_second_per_gpu:749.9046405960374 +Step 2329 | loss:2.1807870864868164 lr:0.00016333280919638015 tokens_per_second_per_gpu:787.9956023168941 +Step 2330 | loss:2.083862066268921 lr:0.00016330235306141595 tokens_per_second_per_gpu:784.9847697752284 +Step 2331 | loss:2.129946708679199 lr:0.00016327188712526787 tokens_per_second_per_gpu:746.3310909512231 +Step 2332 | loss:2.1031877994537354 lr:0.000163241411392653 tokens_per_second_per_gpu:757.82461317472 +Step 2333 | loss:2.128164529800415 lr:0.0001632109258682899 tokens_per_second_per_gpu:761.5520683999191 +Step 2334 | loss:2.128422260284424 lr:0.00016318043055689872 tokens_per_second_per_gpu:784.5841139750898 +Step 2335 | loss:2.1257987022399902 lr:0.0001631499254632011 tokens_per_second_per_gpu:788.4584346544807 +Step 2336 | loss:2.1210761070251465 lr:0.00016311941059192012 tokens_per_second_per_gpu:759.7634741222731 +Step 2337 | loss:2.1220693588256836 lr:0.0001630888859477805 tokens_per_second_per_gpu:775.7684663273232 +Step 2338 | loss:2.125825881958008 lr:0.0001630583515355084 tokens_per_second_per_gpu:758.334789956198 +Step 2339 | loss:2.057013988494873 lr:0.00016302780735983147 tokens_per_second_per_gpu:770.3193568974857 +Step 2340 | loss:2.0726356506347656 lr:0.00016299725342547894 tokens_per_second_per_gpu:748.5634675305688 +Step 2341 | loss:2.133056640625 lr:0.00016296668973718144 tokens_per_second_per_gpu:734.2595446635238 +Step 2342 | loss:2.0871195793151855 lr:0.0001629361162996713 tokens_per_second_per_gpu:789.2396477815585 +Step 2343 | loss:2.192729949951172 lr:0.00016290553311768216 tokens_per_second_per_gpu:739.9467725623597 +Step 2344 | loss:2.125359535217285 lr:0.00016287494019594928 tokens_per_second_per_gpu:737.114919555233 +Step 2345 | loss:2.0856215953826904 lr:0.00016284433753920943 tokens_per_second_per_gpu:756.0527868425451 +Step 2346 | loss:2.124152660369873 lr:0.00016281372515220078 tokens_per_second_per_gpu:780.9832237856893 +Step 2347 | loss:2.096114158630371 lr:0.00016278310303966315 tokens_per_second_per_gpu:780.4235776533174 +Step 2348 | loss:2.1353745460510254 lr:0.00016275247120633779 tokens_per_second_per_gpu:765.1623013178164 +Step 2349 | loss:2.0940775871276855 lr:0.00016272182965696742 tokens_per_second_per_gpu:794.605285522856 +Step 2350 | loss:2.1742684841156006 lr:0.0001626911783962964 tokens_per_second_per_gpu:786.14810923074 +Step 2351 | loss:2.1297268867492676 lr:0.00016266051742907042 tokens_per_second_per_gpu:771.2526824670151 +Step 2352 | loss:2.163879871368408 lr:0.00016262984676003678 tokens_per_second_per_gpu:776.1305087596031 +Step 2353 | loss:2.137047529220581 lr:0.0001625991663939443 tokens_per_second_per_gpu:759.4774633928322 +Step 2354 | loss:2.108860731124878 lr:0.0001625684763355432 tokens_per_second_per_gpu:795.6674042145575 +Step 2355 | loss:2.135316848754883 lr:0.0001625377765895853 tokens_per_second_per_gpu:738.2735654707815 +Step 2356 | loss:2.130683422088623 lr:0.00016250706716082388 tokens_per_second_per_gpu:784.6052991012183 +Step 2357 | loss:2.1442525386810303 lr:0.0001624763480540137 tokens_per_second_per_gpu:764.0315535545217 +Step 2358 | loss:2.165719985961914 lr:0.00016244561927391103 tokens_per_second_per_gpu:783.7673838823921 +Step 2359 | loss:2.119202136993408 lr:0.00016241488082527366 tokens_per_second_per_gpu:770.3737409207102 +Step 2360 | loss:2.056586742401123 lr:0.0001623841327128609 tokens_per_second_per_gpu:766.3611379072856 +Step 2361 | loss:2.1794750690460205 lr:0.0001623533749414335 tokens_per_second_per_gpu:773.3435184861239 +Step 2362 | loss:2.1249656677246094 lr:0.00016232260751575367 tokens_per_second_per_gpu:760.9330689381419 +Step 2363 | loss:2.067558526992798 lr:0.0001622918304405852 tokens_per_second_per_gpu:730.2676128781915 +Step 2364 | loss:2.0897326469421387 lr:0.00016226104372069338 tokens_per_second_per_gpu:772.9583331514283 +Step 2365 | loss:2.1100072860717773 lr:0.0001622302473608449 tokens_per_second_per_gpu:781.7972954290977 +Step 2366 | loss:2.119893789291382 lr:0.00016219944136580807 tokens_per_second_per_gpu:787.9214187107134 +Step 2367 | loss:2.0908751487731934 lr:0.00016216862574035257 tokens_per_second_per_gpu:793.7920109515812 +Step 2368 | loss:2.11960506439209 lr:0.00016213780048924962 tokens_per_second_per_gpu:764.9182099318192 +Step 2369 | loss:2.173107147216797 lr:0.00016210696561727196 tokens_per_second_per_gpu:781.5010562278977 +Step 2370 | loss:2.143449306488037 lr:0.00016207612112919376 tokens_per_second_per_gpu:779.7382376218171 +Step 2371 | loss:2.094942569732666 lr:0.00016204526702979076 tokens_per_second_per_gpu:763.1637287156352 +Step 2372 | loss:2.0737555027008057 lr:0.0001620144033238401 tokens_per_second_per_gpu:727.3555176036243 +Step 2373 | loss:2.125936985015869 lr:0.00016198353001612047 tokens_per_second_per_gpu:743.5003227458043 +Step 2374 | loss:2.083824872970581 lr:0.000161952647111412 tokens_per_second_per_gpu:786.1421876326277 +Step 2375 | loss:2.1310629844665527 lr:0.00016192175461449633 tokens_per_second_per_gpu:789.1055102145191 +Step 2376 | loss:2.1224985122680664 lr:0.00016189085253015656 tokens_per_second_per_gpu:773.957610082839 +Step 2377 | loss:2.0823140144348145 lr:0.0001618599408631774 tokens_per_second_per_gpu:775.4193748538962 +Step 2378 | loss:2.143376111984253 lr:0.00016182901961834484 tokens_per_second_per_gpu:759.951331038866 +Step 2379 | loss:2.047396183013916 lr:0.00016179808880044654 tokens_per_second_per_gpu:748.4301913479674 +Step 2380 | loss:2.13728928565979 lr:0.00016176714841427146 tokens_per_second_per_gpu:779.9181148024479 +Step 2381 | loss:2.126053810119629 lr:0.0001617361984646102 tokens_per_second_per_gpu:798.4647908952559 +Step 2382 | loss:2.110058069229126 lr:0.0001617052389562548 tokens_per_second_per_gpu:749.0223577111105 +Step 2383 | loss:2.1510846614837646 lr:0.0001616742698939987 tokens_per_second_per_gpu:764.8466837880185 +Step 2384 | loss:2.1232848167419434 lr:0.0001616432912826369 tokens_per_second_per_gpu:793.2325877917527 +Step 2385 | loss:2.1634509563446045 lr:0.00016161230312696588 tokens_per_second_per_gpu:767.0931608139797 +Step 2386 | loss:2.0665013790130615 lr:0.00016158130543178357 tokens_per_second_per_gpu:783.5641636036414 +Step 2387 | loss:2.0440049171447754 lr:0.00016155029820188937 tokens_per_second_per_gpu:772.8280310497047 +Step 2388 | loss:2.0965936183929443 lr:0.00016151928144208418 tokens_per_second_per_gpu:737.4046192033979 +Step 2389 | loss:2.162389039993286 lr:0.00016148825515717032 tokens_per_second_per_gpu:767.9385030366313 +Step 2390 | loss:2.113396167755127 lr:0.00016145721935195172 tokens_per_second_per_gpu:765.7978032154881 +Step 2391 | loss:2.1961283683776855 lr:0.00016142617403123365 tokens_per_second_per_gpu:769.8255883115464 +Step 2392 | loss:2.086794853210449 lr:0.00016139511919982283 tokens_per_second_per_gpu:752.5308449744175 +Step 2393 | loss:2.0673987865448 lr:0.0001613640548625276 tokens_per_second_per_gpu:753.1035052151751 +Step 2394 | loss:2.104055643081665 lr:0.0001613329810241577 tokens_per_second_per_gpu:782.807793795508 +Step 2395 | loss:2.088810682296753 lr:0.00016130189768952423 tokens_per_second_per_gpu:764.0778045022691 +Step 2396 | loss:2.078077793121338 lr:0.00016127080486343998 tokens_per_second_per_gpu:766.7142058592394 +Step 2397 | loss:2.103234052658081 lr:0.00016123970255071902 tokens_per_second_per_gpu:773.6673186981743 +Step 2398 | loss:2.107832431793213 lr:0.00016120859075617703 tokens_per_second_per_gpu:769.8074990523861 +Step 2399 | loss:2.1533076763153076 lr:0.000161177469484631 tokens_per_second_per_gpu:770.0204319690586 +Step 2400 | loss:2.1223795413970947 lr:0.00016114633874089954 tokens_per_second_per_gpu:740.0146679513095 +Step 2401 | loss:2.2051517963409424 lr:0.00016111519852980263 tokens_per_second_per_gpu:755.785950024049 +Step 2402 | loss:2.1988651752471924 lr:0.00016108404885616174 tokens_per_second_per_gpu:771.0287142289358 +Step 2403 | loss:2.1267638206481934 lr:0.00016105288972479987 tokens_per_second_per_gpu:760.094158121057 +Step 2404 | loss:2.0604684352874756 lr:0.00016102172114054137 tokens_per_second_per_gpu:774.7694154640727 +Step 2405 | loss:2.1173057556152344 lr:0.00016099054310821215 tokens_per_second_per_gpu:769.1176931896678 +Step 2406 | loss:2.08412504196167 lr:0.0001609593556326395 tokens_per_second_per_gpu:746.7858467754294 +Step 2407 | loss:2.0772287845611572 lr:0.00016092815871865228 tokens_per_second_per_gpu:777.2867814183558 +Step 2408 | loss:2.0900020599365234 lr:0.00016089695237108068 tokens_per_second_per_gpu:774.1366319871889 +Step 2409 | loss:2.0874595642089844 lr:0.0001608657365947565 tokens_per_second_per_gpu:761.4730586165689 +Step 2410 | loss:2.103834629058838 lr:0.0001608345113945128 tokens_per_second_per_gpu:738.9884627028705 +Step 2411 | loss:2.0564675331115723 lr:0.0001608032767751843 tokens_per_second_per_gpu:726.6111210781297 +Step 2412 | loss:2.1063055992126465 lr:0.0001607720327416071 tokens_per_second_per_gpu:768.31731954665 +Step 2413 | loss:2.1105856895446777 lr:0.00016074077929861876 tokens_per_second_per_gpu:774.938668458956 +Step 2414 | loss:2.081789016723633 lr:0.00016070951645105822 tokens_per_second_per_gpu:755.2398614431925 +Step 2415 | loss:2.12666392326355 lr:0.00016067824420376602 tokens_per_second_per_gpu:775.8298515363904 +Step 2416 | loss:2.1335535049438477 lr:0.00016064696256158406 tokens_per_second_per_gpu:755.1245955207432 +Step 2417 | loss:2.045836925506592 lr:0.00016061567152935572 tokens_per_second_per_gpu:788.4775327439305 +Step 2418 | loss:2.0872466564178467 lr:0.0001605843711119258 tokens_per_second_per_gpu:781.7274658655499 +Step 2419 | loss:2.0917835235595703 lr:0.0001605530613141406 tokens_per_second_per_gpu:749.1492551059459 +Step 2420 | loss:2.10684871673584 lr:0.00016052174214084786 tokens_per_second_per_gpu:773.2875582030198 +Step 2421 | loss:2.079437017440796 lr:0.00016049041359689675 tokens_per_second_per_gpu:781.8071997984422 +Step 2422 | loss:2.115262508392334 lr:0.00016045907568713798 tokens_per_second_per_gpu:762.2566356256083 +Step 2423 | loss:2.0792784690856934 lr:0.00016042772841642355 tokens_per_second_per_gpu:780.8541827130587 +Step 2424 | loss:2.092702627182007 lr:0.00016039637178960704 tokens_per_second_per_gpu:785.2377842461249 +Step 2425 | loss:2.171398639678955 lr:0.00016036500581154343 tokens_per_second_per_gpu:769.3830925104844 +Step 2426 | loss:2.102694511413574 lr:0.00016033363048708913 tokens_per_second_per_gpu:740.6786396094755 +Step 2427 | loss:2.117218255996704 lr:0.0001603022458211021 tokens_per_second_per_gpu:762.3229623533643 +Step 2428 | loss:2.1262497901916504 lr:0.00016027085181844156 tokens_per_second_per_gpu:756.1632800220924 +Step 2429 | loss:2.089413642883301 lr:0.00016023944848396834 tokens_per_second_per_gpu:744.1854454281503 +Step 2430 | loss:2.1859631538391113 lr:0.00016020803582254467 tokens_per_second_per_gpu:762.9704670910414 +Step 2431 | loss:2.1253488063812256 lr:0.0001601766138390342 tokens_per_second_per_gpu:777.4656580447476 +Step 2432 | loss:2.077880859375 lr:0.000160145182538302 tokens_per_second_per_gpu:769.1158668965514 +Step 2433 | loss:2.0315496921539307 lr:0.00016011374192521468 tokens_per_second_per_gpu:753.1409943291344 +Step 2434 | loss:2.144782543182373 lr:0.00016008229200464022 tokens_per_second_per_gpu:761.3858339870634 +Step 2435 | loss:2.1020572185516357 lr:0.00016005083278144798 tokens_per_second_per_gpu:729.0999046363293 +Step 2436 | loss:2.133963108062744 lr:0.00016001936426050892 tokens_per_second_per_gpu:767.0816208300348 +Step 2437 | loss:2.1006436347961426 lr:0.00015998788644669532 tokens_per_second_per_gpu:740.5138791025182 +Step 2438 | loss:2.114340305328369 lr:0.0001599563993448809 tokens_per_second_per_gpu:772.824053215616 +Step 2439 | loss:2.0661768913269043 lr:0.00015992490295994088 tokens_per_second_per_gpu:766.2797892967848 +Step 2440 | loss:2.132153272628784 lr:0.00015989339729675188 tokens_per_second_per_gpu:759.6720614997793 +Step 2441 | loss:2.1622040271759033 lr:0.00015986188236019196 tokens_per_second_per_gpu:782.4382724590577 +Step 2442 | loss:2.1019127368927 lr:0.00015983035815514063 tokens_per_second_per_gpu:754.7426456607612 +Step 2443 | loss:2.1219539642333984 lr:0.00015979882468647878 tokens_per_second_per_gpu:760.6250330040368 +Step 2444 | loss:2.087062120437622 lr:0.00015976728195908884 tokens_per_second_per_gpu:776.499118408777 +Step 2445 | loss:2.0720877647399902 lr:0.00015973572997785452 tokens_per_second_per_gpu:740.1505142931252 +Step 2446 | loss:2.1506588459014893 lr:0.00015970416874766118 tokens_per_second_per_gpu:762.9384626941109 +Step 2447 | loss:2.162705421447754 lr:0.0001596725982733954 tokens_per_second_per_gpu:751.2265005265682 +Step 2448 | loss:2.08237886428833 lr:0.00015964101855994527 tokens_per_second_per_gpu:770.7482205452138 +Step 2449 | loss:2.109455108642578 lr:0.00015960942961220034 tokens_per_second_per_gpu:757.925004913136 +Step 2450 | loss:2.1913700103759766 lr:0.0001595778314350516 tokens_per_second_per_gpu:760.6012136170393 +Step 2451 | loss:2.1207306385040283 lr:0.00015954622403339136 tokens_per_second_per_gpu:763.1421698375328 +Step 2452 | loss:2.0965425968170166 lr:0.00015951460741211353 tokens_per_second_per_gpu:756.999948627464 +Step 2453 | loss:2.0838160514831543 lr:0.00015948298157611324 tokens_per_second_per_gpu:761.0466693823412 +Step 2454 | loss:2.1201958656311035 lr:0.00015945134653028728 tokens_per_second_per_gpu:783.1748608570678 +Step 2455 | loss:2.0548057556152344 lr:0.00015941970227953365 tokens_per_second_per_gpu:781.1939438954752 +Step 2456 | loss:2.101193904876709 lr:0.00015938804882875189 tokens_per_second_per_gpu:767.691949699611 +Step 2457 | loss:2.0798208713531494 lr:0.00015935638618284296 tokens_per_second_per_gpu:734.3735387768313 +Step 2458 | loss:2.1547911167144775 lr:0.00015932471434670925 tokens_per_second_per_gpu:741.7483119982159 +Step 2459 | loss:2.1183249950408936 lr:0.00015929303332525452 tokens_per_second_per_gpu:787.6410565113468 +Step 2460 | loss:2.0888171195983887 lr:0.00015926134312338396 tokens_per_second_per_gpu:775.0825905130822 +Step 2461 | loss:2.1105573177337646 lr:0.00015922964374600425 tokens_per_second_per_gpu:761.1560987309954 +Step 2462 | loss:2.110924482345581 lr:0.0001591979351980234 tokens_per_second_per_gpu:737.5478546058968 +Step 2463 | loss:2.1016664505004883 lr:0.00015916621748435095 tokens_per_second_per_gpu:777.6041603421494 +Step 2464 | loss:2.1337974071502686 lr:0.00015913449060989774 tokens_per_second_per_gpu:779.9987795553079 +Step 2465 | loss:2.0496127605438232 lr:0.00015910275457957612 tokens_per_second_per_gpu:761.1203941422323 +Step 2466 | loss:2.0982179641723633 lr:0.00015907100939829976 tokens_per_second_per_gpu:770.1321438301088 +Step 2467 | loss:2.125680923461914 lr:0.00015903925507098387 tokens_per_second_per_gpu:757.5579070517371 +Step 2468 | loss:2.133322238922119 lr:0.00015900749160254499 tokens_per_second_per_gpu:765.6251506464095 +Step 2469 | loss:2.149346113204956 lr:0.00015897571899790107 tokens_per_second_per_gpu:747.5303098651507 +Step 2470 | loss:2.116809606552124 lr:0.00015894393726197155 tokens_per_second_per_gpu:752.9559654941211 +Step 2471 | loss:2.039738655090332 lr:0.0001589121463996772 tokens_per_second_per_gpu:766.2978543441513 +Step 2472 | loss:2.1225385665893555 lr:0.00015888034641594026 tokens_per_second_per_gpu:747.2590621341506 +Step 2473 | loss:2.154592514038086 lr:0.00015884853731568436 tokens_per_second_per_gpu:757.8094348363835 +Step 2474 | loss:2.0867388248443604 lr:0.00015881671910383455 tokens_per_second_per_gpu:745.6576914008656 +Step 2475 | loss:2.0665123462677 lr:0.00015878489178531723 tokens_per_second_per_gpu:768.2026324340876 +Step 2476 | loss:2.086402416229248 lr:0.00015875305536506039 tokens_per_second_per_gpu:765.7768240403735 +Step 2477 | loss:2.132384777069092 lr:0.00015872120984799314 tokens_per_second_per_gpu:774.8086947006454 +Step 2478 | loss:2.0871901512145996 lr:0.0001586893552390463 tokens_per_second_per_gpu:777.5647113022862 +Step 2479 | loss:2.0736310482025146 lr:0.0001586574915431519 tokens_per_second_per_gpu:742.6673584441729 +Step 2480 | loss:2.1554994583129883 lr:0.00015862561876524338 tokens_per_second_per_gpu:741.1160555084475 +Step 2481 | loss:2.0222151279449463 lr:0.00015859373691025575 tokens_per_second_per_gpu:755.6660807701362 +Step 2482 | loss:2.125887870788574 lr:0.00015856184598312528 tokens_per_second_per_gpu:750.630118194398 +Step 2483 | loss:2.0322391986846924 lr:0.00015852994598878963 tokens_per_second_per_gpu:780.1113513419905 +Step 2484 | loss:2.055060863494873 lr:0.00015849803693218802 tokens_per_second_per_gpu:791.8985470586929 +Step 2485 | loss:2.066730260848999 lr:0.00015846611881826088 tokens_per_second_per_gpu:746.6363347966366 +Step 2486 | loss:2.166553020477295 lr:0.00015843419165195014 tokens_per_second_per_gpu:741.6965312973855 +Step 2487 | loss:2.110128879547119 lr:0.0001584022554381992 tokens_per_second_per_gpu:755.1294247916595 +Step 2488 | loss:2.0916757583618164 lr:0.00015837031018195268 tokens_per_second_per_gpu:739.4566617777898 +Step 2489 | loss:2.1162540912628174 lr:0.00015833835588815678 tokens_per_second_per_gpu:761.577226691863 +Step 2490 | loss:2.095524787902832 lr:0.000158306392561759 tokens_per_second_per_gpu:722.1781952934688 +Step 2491 | loss:2.1253812313079834 lr:0.00015827442020770825 tokens_per_second_per_gpu:755.8800339102539 +Step 2492 | loss:2.0898752212524414 lr:0.0001582424388309549 tokens_per_second_per_gpu:718.8095079992416 +Step 2493 | loss:2.139268636703491 lr:0.0001582104484364506 tokens_per_second_per_gpu:754.4193353306335 +Step 2494 | loss:2.082895517349243 lr:0.00015817844902914847 tokens_per_second_per_gpu:788.2146554612689 +Step 2495 | loss:2.1024327278137207 lr:0.0001581464406140031 tokens_per_second_per_gpu:758.4738617331702 +Step 2496 | loss:2.1214404106140137 lr:0.00015811442319597026 tokens_per_second_per_gpu:772.7294024706296 +Step 2497 | loss:2.120565414428711 lr:0.0001580823967800074 tokens_per_second_per_gpu:780.4189239305674 +Step 2498 | loss:2.183016300201416 lr:0.00015805036137107309 tokens_per_second_per_gpu:712.863578171391 +Step 2499 | loss:2.0807676315307617 lr:0.00015801831697412748 tokens_per_second_per_gpu:768.920267483522 +Step 2500 | loss:2.058767557144165 lr:0.000157986263594132 tokens_per_second_per_gpu:756.1402016153888 +Step 2501 | loss:2.161428928375244 lr:0.00015795420123604952 tokens_per_second_per_gpu:739.7880562703662 +Step 2502 | loss:2.1007518768310547 lr:0.00015792212990484438 tokens_per_second_per_gpu:765.3826767284578 +Step 2503 | loss:2.1592931747436523 lr:0.00015789004960548212 tokens_per_second_per_gpu:734.2892940664084 +Step 2504 | loss:2.1535720825195312 lr:0.0001578579603429298 tokens_per_second_per_gpu:780.9040774461189 +Step 2505 | loss:2.0908215045928955 lr:0.00015782586212215586 tokens_per_second_per_gpu:758.2476887924186 +Step 2506 | loss:2.1102378368377686 lr:0.00015779375494813015 tokens_per_second_per_gpu:769.1485650073619 +Step 2507 | loss:2.1129395961761475 lr:0.00015776163882582372 tokens_per_second_per_gpu:743.2841150551453 +Step 2508 | loss:2.038459300994873 lr:0.00015772951376020932 tokens_per_second_per_gpu:747.740485400898 +Step 2509 | loss:2.0823493003845215 lr:0.00015769737975626083 tokens_per_second_per_gpu:774.4548822697037 +Step 2510 | loss:2.099653959274292 lr:0.0001576652368189536 tokens_per_second_per_gpu:777.4477086678315 +Step 2511 | loss:2.108234405517578 lr:0.00015763308495326438 tokens_per_second_per_gpu:773.4653214607029 +Step 2512 | loss:2.103973865509033 lr:0.00015760092416417125 tokens_per_second_per_gpu:771.6312898472423 +Step 2513 | loss:2.128584861755371 lr:0.00015756875445665375 tokens_per_second_per_gpu:754.7945193503994 +Step 2514 | loss:2.129721164703369 lr:0.00015753657583569275 tokens_per_second_per_gpu:763.9275958393345 +Step 2515 | loss:2.1120526790618896 lr:0.00015750438830627048 tokens_per_second_per_gpu:759.2553376519614 +Step 2516 | loss:2.1269664764404297 lr:0.0001574721918733706 tokens_per_second_per_gpu:763.8771864878976 +Step 2517 | loss:2.0653488636016846 lr:0.00015743998654197812 tokens_per_second_per_gpu:771.0434211323384 +Step 2518 | loss:2.0919365882873535 lr:0.0001574077723170794 tokens_per_second_per_gpu:751.1703521993885 +Step 2519 | loss:2.1338911056518555 lr:0.00015737554920366227 tokens_per_second_per_gpu:753.4599086652071 +Step 2520 | loss:2.0781972408294678 lr:0.00015734331720671584 tokens_per_second_per_gpu:773.5017290241027 +Step 2521 | loss:2.1177468299865723 lr:0.00015731107633123063 tokens_per_second_per_gpu:766.3051604374594 +Step 2522 | loss:2.0958828926086426 lr:0.00015727882658219856 tokens_per_second_per_gpu:763.8347311980391 +Step 2523 | loss:2.0986549854278564 lr:0.00015724656796461286 tokens_per_second_per_gpu:758.651072779733 +Step 2524 | loss:2.127794027328491 lr:0.0001572143004834682 tokens_per_second_per_gpu:731.9217823080284 +Step 2525 | loss:2.104123115539551 lr:0.00015718202414376057 tokens_per_second_per_gpu:759.4260395575237 +Step 2526 | loss:2.087651491165161 lr:0.0001571497389504874 tokens_per_second_per_gpu:767.5284235222879 +Step 2527 | loss:2.0949418544769287 lr:0.0001571174449086474 tokens_per_second_per_gpu:737.9544457414869 +Step 2528 | loss:2.0867183208465576 lr:0.00015708514202324075 tokens_per_second_per_gpu:724.74151161028 +Step 2529 | loss:2.0597522258758545 lr:0.0001570528302992689 tokens_per_second_per_gpu:761.9151072738816 +Step 2530 | loss:2.0387136936187744 lr:0.00015702050974173473 tokens_per_second_per_gpu:749.5147823770078 +Step 2531 | loss:2.0715365409851074 lr:0.00015698818035564247 tokens_per_second_per_gpu:744.0545190087621 +Step 2532 | loss:2.087596893310547 lr:0.00015695584214599776 tokens_per_second_per_gpu:763.7185231271167 +Step 2533 | loss:2.115126609802246 lr:0.00015692349511780749 tokens_per_second_per_gpu:762.1793186759012 +Step 2534 | loss:2.0404438972473145 lr:0.00015689113927608005 tokens_per_second_per_gpu:773.907669863037 +Step 2535 | loss:2.1502585411071777 lr:0.00015685877462582514 tokens_per_second_per_gpu:762.829946806705 +Step 2536 | loss:2.0734975337982178 lr:0.00015682640117205377 tokens_per_second_per_gpu:740.2416657464619 +Step 2537 | loss:2.157959222793579 lr:0.00015679401891977837 tokens_per_second_per_gpu:773.5318072562384 +Step 2538 | loss:2.0870583057403564 lr:0.00015676162787401282 tokens_per_second_per_gpu:787.3416907294999 +Step 2539 | loss:2.106743812561035 lr:0.00015672922803977213 tokens_per_second_per_gpu:757.0693153036134 +Step 2540 | loss:2.1213603019714355 lr:0.00015669681942207287 tokens_per_second_per_gpu:777.302245582264 +Step 2541 | loss:2.0834903717041016 lr:0.00015666440202593296 tokens_per_second_per_gpu:769.4752615438716 +Step 2542 | loss:2.165099620819092 lr:0.00015663197585637155 tokens_per_second_per_gpu:784.4788458913122 +Step 2543 | loss:2.091434955596924 lr:0.00015659954091840924 tokens_per_second_per_gpu:764.893579492108 +Step 2544 | loss:2.0809097290039062 lr:0.00015656709721706798 tokens_per_second_per_gpu:740.6985951664597 +Step 2545 | loss:2.1148836612701416 lr:0.00015653464475737109 tokens_per_second_per_gpu:772.676920420744 +Step 2546 | loss:2.0475807189941406 lr:0.00015650218354434323 tokens_per_second_per_gpu:741.1498736742926 +Step 2547 | loss:2.046180009841919 lr:0.00015646971358301037 tokens_per_second_per_gpu:738.237702949527 +Step 2548 | loss:2.1104896068573 lr:0.0001564372348783999 tokens_per_second_per_gpu:774.0888511241972 +Step 2549 | loss:2.1264257431030273 lr:0.00015640474743554053 tokens_per_second_per_gpu:765.4347379028364 +Step 2550 | loss:2.096015691757202 lr:0.00015637225125946232 tokens_per_second_per_gpu:780.6292023560607 +Step 2551 | loss:2.149688243865967 lr:0.00015633974635519674 tokens_per_second_per_gpu:769.9497952069512 +Step 2552 | loss:2.072805643081665 lr:0.00015630723272777654 tokens_per_second_per_gpu:769.2734977860666 +Step 2553 | loss:2.096296548843384 lr:0.0001562747103822358 tokens_per_second_per_gpu:764.4468613218977 +Step 2554 | loss:2.0893313884735107 lr:0.0001562421793236101 tokens_per_second_per_gpu:766.9177813666004 +Step 2555 | loss:2.1102828979492188 lr:0.00015620963955693617 tokens_per_second_per_gpu:755.1581228902483 +Step 2556 | loss:2.09261417388916 lr:0.00015617709108725224 tokens_per_second_per_gpu:751.7179689063227 +Step 2557 | loss:2.1324520111083984 lr:0.0001561445339195978 tokens_per_second_per_gpu:803.9166111378921 +Step 2558 | loss:2.0982391834259033 lr:0.00015611196805901368 tokens_per_second_per_gpu:791.6840691498356 +Step 2559 | loss:2.1002283096313477 lr:0.0001560793935105422 tokens_per_second_per_gpu:773.6073036260931 +Step 2560 | loss:2.082869529724121 lr:0.00015604681027922684 tokens_per_second_per_gpu:747.3905569335193 +Step 2561 | loss:2.094778060913086 lr:0.00015601421837011252 tokens_per_second_per_gpu:760.4899519938198 +Step 2562 | loss:2.088927745819092 lr:0.00015598161778824552 tokens_per_second_per_gpu:757.4246898026212 +Step 2563 | loss:2.124210834503174 lr:0.00015594900853867333 tokens_per_second_per_gpu:781.1738102942045 +Step 2564 | loss:2.136063575744629 lr:0.000155916390626445 tokens_per_second_per_gpu:775.0837825876073 +Step 2565 | loss:2.078852653503418 lr:0.00015588376405661076 tokens_per_second_per_gpu:784.1591304696519 +Step 2566 | loss:2.109579086303711 lr:0.0001558511288342222 tokens_per_second_per_gpu:774.2504935447702 +Step 2567 | loss:2.0539355278015137 lr:0.00015581848496433226 tokens_per_second_per_gpu:743.1494842040443 +Step 2568 | loss:2.1232621669769287 lr:0.00015578583245199533 tokens_per_second_per_gpu:783.8534217851651 +Step 2569 | loss:2.096191167831421 lr:0.0001557531713022669 tokens_per_second_per_gpu:778.3075815272405 +Step 2570 | loss:2.126401901245117 lr:0.0001557205015202041 tokens_per_second_per_gpu:781.9816319744922 +Step 2571 | loss:2.130768299102783 lr:0.00015568782311086503 tokens_per_second_per_gpu:772.2307179474341 +Step 2572 | loss:2.0609655380249023 lr:0.00015565513607930954 tokens_per_second_per_gpu:784.8199923262079 +Step 2573 | loss:2.078847885131836 lr:0.00015562244043059844 tokens_per_second_per_gpu:767.4516048306278 +Step 2574 | loss:2.0641226768493652 lr:0.00015558973616979413 tokens_per_second_per_gpu:721.752227498427 +Step 2575 | loss:2.0923163890838623 lr:0.00015555702330196023 tokens_per_second_per_gpu:747.9392207305145 +Step 2576 | loss:2.022129535675049 lr:0.0001555243018321617 tokens_per_second_per_gpu:766.5703986323255 +Step 2577 | loss:2.088618755340576 lr:0.0001554915717654649 tokens_per_second_per_gpu:754.7974359003621 +Step 2578 | loss:2.1118316650390625 lr:0.00015545883310693741 tokens_per_second_per_gpu:748.9528524540129 +Step 2579 | loss:2.0970120429992676 lr:0.0001554260858616482 tokens_per_second_per_gpu:727.6665265683562 +Step 2580 | loss:2.0840702056884766 lr:0.00015539333003466757 tokens_per_second_per_gpu:785.6661931745207 +Step 2581 | loss:2.1128716468811035 lr:0.0001553605656310672 tokens_per_second_per_gpu:759.1250242304055 +Step 2582 | loss:2.0895626544952393 lr:0.00015532779265591999 tokens_per_second_per_gpu:779.403287215302 +Step 2583 | loss:2.1571249961853027 lr:0.00015529501111430025 tokens_per_second_per_gpu:787.1277794592813 +Step 2584 | loss:2.0821332931518555 lr:0.00015526222101128355 tokens_per_second_per_gpu:766.7095314018201 +Step 2585 | loss:2.0772361755371094 lr:0.00015522942235194682 tokens_per_second_per_gpu:743.5753523417044 +Step 2586 | loss:2.1019136905670166 lr:0.0001551966151413684 tokens_per_second_per_gpu:770.5655419197212 +Step 2587 | loss:2.101793050765991 lr:0.00015516379938462782 tokens_per_second_per_gpu:752.6868918735952 +Step 2588 | loss:2.126866340637207 lr:0.00015513097508680594 tokens_per_second_per_gpu:770.6232224978925 +Step 2589 | loss:2.0370333194732666 lr:0.00015509814225298505 tokens_per_second_per_gpu:763.1756939197684 +Step 2590 | loss:2.1233084201812744 lr:0.0001550653008882487 tokens_per_second_per_gpu:758.9272205413179 +Step 2591 | loss:2.021941900253296 lr:0.0001550324509976817 tokens_per_second_per_gpu:780.4875278892755 +Step 2592 | loss:2.0810770988464355 lr:0.0001549995925863703 tokens_per_second_per_gpu:789.4270402302049 +Step 2593 | loss:2.090183973312378 lr:0.000154966725659402 tokens_per_second_per_gpu:763.6551697128097 +Step 2594 | loss:2.0460426807403564 lr:0.00015493385022186562 tokens_per_second_per_gpu:766.8565477018665 +Step 2595 | loss:2.182563304901123 lr:0.00015490096627885128 tokens_per_second_per_gpu:783.6529048304956 +Step 2596 | loss:2.092287063598633 lr:0.0001548680738354505 tokens_per_second_per_gpu:757.5724458975526 +Step 2597 | loss:2.182421922683716 lr:0.00015483517289675603 tokens_per_second_per_gpu:776.5669967775956 +Step 2598 | loss:2.0929250717163086 lr:0.00015480226346786192 tokens_per_second_per_gpu:784.6108119019237 +Step 2599 | loss:2.057199001312256 lr:0.00015476934555386365 tokens_per_second_per_gpu:769.2384646468752 +Step 2600 | loss:2.1358537673950195 lr:0.0001547364191598579 tokens_per_second_per_gpu:766.0460240169555 +Step 2601 | loss:2.114349126815796 lr:0.00015470348429094273 tokens_per_second_per_gpu:743.4482264912663 +Step 2602 | loss:2.0744686126708984 lr:0.00015467054095221744 tokens_per_second_per_gpu:756.5952898871316 +Step 2603 | loss:2.101428508758545 lr:0.00015463758914878274 tokens_per_second_per_gpu:769.8035655112911 +Step 2604 | loss:2.118521213531494 lr:0.0001546046288857406 tokens_per_second_per_gpu:785.7054754965096 +Step 2605 | loss:2.0622904300689697 lr:0.00015457166016819428 tokens_per_second_per_gpu:760.356268363275 +Step 2606 | loss:2.127537727355957 lr:0.00015453868300124838 tokens_per_second_per_gpu:789.806691242493 +Step 2607 | loss:2.023883581161499 lr:0.00015450569739000876 tokens_per_second_per_gpu:774.553400896506 +Step 2608 | loss:2.145993709564209 lr:0.00015447270333958265 tokens_per_second_per_gpu:772.5361415933784 +Step 2609 | loss:2.0581908226013184 lr:0.0001544397008550786 tokens_per_second_per_gpu:770.4944513115914 +Step 2610 | loss:2.067187547683716 lr:0.00015440668994160637 tokens_per_second_per_gpu:778.5554367506398 +Step 2611 | loss:2.0416078567504883 lr:0.0001543736706042771 tokens_per_second_per_gpu:763.171790920257 +Step 2612 | loss:2.1349806785583496 lr:0.0001543406428482032 tokens_per_second_per_gpu:747.8782313917296 +Step 2613 | loss:2.0627269744873047 lr:0.00015430760667849844 tokens_per_second_per_gpu:774.4317266325605 +Step 2614 | loss:2.1204183101654053 lr:0.00015427456210027782 tokens_per_second_per_gpu:769.7077240782814 +Step 2615 | loss:2.0659945011138916 lr:0.0001542415091186577 tokens_per_second_per_gpu:755.5156988198485 +Step 2616 | loss:2.0999996662139893 lr:0.00015420844773875568 tokens_per_second_per_gpu:784.2334837579667 +Step 2617 | loss:2.0735726356506348 lr:0.0001541753779656907 tokens_per_second_per_gpu:762.7818060558881 +Step 2618 | loss:2.0619606971740723 lr:0.00015414229980458303 tokens_per_second_per_gpu:765.7764765529237 +Step 2619 | loss:2.0797080993652344 lr:0.00015410921326055422 tokens_per_second_per_gpu:779.8796414518466 +Step 2620 | loss:2.142120361328125 lr:0.000154076118338727 tokens_per_second_per_gpu:776.6928079202686 +Step 2621 | loss:2.1000561714172363 lr:0.0001540430150442256 tokens_per_second_per_gpu:771.0679776293108 +Step 2622 | loss:2.1167519092559814 lr:0.0001540099033821754 tokens_per_second_per_gpu:740.2376370696853 +Step 2623 | loss:2.087553024291992 lr:0.00015397678335770314 tokens_per_second_per_gpu:771.8461714382129 +Step 2624 | loss:2.1043803691864014 lr:0.00015394365497593682 tokens_per_second_per_gpu:759.4380424324689 +Step 2625 | loss:2.124840259552002 lr:0.0001539105182420057 tokens_per_second_per_gpu:774.0454960213708 +Step 2626 | loss:2.105785846710205 lr:0.00015387737316104052 tokens_per_second_per_gpu:770.4523048748605 +Step 2627 | loss:2.1451077461242676 lr:0.00015384421973817304 tokens_per_second_per_gpu:760.317691197102 +Step 2628 | loss:2.161853790283203 lr:0.00015381105797853653 tokens_per_second_per_gpu:773.790658190218 +Step 2629 | loss:2.021655559539795 lr:0.0001537778878872654 tokens_per_second_per_gpu:764.2778626607853 +Step 2630 | loss:2.120028018951416 lr:0.00015374470946949548 tokens_per_second_per_gpu:765.2940955424489 +Step 2631 | loss:2.1164331436157227 lr:0.0001537115227303638 tokens_per_second_per_gpu:765.0251968476539 +Step 2632 | loss:2.0663957595825195 lr:0.0001536783276750087 tokens_per_second_per_gpu:785.6031002239566 +Step 2633 | loss:2.0397791862487793 lr:0.00015364512430856984 tokens_per_second_per_gpu:778.0892335417248 +Step 2634 | loss:2.0788378715515137 lr:0.0001536119126361881 tokens_per_second_per_gpu:785.6445788849263 +Step 2635 | loss:2.0449883937835693 lr:0.0001535786926630057 tokens_per_second_per_gpu:764.2515343351065 +Step 2636 | loss:2.1351733207702637 lr:0.0001535454643941661 tokens_per_second_per_gpu:761.8315057442528 +Step 2637 | loss:2.090709686279297 lr:0.00015351222783481416 tokens_per_second_per_gpu:773.4263748530151 +Step 2638 | loss:2.1094603538513184 lr:0.0001534789829900959 tokens_per_second_per_gpu:783.0759046814893 +Step 2639 | loss:2.076338529586792 lr:0.0001534457298651586 tokens_per_second_per_gpu:779.9640951960417 +Step 2640 | loss:2.1095690727233887 lr:0.00015341246846515096 tokens_per_second_per_gpu:761.8528853954954 +Step 2641 | loss:2.050786256790161 lr:0.00015337919879522283 tokens_per_second_per_gpu:734.6647993368696 +Step 2642 | loss:2.07261061668396 lr:0.00015334592086052546 tokens_per_second_per_gpu:738.5333315668641 +Step 2643 | loss:2.096482992172241 lr:0.00015331263466621125 tokens_per_second_per_gpu:773.5991625815125 +Step 2644 | loss:2.1525025367736816 lr:0.00015327934021743399 tokens_per_second_per_gpu:786.4538319004656 +Step 2645 | loss:2.0831549167633057 lr:0.0001532460375193487 tokens_per_second_per_gpu:771.9397062883444 +Step 2646 | loss:2.0539257526397705 lr:0.00015321272657711164 tokens_per_second_per_gpu:785.2073593625395 +Step 2647 | loss:2.110973358154297 lr:0.00015317940739588038 tokens_per_second_per_gpu:764.3307621318007 +Step 2648 | loss:2.088069200515747 lr:0.00015314607998081386 tokens_per_second_per_gpu:754.5603820983554 +Step 2649 | loss:2.0531563758850098 lr:0.00015311274433707207 tokens_per_second_per_gpu:768.8312746779791 +Step 2650 | loss:2.136640787124634 lr:0.00015307940046981657 tokens_per_second_per_gpu:754.1909140065505 +Step 2651 | loss:2.1343278884887695 lr:0.0001530460483842099 tokens_per_second_per_gpu:753.3143156909524 +Step 2652 | loss:2.053008556365967 lr:0.00015301268808541604 tokens_per_second_per_gpu:734.2660626014392 +Step 2653 | loss:2.1055808067321777 lr:0.0001529793195786003 tokens_per_second_per_gpu:742.7860850832093 +Step 2654 | loss:2.1199827194213867 lr:0.00015294594286892904 tokens_per_second_per_gpu:779.1116624534606 +Step 2655 | loss:2.0779874324798584 lr:0.00015291255796157004 tokens_per_second_per_gpu:760.3884818786214 +Step 2656 | loss:2.0520927906036377 lr:0.0001528791648616924 tokens_per_second_per_gpu:719.4359769620161 +Step 2657 | loss:2.0892066955566406 lr:0.00015284576357446636 tokens_per_second_per_gpu:748.1792344285847 +Step 2658 | loss:2.1105000972747803 lr:0.0001528123541050635 tokens_per_second_per_gpu:772.5550957602841 +Step 2659 | loss:2.0838942527770996 lr:0.00015277893645865667 tokens_per_second_per_gpu:779.6951859129998 +Step 2660 | loss:2.146052598953247 lr:0.0001527455106404199 tokens_per_second_per_gpu:772.7213549607775 +Step 2661 | loss:2.033355474472046 lr:0.0001527120766555286 tokens_per_second_per_gpu:763.2936477865942 +Step 2662 | loss:2.1720011234283447 lr:0.00015267863450915944 tokens_per_second_per_gpu:766.0104499842439 +Step 2663 | loss:2.1006765365600586 lr:0.00015264518420649023 tokens_per_second_per_gpu:759.9435584915313 +Step 2664 | loss:2.013951539993286 lr:0.00015261172575270016 tokens_per_second_per_gpu:771.8032998548246 +Step 2665 | loss:2.076582670211792 lr:0.00015257825915296965 tokens_per_second_per_gpu:752.024462930642 +Step 2666 | loss:2.069349527359009 lr:0.00015254478441248035 tokens_per_second_per_gpu:738.7632206917094 +Step 2667 | loss:2.050128698348999 lr:0.00015251130153641523 tokens_per_second_per_gpu:754.7511758714405 +Step 2668 | loss:2.074309825897217 lr:0.00015247781052995846 tokens_per_second_per_gpu:757.2260992677501 +Step 2669 | loss:2.0598325729370117 lr:0.0001524443113982955 tokens_per_second_per_gpu:760.3002804150015 +Step 2670 | loss:2.0674374103546143 lr:0.00015241080414661308 tokens_per_second_per_gpu:784.392177268018 +Step 2671 | loss:2.136678695678711 lr:0.00015237728878009915 tokens_per_second_per_gpu:748.150922600583 +Step 2672 | loss:2.064739465713501 lr:0.00015234376530394295 tokens_per_second_per_gpu:749.9448702588988 +Step 2673 | loss:2.118044853210449 lr:0.00015231023372333494 tokens_per_second_per_gpu:779.7579725722369 +Step 2674 | loss:2.1212410926818848 lr:0.00015227669404346692 tokens_per_second_per_gpu:765.5741235974109 +Step 2675 | loss:2.0301461219787598 lr:0.00015224314626953182 tokens_per_second_per_gpu:736.498332794406 +Step 2676 | loss:2.138833522796631 lr:0.00015220959040672386 tokens_per_second_per_gpu:738.1635614604 +Step 2677 | loss:2.1163618564605713 lr:0.00015217602646023864 tokens_per_second_per_gpu:743.7144097123396 +Step 2678 | loss:2.1319546699523926 lr:0.00015214245443527285 tokens_per_second_per_gpu:760.5552565481921 +Step 2679 | loss:2.057758331298828 lr:0.00015210887433702444 tokens_per_second_per_gpu:785.5844187482836 +Step 2680 | loss:2.09834623336792 lr:0.00015207528617069272 tokens_per_second_per_gpu:767.7105174565636 +Step 2681 | loss:2.1240944862365723 lr:0.00015204168994147817 tokens_per_second_per_gpu:763.6911546551576 +Step 2682 | loss:2.0597615242004395 lr:0.00015200808565458252 tokens_per_second_per_gpu:763.8474123156923 +Step 2683 | loss:2.053260326385498 lr:0.00015197447331520884 tokens_per_second_per_gpu:757.8587365486079 +Step 2684 | loss:2.135953664779663 lr:0.0001519408529285613 tokens_per_second_per_gpu:769.0348099544184 +Step 2685 | loss:2.164682388305664 lr:0.00015190722449984537 tokens_per_second_per_gpu:776.4231622878748 +Step 2686 | loss:2.084575891494751 lr:0.00015187358803426786 tokens_per_second_per_gpu:766.2318537522249 +Step 2687 | loss:2.105422019958496 lr:0.0001518399435370367 tokens_per_second_per_gpu:756.9148839220445 +Step 2688 | loss:2.095811367034912 lr:0.00015180629101336108 tokens_per_second_per_gpu:757.8835883650606 +Step 2689 | loss:2.1712090969085693 lr:0.0001517726304684515 tokens_per_second_per_gpu:763.7772608402429 +Step 2690 | loss:2.101071834564209 lr:0.00015173896190751968 tokens_per_second_per_gpu:758.8766166611481 +Step 2691 | loss:2.07130765914917 lr:0.00015170528533577855 tokens_per_second_per_gpu:771.0870799667384 +Step 2692 | loss:2.1365721225738525 lr:0.00015167160075844227 tokens_per_second_per_gpu:777.0631761151066 +Step 2693 | loss:2.0660369396209717 lr:0.00015163790818072635 tokens_per_second_per_gpu:755.6920861083931 +Step 2694 | loss:2.0791244506835938 lr:0.00015160420760784732 tokens_per_second_per_gpu:771.135811323216 +Step 2695 | loss:2.054701566696167 lr:0.00015157049904502317 tokens_per_second_per_gpu:728.4949129152966 +Step 2696 | loss:2.068099021911621 lr:0.00015153678249747306 tokens_per_second_per_gpu:788.3218911726071 +Step 2697 | loss:2.088120460510254 lr:0.00015150305797041733 tokens_per_second_per_gpu:740.1322396075217 +Step 2698 | loss:2.11305832862854 lr:0.0001514693254690776 tokens_per_second_per_gpu:767.2126061299773 +Step 2699 | loss:2.0759191513061523 lr:0.0001514355849986767 tokens_per_second_per_gpu:749.4275379073946 +Step 2700 | loss:2.059706687927246 lr:0.0001514018365644387 tokens_per_second_per_gpu:736.0375348242831 +Step 2701 | loss:2.0606772899627686 lr:0.00015136808017158894 tokens_per_second_per_gpu:751.2900122775019 +Step 2702 | loss:2.0540947914123535 lr:0.000151334315825354 tokens_per_second_per_gpu:772.9493041372197 +Step 2703 | loss:2.0937340259552 lr:0.00015130054353096155 tokens_per_second_per_gpu:726.7980316775282 +Step 2704 | loss:2.099605083465576 lr:0.00015126676329364072 tokens_per_second_per_gpu:759.7496078191256 +Step 2705 | loss:2.1068530082702637 lr:0.00015123297511862168 tokens_per_second_per_gpu:737.6625866086001 +Step 2706 | loss:2.0883562564849854 lr:0.00015119917901113588 tokens_per_second_per_gpu:752.1137707476416 +Step 2707 | loss:2.1169445514678955 lr:0.00015116537497641605 tokens_per_second_per_gpu:755.530295657832 +Step 2708 | loss:2.11254620552063 lr:0.00015113156301969612 tokens_per_second_per_gpu:779.8313361713733 +Step 2709 | loss:2.1101596355438232 lr:0.0001510977431462112 tokens_per_second_per_gpu:716.4119994890376 +Step 2710 | loss:2.072056770324707 lr:0.00015106391536119767 tokens_per_second_per_gpu:752.9780380750589 +Step 2711 | loss:2.144585371017456 lr:0.00015103007966989318 tokens_per_second_per_gpu:765.4881133936567 +Step 2712 | loss:2.075632095336914 lr:0.0001509962360775365 tokens_per_second_per_gpu:761.4637545836757 +Step 2713 | loss:2.0457141399383545 lr:0.0001509623845893677 tokens_per_second_per_gpu:773.4449133457501 +Step 2714 | loss:2.048562526702881 lr:0.00015092852521062807 tokens_per_second_per_gpu:739.7921707345282 +Step 2715 | loss:2.07987642288208 lr:0.00015089465794656002 tokens_per_second_per_gpu:749.3956005844515 +Step 2716 | loss:2.0438120365142822 lr:0.00015086078280240732 tokens_per_second_per_gpu:773.4088018156622 +Step 2717 | loss:2.087555408477783 lr:0.00015082689978341494 tokens_per_second_per_gpu:776.3592488444805 +Step 2718 | loss:2.094930648803711 lr:0.00015079300889482892 tokens_per_second_per_gpu:727.3142543924733 +Step 2719 | loss:2.1332809925079346 lr:0.00015075911014189675 tokens_per_second_per_gpu:761.2488810276976 +Step 2720 | loss:2.1091854572296143 lr:0.00015072520352986697 tokens_per_second_per_gpu:801.0380924947824 +Step 2721 | loss:2.070711135864258 lr:0.00015069128906398935 tokens_per_second_per_gpu:759.3346143360814 +Step 2722 | loss:2.087395429611206 lr:0.00015065736674951493 tokens_per_second_per_gpu:761.1791801839553 +Step 2723 | loss:2.074759006500244 lr:0.000150623436591696 tokens_per_second_per_gpu:773.1052474730891 +Step 2724 | loss:2.140246868133545 lr:0.0001505894985957859 tokens_per_second_per_gpu:796.3383040997034 +Step 2725 | loss:2.0380001068115234 lr:0.0001505555527670394 tokens_per_second_per_gpu:776.187688297764 +Step 2726 | loss:2.081313371658325 lr:0.00015052159911071233 tokens_per_second_per_gpu:796.8039060087069 +Step 2727 | loss:2.0582222938537598 lr:0.00015048763763206172 tokens_per_second_per_gpu:789.4074497640114 +Step 2728 | loss:2.054140090942383 lr:0.000150453668336346 tokens_per_second_per_gpu:765.1303247675019 +Step 2729 | loss:2.1659679412841797 lr:0.00015041969122882458 tokens_per_second_per_gpu:754.0411593293901 +Step 2730 | loss:2.1522059440612793 lr:0.00015038570631475818 tokens_per_second_per_gpu:753.3527445510914 +Step 2731 | loss:2.194307327270508 lr:0.0001503517135994088 tokens_per_second_per_gpu:749.8327012449315 +Step 2732 | loss:2.093780994415283 lr:0.0001503177130880395 tokens_per_second_per_gpu:781.3549463566555 +Step 2733 | loss:2.0860443115234375 lr:0.00015028370478591466 tokens_per_second_per_gpu:751.9288617784891 +Step 2734 | loss:2.0902700424194336 lr:0.0001502496886982998 tokens_per_second_per_gpu:788.6150855005061 +Step 2735 | loss:2.149151563644409 lr:0.00015021566483046172 tokens_per_second_per_gpu:780.8961463893272 +Step 2736 | loss:2.1026580333709717 lr:0.00015018163318766833 tokens_per_second_per_gpu:800.9942637905008 +Step 2737 | loss:2.0854735374450684 lr:0.00015014759377518885 tokens_per_second_per_gpu:789.8943925243611 +Step 2738 | loss:2.0557680130004883 lr:0.0001501135465982936 tokens_per_second_per_gpu:774.3951489956174 +Step 2739 | loss:2.0881569385528564 lr:0.00015007949166225413 tokens_per_second_per_gpu:777.9195734622558 +Step 2740 | loss:2.0589208602905273 lr:0.00015004542897234326 tokens_per_second_per_gpu:789.1162185592412 +Step 2741 | loss:2.0980725288391113 lr:0.00015001135853383494 tokens_per_second_per_gpu:792.8721542079015 +Step 2742 | loss:2.0841474533081055 lr:0.00014997728035200434 tokens_per_second_per_gpu:784.4942640666984 +Step 2743 | loss:2.0937557220458984 lr:0.0001499431944321278 tokens_per_second_per_gpu:789.863073520854 +Step 2744 | loss:2.097744941711426 lr:0.00014990910077948292 tokens_per_second_per_gpu:792.7767031418464 +Step 2745 | loss:2.0417726039886475 lr:0.00014987499939934847 tokens_per_second_per_gpu:779.4159317755652 +Step 2746 | loss:2.1006572246551514 lr:0.0001498408902970044 tokens_per_second_per_gpu:780.8385688103066 +Step 2747 | loss:2.07938289642334 lr:0.00014980677347773184 tokens_per_second_per_gpu:783.8419909012814 +Step 2748 | loss:2.0692906379699707 lr:0.00014977264894681317 tokens_per_second_per_gpu:786.7247689307479 +Step 2749 | loss:2.083798408508301 lr:0.00014973851670953191 tokens_per_second_per_gpu:765.6746008767011 +Step 2750 | loss:2.1269397735595703 lr:0.00014970437677117287 tokens_per_second_per_gpu:773.645268253694 +Step 2751 | loss:2.0664262771606445 lr:0.00014967022913702188 tokens_per_second_per_gpu:739.4946399661035 +Step 2752 | loss:2.1169586181640625 lr:0.00014963607381236608 tokens_per_second_per_gpu:776.0749672759615 +Step 2753 | loss:2.0762929916381836 lr:0.00014960191080249383 tokens_per_second_per_gpu:779.9691862481586 +Step 2754 | loss:2.0941696166992188 lr:0.0001495677401126946 tokens_per_second_per_gpu:751.542184939247 +Step 2755 | loss:2.059206962585449 lr:0.0001495335617482591 tokens_per_second_per_gpu:761.4059867355187 +Step 2756 | loss:2.1495399475097656 lr:0.00014949937571447926 tokens_per_second_per_gpu:774.3060718415995 +Step 2757 | loss:2.1095848083496094 lr:0.00014946518201664798 tokens_per_second_per_gpu:769.0220336880042 +Step 2758 | loss:2.1118721961975098 lr:0.0001494309806600597 tokens_per_second_per_gpu:790.5347051792011 +Step 2759 | loss:2.0538501739501953 lr:0.00014939677165000975 tokens_per_second_per_gpu:781.9447303823686 +Step 2760 | loss:2.0887207984924316 lr:0.0001493625549917948 tokens_per_second_per_gpu:773.2409866147376 +Step 2761 | loss:2.0494396686553955 lr:0.00014932833069071264 tokens_per_second_per_gpu:776.7589282972954 +Step 2762 | loss:2.1052253246307373 lr:0.00014929409875206226 tokens_per_second_per_gpu:794.23188909447 +Step 2763 | loss:2.046211004257202 lr:0.00014925985918114385 tokens_per_second_per_gpu:749.8551594288298 +Step 2764 | loss:2.115931510925293 lr:0.00014922561198325878 tokens_per_second_per_gpu:780.8474977199694 +Step 2765 | loss:2.042163372039795 lr:0.0001491913571637095 tokens_per_second_per_gpu:738.0450672148703 +Step 2766 | loss:2.1131811141967773 lr:0.00014915709472779985 tokens_per_second_per_gpu:790.1550488637284 +Step 2767 | loss:2.1257379055023193 lr:0.00014912282468083462 tokens_per_second_per_gpu:771.492499318528 +Step 2768 | loss:2.1030735969543457 lr:0.00014908854702811998 tokens_per_second_per_gpu:780.7592660762115 +Step 2769 | loss:2.0701236724853516 lr:0.00014905426177496314 tokens_per_second_per_gpu:746.5259002037554 +Step 2770 | loss:2.0799481868743896 lr:0.0001490199689266725 tokens_per_second_per_gpu:775.1037046108105 +Step 2771 | loss:2.0654220581054688 lr:0.00014898566848855772 tokens_per_second_per_gpu:771.1970018980224 +Step 2772 | loss:2.10958194732666 lr:0.0001489513604659295 tokens_per_second_per_gpu:745.5532810711235 +Step 2773 | loss:2.041551351547241 lr:0.00014891704486409989 tokens_per_second_per_gpu:775.9317913001831 +Step 2774 | loss:2.0958521366119385 lr:0.00014888272168838196 tokens_per_second_per_gpu:768.3896009728563 +Step 2775 | loss:2.0310778617858887 lr:0.00014884839094409002 tokens_per_second_per_gpu:740.6261791095607 +Step 2776 | loss:2.062978744506836 lr:0.00014881405263653954 tokens_per_second_per_gpu:764.4162053241125 +Step 2777 | loss:2.083754062652588 lr:0.0001487797067710472 tokens_per_second_per_gpu:784.040024339585 +Step 2778 | loss:2.093982219696045 lr:0.00014874535335293078 tokens_per_second_per_gpu:777.8164701956813 +Step 2779 | loss:2.0782973766326904 lr:0.00014871099238750925 tokens_per_second_per_gpu:773.0678870736506 +Step 2780 | loss:2.0759594440460205 lr:0.0001486766238801028 tokens_per_second_per_gpu:747.8433631880202 +Step 2781 | loss:2.03765606880188 lr:0.00014864224783603272 tokens_per_second_per_gpu:781.4334477620996 +Step 2782 | loss:2.09140682220459 lr:0.00014860786426062152 tokens_per_second_per_gpu:763.8697660611374 +Step 2783 | loss:2.076955795288086 lr:0.00014857347315919283 tokens_per_second_per_gpu:786.9572475778597 +Step 2784 | loss:2.061269760131836 lr:0.00014853907453707147 tokens_per_second_per_gpu:757.107594589902 +Step 2785 | loss:2.0635650157928467 lr:0.00014850466839958347 tokens_per_second_per_gpu:737.6770626698401 +Step 2786 | loss:2.0626585483551025 lr:0.00014847025475205592 tokens_per_second_per_gpu:757.8316962274258 +Step 2787 | loss:2.057290554046631 lr:0.00014843583359981711 tokens_per_second_per_gpu:769.1509758237905 +Step 2788 | loss:2.0422208309173584 lr:0.00014840140494819658 tokens_per_second_per_gpu:792.4054318895717 +Step 2789 | loss:2.1183061599731445 lr:0.00014836696880252495 tokens_per_second_per_gpu:790.1303913077592 +Step 2790 | loss:2.084184408187866 lr:0.00014833252516813393 tokens_per_second_per_gpu:758.9924871349997 +Step 2791 | loss:2.1234655380249023 lr:0.00014829807405035658 tokens_per_second_per_gpu:748.885390722877 +Step 2792 | loss:2.040073871612549 lr:0.00014826361545452696 tokens_per_second_per_gpu:789.1554589265539 +Step 2793 | loss:2.061863422393799 lr:0.00014822914938598033 tokens_per_second_per_gpu:761.311776580135 +Step 2794 | loss:2.044994354248047 lr:0.00014819467585005313 tokens_per_second_per_gpu:766.5913681429191 +Step 2795 | loss:2.0786192417144775 lr:0.00014816019485208295 tokens_per_second_per_gpu:752.8336431760354 +Step 2796 | loss:2.137014865875244 lr:0.0001481257063974085 tokens_per_second_per_gpu:787.8218140011157 +Step 2797 | loss:2.125873565673828 lr:0.00014809121049136968 tokens_per_second_per_gpu:757.1321180845405 +Step 2798 | loss:2.070479154586792 lr:0.00014805670713930757 tokens_per_second_per_gpu:785.5840081954799 +Step 2799 | loss:2.109764575958252 lr:0.00014802219634656432 tokens_per_second_per_gpu:777.7120273757295 +Step 2800 | loss:2.0806846618652344 lr:0.0001479876781184833 tokens_per_second_per_gpu:748.8431990560308 +Step 2801 | loss:2.0736002922058105 lr:0.00014795315246040903 tokens_per_second_per_gpu:770.0968073536422 +Step 2802 | loss:2.091240882873535 lr:0.0001479186193776871 tokens_per_second_per_gpu:760.522752129693 +Step 2803 | loss:2.0674405097961426 lr:0.0001478840788756644 tokens_per_second_per_gpu:748.6849474215041 +Step 2804 | loss:2.086000919342041 lr:0.00014784953095968881 tokens_per_second_per_gpu:743.3114599002296 +Step 2805 | loss:2.023514747619629 lr:0.00014781497563510945 tokens_per_second_per_gpu:763.8681171088142 +Step 2806 | loss:2.1997735500335693 lr:0.00014778041290727656 tokens_per_second_per_gpu:781.0209696764455 +Step 2807 | loss:2.0744869709014893 lr:0.00014774584278154157 tokens_per_second_per_gpu:777.1713673040074 +Step 2808 | loss:2.1015987396240234 lr:0.00014771126526325694 tokens_per_second_per_gpu:791.3194722480224 +Step 2809 | loss:2.037747383117676 lr:0.00014767668035777642 tokens_per_second_per_gpu:759.5856945163316 +Step 2810 | loss:2.1197798252105713 lr:0.00014764208807045479 tokens_per_second_per_gpu:757.1938063654653 +Step 2811 | loss:2.1043992042541504 lr:0.00014760748840664804 tokens_per_second_per_gpu:765.1514297247862 +Step 2812 | loss:2.0212347507476807 lr:0.0001475728813717133 tokens_per_second_per_gpu:788.6921391489191 +Step 2813 | loss:2.0349135398864746 lr:0.00014753826697100879 tokens_per_second_per_gpu:742.1475843077766 +Step 2814 | loss:2.138394355773926 lr:0.0001475036452098939 tokens_per_second_per_gpu:756.3549800893187 +Step 2815 | loss:2.1347665786743164 lr:0.0001474690160937292 tokens_per_second_per_gpu:783.9814629765149 +Step 2816 | loss:2.1348671913146973 lr:0.0001474343796278763 tokens_per_second_per_gpu:774.7508324614587 +Step 2817 | loss:2.134124755859375 lr:0.00014739973581769805 tokens_per_second_per_gpu:775.062416767701 +Step 2818 | loss:2.094486713409424 lr:0.00014736508466855837 tokens_per_second_per_gpu:775.286670084298 +Step 2819 | loss:2.137284278869629 lr:0.00014733042618582238 tokens_per_second_per_gpu:784.2141359415152 +Step 2820 | loss:2.088463068008423 lr:0.00014729576037485626 tokens_per_second_per_gpu:774.9871877100001 +Step 2821 | loss:2.0601301193237305 lr:0.00014726108724102738 tokens_per_second_per_gpu:764.6370391487561 +Step 2822 | loss:2.0622551441192627 lr:0.00014722640678970422 tokens_per_second_per_gpu:755.5125449526141 +Step 2823 | loss:2.1531224250793457 lr:0.00014719171902625642 tokens_per_second_per_gpu:782.0947104573647 +Step 2824 | loss:2.0831527709960938 lr:0.0001471570239560547 tokens_per_second_per_gpu:773.1592802583497 +Step 2825 | loss:2.1078972816467285 lr:0.00014712232158447096 tokens_per_second_per_gpu:763.4379857396385 +Step 2826 | loss:2.134800434112549 lr:0.00014708761191687815 tokens_per_second_per_gpu:789.4917907867377 +Step 2827 | loss:2.0689845085144043 lr:0.0001470528949586505 tokens_per_second_per_gpu:790.1111021801082 +Step 2828 | loss:2.082528591156006 lr:0.00014701817071516326 tokens_per_second_per_gpu:717.7298958952367 +Step 2829 | loss:2.099977731704712 lr:0.0001469834391917928 tokens_per_second_per_gpu:794.9586109501915 +Step 2830 | loss:2.0274055004119873 lr:0.00014694870039391665 tokens_per_second_per_gpu:763.5479453722925 +Step 2831 | loss:2.115100383758545 lr:0.00014691395432691354 tokens_per_second_per_gpu:793.521107810367 +Step 2832 | loss:2.167914390563965 lr:0.00014687920099616311 tokens_per_second_per_gpu:753.8841377548858 +Step 2833 | loss:2.0628304481506348 lr:0.00014684444040704634 tokens_per_second_per_gpu:783.4799047782797 +Step 2834 | loss:2.1233394145965576 lr:0.00014680967256494528 tokens_per_second_per_gpu:770.227395567965 +Step 2835 | loss:2.045881748199463 lr:0.00014677489747524304 tokens_per_second_per_gpu:782.3837497589454 +Step 2836 | loss:2.0840368270874023 lr:0.00014674011514332388 tokens_per_second_per_gpu:737.3826675224532 +Step 2837 | loss:2.09268856048584 lr:0.00014670532557457323 tokens_per_second_per_gpu:772.1406663984233 +Step 2838 | loss:2.0497665405273438 lr:0.0001466705287743776 tokens_per_second_per_gpu:780.0817375067332 +Step 2839 | loss:2.055652141571045 lr:0.0001466357247481246 tokens_per_second_per_gpu:749.7221063557511 +Step 2840 | loss:2.0865187644958496 lr:0.00014660091350120297 tokens_per_second_per_gpu:745.1983211870117 +Step 2841 | loss:2.061941146850586 lr:0.0001465660950390026 tokens_per_second_per_gpu:764.5122505294121 +Step 2842 | loss:2.119229793548584 lr:0.0001465312693669145 tokens_per_second_per_gpu:781.4907847622945 +Step 2843 | loss:2.1037204265594482 lr:0.00014649643649033078 tokens_per_second_per_gpu:773.2811956356156 +Step 2844 | loss:2.096773624420166 lr:0.00014646159641464458 tokens_per_second_per_gpu:778.4960488974634 +Step 2845 | loss:2.0763773918151855 lr:0.0001464267491452503 tokens_per_second_per_gpu:745.8580975840152 +Step 2846 | loss:2.053370237350464 lr:0.00014639189468754337 tokens_per_second_per_gpu:771.1293042526522 +Step 2847 | loss:2.0936975479125977 lr:0.00014635703304692035 tokens_per_second_per_gpu:780.908259048552 +Step 2848 | loss:2.1808881759643555 lr:0.0001463221642287789 tokens_per_second_per_gpu:746.2968662131498 +Step 2849 | loss:2.126497745513916 lr:0.00014628728823851784 tokens_per_second_per_gpu:781.4886298482008 +Step 2850 | loss:2.0777578353881836 lr:0.00014625240508153703 tokens_per_second_per_gpu:773.575988240737 +Step 2851 | loss:2.060302972793579 lr:0.00014621751476323746 tokens_per_second_per_gpu:779.4817854278471 +Step 2852 | loss:2.0717504024505615 lr:0.00014618261728902132 tokens_per_second_per_gpu:771.596138137289 +Step 2853 | loss:2.084246873855591 lr:0.00014614771266429174 tokens_per_second_per_gpu:749.6171504608916 +Step 2854 | loss:2.1312668323516846 lr:0.00014611280089445305 tokens_per_second_per_gpu:732.6168749673562 +Step 2855 | loss:2.1113526821136475 lr:0.00014607788198491077 tokens_per_second_per_gpu:753.3181105121823 +Step 2856 | loss:2.0937724113464355 lr:0.00014604295594107137 tokens_per_second_per_gpu:758.1038097629649 +Step 2857 | loss:2.029609441757202 lr:0.00014600802276834248 tokens_per_second_per_gpu:745.3272016580368 +Step 2858 | loss:2.1158032417297363 lr:0.00014597308247213294 tokens_per_second_per_gpu:755.1572138429324 +Step 2859 | loss:2.062774896621704 lr:0.00014593813505785249 tokens_per_second_per_gpu:769.3768848754713 +Step 2860 | loss:2.099170207977295 lr:0.00014590318053091215 tokens_per_second_per_gpu:747.8885598074478 +Step 2861 | loss:2.062225818634033 lr:0.00014586821889672394 tokens_per_second_per_gpu:793.2959957656782 +Step 2862 | loss:2.066624164581299 lr:0.00014583325016070104 tokens_per_second_per_gpu:780.2182134198077 +Step 2863 | loss:2.064452648162842 lr:0.0001457982743282577 tokens_per_second_per_gpu:785.8680576697252 +Step 2864 | loss:2.1091971397399902 lr:0.00014576329140480925 tokens_per_second_per_gpu:772.0870854366937 +Step 2865 | loss:2.1207544803619385 lr:0.00014572830139577216 tokens_per_second_per_gpu:726.5287743016287 +Step 2866 | loss:2.0442421436309814 lr:0.00014569330430656399 tokens_per_second_per_gpu:751.2440063502335 +Step 2867 | loss:2.1259801387786865 lr:0.00014565830014260332 tokens_per_second_per_gpu:796.3664298938926 +Step 2868 | loss:2.094452381134033 lr:0.00014562328890930997 tokens_per_second_per_gpu:764.9290878659616 +Step 2869 | loss:2.0423946380615234 lr:0.00014558827061210474 tokens_per_second_per_gpu:779.55974347962 +Step 2870 | loss:2.1047887802124023 lr:0.00014555324525640956 tokens_per_second_per_gpu:774.4649790598565 +Step 2871 | loss:2.0971107482910156 lr:0.00014551821284764746 tokens_per_second_per_gpu:766.9845678870944 +Step 2872 | loss:2.0763168334960938 lr:0.00014548317339124252 tokens_per_second_per_gpu:779.4545166799649 +Step 2873 | loss:2.1025614738464355 lr:0.00014544812689262 tokens_per_second_per_gpu:774.7542916530564 +Step 2874 | loss:2.1369211673736572 lr:0.0001454130733572061 tokens_per_second_per_gpu:801.0834072007142 +Step 2875 | loss:2.084942579269409 lr:0.0001453780127904283 tokens_per_second_per_gpu:776.843613508288 +Step 2876 | loss:2.0769410133361816 lr:0.00014534294519771504 tokens_per_second_per_gpu:757.1483124376339 +Step 2877 | loss:2.14632248878479 lr:0.00014530787058449586 tokens_per_second_per_gpu:787.805751656519 +Step 2878 | loss:2.080435276031494 lr:0.00014527278895620142 tokens_per_second_per_gpu:784.7764274909491 +Step 2879 | loss:2.0440120697021484 lr:0.00014523770031826344 tokens_per_second_per_gpu:786.2096435868082 +Step 2880 | loss:2.056602954864502 lr:0.0001452026046761148 tokens_per_second_per_gpu:790.3776773684555 +Step 2881 | loss:2.092198133468628 lr:0.0001451675020351893 tokens_per_second_per_gpu:793.8631627485397 +Step 2882 | loss:2.1350488662719727 lr:0.00014513239240092202 tokens_per_second_per_gpu:761.1914398868216 +Step 2883 | loss:2.088845729827881 lr:0.000145097275778749 tokens_per_second_per_gpu:790.8929311949934 +Step 2884 | loss:2.107389450073242 lr:0.00014506215217410736 tokens_per_second_per_gpu:791.6705635508519 +Step 2885 | loss:2.134974479675293 lr:0.00014502702159243532 tokens_per_second_per_gpu:782.2300945843579 +Step 2886 | loss:2.0551412105560303 lr:0.0001449918840391723 tokens_per_second_per_gpu:776.8468153492914 +Step 2887 | loss:2.041579008102417 lr:0.00014495673951975857 tokens_per_second_per_gpu:762.685437286814 +Step 2888 | loss:2.1140129566192627 lr:0.00014492158803963568 tokens_per_second_per_gpu:782.6726481768646 +Step 2889 | loss:2.091036796569824 lr:0.00014488642960424613 tokens_per_second_per_gpu:752.3743242118414 +Step 2890 | loss:2.1558098793029785 lr:0.00014485126421903357 tokens_per_second_per_gpu:779.7755720000955 +Step 2891 | loss:2.091052532196045 lr:0.0001448160918894427 tokens_per_second_per_gpu:766.8285665948608 +Step 2892 | loss:2.0688636302948 lr:0.00014478091262091927 tokens_per_second_per_gpu:782.2251561449311 +Step 2893 | loss:2.102288246154785 lr:0.00014474572641891018 tokens_per_second_per_gpu:788.4850710714737 +Step 2894 | loss:2.096113443374634 lr:0.00014471053328886333 tokens_per_second_per_gpu:746.6541921270358 +Step 2895 | loss:2.0770788192749023 lr:0.0001446753332362277 tokens_per_second_per_gpu:746.0475198922597 +Step 2896 | loss:2.0905003547668457 lr:0.00014464012626645335 tokens_per_second_per_gpu:786.4223860891888 +Step 2897 | loss:2.144373893737793 lr:0.0001446049123849915 tokens_per_second_per_gpu:784.093020570253 +Step 2898 | loss:2.098384141921997 lr:0.0001445696915972943 tokens_per_second_per_gpu:792.5478911978689 +Step 2899 | loss:2.029637575149536 lr:0.00014453446390881496 tokens_per_second_per_gpu:774.7801599833348 +Step 2900 | loss:2.0762722492218018 lr:0.00014449922932500799 tokens_per_second_per_gpu:744.670484258293 +Step 2901 | loss:2.0512468814849854 lr:0.00014446398785132865 tokens_per_second_per_gpu:734.7879128150256 +Step 2902 | loss:1.9842208623886108 lr:0.00014442873949323351 tokens_per_second_per_gpu:777.595693025355 +Step 2903 | loss:2.0951387882232666 lr:0.00014439348425618014 tokens_per_second_per_gpu:744.683503284969 +Step 2904 | loss:2.0562949180603027 lr:0.00014435822214562704 tokens_per_second_per_gpu:779.17889826427 +Step 2905 | loss:2.098620891571045 lr:0.000144322953167034 tokens_per_second_per_gpu:733.9841537081985 +Step 2906 | loss:2.1380038261413574 lr:0.00014428767732586173 tokens_per_second_per_gpu:765.3518366620533 +Step 2907 | loss:1.9721741676330566 lr:0.00014425239462757198 tokens_per_second_per_gpu:765.6790226016249 +Step 2908 | loss:2.097053050994873 lr:0.00014421710507762768 tokens_per_second_per_gpu:776.172485170088 +Step 2909 | loss:2.0936756134033203 lr:0.00014418180868149274 tokens_per_second_per_gpu:773.0186800621885 +Step 2910 | loss:2.114515781402588 lr:0.00014414650544463214 tokens_per_second_per_gpu:785.363879002402 +Step 2911 | loss:2.075404167175293 lr:0.00014411119537251189 tokens_per_second_per_gpu:782.0098794885148 +Step 2912 | loss:2.05267071723938 lr:0.00014407587847059913 tokens_per_second_per_gpu:795.5177094299737 +Step 2913 | loss:2.0839641094207764 lr:0.00014404055474436206 tokens_per_second_per_gpu:763.7647895838709 +Step 2914 | loss:2.091026782989502 lr:0.00014400522419926983 tokens_per_second_per_gpu:779.263350780953 +Step 2915 | loss:2.1306517124176025 lr:0.00014396988684079273 tokens_per_second_per_gpu:752.9500018575168 +Step 2916 | loss:2.01131010055542 lr:0.00014393454267440213 tokens_per_second_per_gpu:779.3465812120883 +Step 2917 | loss:2.1457033157348633 lr:0.00014389919170557032 tokens_per_second_per_gpu:788.1661883959865 +Step 2918 | loss:2.110870838165283 lr:0.00014386383393977085 tokens_per_second_per_gpu:734.2156372656873 +Step 2919 | loss:2.0729103088378906 lr:0.00014382846938247815 tokens_per_second_per_gpu:768.0800218621154 +Step 2920 | loss:2.0501790046691895 lr:0.0001437930980391677 tokens_per_second_per_gpu:778.2060706957211 +Step 2921 | loss:2.0741629600524902 lr:0.00014375771991531624 tokens_per_second_per_gpu:767.0621277154505 +Step 2922 | loss:2.103327751159668 lr:0.00014372233501640128 tokens_per_second_per_gpu:779.0932281172961 +Step 2923 | loss:2.0845396518707275 lr:0.00014368694334790155 tokens_per_second_per_gpu:780.2549723715144 +Step 2924 | loss:2.0130374431610107 lr:0.0001436515449152968 tokens_per_second_per_gpu:778.3735577464882 +Step 2925 | loss:2.07222580909729 lr:0.00014361613972406777 tokens_per_second_per_gpu:741.7124565995911 +Step 2926 | loss:2.141449213027954 lr:0.00014358072777969632 tokens_per_second_per_gpu:784.9552970476853 +Step 2927 | loss:2.0361526012420654 lr:0.0001435453090876654 tokens_per_second_per_gpu:769.4335855092907 +Step 2928 | loss:2.120706796646118 lr:0.00014350988365345878 tokens_per_second_per_gpu:754.2490763582483 +Step 2929 | loss:1.9982529878616333 lr:0.00014347445148256153 tokens_per_second_per_gpu:779.723095973621 +Step 2930 | loss:2.1386477947235107 lr:0.00014343901258045966 tokens_per_second_per_gpu:779.9153398320381 +Step 2931 | loss:2.125122547149658 lr:0.0001434035669526402 tokens_per_second_per_gpu:743.7169728274704 +Step 2932 | loss:2.1020569801330566 lr:0.0001433681146045912 tokens_per_second_per_gpu:788.9750886011582 +Step 2933 | loss:2.0473389625549316 lr:0.00014333265554180183 tokens_per_second_per_gpu:786.1485793709242 +Step 2934 | loss:2.038275718688965 lr:0.0001432971897697623 tokens_per_second_per_gpu:751.8056409669005 +Step 2935 | loss:2.04879093170166 lr:0.00014326171729396375 tokens_per_second_per_gpu:760.4535769910775 +Step 2936 | loss:2.0906620025634766 lr:0.00014322623811989843 tokens_per_second_per_gpu:751.7954169694219 +Step 2937 | loss:2.1371684074401855 lr:0.00014319075225305972 tokens_per_second_per_gpu:770.367318985311 +Step 2938 | loss:2.111707925796509 lr:0.00014315525969894183 tokens_per_second_per_gpu:771.8416856910159 +Step 2939 | loss:2.0974526405334473 lr:0.00014311976046304015 tokens_per_second_per_gpu:775.5294989073152 +Step 2940 | loss:2.112305164337158 lr:0.00014308425455085116 tokens_per_second_per_gpu:780.4579508272099 +Step 2941 | loss:2.14164400100708 lr:0.00014304874196787216 tokens_per_second_per_gpu:741.1820187738159 +Step 2942 | loss:2.079113721847534 lr:0.00014301322271960165 tokens_per_second_per_gpu:780.8219352451782 +Step 2943 | loss:2.034252882003784 lr:0.00014297769681153913 tokens_per_second_per_gpu:764.7649768413675 +Step 2944 | loss:2.019604206085205 lr:0.00014294216424918515 tokens_per_second_per_gpu:768.1589508129433 +Step 2945 | loss:2.0454230308532715 lr:0.00014290662503804123 tokens_per_second_per_gpu:730.609479495896 +Step 2946 | loss:2.088322162628174 lr:0.00014287107918360993 tokens_per_second_per_gpu:776.0848069068527 +Step 2947 | loss:2.1134233474731445 lr:0.00014283552669139488 tokens_per_second_per_gpu:764.2723183134808 +Step 2948 | loss:2.0960135459899902 lr:0.00014279996756690075 tokens_per_second_per_gpu:784.9400405914756 +Step 2949 | loss:2.0887627601623535 lr:0.00014276440181563318 tokens_per_second_per_gpu:764.6117963577237 +Step 2950 | loss:2.1170620918273926 lr:0.00014272882944309882 tokens_per_second_per_gpu:774.1062802970869 +Step 2951 | loss:2.0480687618255615 lr:0.0001426932504548055 tokens_per_second_per_gpu:778.1872428167717 +Step 2952 | loss:2.084500312805176 lr:0.0001426576648562618 tokens_per_second_per_gpu:766.8474434520388 +Step 2953 | loss:2.093101739883423 lr:0.0001426220726529776 tokens_per_second_per_gpu:782.0534241592512 +Step 2954 | loss:2.138657569885254 lr:0.00014258647385046363 tokens_per_second_per_gpu:784.8847624768382 +Step 2955 | loss:2.0611484050750732 lr:0.00014255086845423176 tokens_per_second_per_gpu:769.5011253568141 +Step 2956 | loss:2.0749173164367676 lr:0.00014251525646979474 tokens_per_second_per_gpu:782.1231604150607 +Step 2957 | loss:2.076941728591919 lr:0.0001424796379026665 tokens_per_second_per_gpu:761.9506394775599 +Step 2958 | loss:2.057302713394165 lr:0.00014244401275836187 tokens_per_second_per_gpu:781.0992100371747 +Step 2959 | loss:2.072941780090332 lr:0.0001424083810423967 tokens_per_second_per_gpu:765.8940375400248 +Step 2960 | loss:2.1036441326141357 lr:0.0001423727427602879 tokens_per_second_per_gpu:766.9611066120198 +Step 2961 | loss:2.0802085399627686 lr:0.00014233709791755346 tokens_per_second_per_gpu:760.9737709162879 +Step 2962 | loss:2.0446763038635254 lr:0.0001423014465197123 tokens_per_second_per_gpu:781.371179873279 +Step 2963 | loss:2.0113165378570557 lr:0.00014226578857228427 tokens_per_second_per_gpu:796.6696553900701 +Step 2964 | loss:2.037335157394409 lr:0.00014223012408079048 tokens_per_second_per_gpu:771.4428430708945 +Step 2965 | loss:2.0952532291412354 lr:0.0001421944530507528 tokens_per_second_per_gpu:776.6393520102118 +Step 2966 | loss:2.035444736480713 lr:0.00014215877548769427 tokens_per_second_per_gpu:758.4240663835665 +Step 2967 | loss:2.0685598850250244 lr:0.00014212309139713887 tokens_per_second_per_gpu:758.9152204522222 +Step 2968 | loss:2.0777549743652344 lr:0.00014208740078461166 tokens_per_second_per_gpu:752.6339775622165 +Step 2969 | loss:2.1406049728393555 lr:0.0001420517036556386 tokens_per_second_per_gpu:755.0742458154816 +Step 2970 | loss:2.0360796451568604 lr:0.00014201600001574678 tokens_per_second_per_gpu:758.8902239388037 +Step 2971 | loss:2.078461170196533 lr:0.00014198028987046413 tokens_per_second_per_gpu:777.5045838415192 +Step 2972 | loss:2.1285691261291504 lr:0.00014194457322531985 tokens_per_second_per_gpu:783.7636663492825 +Step 2973 | loss:2.1034603118896484 lr:0.00014190885008584395 tokens_per_second_per_gpu:744.4004783786211 +Step 2974 | loss:2.0668790340423584 lr:0.00014187312045756738 tokens_per_second_per_gpu:776.0223549833473 +Step 2975 | loss:2.046933650970459 lr:0.00014183738434602234 tokens_per_second_per_gpu:767.8145371102506 +Step 2976 | loss:2.043696403503418 lr:0.00014180164175674184 tokens_per_second_per_gpu:768.2231862509841 +Step 2977 | loss:2.046426773071289 lr:0.0001417658926952599 tokens_per_second_per_gpu:790.9348405598087 +Step 2978 | loss:2.088940143585205 lr:0.0001417301371671117 tokens_per_second_per_gpu:739.9008924858881 +Step 2979 | loss:2.0551834106445312 lr:0.00014169437517783323 tokens_per_second_per_gpu:756.1037866799155 +Step 2980 | loss:2.0998106002807617 lr:0.0001416586067329616 tokens_per_second_per_gpu:764.6184376387018 +Step 2981 | loss:2.071247100830078 lr:0.00014162283183803492 tokens_per_second_per_gpu:793.765401158076 +Step 2982 | loss:2.106571674346924 lr:0.00014158705049859216 tokens_per_second_per_gpu:772.0766011106474 +Step 2983 | loss:2.12526798248291 lr:0.00014155126272017346 tokens_per_second_per_gpu:779.4255801585408 +Step 2984 | loss:2.0213325023651123 lr:0.00014151546850831988 tokens_per_second_per_gpu:773.7758144139558 +Step 2985 | loss:2.0969276428222656 lr:0.0001414796678685735 tokens_per_second_per_gpu:772.3306776852586 +Step 2986 | loss:2.10190486907959 lr:0.00014144386080647734 tokens_per_second_per_gpu:794.8272512220116 +Step 2987 | loss:2.0610575675964355 lr:0.00014140804732757546 tokens_per_second_per_gpu:760.0075932432113 +Step 2988 | loss:2.0539753437042236 lr:0.00014137222743741297 tokens_per_second_per_gpu:778.2156856987623 +Step 2989 | loss:2.13478422164917 lr:0.0001413364011415358 tokens_per_second_per_gpu:800.1175934301082 +Step 2990 | loss:2.118868827819824 lr:0.00014130056844549106 tokens_per_second_per_gpu:757.5296518840651 +Step 2991 | loss:2.078845262527466 lr:0.00014126472935482677 tokens_per_second_per_gpu:767.5547588432604 +Step 2992 | loss:2.0192251205444336 lr:0.00014122888387509193 tokens_per_second_per_gpu:759.2580519377336 +Step 2993 | loss:2.1305105686187744 lr:0.0001411930320118365 tokens_per_second_per_gpu:752.528884178848 +Step 2994 | loss:2.091113567352295 lr:0.00014115717377061152 tokens_per_second_per_gpu:750.3067303825305 +Step 2995 | loss:2.0339081287384033 lr:0.00014112130915696893 tokens_per_second_per_gpu:748.8382954887628 +Step 2996 | loss:2.1022210121154785 lr:0.00014108543817646174 tokens_per_second_per_gpu:793.1528019214005 +Step 2997 | loss:2.0314111709594727 lr:0.0001410495608346439 tokens_per_second_per_gpu:761.3147670260429 +Step 2998 | loss:2.09250807762146 lr:0.00014101367713707026 tokens_per_second_per_gpu:766.4990026482888 +Step 2999 | loss:2.1141743659973145 lr:0.00014097778708929682 tokens_per_second_per_gpu:736.6531338796192 +Step 3000 | loss:2.0986037254333496 lr:0.00014094189069688046 tokens_per_second_per_gpu:766.9090522118455 +Step 3001 | loss:2.081010341644287 lr:0.00014090598796537906 tokens_per_second_per_gpu:783.5314746580642 +Step 3002 | loss:2.042357921600342 lr:0.0001408700789003515 tokens_per_second_per_gpu:766.1020041992916 +Step 3003 | loss:2.0936501026153564 lr:0.0001408341635073576 tokens_per_second_per_gpu:792.4835631170682 +Step 3004 | loss:2.078617572784424 lr:0.00014079824179195823 tokens_per_second_per_gpu:751.8199515169607 +Step 3005 | loss:2.094686508178711 lr:0.00014076231375971513 tokens_per_second_per_gpu:761.0347826044838 +Step 3006 | loss:2.0723302364349365 lr:0.00014072637941619113 tokens_per_second_per_gpu:774.8200035032667 +Step 3007 | loss:2.0587451457977295 lr:0.00014069043876694997 tokens_per_second_per_gpu:766.2234536672219 +Step 3008 | loss:2.0736610889434814 lr:0.00014065449181755642 tokens_per_second_per_gpu:751.993593243936 +Step 3009 | loss:2.0499937534332275 lr:0.00014061853857357616 tokens_per_second_per_gpu:766.3427223130152 +Step 3010 | loss:2.046091318130493 lr:0.00014058257904057587 tokens_per_second_per_gpu:775.702407087375 +Step 3011 | loss:2.07035231590271 lr:0.00014054661322412325 tokens_per_second_per_gpu:774.1326606912905 +Step 3012 | loss:2.070631980895996 lr:0.0001405106411297869 tokens_per_second_per_gpu:771.7208617531273 +Step 3013 | loss:2.0984389781951904 lr:0.00014047466276313642 tokens_per_second_per_gpu:791.0712813771079 +Step 3014 | loss:2.0647428035736084 lr:0.00014043867812974238 tokens_per_second_per_gpu:778.2819189707704 +Step 3015 | loss:2.082364320755005 lr:0.00014040268723517637 tokens_per_second_per_gpu:774.2711742319401 +Step 3016 | loss:2.1240594387054443 lr:0.0001403666900850109 tokens_per_second_per_gpu:760.7343245533422 +Step 3017 | loss:2.0395145416259766 lr:0.0001403306866848194 tokens_per_second_per_gpu:763.9577309388317 +Step 3018 | loss:2.088545322418213 lr:0.00014029467704017637 tokens_per_second_per_gpu:737.3870445730812 +Step 3019 | loss:2.108212471008301 lr:0.0001402586611566572 tokens_per_second_per_gpu:798.9493221814447 +Step 3020 | loss:2.07119083404541 lr:0.0001402226390398383 tokens_per_second_per_gpu:780.538393632132 +Step 3021 | loss:2.035440683364868 lr:0.00014018661069529706 tokens_per_second_per_gpu:790.9515713737081 +Step 3022 | loss:2.0540945529937744 lr:0.0001401505761286117 tokens_per_second_per_gpu:783.1435799361113 +Step 3023 | loss:2.0715384483337402 lr:0.00014011453534536157 tokens_per_second_per_gpu:796.837957169703 +Step 3024 | loss:2.057309865951538 lr:0.00014007848835112687 tokens_per_second_per_gpu:766.1116197068068 +Step 3025 | loss:2.1584911346435547 lr:0.00014004243515148882 tokens_per_second_per_gpu:744.7665839515969 +Step 3026 | loss:2.130636215209961 lr:0.00014000637575202956 tokens_per_second_per_gpu:779.0924335800028 +Step 3027 | loss:2.101208209991455 lr:0.0001399703101583323 tokens_per_second_per_gpu:760.6706220192906 +Step 3028 | loss:2.111262321472168 lr:0.00013993423837598093 tokens_per_second_per_gpu:766.9097005252472 +Step 3029 | loss:2.041572332382202 lr:0.0001398981604105607 tokens_per_second_per_gpu:770.1440092280443 +Step 3030 | loss:2.0198869705200195 lr:0.00013986207626765754 tokens_per_second_per_gpu:766.4843672759752 +Step 3031 | loss:2.070234537124634 lr:0.00013982598595285833 tokens_per_second_per_gpu:774.7512253267914 +Step 3032 | loss:1.9884984493255615 lr:0.00013978988947175108 tokens_per_second_per_gpu:778.7571031729536 +Step 3033 | loss:2.0896244049072266 lr:0.00013975378682992457 tokens_per_second_per_gpu:786.8368924956233 +Step 3034 | loss:2.0712642669677734 lr:0.00013971767803296867 tokens_per_second_per_gpu:792.6860973517552 +Step 3035 | loss:2.0412988662719727 lr:0.00013968156308647418 tokens_per_second_per_gpu:753.875450676314 +Step 3036 | loss:2.045870065689087 lr:0.00013964544199603275 tokens_per_second_per_gpu:785.134796037287 +Step 3037 | loss:2.0765280723571777 lr:0.00013960931476723705 tokens_per_second_per_gpu:781.4334103899497 +Step 3038 | loss:2.06274151802063 lr:0.00013957318140568077 tokens_per_second_per_gpu:769.7370307202522 +Step 3039 | loss:1.9841282367706299 lr:0.00013953704191695847 tokens_per_second_per_gpu:753.1217363455817 +Step 3040 | loss:2.1357765197753906 lr:0.00013950089630666564 tokens_per_second_per_gpu:783.1319253216677 +Step 3041 | loss:2.0967354774475098 lr:0.00013946474458039875 tokens_per_second_per_gpu:772.5527929017812 +Step 3042 | loss:2.114799737930298 lr:0.00013942858674375526 tokens_per_second_per_gpu:787.4998614069875 +Step 3043 | loss:2.1055667400360107 lr:0.00013939242280233352 tokens_per_second_per_gpu:759.6739702692636 +Step 3044 | loss:2.0639843940734863 lr:0.00013935625276173278 tokens_per_second_per_gpu:784.766854799334 +Step 3045 | loss:2.1098885536193848 lr:0.00013932007662755338 tokens_per_second_per_gpu:772.5667452867293 +Step 3046 | loss:2.1583285331726074 lr:0.00013928389440539645 tokens_per_second_per_gpu:761.2212725712576 +Step 3047 | loss:2.0274815559387207 lr:0.00013924770610086422 tokens_per_second_per_gpu:788.2316401444717 +Step 3048 | loss:2.1130354404449463 lr:0.0001392115117195597 tokens_per_second_per_gpu:751.5405434709727 +Step 3049 | loss:2.0687971115112305 lr:0.00013917531126708688 tokens_per_second_per_gpu:744.2245960750073 +Step 3050 | loss:2.0928292274475098 lr:0.00013913910474905078 tokens_per_second_per_gpu:780.9917040587897 +Step 3051 | loss:2.0413684844970703 lr:0.0001391028921710573 tokens_per_second_per_gpu:767.1832736391077 +Step 3052 | loss:2.0119009017944336 lr:0.00013906667353871322 tokens_per_second_per_gpu:747.9691903149842 +Step 3053 | loss:2.037106990814209 lr:0.00013903044885762642 tokens_per_second_per_gpu:725.5469075670917 +Step 3054 | loss:2.049935817718506 lr:0.00013899421813340552 tokens_per_second_per_gpu:760.7062797657761 +Step 3055 | loss:2.0577645301818848 lr:0.0001389579813716602 tokens_per_second_per_gpu:761.7635249367883 +Step 3056 | loss:2.0769166946411133 lr:0.00013892173857800108 tokens_per_second_per_gpu:740.7538329294224 +Step 3057 | loss:2.084042549133301 lr:0.00013888548975803962 tokens_per_second_per_gpu:751.5127773915327 +Step 3058 | loss:2.0800483226776123 lr:0.0001388492349173883 tokens_per_second_per_gpu:748.8944580536274 +Step 3059 | loss:2.041916847229004 lr:0.00013881297406166053 tokens_per_second_per_gpu:762.1318854794986 +Step 3060 | loss:2.0333433151245117 lr:0.00013877670719647056 tokens_per_second_per_gpu:756.0149560542342 +Step 3061 | loss:2.044919967651367 lr:0.00013874043432743368 tokens_per_second_per_gpu:780.9298757247384 +Step 3062 | loss:2.0367186069488525 lr:0.00013870415546016605 tokens_per_second_per_gpu:781.5070378772951 +Step 3063 | loss:2.0945816040039062 lr:0.00013866787060028482 tokens_per_second_per_gpu:768.9197915748063 +Step 3064 | loss:2.0775833129882812 lr:0.00013863157975340791 tokens_per_second_per_gpu:775.2363500702334 +Step 3065 | loss:2.1026692390441895 lr:0.00013859528292515437 tokens_per_second_per_gpu:727.4502327798793 +Step 3066 | loss:2.0923664569854736 lr:0.00013855898012114407 tokens_per_second_per_gpu:784.8820079151025 +Step 3067 | loss:2.0888078212738037 lr:0.00013852267134699782 tokens_per_second_per_gpu:780.6064276186003 +Step 3068 | loss:2.117526054382324 lr:0.00013848635660833734 tokens_per_second_per_gpu:788.818950390608 +Step 3069 | loss:2.0635251998901367 lr:0.00013845003591078528 tokens_per_second_per_gpu:787.8956171186163 +Step 3070 | loss:2.06575608253479 lr:0.00013841370925996523 tokens_per_second_per_gpu:708.3994364893905 +Step 3071 | loss:2.1607136726379395 lr:0.0001383773766615017 tokens_per_second_per_gpu:787.2877053261309 +Step 3072 | loss:2.0743446350097656 lr:0.00013834103812102012 tokens_per_second_per_gpu:738.248922601543 +Step 3073 | loss:2.0914764404296875 lr:0.00013830469364414674 tokens_per_second_per_gpu:783.6673871731116 +Step 3074 | loss:2.0702099800109863 lr:0.000138268343236509 tokens_per_second_per_gpu:784.9338563378284 +Step 3075 | loss:1.9993335008621216 lr:0.00013823198690373492 tokens_per_second_per_gpu:758.7798801582791 +Step 3076 | loss:2.0755367279052734 lr:0.00013819562465145366 tokens_per_second_per_gpu:783.1480133426409 +Step 3077 | loss:2.0830278396606445 lr:0.00013815925648529527 tokens_per_second_per_gpu:768.814153684276 +Step 3078 | loss:2.105628490447998 lr:0.00013812288241089063 tokens_per_second_per_gpu:781.6155040225584 +Step 3079 | loss:2.113539218902588 lr:0.00013808650243387155 tokens_per_second_per_gpu:770.4343524949534 +Step 3080 | loss:2.0196492671966553 lr:0.00013805011655987083 tokens_per_second_per_gpu:772.7854544281045 +Step 3081 | loss:2.06046462059021 lr:0.00013801372479452218 tokens_per_second_per_gpu:787.0989470646558 +Step 3082 | loss:2.104506731033325 lr:0.00013797732714346012 tokens_per_second_per_gpu:771.3157242016574 +Step 3083 | loss:2.0419039726257324 lr:0.0001379409236123202 tokens_per_second_per_gpu:753.3166766186259 +Step 3084 | loss:2.083146572113037 lr:0.00013790451420673877 tokens_per_second_per_gpu:790.1181422899269 +Step 3085 | loss:2.067783832550049 lr:0.00013786809893235317 tokens_per_second_per_gpu:794.5560446539362 +Step 3086 | loss:2.0920467376708984 lr:0.00013783167779480166 tokens_per_second_per_gpu:768.9843850897427 +Step 3087 | loss:2.085674285888672 lr:0.0001377952507997233 tokens_per_second_per_gpu:766.721326364158 +Step 3088 | loss:2.1145267486572266 lr:0.00013775881795275816 tokens_per_second_per_gpu:759.558515744086 +Step 3089 | loss:2.1273646354675293 lr:0.0001377223792595472 tokens_per_second_per_gpu:767.0175407351699 +Step 3090 | loss:2.0889735221862793 lr:0.00013768593472573225 tokens_per_second_per_gpu:786.3149829270466 +Step 3091 | loss:2.0465264320373535 lr:0.00013764948435695607 tokens_per_second_per_gpu:764.6943298816911 +Step 3092 | loss:2.1296191215515137 lr:0.0001376130281588623 tokens_per_second_per_gpu:797.054031136922 +Step 3093 | loss:2.054204225540161 lr:0.00013757656613709558 tokens_per_second_per_gpu:796.2545986643121 +Step 3094 | loss:2.136272668838501 lr:0.00013754009829730122 tokens_per_second_per_gpu:770.8998307193406 +Step 3095 | loss:2.0334348678588867 lr:0.00013750362464512575 tokens_per_second_per_gpu:800.4787974248779 +Step 3096 | loss:2.0615108013153076 lr:0.0001374671451862163 tokens_per_second_per_gpu:779.1946174720276 +Step 3097 | loss:2.0314457416534424 lr:0.00013743065992622108 tokens_per_second_per_gpu:788.6257565036475 +Step 3098 | loss:2.0380547046661377 lr:0.00013739416887078917 tokens_per_second_per_gpu:766.3498234681276 +Step 3099 | loss:2.0069539546966553 lr:0.00013735767202557053 tokens_per_second_per_gpu:785.9116783129164 +Step 3100 | loss:2.124077320098877 lr:0.00013732116939621592 tokens_per_second_per_gpu:780.1691519539319 +Step 3101 | loss:2.092787265777588 lr:0.00013728466098837725 tokens_per_second_per_gpu:793.7360965439037 +Step 3102 | loss:2.0745675563812256 lr:0.00013724814680770702 tokens_per_second_per_gpu:787.3090301467643 +Step 3103 | loss:2.103759765625 lr:0.0001372116268598588 tokens_per_second_per_gpu:763.0351439809534 +Step 3104 | loss:2.1041717529296875 lr:0.0001371751011504871 tokens_per_second_per_gpu:764.3308429861856 +Step 3105 | loss:2.0504469871520996 lr:0.00013713856968524714 tokens_per_second_per_gpu:760.1261286680365 +Step 3106 | loss:2.0976481437683105 lr:0.0001371020324697952 tokens_per_second_per_gpu:764.3776229381584 +Step 3107 | loss:2.0433707237243652 lr:0.00013706548950978833 tokens_per_second_per_gpu:776.2616595376654 +Step 3108 | loss:2.0727221965789795 lr:0.00013702894081088455 tokens_per_second_per_gpu:768.3560838358712 +Step 3109 | loss:2.086482524871826 lr:0.00013699238637874275 tokens_per_second_per_gpu:785.9438022031726 +Step 3110 | loss:2.0938353538513184 lr:0.00013695582621902272 tokens_per_second_per_gpu:795.5563432511062 +Step 3111 | loss:2.07193660736084 lr:0.00013691926033738508 tokens_per_second_per_gpu:785.7097448037074 +Step 3112 | loss:2.0708789825439453 lr:0.00013688268873949134 tokens_per_second_per_gpu:763.9371213755994 +Step 3113 | loss:2.151620626449585 lr:0.000136846111431004 tokens_per_second_per_gpu:751.1574276837853 +Step 3114 | loss:2.092022657394409 lr:0.00013680952841758635 tokens_per_second_per_gpu:795.2908084383823 +Step 3115 | loss:2.0824778079986572 lr:0.00013677293970490258 tokens_per_second_per_gpu:769.7675646468338 +Step 3116 | loss:2.0834133625030518 lr:0.00013673634529861773 tokens_per_second_per_gpu:779.4614688573128 +Step 3117 | loss:2.0706539154052734 lr:0.0001366997452043978 tokens_per_second_per_gpu:771.1789917591491 +Step 3118 | loss:2.071113109588623 lr:0.0001366631394279096 tokens_per_second_per_gpu:744.9812124033712 +Step 3119 | loss:2.066251039505005 lr:0.0001366265279748209 tokens_per_second_per_gpu:776.4748307720947 +Step 3120 | loss:2.031045913696289 lr:0.00013658991085080025 tokens_per_second_per_gpu:752.099655545334 +Step 3121 | loss:2.103471517562866 lr:0.00013655328806151714 tokens_per_second_per_gpu:750.6829260907228 +Step 3122 | loss:2.081953763961792 lr:0.00013651665961264192 tokens_per_second_per_gpu:779.435991893324 +Step 3123 | loss:2.0722923278808594 lr:0.00013648002550984583 tokens_per_second_per_gpu:776.1507997122344 +Step 3124 | loss:2.0336978435516357 lr:0.00013644338575880097 tokens_per_second_per_gpu:763.0247530602408 +Step 3125 | loss:2.082854747772217 lr:0.00013640674036518032 tokens_per_second_per_gpu:784.9495586752988 +Step 3126 | loss:2.1235716342926025 lr:0.00013637008933465772 tokens_per_second_per_gpu:772.1818957936816 +Step 3127 | loss:2.083892583847046 lr:0.0001363334326729079 tokens_per_second_per_gpu:784.0634327478589 +Step 3128 | loss:2.079824447631836 lr:0.0001362967703856065 tokens_per_second_per_gpu:773.9919037640939 +Step 3129 | loss:2.0189287662506104 lr:0.00013626010247842988 tokens_per_second_per_gpu:772.7712058241606 +Step 3130 | loss:2.100130081176758 lr:0.00013622342895705552 tokens_per_second_per_gpu:753.5249655436818 +Step 3131 | loss:2.0406033992767334 lr:0.00013618674982716154 tokens_per_second_per_gpu:767.2200163783576 +Step 3132 | loss:2.058201313018799 lr:0.000136150065094427 tokens_per_second_per_gpu:782.9698581811579 +Step 3133 | loss:2.0554943084716797 lr:0.00013611337476453192 tokens_per_second_per_gpu:787.2941264655301 +Step 3134 | loss:2.0803961753845215 lr:0.00013607667884315706 tokens_per_second_per_gpu:759.3723891050976 +Step 3135 | loss:2.0649852752685547 lr:0.0001360399773359841 tokens_per_second_per_gpu:770.3293332355388 +Step 3136 | loss:2.0398240089416504 lr:0.0001360032702486956 tokens_per_second_per_gpu:770.5640602327007 +Step 3137 | loss:2.103848934173584 lr:0.00013596655758697494 tokens_per_second_per_gpu:768.1876670536203 +Step 3138 | loss:2.013814926147461 lr:0.0001359298393565064 tokens_per_second_per_gpu:767.8106857597296 +Step 3139 | loss:2.0430893898010254 lr:0.0001358931155629751 tokens_per_second_per_gpu:735.4754225922305 +Step 3140 | loss:2.0445244312286377 lr:0.00013585638621206706 tokens_per_second_per_gpu:795.9666607320512 +Step 3141 | loss:2.0460851192474365 lr:0.0001358196513094691 tokens_per_second_per_gpu:764.6742461173691 +Step 3142 | loss:2.0744242668151855 lr:0.00013578291086086897 tokens_per_second_per_gpu:774.2160457357551 +Step 3143 | loss:2.091695547103882 lr:0.00013574616487195518 tokens_per_second_per_gpu:787.7925941903617 +Step 3144 | loss:2.0661392211914062 lr:0.00013570941334841723 tokens_per_second_per_gpu:785.7593712747606 +Step 3145 | loss:2.0466556549072266 lr:0.00013567265629594534 tokens_per_second_per_gpu:786.7624086434536 +Step 3146 | loss:2.0031790733337402 lr:0.00013563589372023069 tokens_per_second_per_gpu:790.3994430205775 +Step 3147 | loss:2.0552027225494385 lr:0.0001355991256269653 tokens_per_second_per_gpu:785.6293852433026 +Step 3148 | loss:2.0945851802825928 lr:0.00013556235202184192 tokens_per_second_per_gpu:785.543252472267 +Step 3149 | loss:2.036613941192627 lr:0.00013552557291055437 tokens_per_second_per_gpu:766.838093116282 +Step 3150 | loss:2.0489771366119385 lr:0.00013548878829879716 tokens_per_second_per_gpu:779.8230783421177 +Step 3151 | loss:2.084077835083008 lr:0.00013545199819226566 tokens_per_second_per_gpu:766.9607124269937 +Step 3152 | loss:2.0463931560516357 lr:0.0001354152025966562 tokens_per_second_per_gpu:770.8285350006901 +Step 3153 | loss:2.0283899307250977 lr:0.00013537840151766587 tokens_per_second_per_gpu:766.4874238401673 +Step 3154 | loss:2.0628793239593506 lr:0.00013534159496099256 tokens_per_second_per_gpu:746.3099671671241 +Step 3155 | loss:2.061887741088867 lr:0.00013530478293233517 tokens_per_second_per_gpu:734.7578884690275 +Step 3156 | loss:2.0543324947357178 lr:0.0001352679654373933 tokens_per_second_per_gpu:793.465835455331 +Step 3157 | loss:2.07958984375 lr:0.00013523114248186746 tokens_per_second_per_gpu:769.669803309942 +Step 3158 | loss:2.0775198936462402 lr:0.00013519431407145902 tokens_per_second_per_gpu:798.9541076281241 +Step 3159 | loss:2.027270555496216 lr:0.0001351574802118701 tokens_per_second_per_gpu:780.9886228989857 +Step 3160 | loss:1.9462006092071533 lr:0.0001351206409088038 tokens_per_second_per_gpu:777.3167383085139 +Step 3161 | loss:2.108196258544922 lr:0.00013508379616796398 tokens_per_second_per_gpu:788.9299144266464 +Step 3162 | loss:2.0526444911956787 lr:0.00013504694599505537 tokens_per_second_per_gpu:778.2387958307288 +Step 3163 | loss:2.0726723670959473 lr:0.00013501009039578347 tokens_per_second_per_gpu:766.8235322335072 +Step 3164 | loss:2.1163644790649414 lr:0.00013497322937585475 tokens_per_second_per_gpu:777.4028340066764 +Step 3165 | loss:2.097830057144165 lr:0.00013493636294097642 tokens_per_second_per_gpu:771.1403000781579 +Step 3166 | loss:2.0950331687927246 lr:0.00013489949109685655 tokens_per_second_per_gpu:761.9621899237281 +Step 3167 | loss:2.037090539932251 lr:0.00013486261384920408 tokens_per_second_per_gpu:774.5247911798999 +Step 3168 | loss:2.0933644771575928 lr:0.00013482573120372873 tokens_per_second_per_gpu:775.7595798825696 +Step 3169 | loss:2.111854314804077 lr:0.0001347888431661411 tokens_per_second_per_gpu:781.3832929547228 +Step 3170 | loss:2.1028997898101807 lr:0.00013475194974215258 tokens_per_second_per_gpu:796.5307081206391 +Step 3171 | loss:2.0746397972106934 lr:0.00013471505093747555 tokens_per_second_per_gpu:778.1404402614687 +Step 3172 | loss:2.0934271812438965 lr:0.0001346781467578229 tokens_per_second_per_gpu:782.4165496185666 +Step 3173 | loss:2.085054636001587 lr:0.0001346412372089087 tokens_per_second_per_gpu:752.2256976146149 +Step 3174 | loss:2.0832183361053467 lr:0.0001346043222964477 tokens_per_second_per_gpu:750.0097008017823 +Step 3175 | loss:2.0838980674743652 lr:0.00013456740202615538 tokens_per_second_per_gpu:783.3004287198368 +Step 3176 | loss:2.0241453647613525 lr:0.00013453047640374827 tokens_per_second_per_gpu:772.8002658316243 +Step 3177 | loss:2.0919599533081055 lr:0.00013449354543494354 tokens_per_second_per_gpu:787.8824239963515 +Step 3178 | loss:2.051398277282715 lr:0.00013445660912545925 tokens_per_second_per_gpu:801.3930420770826 +Step 3179 | loss:2.083536148071289 lr:0.00013441966748101435 tokens_per_second_per_gpu:759.2904945021633 +Step 3180 | loss:2.0325417518615723 lr:0.00013438272050732853 tokens_per_second_per_gpu:782.6455312417638 +Step 3181 | loss:2.054441452026367 lr:0.00013434576821012232 tokens_per_second_per_gpu:771.9424408723698 +Step 3182 | loss:2.129638433456421 lr:0.00013430881059511713 tokens_per_second_per_gpu:769.9080032805931 +Step 3183 | loss:2.0643560886383057 lr:0.00013427184766803515 tokens_per_second_per_gpu:794.4132589308258 +Step 3184 | loss:2.123115062713623 lr:0.00013423487943459934 tokens_per_second_per_gpu:750.4877804310192 +Step 3185 | loss:2.050114393234253 lr:0.00013419790590053364 tokens_per_second_per_gpu:779.6416727425152 +Step 3186 | loss:2.0960159301757812 lr:0.00013416092707156261 tokens_per_second_per_gpu:788.7225318759456 +Step 3187 | loss:2.1016476154327393 lr:0.00013412394295341174 tokens_per_second_per_gpu:761.7704478914918 +Step 3188 | loss:2.0442264080047607 lr:0.00013408695355180742 tokens_per_second_per_gpu:750.7038256129775 +Step 3189 | loss:2.1266262531280518 lr:0.0001340499588724767 tokens_per_second_per_gpu:762.3367941615195 +Step 3190 | loss:2.043119430541992 lr:0.0001340129589211475 tokens_per_second_per_gpu:764.3855850544435 +Step 3191 | loss:2.0449378490448 lr:0.00013397595370354855 tokens_per_second_per_gpu:774.7258396786499 +Step 3192 | loss:2.057790756225586 lr:0.0001339389432254095 tokens_per_second_per_gpu:762.6444653391419 +Step 3193 | loss:2.0803632736206055 lr:0.0001339019274924607 tokens_per_second_per_gpu:786.6731895444999 +Step 3194 | loss:2.045206308364868 lr:0.00013386490651043326 tokens_per_second_per_gpu:789.8383031473402 +Step 3195 | loss:2.1098458766937256 lr:0.0001338278802850593 tokens_per_second_per_gpu:781.5504810748494 +Step 3196 | loss:2.0721256732940674 lr:0.00013379084882207158 tokens_per_second_per_gpu:768.3186026496293 +Step 3197 | loss:2.115626573562622 lr:0.00013375381212720372 tokens_per_second_per_gpu:766.2359142055105 +Step 3198 | loss:1.9963328838348389 lr:0.0001337167702061902 tokens_per_second_per_gpu:765.1816179719644 +Step 3199 | loss:2.077854871749878 lr:0.0001336797230647662 tokens_per_second_per_gpu:781.4090337228621 +Step 3200 | loss:2.0889086723327637 lr:0.00013364267070866786 tokens_per_second_per_gpu:763.2252696026485 +Step 3201 | loss:2.054513931274414 lr:0.00013360561314363202 tokens_per_second_per_gpu:784.8243745773332 +Step 3202 | loss:2.0351474285125732 lr:0.00013356855037539625 tokens_per_second_per_gpu:768.3847545232315 +Step 3203 | loss:2.100055694580078 lr:0.0001335314824096992 tokens_per_second_per_gpu:787.8318010314565 +Step 3204 | loss:2.0805981159210205 lr:0.00013349440925228002 tokens_per_second_per_gpu:782.491729359933 +Step 3205 | loss:2.140991449356079 lr:0.00013345733090887882 tokens_per_second_per_gpu:778.8607650034814 +Step 3206 | loss:2.137828826904297 lr:0.00013342024738523652 tokens_per_second_per_gpu:770.2438491005041 +Step 3207 | loss:2.0988218784332275 lr:0.00013338315868709476 tokens_per_second_per_gpu:771.3151997802064 +Step 3208 | loss:2.1090707778930664 lr:0.00013334606482019607 tokens_per_second_per_gpu:752.8586273958352 +Step 3209 | loss:2.036339282989502 lr:0.00013330896579028377 tokens_per_second_per_gpu:758.4363873273179 +Step 3210 | loss:2.112090587615967 lr:0.00013327186160310184 tokens_per_second_per_gpu:762.1057820673624 +Step 3211 | loss:2.093384027481079 lr:0.0001332347522643953 tokens_per_second_per_gpu:757.86506742546 +Step 3212 | loss:2.0269417762756348 lr:0.00013319763777990974 tokens_per_second_per_gpu:778.0254825934455 +Step 3213 | loss:2.0772855281829834 lr:0.0001331605181553917 tokens_per_second_per_gpu:762.0883291929196 +Step 3214 | loss:2.0951709747314453 lr:0.0001331233933965884 tokens_per_second_per_gpu:761.6609712654085 +Step 3215 | loss:2.0497007369995117 lr:0.00013308626350924798 tokens_per_second_per_gpu:790.9779502171316 +Step 3216 | loss:2.072303056716919 lr:0.00013304912849911927 tokens_per_second_per_gpu:733.1431202155197 +Step 3217 | loss:2.040616989135742 lr:0.00013301198837195195 tokens_per_second_per_gpu:787.094070367118 +Step 3218 | loss:2.0609259605407715 lr:0.00013297484313349643 tokens_per_second_per_gpu:728.7407453425978 +Step 3219 | loss:2.036895990371704 lr:0.00013293769278950403 tokens_per_second_per_gpu:726.3460142522094 +Step 3220 | loss:2.0928683280944824 lr:0.0001329005373457267 tokens_per_second_per_gpu:777.9118751634654 +Step 3221 | loss:2.038172960281372 lr:0.00013286337680791733 tokens_per_second_per_gpu:768.3694803614368 +Step 3222 | loss:2.0680744647979736 lr:0.00013282621118182952 tokens_per_second_per_gpu:768.6178354736038 +Step 3223 | loss:2.0780234336853027 lr:0.00013278904047321762 tokens_per_second_per_gpu:763.0295687866513 +Step 3224 | loss:2.044752597808838 lr:0.00013275186468783687 tokens_per_second_per_gpu:765.1205326171251 +Step 3225 | loss:2.1147255897521973 lr:0.00013271468383144324 tokens_per_second_per_gpu:753.9820520582336 +Step 3226 | loss:2.078887939453125 lr:0.0001326774979097935 tokens_per_second_per_gpu:774.024230046296 +Step 3227 | loss:2.1094441413879395 lr:0.00013264030692864513 tokens_per_second_per_gpu:766.9658915094847 +Step 3228 | loss:2.120718002319336 lr:0.00013260311089375657 tokens_per_second_per_gpu:760.3488311049707 +Step 3229 | loss:2.05586576461792 lr:0.00013256590981088677 tokens_per_second_per_gpu:778.8112037398512 +Step 3230 | loss:2.04775333404541 lr:0.0001325287036857958 tokens_per_second_per_gpu:793.3806780678799 +Step 3231 | loss:2.073253870010376 lr:0.0001324914925242442 tokens_per_second_per_gpu:747.5720305333781 +Step 3232 | loss:2.0118699073791504 lr:0.00013245427633199345 tokens_per_second_per_gpu:777.9267000418803 +Step 3233 | loss:2.037850856781006 lr:0.00013241705511480586 tokens_per_second_per_gpu:750.3815204614983 +Step 3234 | loss:2.016711711883545 lr:0.0001323798288784443 tokens_per_second_per_gpu:767.8277363364402 +Step 3235 | loss:2.1377410888671875 lr:0.00013234259762867265 tokens_per_second_per_gpu:746.2848692542384 +Step 3236 | loss:2.0711896419525146 lr:0.0001323053613712555 tokens_per_second_per_gpu:743.3589772973065 +Step 3237 | loss:2.0919790267944336 lr:0.0001322681201119581 tokens_per_second_per_gpu:783.2211580377298 +Step 3238 | loss:2.0815305709838867 lr:0.00013223087385654659 tokens_per_second_per_gpu:799.6602020099119 +Step 3239 | loss:2.107997417449951 lr:0.00013219362261078786 tokens_per_second_per_gpu:758.2961022909226 +Step 3240 | loss:2.029881477355957 lr:0.0001321563663804496 tokens_per_second_per_gpu:751.8481623168694 +Step 3241 | loss:2.0743024349212646 lr:0.00013211910517130023 tokens_per_second_per_gpu:791.4065818853437 +Step 3242 | loss:2.0483968257904053 lr:0.00013208183898910888 tokens_per_second_per_gpu:762.6145906061332 +Step 3243 | loss:2.0682730674743652 lr:0.00013204456783964564 tokens_per_second_per_gpu:788.9266459988902 +Step 3244 | loss:2.07330322265625 lr:0.00013200729172868113 tokens_per_second_per_gpu:774.8825890118038 +Step 3245 | loss:2.086881637573242 lr:0.00013197001066198692 tokens_per_second_per_gpu:777.0346786003307 +Step 3246 | loss:2.070618152618408 lr:0.0001319327246453353 tokens_per_second_per_gpu:774.2278026420473 +Step 3247 | loss:2.0645689964294434 lr:0.00013189543368449927 tokens_per_second_per_gpu:786.3591510628079 +Step 3248 | loss:2.052161693572998 lr:0.00013185813778525263 tokens_per_second_per_gpu:796.3583078546754 +Step 3249 | loss:2.1085965633392334 lr:0.00013182083695337005 tokens_per_second_per_gpu:777.8474139469993 +Step 3250 | loss:2.0574984550476074 lr:0.00013178353119462673 tokens_per_second_per_gpu:762.8784385467137 +Step 3251 | loss:2.0453057289123535 lr:0.00013174622051479883 tokens_per_second_per_gpu:762.2343318753736 +Step 3252 | loss:2.1234750747680664 lr:0.00013170890491966323 tokens_per_second_per_gpu:797.6037816977517 +Step 3253 | loss:2.0422494411468506 lr:0.00013167158441499752 tokens_per_second_per_gpu:775.9858097738631 +Step 3254 | loss:2.109586715698242 lr:0.0001316342590065801 tokens_per_second_per_gpu:784.7849505986061 +Step 3255 | loss:2.04315185546875 lr:0.0001315969287001901 tokens_per_second_per_gpu:770.6955749208182 +Step 3256 | loss:2.018616199493408 lr:0.00013155959350160738 tokens_per_second_per_gpu:752.5279590627313 +Step 3257 | loss:2.0137434005737305 lr:0.0001315222534166127 tokens_per_second_per_gpu:786.8887586830552 +Step 3258 | loss:2.044494390487671 lr:0.00013148490845098736 tokens_per_second_per_gpu:747.9588060744593 +Step 3259 | loss:2.12007212638855 lr:0.0001314475586105136 tokens_per_second_per_gpu:745.5366350270366 +Step 3260 | loss:2.125286102294922 lr:0.00013141020390097433 tokens_per_second_per_gpu:777.465530020148 +Step 3261 | loss:2.069629192352295 lr:0.00013137284432815323 tokens_per_second_per_gpu:774.073096370538 +Step 3262 | loss:2.0817253589630127 lr:0.0001313354798978347 tokens_per_second_per_gpu:792.4076887347086 +Step 3263 | loss:2.097546100616455 lr:0.00013129811061580394 tokens_per_second_per_gpu:770.3454720060736 +Step 3264 | loss:2.0283617973327637 lr:0.00013126073648784688 tokens_per_second_per_gpu:780.3957211508391 +Step 3265 | loss:2.0292739868164062 lr:0.00013122335751975021 tokens_per_second_per_gpu:766.2297053662344 +Step 3266 | loss:2.063253879547119 lr:0.00013118597371730137 tokens_per_second_per_gpu:763.1148883622228 +Step 3267 | loss:2.0291717052459717 lr:0.00013114858508628857 tokens_per_second_per_gpu:788.9972246270349 +Step 3268 | loss:2.0549442768096924 lr:0.00013111119163250064 tokens_per_second_per_gpu:789.675115289497 +Step 3269 | loss:2.0625782012939453 lr:0.00013107379336172733 tokens_per_second_per_gpu:776.3590841291943 +Step 3270 | loss:2.0440521240234375 lr:0.0001310363902797591 tokens_per_second_per_gpu:781.7356174576705 +Step 3271 | loss:2.075863838195801 lr:0.00013099898239238704 tokens_per_second_per_gpu:779.9798558826537 +Step 3272 | loss:2.0353119373321533 lr:0.00013096156970540305 tokens_per_second_per_gpu:783.7107488988365 +Step 3273 | loss:2.0668458938598633 lr:0.00013092415222459988 tokens_per_second_per_gpu:783.9707544945892 +Step 3274 | loss:2.0512478351593018 lr:0.00013088672995577086 tokens_per_second_per_gpu:763.6952813754064 +Step 3275 | loss:2.079829692840576 lr:0.00013084930290471012 tokens_per_second_per_gpu:758.0813199841615 +Step 3276 | loss:2.0108141899108887 lr:0.00013081187107721255 tokens_per_second_per_gpu:782.3819388416144 +Step 3277 | loss:2.1381428241729736 lr:0.0001307744344790738 tokens_per_second_per_gpu:770.0337620708481 +Step 3278 | loss:2.0744364261627197 lr:0.00013073699311609015 tokens_per_second_per_gpu:798.2755186514079 +Step 3279 | loss:2.030697822570801 lr:0.00013069954699405876 tokens_per_second_per_gpu:768.2444578529299 +Step 3280 | loss:2.060511350631714 lr:0.00013066209611877746 tokens_per_second_per_gpu:781.0065251494603 +Step 3281 | loss:2.0208804607391357 lr:0.0001306246404960448 tokens_per_second_per_gpu:787.7603326044718 +Step 3282 | loss:2.0681653022766113 lr:0.00013058718013166004 tokens_per_second_per_gpu:796.4896541874266 +Step 3283 | loss:2.062075614929199 lr:0.0001305497150314233 tokens_per_second_per_gpu:790.5893328981671 +Step 3284 | loss:2.0825822353363037 lr:0.0001305122452011353 tokens_per_second_per_gpu:773.4943370236344 +Step 3285 | loss:2.062548875808716 lr:0.00013047477064659753 tokens_per_second_per_gpu:779.0524127498352 +Step 3286 | loss:2.1022891998291016 lr:0.00013043729137361223 tokens_per_second_per_gpu:780.7087243380889 +Step 3287 | loss:2.0702662467956543 lr:0.00013039980738798244 tokens_per_second_per_gpu:765.312417179041 +Step 3288 | loss:2.071666717529297 lr:0.0001303623186955117 tokens_per_second_per_gpu:775.8553464531157 +Step 3289 | loss:2.0447680950164795 lr:0.00013032482530200457 tokens_per_second_per_gpu:757.4329459671368 +Step 3290 | loss:2.0660128593444824 lr:0.00013028732721326612 tokens_per_second_per_gpu:775.4470155300774 +Step 3291 | loss:2.036367654800415 lr:0.0001302498244351023 tokens_per_second_per_gpu:787.0274341114796 +Step 3292 | loss:2.09346604347229 lr:0.00013021231697331963 tokens_per_second_per_gpu:775.6062458311669 +Step 3293 | loss:2.1086626052856445 lr:0.0001301748048337255 tokens_per_second_per_gpu:788.9195946912549 +Step 3294 | loss:1.9967002868652344 lr:0.00013013728802212793 tokens_per_second_per_gpu:771.8127733915151 +Step 3295 | loss:2.0340688228607178 lr:0.0001300997665443357 tokens_per_second_per_gpu:793.5613232028818 +Step 3296 | loss:2.0791308879852295 lr:0.00013006224040615832 tokens_per_second_per_gpu:776.7885650191726 +Step 3297 | loss:2.093761920928955 lr:0.000130024709613406 tokens_per_second_per_gpu:748.5701740855233 +Step 3298 | loss:2.0695037841796875 lr:0.0001299871741718897 tokens_per_second_per_gpu:776.4411561641731 +Step 3299 | loss:2.0461175441741943 lr:0.00012994963408742102 tokens_per_second_per_gpu:765.2399363917492 +Step 3300 | loss:2.034935474395752 lr:0.00012991208936581242 tokens_per_second_per_gpu:769.1474623413403 +Step 3301 | loss:2.037073850631714 lr:0.00012987454001287695 tokens_per_second_per_gpu:790.9751874687513 +Step 3302 | loss:2.1300082206726074 lr:0.00012983698603442843 tokens_per_second_per_gpu:761.9663593058867 +Step 3303 | loss:1.9949429035186768 lr:0.0001297994274362814 tokens_per_second_per_gpu:776.0245008858708 +Step 3304 | loss:2.038057804107666 lr:0.0001297618642242511 tokens_per_second_per_gpu:775.6952022746123 +Step 3305 | loss:2.0370593070983887 lr:0.00012972429640415348 tokens_per_second_per_gpu:773.396974698482 +Step 3306 | loss:2.0042030811309814 lr:0.0001296867239818052 tokens_per_second_per_gpu:781.7544800129746 +Step 3307 | loss:2.031964063644409 lr:0.0001296491469630237 tokens_per_second_per_gpu:795.171701932742 +Step 3308 | loss:2.0351784229278564 lr:0.00012961156535362705 tokens_per_second_per_gpu:779.4936123063178 +Step 3309 | loss:2.0652287006378174 lr:0.00012957397915943402 tokens_per_second_per_gpu:768.8194853298645 +Step 3310 | loss:2.070967674255371 lr:0.00012953638838626418 tokens_per_second_per_gpu:784.74417918668 +Step 3311 | loss:2.034137487411499 lr:0.00012949879303993775 tokens_per_second_per_gpu:775.1827739039873 +Step 3312 | loss:2.104414701461792 lr:0.00012946119312627565 tokens_per_second_per_gpu:782.1278545807768 +Step 3313 | loss:2.0597281455993652 lr:0.0001294235886510995 tokens_per_second_per_gpu:765.8059824288315 +Step 3314 | loss:2.1101455688476562 lr:0.00012938597962023173 tokens_per_second_per_gpu:743.2223432699994 +Step 3315 | loss:2.0149641036987305 lr:0.0001293483660394953 tokens_per_second_per_gpu:751.0746458960448 +Step 3316 | loss:2.0127973556518555 lr:0.00012931074791471401 tokens_per_second_per_gpu:763.2453375179061 +Step 3317 | loss:2.0736396312713623 lr:0.00012927312525171236 tokens_per_second_per_gpu:760.6190016848142 +Step 3318 | loss:2.018960475921631 lr:0.00012923549805631546 tokens_per_second_per_gpu:767.7317771558631 +Step 3319 | loss:2.012688398361206 lr:0.00012919786633434915 tokens_per_second_per_gpu:783.2481959592778 +Step 3320 | loss:2.063368797302246 lr:0.0001291602300916401 tokens_per_second_per_gpu:786.625378961249 +Step 3321 | loss:2.0358216762542725 lr:0.0001291225893340155 tokens_per_second_per_gpu:762.9347320996366 +Step 3322 | loss:2.0353565216064453 lr:0.0001290849440673033 tokens_per_second_per_gpu:756.7270526527462 +Step 3323 | loss:2.0459656715393066 lr:0.00012904729429733222 tokens_per_second_per_gpu:777.7102301632067 +Step 3324 | loss:2.0481390953063965 lr:0.0001290096400299316 tokens_per_second_per_gpu:797.0470605454257 +Step 3325 | loss:1.9927074909210205 lr:0.0001289719812709315 tokens_per_second_per_gpu:759.5147020540775 +Step 3326 | loss:2.0511841773986816 lr:0.00012893431802616268 tokens_per_second_per_gpu:767.4015214895511 +Step 3327 | loss:2.095010757446289 lr:0.0001288966503014566 tokens_per_second_per_gpu:758.7520407170343 +Step 3328 | loss:2.100971221923828 lr:0.00012885897810264532 tokens_per_second_per_gpu:767.040411540045 +Step 3329 | loss:2.0158724784851074 lr:0.00012882130143556178 tokens_per_second_per_gpu:771.0676920510164 +Step 3330 | loss:2.047945499420166 lr:0.00012878362030603946 tokens_per_second_per_gpu:796.4627456716188 +Step 3331 | loss:2.0885376930236816 lr:0.00012874593471991257 tokens_per_second_per_gpu:790.1877971989759 +Step 3332 | loss:2.0702483654022217 lr:0.000128708244683016 tokens_per_second_per_gpu:765.8282576264982 +Step 3333 | loss:2.0144433975219727 lr:0.00012867055020118542 tokens_per_second_per_gpu:786.0819571058348 +Step 3334 | loss:2.105672836303711 lr:0.00012863285128025703 tokens_per_second_per_gpu:785.8227153639693 +Step 3335 | loss:2.0907881259918213 lr:0.00012859514792606786 tokens_per_second_per_gpu:789.674593985191 +Step 3336 | loss:2.0703539848327637 lr:0.00012855744014445553 tokens_per_second_per_gpu:790.8607955308526 +Step 3337 | loss:2.0302062034606934 lr:0.00012851972794125847 tokens_per_second_per_gpu:802.9883650645908 +Step 3338 | loss:2.0576417446136475 lr:0.00012848201132231556 tokens_per_second_per_gpu:749.1451447452297 +Step 3339 | loss:2.079613447189331 lr:0.00012844429029346664 tokens_per_second_per_gpu:771.5565325236332 +Step 3340 | loss:2.034529685974121 lr:0.000128406564860552 tokens_per_second_per_gpu:758.5186708754123 +Step 3341 | loss:2.059161901473999 lr:0.00012836883502941282 tokens_per_second_per_gpu:757.4282451135451 +Step 3342 | loss:2.07824969291687 lr:0.00012833110080589082 tokens_per_second_per_gpu:772.7748142466007 +Step 3343 | loss:2.1115894317626953 lr:0.00012829336219582842 tokens_per_second_per_gpu:779.6338505395637 +Step 3344 | loss:1.9966411590576172 lr:0.00012825561920506873 tokens_per_second_per_gpu:773.5375306751062 +Step 3345 | loss:2.0749382972717285 lr:0.0001282178718394556 tokens_per_second_per_gpu:759.6077855170819 +Step 3346 | loss:2.082681179046631 lr:0.00012818012010483342 tokens_per_second_per_gpu:779.960637791368 +Step 3347 | loss:2.1029326915740967 lr:0.00012814236400704738 tokens_per_second_per_gpu:769.9764413968259 +Step 3348 | loss:2.070167064666748 lr:0.00012810460355194335 tokens_per_second_per_gpu:761.7162775267205 +Step 3349 | loss:2.0570836067199707 lr:0.00012806683874536776 tokens_per_second_per_gpu:741.3264413648252 +Step 3350 | loss:2.0643932819366455 lr:0.0001280290695931678 tokens_per_second_per_gpu:771.54519644327 +Step 3351 | loss:2.0333616733551025 lr:0.00012799129610119138 tokens_per_second_per_gpu:801.8004459149711 +Step 3352 | loss:2.071415662765503 lr:0.00012795351827528693 tokens_per_second_per_gpu:774.8609461946513 +Step 3353 | loss:2.0322694778442383 lr:0.00012791573612130365 tokens_per_second_per_gpu:761.1292550553584 +Step 3354 | loss:2.058586597442627 lr:0.00012787794964509147 tokens_per_second_per_gpu:794.1505846302487 +Step 3355 | loss:2.129044532775879 lr:0.00012784015885250084 tokens_per_second_per_gpu:779.0803755525953 +Step 3356 | loss:2.0880322456359863 lr:0.00012780236374938298 tokens_per_second_per_gpu:774.1574527122501 +Step 3357 | loss:2.04024338722229 lr:0.00012776456434158978 tokens_per_second_per_gpu:769.7670683062249 +Step 3358 | loss:2.0783438682556152 lr:0.00012772676063497375 tokens_per_second_per_gpu:752.0903932448392 +Step 3359 | loss:2.1070196628570557 lr:0.00012768895263538807 tokens_per_second_per_gpu:789.5765990314469 +Step 3360 | loss:2.1399388313293457 lr:0.00012765114034868664 tokens_per_second_per_gpu:747.67539114989 +Step 3361 | loss:2.100433111190796 lr:0.00012761332378072397 tokens_per_second_per_gpu:787.5737198294337 +Step 3362 | loss:2.0999345779418945 lr:0.0001275755029373552 tokens_per_second_per_gpu:769.2817417050278 +Step 3363 | loss:2.0824172496795654 lr:0.00012753767782443625 tokens_per_second_per_gpu:740.620018283686 +Step 3364 | loss:2.0893402099609375 lr:0.0001274998484478236 tokens_per_second_per_gpu:761.3376735940496 +Step 3365 | loss:2.030924081802368 lr:0.0001274620148133744 tokens_per_second_per_gpu:794.1305327246309 +Step 3366 | loss:2.061490058898926 lr:0.00012742417692694651 tokens_per_second_per_gpu:790.9644174347806 +Step 3367 | loss:2.089946746826172 lr:0.0001273863347943984 tokens_per_second_per_gpu:773.3994788361296 +Step 3368 | loss:2.1336829662323 lr:0.00012734848842158925 tokens_per_second_per_gpu:761.4478601311527 +Step 3369 | loss:2.061342716217041 lr:0.0001273106378143788 tokens_per_second_per_gpu:757.5242655553949 +Step 3370 | loss:2.0788235664367676 lr:0.00012727278297862757 tokens_per_second_per_gpu:766.5723490011097 +Step 3371 | loss:2.083418607711792 lr:0.00012723492392019664 tokens_per_second_per_gpu:772.8218668809149 +Step 3372 | loss:2.017761707305908 lr:0.00012719706064494779 tokens_per_second_per_gpu:795.6031705723714 +Step 3373 | loss:2.0042266845703125 lr:0.00012715919315874343 tokens_per_second_per_gpu:779.6123913821754 +Step 3374 | loss:2.0399868488311768 lr:0.0001271213214674466 tokens_per_second_per_gpu:762.5630963898445 +Step 3375 | loss:2.0596606731414795 lr:0.0001270834455769211 tokens_per_second_per_gpu:774.7589035604643 +Step 3376 | loss:2.100490093231201 lr:0.00012704556549303123 tokens_per_second_per_gpu:774.5759316537943 +Step 3377 | loss:2.0888500213623047 lr:0.00012700768122164203 tokens_per_second_per_gpu:782.1026610131843 +Step 3378 | loss:2.0353524684906006 lr:0.0001269697927686192 tokens_per_second_per_gpu:792.036766534547 +Step 3379 | loss:2.13897442817688 lr:0.00012693190013982904 tokens_per_second_per_gpu:774.9646901700277 +Step 3380 | loss:2.0664260387420654 lr:0.0001268940033411385 tokens_per_second_per_gpu:775.8563570469595 +Step 3381 | loss:2.0946216583251953 lr:0.0001268561023784152 tokens_per_second_per_gpu:771.5069085723509 +Step 3382 | loss:2.01387357711792 lr:0.00012681819725752735 tokens_per_second_per_gpu:770.6956375662116 +Step 3383 | loss:2.0721726417541504 lr:0.00012678028798434395 tokens_per_second_per_gpu:775.500153643838 +Step 3384 | loss:2.1030423641204834 lr:0.00012674237456473443 tokens_per_second_per_gpu:773.7447841985347 +Step 3385 | loss:2.0506958961486816 lr:0.0001267044570045691 tokens_per_second_per_gpu:717.0000586890828 +Step 3386 | loss:2.0249030590057373 lr:0.00012666653530971864 tokens_per_second_per_gpu:772.3602249359158 +Step 3387 | loss:2.042945623397827 lr:0.00012662860948605458 tokens_per_second_per_gpu:764.4559479075041 +Step 3388 | loss:2.0433247089385986 lr:0.0001265906795394491 tokens_per_second_per_gpu:776.6325313774429 +Step 3389 | loss:2.077892541885376 lr:0.0001265527454757748 tokens_per_second_per_gpu:763.6479500102829 +Step 3390 | loss:2.0359652042388916 lr:0.00012651480730090518 tokens_per_second_per_gpu:743.0824879599176 +Step 3391 | loss:2.078697919845581 lr:0.00012647686502071417 tokens_per_second_per_gpu:767.4639734601989 +Step 3392 | loss:2.0314226150512695 lr:0.00012643891864107644 tokens_per_second_per_gpu:768.4307984358475 +Step 3393 | loss:2.0001564025878906 lr:0.00012640096816786734 tokens_per_second_per_gpu:755.414012881654 +Step 3394 | loss:2.0520782470703125 lr:0.0001263630136069627 tokens_per_second_per_gpu:766.8054604268085 +Step 3395 | loss:2.11181640625 lr:0.00012632505496423913 tokens_per_second_per_gpu:780.0657251115014 +Step 3396 | loss:2.050387382507324 lr:0.0001262870922455738 tokens_per_second_per_gpu:771.2342828367123 +Step 3397 | loss:2.0316240787506104 lr:0.00012624912545684453 tokens_per_second_per_gpu:791.4742316468823 +Step 3398 | loss:1.9935338497161865 lr:0.00012621115460392977 tokens_per_second_per_gpu:784.5532361962739 +Step 3399 | loss:2.070836305618286 lr:0.0001261731796927086 tokens_per_second_per_gpu:775.1297997978121 +Step 3400 | loss:2.074091672897339 lr:0.0001261352007290607 tokens_per_second_per_gpu:772.997970188164 +Step 3401 | loss:2.066619873046875 lr:0.00012609721771886638 tokens_per_second_per_gpu:744.8501854660319 +Step 3402 | loss:2.0769975185394287 lr:0.00012605923066800668 tokens_per_second_per_gpu:777.4724832255015 +Step 3403 | loss:2.0175676345825195 lr:0.0001260212395823631 tokens_per_second_per_gpu:773.4385737768633 +Step 3404 | loss:2.082198143005371 lr:0.00012598324446781787 tokens_per_second_per_gpu:755.2218098642743 +Step 3405 | loss:2.035507917404175 lr:0.00012594524533025386 tokens_per_second_per_gpu:760.3813920980652 +Step 3406 | loss:2.0892438888549805 lr:0.00012590724217555448 tokens_per_second_per_gpu:746.4287538366592 +Step 3407 | loss:2.0436549186706543 lr:0.00012586923500960387 tokens_per_second_per_gpu:781.0063883481063 +Step 3408 | loss:2.020585536956787 lr:0.00012583122383828666 tokens_per_second_per_gpu:780.0175815651132 +Step 3409 | loss:2.0015294551849365 lr:0.00012579320866748818 tokens_per_second_per_gpu:785.0200734649065 +Step 3410 | loss:2.0011911392211914 lr:0.00012575518950309436 tokens_per_second_per_gpu:768.381444834917 +Step 3411 | loss:1.9915333986282349 lr:0.0001257171663509918 tokens_per_second_per_gpu:767.3466185278668 +Step 3412 | loss:2.049572229385376 lr:0.00012567913921706766 tokens_per_second_per_gpu:751.8352260065129 +Step 3413 | loss:2.071904182434082 lr:0.0001256411081072097 tokens_per_second_per_gpu:769.0098678953716 +Step 3414 | loss:2.046914577484131 lr:0.00012560307302730635 tokens_per_second_per_gpu:760.7004786611732 +Step 3415 | loss:1.977409839630127 lr:0.00012556503398324664 tokens_per_second_per_gpu:772.5538900325074 +Step 3416 | loss:2.0688905715942383 lr:0.00012552699098092014 tokens_per_second_per_gpu:780.427559058373 +Step 3417 | loss:2.0330862998962402 lr:0.00012548894402621719 tokens_per_second_per_gpu:778.0886132821604 +Step 3418 | loss:2.0531139373779297 lr:0.0001254508931250286 tokens_per_second_per_gpu:756.94270028149 +Step 3419 | loss:2.0561044216156006 lr:0.00012541283828324578 tokens_per_second_per_gpu:791.1519747700611 +Step 3420 | loss:2.056948661804199 lr:0.00012537477950676093 tokens_per_second_per_gpu:769.6600061859082 +Step 3421 | loss:2.0057992935180664 lr:0.00012533671680146666 tokens_per_second_per_gpu:771.9553698781441 +Step 3422 | loss:2.0525522232055664 lr:0.00012529865017325625 tokens_per_second_per_gpu:744.0376955930824 +Step 3423 | loss:2.016921281814575 lr:0.0001252605796280237 tokens_per_second_per_gpu:773.8794323743538 +Step 3424 | loss:2.021777629852295 lr:0.00012522250517166343 tokens_per_second_per_gpu:790.5061058737735 +Step 3425 | loss:2.0353164672851562 lr:0.00012518442681007058 tokens_per_second_per_gpu:791.1519670514779 +Step 3426 | loss:2.078970193862915 lr:0.00012514634454914092 tokens_per_second_per_gpu:786.9901754046198 +Step 3427 | loss:2.067915916442871 lr:0.0001251082583947707 tokens_per_second_per_gpu:748.9359790538131 +Step 3428 | loss:2.013794183731079 lr:0.00012507016835285688 tokens_per_second_per_gpu:761.5551483858377 +Step 3429 | loss:2.06701397895813 lr:0.00012503207442929697 tokens_per_second_per_gpu:696.3209472829843 +Step 3430 | loss:2.0041861534118652 lr:0.00012499397662998917 tokens_per_second_per_gpu:774.625415851861 +Step 3431 | loss:2.088181495666504 lr:0.0001249558749608321 tokens_per_second_per_gpu:773.2246250213775 +Step 3432 | loss:2.0881240367889404 lr:0.00012491776942772525 tokens_per_second_per_gpu:794.8912548609683 +Step 3433 | loss:2.0473833084106445 lr:0.00012487966003656836 tokens_per_second_per_gpu:787.7472008237444 +Step 3434 | loss:2.0730857849121094 lr:0.0001248415467932621 tokens_per_second_per_gpu:746.9597204755044 +Step 3435 | loss:2.058475971221924 lr:0.0001248034297037075 tokens_per_second_per_gpu:771.4824105727876 +Step 3436 | loss:2.0038816928863525 lr:0.00012476530877380634 tokens_per_second_per_gpu:733.5549592599355 +Step 3437 | loss:2.0304760932922363 lr:0.0001247271840094609 tokens_per_second_per_gpu:769.0183971968203 +Step 3438 | loss:2.0910849571228027 lr:0.0001246890554165741 tokens_per_second_per_gpu:769.5286092666482 +Step 3439 | loss:2.0672354698181152 lr:0.00012465092300104945 tokens_per_second_per_gpu:737.4490321390551 +Step 3440 | loss:2.0644314289093018 lr:0.00012461278676879098 tokens_per_second_per_gpu:801.6005411047043 +Step 3441 | loss:2.0410172939300537 lr:0.00012457464672570342 tokens_per_second_per_gpu:780.3146719658114 +Step 3442 | loss:2.086895227432251 lr:0.00012453650287769209 tokens_per_second_per_gpu:735.6744901300918 +Step 3443 | loss:2.012854814529419 lr:0.00012449835523066272 tokens_per_second_per_gpu:797.885768663891 +Step 3444 | loss:2.036200523376465 lr:0.00012446020379052185 tokens_per_second_per_gpu:782.8663334707381 +Step 3445 | loss:2.077758550643921 lr:0.00012442204856317655 tokens_per_second_per_gpu:776.3913581377738 +Step 3446 | loss:2.033108949661255 lr:0.00012438388955453433 tokens_per_second_per_gpu:763.6461733437344 +Step 3447 | loss:2.055757522583008 lr:0.00012434572677050352 tokens_per_second_per_gpu:773.1953065247335 +Step 3448 | loss:2.0789225101470947 lr:0.00012430756021699282 tokens_per_second_per_gpu:776.7921031702466 +Step 3449 | loss:2.0398333072662354 lr:0.0001242693898999116 tokens_per_second_per_gpu:738.3826185776112 +Step 3450 | loss:2.0303401947021484 lr:0.00012423121582516995 tokens_per_second_per_gpu:760.5280795993617 +Step 3451 | loss:2.015568256378174 lr:0.00012419303799867824 tokens_per_second_per_gpu:764.939294062465 +Step 3452 | loss:2.0159826278686523 lr:0.00012415485642634772 tokens_per_second_per_gpu:777.9090337673396 +Step 3453 | loss:2.0156288146972656 lr:0.00012411667111409002 tokens_per_second_per_gpu:762.8020576838388 +Step 3454 | loss:2.041477680206299 lr:0.00012407848206781745 tokens_per_second_per_gpu:792.8558750018765 +Step 3455 | loss:2.061410665512085 lr:0.00012404028929344284 tokens_per_second_per_gpu:789.4659816103052 +Step 3456 | loss:2.0964925289154053 lr:0.0001240020927968797 tokens_per_second_per_gpu:793.9147646289073 +Step 3457 | loss:2.01351261138916 lr:0.00012396389258404194 tokens_per_second_per_gpu:754.1016852910801 +Step 3458 | loss:2.0251572132110596 lr:0.0001239256886608442 tokens_per_second_per_gpu:756.0575462424424 +Step 3459 | loss:2.076768159866333 lr:0.00012388748103320162 tokens_per_second_per_gpu:778.0628585362297 +Step 3460 | loss:2.0350892543792725 lr:0.00012384926970703 tokens_per_second_per_gpu:773.4470090867974 +Step 3461 | loss:2.1045031547546387 lr:0.00012381105468824556 tokens_per_second_per_gpu:783.1373891772554 +Step 3462 | loss:2.0576536655426025 lr:0.00012377283598276524 tokens_per_second_per_gpu:783.6200705928096 +Step 3463 | loss:2.018406629562378 lr:0.0001237346135965065 tokens_per_second_per_gpu:755.9670052384652 +Step 3464 | loss:2.0277411937713623 lr:0.0001236963875353873 tokens_per_second_per_gpu:767.3015831270528 +Step 3465 | loss:2.0572926998138428 lr:0.00012365815780532625 tokens_per_second_per_gpu:784.0645966719819 +Step 3466 | loss:2.0893380641937256 lr:0.00012361992441224258 tokens_per_second_per_gpu:786.3673585000586 +Step 3467 | loss:2.047457695007324 lr:0.00012358168736205589 tokens_per_second_per_gpu:782.1840552018165 +Step 3468 | loss:2.010277271270752 lr:0.0001235434466606866 tokens_per_second_per_gpu:781.623611443972 +Step 3469 | loss:2.038963794708252 lr:0.00012350520231405545 tokens_per_second_per_gpu:744.9640042132385 +Step 3470 | loss:2.097303867340088 lr:0.0001234669543280839 tokens_per_second_per_gpu:773.6912265892937 +Step 3471 | loss:2.099917411804199 lr:0.000123428702708694 tokens_per_second_per_gpu:802.588468216449 +Step 3472 | loss:2.0271644592285156 lr:0.00012339044746180824 tokens_per_second_per_gpu:774.0724001091828 +Step 3473 | loss:2.023052930831909 lr:0.0001233521885933497 tokens_per_second_per_gpu:769.6141398755752 +Step 3474 | loss:2.024718999862671 lr:0.00012331392610924214 tokens_per_second_per_gpu:774.2349327128404 +Step 3475 | loss:2.0574734210968018 lr:0.00012327566001540968 tokens_per_second_per_gpu:749.2133515258553 +Step 3476 | loss:2.0748274326324463 lr:0.00012323739031777718 tokens_per_second_per_gpu:764.1831828729269 +Step 3477 | loss:2.034696578979492 lr:0.00012319911702226996 tokens_per_second_per_gpu:777.7481774285628 +Step 3478 | loss:2.0715017318725586 lr:0.00012316084013481394 tokens_per_second_per_gpu:746.0437827045489 +Step 3479 | loss:2.0533416271209717 lr:0.00012312255966133554 tokens_per_second_per_gpu:734.2533530910968 +Step 3480 | loss:2.0867953300476074 lr:0.00012308427560776185 tokens_per_second_per_gpu:753.7695276987272 +Step 3481 | loss:2.0032706260681152 lr:0.00012304598798002037 tokens_per_second_per_gpu:767.86140154922 +Step 3482 | loss:2.102393865585327 lr:0.00012300769678403922 tokens_per_second_per_gpu:734.2825130403621 +Step 3483 | loss:2.0413150787353516 lr:0.00012296940202574715 tokens_per_second_per_gpu:774.7404691898638 +Step 3484 | loss:2.1091058254241943 lr:0.0001229311037110733 tokens_per_second_per_gpu:775.1192795569596 +Step 3485 | loss:2.1278469562530518 lr:0.00012289280184594746 tokens_per_second_per_gpu:737.8605546473484 +Step 3486 | loss:1.9888794422149658 lr:0.0001228544964363 tokens_per_second_per_gpu:777.834860876621 +Step 3487 | loss:2.059417724609375 lr:0.00012281618748806182 tokens_per_second_per_gpu:763.0214235855465 +Step 3488 | loss:2.035226583480835 lr:0.00012277787500716424 tokens_per_second_per_gpu:800.9192330730508 +Step 3489 | loss:2.0988032817840576 lr:0.0001227395589995393 tokens_per_second_per_gpu:728.5205823197513 +Step 3490 | loss:2.0717499256134033 lr:0.00012270123947111952 tokens_per_second_per_gpu:770.4727363384856 +Step 3491 | loss:1.9929969310760498 lr:0.0001226629164278379 tokens_per_second_per_gpu:776.3258264491695 +Step 3492 | loss:2.0859405994415283 lr:0.00012262458987562813 tokens_per_second_per_gpu:761.5212442380981 +Step 3493 | loss:1.990464687347412 lr:0.00012258625982042434 tokens_per_second_per_gpu:752.0351776485943 +Step 3494 | loss:2.0727806091308594 lr:0.0001225479262681611 tokens_per_second_per_gpu:780.8111823135913 +Step 3495 | loss:2.094094753265381 lr:0.00012250958922477385 tokens_per_second_per_gpu:745.1533908258489 +Step 3496 | loss:2.0641162395477295 lr:0.00012247124869619824 tokens_per_second_per_gpu:778.3562365427746 +Step 3497 | loss:2.08066725730896 lr:0.00012243290468837053 tokens_per_second_per_gpu:767.6640142213279 +Step 3498 | loss:2.045466661453247 lr:0.0001223945572072277 tokens_per_second_per_gpu:769.8231490426384 +Step 3499 | loss:2.084094762802124 lr:0.0001223562062587071 tokens_per_second_per_gpu:795.2243970774443 +Step 3500 | loss:2.06276535987854 lr:0.00012231785184874659 tokens_per_second_per_gpu:786.3495194690466 +Step 3501 | loss:2.0469698905944824 lr:0.00012227949398328468 tokens_per_second_per_gpu:769.0178759909933 +Step 3502 | loss:2.0758824348449707 lr:0.0001222411326682604 tokens_per_second_per_gpu:725.4265537935607 +Step 3503 | loss:2.0488836765289307 lr:0.00012220276790961317 tokens_per_second_per_gpu:784.1491009974011 +Step 3504 | loss:2.0961337089538574 lr:0.00012216439971328322 tokens_per_second_per_gpu:744.7121781804841 +Step 3505 | loss:2.0839173793792725 lr:0.000122126028085211 tokens_per_second_per_gpu:783.109382414548 +Step 3506 | loss:2.0872113704681396 lr:0.00012208765303133772 tokens_per_second_per_gpu:801.2109076094255 +Step 3507 | loss:2.060502529144287 lr:0.00012204927455760501 tokens_per_second_per_gpu:787.3617950523237 +Step 3508 | loss:2.025278329849243 lr:0.00012201089266995506 tokens_per_second_per_gpu:781.0472099506985 +Step 3509 | loss:2.0748538970947266 lr:0.00012197250737433057 tokens_per_second_per_gpu:780.7098927803239 +Step 3510 | loss:2.0051894187927246 lr:0.00012193411867667484 tokens_per_second_per_gpu:780.4736119574394 +Step 3511 | loss:1.95576810836792 lr:0.00012189572658293158 tokens_per_second_per_gpu:795.2434601995412 +Step 3512 | loss:2.047166347503662 lr:0.00012185733109904511 tokens_per_second_per_gpu:772.3373641856208 +Step 3513 | loss:2.1172027587890625 lr:0.00012181893223096024 tokens_per_second_per_gpu:762.1240345602126 +Step 3514 | loss:2.0452473163604736 lr:0.00012178052998462237 tokens_per_second_per_gpu:757.4539688064372 +Step 3515 | loss:2.0094687938690186 lr:0.00012174212436597727 tokens_per_second_per_gpu:757.4582922957909 +Step 3516 | loss:2.0481748580932617 lr:0.00012170371538097143 tokens_per_second_per_gpu:761.1877012008027 +Step 3517 | loss:2.0523321628570557 lr:0.0001216653030355517 tokens_per_second_per_gpu:779.8050820487379 +Step 3518 | loss:2.087498903274536 lr:0.00012162688733566553 tokens_per_second_per_gpu:792.712035302247 +Step 3519 | loss:2.0161406993865967 lr:0.00012158846828726087 tokens_per_second_per_gpu:751.9733919236228 +Step 3520 | loss:2.004302978515625 lr:0.00012155004589628623 tokens_per_second_per_gpu:786.1124930449319 +Step 3521 | loss:2.1044113636016846 lr:0.00012151162016869049 tokens_per_second_per_gpu:770.6812393766409 +Step 3522 | loss:2.0540950298309326 lr:0.00012147319111042328 tokens_per_second_per_gpu:770.4062740007298 +Step 3523 | loss:2.0281765460968018 lr:0.00012143475872743458 tokens_per_second_per_gpu:735.8908338927338 +Step 3524 | loss:2.1335980892181396 lr:0.00012139632302567483 tokens_per_second_per_gpu:772.3593900429345 +Step 3525 | loss:2.0019171237945557 lr:0.00012135788401109523 tokens_per_second_per_gpu:795.3245230185416 +Step 3526 | loss:2.0691561698913574 lr:0.00012131944168964727 tokens_per_second_per_gpu:785.7895818955899 +Step 3527 | loss:2.0084481239318848 lr:0.00012128099606728295 tokens_per_second_per_gpu:777.4542883870021 +Step 3528 | loss:2.073286533355713 lr:0.000121242547149955 tokens_per_second_per_gpu:759.1783346619594 +Step 3529 | loss:2.070305347442627 lr:0.00012120409494361642 tokens_per_second_per_gpu:782.118705082286 +Step 3530 | loss:2.048150062561035 lr:0.00012116563945422084 tokens_per_second_per_gpu:781.7827044768793 +Step 3531 | loss:2.0820889472961426 lr:0.00012112718068772237 tokens_per_second_per_gpu:779.8318051506948 +Step 3532 | loss:2.0097005367279053 lr:0.00012108871865007562 tokens_per_second_per_gpu:786.6615249931441 +Step 3533 | loss:2.089315891265869 lr:0.00012105025334723572 tokens_per_second_per_gpu:771.4691303486638 +Step 3534 | loss:2.04219651222229 lr:0.00012101178478515834 tokens_per_second_per_gpu:792.4564194235928 +Step 3535 | loss:2.0683465003967285 lr:0.00012097331296979954 tokens_per_second_per_gpu:780.3166798651367 +Step 3536 | loss:2.071781635284424 lr:0.00012093483790711604 tokens_per_second_per_gpu:776.047770395905 +Step 3537 | loss:2.065918207168579 lr:0.00012089635960306491 tokens_per_second_per_gpu:755.221738341855 +Step 3538 | loss:2.0388453006744385 lr:0.00012085787806360387 tokens_per_second_per_gpu:767.5469106975419 +Step 3539 | loss:2.0933587551116943 lr:0.00012081939329469101 tokens_per_second_per_gpu:776.7619342429487 +Step 3540 | loss:2.0232744216918945 lr:0.00012078090530228498 tokens_per_second_per_gpu:799.002320462195 +Step 3541 | loss:2.0519416332244873 lr:0.00012074241409234497 tokens_per_second_per_gpu:777.8806260876535 +Step 3542 | loss:2.06455659866333 lr:0.00012070391967083057 tokens_per_second_per_gpu:800.3247972665006 +Step 3543 | loss:2.0604476928710938 lr:0.00012066542204370193 tokens_per_second_per_gpu:760.7299780248725 +Step 3544 | loss:2.0955915451049805 lr:0.00012062692121691972 tokens_per_second_per_gpu:780.9055595894016 +Step 3545 | loss:2.006754159927368 lr:0.000120588417196445 tokens_per_second_per_gpu:771.7645218089953 +Step 3546 | loss:2.046731472015381 lr:0.00012054990998823949 tokens_per_second_per_gpu:765.4151532722071 +Step 3547 | loss:2.054013252258301 lr:0.0001205113995982653 tokens_per_second_per_gpu:774.6449913419636 +Step 3548 | loss:2.053457736968994 lr:0.00012047288603248492 tokens_per_second_per_gpu:763.0147598376788 +Step 3549 | loss:2.0107173919677734 lr:0.00012043436929686161 tokens_per_second_per_gpu:786.3367421463673 +Step 3550 | loss:2.0722551345825195 lr:0.00012039584939735889 tokens_per_second_per_gpu:776.2367433926229 +Step 3551 | loss:2.0823163986206055 lr:0.00012035732633994082 tokens_per_second_per_gpu:790.5196297440383 +Step 3552 | loss:2.047517776489258 lr:0.00012031880013057204 tokens_per_second_per_gpu:790.5911927373639 +Step 3553 | loss:2.0274746417999268 lr:0.00012028027077521758 tokens_per_second_per_gpu:772.8023641488638 +Step 3554 | loss:2.062490940093994 lr:0.00012024173827984296 tokens_per_second_per_gpu:778.5680387955389 +Step 3555 | loss:1.9850177764892578 lr:0.00012020320265041427 tokens_per_second_per_gpu:773.0816888914073 +Step 3556 | loss:2.090477466583252 lr:0.00012016466389289798 tokens_per_second_per_gpu:760.874671521622 +Step 3557 | loss:2.0667967796325684 lr:0.00012012612201326114 tokens_per_second_per_gpu:777.2907695189689 +Step 3558 | loss:2.055777072906494 lr:0.00012008757701747122 tokens_per_second_per_gpu:765.1100416109924 +Step 3559 | loss:2.0903306007385254 lr:0.00012004902891149616 tokens_per_second_per_gpu:780.4062138650448 +Step 3560 | loss:2.055635452270508 lr:0.00012001047770130447 tokens_per_second_per_gpu:793.0769505508244 +Step 3561 | loss:2.035891056060791 lr:0.00011997192339286503 tokens_per_second_per_gpu:796.622889676119 +Step 3562 | loss:2.0569992065429688 lr:0.0001199333659921473 tokens_per_second_per_gpu:773.2634169696647 +Step 3563 | loss:2.000596523284912 lr:0.00011989480550512113 tokens_per_second_per_gpu:789.7150255200917 +Step 3564 | loss:2.0388753414154053 lr:0.00011985624193775691 tokens_per_second_per_gpu:764.7960000576268 +Step 3565 | loss:2.0408120155334473 lr:0.0001198176752960255 tokens_per_second_per_gpu:773.18521430213 +Step 3566 | loss:2.113563299179077 lr:0.00011977910558589817 tokens_per_second_per_gpu:776.5957476414017 +Step 3567 | loss:2.021512508392334 lr:0.00011974053281334679 tokens_per_second_per_gpu:777.7789027303866 +Step 3568 | loss:2.0602200031280518 lr:0.00011970195698434359 tokens_per_second_per_gpu:773.3727188525395 +Step 3569 | loss:2.0834269523620605 lr:0.00011966337810486127 tokens_per_second_per_gpu:764.1241260570018 +Step 3570 | loss:2.1116316318511963 lr:0.00011962479618087315 tokens_per_second_per_gpu:782.3509883459593 +Step 3571 | loss:2.0552303791046143 lr:0.00011958621121835286 tokens_per_second_per_gpu:749.2836930450273 +Step 3572 | loss:2.134263038635254 lr:0.00011954762322327451 tokens_per_second_per_gpu:786.6546414450247 +Step 3573 | loss:2.0480735301971436 lr:0.00011950903220161285 tokens_per_second_per_gpu:757.9564513945412 +Step 3574 | loss:2.0764801502227783 lr:0.00011947043815934287 tokens_per_second_per_gpu:771.5168239685895 +Step 3575 | loss:2.048945188522339 lr:0.00011943184110244017 tokens_per_second_per_gpu:759.3163284606309 +Step 3576 | loss:2.0540411472320557 lr:0.0001193932410368808 tokens_per_second_per_gpu:798.8429740688433 +Step 3577 | loss:2.0866994857788086 lr:0.00011935463796864126 tokens_per_second_per_gpu:764.0692625526552 +Step 3578 | loss:2.0070862770080566 lr:0.00011931603190369843 tokens_per_second_per_gpu:753.2763598610809 +Step 3579 | loss:2.0470292568206787 lr:0.00011927742284802986 tokens_per_second_per_gpu:780.223817584008 +Step 3580 | loss:2.0294148921966553 lr:0.00011923881080761335 tokens_per_second_per_gpu:790.8166073956975 +Step 3581 | loss:2.0607264041900635 lr:0.00011920019578842727 tokens_per_second_per_gpu:784.118563867164 +Step 3582 | loss:2.0471596717834473 lr:0.0001191615777964505 tokens_per_second_per_gpu:768.2422221773362 +Step 3583 | loss:2.003962755203247 lr:0.00011912295683766219 tokens_per_second_per_gpu:773.3766360393145 +Step 3584 | loss:2.0676229000091553 lr:0.00011908433291804217 tokens_per_second_per_gpu:779.2267004136519 +Step 3585 | loss:2.070470094680786 lr:0.00011904570604357061 tokens_per_second_per_gpu:793.8729530620623 +Step 3586 | loss:2.123713493347168 lr:0.00011900707622022813 tokens_per_second_per_gpu:783.6550448456122 +Step 3587 | loss:2.0335707664489746 lr:0.00011896844345399584 tokens_per_second_per_gpu:768.1185659302256 +Step 3588 | loss:2.085763931274414 lr:0.00011892980775085531 tokens_per_second_per_gpu:751.7831226328846 +Step 3589 | loss:2.0418460369110107 lr:0.00011889116911678859 tokens_per_second_per_gpu:749.4169559303657 +Step 3590 | loss:2.1080899238586426 lr:0.0001188525275577781 tokens_per_second_per_gpu:763.1671139348915 +Step 3591 | loss:2.0268754959106445 lr:0.00011881388307980676 tokens_per_second_per_gpu:787.8991197989942 +Step 3592 | loss:2.0661399364471436 lr:0.000118775235688858 tokens_per_second_per_gpu:803.2867402337343 +Step 3593 | loss:1.9995197057724 lr:0.00011873658539091556 tokens_per_second_per_gpu:743.6761609511374 +Step 3594 | loss:2.0608484745025635 lr:0.00011869793219196379 tokens_per_second_per_gpu:768.1167561815054 +Step 3595 | loss:2.0908071994781494 lr:0.0001186592760979874 tokens_per_second_per_gpu:774.1583757094015 +Step 3596 | loss:2.0695440769195557 lr:0.00011862061711497148 tokens_per_second_per_gpu:804.1917769200919 +Step 3597 | loss:2.0389108657836914 lr:0.00011858195524890178 tokens_per_second_per_gpu:791.5074811466072 +Step 3598 | loss:1.9874885082244873 lr:0.0001185432905057643 tokens_per_second_per_gpu:731.8759015836217 +Step 3599 | loss:2.066244602203369 lr:0.00011850462289154552 tokens_per_second_per_gpu:788.7827048281997 +Step 3600 | loss:2.04111647605896 lr:0.00011846595241223247 tokens_per_second_per_gpu:793.2836107276548 +Step 3601 | loss:1.9996224641799927 lr:0.00011842727907381248 tokens_per_second_per_gpu:795.7487636592851 +Step 3602 | loss:2.058926582336426 lr:0.0001183886028822734 tokens_per_second_per_gpu:798.7651580467684 +Step 3603 | loss:2.0083789825439453 lr:0.00011834992384360357 tokens_per_second_per_gpu:786.4225075438761 +Step 3604 | loss:2.059185028076172 lr:0.00011831124196379168 tokens_per_second_per_gpu:775.341290098335 +Step 3605 | loss:1.995887279510498 lr:0.00011827255724882688 tokens_per_second_per_gpu:761.9088212070984 +Step 3606 | loss:2.060431957244873 lr:0.0001182338697046988 tokens_per_second_per_gpu:789.3297320856998 +Step 3607 | loss:2.0303797721862793 lr:0.00011819517933739747 tokens_per_second_per_gpu:772.3580781075304 +Step 3608 | loss:2.0361485481262207 lr:0.00011815648615291338 tokens_per_second_per_gpu:768.006867175006 +Step 3609 | loss:2.0184335708618164 lr:0.00011811779015723743 tokens_per_second_per_gpu:755.0240909993481 +Step 3610 | loss:2.017878532409668 lr:0.00011807909135636094 tokens_per_second_per_gpu:734.9892510396118 +Step 3611 | loss:2.0591745376586914 lr:0.00011804038975627576 tokens_per_second_per_gpu:771.0836620920778 +Step 3612 | loss:2.056220769882202 lr:0.00011800168536297407 tokens_per_second_per_gpu:772.2240622179605 +Step 3613 | loss:2.06166410446167 lr:0.00011796297818244854 tokens_per_second_per_gpu:778.0341045744699 +Step 3614 | loss:2.054213047027588 lr:0.00011792426822069223 tokens_per_second_per_gpu:799.2100203621612 +Step 3615 | loss:2.0520999431610107 lr:0.00011788555548369864 tokens_per_second_per_gpu:791.6785458947152 +Step 3616 | loss:2.0573761463165283 lr:0.00011784683997746178 tokens_per_second_per_gpu:768.5301558058507 +Step 3617 | loss:2.0954229831695557 lr:0.00011780812170797593 tokens_per_second_per_gpu:784.2823894915199 +Step 3618 | loss:2.0763301849365234 lr:0.00011776940068123594 tokens_per_second_per_gpu:777.4407881750776 +Step 3619 | loss:2.0167737007141113 lr:0.00011773067690323708 tokens_per_second_per_gpu:771.3999016673387 +Step 3620 | loss:1.994287133216858 lr:0.00011769195037997487 tokens_per_second_per_gpu:785.9598566400778 +Step 3621 | loss:2.0026774406433105 lr:0.00011765322111744554 tokens_per_second_per_gpu:777.4450613748099 +Step 3622 | loss:2.029576063156128 lr:0.0001176144891216455 tokens_per_second_per_gpu:783.9030104766838 +Step 3623 | loss:2.043342113494873 lr:0.00011757575439857167 tokens_per_second_per_gpu:776.1847143886815 +Step 3624 | loss:2.096649646759033 lr:0.00011753701695422146 tokens_per_second_per_gpu:781.2978753684691 +Step 3625 | loss:2.06476092338562 lr:0.00011749827679459258 tokens_per_second_per_gpu:794.7273897780635 +Step 3626 | loss:2.038116455078125 lr:0.00011745953392568321 tokens_per_second_per_gpu:750.2111859452972 +Step 3627 | loss:2.1166932582855225 lr:0.00011742078835349202 tokens_per_second_per_gpu:779.6707861791266 +Step 3628 | loss:2.1100893020629883 lr:0.00011738204008401798 tokens_per_second_per_gpu:756.4513542276942 +Step 3629 | loss:2.0766592025756836 lr:0.00011734328912326056 tokens_per_second_per_gpu:753.4289064597594 +Step 3630 | loss:2.008406639099121 lr:0.00011730453547721964 tokens_per_second_per_gpu:727.0639790596651 +Step 3631 | loss:2.036257266998291 lr:0.00011726577915189545 tokens_per_second_per_gpu:749.7369679149629 +Step 3632 | loss:2.0939087867736816 lr:0.00011722702015328869 tokens_per_second_per_gpu:779.4123744481174 +Step 3633 | loss:2.0165319442749023 lr:0.00011718825848740049 tokens_per_second_per_gpu:784.9907321877909 +Step 3634 | loss:2.062840223312378 lr:0.00011714949416023236 tokens_per_second_per_gpu:759.5687970574206 +Step 3635 | loss:2.076368808746338 lr:0.00011711072717778622 tokens_per_second_per_gpu:784.1173624657738 +Step 3636 | loss:2.034731388092041 lr:0.00011707195754606443 tokens_per_second_per_gpu:773.8798961446373 +Step 3637 | loss:2.005582094192505 lr:0.0001170331852710697 tokens_per_second_per_gpu:758.5077654330597 +Step 3638 | loss:2.029675245285034 lr:0.00011699441035880526 tokens_per_second_per_gpu:760.1273772267967 +Step 3639 | loss:1.9946331977844238 lr:0.0001169556328152746 tokens_per_second_per_gpu:791.0060161196557 +Step 3640 | loss:2.0599312782287598 lr:0.00011691685264648176 tokens_per_second_per_gpu:767.7543136090374 +Step 3641 | loss:2.076615810394287 lr:0.00011687806985843107 tokens_per_second_per_gpu:796.344368710944 +Step 3642 | loss:1.9954723119735718 lr:0.00011683928445712735 tokens_per_second_per_gpu:786.7609894260778 +Step 3643 | loss:2.0138580799102783 lr:0.00011680049644857582 tokens_per_second_per_gpu:796.1493939365772 +Step 3644 | loss:2.0630788803100586 lr:0.00011676170583878201 tokens_per_second_per_gpu:762.2757116188774 +Step 3645 | loss:2.083022356033325 lr:0.00011672291263375198 tokens_per_second_per_gpu:747.1927682087714 +Step 3646 | loss:2.058211326599121 lr:0.0001166841168394921 tokens_per_second_per_gpu:759.6177419854389 +Step 3647 | loss:2.0804662704467773 lr:0.00011664531846200914 tokens_per_second_per_gpu:783.8429831735951 +Step 3648 | loss:2.054050922393799 lr:0.0001166065175073104 tokens_per_second_per_gpu:777.7111881963524 +Step 3649 | loss:2.108158826828003 lr:0.00011656771398140343 tokens_per_second_per_gpu:752.1081530126997 +Step 3650 | loss:2.099269390106201 lr:0.00011652890789029615 tokens_per_second_per_gpu:769.7628163749808 +Step 3651 | loss:2.043429374694824 lr:0.00011649009923999707 tokens_per_second_per_gpu:781.5859469705132 +Step 3652 | loss:2.090812921524048 lr:0.00011645128803651495 tokens_per_second_per_gpu:773.221381828441 +Step 3653 | loss:2.0381522178649902 lr:0.00011641247428585893 tokens_per_second_per_gpu:785.1477595898709 +Step 3654 | loss:2.0636560916900635 lr:0.00011637365799403868 tokens_per_second_per_gpu:776.4015973342357 +Step 3655 | loss:2.0797712802886963 lr:0.00011633483916706409 tokens_per_second_per_gpu:783.9796532604265 +Step 3656 | loss:2.0445125102996826 lr:0.00011629601781094556 tokens_per_second_per_gpu:762.7240841086394 +Step 3657 | loss:2.0004429817199707 lr:0.0001162571939316939 tokens_per_second_per_gpu:771.4243281012001 +Step 3658 | loss:2.0183568000793457 lr:0.00011621836753532019 tokens_per_second_per_gpu:766.2722059110584 +Step 3659 | loss:2.0596461296081543 lr:0.00011617953862783598 tokens_per_second_per_gpu:751.1103878048631 +Step 3660 | loss:2.0835604667663574 lr:0.00011614070721525325 tokens_per_second_per_gpu:773.7951760696034 +Step 3661 | loss:2.035073757171631 lr:0.00011610187330358427 tokens_per_second_per_gpu:769.4308205290484 +Step 3662 | loss:2.07765793800354 lr:0.00011606303689884173 tokens_per_second_per_gpu:773.3788924634786 +Step 3663 | loss:2.0066335201263428 lr:0.00011602419800703874 tokens_per_second_per_gpu:788.6487886885178 +Step 3664 | loss:2.0829579830169678 lr:0.00011598535663418884 tokens_per_second_per_gpu:725.2922553995429 +Step 3665 | loss:2.019923210144043 lr:0.00011594651278630577 tokens_per_second_per_gpu:782.328453817319 +Step 3666 | loss:2.062558174133301 lr:0.00011590766646940385 tokens_per_second_per_gpu:796.1081192704903 +Step 3667 | loss:2.106627941131592 lr:0.0001158688176894977 tokens_per_second_per_gpu:748.1508497276801 +Step 3668 | loss:2.066340208053589 lr:0.00011582996645260232 tokens_per_second_per_gpu:761.1847620618737 +Step 3669 | loss:2.041461229324341 lr:0.00011579111276473306 tokens_per_second_per_gpu:785.3978286350114 +Step 3670 | loss:2.061803102493286 lr:0.00011575225663190576 tokens_per_second_per_gpu:770.5089980965773 +Step 3671 | loss:2.0191142559051514 lr:0.00011571339806013646 tokens_per_second_per_gpu:769.9314713460789 +Step 3672 | loss:2.0025906562805176 lr:0.0001156745370554418 tokens_per_second_per_gpu:777.1724289988513 +Step 3673 | loss:2.050335168838501 lr:0.00011563567362383861 tokens_per_second_per_gpu:797.1352536007605 +Step 3674 | loss:2.022052526473999 lr:0.00011559680777134414 tokens_per_second_per_gpu:770.1499210961512 +Step 3675 | loss:2.0526609420776367 lr:0.00011555793950397611 tokens_per_second_per_gpu:761.4762084369786 +Step 3676 | loss:1.987147331237793 lr:0.00011551906882775251 tokens_per_second_per_gpu:784.0841857956076 +Step 3677 | loss:2.0555949211120605 lr:0.00011548019574869168 tokens_per_second_per_gpu:773.6962823601051 +Step 3678 | loss:2.057321548461914 lr:0.00011544132027281251 tokens_per_second_per_gpu:769.0827107852723 +Step 3679 | loss:2.0435078144073486 lr:0.00011540244240613404 tokens_per_second_per_gpu:764.5422606584033 +Step 3680 | loss:2.026271343231201 lr:0.00011536356215467581 tokens_per_second_per_gpu:783.039305722599 +Step 3681 | loss:2.099376678466797 lr:0.00011532467952445774 tokens_per_second_per_gpu:775.538154353461 +Step 3682 | loss:2.0125584602355957 lr:0.00011528579452149999 tokens_per_second_per_gpu:788.7439360958588 +Step 3683 | loss:2.070653200149536 lr:0.00011524690715182325 tokens_per_second_per_gpu:795.9302671708101 +Step 3684 | loss:2.0338895320892334 lr:0.00011520801742144847 tokens_per_second_per_gpu:772.5848523978033 +Step 3685 | loss:2.0295372009277344 lr:0.00011516912533639699 tokens_per_second_per_gpu:788.6394881652441 +Step 3686 | loss:2.0250377655029297 lr:0.00011513023090269053 tokens_per_second_per_gpu:786.4945076483809 +Step 3687 | loss:2.0722134113311768 lr:0.00011509133412635118 tokens_per_second_per_gpu:720.8395569755446 +Step 3688 | loss:2.03713321685791 lr:0.00011505243501340135 tokens_per_second_per_gpu:755.1405316003019 +Step 3689 | loss:2.0711607933044434 lr:0.00011501353356986383 tokens_per_second_per_gpu:768.3129710723729 +Step 3690 | loss:2.0609304904937744 lr:0.00011497462980176184 tokens_per_second_per_gpu:751.8798389067653 +Step 3691 | loss:2.1142077445983887 lr:0.00011493572371511888 tokens_per_second_per_gpu:786.426037784685 +Step 3692 | loss:2.058072328567505 lr:0.00011489681531595875 tokens_per_second_per_gpu:797.4458449936608 +Step 3693 | loss:2.0293192863464355 lr:0.00011485790461030577 tokens_per_second_per_gpu:758.694487676892 +Step 3694 | loss:2.0785531997680664 lr:0.00011481899160418454 tokens_per_second_per_gpu:742.5848187546139 +Step 3695 | loss:2.0321590900421143 lr:0.00011478007630361995 tokens_per_second_per_gpu:798.3533940937015 +Step 3696 | loss:2.0492329597473145 lr:0.00011474115871463736 tokens_per_second_per_gpu:791.8770965240211 +Step 3697 | loss:2.0928711891174316 lr:0.00011470223884326239 tokens_per_second_per_gpu:772.7827129470082 +Step 3698 | loss:2.1248412132263184 lr:0.00011466331669552108 tokens_per_second_per_gpu:763.4460114848071 +Step 3699 | loss:2.0129661560058594 lr:0.00011462439227743977 tokens_per_second_per_gpu:791.7341502910834 +Step 3700 | loss:2.025237798690796 lr:0.00011458546559504521 tokens_per_second_per_gpu:778.3612422782232 +Step 3701 | loss:2.053180456161499 lr:0.00011454653665436443 tokens_per_second_per_gpu:777.510653172451 +Step 3702 | loss:2.028754711151123 lr:0.00011450760546142491 tokens_per_second_per_gpu:773.1566473864775 +Step 3703 | loss:2.0355448722839355 lr:0.00011446867202225438 tokens_per_second_per_gpu:735.937962416281 +Step 3704 | loss:2.0388221740722656 lr:0.00011442973634288087 tokens_per_second_per_gpu:772.8383672532939 +Step 3705 | loss:2.043360710144043 lr:0.000114390798429333 tokens_per_second_per_gpu:781.0461082153279 +Step 3706 | loss:2.0562868118286133 lr:0.00011435185828763946 tokens_per_second_per_gpu:766.2243329753787 +Step 3707 | loss:2.0350499153137207 lr:0.00011431291592382943 tokens_per_second_per_gpu:796.7433287545015 +Step 3708 | loss:2.0969839096069336 lr:0.00011427397134393245 tokens_per_second_per_gpu:777.1399369507998 +Step 3709 | loss:2.1003832817077637 lr:0.0001142350245539783 tokens_per_second_per_gpu:770.1721145647349 +Step 3710 | loss:2.066986322402954 lr:0.00011419607555999716 tokens_per_second_per_gpu:758.0718806257148 +Step 3711 | loss:2.0682296752929688 lr:0.00011415712436801962 tokens_per_second_per_gpu:780.8857149938237 +Step 3712 | loss:2.039581775665283 lr:0.00011411817098407646 tokens_per_second_per_gpu:791.7669625162046 +Step 3713 | loss:2.074895143508911 lr:0.00011407921541419895 tokens_per_second_per_gpu:759.1493578176281 +Step 3714 | loss:2.0897297859191895 lr:0.0001140402576644186 tokens_per_second_per_gpu:750.6159816099959 +Step 3715 | loss:2.0547797679901123 lr:0.00011400129774076728 tokens_per_second_per_gpu:792.0593375685286 +Step 3716 | loss:2.0703630447387695 lr:0.0001139623356492772 tokens_per_second_per_gpu:765.1995048773717 +Step 3717 | loss:2.0769455432891846 lr:0.00011392337139598093 tokens_per_second_per_gpu:749.8655995115367 +Step 3718 | loss:2.0311503410339355 lr:0.00011388440498691138 tokens_per_second_per_gpu:778.2092715439974 +Step 3719 | loss:2.036708354949951 lr:0.0001138454364281017 tokens_per_second_per_gpu:774.4579295089741 +Step 3720 | loss:2.043879508972168 lr:0.00011380646572558548 tokens_per_second_per_gpu:758.5680396429534 +Step 3721 | loss:2.0703608989715576 lr:0.00011376749288539664 tokens_per_second_per_gpu:779.4685672072993 +Step 3722 | loss:2.069517135620117 lr:0.00011372851791356934 tokens_per_second_per_gpu:759.3041362466204 +Step 3723 | loss:1.983980417251587 lr:0.00011368954081613812 tokens_per_second_per_gpu:784.492265963724 +Step 3724 | loss:1.9974398612976074 lr:0.00011365056159913789 tokens_per_second_per_gpu:776.0756694994925 +Step 3725 | loss:2.038466453552246 lr:0.00011361158026860383 tokens_per_second_per_gpu:780.0023790225912 +Step 3726 | loss:2.0206267833709717 lr:0.00011357259683057147 tokens_per_second_per_gpu:773.1108895530542 +Step 3727 | loss:2.013805389404297 lr:0.00011353361129107669 tokens_per_second_per_gpu:781.6779833953924 +Step 3728 | loss:1.9940739870071411 lr:0.00011349462365615562 tokens_per_second_per_gpu:772.4294491237168 +Step 3729 | loss:1.9989888668060303 lr:0.00011345563393184483 tokens_per_second_per_gpu:791.5045113707472 +Step 3730 | loss:2.0742530822753906 lr:0.00011341664212418111 tokens_per_second_per_gpu:763.9818654524784 +Step 3731 | loss:2.0689353942871094 lr:0.00011337764823920161 tokens_per_second_per_gpu:775.2683906610613 +Step 3732 | loss:1.9926570653915405 lr:0.00011333865228294382 tokens_per_second_per_gpu:775.7363024645856 +Step 3733 | loss:2.042902708053589 lr:0.0001132996542614455 tokens_per_second_per_gpu:773.5312034260972 +Step 3734 | loss:2.0569121837615967 lr:0.00011326065418074478 tokens_per_second_per_gpu:790.1370518199215 +Step 3735 | loss:1.9879939556121826 lr:0.00011322165204688016 tokens_per_second_per_gpu:764.324621217866 +Step 3736 | loss:1.953776240348816 lr:0.00011318264786589028 tokens_per_second_per_gpu:779.2821622340513 +Step 3737 | loss:2.0564441680908203 lr:0.00011314364164381426 tokens_per_second_per_gpu:768.3454303790686 +Step 3738 | loss:2.0663599967956543 lr:0.00011310463338669146 tokens_per_second_per_gpu:761.4519218417986 +Step 3739 | loss:2.016252279281616 lr:0.00011306562310056163 tokens_per_second_per_gpu:762.7351669669019 +Step 3740 | loss:1.9855766296386719 lr:0.00011302661079146473 tokens_per_second_per_gpu:763.002692335677 +Step 3741 | loss:2.0795207023620605 lr:0.0001129875964654411 tokens_per_second_per_gpu:789.8490664128868 +Step 3742 | loss:2.0126821994781494 lr:0.00011294858012853143 tokens_per_second_per_gpu:761.3818238850544 +Step 3743 | loss:2.0382769107818604 lr:0.00011290956178677656 tokens_per_second_per_gpu:757.0901338365504 +Step 3744 | loss:2.077385187149048 lr:0.00011287054144621783 tokens_per_second_per_gpu:798.505368653076 +Step 3745 | loss:2.059870719909668 lr:0.0001128315191128968 tokens_per_second_per_gpu:755.944990406853 +Step 3746 | loss:2.044543981552124 lr:0.00011279249479285534 tokens_per_second_per_gpu:757.4886449592797 +Step 3747 | loss:2.064202070236206 lr:0.00011275346849213561 tokens_per_second_per_gpu:782.3893209136425 +Step 3748 | loss:2.037487268447876 lr:0.00011271444021678015 tokens_per_second_per_gpu:770.8334879588033 +Step 3749 | loss:2.019670248031616 lr:0.00011267540997283173 tokens_per_second_per_gpu:754.2071032594118 +Step 3750 | loss:2.0951263904571533 lr:0.00011263637776633342 tokens_per_second_per_gpu:771.8348962991283 +Step 3751 | loss:2.09146785736084 lr:0.0001125973436033287 tokens_per_second_per_gpu:777.0934446473118 +Step 3752 | loss:2.0775136947631836 lr:0.00011255830748986123 tokens_per_second_per_gpu:766.4668060273113 +Step 3753 | loss:2.0263216495513916 lr:0.00011251926943197499 tokens_per_second_per_gpu:763.1483855358518 +Step 3754 | loss:2.056452751159668 lr:0.00011248022943571439 tokens_per_second_per_gpu:784.6996230913318 +Step 3755 | loss:2.0448639392852783 lr:0.00011244118750712394 tokens_per_second_per_gpu:734.6920574702939 +Step 3756 | loss:2.1265203952789307 lr:0.00011240214365224861 tokens_per_second_per_gpu:780.3524772643566 +Step 3757 | loss:2.070704460144043 lr:0.00011236309787713361 tokens_per_second_per_gpu:766.611463336031 +Step 3758 | loss:1.9986765384674072 lr:0.00011232405018782441 tokens_per_second_per_gpu:781.5835530393957 +Step 3759 | loss:2.0515174865722656 lr:0.00011228500059036688 tokens_per_second_per_gpu:742.3913127534788 +Step 3760 | loss:2.0246243476867676 lr:0.00011224594909080704 tokens_per_second_per_gpu:750.6198280689626 +Step 3761 | loss:2.0916335582733154 lr:0.00011220689569519132 tokens_per_second_per_gpu:788.6752687793312 +Step 3762 | loss:2.003709077835083 lr:0.00011216784040956643 tokens_per_second_per_gpu:780.493010456625 +Step 3763 | loss:2.023940086364746 lr:0.00011212878323997928 tokens_per_second_per_gpu:752.1735882065933 +Step 3764 | loss:2.0601296424865723 lr:0.00011208972419247723 tokens_per_second_per_gpu:773.2263738940117 +Step 3765 | loss:2.04652738571167 lr:0.00011205066327310776 tokens_per_second_per_gpu:797.4562862952868 +Step 3766 | loss:2.0766701698303223 lr:0.00011201160048791881 tokens_per_second_per_gpu:755.0686258622715 +Step 3767 | loss:1.9762823581695557 lr:0.00011197253584295844 tokens_per_second_per_gpu:788.8108581459232 +Step 3768 | loss:1.993910789489746 lr:0.00011193346934427512 tokens_per_second_per_gpu:773.7792341373283 +Step 3769 | loss:2.063960552215576 lr:0.00011189440099791755 tokens_per_second_per_gpu:765.7957949775458 +Step 3770 | loss:2.0409128665924072 lr:0.00011185533080993474 tokens_per_second_per_gpu:792.1277867750463 +Step 3771 | loss:1.9954005479812622 lr:0.00011181625878637596 tokens_per_second_per_gpu:777.3622516976576 +Step 3772 | loss:1.985953450202942 lr:0.00011177718493329082 tokens_per_second_per_gpu:785.4941702739931 +Step 3773 | loss:2.0221593379974365 lr:0.00011173810925672912 tokens_per_second_per_gpu:779.1557901695951 +Step 3774 | loss:2.0302820205688477 lr:0.00011169903176274104 tokens_per_second_per_gpu:747.0095429713502 +Step 3775 | loss:2.044888496398926 lr:0.00011165995245737699 tokens_per_second_per_gpu:756.9964423306811 +Step 3776 | loss:2.041376829147339 lr:0.00011162087134668767 tokens_per_second_per_gpu:770.1919195076849 +Step 3777 | loss:2.081536293029785 lr:0.00011158178843672402 tokens_per_second_per_gpu:744.0667140424674 +Step 3778 | loss:2.0791547298431396 lr:0.00011154270373353737 tokens_per_second_per_gpu:763.9845977025138 +Step 3779 | loss:2.042027473449707 lr:0.0001115036172431792 tokens_per_second_per_gpu:754.7059479533535 +Step 3780 | loss:2.0709660053253174 lr:0.00011146452897170132 tokens_per_second_per_gpu:786.1619465540549 +Step 3781 | loss:2.056143045425415 lr:0.00011142543892515582 tokens_per_second_per_gpu:755.306839053735 +Step 3782 | loss:1.9869718551635742 lr:0.00011138634710959508 tokens_per_second_per_gpu:767.6890526320415 +Step 3783 | loss:2.1066501140594482 lr:0.00011134725353107176 tokens_per_second_per_gpu:732.9346441532679 +Step 3784 | loss:1.9324666261672974 lr:0.00011130815819563869 tokens_per_second_per_gpu:770.2049401565089 +Step 3785 | loss:2.017465353012085 lr:0.00011126906110934912 tokens_per_second_per_gpu:793.9443523238797 +Step 3786 | loss:2.0540101528167725 lr:0.00011122996227825648 tokens_per_second_per_gpu:752.4720751006976 +Step 3787 | loss:2.016610860824585 lr:0.00011119086170841449 tokens_per_second_per_gpu:768.6348241303189 +Step 3788 | loss:2.017651319503784 lr:0.00011115175940587712 tokens_per_second_per_gpu:778.469557159125 +Step 3789 | loss:2.0555524826049805 lr:0.00011111265537669866 tokens_per_second_per_gpu:790.4619737979737 +Step 3790 | loss:2.05646014213562 lr:0.00011107354962693366 tokens_per_second_per_gpu:768.3775604508331 +Step 3791 | loss:2.0886483192443848 lr:0.00011103444216263685 tokens_per_second_per_gpu:776.357179631688 +Step 3792 | loss:2.0443367958068848 lr:0.00011099533298986331 tokens_per_second_per_gpu:791.7880121221646 +Step 3793 | loss:2.078854560852051 lr:0.0001109562221146684 tokens_per_second_per_gpu:743.9531648765231 +Step 3794 | loss:2.0401127338409424 lr:0.00011091710954310765 tokens_per_second_per_gpu:779.44191256451 +Step 3795 | loss:2.0383641719818115 lr:0.00011087799528123695 tokens_per_second_per_gpu:777.1657545591667 +Step 3796 | loss:2.071535110473633 lr:0.00011083887933511241 tokens_per_second_per_gpu:787.0215443048103 +Step 3797 | loss:2.0692360401153564 lr:0.00011079976171079036 tokens_per_second_per_gpu:783.6844994463504 +Step 3798 | loss:2.0759663581848145 lr:0.00011076064241432747 tokens_per_second_per_gpu:745.9881062257863 +Step 3799 | loss:2.051537036895752 lr:0.00011072152145178063 tokens_per_second_per_gpu:786.6989821597499 +Step 3800 | loss:2.0261521339416504 lr:0.00011068239882920699 tokens_per_second_per_gpu:766.4351640811865 +Step 3801 | loss:2.096296787261963 lr:0.00011064327455266392 tokens_per_second_per_gpu:773.1961216733292 +Step 3802 | loss:1.9986042976379395 lr:0.00011060414862820913 tokens_per_second_per_gpu:785.4445071030067 +Step 3803 | loss:2.0387279987335205 lr:0.0001105650210619005 tokens_per_second_per_gpu:755.3676219769941 +Step 3804 | loss:2.0220227241516113 lr:0.00011052589185979621 tokens_per_second_per_gpu:764.2437264304735 +Step 3805 | loss:2.048536539077759 lr:0.00011048676102795472 tokens_per_second_per_gpu:792.2356695323929 +Step 3806 | loss:2.0303335189819336 lr:0.00011044762857243464 tokens_per_second_per_gpu:756.8304211660123 +Step 3807 | loss:2.008455514907837 lr:0.00011040849449929494 tokens_per_second_per_gpu:764.4077789033712 +Step 3808 | loss:2.021214246749878 lr:0.00011036935881459478 tokens_per_second_per_gpu:760.0161167992167 +Step 3809 | loss:2.0647687911987305 lr:0.0001103302215243936 tokens_per_second_per_gpu:788.1467575111801 +Step 3810 | loss:2.1233184337615967 lr:0.00011029108263475112 tokens_per_second_per_gpu:732.471355937418 +Step 3811 | loss:2.0589723587036133 lr:0.00011025194215172718 tokens_per_second_per_gpu:754.5826615241724 +Step 3812 | loss:2.068692684173584 lr:0.000110212800081382 tokens_per_second_per_gpu:789.783334041046 +Step 3813 | loss:2.0340099334716797 lr:0.00011017365642977599 tokens_per_second_per_gpu:794.2365656337587 +Step 3814 | loss:2.032745838165283 lr:0.00011013451120296982 tokens_per_second_per_gpu:778.6473253886514 +Step 3815 | loss:2.0730066299438477 lr:0.00011009536440702437 tokens_per_second_per_gpu:776.0997325237172 +Step 3816 | loss:2.025526523590088 lr:0.00011005621604800078 tokens_per_second_per_gpu:741.8908540606795 +Step 3817 | loss:2.012328624725342 lr:0.0001100170661319605 tokens_per_second_per_gpu:754.270887836779 +Step 3818 | loss:1.995675802230835 lr:0.00010997791466496511 tokens_per_second_per_gpu:800.4922112363012 +Step 3819 | loss:2.1283175945281982 lr:0.00010993876165307648 tokens_per_second_per_gpu:755.1649421380881 +Step 3820 | loss:2.0897216796875 lr:0.00010989960710235679 tokens_per_second_per_gpu:771.8739031601173 +Step 3821 | loss:2.0348243713378906 lr:0.00010986045101886828 tokens_per_second_per_gpu:785.7687427405139 +Step 3822 | loss:2.037092685699463 lr:0.0001098212934086736 tokens_per_second_per_gpu:778.388576889994 +Step 3823 | loss:2.0204169750213623 lr:0.00010978213427783557 tokens_per_second_per_gpu:754.8965732613019 +Step 3824 | loss:2.048328161239624 lr:0.00010974297363241724 tokens_per_second_per_gpu:793.6605894749284 +Step 3825 | loss:2.0425591468811035 lr:0.0001097038114784819 tokens_per_second_per_gpu:747.5980490046551 +Step 3826 | loss:2.0492289066314697 lr:0.00010966464782209311 tokens_per_second_per_gpu:756.4127455585648 +Step 3827 | loss:2.035705089569092 lr:0.00010962548266931456 tokens_per_second_per_gpu:747.0068170979093 +Step 3828 | loss:2.015496253967285 lr:0.00010958631602621028 tokens_per_second_per_gpu:792.3695536865333 +Step 3829 | loss:2.080749988555908 lr:0.00010954714789884452 tokens_per_second_per_gpu:764.4496661117082 +Step 3830 | loss:2.085075855255127 lr:0.0001095079782932817 tokens_per_second_per_gpu:800.0284850631725 +Step 3831 | loss:2.0907177925109863 lr:0.00010946880721558648 tokens_per_second_per_gpu:760.7483918276138 +Step 3832 | loss:2.070352554321289 lr:0.00010942963467182379 tokens_per_second_per_gpu:784.4979796146978 +Step 3833 | loss:2.0584981441497803 lr:0.00010939046066805877 tokens_per_second_per_gpu:787.8135959594574 +Step 3834 | loss:2.038163661956787 lr:0.00010935128521035677 tokens_per_second_per_gpu:792.078679217734 +Step 3835 | loss:1.9968786239624023 lr:0.00010931210830478338 tokens_per_second_per_gpu:791.1814292495158 +Step 3836 | loss:2.0434067249298096 lr:0.00010927292995740444 tokens_per_second_per_gpu:775.9317115363726 +Step 3837 | loss:2.0494842529296875 lr:0.00010923375017428592 tokens_per_second_per_gpu:789.5290173577226 +Step 3838 | loss:2.0612330436706543 lr:0.00010919456896149411 tokens_per_second_per_gpu:789.5413941439108 +Step 3839 | loss:2.078580379486084 lr:0.0001091553863250955 tokens_per_second_per_gpu:795.3910503046703 +Step 3840 | loss:2.101384401321411 lr:0.00010911620227115678 tokens_per_second_per_gpu:748.6370882940982 +Step 3841 | loss:2.0408623218536377 lr:0.00010907701680574486 tokens_per_second_per_gpu:793.3453240275444 +Step 3842 | loss:2.049802303314209 lr:0.00010903782993492689 tokens_per_second_per_gpu:752.9030753957973 +Step 3843 | loss:2.1074390411376953 lr:0.00010899864166477019 tokens_per_second_per_gpu:774.1633746273557 +Step 3844 | loss:2.064236879348755 lr:0.00010895945200134235 tokens_per_second_per_gpu:789.9250395643082 +Step 3845 | loss:2.0848166942596436 lr:0.00010892026095071115 tokens_per_second_per_gpu:804.7427568129515 +Step 3846 | loss:2.0281646251678467 lr:0.00010888106851894459 tokens_per_second_per_gpu:776.1239919645277 +Step 3847 | loss:2.0338656902313232 lr:0.00010884187471211094 tokens_per_second_per_gpu:766.1319668486375 +Step 3848 | loss:2.0347166061401367 lr:0.00010880267953627852 tokens_per_second_per_gpu:798.6020782874729 +Step 3849 | loss:2.0895471572875977 lr:0.00010876348299751604 tokens_per_second_per_gpu:764.8065699537954 +Step 3850 | loss:2.024423837661743 lr:0.00010872428510189237 tokens_per_second_per_gpu:791.0096738427827 +Step 3851 | loss:2.0467257499694824 lr:0.0001086850858554765 tokens_per_second_per_gpu:773.0723155744824 +Step 3852 | loss:2.069443702697754 lr:0.00010864588526433772 tokens_per_second_per_gpu:743.8971362063229 +Step 3853 | loss:2.0501346588134766 lr:0.00010860668333454557 tokens_per_second_per_gpu:800.4189323337091 +Step 3854 | loss:2.070496082305908 lr:0.00010856748007216966 tokens_per_second_per_gpu:784.2842480614274 +Step 3855 | loss:1.9939554929733276 lr:0.00010852827548327991 tokens_per_second_per_gpu:779.4512925672237 +Step 3856 | loss:2.015012264251709 lr:0.00010848906957394643 tokens_per_second_per_gpu:755.3813789734769 +Step 3857 | loss:2.006706953048706 lr:0.00010844986235023948 tokens_per_second_per_gpu:751.192527323195 +Step 3858 | loss:2.03279972076416 lr:0.00010841065381822959 tokens_per_second_per_gpu:775.6516345271954 +Step 3859 | loss:2.0779807567596436 lr:0.00010837144398398747 tokens_per_second_per_gpu:792.7409924077454 +Step 3860 | loss:2.024470806121826 lr:0.00010833223285358405 tokens_per_second_per_gpu:719.7153021220821 +Step 3861 | loss:2.07346510887146 lr:0.00010829302043309037 tokens_per_second_per_gpu:776.4847123170624 +Step 3862 | loss:2.073198080062866 lr:0.00010825380672857782 tokens_per_second_per_gpu:763.2496830553158 +Step 3863 | loss:2.124361991882324 lr:0.00010821459174611785 tokens_per_second_per_gpu:766.6932015533652 +Step 3864 | loss:1.9957001209259033 lr:0.0001081753754917822 tokens_per_second_per_gpu:769.8966969974863 +Step 3865 | loss:2.0394420623779297 lr:0.00010813615797164276 tokens_per_second_per_gpu:757.2049975294256 +Step 3866 | loss:2.0388221740722656 lr:0.0001080969391917716 tokens_per_second_per_gpu:778.4265184795202 +Step 3867 | loss:2.02384352684021 lr:0.00010805771915824105 tokens_per_second_per_gpu:783.001957781149 +Step 3868 | loss:2.0659642219543457 lr:0.00010801849787712364 tokens_per_second_per_gpu:768.7652284920529 +Step 3869 | loss:2.010742664337158 lr:0.00010797927535449195 tokens_per_second_per_gpu:775.3648734036951 +Step 3870 | loss:2.0741000175476074 lr:0.0001079400515964189 tokens_per_second_per_gpu:789.4088218024792 +Step 3871 | loss:2.03121018409729 lr:0.00010790082660897758 tokens_per_second_per_gpu:791.0959298509241 +Step 3872 | loss:2.0185365676879883 lr:0.00010786160039824123 tokens_per_second_per_gpu:786.0591271411408 +Step 3873 | loss:2.043802499771118 lr:0.00010782237297028326 tokens_per_second_per_gpu:775.4934124707637 +Step 3874 | loss:2.04240345954895 lr:0.00010778314433117733 tokens_per_second_per_gpu:728.8021781823702 +Step 3875 | loss:2.1232593059539795 lr:0.00010774391448699728 tokens_per_second_per_gpu:783.0422417570023 +Step 3876 | loss:2.032766819000244 lr:0.00010770468344381708 tokens_per_second_per_gpu:774.0194604790942 +Step 3877 | loss:2.016711711883545 lr:0.00010766545120771094 tokens_per_second_per_gpu:760.3282367564092 +Step 3878 | loss:1.999919056892395 lr:0.00010762621778475323 tokens_per_second_per_gpu:776.0783233435881 +Step 3879 | loss:2.051765203475952 lr:0.00010758698318101852 tokens_per_second_per_gpu:736.1520154889031 +Step 3880 | loss:2.052973747253418 lr:0.00010754774740258158 tokens_per_second_per_gpu:757.7999113599152 +Step 3881 | loss:2.05534291267395 lr:0.00010750851045551727 tokens_per_second_per_gpu:779.4322905152203 +Step 3882 | loss:2.094057559967041 lr:0.00010746927234590071 tokens_per_second_per_gpu:789.4629788429579 +Step 3883 | loss:2.0680956840515137 lr:0.00010743003307980724 tokens_per_second_per_gpu:800.9608581611856 +Step 3884 | loss:2.0352678298950195 lr:0.0001073907926633123 tokens_per_second_per_gpu:770.2058662563911 +Step 3885 | loss:2.1059422492980957 lr:0.0001073515511024915 tokens_per_second_per_gpu:804.89428307953 +Step 3886 | loss:2.0814578533172607 lr:0.0001073123084034207 tokens_per_second_per_gpu:792.541979733405 +Step 3887 | loss:2.027993679046631 lr:0.0001072730645721759 tokens_per_second_per_gpu:778.4585966590593 +Step 3888 | loss:1.987100601196289 lr:0.00010723381961483326 tokens_per_second_per_gpu:778.0543700838352 +Step 3889 | loss:2.017123222351074 lr:0.0001071945735374691 tokens_per_second_per_gpu:770.7458543621407 +Step 3890 | loss:2.091167449951172 lr:0.00010715532634615996 tokens_per_second_per_gpu:734.2711392362967 +Step 3891 | loss:2.031280517578125 lr:0.00010711607804698254 tokens_per_second_per_gpu:777.1457099424724 +Step 3892 | loss:2.032895565032959 lr:0.00010707682864601372 tokens_per_second_per_gpu:797.5313194995613 +Step 3893 | loss:1.9893488883972168 lr:0.00010703757814933049 tokens_per_second_per_gpu:777.914561295392 +Step 3894 | loss:2.046383857727051 lr:0.00010699832656301008 tokens_per_second_per_gpu:791.6737502962611 +Step 3895 | loss:2.093892812728882 lr:0.00010695907389312989 tokens_per_second_per_gpu:776.7660777306226 +Step 3896 | loss:2.0380163192749023 lr:0.00010691982014576742 tokens_per_second_per_gpu:781.9934041693255 +Step 3897 | loss:2.0109894275665283 lr:0.00010688056532700039 tokens_per_second_per_gpu:763.1377862487149 +Step 3898 | loss:1.9900364875793457 lr:0.00010684130944290669 tokens_per_second_per_gpu:771.3676610607159 +Step 3899 | loss:2.038443088531494 lr:0.00010680205249956432 tokens_per_second_per_gpu:781.2065003600226 +Step 3900 | loss:2.0328378677368164 lr:0.00010676279450305152 tokens_per_second_per_gpu:758.3202869865884 +Step 3901 | loss:2.030045986175537 lr:0.00010672353545944663 tokens_per_second_per_gpu:765.3559131658444 +Step 3902 | loss:2.0183959007263184 lr:0.00010668427537482819 tokens_per_second_per_gpu:786.9932835046689 +Step 3903 | loss:2.0052130222320557 lr:0.00010664501425527489 tokens_per_second_per_gpu:798.1882299357659 +Step 3904 | loss:2.124379873275757 lr:0.00010660575210686558 tokens_per_second_per_gpu:772.8663896691266 +Step 3905 | loss:2.0209665298461914 lr:0.00010656648893567927 tokens_per_second_per_gpu:799.0210025177086 +Step 3906 | loss:2.043698787689209 lr:0.0001065272247477951 tokens_per_second_per_gpu:788.4146695810055 +Step 3907 | loss:2.052219867706299 lr:0.00010648795954929245 tokens_per_second_per_gpu:756.3609880621774 +Step 3908 | loss:2.050325632095337 lr:0.00010644869334625074 tokens_per_second_per_gpu:771.2188515853013 +Step 3909 | loss:2.061906576156616 lr:0.00010640942614474962 tokens_per_second_per_gpu:775.6525324977036 +Step 3910 | loss:2.066771984100342 lr:0.00010637015795086894 tokens_per_second_per_gpu:792.3464895692371 +Step 3911 | loss:2.0625627040863037 lr:0.00010633088877068858 tokens_per_second_per_gpu:766.8721446982353 +Step 3912 | loss:2.0563812255859375 lr:0.00010629161861028862 tokens_per_second_per_gpu:785.7992392062721 +Step 3913 | loss:2.0171611309051514 lr:0.00010625234747574937 tokens_per_second_per_gpu:786.0280638987782 +Step 3914 | loss:2.074774980545044 lr:0.00010621307537315124 tokens_per_second_per_gpu:791.2758282129796 +Step 3915 | loss:2.0133421421051025 lr:0.0001061738023085747 tokens_per_second_per_gpu:771.590733994211 +Step 3916 | loss:2.025481700897217 lr:0.00010613452828810049 tokens_per_second_per_gpu:787.7817948488904 +Step 3917 | loss:2.070260524749756 lr:0.00010609525331780947 tokens_per_second_per_gpu:753.5472339544027 +Step 3918 | loss:2.1404972076416016 lr:0.00010605597740378261 tokens_per_second_per_gpu:759.4339597850102 +Step 3919 | loss:2.060242176055908 lr:0.0001060167005521011 tokens_per_second_per_gpu:752.9305103882505 +Step 3920 | loss:2.0290133953094482 lr:0.00010597742276884614 tokens_per_second_per_gpu:749.0861817683732 +Step 3921 | loss:1.9998035430908203 lr:0.00010593814406009923 tokens_per_second_per_gpu:788.3841508043796 +Step 3922 | loss:2.0649592876434326 lr:0.00010589886443194193 tokens_per_second_per_gpu:761.1951206186422 +Step 3923 | loss:2.0784852504730225 lr:0.00010585958389045591 tokens_per_second_per_gpu:775.9533731169294 +Step 3924 | loss:2.061342477798462 lr:0.0001058203024417231 tokens_per_second_per_gpu:752.5869124378702 +Step 3925 | loss:2.0552775859832764 lr:0.00010578102009182544 tokens_per_second_per_gpu:764.3137179524165 +Step 3926 | loss:2.0763955116271973 lr:0.00010574173684684507 tokens_per_second_per_gpu:776.9883383287372 +Step 3927 | loss:2.07550048828125 lr:0.00010570245271286428 tokens_per_second_per_gpu:783.8570332182649 +Step 3928 | loss:2.011857032775879 lr:0.0001056631676959655 tokens_per_second_per_gpu:728.9825484999012 +Step 3929 | loss:2.012216567993164 lr:0.00010562388180223124 tokens_per_second_per_gpu:740.7200634027884 +Step 3930 | loss:2.034679412841797 lr:0.0001055845950377442 tokens_per_second_per_gpu:759.8081392713239 +Step 3931 | loss:2.0200626850128174 lr:0.00010554530740858724 tokens_per_second_per_gpu:749.3861612473792 +Step 3932 | loss:2.0694518089294434 lr:0.00010550601892084325 tokens_per_second_per_gpu:772.9778006424848 +Step 3933 | loss:2.0038866996765137 lr:0.00010546672958059532 tokens_per_second_per_gpu:762.8716009619545 +Step 3934 | loss:2.0645203590393066 lr:0.00010542743939392673 tokens_per_second_per_gpu:747.1299303196924 +Step 3935 | loss:2.062687635421753 lr:0.00010538814836692077 tokens_per_second_per_gpu:762.5756191675977 +Step 3936 | loss:1.992291808128357 lr:0.00010534885650566096 tokens_per_second_per_gpu:792.0690723348978 +Step 3937 | loss:2.0254790782928467 lr:0.00010530956381623088 tokens_per_second_per_gpu:779.9476222766572 +Step 3938 | loss:2.053034782409668 lr:0.00010527027030471428 tokens_per_second_per_gpu:788.8179261832588 +Step 3939 | loss:2.0758724212646484 lr:0.000105230975977195 tokens_per_second_per_gpu:742.2160772731762 +Step 3940 | loss:1.957747220993042 lr:0.00010519168083975708 tokens_per_second_per_gpu:761.9508434688045 +Step 3941 | loss:2.0742175579071045 lr:0.00010515238489848462 tokens_per_second_per_gpu:798.1753849717093 +Step 3942 | loss:1.9915335178375244 lr:0.0001051130881594618 tokens_per_second_per_gpu:790.6257381496793 +Step 3943 | loss:2.1014084815979004 lr:0.00010507379062877308 tokens_per_second_per_gpu:760.1932354657475 +Step 3944 | loss:2.060661554336548 lr:0.00010503449231250291 tokens_per_second_per_gpu:778.8151263889577 +Step 3945 | loss:2.0329430103302 lr:0.00010499519321673583 tokens_per_second_per_gpu:763.6800252730734 +Step 3946 | loss:1.991830825805664 lr:0.00010495589334755667 tokens_per_second_per_gpu:778.7389078777038 +Step 3947 | loss:2.0729119777679443 lr:0.00010491659271105023 tokens_per_second_per_gpu:788.9745665858899 +Step 3948 | loss:2.029939651489258 lr:0.00010487729131330146 tokens_per_second_per_gpu:782.2691116794601 +Step 3949 | loss:2.078705072402954 lr:0.0001048379891603955 tokens_per_second_per_gpu:758.4778119323785 +Step 3950 | loss:2.0123491287231445 lr:0.00010479868625841753 tokens_per_second_per_gpu:776.3509015518092 +Step 3951 | loss:2.0495262145996094 lr:0.00010475938261345283 tokens_per_second_per_gpu:772.9913423091858 +Step 3952 | loss:2.068033218383789 lr:0.0001047200782315869 tokens_per_second_per_gpu:769.6347933635197 +Step 3953 | loss:2.0736799240112305 lr:0.0001046807731189052 tokens_per_second_per_gpu:785.0357687025062 +Step 3954 | loss:2.0773801803588867 lr:0.00010464146728149349 tokens_per_second_per_gpu:756.758506994579 +Step 3955 | loss:2.0584475994110107 lr:0.00010460216072543747 tokens_per_second_per_gpu:759.0944138179111 +Step 3956 | loss:2.0607428550720215 lr:0.00010456285345682307 tokens_per_second_per_gpu:775.8251505252146 +Step 3957 | loss:2.0158276557922363 lr:0.00010452354548173621 tokens_per_second_per_gpu:772.5465927957457 +Step 3958 | loss:2.0370752811431885 lr:0.00010448423680626309 tokens_per_second_per_gpu:771.4494005634521 +Step 3959 | loss:2.040945291519165 lr:0.00010444492743648987 tokens_per_second_per_gpu:783.6000306087245 +Step 3960 | loss:2.054110288619995 lr:0.0001044056173785029 tokens_per_second_per_gpu:784.7076211673918 +Step 3961 | loss:2.0234169960021973 lr:0.00010436630663838856 tokens_per_second_per_gpu:783.4055993507603 +Step 3962 | loss:2.081840753555298 lr:0.00010432699522223342 tokens_per_second_per_gpu:769.6817303983923 +Step 3963 | loss:1.9939069747924805 lr:0.00010428768313612407 tokens_per_second_per_gpu:743.3807964531496 +Step 3964 | loss:1.981386423110962 lr:0.00010424837038614733 tokens_per_second_per_gpu:752.1313614351578 +Step 3965 | loss:2.088069438934326 lr:0.00010420905697838996 tokens_per_second_per_gpu:765.4371210799263 +Step 3966 | loss:2.043644428253174 lr:0.00010416974291893897 tokens_per_second_per_gpu:764.4556594240877 +Step 3967 | loss:2.050607681274414 lr:0.00010413042821388135 tokens_per_second_per_gpu:782.3951631387033 +Step 3968 | loss:2.0422308444976807 lr:0.0001040911128693043 tokens_per_second_per_gpu:777.0414803521775 +Step 3969 | loss:1.9941895008087158 lr:0.000104051796891295 tokens_per_second_per_gpu:775.7922379474365 +Step 3970 | loss:2.0572259426116943 lr:0.00010401248028594088 tokens_per_second_per_gpu:787.7917852624972 +Step 3971 | loss:2.0359933376312256 lr:0.00010397316305932932 tokens_per_second_per_gpu:782.5488267885528 +Step 3972 | loss:2.0544159412384033 lr:0.00010393384521754783 tokens_per_second_per_gpu:768.3687485087495 +Step 3973 | loss:2.1079137325286865 lr:0.00010389452676668412 tokens_per_second_per_gpu:768.7404487240577 +Step 3974 | loss:2.0416276454925537 lr:0.00010385520771282589 tokens_per_second_per_gpu:767.164307190039 +Step 3975 | loss:2.12105393409729 lr:0.00010381588806206087 tokens_per_second_per_gpu:766.3002614796029 +Step 3976 | loss:2.0137999057769775 lr:0.00010377656782047711 tokens_per_second_per_gpu:777.821701852582 +Step 3977 | loss:2.060873508453369 lr:0.00010373724699416252 tokens_per_second_per_gpu:789.3092893181843 +Step 3978 | loss:2.047524929046631 lr:0.00010369792558920521 tokens_per_second_per_gpu:772.4413636037541 +Step 3979 | loss:2.0669972896575928 lr:0.00010365860361169341 tokens_per_second_per_gpu:766.0808699579327 +Step 3980 | loss:2.0253190994262695 lr:0.00010361928106771535 tokens_per_second_per_gpu:777.4691436185602 +Step 3981 | loss:2.034698009490967 lr:0.00010357995796335937 tokens_per_second_per_gpu:763.0701241868167 +Step 3982 | loss:2.0627331733703613 lr:0.00010354063430471399 tokens_per_second_per_gpu:789.7339022103441 +Step 3983 | loss:2.0398099422454834 lr:0.00010350131009786766 tokens_per_second_per_gpu:788.7546930168058 +Step 3984 | loss:2.0321335792541504 lr:0.00010346198534890902 tokens_per_second_per_gpu:773.9905284213467 +Step 3985 | loss:2.0286314487457275 lr:0.0001034226600639268 tokens_per_second_per_gpu:777.6195857440453 +Step 3986 | loss:1.9827524423599243 lr:0.00010338333424900979 tokens_per_second_per_gpu:774.4558587648906 +Step 3987 | loss:2.0732996463775635 lr:0.0001033440079102468 tokens_per_second_per_gpu:772.6930679116177 +Step 3988 | loss:2.095893383026123 lr:0.00010330468105372681 tokens_per_second_per_gpu:793.729005517327 +Step 3989 | loss:2.016993284225464 lr:0.00010326535368553889 tokens_per_second_per_gpu:753.7982260534328 +Step 3990 | loss:2.043579339981079 lr:0.00010322602581177205 tokens_per_second_per_gpu:774.0908945773256 +Step 3991 | loss:2.0780816078186035 lr:0.00010318669743851556 tokens_per_second_per_gpu:783.2514934959767 +Step 3992 | loss:2.071009397506714 lr:0.00010314736857185865 tokens_per_second_per_gpu:773.2379880227638 +Step 3993 | loss:2.048978090286255 lr:0.00010310803921789063 tokens_per_second_per_gpu:756.0540903108756 +Step 3994 | loss:2.0678887367248535 lr:0.00010306870938270097 tokens_per_second_per_gpu:787.9611505871273 +Step 3995 | loss:2.034625291824341 lr:0.00010302937907237915 tokens_per_second_per_gpu:787.6564514193849 +Step 3996 | loss:2.0286965370178223 lr:0.00010299004829301466 tokens_per_second_per_gpu:720.5419396819947 +Step 3997 | loss:1.9975098371505737 lr:0.00010295071705069723 tokens_per_second_per_gpu:765.8824575068687 +Step 3998 | loss:1.9945785999298096 lr:0.00010291138535151652 tokens_per_second_per_gpu:754.7037216785152 +Step 3999 | loss:2.0539157390594482 lr:0.00010287205320156226 tokens_per_second_per_gpu:788.2986004676351 +Step 4000 | loss:1.9629576206207275 lr:0.00010283272060692441 tokens_per_second_per_gpu:787.8479600169533 +Step 4001 | loss:1.9718730449676514 lr:0.00010279338757369279 tokens_per_second_per_gpu:791.4269519768756 +Step 4002 | loss:2.0721359252929688 lr:0.00010275405410795743 tokens_per_second_per_gpu:792.1650400327495 +Step 4003 | loss:2.02046799659729 lr:0.00010271472021580838 tokens_per_second_per_gpu:767.6857095315203 +Step 4004 | loss:2.03737473487854 lr:0.00010267538590333572 tokens_per_second_per_gpu:780.8657512331023 +Step 4005 | loss:2.0127696990966797 lr:0.00010263605117662966 tokens_per_second_per_gpu:781.3392234235218 +Step 4006 | loss:2.050935745239258 lr:0.00010259671604178047 tokens_per_second_per_gpu:763.6196433983807 +Step 4007 | loss:2.016860008239746 lr:0.00010255738050487839 tokens_per_second_per_gpu:787.1834355842681 +Step 4008 | loss:2.0972530841827393 lr:0.00010251804457201386 tokens_per_second_per_gpu:785.8396622044212 +Step 4009 | loss:2.0132594108581543 lr:0.00010247870824927728 tokens_per_second_per_gpu:792.0272084610746 +Step 4010 | loss:2.066246509552002 lr:0.00010243937154275915 tokens_per_second_per_gpu:775.5313881431832 +Step 4011 | loss:2.045516014099121 lr:0.00010240003445855 tokens_per_second_per_gpu:777.0336713157935 +Step 4012 | loss:1.983621597290039 lr:0.00010236069700274047 tokens_per_second_per_gpu:788.9716524571139 +Step 4013 | loss:2.077484130859375 lr:0.00010232135918142124 tokens_per_second_per_gpu:737.7751179746778 +Step 4014 | loss:2.087040662765503 lr:0.000102282021000683 tokens_per_second_per_gpu:797.201418935723 +Step 4015 | loss:2.083169460296631 lr:0.00010224268246661652 tokens_per_second_per_gpu:759.1936820905506 +Step 4016 | loss:2.0561656951904297 lr:0.00010220334358531272 tokens_per_second_per_gpu:767.2414454997233 +Step 4017 | loss:2.066312551498413 lr:0.00010216400436286237 tokens_per_second_per_gpu:769.009949856602 +Step 4018 | loss:2.057382583618164 lr:0.00010212466480535649 tokens_per_second_per_gpu:767.9315199575059 +Step 4019 | loss:2.029155731201172 lr:0.00010208532491888608 tokens_per_second_per_gpu:742.8437943361771 +Step 4020 | loss:2.089935064315796 lr:0.0001020459847095421 tokens_per_second_per_gpu:777.6816484708303 +Step 4021 | loss:2.0745503902435303 lr:0.00010200664418341574 tokens_per_second_per_gpu:779.6286804449352 +Step 4022 | loss:1.9996514320373535 lr:0.00010196730334659812 tokens_per_second_per_gpu:776.6497234606476 +Step 4023 | loss:2.008779287338257 lr:0.00010192796220518039 tokens_per_second_per_gpu:785.6806048065347 +Step 4024 | loss:2.0535316467285156 lr:0.00010188862076525385 tokens_per_second_per_gpu:796.5303362977734 +Step 4025 | loss:2.013458251953125 lr:0.00010184927903290975 tokens_per_second_per_gpu:798.6635382526715 +Step 4026 | loss:2.0662662982940674 lr:0.00010180993701423938 tokens_per_second_per_gpu:759.0160276927983 +Step 4027 | loss:2.0709524154663086 lr:0.00010177059471533421 tokens_per_second_per_gpu:789.5816273846382 +Step 4028 | loss:2.046288251876831 lr:0.00010173125214228559 tokens_per_second_per_gpu:754.336145758207 +Step 4029 | loss:1.9963933229446411 lr:0.00010169190930118498 tokens_per_second_per_gpu:765.0371882536305 +Step 4030 | loss:2.0408966541290283 lr:0.00010165256619812393 tokens_per_second_per_gpu:756.5000915001422 +Step 4031 | loss:2.050445556640625 lr:0.00010161322283919392 tokens_per_second_per_gpu:782.8280572414471 +Step 4032 | loss:2.088717460632324 lr:0.00010157387923048658 tokens_per_second_per_gpu:783.560005599511 +Step 4033 | loss:2.0185723304748535 lr:0.00010153453537809354 tokens_per_second_per_gpu:788.0169473253642 +Step 4034 | loss:2.0225424766540527 lr:0.00010149519128810641 tokens_per_second_per_gpu:788.4535961079023 +Step 4035 | loss:1.9936294555664062 lr:0.0001014558469666169 tokens_per_second_per_gpu:766.0200946713136 +Step 4036 | loss:2.008897542953491 lr:0.00010141650241971676 tokens_per_second_per_gpu:759.9632559326473 +Step 4037 | loss:2.0992703437805176 lr:0.00010137715765349778 tokens_per_second_per_gpu:739.9796719245489 +Step 4038 | loss:2.0330004692077637 lr:0.00010133781267405169 tokens_per_second_per_gpu:768.1180178187855 +Step 4039 | loss:2.0734755992889404 lr:0.00010129846748747036 tokens_per_second_per_gpu:778.9398731278541 +Step 4040 | loss:2.0005078315734863 lr:0.0001012591220998457 tokens_per_second_per_gpu:776.0681561262829 +Step 4041 | loss:2.080535411834717 lr:0.0001012197765172695 tokens_per_second_per_gpu:784.2895662000211 +Step 4042 | loss:2.045915126800537 lr:0.0001011804307458338 tokens_per_second_per_gpu:788.8123347089509 +Step 4043 | loss:2.018798589706421 lr:0.00010114108479163049 tokens_per_second_per_gpu:764.0584945108253 +Step 4044 | loss:1.998307228088379 lr:0.00010110173866075152 tokens_per_second_per_gpu:773.9332579554934 +Step 4045 | loss:2.030116558074951 lr:0.00010106239235928902 tokens_per_second_per_gpu:785.082417761851 +Step 4046 | loss:2.0634636878967285 lr:0.00010102304589333496 tokens_per_second_per_gpu:729.1195634095897 +Step 4047 | loss:1.969130516052246 lr:0.00010098369926898135 tokens_per_second_per_gpu:747.0359561460242 +Step 4048 | loss:2.0177977085113525 lr:0.00010094435249232037 tokens_per_second_per_gpu:784.8032991993427 +Step 4049 | loss:2.010287046432495 lr:0.00010090500556944409 tokens_per_second_per_gpu:754.8228213974702 +Step 4050 | loss:2.0791256427764893 lr:0.00010086565850644462 tokens_per_second_per_gpu:772.1068413425239 +Step 4051 | loss:2.0040786266326904 lr:0.00010082631130941417 tokens_per_second_per_gpu:738.3578645296195 +Step 4052 | loss:2.0473225116729736 lr:0.00010078696398444487 tokens_per_second_per_gpu:708.0406602067007 +Step 4053 | loss:2.039424180984497 lr:0.00010074761653762894 tokens_per_second_per_gpu:725.8846537827083 +Step 4054 | loss:2.0066163539886475 lr:0.0001007082689750586 tokens_per_second_per_gpu:784.5071136149552 +Step 4055 | loss:2.077146053314209 lr:0.00010066892130282605 tokens_per_second_per_gpu:766.2571283675234 +Step 4056 | loss:2.02992844581604 lr:0.00010062957352702358 tokens_per_second_per_gpu:772.6493116393317 +Step 4057 | loss:2.018576145172119 lr:0.00010059022565374345 tokens_per_second_per_gpu:755.8753956541008 +Step 4058 | loss:2.041621208190918 lr:0.00010055087768907791 tokens_per_second_per_gpu:756.794728126785 +Step 4059 | loss:1.9745335578918457 lr:0.00010051152963911929 tokens_per_second_per_gpu:775.6107187835703 +Step 4060 | loss:2.0430917739868164 lr:0.00010047218150995988 tokens_per_second_per_gpu:778.0107168523227 +Step 4061 | loss:2.036220073699951 lr:0.00010043283330769202 tokens_per_second_per_gpu:787.4973014392544 +Step 4062 | loss:1.9936531782150269 lr:0.00010039348503840802 tokens_per_second_per_gpu:772.5627651630368 +Step 4063 | loss:2.0550601482391357 lr:0.00010035413670820022 tokens_per_second_per_gpu:759.3452233916446 +Step 4064 | loss:2.0581088066101074 lr:0.000100314788323161 tokens_per_second_per_gpu:786.5448131883107 +Step 4065 | loss:2.002906322479248 lr:0.00010027543988938269 tokens_per_second_per_gpu:745.4545673685501 +Step 4066 | loss:2.0249710083007812 lr:0.00010023609141295767 tokens_per_second_per_gpu:749.7432461793019 +Step 4067 | loss:2.043982744216919 lr:0.00010019674289997834 tokens_per_second_per_gpu:791.543931933183 +Step 4068 | loss:2.0754294395446777 lr:0.00010015739435653699 tokens_per_second_per_gpu:753.5834347786606 +Step 4069 | loss:2.0242953300476074 lr:0.00010011804578872614 tokens_per_second_per_gpu:758.3319898536829 +Step 4070 | loss:2.0498080253601074 lr:0.0001000786972026381 tokens_per_second_per_gpu:780.184627301099 +Step 4071 | loss:1.9929507970809937 lr:0.00010003934860436523 tokens_per_second_per_gpu:777.2415743197005 +Step 4072 | loss:2.000020980834961 lr:0.0001 tokens_per_second_per_gpu:769.4940470562398 +Step 4073 | loss:2.0199952125549316 lr:9.996065139563479e-05 tokens_per_second_per_gpu:774.4629415489464 +Step 4074 | loss:2.0329113006591797 lr:9.992130279736195e-05 tokens_per_second_per_gpu:797.4317507953106 +Step 4075 | loss:2.0707221031188965 lr:9.988195421127387e-05 tokens_per_second_per_gpu:759.0389919499875 +Step 4076 | loss:2.0580031871795654 lr:9.9842605643463e-05 tokens_per_second_per_gpu:783.9824223179834 +Step 4077 | loss:2.0230445861816406 lr:9.98032571000217e-05 tokens_per_second_per_gpu:762.7627100459861 +Step 4078 | loss:2.0261118412017822 lr:9.976390858704237e-05 tokens_per_second_per_gpu:790.8566082225599 +Step 4079 | loss:2.0216450691223145 lr:9.972456011061736e-05 tokens_per_second_per_gpu:789.5045415668823 +Step 4080 | loss:1.9816064834594727 lr:9.968521167683905e-05 tokens_per_second_per_gpu:760.4361547583553 +Step 4081 | loss:2.0147860050201416 lr:9.96458632917998e-05 tokens_per_second_per_gpu:799.7367834878826 +Step 4082 | loss:2.0674991607666016 lr:9.960651496159201e-05 tokens_per_second_per_gpu:779.7875649557722 +Step 4083 | loss:1.9963960647583008 lr:9.9567166692308e-05 tokens_per_second_per_gpu:773.0723459603795 +Step 4084 | loss:2.055846691131592 lr:9.952781849004013e-05 tokens_per_second_per_gpu:782.5697555080142 +Step 4085 | loss:2.0497772693634033 lr:9.948847036088073e-05 tokens_per_second_per_gpu:792.9016308114684 +Step 4086 | loss:2.0134634971618652 lr:9.94491223109221e-05 tokens_per_second_per_gpu:790.0198553936816 +Step 4087 | loss:2.0700736045837402 lr:9.940977434625656e-05 tokens_per_second_per_gpu:772.4394200617725 +Step 4088 | loss:2.004149913787842 lr:9.937042647297643e-05 tokens_per_second_per_gpu:770.2757180145584 +Step 4089 | loss:2.072582244873047 lr:9.933107869717396e-05 tokens_per_second_per_gpu:747.1974932479208 +Step 4090 | loss:2.0127992630004883 lr:9.929173102494144e-05 tokens_per_second_per_gpu:768.2617291722835 +Step 4091 | loss:2.095367431640625 lr:9.925238346237106e-05 tokens_per_second_per_gpu:744.3409807659691 +Step 4092 | loss:2.022581100463867 lr:9.921303601555512e-05 tokens_per_second_per_gpu:787.6239449110649 +Step 4093 | loss:2.0761942863464355 lr:9.917368869058585e-05 tokens_per_second_per_gpu:772.5543731606037 +Step 4094 | loss:2.0367255210876465 lr:9.91343414935554e-05 tokens_per_second_per_gpu:794.9333558820871 +Step 4095 | loss:2.051677703857422 lr:9.909499443055594e-05 tokens_per_second_per_gpu:766.9344247053466 +Step 4096 | loss:1.9913866519927979 lr:9.905564750767967e-05 tokens_per_second_per_gpu:771.7267862319804 +Step 4097 | loss:2.063683032989502 lr:9.901630073101865e-05 tokens_per_second_per_gpu:778.1528218662728 +Step 4098 | loss:1.9881869554519653 lr:9.897695410666506e-05 tokens_per_second_per_gpu:761.2124367576405 +Step 4099 | loss:2.0172595977783203 lr:9.8937607640711e-05 tokens_per_second_per_gpu:775.4982629622059 +Step 4100 | loss:2.052243709564209 lr:9.889826133924849e-05 tokens_per_second_per_gpu:768.5182856855857 +Step 4101 | loss:2.021239995956421 lr:9.885891520836956e-05 tokens_per_second_per_gpu:769.1180580222755 +Step 4102 | loss:1.9964685440063477 lr:9.881956925416622e-05 tokens_per_second_per_gpu:763.5372632429369 +Step 4103 | loss:2.023611545562744 lr:9.878022348273052e-05 tokens_per_second_per_gpu:785.4780495508846 +Step 4104 | loss:1.9623390436172485 lr:9.874087790015434e-05 tokens_per_second_per_gpu:771.2978121234078 +Step 4105 | loss:2.040262460708618 lr:9.870153251252967e-05 tokens_per_second_per_gpu:774.7938529088542 +Step 4106 | loss:2.0243782997131348 lr:9.866218732594836e-05 tokens_per_second_per_gpu:783.1949391544302 +Step 4107 | loss:2.032365560531616 lr:9.862284234650225e-05 tokens_per_second_per_gpu:772.5386072043026 +Step 4108 | loss:2.0416128635406494 lr:9.858349758028324e-05 tokens_per_second_per_gpu:728.8864451253402 +Step 4109 | loss:2.0457873344421387 lr:9.854415303338311e-05 tokens_per_second_per_gpu:777.4569546631287 +Step 4110 | loss:2.08902645111084 lr:9.850480871189361e-05 tokens_per_second_per_gpu:788.4311559897993 +Step 4111 | loss:2.0507304668426514 lr:9.84654646219065e-05 tokens_per_second_per_gpu:723.5448729160539 +Step 4112 | loss:2.0662646293640137 lr:9.842612076951343e-05 tokens_per_second_per_gpu:748.1732664216839 +Step 4113 | loss:2.03544020652771 lr:9.838677716080609e-05 tokens_per_second_per_gpu:788.6741649665917 +Step 4114 | loss:2.022145986557007 lr:9.834743380187609e-05 tokens_per_second_per_gpu:752.6586609006395 +Step 4115 | loss:2.0420970916748047 lr:9.830809069881504e-05 tokens_per_second_per_gpu:751.100707962948 +Step 4116 | loss:2.03800106048584 lr:9.826874785771444e-05 tokens_per_second_per_gpu:787.036699607568 +Step 4117 | loss:2.0808982849121094 lr:9.822940528466584e-05 tokens_per_second_per_gpu:799.5866002413544 +Step 4118 | loss:2.0221309661865234 lr:9.819006298576062e-05 tokens_per_second_per_gpu:773.641144026556 +Step 4119 | loss:1.9981565475463867 lr:9.815072096709027e-05 tokens_per_second_per_gpu:763.6564252317826 +Step 4120 | loss:2.000739336013794 lr:9.811137923474617e-05 tokens_per_second_per_gpu:780.9213103191639 +Step 4121 | loss:2.0119545459747314 lr:9.807203779481963e-05 tokens_per_second_per_gpu:790.340297761515 +Step 4122 | loss:2.0821478366851807 lr:9.803269665340192e-05 tokens_per_second_per_gpu:774.2278245972725 +Step 4123 | loss:1.983885645866394 lr:9.799335581658425e-05 tokens_per_second_per_gpu:775.5051371816339 +Step 4124 | loss:2.0351130962371826 lr:9.79540152904579e-05 tokens_per_second_per_gpu:736.3376797923919 +Step 4125 | loss:2.002342700958252 lr:9.791467508111395e-05 tokens_per_second_per_gpu:749.3318333726522 +Step 4126 | loss:2.0191524028778076 lr:9.787533519464353e-05 tokens_per_second_per_gpu:791.6047375192999 +Step 4127 | loss:2.0419254302978516 lr:9.783599563713766e-05 tokens_per_second_per_gpu:783.0928724958444 +Step 4128 | loss:2.046978235244751 lr:9.779665641468733e-05 tokens_per_second_per_gpu:756.4402099513981 +Step 4129 | loss:2.0347187519073486 lr:9.775731753338346e-05 tokens_per_second_per_gpu:782.6191793170523 +Step 4130 | loss:2.0492143630981445 lr:9.771797899931702e-05 tokens_per_second_per_gpu:778.5238279195025 +Step 4131 | loss:2.055270195007324 lr:9.767864081857878e-05 tokens_per_second_per_gpu:745.1869307876636 +Step 4132 | loss:2.092231273651123 lr:9.763930299725956e-05 tokens_per_second_per_gpu:792.1775180917629 +Step 4133 | loss:1.9969978332519531 lr:9.759996554145003e-05 tokens_per_second_per_gpu:755.9723628041849 +Step 4134 | loss:1.9928762912750244 lr:9.756062845724087e-05 tokens_per_second_per_gpu:767.3107583362967 +Step 4135 | loss:2.0237889289855957 lr:9.752129175072273e-05 tokens_per_second_per_gpu:790.4386986998794 +Step 4136 | loss:2.0782127380371094 lr:9.748195542798615e-05 tokens_per_second_per_gpu:775.871751471847 +Step 4137 | loss:2.0487236976623535 lr:9.744261949512162e-05 tokens_per_second_per_gpu:788.4371355150478 +Step 4138 | loss:2.0139904022216797 lr:9.740328395821957e-05 tokens_per_second_per_gpu:770.3027437046076 +Step 4139 | loss:1.9768404960632324 lr:9.736394882337037e-05 tokens_per_second_per_gpu:776.3456000534688 +Step 4140 | loss:2.0323407649993896 lr:9.732461409666429e-05 tokens_per_second_per_gpu:779.6793929617448 +Step 4141 | loss:2.0630781650543213 lr:9.728527978419164e-05 tokens_per_second_per_gpu:770.4090812673106 +Step 4142 | loss:1.9965338706970215 lr:9.724594589204258e-05 tokens_per_second_per_gpu:769.9582063860462 +Step 4143 | loss:2.1020662784576416 lr:9.720661242630722e-05 tokens_per_second_per_gpu:765.7435667341224 +Step 4144 | loss:2.098360776901245 lr:9.716727939307562e-05 tokens_per_second_per_gpu:797.317240049565 +Step 4145 | loss:2.013153314590454 lr:9.712794679843773e-05 tokens_per_second_per_gpu:767.920482753988 +Step 4146 | loss:2.027266502380371 lr:9.70886146484835e-05 tokens_per_second_per_gpu:770.8605286764688 +Step 4147 | loss:2.0540430545806885 lr:9.70492829493028e-05 tokens_per_second_per_gpu:793.6461914498785 +Step 4148 | loss:2.03973388671875 lr:9.700995170698537e-05 tokens_per_second_per_gpu:793.2728466830799 +Step 4149 | loss:2.0310235023498535 lr:9.69706209276209e-05 tokens_per_second_per_gpu:784.4314983594022 +Step 4150 | loss:2.0142829418182373 lr:9.693129061729904e-05 tokens_per_second_per_gpu:777.8521625078301 +Step 4151 | loss:2.04311466217041 lr:9.689196078210937e-05 tokens_per_second_per_gpu:774.9724978806817 +Step 4152 | loss:2.1317965984344482 lr:9.685263142814137e-05 tokens_per_second_per_gpu:763.7260644881381 +Step 4153 | loss:2.0031979084014893 lr:9.681330256148446e-05 tokens_per_second_per_gpu:742.8832252561454 +Step 4154 | loss:2.0142335891723633 lr:9.677397418822797e-05 tokens_per_second_per_gpu:775.8543597387785 +Step 4155 | loss:1.987852931022644 lr:9.673464631446115e-05 tokens_per_second_per_gpu:753.1320534313949 +Step 4156 | loss:2.0009288787841797 lr:9.669531894627317e-05 tokens_per_second_per_gpu:784.805931771334 +Step 4157 | loss:2.0231146812438965 lr:9.66559920897532e-05 tokens_per_second_per_gpu:766.6509471341203 +Step 4158 | loss:2.0232882499694824 lr:9.661666575099024e-05 tokens_per_second_per_gpu:747.9294335428958 +Step 4159 | loss:2.0002708435058594 lr:9.657733993607321e-05 tokens_per_second_per_gpu:777.3693476516871 +Step 4160 | loss:2.0020060539245605 lr:9.653801465109101e-05 tokens_per_second_per_gpu:765.3075579529558 +Step 4161 | loss:2.048692226409912 lr:9.649868990213235e-05 tokens_per_second_per_gpu:773.2627383830837 +Step 4162 | loss:2.045361280441284 lr:9.645936569528603e-05 tokens_per_second_per_gpu:781.0450094628632 +Step 4163 | loss:2.0900015830993652 lr:9.642004203664064e-05 tokens_per_second_per_gpu:790.1817464896212 +Step 4164 | loss:2.0153732299804688 lr:9.638071893228467e-05 tokens_per_second_per_gpu:799.384504864234 +Step 4165 | loss:2.113618850708008 lr:9.634139638830661e-05 tokens_per_second_per_gpu:793.2801441809902 +Step 4166 | loss:2.0452945232391357 lr:9.630207441079477e-05 tokens_per_second_per_gpu:787.8625901299711 +Step 4167 | loss:2.0534369945526123 lr:9.62627530058375e-05 tokens_per_second_per_gpu:790.7818867755492 +Step 4168 | loss:2.0901434421539307 lr:9.622343217952291e-05 tokens_per_second_per_gpu:774.2239532457447 +Step 4169 | loss:2.0548810958862305 lr:9.618411193793914e-05 tokens_per_second_per_gpu:750.1743420118636 +Step 4170 | loss:2.004159688949585 lr:9.614479228717417e-05 tokens_per_second_per_gpu:769.0682632623774 +Step 4171 | loss:2.05415415763855 lr:9.610547323331593e-05 tokens_per_second_per_gpu:771.5192696126795 +Step 4172 | loss:2.074406623840332 lr:9.606615478245217e-05 tokens_per_second_per_gpu:777.7691891264144 +Step 4173 | loss:2.0155155658721924 lr:9.602683694067069e-05 tokens_per_second_per_gpu:745.4184993751774 +Step 4174 | loss:2.0153210163116455 lr:9.598751971405914e-05 tokens_per_second_per_gpu:777.2316814856382 +Step 4175 | loss:2.0510237216949463 lr:9.594820310870501e-05 tokens_per_second_per_gpu:775.8435500387577 +Step 4176 | loss:2.0209503173828125 lr:9.590888713069573e-05 tokens_per_second_per_gpu:800.5567385948616 +Step 4177 | loss:2.076785087585449 lr:9.586957178611866e-05 tokens_per_second_per_gpu:784.9072879849163 +Step 4178 | loss:2.022432565689087 lr:9.583025708106107e-05 tokens_per_second_per_gpu:758.0334407076026 +Step 4179 | loss:2.05570912361145 lr:9.579094302161005e-05 tokens_per_second_per_gpu:758.3935359093948 +Step 4180 | loss:2.0334272384643555 lr:9.575162961385271e-05 tokens_per_second_per_gpu:791.4452208263823 +Step 4181 | loss:2.0167646408081055 lr:9.571231686387597e-05 tokens_per_second_per_gpu:768.6402107370917 +Step 4182 | loss:2.053374767303467 lr:9.56730047777666e-05 tokens_per_second_per_gpu:782.9003815862121 +Step 4183 | loss:2.0065057277679443 lr:9.563369336161145e-05 tokens_per_second_per_gpu:780.1522868150685 +Step 4184 | loss:2.049980401992798 lr:9.559438262149714e-05 tokens_per_second_per_gpu:765.79466866817 +Step 4185 | loss:2.0310299396514893 lr:9.555507256351013e-05 tokens_per_second_per_gpu:777.8476885877133 +Step 4186 | loss:2.0577523708343506 lr:9.551576319373692e-05 tokens_per_second_per_gpu:777.5226547430551 +Step 4187 | loss:2.012326717376709 lr:9.547645451826382e-05 tokens_per_second_per_gpu:764.4361473226058 +Step 4188 | loss:2.0081539154052734 lr:9.543714654317697e-05 tokens_per_second_per_gpu:782.2240198727433 +Step 4189 | loss:2.0338356494903564 lr:9.539783927456253e-05 tokens_per_second_per_gpu:758.5995831766967 +Step 4190 | loss:2.088153123855591 lr:9.535853271850655e-05 tokens_per_second_per_gpu:761.1699764066293 +Step 4191 | loss:1.9819276332855225 lr:9.53192268810948e-05 tokens_per_second_per_gpu:735.6533941897674 +Step 4192 | loss:2.0403621196746826 lr:9.527992176841315e-05 tokens_per_second_per_gpu:785.6543070509962 +Step 4193 | loss:2.0331737995147705 lr:9.524061738654718e-05 tokens_per_second_per_gpu:788.4143801477046 +Step 4194 | loss:2.1043894290924072 lr:9.52013137415825e-05 tokens_per_second_per_gpu:756.9622843116713 +Step 4195 | loss:2.057497501373291 lr:9.51620108396045e-05 tokens_per_second_per_gpu:757.2437562922181 +Step 4196 | loss:1.9952285289764404 lr:9.512270868669855e-05 tokens_per_second_per_gpu:785.0817442173822 +Step 4197 | loss:1.9962670803070068 lr:9.50834072889498e-05 tokens_per_second_per_gpu:780.2349171927742 +Step 4198 | loss:2.0448079109191895 lr:9.504410665244337e-05 tokens_per_second_per_gpu:765.7879372169109 +Step 4199 | loss:2.0567827224731445 lr:9.500480678326418e-05 tokens_per_second_per_gpu:758.8018337272343 +Step 4200 | loss:2.0454797744750977 lr:9.496550768749713e-05 tokens_per_second_per_gpu:765.7405058296123 +Step 4201 | loss:1.9980559349060059 lr:9.492620937122693e-05 tokens_per_second_per_gpu:751.3264499539513 +Step 4202 | loss:2.0211169719696045 lr:9.488691184053823e-05 tokens_per_second_per_gpu:725.3401904452758 +Step 4203 | loss:2.029097557067871 lr:9.484761510151543e-05 tokens_per_second_per_gpu:780.0254915877812 +Step 4204 | loss:2.0061585903167725 lr:9.480831916024292e-05 tokens_per_second_per_gpu:796.8578077773498 +Step 4205 | loss:2.0167956352233887 lr:9.476902402280501e-05 tokens_per_second_per_gpu:764.9544835928314 +Step 4206 | loss:2.027522563934326 lr:9.472972969528574e-05 tokens_per_second_per_gpu:769.2234418021214 +Step 4207 | loss:2.1229441165924072 lr:9.469043618376916e-05 tokens_per_second_per_gpu:800.8780617391121 +Step 4208 | loss:1.9411437511444092 lr:9.465114349433909e-05 tokens_per_second_per_gpu:770.1664135754506 +Step 4209 | loss:2.059438943862915 lr:9.461185163307924e-05 tokens_per_second_per_gpu:781.503468756977 +Step 4210 | loss:2.0460686683654785 lr:9.457256060607328e-05 tokens_per_second_per_gpu:784.9421590879455 +Step 4211 | loss:2.0070085525512695 lr:9.45332704194047e-05 tokens_per_second_per_gpu:734.7954918382972 +Step 4212 | loss:2.0424110889434814 lr:9.449398107915679e-05 tokens_per_second_per_gpu:781.5912945449336 +Step 4213 | loss:1.9780504703521729 lr:9.445469259141281e-05 tokens_per_second_per_gpu:763.4427129826921 +Step 4214 | loss:2.0922298431396484 lr:9.441540496225584e-05 tokens_per_second_per_gpu:776.2221783433847 +Step 4215 | loss:2.0586256980895996 lr:9.437611819776878e-05 tokens_per_second_per_gpu:767.4690671237934 +Step 4216 | loss:1.9580748081207275 lr:9.433683230403452e-05 tokens_per_second_per_gpu:774.6905468215998 +Step 4217 | loss:2.0035810470581055 lr:9.429754728713574e-05 tokens_per_second_per_gpu:790.405781643196 +Step 4218 | loss:2.0146822929382324 lr:9.425826315315495e-05 tokens_per_second_per_gpu:753.3161355153197 +Step 4219 | loss:2.0464298725128174 lr:9.421897990817461e-05 tokens_per_second_per_gpu:787.2080084103395 +Step 4220 | loss:2.1090505123138428 lr:9.417969755827691e-05 tokens_per_second_per_gpu:747.2294018302459 +Step 4221 | loss:2.057150363922119 lr:9.414041610954411e-05 tokens_per_second_per_gpu:757.2185071922065 +Step 4222 | loss:1.9446523189544678 lr:9.41011355680581e-05 tokens_per_second_per_gpu:750.7749536896516 +Step 4223 | loss:2.0816469192504883 lr:9.40618559399008e-05 tokens_per_second_per_gpu:773.2133624678328 +Step 4224 | loss:2.050309181213379 lr:9.402257723115387e-05 tokens_per_second_per_gpu:762.6907028180956 +Step 4225 | loss:2.0653679370880127 lr:9.398329944789892e-05 tokens_per_second_per_gpu:777.890329253641 +Step 4226 | loss:2.104048252105713 lr:9.39440225962174e-05 tokens_per_second_per_gpu:793.4504379564601 +Step 4227 | loss:2.009208917617798 lr:9.390474668219054e-05 tokens_per_second_per_gpu:787.7359756344671 +Step 4228 | loss:2.0584564208984375 lr:9.386547171189953e-05 tokens_per_second_per_gpu:776.0253745576833 +Step 4229 | loss:1.9513142108917236 lr:9.382619769142536e-05 tokens_per_second_per_gpu:746.5188146046978 +Step 4230 | loss:2.1065759658813477 lr:9.378692462684881e-05 tokens_per_second_per_gpu:795.0873094367092 +Step 4231 | loss:2.054500102996826 lr:9.374765252425061e-05 tokens_per_second_per_gpu:777.1682177243125 +Step 4232 | loss:2.043720245361328 lr:9.370838138971139e-05 tokens_per_second_per_gpu:788.1029119245477 +Step 4233 | loss:2.0626368522644043 lr:9.366911122931146e-05 tokens_per_second_per_gpu:767.097540498494 +Step 4234 | loss:1.9930733442306519 lr:9.36298420491311e-05 tokens_per_second_per_gpu:794.3236732753213 +Step 4235 | loss:2.0215625762939453 lr:9.35905738552504e-05 tokens_per_second_per_gpu:792.5075566603145 +Step 4236 | loss:2.0107061862945557 lr:9.355130665374928e-05 tokens_per_second_per_gpu:764.3430297070109 +Step 4237 | loss:1.9681986570358276 lr:9.351204045070757e-05 tokens_per_second_per_gpu:779.7233333507019 +Step 4238 | loss:2.0018131732940674 lr:9.347277525220492e-05 tokens_per_second_per_gpu:764.4371262376517 +Step 4239 | loss:2.0466158390045166 lr:9.343351106432076e-05 tokens_per_second_per_gpu:737.3503805697443 +Step 4240 | loss:2.007035255432129 lr:9.339424789313445e-05 tokens_per_second_per_gpu:792.1422487695095 +Step 4241 | loss:2.034497022628784 lr:9.335498574472516e-05 tokens_per_second_per_gpu:757.3189584862307 +Step 4242 | loss:2.0359103679656982 lr:9.331572462517183e-05 tokens_per_second_per_gpu:793.184545797314 +Step 4243 | loss:2.0799560546875 lr:9.327646454055338e-05 tokens_per_second_per_gpu:801.1481280896667 +Step 4244 | loss:2.029917001724243 lr:9.323720549694852e-05 tokens_per_second_per_gpu:747.4228546062725 +Step 4245 | loss:2.039431571960449 lr:9.319794750043572e-05 tokens_per_second_per_gpu:791.3055864893618 +Step 4246 | loss:2.0015487670898438 lr:9.315869055709337e-05 tokens_per_second_per_gpu:781.8435031827064 +Step 4247 | loss:2.045189619064331 lr:9.311943467299962e-05 tokens_per_second_per_gpu:770.286173307002 +Step 4248 | loss:2.0265252590179443 lr:9.30801798542326e-05 tokens_per_second_per_gpu:785.586192321688 +Step 4249 | loss:2.0050435066223145 lr:9.304092610687012e-05 tokens_per_second_per_gpu:771.5530297502225 +Step 4250 | loss:2.0202560424804688 lr:9.300167343698993e-05 tokens_per_second_per_gpu:760.9192120851525 +Step 4251 | loss:2.025301456451416 lr:9.296242185066953e-05 tokens_per_second_per_gpu:759.5065636760104 +Step 4252 | loss:2.013693332672119 lr:9.292317135398629e-05 tokens_per_second_per_gpu:786.4313773907743 +Step 4253 | loss:1.9813660383224487 lr:9.288392195301747e-05 tokens_per_second_per_gpu:777.1493939140255 +Step 4254 | loss:1.9570167064666748 lr:9.284467365384005e-05 tokens_per_second_per_gpu:754.6699667545971 +Step 4255 | loss:2.0404694080352783 lr:9.280542646253094e-05 tokens_per_second_per_gpu:772.7154354826444 +Step 4256 | loss:2.0172388553619385 lr:9.27661803851668e-05 tokens_per_second_per_gpu:755.6574467849256 +Step 4257 | loss:1.9950311183929443 lr:9.272693542782414e-05 tokens_per_second_per_gpu:771.8558170834269 +Step 4258 | loss:1.9762574434280396 lr:9.26876915965793e-05 tokens_per_second_per_gpu:782.6359534514751 +Step 4259 | loss:2.0259668827056885 lr:9.264844889750852e-05 tokens_per_second_per_gpu:770.9326871759882 +Step 4260 | loss:2.0296390056610107 lr:9.260920733668772e-05 tokens_per_second_per_gpu:775.7487058168509 +Step 4261 | loss:2.065526008605957 lr:9.256996692019279e-05 tokens_per_second_per_gpu:790.0564296247901 +Step 4262 | loss:2.058577537536621 lr:9.253072765409933e-05 tokens_per_second_per_gpu:770.6641682918419 +Step 4263 | loss:2.0897350311279297 lr:9.249148954448277e-05 tokens_per_second_per_gpu:777.272444571993 +Step 4264 | loss:2.022984027862549 lr:9.245225259741845e-05 tokens_per_second_per_gpu:757.6664862098255 +Step 4265 | loss:2.046616554260254 lr:9.241301681898151e-05 tokens_per_second_per_gpu:776.8377058309864 +Step 4266 | loss:2.0237247943878174 lr:9.237378221524679e-05 tokens_per_second_per_gpu:781.0921187193666 +Step 4267 | loss:1.9789845943450928 lr:9.23345487922891e-05 tokens_per_second_per_gpu:758.4073941902928 +Step 4268 | loss:2.0301291942596436 lr:9.229531655618293e-05 tokens_per_second_per_gpu:780.9961274141178 +Step 4269 | loss:1.9742000102996826 lr:9.225608551300274e-05 tokens_per_second_per_gpu:785.184930912831 +Step 4270 | loss:2.0667872428894043 lr:9.221685566882268e-05 tokens_per_second_per_gpu:744.3372489069577 +Step 4271 | loss:2.0135140419006348 lr:9.217762702971677e-05 tokens_per_second_per_gpu:759.6464027425359 +Step 4272 | loss:2.0674195289611816 lr:9.21383996017588e-05 tokens_per_second_per_gpu:743.3053109253692 +Step 4273 | loss:2.0742874145507812 lr:9.209917339102245e-05 tokens_per_second_per_gpu:783.7849412608291 +Step 4274 | loss:2.023521900177002 lr:9.20599484035811e-05 tokens_per_second_per_gpu:724.2322650404118 +Step 4275 | loss:2.0746750831604004 lr:9.202072464550809e-05 tokens_per_second_per_gpu:771.3595562062687 +Step 4276 | loss:2.0496745109558105 lr:9.19815021228764e-05 tokens_per_second_per_gpu:777.6183947172667 +Step 4277 | loss:1.9800705909729004 lr:9.194228084175897e-05 tokens_per_second_per_gpu:759.1899857322813 +Step 4278 | loss:2.0283586978912354 lr:9.190306080822841e-05 tokens_per_second_per_gpu:759.5315412635015 +Step 4279 | loss:2.0521717071533203 lr:9.186384202835725e-05 tokens_per_second_per_gpu:782.2652224617806 +Step 4280 | loss:1.9813417196273804 lr:9.182462450821781e-05 tokens_per_second_per_gpu:773.7760187740427 +Step 4281 | loss:2.0352745056152344 lr:9.178540825388216e-05 tokens_per_second_per_gpu:798.3740435763516 +Step 4282 | loss:2.0701801776885986 lr:9.174619327142221e-05 tokens_per_second_per_gpu:791.0741072702311 +Step 4283 | loss:2.049919843673706 lr:9.170697956690966e-05 tokens_per_second_per_gpu:776.2768675716051 +Step 4284 | loss:2.045509099960327 lr:9.166776714641599e-05 tokens_per_second_per_gpu:777.3476524037632 +Step 4285 | loss:2.0910491943359375 lr:9.162855601601254e-05 tokens_per_second_per_gpu:772.6106362172067 +Step 4286 | loss:2.067657947540283 lr:9.158934618177044e-05 tokens_per_second_per_gpu:766.9591740172227 +Step 4287 | loss:2.085340976715088 lr:9.155013764976054e-05 tokens_per_second_per_gpu:762.9280746529988 +Step 4288 | loss:2.0171756744384766 lr:9.151093042605362e-05 tokens_per_second_per_gpu:781.8836714838549 +Step 4289 | loss:2.042842388153076 lr:9.147172451672014e-05 tokens_per_second_per_gpu:759.1415366041426 +Step 4290 | loss:1.9970042705535889 lr:9.143251992783036e-05 tokens_per_second_per_gpu:804.2492756970977 +Step 4291 | loss:2.046517848968506 lr:9.139331666545445e-05 tokens_per_second_per_gpu:789.7351037526242 +Step 4292 | loss:2.045267105102539 lr:9.135411473566229e-05 tokens_per_second_per_gpu:785.0289154783262 +Step 4293 | loss:2.0698983669281006 lr:9.131491414452352e-05 tokens_per_second_per_gpu:767.9622107427557 +Step 4294 | loss:2.0279910564422607 lr:9.127571489810768e-05 tokens_per_second_per_gpu:739.9867899958286 +Step 4295 | loss:2.0455801486968994 lr:9.123651700248396e-05 tokens_per_second_per_gpu:776.9011482932451 +Step 4296 | loss:2.0293655395507812 lr:9.119732046372149e-05 tokens_per_second_per_gpu:807.6189731476358 +Step 4297 | loss:2.011406421661377 lr:9.115812528788908e-05 tokens_per_second_per_gpu:781.4696602796467 +Step 4298 | loss:2.0389537811279297 lr:9.111893148105542e-05 tokens_per_second_per_gpu:759.7967587713576 +Step 4299 | loss:2.031374454498291 lr:9.107973904928888e-05 tokens_per_second_per_gpu:787.0568623990393 +Step 4300 | loss:1.9777262210845947 lr:9.104054799865769e-05 tokens_per_second_per_gpu:741.2980156914059 +Step 4301 | loss:2.024625301361084 lr:9.100135833522982e-05 tokens_per_second_per_gpu:770.7953292744496 +Step 4302 | loss:2.011448383331299 lr:9.096217006507315e-05 tokens_per_second_per_gpu:781.4866566863401 +Step 4303 | loss:2.054736375808716 lr:9.092298319425514e-05 tokens_per_second_per_gpu:775.1388982046994 +Step 4304 | loss:2.021566152572632 lr:9.088379772884325e-05 tokens_per_second_per_gpu:768.7554130195081 +Step 4305 | loss:2.026218891143799 lr:9.084461367490451e-05 tokens_per_second_per_gpu:794.1333329106653 +Step 4306 | loss:2.0218849182128906 lr:9.080543103850587e-05 tokens_per_second_per_gpu:780.4531457972822 +Step 4307 | loss:2.0738093852996826 lr:9.076624982571409e-05 tokens_per_second_per_gpu:786.1261457350319 +Step 4308 | loss:2.0375447273254395 lr:9.072707004259557e-05 tokens_per_second_per_gpu:779.3551484937813 +Step 4309 | loss:2.0437188148498535 lr:9.068789169521663e-05 tokens_per_second_per_gpu:802.8504280505535 +Step 4310 | loss:2.0495800971984863 lr:9.064871478964326e-05 tokens_per_second_per_gpu:780.3657866589043 +Step 4311 | loss:2.018582820892334 lr:9.060953933194123e-05 tokens_per_second_per_gpu:778.7767581869961 +Step 4312 | loss:2.0547306537628174 lr:9.057036532817622e-05 tokens_per_second_per_gpu:771.9981644616935 +Step 4313 | loss:2.0249714851379395 lr:9.053119278441356e-05 tokens_per_second_per_gpu:774.1671901297018 +Step 4314 | loss:1.9709501266479492 lr:9.049202170671833e-05 tokens_per_second_per_gpu:754.4089149676921 +Step 4315 | loss:2.071460247039795 lr:9.045285210115551e-05 tokens_per_second_per_gpu:779.3727067596906 +Step 4316 | loss:2.066147565841675 lr:9.041368397378976e-05 tokens_per_second_per_gpu:744.3666622273619 +Step 4317 | loss:2.047578811645508 lr:9.037451733068546e-05 tokens_per_second_per_gpu:759.0199234413611 +Step 4318 | loss:1.9714195728302002 lr:9.033535217790692e-05 tokens_per_second_per_gpu:781.0149119056862 +Step 4319 | loss:2.0800886154174805 lr:9.029618852151812e-05 tokens_per_second_per_gpu:752.4236807152787 +Step 4320 | loss:2.027862071990967 lr:9.025702636758277e-05 tokens_per_second_per_gpu:785.8738001232073 +Step 4321 | loss:1.9917678833007812 lr:9.021786572216447e-05 tokens_per_second_per_gpu:788.8000339137149 +Step 4322 | loss:2.0276193618774414 lr:9.01787065913264e-05 tokens_per_second_per_gpu:758.0263772939304 +Step 4323 | loss:2.0158867835998535 lr:9.013954898113175e-05 tokens_per_second_per_gpu:778.1351005297372 +Step 4324 | loss:2.0393762588500977 lr:9.010039289764325e-05 tokens_per_second_per_gpu:777.3127724906973 +Step 4325 | loss:2.019273281097412 lr:9.006123834692353e-05 tokens_per_second_per_gpu:774.2081081603055 +Step 4326 | loss:2.0512466430664062 lr:9.002208533503491e-05 tokens_per_second_per_gpu:801.0392301855031 +Step 4327 | loss:2.064858913421631 lr:8.998293386803949e-05 tokens_per_second_per_gpu:784.0861633612445 +Step 4328 | loss:2.0331482887268066 lr:8.99437839519992e-05 tokens_per_second_per_gpu:759.6626025784905 +Step 4329 | loss:1.9808992147445679 lr:8.990463559297566e-05 tokens_per_second_per_gpu:768.7165756012492 +Step 4330 | loss:1.987339973449707 lr:8.98654887970302e-05 tokens_per_second_per_gpu:776.2802159872857 +Step 4331 | loss:2.1135027408599854 lr:8.982634357022403e-05 tokens_per_second_per_gpu:778.2152475408762 +Step 4332 | loss:1.9969596862792969 lr:8.978719991861801e-05 tokens_per_second_per_gpu:746.8153385113359 +Step 4333 | loss:2.0593130588531494 lr:8.974805784827281e-05 tokens_per_second_per_gpu:754.0853137161297 +Step 4334 | loss:2.098904609680176 lr:8.97089173652489e-05 tokens_per_second_per_gpu:762.6338150897193 +Step 4335 | loss:2.017648696899414 lr:8.96697784756064e-05 tokens_per_second_per_gpu:791.0587383138333 +Step 4336 | loss:1.9722752571105957 lr:8.963064118540523e-05 tokens_per_second_per_gpu:773.9894872734291 +Step 4337 | loss:2.0171384811401367 lr:8.959150550070511e-05 tokens_per_second_per_gpu:741.6586359140554 +Step 4338 | loss:2.016280174255371 lr:8.955237142756538e-05 tokens_per_second_per_gpu:775.7410890990907 +Step 4339 | loss:2.127829074859619 lr:8.951323897204531e-05 tokens_per_second_per_gpu:772.4991667729045 +Step 4340 | loss:2.029982566833496 lr:8.94741081402038e-05 tokens_per_second_per_gpu:727.685340053047 +Step 4341 | loss:2.055964469909668 lr:8.943497893809953e-05 tokens_per_second_per_gpu:765.7319520535746 +Step 4342 | loss:2.065657138824463 lr:8.939585137179092e-05 tokens_per_second_per_gpu:752.3115743657504 +Step 4343 | loss:2.0812430381774902 lr:8.935672544733609e-05 tokens_per_second_per_gpu:773.139362186185 +Step 4344 | loss:2.075531005859375 lr:8.931760117079304e-05 tokens_per_second_per_gpu:735.9529227673303 +Step 4345 | loss:1.9760091304779053 lr:8.927847854821938e-05 tokens_per_second_per_gpu:743.7066384744268 +Step 4346 | loss:2.031691074371338 lr:8.923935758567256e-05 tokens_per_second_per_gpu:781.0541751855229 +Step 4347 | loss:2.038403034210205 lr:8.920023828920965e-05 tokens_per_second_per_gpu:768.0233415287979 +Step 4348 | loss:2.0566787719726562 lr:8.916112066488764e-05 tokens_per_second_per_gpu:777.0571542181426 +Step 4349 | loss:2.0062685012817383 lr:8.912200471876306e-05 tokens_per_second_per_gpu:765.4329514741795 +Step 4350 | loss:2.02966046333313 lr:8.908289045689237e-05 tokens_per_second_per_gpu:769.4702455004298 +Step 4351 | loss:2.0538957118988037 lr:8.904377788533162e-05 tokens_per_second_per_gpu:755.5046422046919 +Step 4352 | loss:2.002687454223633 lr:8.900466701013672e-05 tokens_per_second_per_gpu:790.9635486685689 +Step 4353 | loss:2.072192907333374 lr:8.896555783736317e-05 tokens_per_second_per_gpu:770.7468467653669 +Step 4354 | loss:2.039170742034912 lr:8.892645037306634e-05 tokens_per_second_per_gpu:762.7588565835305 +Step 4355 | loss:2.0225155353546143 lr:8.888734462330132e-05 tokens_per_second_per_gpu:786.3753332341603 +Step 4356 | loss:2.017263174057007 lr:8.884824059412289e-05 tokens_per_second_per_gpu:759.5958080046605 +Step 4357 | loss:1.9837634563446045 lr:8.880913829158554e-05 tokens_per_second_per_gpu:777.4218771872944 +Step 4358 | loss:2.044365882873535 lr:8.877003772174355e-05 tokens_per_second_per_gpu:781.6966043166683 +Step 4359 | loss:1.9523874521255493 lr:8.873093889065091e-05 tokens_per_second_per_gpu:794.3265255623379 +Step 4360 | loss:1.9908456802368164 lr:8.869184180436129e-05 tokens_per_second_per_gpu:760.6843364295661 +Step 4361 | loss:2.067814588546753 lr:8.865274646892827e-05 tokens_per_second_per_gpu:777.6226389650769 +Step 4362 | loss:2.0456290245056152 lr:8.861365289040495e-05 tokens_per_second_per_gpu:776.1649761366059 +Step 4363 | loss:2.085651159286499 lr:8.85745610748442e-05 tokens_per_second_per_gpu:781.3618959625837 +Step 4364 | loss:2.0059871673583984 lr:8.853547102829873e-05 tokens_per_second_per_gpu:783.8413522699515 +Step 4365 | loss:2.00291109085083 lr:8.849638275682083e-05 tokens_per_second_per_gpu:788.2265515586203 +Step 4366 | loss:2.021758794784546 lr:8.845729626646264e-05 tokens_per_second_per_gpu:789.5657358046997 +Step 4367 | loss:2.0105409622192383 lr:8.841821156327599e-05 tokens_per_second_per_gpu:760.1920110965086 +Step 4368 | loss:2.015859365463257 lr:8.837912865331236e-05 tokens_per_second_per_gpu:777.0370575953233 +Step 4369 | loss:2.0563271045684814 lr:8.834004754262303e-05 tokens_per_second_per_gpu:783.0121674154791 +Step 4370 | loss:2.042600631713867 lr:8.830096823725897e-05 tokens_per_second_per_gpu:758.5895407449792 +Step 4371 | loss:2.039273500442505 lr:8.82618907432709e-05 tokens_per_second_per_gpu:757.6516474595529 +Step 4372 | loss:1.9610862731933594 lr:8.82228150667092e-05 tokens_per_second_per_gpu:783.549790205815 +Step 4373 | loss:2.0024735927581787 lr:8.818374121362407e-05 tokens_per_second_per_gpu:790.2928529955649 +Step 4374 | loss:2.021716833114624 lr:8.81446691900653e-05 tokens_per_second_per_gpu:793.7123262447556 +Step 4375 | loss:2.068307638168335 lr:8.81055990020825e-05 tokens_per_second_per_gpu:741.0280514002957 +Step 4376 | loss:2.0004444122314453 lr:8.80665306557249e-05 tokens_per_second_per_gpu:778.1889216477105 +Step 4377 | loss:2.027984142303467 lr:8.802746415704158e-05 tokens_per_second_per_gpu:774.7352764608684 +Step 4378 | loss:2.0258524417877197 lr:8.798839951208123e-05 tokens_per_second_per_gpu:779.6913899758738 +Step 4379 | loss:2.0621705055236816 lr:8.794933672689225e-05 tokens_per_second_per_gpu:777.5639844979058 +Step 4380 | loss:2.0661044120788574 lr:8.79102758075228e-05 tokens_per_second_per_gpu:753.193853423375 +Step 4381 | loss:2.0408952236175537 lr:8.78712167600207e-05 tokens_per_second_per_gpu:786.5438277989456 +Step 4382 | loss:2.08144211769104 lr:8.78321595904336e-05 tokens_per_second_per_gpu:725.2318357485709 +Step 4383 | loss:2.0309672355651855 lr:8.77931043048087e-05 tokens_per_second_per_gpu:784.9076761425321 +Step 4384 | loss:2.0243706703186035 lr:8.775405090919299e-05 tokens_per_second_per_gpu:791.0175523829447 +Step 4385 | loss:2.0342211723327637 lr:8.771499940963317e-05 tokens_per_second_per_gpu:778.6314702060718 +Step 4386 | loss:2.0079333782196045 lr:8.767594981217558e-05 tokens_per_second_per_gpu:778.8627938723946 +Step 4387 | loss:1.9942057132720947 lr:8.76369021228664e-05 tokens_per_second_per_gpu:771.2801090843132 +Step 4388 | loss:2.0238759517669678 lr:8.75978563477514e-05 tokens_per_second_per_gpu:796.5265360440468 +Step 4389 | loss:2.0481221675872803 lr:8.755881249287608e-05 tokens_per_second_per_gpu:749.220591572254 +Step 4390 | loss:2.1146490573883057 lr:8.751977056428565e-05 tokens_per_second_per_gpu:766.1241393462284 +Step 4391 | loss:2.065317153930664 lr:8.748073056802504e-05 tokens_per_second_per_gpu:755.3898421100786 +Step 4392 | loss:2.0765819549560547 lr:8.744169251013881e-05 tokens_per_second_per_gpu:742.7433119720932 +Step 4393 | loss:2.07798171043396 lr:8.740265639667133e-05 tokens_per_second_per_gpu:776.5113143233376 +Step 4394 | loss:2.015133857727051 lr:8.73636222336666e-05 tokens_per_second_per_gpu:785.3289614588745 +Step 4395 | loss:1.9732121229171753 lr:8.732459002716831e-05 tokens_per_second_per_gpu:765.2299422213871 +Step 4396 | loss:2.01810359954834 lr:8.728555978321989e-05 tokens_per_second_per_gpu:747.2899744567596 +Step 4397 | loss:2.0126078128814697 lr:8.72465315078644e-05 tokens_per_second_per_gpu:775.8832611757763 +Step 4398 | loss:1.998591661453247 lr:8.72075052071447e-05 tokens_per_second_per_gpu:773.553928153225 +Step 4399 | loss:2.0542643070220947 lr:8.716848088710321e-05 tokens_per_second_per_gpu:788.6640089020634 +Step 4400 | loss:2.0574827194213867 lr:8.712945855378218e-05 tokens_per_second_per_gpu:763.2868575934913 +Step 4401 | loss:2.0336973667144775 lr:8.709043821322346e-05 tokens_per_second_per_gpu:766.1166842878375 +Step 4402 | loss:2.0341086387634277 lr:8.705141987146858e-05 tokens_per_second_per_gpu:785.1539179536519 +Step 4403 | loss:2.0523452758789062 lr:8.701240353455889e-05 tokens_per_second_per_gpu:754.4511886236842 +Step 4404 | loss:2.034611701965332 lr:8.697338920853528e-05 tokens_per_second_per_gpu:783.3081179847903 +Step 4405 | loss:2.023275136947632 lr:8.693437689943838e-05 tokens_per_second_per_gpu:791.7997752376151 +Step 4406 | loss:2.028688907623291 lr:8.689536661330856e-05 tokens_per_second_per_gpu:770.423992054385 +Step 4407 | loss:2.0154359340667725 lr:8.685635835618577e-05 tokens_per_second_per_gpu:753.8127897368136 +Step 4408 | loss:2.0214130878448486 lr:8.681735213410973e-05 tokens_per_second_per_gpu:790.6196481833457 +Step 4409 | loss:2.0535941123962402 lr:8.677834795311988e-05 tokens_per_second_per_gpu:764.6434294333546 +Step 4410 | loss:2.050813913345337 lr:8.673934581925523e-05 tokens_per_second_per_gpu:769.7655347408362 +Step 4411 | loss:1.9984259605407715 lr:8.670034573855452e-05 tokens_per_second_per_gpu:766.8395245726848 +Step 4412 | loss:2.037665605545044 lr:8.666134771705623e-05 tokens_per_second_per_gpu:767.0721339652666 +Step 4413 | loss:2.0128211975097656 lr:8.66223517607984e-05 tokens_per_second_per_gpu:751.1796808894953 +Step 4414 | loss:2.0576939582824707 lr:8.65833578758189e-05 tokens_per_second_per_gpu:771.0997103116006 +Step 4415 | loss:2.055290699005127 lr:8.654436606815519e-05 tokens_per_second_per_gpu:788.4482392048636 +Step 4416 | loss:2.050560712814331 lr:8.65053763438444e-05 tokens_per_second_per_gpu:731.2223911271004 +Step 4417 | loss:2.0268633365631104 lr:8.646638870892333e-05 tokens_per_second_per_gpu:785.8700161278759 +Step 4418 | loss:2.0544662475585938 lr:8.642740316942857e-05 tokens_per_second_per_gpu:767.9305753020358 +Step 4419 | loss:2.040717840194702 lr:8.638841973139619e-05 tokens_per_second_per_gpu:787.3798806840206 +Step 4420 | loss:2.0276432037353516 lr:8.634943840086213e-05 tokens_per_second_per_gpu:786.8418114658396 +Step 4421 | loss:2.0450234413146973 lr:8.631045918386192e-05 tokens_per_second_per_gpu:794.8556219612104 +Step 4422 | loss:1.974467158317566 lr:8.62714820864307e-05 tokens_per_second_per_gpu:798.5526141284269 +Step 4423 | loss:2.0095925331115723 lr:8.62325071146034e-05 tokens_per_second_per_gpu:771.0928482146999 +Step 4424 | loss:2.023922920227051 lr:8.619353427441451e-05 tokens_per_second_per_gpu:793.9197141159506 +Step 4425 | loss:2.0359787940979004 lr:8.615456357189831e-05 tokens_per_second_per_gpu:787.5925638732762 +Step 4426 | loss:2.0315847396850586 lr:8.611559501308864e-05 tokens_per_second_per_gpu:771.7972362555751 +Step 4427 | loss:1.978806495666504 lr:8.607662860401908e-05 tokens_per_second_per_gpu:760.100538466626 +Step 4428 | loss:2.069249153137207 lr:8.603766435072281e-05 tokens_per_second_per_gpu:768.0906597026733 +Step 4429 | loss:1.9914979934692383 lr:8.599870225923273e-05 tokens_per_second_per_gpu:782.0351108945854 +Step 4430 | loss:2.0370917320251465 lr:8.595974233558141e-05 tokens_per_second_per_gpu:778.771794823974 +Step 4431 | loss:2.023746967315674 lr:8.592078458580108e-05 tokens_per_second_per_gpu:793.5679952566633 +Step 4432 | loss:2.0423707962036133 lr:8.588182901592355e-05 tokens_per_second_per_gpu:774.6506252829844 +Step 4433 | loss:2.025437831878662 lr:8.584287563198043e-05 tokens_per_second_per_gpu:764.7153331821012 +Step 4434 | loss:2.035792827606201 lr:8.580392444000285e-05 tokens_per_second_per_gpu:742.0564542303773 +Step 4435 | loss:1.9720855951309204 lr:8.576497544602171e-05 tokens_per_second_per_gpu:780.6433070986219 +Step 4436 | loss:2.056753635406494 lr:8.572602865606758e-05 tokens_per_second_per_gpu:801.9638833725529 +Step 4437 | loss:2.0835764408111572 lr:8.568708407617058e-05 tokens_per_second_per_gpu:775.3795797453059 +Step 4438 | loss:2.0212562084198 lr:8.564814171236057e-05 tokens_per_second_per_gpu:761.5564207503088 +Step 4439 | loss:1.9963548183441162 lr:8.560920157066706e-05 tokens_per_second_per_gpu:775.1553326229194 +Step 4440 | loss:2.0117783546447754 lr:8.557026365711912e-05 tokens_per_second_per_gpu:784.9381944969962 +Step 4441 | loss:1.9942636489868164 lr:8.553132797774566e-05 tokens_per_second_per_gpu:760.1880651902167 +Step 4442 | loss:2.0204317569732666 lr:8.549239453857511e-05 tokens_per_second_per_gpu:770.7075134281357 +Step 4443 | loss:2.018338918685913 lr:8.545346334563559e-05 tokens_per_second_per_gpu:788.4967151730108 +Step 4444 | loss:2.0519752502441406 lr:8.541453440495481e-05 tokens_per_second_per_gpu:769.5741725216901 +Step 4445 | loss:2.011925220489502 lr:8.537560772256022e-05 tokens_per_second_per_gpu:765.5353928956873 +Step 4446 | loss:1.9997050762176514 lr:8.533668330447894e-05 tokens_per_second_per_gpu:786.4080952563822 +Step 4447 | loss:2.022428512573242 lr:8.529776115673762e-05 tokens_per_second_per_gpu:786.8930756713941 +Step 4448 | loss:2.0032167434692383 lr:8.525884128536268e-05 tokens_per_second_per_gpu:782.6493243102557 +Step 4449 | loss:1.9888427257537842 lr:8.521992369638007e-05 tokens_per_second_per_gpu:795.628030213638 +Step 4450 | loss:2.0163815021514893 lr:8.51810083958155e-05 tokens_per_second_per_gpu:778.6512324818079 +Step 4451 | loss:2.0355911254882812 lr:8.514209538969422e-05 tokens_per_second_per_gpu:783.1137801906967 +Step 4452 | loss:2.0378975868225098 lr:8.510318468404127e-05 tokens_per_second_per_gpu:773.7784089078503 +Step 4453 | loss:2.0399060249328613 lr:8.506427628488116e-05 tokens_per_second_per_gpu:788.7244655672082 +Step 4454 | loss:2.1002373695373535 lr:8.502537019823819e-05 tokens_per_second_per_gpu:773.9327658881655 +Step 4455 | loss:2.0502398014068604 lr:8.498646643013618e-05 tokens_per_second_per_gpu:779.74739887307 +Step 4456 | loss:2.020644187927246 lr:8.494756498659866e-05 tokens_per_second_per_gpu:790.6672395655163 +Step 4457 | loss:2.022383213043213 lr:8.490866587364884e-05 tokens_per_second_per_gpu:799.7188912727569 +Step 4458 | loss:1.9776453971862793 lr:8.48697690973095e-05 tokens_per_second_per_gpu:791.2190653903674 +Step 4459 | loss:1.9769418239593506 lr:8.483087466360303e-05 tokens_per_second_per_gpu:784.1401351025532 +Step 4460 | loss:2.0481996536254883 lr:8.479198257855157e-05 tokens_per_second_per_gpu:791.1511121028846 +Step 4461 | loss:2.035383939743042 lr:8.475309284817679e-05 tokens_per_second_per_gpu:776.2408006497988 +Step 4462 | loss:2.0223641395568848 lr:8.47142054785e-05 tokens_per_second_per_gpu:769.6997737812378 +Step 4463 | loss:2.006417751312256 lr:8.467532047554229e-05 tokens_per_second_per_gpu:773.9519151456325 +Step 4464 | loss:2.008370876312256 lr:8.46364378453242e-05 tokens_per_second_per_gpu:777.0364465012631 +Step 4465 | loss:2.047285795211792 lr:8.459755759386597e-05 tokens_per_second_per_gpu:779.8393324825724 +Step 4466 | loss:2.051234722137451 lr:8.455867972718753e-05 tokens_per_second_per_gpu:756.9399933417557 +Step 4467 | loss:1.993593692779541 lr:8.45198042513083e-05 tokens_per_second_per_gpu:790.536984092023 +Step 4468 | loss:2.0436761379241943 lr:8.448093117224751e-05 tokens_per_second_per_gpu:778.9340927820757 +Step 4469 | loss:1.968532681465149 lr:8.444206049602391e-05 tokens_per_second_per_gpu:772.5103698992596 +Step 4470 | loss:2.104853630065918 lr:8.44031922286559e-05 tokens_per_second_per_gpu:792.5788273335245 +Step 4471 | loss:2.0558526515960693 lr:8.436432637616143e-05 tokens_per_second_per_gpu:769.9378471742539 +Step 4472 | loss:2.094423770904541 lr:8.43254629445582e-05 tokens_per_second_per_gpu:783.464101807176 +Step 4473 | loss:1.9955488443374634 lr:8.428660193986353e-05 tokens_per_second_per_gpu:782.7662784145206 +Step 4474 | loss:2.0197412967681885 lr:8.424774336809426e-05 tokens_per_second_per_gpu:774.2032533916897 +Step 4475 | loss:2.0468902587890625 lr:8.420888723526695e-05 tokens_per_second_per_gpu:783.6017370282493 +Step 4476 | loss:2.031642436981201 lr:8.417003354739769e-05 tokens_per_second_per_gpu:762.8882204476921 +Step 4477 | loss:1.9811266660690308 lr:8.413118231050232e-05 tokens_per_second_per_gpu:784.1226641760671 +Step 4478 | loss:1.9797323942184448 lr:8.409233353059615e-05 tokens_per_second_per_gpu:790.1784633873559 +Step 4479 | loss:2.022855043411255 lr:8.405348721369425e-05 tokens_per_second_per_gpu:780.9207897764319 +Step 4480 | loss:2.0509772300720215 lr:8.40146433658112e-05 tokens_per_second_per_gpu:783.9739129732907 +Step 4481 | loss:2.045008897781372 lr:8.397580199296127e-05 tokens_per_second_per_gpu:777.8016999654974 +Step 4482 | loss:1.9830174446105957 lr:8.39369631011583e-05 tokens_per_second_per_gpu:773.3782039419191 +Step 4483 | loss:2.015645980834961 lr:8.389812669641574e-05 tokens_per_second_per_gpu:757.8854250305274 +Step 4484 | loss:2.0264317989349365 lr:8.385929278474678e-05 tokens_per_second_per_gpu:772.2078369635741 +Step 4485 | loss:2.0909321308135986 lr:8.382046137216403e-05 tokens_per_second_per_gpu:791.5599549214925 +Step 4486 | loss:2.0234320163726807 lr:8.378163246467983e-05 tokens_per_second_per_gpu:792.5010934395627 +Step 4487 | loss:2.0519323348999023 lr:8.374280606830614e-05 tokens_per_second_per_gpu:796.90028734074 +Step 4488 | loss:2.0679280757904053 lr:8.370398218905442e-05 tokens_per_second_per_gpu:778.9848185457419 +Step 4489 | loss:2.009402275085449 lr:8.366516083293591e-05 tokens_per_second_per_gpu:770.8366270502762 +Step 4490 | loss:2.090367078781128 lr:8.362634200596134e-05 tokens_per_second_per_gpu:795.9247087794797 +Step 4491 | loss:2.006380081176758 lr:8.358752571414108e-05 tokens_per_second_per_gpu:753.7917715433827 +Step 4492 | loss:2.0662803649902344 lr:8.354871196348508e-05 tokens_per_second_per_gpu:794.8568615350559 +Step 4493 | loss:1.9934207201004028 lr:8.350990076000297e-05 tokens_per_second_per_gpu:787.148265726692 +Step 4494 | loss:2.030491590499878 lr:8.347109210970386e-05 tokens_per_second_per_gpu:798.3070487811682 +Step 4495 | loss:2.066426992416382 lr:8.343228601859661e-05 tokens_per_second_per_gpu:779.6540643772129 +Step 4496 | loss:2.0123348236083984 lr:8.339348249268962e-05 tokens_per_second_per_gpu:794.7982595759045 +Step 4497 | loss:2.0489540100097656 lr:8.335468153799088e-05 tokens_per_second_per_gpu:764.6607728356023 +Step 4498 | loss:2.0179367065429688 lr:8.331588316050794e-05 tokens_per_second_per_gpu:754.5967197208678 +Step 4499 | loss:2.020552158355713 lr:8.327708736624803e-05 tokens_per_second_per_gpu:788.0948554135108 +Step 4500 | loss:1.9916961193084717 lr:8.3238294161218e-05 tokens_per_second_per_gpu:763.9499959802889 +Step 4501 | loss:1.9897265434265137 lr:8.31995035514242e-05 tokens_per_second_per_gpu:784.9453991956585 +Step 4502 | loss:1.989264965057373 lr:8.316071554287267e-05 tokens_per_second_per_gpu:732.765941066741 +Step 4503 | loss:2.0713510513305664 lr:8.312193014156894e-05 tokens_per_second_per_gpu:769.6223169539694 +Step 4504 | loss:2.0123586654663086 lr:8.308314735351825e-05 tokens_per_second_per_gpu:792.7633681854037 +Step 4505 | loss:2.027863025665283 lr:8.304436718472541e-05 tokens_per_second_per_gpu:784.0043902379481 +Step 4506 | loss:1.9550034999847412 lr:8.300558964119478e-05 tokens_per_second_per_gpu:790.0967135846897 +Step 4507 | loss:1.9574439525604248 lr:8.296681472893031e-05 tokens_per_second_per_gpu:771.303054856324 +Step 4508 | loss:2.022298574447632 lr:8.292804245393562e-05 tokens_per_second_per_gpu:727.7090051477966 +Step 4509 | loss:1.962199091911316 lr:8.288927282221381e-05 tokens_per_second_per_gpu:789.6950139722776 +Step 4510 | loss:2.049107789993286 lr:8.285050583976764e-05 tokens_per_second_per_gpu:776.696843122874 +Step 4511 | loss:2.002821922302246 lr:8.281174151259952e-05 tokens_per_second_per_gpu:770.8907123735538 +Step 4512 | loss:2.0523698329925537 lr:8.277297984671132e-05 tokens_per_second_per_gpu:800.4661596168054 +Step 4513 | loss:2.0110230445861816 lr:8.273422084810459e-05 tokens_per_second_per_gpu:775.8039150670513 +Step 4514 | loss:1.9858866930007935 lr:8.269546452278041e-05 tokens_per_second_per_gpu:792.5456518556566 +Step 4515 | loss:2.0714099407196045 lr:8.265671087673943e-05 tokens_per_second_per_gpu:776.8798832016336 +Step 4516 | loss:2.000349760055542 lr:8.261795991598201e-05 tokens_per_second_per_gpu:769.6922280718222 +Step 4517 | loss:2.0414047241210938 lr:8.257921164650799e-05 tokens_per_second_per_gpu:785.8174389876918 +Step 4518 | loss:1.9886677265167236 lr:8.254046607431681e-05 tokens_per_second_per_gpu:779.6035593022083 +Step 4519 | loss:2.02343487739563 lr:8.250172320540745e-05 tokens_per_second_per_gpu:765.3237832469603 +Step 4520 | loss:2.004389524459839 lr:8.24629830457786e-05 tokens_per_second_per_gpu:773.5202135017978 +Step 4521 | loss:2.039975166320801 lr:8.242424560142834e-05 tokens_per_second_per_gpu:799.7087627590183 +Step 4522 | loss:2.053859233856201 lr:8.23855108783545e-05 tokens_per_second_per_gpu:764.1967842041875 +Step 4523 | loss:2.030402660369873 lr:8.234677888255448e-05 tokens_per_second_per_gpu:783.9110662779668 +Step 4524 | loss:2.0260109901428223 lr:8.230804962002514e-05 tokens_per_second_per_gpu:795.7757578742837 +Step 4525 | loss:2.039825439453125 lr:8.226932309676298e-05 tokens_per_second_per_gpu:756.6581746653744 +Step 4526 | loss:2.0547733306884766 lr:8.223059931876404e-05 tokens_per_second_per_gpu:785.6603572633439 +Step 4527 | loss:2.029245376586914 lr:8.21918782920241e-05 tokens_per_second_per_gpu:780.9005757569475 +Step 4528 | loss:2.0856475830078125 lr:8.215316002253825e-05 tokens_per_second_per_gpu:783.520539369394 +Step 4529 | loss:1.9630688428878784 lr:8.211444451630138e-05 tokens_per_second_per_gpu:789.1561307255358 +Step 4530 | loss:2.016106128692627 lr:8.207573177930781e-05 tokens_per_second_per_gpu:758.1701234747916 +Step 4531 | loss:2.0547144412994385 lr:8.203702181755148e-05 tokens_per_second_per_gpu:757.0670575176489 +Step 4532 | loss:1.9988384246826172 lr:8.199831463702594e-05 tokens_per_second_per_gpu:771.3495892402541 +Step 4533 | loss:2.0019335746765137 lr:8.195961024372427e-05 tokens_per_second_per_gpu:728.056631672791 +Step 4534 | loss:2.0081934928894043 lr:8.192090864363908e-05 tokens_per_second_per_gpu:773.6278938455715 +Step 4535 | loss:2.021955966949463 lr:8.188220984276262e-05 tokens_per_second_per_gpu:770.089428860718 +Step 4536 | loss:2.0052976608276367 lr:8.184351384708666e-05 tokens_per_second_per_gpu:771.958776378253 +Step 4537 | loss:1.9740499258041382 lr:8.180482066260252e-05 tokens_per_second_per_gpu:776.3817436906921 +Step 4538 | loss:2.038153648376465 lr:8.17661302953012e-05 tokens_per_second_per_gpu:773.4713568578097 +Step 4539 | loss:2.059157371520996 lr:8.172744275117314e-05 tokens_per_second_per_gpu:766.0655356147055 +Step 4540 | loss:2.068772554397583 lr:8.168875803620834e-05 tokens_per_second_per_gpu:782.8016588369084 +Step 4541 | loss:1.995571255683899 lr:8.165007615639646e-05 tokens_per_second_per_gpu:766.878887593216 +Step 4542 | loss:2.000861406326294 lr:8.161139711772659e-05 tokens_per_second_per_gpu:770.5617412565651 +Step 4543 | loss:2.0316858291625977 lr:8.157272092618755e-05 tokens_per_second_per_gpu:789.5450828352248 +Step 4544 | loss:1.9651718139648438 lr:8.153404758776757e-05 tokens_per_second_per_gpu:752.621442131745 +Step 4545 | loss:2.034870147705078 lr:8.149537710845452e-05 tokens_per_second_per_gpu:786.1498270269875 +Step 4546 | loss:2.0610694885253906 lr:8.145670949423574e-05 tokens_per_second_per_gpu:795.043151172549 +Step 4547 | loss:2.048802614212036 lr:8.141804475109823e-05 tokens_per_second_per_gpu:788.8913359569957 +Step 4548 | loss:1.9601315259933472 lr:8.137938288502851e-05 tokens_per_second_per_gpu:764.372749046023 +Step 4549 | loss:2.0488390922546387 lr:8.134072390201264e-05 tokens_per_second_per_gpu:770.5589395344983 +Step 4550 | loss:2.021165609359741 lr:8.130206780803625e-05 tokens_per_second_per_gpu:745.601636544855 +Step 4551 | loss:2.0591306686401367 lr:8.126341460908448e-05 tokens_per_second_per_gpu:770.2719701130031 +Step 4552 | loss:2.010887622833252 lr:8.122476431114205e-05 tokens_per_second_per_gpu:787.5610671460696 +Step 4553 | loss:1.9936937093734741 lr:8.118611692019325e-05 tokens_per_second_per_gpu:769.2822345760568 +Step 4554 | loss:1.9716637134552002 lr:8.114747244222193e-05 tokens_per_second_per_gpu:773.8935805518693 +Step 4555 | loss:2.0284154415130615 lr:8.110883088321143e-05 tokens_per_second_per_gpu:776.6750158271607 +Step 4556 | loss:2.0273830890655518 lr:8.10701922491447e-05 tokens_per_second_per_gpu:772.2506348607374 +Step 4557 | loss:2.0229458808898926 lr:8.103155654600418e-05 tokens_per_second_per_gpu:769.5187229576605 +Step 4558 | loss:2.0486531257629395 lr:8.09929237797719e-05 tokens_per_second_per_gpu:790.0866435232211 +Step 4559 | loss:2.012118339538574 lr:8.095429395642941e-05 tokens_per_second_per_gpu:769.0021535195401 +Step 4560 | loss:2.014519691467285 lr:8.091566708195786e-05 tokens_per_second_per_gpu:774.6932929600241 +Step 4561 | loss:2.0506887435913086 lr:8.087704316233782e-05 tokens_per_second_per_gpu:763.897418797953 +Step 4562 | loss:2.0075738430023193 lr:8.083842220354956e-05 tokens_per_second_per_gpu:797.6633650112574 +Step 4563 | loss:2.0521860122680664 lr:8.079980421157271e-05 tokens_per_second_per_gpu:791.2828151045794 +Step 4564 | loss:2.0439271926879883 lr:8.076118919238666e-05 tokens_per_second_per_gpu:753.5987361483947 +Step 4565 | loss:2.007676601409912 lr:8.072257715197017e-05 tokens_per_second_per_gpu:790.7708905871016 +Step 4566 | loss:1.9942989349365234 lr:8.068396809630158e-05 tokens_per_second_per_gpu:789.7630122870116 +Step 4567 | loss:2.0751075744628906 lr:8.06453620313588e-05 tokens_per_second_per_gpu:782.1961980512275 +Step 4568 | loss:2.028939962387085 lr:8.060675896311925e-05 tokens_per_second_per_gpu:780.1304590071816 +Step 4569 | loss:2.0355682373046875 lr:8.056815889755984e-05 tokens_per_second_per_gpu:757.5072163569533 +Step 4570 | loss:2.0613648891448975 lr:8.052956184065714e-05 tokens_per_second_per_gpu:793.7010974304318 +Step 4571 | loss:2.0415451526641846 lr:8.049096779838719e-05 tokens_per_second_per_gpu:713.7436527787562 +Step 4572 | loss:2.0371181964874268 lr:8.04523767767255e-05 tokens_per_second_per_gpu:792.2088181160825 +Step 4573 | loss:2.020996570587158 lr:8.04137887816472e-05 tokens_per_second_per_gpu:762.595855676106 +Step 4574 | loss:2.000408887863159 lr:8.037520381912685e-05 tokens_per_second_per_gpu:776.31999956179 +Step 4575 | loss:2.018021821975708 lr:8.033662189513874e-05 tokens_per_second_per_gpu:787.5291031742556 +Step 4576 | loss:2.044468641281128 lr:8.029804301565645e-05 tokens_per_second_per_gpu:794.9886421657804 +Step 4577 | loss:2.0571064949035645 lr:8.025946718665325e-05 tokens_per_second_per_gpu:778.7081332287063 +Step 4578 | loss:1.9966180324554443 lr:8.022089441410185e-05 tokens_per_second_per_gpu:779.5982519219762 +Step 4579 | loss:2.015627861022949 lr:8.018232470397455e-05 tokens_per_second_per_gpu:765.0758162530642 +Step 4580 | loss:2.0740723609924316 lr:8.014375806224309e-05 tokens_per_second_per_gpu:798.7356116359896 +Step 4581 | loss:2.0380747318267822 lr:8.01051944948789e-05 tokens_per_second_per_gpu:774.3599743183369 +Step 4582 | loss:2.090820074081421 lr:8.006663400785272e-05 tokens_per_second_per_gpu:742.3902734235724 +Step 4583 | loss:1.9915392398834229 lr:8.0028076607135e-05 tokens_per_second_per_gpu:761.1653033891813 +Step 4584 | loss:2.053516387939453 lr:7.998952229869557e-05 tokens_per_second_per_gpu:780.4721888339293 +Step 4585 | loss:2.0051488876342773 lr:7.995097108850384e-05 tokens_per_second_per_gpu:794.6773919455352 +Step 4586 | loss:2.016573905944824 lr:7.991242298252881e-05 tokens_per_second_per_gpu:760.6307898574983 +Step 4587 | loss:2.0131185054779053 lr:7.98738779867389e-05 tokens_per_second_per_gpu:776.5706736955742 +Step 4588 | loss:2.0471200942993164 lr:7.983533610710203e-05 tokens_per_second_per_gpu:751.8823760697928 +Step 4589 | loss:2.0239975452423096 lr:7.979679734958578e-05 tokens_per_second_per_gpu:769.7228868455626 +Step 4590 | loss:2.0101356506347656 lr:7.975826172015704e-05 tokens_per_second_per_gpu:767.3300255877713 +Step 4591 | loss:2.0462327003479004 lr:7.971972922478243e-05 tokens_per_second_per_gpu:794.0712370411752 +Step 4592 | loss:2.059976100921631 lr:7.968119986942799e-05 tokens_per_second_per_gpu:775.3204225787443 +Step 4593 | loss:1.9960196018218994 lr:7.964267366005921e-05 tokens_per_second_per_gpu:776.5975988568374 +Step 4594 | loss:2.024838924407959 lr:7.960415060264115e-05 tokens_per_second_per_gpu:770.8418720597296 +Step 4595 | loss:2.0563929080963135 lr:7.956563070313843e-05 tokens_per_second_per_gpu:776.2275514067791 +Step 4596 | loss:2.0001111030578613 lr:7.952711396751507e-05 tokens_per_second_per_gpu:791.9246165050344 +Step 4597 | loss:1.9678285121917725 lr:7.948860040173474e-05 tokens_per_second_per_gpu:793.4942135931259 +Step 4598 | loss:2.0072519779205322 lr:7.945009001176052e-05 tokens_per_second_per_gpu:761.1871625968399 +Step 4599 | loss:1.9709932804107666 lr:7.941158280355501e-05 tokens_per_second_per_gpu:774.4032339502647 +Step 4600 | loss:2.075244426727295 lr:7.937307878308032e-05 tokens_per_second_per_gpu:767.1364295668459 +Step 4601 | loss:2.0009641647338867 lr:7.933457795629808e-05 tokens_per_second_per_gpu:777.450702122734 +Step 4602 | loss:2.031144142150879 lr:7.929608032916946e-05 tokens_per_second_per_gpu:795.8125291585576 +Step 4603 | loss:2.011007785797119 lr:7.925758590765505e-05 tokens_per_second_per_gpu:775.2514116335425 +Step 4604 | loss:2.049691915512085 lr:7.921909469771504e-05 tokens_per_second_per_gpu:782.5406188514258 +Step 4605 | loss:2.0390303134918213 lr:7.918060670530904e-05 tokens_per_second_per_gpu:759.317903605989 +Step 4606 | loss:2.047083854675293 lr:7.914212193639614e-05 tokens_per_second_per_gpu:784.5153167387932 +Step 4607 | loss:2.009230613708496 lr:7.910364039693508e-05 tokens_per_second_per_gpu:769.5744749034341 +Step 4608 | loss:2.0036330223083496 lr:7.9065162092884e-05 tokens_per_second_per_gpu:759.825183508086 +Step 4609 | loss:2.034313678741455 lr:7.902668703020047e-05 tokens_per_second_per_gpu:758.316580934811 +Step 4610 | loss:2.0668246746063232 lr:7.89882152148417e-05 tokens_per_second_per_gpu:771.6774506631546 +Step 4611 | loss:1.9645793437957764 lr:7.89497466527643e-05 tokens_per_second_per_gpu:772.1044846318886 +Step 4612 | loss:2.0624687671661377 lr:7.89112813499244e-05 tokens_per_second_per_gpu:778.9118414723146 +Step 4613 | loss:2.0101511478424072 lr:7.887281931227765e-05 tokens_per_second_per_gpu:763.4952669132517 +Step 4614 | loss:2.036288261413574 lr:7.88343605457792e-05 tokens_per_second_per_gpu:773.3961329230258 +Step 4615 | loss:2.115882635116577 lr:7.87959050563836e-05 tokens_per_second_per_gpu:769.2305070664687 +Step 4616 | loss:2.038964033126831 lr:7.875745285004504e-05 tokens_per_second_per_gpu:763.1541278680572 +Step 4617 | loss:2.0604703426361084 lr:7.871900393271704e-05 tokens_per_second_per_gpu:780.4934182710126 +Step 4618 | loss:2.0142550468444824 lr:7.868055831035276e-05 tokens_per_second_per_gpu:777.5898263779376 +Step 4619 | loss:2.0146284103393555 lr:7.864211598890478e-05 tokens_per_second_per_gpu:764.7258178733869 +Step 4620 | loss:1.9800387620925903 lr:7.860367697432518e-05 tokens_per_second_per_gpu:776.8324921089397 +Step 4621 | loss:2.011336326599121 lr:7.856524127256548e-05 tokens_per_second_per_gpu:762.6322175269748 +Step 4622 | loss:2.0586307048797607 lr:7.852680888957673e-05 tokens_per_second_per_gpu:784.0316096019584 +Step 4623 | loss:2.0060791969299316 lr:7.848837983130951e-05 tokens_per_second_per_gpu:781.9126164040628 +Step 4624 | loss:2.019670009613037 lr:7.844995410371381e-05 tokens_per_second_per_gpu:769.8567050983737 +Step 4625 | loss:2.040975332260132 lr:7.841153171273914e-05 tokens_per_second_per_gpu:808.7948877598898 +Step 4626 | loss:1.991462230682373 lr:7.837311266433452e-05 tokens_per_second_per_gpu:778.3165596875841 +Step 4627 | loss:2.0475988388061523 lr:7.833469696444833e-05 tokens_per_second_per_gpu:777.5818789516142 +Step 4628 | loss:2.0057520866394043 lr:7.829628461902858e-05 tokens_per_second_per_gpu:792.518180229489 +Step 4629 | loss:1.9924753904342651 lr:7.825787563402273e-05 tokens_per_second_per_gpu:791.7859233836646 +Step 4630 | loss:2.016221046447754 lr:7.821947001537766e-05 tokens_per_second_per_gpu:784.3075636091613 +Step 4631 | loss:2.071423053741455 lr:7.818106776903977e-05 tokens_per_second_per_gpu:755.0695221726443 +Step 4632 | loss:1.9977738857269287 lr:7.814266890095494e-05 tokens_per_second_per_gpu:761.0523830837742 +Step 4633 | loss:1.956131935119629 lr:7.810427341706844e-05 tokens_per_second_per_gpu:775.9031244871912 +Step 4634 | loss:2.034677743911743 lr:7.806588132332517e-05 tokens_per_second_per_gpu:786.5396419256009 +Step 4635 | loss:2.027233839035034 lr:7.802749262566944e-05 tokens_per_second_per_gpu:756.1196586714979 +Step 4636 | loss:1.993596076965332 lr:7.798910733004496e-05 tokens_per_second_per_gpu:751.4335117725695 +Step 4637 | loss:2.063812255859375 lr:7.795072544239502e-05 tokens_per_second_per_gpu:783.6027277683559 +Step 4638 | loss:2.035518169403076 lr:7.791234696866233e-05 tokens_per_second_per_gpu:772.0513969205157 +Step 4639 | loss:2.040458917617798 lr:7.787397191478901e-05 tokens_per_second_per_gpu:768.5168011628488 +Step 4640 | loss:2.0367844104766846 lr:7.783560028671681e-05 tokens_per_second_per_gpu:782.3251526989644 +Step 4641 | loss:1.9763554334640503 lr:7.779723209038683e-05 tokens_per_second_per_gpu:798.7064809086946 +Step 4642 | loss:2.0125279426574707 lr:7.775886733173964e-05 tokens_per_second_per_gpu:751.7667407213871 +Step 4643 | loss:2.0170326232910156 lr:7.772050601671535e-05 tokens_per_second_per_gpu:789.8643667737919 +Step 4644 | loss:2.014516592025757 lr:7.768214815125344e-05 tokens_per_second_per_gpu:787.2759767428511 +Step 4645 | loss:1.9928464889526367 lr:7.764379374129292e-05 tokens_per_second_per_gpu:760.9973909598212 +Step 4646 | loss:2.019195556640625 lr:7.760544279277231e-05 tokens_per_second_per_gpu:772.2587687315448 +Step 4647 | loss:2.064779281616211 lr:7.756709531162948e-05 tokens_per_second_per_gpu:768.6998664046696 +Step 4648 | loss:2.008298873901367 lr:7.752875130380181e-05 tokens_per_second_per_gpu:751.1614091046092 +Step 4649 | loss:2.051208019256592 lr:7.749041077522614e-05 tokens_per_second_per_gpu:777.5049920641005 +Step 4650 | loss:2.0086517333984375 lr:7.745207373183887e-05 tokens_per_second_per_gpu:755.8504643520943 +Step 4651 | loss:2.0293936729431152 lr:7.74137401795757e-05 tokens_per_second_per_gpu:770.4347688228851 +Step 4652 | loss:2.069087266921997 lr:7.737541012437188e-05 tokens_per_second_per_gpu:772.7662638665349 +Step 4653 | loss:2.0363214015960693 lr:7.733708357216213e-05 tokens_per_second_per_gpu:780.7069081570437 +Step 4654 | loss:2.027137517929077 lr:7.729876052888053e-05 tokens_per_second_per_gpu:779.8654277712462 +Step 4655 | loss:2.0924930572509766 lr:7.72604410004607e-05 tokens_per_second_per_gpu:789.592019936832 +Step 4656 | loss:1.995215892791748 lr:7.722212499283578e-05 tokens_per_second_per_gpu:780.1771417305054 +Step 4657 | loss:2.0216176509857178 lr:7.718381251193822e-05 tokens_per_second_per_gpu:768.1717899866591 +Step 4658 | loss:1.9919430017471313 lr:7.714550356370001e-05 tokens_per_second_per_gpu:768.0955278872061 +Step 4659 | loss:1.984379529953003 lr:7.710719815405257e-05 tokens_per_second_per_gpu:783.3411875794485 +Step 4660 | loss:2.0762932300567627 lr:7.706889628892673e-05 tokens_per_second_per_gpu:781.3391020269365 +Step 4661 | loss:2.008669853210449 lr:7.703059797425288e-05 tokens_per_second_per_gpu:768.8214301348863 +Step 4662 | loss:2.043405532836914 lr:7.699230321596079e-05 tokens_per_second_per_gpu:776.4779799581147 +Step 4663 | loss:2.0446605682373047 lr:7.695401201997967e-05 tokens_per_second_per_gpu:773.6870001060279 +Step 4664 | loss:2.031339406967163 lr:7.69157243922382e-05 tokens_per_second_per_gpu:738.9225598619742 +Step 4665 | loss:2.0451126098632812 lr:7.687744033866445e-05 tokens_per_second_per_gpu:755.1874168905649 +Step 4666 | loss:1.9860846996307373 lr:7.683915986518609e-05 tokens_per_second_per_gpu:777.8412346697395 +Step 4667 | loss:2.018077850341797 lr:7.680088297773006e-05 tokens_per_second_per_gpu:790.6882505041201 +Step 4668 | loss:2.0508346557617188 lr:7.676260968222286e-05 tokens_per_second_per_gpu:785.8727657607735 +Step 4669 | loss:2.0020978450775146 lr:7.672433998459035e-05 tokens_per_second_per_gpu:761.0532216641707 +Step 4670 | loss:2.046715021133423 lr:7.668607389075792e-05 tokens_per_second_per_gpu:758.7521935118618 +Step 4671 | loss:2.0177531242370605 lr:7.66478114066503e-05 tokens_per_second_per_gpu:760.672850617059 +Step 4672 | loss:2.018808364868164 lr:7.660955253819178e-05 tokens_per_second_per_gpu:771.7489636205277 +Step 4673 | loss:2.018301486968994 lr:7.657129729130602e-05 tokens_per_second_per_gpu:789.8645802174215 +Step 4674 | loss:2.015213966369629 lr:7.653304567191611e-05 tokens_per_second_per_gpu:770.467965959618 +Step 4675 | loss:1.9572681188583374 lr:7.649479768594459e-05 tokens_per_second_per_gpu:800.052090464642 +Step 4676 | loss:1.9700274467468262 lr:7.645655333931343e-05 tokens_per_second_per_gpu:794.3912188675472 +Step 4677 | loss:2.0558440685272217 lr:7.641831263794412e-05 tokens_per_second_per_gpu:751.6067904420046 +Step 4678 | loss:1.9917323589324951 lr:7.638007558775746e-05 tokens_per_second_per_gpu:734.6548863378324 +Step 4679 | loss:2.0107758045196533 lr:7.634184219467376e-05 tokens_per_second_per_gpu:784.3315721840711 +Step 4680 | loss:1.9930499792099 lr:7.630361246461275e-05 tokens_per_second_per_gpu:776.098780687598 +Step 4681 | loss:2.009436845779419 lr:7.626538640349353e-05 tokens_per_second_per_gpu:761.5285769171654 +Step 4682 | loss:2.009324789047241 lr:7.622716401723476e-05 tokens_per_second_per_gpu:747.8499764483357 +Step 4683 | loss:2.038990020751953 lr:7.618894531175446e-05 tokens_per_second_per_gpu:796.2057990654565 +Step 4684 | loss:1.9906842708587646 lr:7.615073029297003e-05 tokens_per_second_per_gpu:779.277967948541 +Step 4685 | loss:2.0254125595092773 lr:7.61125189667984e-05 tokens_per_second_per_gpu:780.6637567936757 +Step 4686 | loss:1.9972290992736816 lr:7.607431133915586e-05 tokens_per_second_per_gpu:786.374950460723 +Step 4687 | loss:2.032930850982666 lr:7.60361074159581e-05 tokens_per_second_per_gpu:751.0090000406007 +Step 4688 | loss:2.012017250061035 lr:7.599790720312035e-05 tokens_per_second_per_gpu:751.182534174907 +Step 4689 | loss:2.0045394897460938 lr:7.595971070655717e-05 tokens_per_second_per_gpu:772.9910175495662 +Step 4690 | loss:2.004136800765991 lr:7.592151793218257e-05 tokens_per_second_per_gpu:777.2549053792908 +Step 4691 | loss:2.0217480659484863 lr:7.588332888591001e-05 tokens_per_second_per_gpu:776.6839590777804 +Step 4692 | loss:2.022298812866211 lr:7.584514357365229e-05 tokens_per_second_per_gpu:769.2064549033707 +Step 4693 | loss:2.0003652572631836 lr:7.580696200132177e-05 tokens_per_second_per_gpu:789.9917343397931 +Step 4694 | loss:2.0297000408172607 lr:7.576878417483009e-05 tokens_per_second_per_gpu:790.6595200625718 +Step 4695 | loss:2.0328426361083984 lr:7.573061010008839e-05 tokens_per_second_per_gpu:800.9096823966415 +Step 4696 | loss:1.992631196975708 lr:7.569243978300722e-05 tokens_per_second_per_gpu:771.2329593111026 +Step 4697 | loss:1.9872452020645142 lr:7.565427322949654e-05 tokens_per_second_per_gpu:798.234911920152 +Step 4698 | loss:2.03011155128479 lr:7.561611044546567e-05 tokens_per_second_per_gpu:764.1994096263711 +Step 4699 | loss:2.039219856262207 lr:7.557795143682346e-05 tokens_per_second_per_gpu:777.4530349456477 +Step 4700 | loss:2.0135388374328613 lr:7.553979620947815e-05 tokens_per_second_per_gpu:783.0251102482111 +Step 4701 | loss:2.037583827972412 lr:7.550164476933732e-05 tokens_per_second_per_gpu:768.1232937230408 +Step 4702 | loss:2.0333704948425293 lr:7.546349712230798e-05 tokens_per_second_per_gpu:787.6149493139002 +Step 4703 | loss:2.1017327308654785 lr:7.542535327429658e-05 tokens_per_second_per_gpu:786.007445989326 +Step 4704 | loss:2.052651882171631 lr:7.538721323120906e-05 tokens_per_second_per_gpu:725.9165738208209 +Step 4705 | loss:2.0445196628570557 lr:7.534907699895059e-05 tokens_per_second_per_gpu:780.1509207696007 +Step 4706 | loss:1.9738056659698486 lr:7.531094458342593e-05 tokens_per_second_per_gpu:761.7311799008945 +Step 4707 | loss:2.08150315284729 lr:7.527281599053914e-05 tokens_per_second_per_gpu:779.7220668007791 +Step 4708 | loss:1.9947044849395752 lr:7.523469122619368e-05 tokens_per_second_per_gpu:760.1369218356608 +Step 4709 | loss:1.9732036590576172 lr:7.51965702962925e-05 tokens_per_second_per_gpu:768.0130647681439 +Step 4710 | loss:2.051222085952759 lr:7.515845320673793e-05 tokens_per_second_per_gpu:788.9892688558914 +Step 4711 | loss:2.023710250854492 lr:7.512033996343165e-05 tokens_per_second_per_gpu:755.2473635477551 +Step 4712 | loss:1.9996960163116455 lr:7.50822305722748e-05 tokens_per_second_per_gpu:789.777353348371 +Step 4713 | loss:2.0085296630859375 lr:7.504412503916791e-05 tokens_per_second_per_gpu:766.9494066022189 +Step 4714 | loss:2.0519895553588867 lr:7.500602337001086e-05 tokens_per_second_per_gpu:774.2108741617552 +Step 4715 | loss:2.0562283992767334 lr:7.496792557070302e-05 tokens_per_second_per_gpu:801.5429930502544 +Step 4716 | loss:2.0270650386810303 lr:7.492983164714316e-05 tokens_per_second_per_gpu:769.2097949101624 +Step 4717 | loss:2.019613265991211 lr:7.489174160522933e-05 tokens_per_second_per_gpu:777.54250210235 +Step 4718 | loss:2.067697286605835 lr:7.485365545085914e-05 tokens_per_second_per_gpu:781.4877843394139 +Step 4719 | loss:2.0318896770477295 lr:7.481557318992942e-05 tokens_per_second_per_gpu:782.1656973273956 +Step 4720 | loss:1.9954078197479248 lr:7.47774948283366e-05 tokens_per_second_per_gpu:779.2705989099728 +Step 4721 | loss:1.9335529804229736 lr:7.473942037197633e-05 tokens_per_second_per_gpu:783.966044265351 +Step 4722 | loss:2.000317096710205 lr:7.470134982674376e-05 tokens_per_second_per_gpu:750.8616319918524 +Step 4723 | loss:2.00606107711792 lr:7.466328319853338e-05 tokens_per_second_per_gpu:766.0510408296666 +Step 4724 | loss:2.0555081367492676 lr:7.462522049323908e-05 tokens_per_second_per_gpu:789.12223620847 +Step 4725 | loss:2.0379929542541504 lr:7.458716171675421e-05 tokens_per_second_per_gpu:777.4865451723788 +Step 4726 | loss:2.042034864425659 lr:7.454910687497143e-05 tokens_per_second_per_gpu:771.2899034538518 +Step 4727 | loss:2.045180320739746 lr:7.451105597378282e-05 tokens_per_second_per_gpu:783.10744269678 +Step 4728 | loss:2.012968063354492 lr:7.447300901907988e-05 tokens_per_second_per_gpu:758.3009020191771 +Step 4729 | loss:2.0283985137939453 lr:7.443496601675339e-05 tokens_per_second_per_gpu:773.1447912851103 +Step 4730 | loss:2.001370429992676 lr:7.439692697269364e-05 tokens_per_second_per_gpu:779.7048915987602 +Step 4731 | loss:1.9663766622543335 lr:7.43588918927903e-05 tokens_per_second_per_gpu:779.0090970917282 +Step 4732 | loss:2.062753438949585 lr:7.432086078293234e-05 tokens_per_second_per_gpu:756.1810948907979 +Step 4733 | loss:2.042086124420166 lr:7.428283364900821e-05 tokens_per_second_per_gpu:786.07021836456 +Step 4734 | loss:2.02058482170105 lr:7.424481049690566e-05 tokens_per_second_per_gpu:748.330248419915 +Step 4735 | loss:2.014732837677002 lr:7.420679133251185e-05 tokens_per_second_per_gpu:794.7832950316684 +Step 4736 | loss:1.9820740222930908 lr:7.416877616171336e-05 tokens_per_second_per_gpu:767.4662190078675 +Step 4737 | loss:2.0297789573669434 lr:7.413076499039617e-05 tokens_per_second_per_gpu:798.0279389437895 +Step 4738 | loss:2.0219168663024902 lr:7.409275782444551e-05 tokens_per_second_per_gpu:743.0401555665231 +Step 4739 | loss:2.0656731128692627 lr:7.405475466974616e-05 tokens_per_second_per_gpu:785.6931937239779 +Step 4740 | loss:1.9699691534042358 lr:7.401675553218216e-05 tokens_per_second_per_gpu:778.0512164914109 +Step 4741 | loss:2.0316882133483887 lr:7.397876041763694e-05 tokens_per_second_per_gpu:787.4090548754762 +Step 4742 | loss:2.010476589202881 lr:7.394076933199336e-05 tokens_per_second_per_gpu:796.5737823330952 +Step 4743 | loss:2.058178424835205 lr:7.390278228113365e-05 tokens_per_second_per_gpu:786.5620653672767 +Step 4744 | loss:2.065136432647705 lr:7.386479927093935e-05 tokens_per_second_per_gpu:785.43550749027 +Step 4745 | loss:2.000835657119751 lr:7.382682030729146e-05 tokens_per_second_per_gpu:768.6696720243275 +Step 4746 | loss:2.055556535720825 lr:7.378884539607022e-05 tokens_per_second_per_gpu:772.0011521037557 +Step 4747 | loss:1.99934720993042 lr:7.375087454315548e-05 tokens_per_second_per_gpu:780.6535947647031 +Step 4748 | loss:2.015071153640747 lr:7.371290775442621e-05 tokens_per_second_per_gpu:775.5374153212765 +Step 4749 | loss:2.014345407485962 lr:7.36749450357609e-05 tokens_per_second_per_gpu:767.0693560188516 +Step 4750 | loss:2.021721124649048 lr:7.363698639303732e-05 tokens_per_second_per_gpu:755.9969272345783 +Step 4751 | loss:2.015491485595703 lr:7.359903183213269e-05 tokens_per_second_per_gpu:770.351843211551 +Step 4752 | loss:1.9083902835845947 lr:7.356108135892357e-05 tokens_per_second_per_gpu:785.1043404479012 +Step 4753 | loss:1.9856432676315308 lr:7.352313497928584e-05 tokens_per_second_per_gpu:786.5462032545951 +Step 4754 | loss:1.9539076089859009 lr:7.348519269909486e-05 tokens_per_second_per_gpu:756.4050082374009 +Step 4755 | loss:2.040635108947754 lr:7.344725452422523e-05 tokens_per_second_per_gpu:776.2177005471652 +Step 4756 | loss:1.993963599205017 lr:7.340932046055096e-05 tokens_per_second_per_gpu:763.2759299510949 +Step 4757 | loss:2.0302951335906982 lr:7.33713905139454e-05 tokens_per_second_per_gpu:778.6858598926091 +Step 4758 | loss:1.9975541830062866 lr:7.333346469028138e-05 tokens_per_second_per_gpu:786.1159712592678 +Step 4759 | loss:2.0002520084381104 lr:7.329554299543095e-05 tokens_per_second_per_gpu:789.8527671676629 +Step 4760 | loss:1.9786843061447144 lr:7.325762543526558e-05 tokens_per_second_per_gpu:774.0141725867462 +Step 4761 | loss:2.0985934734344482 lr:7.321971201565612e-05 tokens_per_second_per_gpu:787.9163263426984 +Step 4762 | loss:2.040984869003296 lr:7.318180274247266e-05 tokens_per_second_per_gpu:788.7594589736939 +Step 4763 | loss:1.9556689262390137 lr:7.314389762158485e-05 tokens_per_second_per_gpu:777.7243457957524 +Step 4764 | loss:2.0314364433288574 lr:7.310599665886156e-05 tokens_per_second_per_gpu:778.8189138224649 +Step 4765 | loss:2.0258030891418457 lr:7.306809986017101e-05 tokens_per_second_per_gpu:794.5634631388605 +Step 4766 | loss:2.046077013015747 lr:7.303020723138083e-05 tokens_per_second_per_gpu:778.6556951038284 +Step 4767 | loss:2.0117485523223877 lr:7.299231877835797e-05 tokens_per_second_per_gpu:764.5813164095259 +Step 4768 | loss:1.9828455448150635 lr:7.29544345069688e-05 tokens_per_second_per_gpu:771.1518598347017 +Step 4769 | loss:2.004409074783325 lr:7.291655442307892e-05 tokens_per_second_per_gpu:768.6388774570856 +Step 4770 | loss:1.996281385421753 lr:7.287867853255342e-05 tokens_per_second_per_gpu:774.9499630576242 +Step 4771 | loss:2.0630528926849365 lr:7.284080684125661e-05 tokens_per_second_per_gpu:777.1617406121965 +Step 4772 | loss:2.011054515838623 lr:7.280293935505225e-05 tokens_per_second_per_gpu:778.9940310223855 +Step 4773 | loss:2.0448074340820312 lr:7.276507607980336e-05 tokens_per_second_per_gpu:790.7193762425263 +Step 4774 | loss:2.04811692237854 lr:7.272721702137244e-05 tokens_per_second_per_gpu:776.7529037219081 +Step 4775 | loss:1.9680707454681396 lr:7.26893621856212e-05 tokens_per_second_per_gpu:769.2261874322246 +Step 4776 | loss:2.054136037826538 lr:7.26515115784108e-05 tokens_per_second_per_gpu:808.091874454435 +Step 4777 | loss:2.0291295051574707 lr:7.261366520560161e-05 tokens_per_second_per_gpu:771.5099693633144 +Step 4778 | loss:1.9927966594696045 lr:7.257582307305348e-05 tokens_per_second_per_gpu:756.9401219929176 +Step 4779 | loss:1.9781057834625244 lr:7.253798518662561e-05 tokens_per_second_per_gpu:790.2187023676338 +Step 4780 | loss:2.048218011856079 lr:7.250015155217642e-05 tokens_per_second_per_gpu:789.5079186358656 +Step 4781 | loss:2.0080199241638184 lr:7.246232217556377e-05 tokens_per_second_per_gpu:774.0796984095371 +Step 4782 | loss:2.066443681716919 lr:7.242449706264484e-05 tokens_per_second_per_gpu:762.0097265685913 +Step 4783 | loss:2.045478343963623 lr:7.238667621927606e-05 tokens_per_second_per_gpu:798.8914664114675 +Step 4784 | loss:2.01674485206604 lr:7.234885965131337e-05 tokens_per_second_per_gpu:780.7234264903093 +Step 4785 | loss:2.033872604370117 lr:7.231104736461194e-05 tokens_per_second_per_gpu:770.2628493821625 +Step 4786 | loss:1.9750406742095947 lr:7.227323936502627e-05 tokens_per_second_per_gpu:804.073560605959 +Step 4787 | loss:2.0612826347351074 lr:7.223543565841024e-05 tokens_per_second_per_gpu:788.5569431101674 +Step 4788 | loss:2.0298361778259277 lr:7.219763625061707e-05 tokens_per_second_per_gpu:786.1031514107719 +Step 4789 | loss:1.9669122695922852 lr:7.215984114749919e-05 tokens_per_second_per_gpu:773.2300456254144 +Step 4790 | loss:2.033958673477173 lr:7.212205035490855e-05 tokens_per_second_per_gpu:761.9829778132483 +Step 4791 | loss:1.9960963726043701 lr:7.208426387869636e-05 tokens_per_second_per_gpu:794.0930334531622 +Step 4792 | loss:2.017023801803589 lr:7.20464817247131e-05 tokens_per_second_per_gpu:782.3230429026901 +Step 4793 | loss:2.0224697589874268 lr:7.200870389880867e-05 tokens_per_second_per_gpu:780.1550772093686 +Step 4794 | loss:1.9694015979766846 lr:7.197093040683218e-05 tokens_per_second_per_gpu:766.6313378847397 +Step 4795 | loss:2.021198272705078 lr:7.193316125463225e-05 tokens_per_second_per_gpu:771.7668425045595 +Step 4796 | loss:1.996907353401184 lr:7.189539644805668e-05 tokens_per_second_per_gpu:771.9315456133227 +Step 4797 | loss:2.058161735534668 lr:7.185763599295264e-05 tokens_per_second_per_gpu:785.4636553856777 +Step 4798 | loss:1.978672981262207 lr:7.181987989516661e-05 tokens_per_second_per_gpu:706.8093784804773 +Step 4799 | loss:1.986973524093628 lr:7.178212816054446e-05 tokens_per_second_per_gpu:780.0542445438292 +Step 4800 | loss:1.975876808166504 lr:7.174438079493128e-05 tokens_per_second_per_gpu:762.0052867927212 +Step 4801 | loss:2.003166437149048 lr:7.170663780417161e-05 tokens_per_second_per_gpu:795.4822895995965 +Step 4802 | loss:1.9973965883255005 lr:7.166889919410919e-05 tokens_per_second_per_gpu:799.292832179933 +Step 4803 | loss:2.005861520767212 lr:7.163116497058719e-05 tokens_per_second_per_gpu:791.7449063145082 +Step 4804 | loss:1.9919734001159668 lr:7.159343513944801e-05 tokens_per_second_per_gpu:772.3484578401403 +Step 4805 | loss:2.0203235149383545 lr:7.155570970653338e-05 tokens_per_second_per_gpu:780.9969915468221 +Step 4806 | loss:2.042410135269165 lr:7.151798867768444e-05 tokens_per_second_per_gpu:795.612410652307 +Step 4807 | loss:2.0112721920013428 lr:7.148027205874157e-05 tokens_per_second_per_gpu:746.9552772569637 +Step 4808 | loss:2.0173940658569336 lr:7.144255985554446e-05 tokens_per_second_per_gpu:761.2478473506646 +Step 4809 | loss:1.9806599617004395 lr:7.140485207393217e-05 tokens_per_second_per_gpu:781.1764695375842 +Step 4810 | loss:2.011636734008789 lr:7.136714871974296e-05 tokens_per_second_per_gpu:795.2317373533377 +Step 4811 | loss:1.9728690385818481 lr:7.132944979881459e-05 tokens_per_second_per_gpu:751.3687591999801 +Step 4812 | loss:2.0696020126342773 lr:7.129175531698401e-05 tokens_per_second_per_gpu:764.3875298295452 +Step 4813 | loss:2.0523366928100586 lr:7.125406528008747e-05 tokens_per_second_per_gpu:775.714108745803 +Step 4814 | loss:2.0271172523498535 lr:7.121637969396059e-05 tokens_per_second_per_gpu:778.6854083467479 +Step 4815 | loss:2.0298757553100586 lr:7.117869856443827e-05 tokens_per_second_per_gpu:801.0326081719306 +Step 4816 | loss:2.0162582397460938 lr:7.11410218973547e-05 tokens_per_second_per_gpu:789.1134356690725 +Step 4817 | loss:1.97479248046875 lr:7.110334969854344e-05 tokens_per_second_per_gpu:793.9805151630964 +Step 4818 | loss:1.9694803953170776 lr:7.106568197383734e-05 tokens_per_second_per_gpu:772.3050298753068 +Step 4819 | loss:2.084775924682617 lr:7.102801872906852e-05 tokens_per_second_per_gpu:763.8191832354934 +Step 4820 | loss:2.0086684226989746 lr:7.099035997006842e-05 tokens_per_second_per_gpu:795.3793243711247 +Step 4821 | loss:1.9792964458465576 lr:7.095270570266779e-05 tokens_per_second_per_gpu:798.6184331549176 +Step 4822 | loss:2.039156436920166 lr:7.091505593269671e-05 tokens_per_second_per_gpu:771.531385730955 +Step 4823 | loss:1.978938341140747 lr:7.087741066598453e-05 tokens_per_second_per_gpu:800.8454070305996 +Step 4824 | loss:1.9734241962432861 lr:7.083976990835994e-05 tokens_per_second_per_gpu:788.3623949039021 +Step 4825 | loss:2.0144693851470947 lr:7.080213366565084e-05 tokens_per_second_per_gpu:727.6821875210517 +Step 4826 | loss:2.090754747390747 lr:7.076450194368455e-05 tokens_per_second_per_gpu:756.4994859291278 +Step 4827 | loss:1.9913392066955566 lr:7.072687474828765e-05 tokens_per_second_per_gpu:765.184634698918 +Step 4828 | loss:1.9448413848876953 lr:7.068925208528598e-05 tokens_per_second_per_gpu:768.7705622813115 +Step 4829 | loss:2.050050735473633 lr:7.065163396050471e-05 tokens_per_second_per_gpu:768.3052274188449 +Step 4830 | loss:1.9896180629730225 lr:7.06140203797683e-05 tokens_per_second_per_gpu:742.994477425495 +Step 4831 | loss:2.0536444187164307 lr:7.05764113489005e-05 tokens_per_second_per_gpu:748.7774822568146 +Step 4832 | loss:2.097039222717285 lr:7.053880687372435e-05 tokens_per_second_per_gpu:763.5099676375537 +Step 4833 | loss:2.036630630493164 lr:7.050120696006226e-05 tokens_per_second_per_gpu:785.1686751146415 +Step 4834 | loss:1.993769884109497 lr:7.046361161373585e-05 tokens_per_second_per_gpu:778.9226597000688 +Step 4835 | loss:2.00785756111145 lr:7.0426020840566e-05 tokens_per_second_per_gpu:767.7056945001196 +Step 4836 | loss:2.014190196990967 lr:7.038843464637302e-05 tokens_per_second_per_gpu:771.0925011139914 +Step 4837 | loss:2.0114989280700684 lr:7.035085303697632e-05 tokens_per_second_per_gpu:795.1642012516807 +Step 4838 | loss:2.0188050270080566 lr:7.03132760181948e-05 tokens_per_second_per_gpu:787.0963207420301 +Step 4839 | loss:1.970815896987915 lr:7.027570359584657e-05 tokens_per_second_per_gpu:780.912154482181 +Step 4840 | loss:2.0296154022216797 lr:7.023813577574893e-05 tokens_per_second_per_gpu:775.0038172741805 +Step 4841 | loss:2.0635247230529785 lr:7.020057256371863e-05 tokens_per_second_per_gpu:790.715920134911 +Step 4842 | loss:2.065009355545044 lr:7.016301396557156e-05 tokens_per_second_per_gpu:776.7487938582591 +Step 4843 | loss:2.0420491695404053 lr:7.012545998712308e-05 tokens_per_second_per_gpu:762.1464742132839 +Step 4844 | loss:2.0048625469207764 lr:7.008791063418759e-05 tokens_per_second_per_gpu:784.2133570080603 +Step 4845 | loss:2.054471015930176 lr:7.005036591257899e-05 tokens_per_second_per_gpu:770.2091155567981 +Step 4846 | loss:2.0572829246520996 lr:7.001282582811033e-05 tokens_per_second_per_gpu:756.0407820828844 +Step 4847 | loss:1.969512939453125 lr:6.997529038659402e-05 tokens_per_second_per_gpu:768.015944786686 +Step 4848 | loss:2.010901927947998 lr:6.993775959384167e-05 tokens_per_second_per_gpu:765.7601377722814 +Step 4849 | loss:2.0613327026367188 lr:6.990023345566431e-05 tokens_per_second_per_gpu:797.6679709758009 +Step 4850 | loss:2.0170998573303223 lr:6.986271197787207e-05 tokens_per_second_per_gpu:793.9519338838807 +Step 4851 | loss:1.9894938468933105 lr:6.982519516627453e-05 tokens_per_second_per_gpu:772.3627906548481 +Step 4852 | loss:2.0210466384887695 lr:6.978768302668037e-05 tokens_per_second_per_gpu:778.5522184117815 +Step 4853 | loss:2.0056400299072266 lr:6.975017556489769e-05 tokens_per_second_per_gpu:781.5022166932682 +Step 4854 | loss:2.0001609325408936 lr:6.971267278673386e-05 tokens_per_second_per_gpu:771.3500276820569 +Step 4855 | loss:2.06964111328125 lr:6.967517469799545e-05 tokens_per_second_per_gpu:768.12038771261 +Step 4856 | loss:1.9807374477386475 lr:6.96376813044883e-05 tokens_per_second_per_gpu:785.5530042770638 +Step 4857 | loss:2.0453925132751465 lr:6.960019261201761e-05 tokens_per_second_per_gpu:784.541230535733 +Step 4858 | loss:2.007999897003174 lr:6.956270862638778e-05 tokens_per_second_per_gpu:774.898723734502 +Step 4859 | loss:2.0188517570495605 lr:6.952522935340246e-05 tokens_per_second_per_gpu:764.1080367112967 +Step 4860 | loss:2.004037618637085 lr:6.948775479886471e-05 tokens_per_second_per_gpu:775.8419936384931 +Step 4861 | loss:2.0137126445770264 lr:6.945028496857672e-05 tokens_per_second_per_gpu:785.0466610923155 +Step 4862 | loss:2.061347484588623 lr:6.941281986833996e-05 tokens_per_second_per_gpu:754.1599075785288 +Step 4863 | loss:2.054133653640747 lr:6.937535950395526e-05 tokens_per_second_per_gpu:784.5199269532768 +Step 4864 | loss:2.074101448059082 lr:6.933790388122256e-05 tokens_per_second_per_gpu:764.0610295627714 +Step 4865 | loss:2.0233306884765625 lr:6.930045300594123e-05 tokens_per_second_per_gpu:735.7775077771958 +Step 4866 | loss:1.9852795600891113 lr:6.926300688390987e-05 tokens_per_second_per_gpu:785.0220349615425 +Step 4867 | loss:2.014397144317627 lr:6.922556552092625e-05 tokens_per_second_per_gpu:772.4003408950804 +Step 4868 | loss:2.0461955070495605 lr:6.918812892278749e-05 tokens_per_second_per_gpu:792.4752459250534 +Step 4869 | loss:1.99655282497406 lr:6.91506970952899e-05 tokens_per_second_per_gpu:740.6436708684209 +Step 4870 | loss:1.9627635478973389 lr:6.911327004422917e-05 tokens_per_second_per_gpu:762.2080339426955 +Step 4871 | loss:1.9723669290542603 lr:6.907584777540013e-05 tokens_per_second_per_gpu:774.5134561144984 +Step 4872 | loss:1.978621482849121 lr:6.903843029459696e-05 tokens_per_second_per_gpu:777.152122226833 +Step 4873 | loss:2.029183864593506 lr:6.9001017607613e-05 tokens_per_second_per_gpu:770.5738539730967 +Step 4874 | loss:2.043004274368286 lr:6.896360972024094e-05 tokens_per_second_per_gpu:764.6019547111962 +Step 4875 | loss:1.9652289152145386 lr:6.892620663827265e-05 tokens_per_second_per_gpu:750.0373116552863 +Step 4876 | loss:2.0616393089294434 lr:6.888880836749938e-05 tokens_per_second_per_gpu:768.4699189698398 +Step 4877 | loss:2.0414154529571533 lr:6.885141491371147e-05 tokens_per_second_per_gpu:767.0467738984236 +Step 4878 | loss:2.0354251861572266 lr:6.881402628269864e-05 tokens_per_second_per_gpu:765.8779613212105 +Step 4879 | loss:2.033482789993286 lr:6.87766424802498e-05 tokens_per_second_per_gpu:775.3395659582397 +Step 4880 | loss:1.9765856266021729 lr:6.873926351215312e-05 tokens_per_second_per_gpu:774.9819246930807 +Step 4881 | loss:2.047203540802002 lr:6.870188938419608e-05 tokens_per_second_per_gpu:778.949389682475 +Step 4882 | loss:1.96723473072052 lr:6.866452010216533e-05 tokens_per_second_per_gpu:781.5497033644857 +Step 4883 | loss:2.033830404281616 lr:6.862715567184681e-05 tokens_per_second_per_gpu:787.4295869503956 +Step 4884 | loss:2.018803358078003 lr:6.858979609902571e-05 tokens_per_second_per_gpu:786.3598041451016 +Step 4885 | loss:2.0343542098999023 lr:6.855244138948639e-05 tokens_per_second_per_gpu:776.7692761992744 +Step 4886 | loss:2.0221049785614014 lr:6.851509154901264e-05 tokens_per_second_per_gpu:791.4282815277974 +Step 4887 | loss:2.02652645111084 lr:6.847774658338733e-05 tokens_per_second_per_gpu:786.2140850014531 +Step 4888 | loss:1.9674136638641357 lr:6.844040649839263e-05 tokens_per_second_per_gpu:794.2849817578415 +Step 4889 | loss:2.0017685890197754 lr:6.840307129980996e-05 tokens_per_second_per_gpu:769.7801874888382 +Step 4890 | loss:1.9570558071136475 lr:6.836574099341997e-05 tokens_per_second_per_gpu:785.4997136210482 +Step 4891 | loss:1.9878308773040771 lr:6.832841558500251e-05 tokens_per_second_per_gpu:772.9559198717701 +Step 4892 | loss:2.0095744132995605 lr:6.829109508033679e-05 tokens_per_second_per_gpu:781.9006886478105 +Step 4893 | loss:2.072331666946411 lr:6.82537794852012e-05 tokens_per_second_per_gpu:749.4190335416718 +Step 4894 | loss:2.0334980487823486 lr:6.821646880537332e-05 tokens_per_second_per_gpu:785.0570817744714 +Step 4895 | loss:2.053443670272827 lr:6.817916304663002e-05 tokens_per_second_per_gpu:785.40053758466 +Step 4896 | loss:2.0742597579956055 lr:6.814186221474735e-05 tokens_per_second_per_gpu:775.8712317806936 +Step 4897 | loss:1.9519555568695068 lr:6.810456631550076e-05 tokens_per_second_per_gpu:774.4617565156035 +Step 4898 | loss:2.040288209915161 lr:6.806727535466473e-05 tokens_per_second_per_gpu:792.1825188511913 +Step 4899 | loss:2.0653247833251953 lr:6.80299893380131e-05 tokens_per_second_per_gpu:789.552611404635 +Step 4900 | loss:1.9888036251068115 lr:6.79927082713189e-05 tokens_per_second_per_gpu:773.9924582450958 +Step 4901 | loss:2.02897310256958 lr:6.795543216035437e-05 tokens_per_second_per_gpu:778.3944082181432 +Step 4902 | loss:2.0475430488586426 lr:6.791816101089111e-05 tokens_per_second_per_gpu:770.0244326564684 +Step 4903 | loss:2.0080456733703613 lr:6.78808948286998e-05 tokens_per_second_per_gpu:770.4036035827575 +Step 4904 | loss:2.013681411743164 lr:6.78436336195504e-05 tokens_per_second_per_gpu:779.046663819165 +Step 4905 | loss:1.995286464691162 lr:6.780637738921216e-05 tokens_per_second_per_gpu:764.3089798411436 +Step 4906 | loss:2.0470597743988037 lr:6.776912614345344e-05 tokens_per_second_per_gpu:786.4699407743254 +Step 4907 | loss:2.0450279712677 lr:6.773187988804192e-05 tokens_per_second_per_gpu:778.1602666253341 +Step 4908 | loss:1.9863512516021729 lr:6.769463862874454e-05 tokens_per_second_per_gpu:775.0774757463003 +Step 4909 | loss:1.9851157665252686 lr:6.765740237132736e-05 tokens_per_second_per_gpu:798.204097313503 +Step 4910 | loss:2.0003039836883545 lr:6.762017112155572e-05 tokens_per_second_per_gpu:776.7626584649955 +Step 4911 | loss:1.9787153005599976 lr:6.758294488519421e-05 tokens_per_second_per_gpu:787.753144738 +Step 4912 | loss:2.0279014110565186 lr:6.754572366800656e-05 tokens_per_second_per_gpu:746.8797295243356 +Step 4913 | loss:1.9868838787078857 lr:6.750850747575581e-05 tokens_per_second_per_gpu:799.4297978832574 +Step 4914 | loss:1.9883657693862915 lr:6.747129631420423e-05 tokens_per_second_per_gpu:766.9363278897679 +Step 4915 | loss:2.061992883682251 lr:6.743409018911324e-05 tokens_per_second_per_gpu:738.6447344564081 +Step 4916 | loss:2.013749122619629 lr:6.73968891062435e-05 tokens_per_second_per_gpu:780.1393267420573 +Step 4917 | loss:2.01491641998291 lr:6.73596930713549e-05 tokens_per_second_per_gpu:770.1157472735114 +Step 4918 | loss:2.0375514030456543 lr:6.732250209020653e-05 tokens_per_second_per_gpu:760.4157928753966 +Step 4919 | loss:2.056001663208008 lr:6.728531616855677e-05 tokens_per_second_per_gpu:783.2229074008684 +Step 4920 | loss:1.9983118772506714 lr:6.724813531216316e-05 tokens_per_second_per_gpu:789.6118120077031 +Step 4921 | loss:2.036027669906616 lr:6.72109595267824e-05 tokens_per_second_per_gpu:782.3320563842233 +Step 4922 | loss:2.013298988342285 lr:6.717378881817053e-05 tokens_per_second_per_gpu:799.9107534515015 +Step 4923 | loss:1.9791443347930908 lr:6.713662319208267e-05 tokens_per_second_per_gpu:762.8256804159258 +Step 4924 | loss:1.9765994548797607 lr:6.709946265427332e-05 tokens_per_second_per_gpu:787.8170971097691 +Step 4925 | loss:2.0278701782226562 lr:6.7062307210496e-05 tokens_per_second_per_gpu:758.2453146810834 +Step 4926 | loss:2.1008872985839844 lr:6.702515686650358e-05 tokens_per_second_per_gpu:776.026951678936 +Step 4927 | loss:2.0250065326690674 lr:6.698801162804807e-05 tokens_per_second_per_gpu:789.9488941443087 +Step 4928 | loss:2.0405209064483643 lr:6.695087150088071e-05 tokens_per_second_per_gpu:786.50510924322 +Step 4929 | loss:1.984710931777954 lr:6.691373649075203e-05 tokens_per_second_per_gpu:790.6839718997991 +Step 4930 | loss:2.021897077560425 lr:6.68766066034116e-05 tokens_per_second_per_gpu:774.0657107222635 +Step 4931 | loss:2.0508522987365723 lr:6.683948184460834e-05 tokens_per_second_per_gpu:774.7250434571786 +Step 4932 | loss:2.074441432952881 lr:6.680236222009028e-05 tokens_per_second_per_gpu:746.4970541451999 +Step 4933 | loss:1.980512022972107 lr:6.676524773560472e-05 tokens_per_second_per_gpu:782.8903617679272 +Step 4934 | loss:2.0138511657714844 lr:6.672813839689814e-05 tokens_per_second_per_gpu:787.183179948581 +Step 4935 | loss:2.010631561279297 lr:6.669103420971625e-05 tokens_per_second_per_gpu:759.7419066246177 +Step 4936 | loss:1.9993456602096558 lr:6.665393517980394e-05 tokens_per_second_per_gpu:765.7443205115896 +Step 4937 | loss:2.0655078887939453 lr:6.661684131290525e-05 tokens_per_second_per_gpu:770.2220462534996 +Step 4938 | loss:2.0042834281921387 lr:6.657975261476352e-05 tokens_per_second_per_gpu:774.8820113467863 +Step 4939 | loss:1.984715223312378 lr:6.654266909112119e-05 tokens_per_second_per_gpu:804.252299876703 +Step 4940 | loss:2.0492396354675293 lr:6.650559074772e-05 tokens_per_second_per_gpu:789.2376061849918 +Step 4941 | loss:2.078713893890381 lr:6.646851759030082e-05 tokens_per_second_per_gpu:780.4720937409662 +Step 4942 | loss:2.0132899284362793 lr:6.643144962460374e-05 tokens_per_second_per_gpu:801.0221671953366 +Step 4943 | loss:2.023455858230591 lr:6.639438685636803e-05 tokens_per_second_per_gpu:783.1799862646342 +Step 4944 | loss:1.947892189025879 lr:6.635732929133213e-05 tokens_per_second_per_gpu:777.5794855950586 +Step 4945 | loss:1.9957314729690552 lr:6.63202769352338e-05 tokens_per_second_per_gpu:752.4869100976621 +Step 4946 | loss:2.0695414543151855 lr:6.628322979380982e-05 tokens_per_second_per_gpu:771.3356062315117 +Step 4947 | loss:2.0231730937957764 lr:6.62461878727963e-05 tokens_per_second_per_gpu:778.5528882324231 +Step 4948 | loss:2.0586328506469727 lr:6.620915117792844e-05 tokens_per_second_per_gpu:762.7850778731887 +Step 4949 | loss:2.0424280166625977 lr:6.617211971494072e-05 tokens_per_second_per_gpu:786.3252845195559 +Step 4950 | loss:2.0412681102752686 lr:6.613509348956672e-05 tokens_per_second_per_gpu:762.1834061248825 +Step 4951 | loss:2.093738555908203 lr:6.609807250753935e-05 tokens_per_second_per_gpu:769.5447483012164 +Step 4952 | loss:1.974902868270874 lr:6.60610567745905e-05 tokens_per_second_per_gpu:776.9420137103197 +Step 4953 | loss:2.0202159881591797 lr:6.602404629645146e-05 tokens_per_second_per_gpu:789.1183428147264 +Step 4954 | loss:1.9756321907043457 lr:6.598704107885254e-05 tokens_per_second_per_gpu:778.0953433660001 +Step 4955 | loss:2.0231199264526367 lr:6.59500411275233e-05 tokens_per_second_per_gpu:786.5791065845011 +Step 4956 | loss:2.003661870956421 lr:6.591304644819259e-05 tokens_per_second_per_gpu:769.5863644331005 +Step 4957 | loss:2.0226123332977295 lr:6.587605704658826e-05 tokens_per_second_per_gpu:763.7875853232247 +Step 4958 | loss:1.9431402683258057 lr:6.583907292843742e-05 tokens_per_second_per_gpu:770.2378172005892 +Step 4959 | loss:2.0617787837982178 lr:6.580209409946641e-05 tokens_per_second_per_gpu:798.31102505347 +Step 4960 | loss:2.0194718837738037 lr:6.576512056540067e-05 tokens_per_second_per_gpu:791.815316412802 +Step 4961 | loss:1.9888861179351807 lr:6.572815233196486e-05 tokens_per_second_per_gpu:763.1462081889983 +Step 4962 | loss:2.0005605220794678 lr:6.569118940488288e-05 tokens_per_second_per_gpu:767.5752811203309 +Step 4963 | loss:2.0144381523132324 lr:6.56542317898777e-05 tokens_per_second_per_gpu:783.1856975553213 +Step 4964 | loss:2.0371737480163574 lr:6.56172794926715e-05 tokens_per_second_per_gpu:775.4810653857579 +Step 4965 | loss:1.9937193393707275 lr:6.558033251898569e-05 tokens_per_second_per_gpu:777.5819917253748 +Step 4966 | loss:2.0251474380493164 lr:6.554339087454076e-05 tokens_per_second_per_gpu:792.8161341508327 +Step 4967 | loss:2.0437443256378174 lr:6.550645456505647e-05 tokens_per_second_per_gpu:767.5244098975822 +Step 4968 | loss:2.0147576332092285 lr:6.546952359625176e-05 tokens_per_second_per_gpu:757.9255987021089 +Step 4969 | loss:2.072542667388916 lr:6.543259797384463e-05 tokens_per_second_per_gpu:772.3328749777532 +Step 4970 | loss:2.001598834991455 lr:6.539567770355234e-05 tokens_per_second_per_gpu:760.1140953009699 +Step 4971 | loss:1.9797487258911133 lr:6.535876279109127e-05 tokens_per_second_per_gpu:762.5161269726693 +Step 4972 | loss:2.0675246715545654 lr:6.53218532421771e-05 tokens_per_second_per_gpu:778.4175896512194 +Step 4973 | loss:2.0563762187957764 lr:6.528494906252449e-05 tokens_per_second_per_gpu:789.7753970649538 +Step 4974 | loss:1.9705677032470703 lr:6.524805025784741e-05 tokens_per_second_per_gpu:752.649382870378 +Step 4975 | loss:2.0705156326293945 lr:6.521115683385892e-05 tokens_per_second_per_gpu:760.9471132650889 +Step 4976 | loss:1.9817070960998535 lr:6.517426879627132e-05 tokens_per_second_per_gpu:781.9886984815727 +Step 4977 | loss:2.02565860748291 lr:6.513738615079595e-05 tokens_per_second_per_gpu:766.1970513693734 +Step 4978 | loss:2.009550094604492 lr:6.510050890314347e-05 tokens_per_second_per_gpu:759.0371675515493 +Step 4979 | loss:2.0324625968933105 lr:6.50636370590236e-05 tokens_per_second_per_gpu:754.2736268626201 +Step 4980 | loss:2.0093493461608887 lr:6.502677062414528e-05 tokens_per_second_per_gpu:790.0995556410195 +Step 4981 | loss:2.005842685699463 lr:6.498990960421654e-05 tokens_per_second_per_gpu:775.3977141934425 +Step 4982 | loss:2.0369856357574463 lr:6.495305400494464e-05 tokens_per_second_per_gpu:779.6199058569226 +Step 4983 | loss:2.0323243141174316 lr:6.491620383203602e-05 tokens_per_second_per_gpu:788.9393542632301 +Step 4984 | loss:2.0372188091278076 lr:6.487935909119622e-05 tokens_per_second_per_gpu:771.0381547780648 +Step 4985 | loss:1.9519768953323364 lr:6.484251978812992e-05 tokens_per_second_per_gpu:777.4169018541274 +Step 4986 | loss:1.9919202327728271 lr:6.480568592854103e-05 tokens_per_second_per_gpu:786.8492005427082 +Step 4987 | loss:2.031963348388672 lr:6.476885751813255e-05 tokens_per_second_per_gpu:765.1921365077596 +Step 4988 | loss:1.961049199104309 lr:6.47320345626067e-05 tokens_per_second_per_gpu:763.211431626818 +Step 4989 | loss:1.9419623613357544 lr:6.469521706766483e-05 tokens_per_second_per_gpu:797.0095577799716 +Step 4990 | loss:2.027284860610962 lr:6.465840503900746e-05 tokens_per_second_per_gpu:761.2329752756244 +Step 4991 | loss:2.0107688903808594 lr:6.462159848233417e-05 tokens_per_second_per_gpu:789.3802829290272 +Step 4992 | loss:1.9869235754013062 lr:6.458479740334383e-05 tokens_per_second_per_gpu:786.5798090333409 +Step 4993 | loss:1.9678696393966675 lr:6.454800180773432e-05 tokens_per_second_per_gpu:779.9678625183614 +Step 4994 | loss:1.9811034202575684 lr:6.451121170120284e-05 tokens_per_second_per_gpu:793.32435082793 +Step 4995 | loss:2.024700164794922 lr:6.447442708944564e-05 tokens_per_second_per_gpu:763.8969009644343 +Step 4996 | loss:2.0472252368927 lr:6.44376479781581e-05 tokens_per_second_per_gpu:769.2014862439978 +Step 4997 | loss:1.9843984842300415 lr:6.440087437303474e-05 tokens_per_second_per_gpu:760.7841615276425 +Step 4998 | loss:2.0329596996307373 lr:6.43641062797693e-05 tokens_per_second_per_gpu:740.6556468860383 +Step 4999 | loss:1.9758198261260986 lr:6.432734370405467e-05 tokens_per_second_per_gpu:777.5957611298977 +Step 5000 | loss:2.0373048782348633 lr:6.429058665158279e-05 tokens_per_second_per_gpu:771.7618592592574 +Step 5001 | loss:1.9173169136047363 lr:6.425383512804484e-05 tokens_per_second_per_gpu:795.9340046906563 +Step 5002 | loss:2.0365548133850098 lr:6.421708913913107e-05 tokens_per_second_per_gpu:748.1131043812131 +Step 5003 | loss:2.0123777389526367 lr:6.418034869053089e-05 tokens_per_second_per_gpu:784.9416491571155 +Step 5004 | loss:2.0737171173095703 lr:6.414361378793294e-05 tokens_per_second_per_gpu:776.451519475107 +Step 5005 | loss:1.9851675033569336 lr:6.410688443702492e-05 tokens_per_second_per_gpu:774.2866414613304 +Step 5006 | loss:2.038922071456909 lr:6.407016064349363e-05 tokens_per_second_per_gpu:767.3455408421515 +Step 5007 | loss:1.996429443359375 lr:6.40334424130251e-05 tokens_per_second_per_gpu:793.0221822597708 +Step 5008 | loss:1.976952314376831 lr:6.399672975130444e-05 tokens_per_second_per_gpu:805.3747918612678 +Step 5009 | loss:1.9773967266082764 lr:6.396002266401589e-05 tokens_per_second_per_gpu:794.4175511725475 +Step 5010 | loss:2.048602819442749 lr:6.392332115684296e-05 tokens_per_second_per_gpu:788.2587931066075 +Step 5011 | loss:1.9913346767425537 lr:6.388662523546811e-05 tokens_per_second_per_gpu:796.2151365755846 +Step 5012 | loss:1.9917510747909546 lr:6.3849934905573e-05 tokens_per_second_per_gpu:750.0317318128352 +Step 5013 | loss:2.0400197505950928 lr:6.381325017283851e-05 tokens_per_second_per_gpu:784.7962780292429 +Step 5014 | loss:1.994964599609375 lr:6.37765710429445e-05 tokens_per_second_per_gpu:763.9155266631724 +Step 5015 | loss:2.0286264419555664 lr:6.37398975215701e-05 tokens_per_second_per_gpu:768.1682310636486 +Step 5016 | loss:2.0197041034698486 lr:6.370322961439355e-05 tokens_per_second_per_gpu:786.2596538954722 +Step 5017 | loss:2.0476601123809814 lr:6.366656732709213e-05 tokens_per_second_per_gpu:758.9925003614202 +Step 5018 | loss:2.0635507106781006 lr:6.362991066534231e-05 tokens_per_second_per_gpu:747.7584535289586 +Step 5019 | loss:2.0221636295318604 lr:6.359325963481972e-05 tokens_per_second_per_gpu:797.8342161898103 +Step 5020 | loss:2.0008459091186523 lr:6.355661424119905e-05 tokens_per_second_per_gpu:783.4417830381166 +Step 5021 | loss:2.0345261096954346 lr:6.351997449015418e-05 tokens_per_second_per_gpu:776.8663645300013 +Step 5022 | loss:2.009760856628418 lr:6.34833403873581e-05 tokens_per_second_per_gpu:789.4700425893503 +Step 5023 | loss:2.049417018890381 lr:6.34467119384829e-05 tokens_per_second_per_gpu:774.312651155892 +Step 5024 | loss:2.042370080947876 lr:6.341008914919979e-05 tokens_per_second_per_gpu:781.7734231740284 +Step 5025 | loss:2.042279005050659 lr:6.337347202517911e-05 tokens_per_second_per_gpu:728.6869903202316 +Step 5026 | loss:2.0437564849853516 lr:6.33368605720904e-05 tokens_per_second_per_gpu:780.0097783948372 +Step 5027 | loss:2.0079164505004883 lr:6.330025479560223e-05 tokens_per_second_per_gpu:765.9864091497658 +Step 5028 | loss:2.045205593109131 lr:6.326365470138231e-05 tokens_per_second_per_gpu:762.5012449307833 +Step 5029 | loss:2.0352180004119873 lr:6.322706029509746e-05 tokens_per_second_per_gpu:757.4016451329305 +Step 5030 | loss:2.010209321975708 lr:6.319047158241367e-05 tokens_per_second_per_gpu:790.3919281957217 +Step 5031 | loss:2.0103015899658203 lr:6.3153888568996e-05 tokens_per_second_per_gpu:753.9445109632567 +Step 5032 | loss:2.0642595291137695 lr:6.311731126050866e-05 tokens_per_second_per_gpu:771.9848293444657 +Step 5033 | loss:2.066718578338623 lr:6.308073966261496e-05 tokens_per_second_per_gpu:773.3962874894941 +Step 5034 | loss:2.034388542175293 lr:6.304417378097731e-05 tokens_per_second_per_gpu:776.3560767470422 +Step 5035 | loss:2.074857711791992 lr:6.300761362125727e-05 tokens_per_second_per_gpu:737.0342454755753 +Step 5036 | loss:2.0186171531677246 lr:6.297105918911545e-05 tokens_per_second_per_gpu:757.552653477846 +Step 5037 | loss:2.056760787963867 lr:6.293451049021168e-05 tokens_per_second_per_gpu:759.4015588326059 +Step 5038 | loss:1.9883546829223633 lr:6.289796753020484e-05 tokens_per_second_per_gpu:769.2324445289469 +Step 5039 | loss:1.9504058361053467 lr:6.286143031475289e-05 tokens_per_second_per_gpu:787.3886866012735 +Step 5040 | loss:2.039989471435547 lr:6.282489884951295e-05 tokens_per_second_per_gpu:789.065874871819 +Step 5041 | loss:1.9957200288772583 lr:6.278837314014119e-05 tokens_per_second_per_gpu:770.941674056886 +Step 5042 | loss:2.007505178451538 lr:6.2751853192293e-05 tokens_per_second_per_gpu:738.7399103727619 +Step 5043 | loss:1.9907996654510498 lr:6.271533901162278e-05 tokens_per_second_per_gpu:786.3946002221038 +Step 5044 | loss:2.0606253147125244 lr:6.267883060378409e-05 tokens_per_second_per_gpu:769.9372956855703 +Step 5045 | loss:1.975369930267334 lr:6.264232797442952e-05 tokens_per_second_per_gpu:783.345120481963 +Step 5046 | loss:1.971022129058838 lr:6.260583112921082e-05 tokens_per_second_per_gpu:769.906638026156 +Step 5047 | loss:2.0332725048065186 lr:6.256934007377893e-05 tokens_per_second_per_gpu:769.8439735727935 +Step 5048 | loss:1.9676849842071533 lr:6.253285481378371e-05 tokens_per_second_per_gpu:779.5542021292357 +Step 5049 | loss:2.0150539875030518 lr:6.249637535487429e-05 tokens_per_second_per_gpu:777.685325544247 +Step 5050 | loss:2.0231332778930664 lr:6.24599017026988e-05 tokens_per_second_per_gpu:774.62888644552 +Step 5051 | loss:2.0166215896606445 lr:6.242343386290447e-05 tokens_per_second_per_gpu:789.420004886103 +Step 5052 | loss:2.039278507232666 lr:6.238697184113768e-05 tokens_per_second_per_gpu:760.0456177348664 +Step 5053 | loss:2.0451736450195312 lr:6.235051564304395e-05 tokens_per_second_per_gpu:745.7615615773378 +Step 5054 | loss:1.9749042987823486 lr:6.231406527426776e-05 tokens_per_second_per_gpu:781.2643101059408 +Step 5055 | loss:2.0300397872924805 lr:6.227762074045283e-05 tokens_per_second_per_gpu:777.3539222686826 +Step 5056 | loss:2.0580360889434814 lr:6.224118204724185e-05 tokens_per_second_per_gpu:755.2732293030274 +Step 5057 | loss:2.0430846214294434 lr:6.220474920027673e-05 tokens_per_second_per_gpu:771.9231015351296 +Step 5058 | loss:1.9464302062988281 lr:6.216832220519837e-05 tokens_per_second_per_gpu:779.7981659491512 +Step 5059 | loss:2.0101799964904785 lr:6.213190106764684e-05 tokens_per_second_per_gpu:788.4022364893409 +Step 5060 | loss:2.0500433444976807 lr:6.209548579326126e-05 tokens_per_second_per_gpu:765.1932375781315 +Step 5061 | loss:1.9656022787094116 lr:6.205907638767984e-05 tokens_per_second_per_gpu:759.1997179032975 +Step 5062 | loss:1.9974439144134521 lr:6.202267285653988e-05 tokens_per_second_per_gpu:779.7942038369114 +Step 5063 | loss:2.043210029602051 lr:6.198627520547782e-05 tokens_per_second_per_gpu:786.9132244720323 +Step 5064 | loss:2.0136501789093018 lr:6.194988344012917e-05 tokens_per_second_per_gpu:778.9307306073288 +Step 5065 | loss:2.002040386199951 lr:6.191349756612849e-05 tokens_per_second_per_gpu:781.6510093669933 +Step 5066 | loss:2.0145840644836426 lr:6.187711758910943e-05 tokens_per_second_per_gpu:774.0638462774585 +Step 5067 | loss:1.9599215984344482 lr:6.184074351470479e-05 tokens_per_second_per_gpu:795.2872243284314 +Step 5068 | loss:1.9803028106689453 lr:6.180437534854635e-05 tokens_per_second_per_gpu:796.3536748392157 +Step 5069 | loss:2.0094692707061768 lr:6.176801309626508e-05 tokens_per_second_per_gpu:776.1683937321432 +Step 5070 | loss:1.9896390438079834 lr:6.173165676349103e-05 tokens_per_second_per_gpu:773.2425269540691 +Step 5071 | loss:2.0101559162139893 lr:6.169530635585327e-05 tokens_per_second_per_gpu:742.7855044516723 +Step 5072 | loss:2.0201761722564697 lr:6.165896187897993e-05 tokens_per_second_per_gpu:777.2165359396624 +Step 5073 | loss:2.019667625427246 lr:6.16226233384983e-05 tokens_per_second_per_gpu:795.4057327878131 +Step 5074 | loss:2.0054874420166016 lr:6.158629074003479e-05 tokens_per_second_per_gpu:789.3030423043502 +Step 5075 | loss:2.036055326461792 lr:6.154996408921474e-05 tokens_per_second_per_gpu:792.8641344983874 +Step 5076 | loss:2.020259380340576 lr:6.15136433916627e-05 tokens_per_second_per_gpu:779.1695590834308 +Step 5077 | loss:2.017002820968628 lr:6.147732865300221e-05 tokens_per_second_per_gpu:787.0381101151503 +Step 5078 | loss:1.9939048290252686 lr:6.144101987885595e-05 tokens_per_second_per_gpu:788.1896858233466 +Step 5079 | loss:1.994433879852295 lr:6.140471707484563e-05 tokens_per_second_per_gpu:774.0379026711123 +Step 5080 | loss:2.018350839614868 lr:6.136842024659211e-05 tokens_per_second_per_gpu:779.366806842915 +Step 5081 | loss:1.9662208557128906 lr:6.133212939971521e-05 tokens_per_second_per_gpu:771.3774604425529 +Step 5082 | loss:1.95120370388031 lr:6.129584453983397e-05 tokens_per_second_per_gpu:736.2927316520678 +Step 5083 | loss:2.0084269046783447 lr:6.125956567256634e-05 tokens_per_second_per_gpu:756.5926642004044 +Step 5084 | loss:2.0648550987243652 lr:6.122329280352945e-05 tokens_per_second_per_gpu:791.303262064891 +Step 5085 | loss:2.0682878494262695 lr:6.11870259383395e-05 tokens_per_second_per_gpu:778.4167446316563 +Step 5086 | loss:2.0370445251464844 lr:6.115076508261171e-05 tokens_per_second_per_gpu:794.1996724246374 +Step 5087 | loss:2.008049964904785 lr:6.11145102419604e-05 tokens_per_second_per_gpu:790.6367903114057 +Step 5088 | loss:2.008654832839966 lr:6.107826142199894e-05 tokens_per_second_per_gpu:789.1259485478407 +Step 5089 | loss:2.03914213180542 lr:6.104201862833979e-05 tokens_per_second_per_gpu:775.6811071210248 +Step 5090 | loss:2.000710964202881 lr:6.100578186659448e-05 tokens_per_second_per_gpu:769.7228223397954 +Step 5091 | loss:2.0500545501708984 lr:6.0969551142373607e-05 tokens_per_second_per_gpu:739.8448614544355 +Step 5092 | loss:2.0205299854278564 lr:6.09333264612868e-05 tokens_per_second_per_gpu:780.884770818057 +Step 5093 | loss:2.018683433532715 lr:6.089710782894273e-05 tokens_per_second_per_gpu:744.2719207518621 +Step 5094 | loss:2.044801950454712 lr:6.086089525094926e-05 tokens_per_second_per_gpu:746.2586152598184 +Step 5095 | loss:2.079357147216797 lr:6.0824688732913134e-05 tokens_per_second_per_gpu:787.6365437941839 +Step 5096 | loss:1.9414112567901611 lr:6.0788488280440327e-05 tokens_per_second_per_gpu:747.6942466414038 +Step 5097 | loss:2.018470048904419 lr:6.075229389913579e-05 tokens_per_second_per_gpu:738.2549986806516 +Step 5098 | loss:2.021183490753174 lr:6.071610559460354e-05 tokens_per_second_per_gpu:780.9782479491523 +Step 5099 | loss:1.9918851852416992 lr:6.067992337244663e-05 tokens_per_second_per_gpu:768.3486748831366 +Step 5100 | loss:2.0700573921203613 lr:6.06437472382672e-05 tokens_per_second_per_gpu:791.3977948893212 +Step 5101 | loss:1.9896939992904663 lr:6.060757719766651e-05 tokens_per_second_per_gpu:753.0166779453365 +Step 5102 | loss:2.0649590492248535 lr:6.0571413256244756e-05 tokens_per_second_per_gpu:773.7295758127314 +Step 5103 | loss:2.0162594318389893 lr:6.053525541960128e-05 tokens_per_second_per_gpu:770.4024855032671 +Step 5104 | loss:2.0193231105804443 lr:6.0499103693334414e-05 tokens_per_second_per_gpu:784.9851039990109 +Step 5105 | loss:2.04805064201355 lr:6.0462958083041564e-05 tokens_per_second_per_gpu:778.1087045820005 +Step 5106 | loss:2.015449285507202 lr:6.0426818594319236e-05 tokens_per_second_per_gpu:775.3227641976491 +Step 5107 | loss:2.0158300399780273 lr:6.039068523276297e-05 tokens_per_second_per_gpu:771.5233338211597 +Step 5108 | loss:1.9993185997009277 lr:6.03545580039673e-05 tokens_per_second_per_gpu:789.9083502322669 +Step 5109 | loss:2.027782678604126 lr:6.031843691352588e-05 tokens_per_second_per_gpu:758.163148235854 +Step 5110 | loss:1.9372807741165161 lr:6.028232196703134e-05 tokens_per_second_per_gpu:766.5719425251134 +Step 5111 | loss:1.9928463697433472 lr:6.0246213170075435e-05 tokens_per_second_per_gpu:771.6385737150737 +Step 5112 | loss:1.9801762104034424 lr:6.021011052824894e-05 tokens_per_second_per_gpu:771.3882882168732 +Step 5113 | loss:2.0560338497161865 lr:6.017401404714169e-05 tokens_per_second_per_gpu:793.2576225869024 +Step 5114 | loss:2.078827381134033 lr:6.013792373234249e-05 tokens_per_second_per_gpu:740.3825338585841 +Step 5115 | loss:2.016756534576416 lr:6.010183958943931e-05 tokens_per_second_per_gpu:785.0684694703247 +Step 5116 | loss:2.0531442165374756 lr:6.006576162401905e-05 tokens_per_second_per_gpu:773.7808930818393 +Step 5117 | loss:1.9985315799713135 lr:6.002968984166775e-05 tokens_per_second_per_gpu:780.2976627798367 +Step 5118 | loss:2.018768072128296 lr:5.999362424797046e-05 tokens_per_second_per_gpu:779.6570532426095 +Step 5119 | loss:2.046996593475342 lr:5.995756484851123e-05 tokens_per_second_per_gpu:774.3157483715983 +Step 5120 | loss:2.012530565261841 lr:5.992151164887316e-05 tokens_per_second_per_gpu:755.8343055035397 +Step 5121 | loss:2.0533483028411865 lr:5.988546465463845e-05 tokens_per_second_per_gpu:793.0081267536124 +Step 5122 | loss:1.983280897140503 lr:5.984942387138831e-05 tokens_per_second_per_gpu:785.2294968830607 +Step 5123 | loss:2.006798505783081 lr:5.981338930470295e-05 tokens_per_second_per_gpu:787.6478503989422 +Step 5124 | loss:2.002845048904419 lr:5.977736096016169e-05 tokens_per_second_per_gpu:764.1957343080129 +Step 5125 | loss:2.0220344066619873 lr:5.974133884334282e-05 tokens_per_second_per_gpu:763.9019469149097 +Step 5126 | loss:1.9944897890090942 lr:5.9705322959823664e-05 tokens_per_second_per_gpu:749.6952945440528 +Step 5127 | loss:2.028995990753174 lr:5.966931331518061e-05 tokens_per_second_per_gpu:777.3080796441743 +Step 5128 | loss:2.0246222019195557 lr:5.963330991498914e-05 tokens_per_second_per_gpu:773.0020116913823 +Step 5129 | loss:2.037503719329834 lr:5.9597312764823635e-05 tokens_per_second_per_gpu:760.3568301162633 +Step 5130 | loss:2.0474798679351807 lr:5.956132187025765e-05 tokens_per_second_per_gpu:780.2324481498509 +Step 5131 | loss:2.008589267730713 lr:5.952533723686364e-05 tokens_per_second_per_gpu:777.1506052810145 +Step 5132 | loss:2.0258119106292725 lr:5.948935887021314e-05 tokens_per_second_per_gpu:804.0386081873809 +Step 5133 | loss:2.009639263153076 lr:5.9453386775876776e-05 tokens_per_second_per_gpu:786.988774312039 +Step 5134 | loss:2.033104658126831 lr:5.9417420959424156e-05 tokens_per_second_per_gpu:786.2001779718347 +Step 5135 | loss:1.9974100589752197 lr:5.938146142642386e-05 tokens_per_second_per_gpu:777.0737717681982 +Step 5136 | loss:1.9667987823486328 lr:5.934550818244361e-05 tokens_per_second_per_gpu:770.7821883179269 +Step 5137 | loss:2.062410354614258 lr:5.930956123305006e-05 tokens_per_second_per_gpu:767.5374940780722 +Step 5138 | loss:2.075582981109619 lr:5.927362058380889e-05 tokens_per_second_per_gpu:776.9995448275398 +Step 5139 | loss:1.978935956954956 lr:5.923768624028488e-05 tokens_per_second_per_gpu:786.4911849385338 +Step 5140 | loss:2.055583953857422 lr:5.920175820804181e-05 tokens_per_second_per_gpu:768.5766932426201 +Step 5141 | loss:2.04459810256958 lr:5.9165836492642426e-05 tokens_per_second_per_gpu:786.0663902018928 +Step 5142 | loss:1.9468650817871094 lr:5.912992109964854e-05 tokens_per_second_per_gpu:779.6068997697794 +Step 5143 | loss:2.0333738327026367 lr:5.909401203462095e-05 tokens_per_second_per_gpu:791.7925369393038 +Step 5144 | loss:2.0277767181396484 lr:5.9058109303119543e-05 tokens_per_second_per_gpu:780.9809197433823 +Step 5145 | loss:1.9936480522155762 lr:5.90222129107032e-05 tokens_per_second_per_gpu:764.0983492917101 +Step 5146 | loss:1.9975967407226562 lr:5.898632286292978e-05 tokens_per_second_per_gpu:784.0124249601516 +Step 5147 | loss:2.039783000946045 lr:5.895043916535616e-05 tokens_per_second_per_gpu:778.510283215057 +Step 5148 | loss:1.9911737442016602 lr:5.891456182353825e-05 tokens_per_second_per_gpu:745.1192756357018 +Step 5149 | loss:1.9738370180130005 lr:5.8878690843031084e-05 tokens_per_second_per_gpu:770.1628119078907 +Step 5150 | loss:1.9909454584121704 lr:5.884282622938849e-05 tokens_per_second_per_gpu:723.953624784542 +Step 5151 | loss:2.074899911880493 lr:5.880696798816352e-05 tokens_per_second_per_gpu:765.0310252492451 +Step 5152 | loss:2.0324668884277344 lr:5.877111612490812e-05 tokens_per_second_per_gpu:765.3662143365235 +Step 5153 | loss:2.0297696590423584 lr:5.873527064517326e-05 tokens_per_second_per_gpu:781.0458967999925 +Step 5154 | loss:2.0001347064971924 lr:5.869943155450892e-05 tokens_per_second_per_gpu:768.9622983097338 +Step 5155 | loss:1.9884155988693237 lr:5.8663598858464205e-05 tokens_per_second_per_gpu:739.9239477294971 +Step 5156 | loss:2.048372507095337 lr:5.862777256258706e-05 tokens_per_second_per_gpu:709.4463818625992 +Step 5157 | loss:2.0247087478637695 lr:5.8591952672424545e-05 tokens_per_second_per_gpu:764.115323821363 +Step 5158 | loss:2.0142951011657715 lr:5.8556139193522695e-05 tokens_per_second_per_gpu:775.1480196922031 +Step 5159 | loss:1.9955838918685913 lr:5.8520332131426523e-05 tokens_per_second_per_gpu:761.560696834521 +Step 5160 | loss:2.003004789352417 lr:5.8484531491680126e-05 tokens_per_second_per_gpu:774.2747122627023 +Step 5161 | loss:1.9801745414733887 lr:5.844873727982656e-05 tokens_per_second_per_gpu:784.0387762284156 +Step 5162 | loss:2.0375921726226807 lr:5.8412949501407874e-05 tokens_per_second_per_gpu:764.4752024110401 +Step 5163 | loss:2.074514865875244 lr:5.837716816196515e-05 tokens_per_second_per_gpu:758.8687009182644 +Step 5164 | loss:1.9929591417312622 lr:5.834139326703838e-05 tokens_per_second_per_gpu:754.715636333182 +Step 5165 | loss:1.9933000802993774 lr:5.8305624822166796e-05 tokens_per_second_per_gpu:745.5101298490756 +Step 5166 | loss:1.9891270399093628 lr:5.826986283288832e-05 tokens_per_second_per_gpu:773.9684530025783 +Step 5167 | loss:2.0178823471069336 lr:5.8234107304740104e-05 tokens_per_second_per_gpu:775.2353382587753 +Step 5168 | loss:2.0241689682006836 lr:5.8198358243258233e-05 tokens_per_second_per_gpu:778.8813784251159 +Step 5169 | loss:1.960384488105774 lr:5.8162615653977705e-05 tokens_per_second_per_gpu:778.6750930326664 +Step 5170 | loss:2.043272018432617 lr:5.81268795424326e-05 tokens_per_second_per_gpu:780.0016987075683 +Step 5171 | loss:2.0283451080322266 lr:5.80911499141561e-05 tokens_per_second_per_gpu:775.7918734522408 +Step 5172 | loss:2.018378973007202 lr:5.805542677468014e-05 tokens_per_second_per_gpu:780.1114619751254 +Step 5173 | loss:2.0607807636260986 lr:5.8019710129535844e-05 tokens_per_second_per_gpu:793.9366358124537 +Step 5174 | loss:2.002389907836914 lr:5.798399998425329e-05 tokens_per_second_per_gpu:774.4181051403356 +Step 5175 | loss:2.028470993041992 lr:5.7948296344361405e-05 tokens_per_second_per_gpu:781.7653304302466 +Step 5176 | loss:1.9777135848999023 lr:5.791259921538834e-05 tokens_per_second_per_gpu:783.1457973396059 +Step 5177 | loss:2.0074551105499268 lr:5.787690860286115e-05 tokens_per_second_per_gpu:780.5049844923997 +Step 5178 | loss:2.052018642425537 lr:5.784122451230576e-05 tokens_per_second_per_gpu:748.8685929550322 +Step 5179 | loss:2.0199265480041504 lr:5.7805546949247225e-05 tokens_per_second_per_gpu:783.3230302672798 +Step 5180 | loss:2.066115617752075 lr:5.776987591920955e-05 tokens_per_second_per_gpu:759.1889449164314 +Step 5181 | loss:2.0263967514038086 lr:5.7734211427715714e-05 tokens_per_second_per_gpu:753.6044310643659 +Step 5182 | loss:2.0375213623046875 lr:5.769855348028772e-05 tokens_per_second_per_gpu:745.9739047168221 +Step 5183 | loss:2.0011019706726074 lr:5.766290208244656e-05 tokens_per_second_per_gpu:795.599166526577 +Step 5184 | loss:2.0013163089752197 lr:5.762725723971212e-05 tokens_per_second_per_gpu:751.4027345157768 +Step 5185 | loss:1.979524850845337 lr:5.759161895760334e-05 tokens_per_second_per_gpu:785.1070672823508 +Step 5186 | loss:2.0605311393737793 lr:5.755598724163818e-05 tokens_per_second_per_gpu:775.3101775670624 +Step 5187 | loss:2.0460801124572754 lr:5.752036209733351e-05 tokens_per_second_per_gpu:779.6912867637835 +Step 5188 | loss:1.9790576696395874 lr:5.748474353020524e-05 tokens_per_second_per_gpu:769.4485664709006 +Step 5189 | loss:2.056885242462158 lr:5.7449131545768275e-05 tokens_per_second_per_gpu:771.3277929918488 +Step 5190 | loss:1.9746334552764893 lr:5.741352614953639e-05 tokens_per_second_per_gpu:762.1855403939544 +Step 5191 | loss:2.061681032180786 lr:5.7377927347022384e-05 tokens_per_second_per_gpu:797.4659405878244 +Step 5192 | loss:1.947845697402954 lr:5.734233514373822e-05 tokens_per_second_per_gpu:775.9432956013364 +Step 5193 | loss:1.974340796470642 lr:5.730674954519455e-05 tokens_per_second_per_gpu:761.3427587208016 +Step 5194 | loss:2.016972064971924 lr:5.7271170556901164e-05 tokens_per_second_per_gpu:774.0278563347217 +Step 5195 | loss:2.01779842376709 lr:5.723559818436688e-05 tokens_per_second_per_gpu:744.2526723890523 +Step 5196 | loss:2.0195488929748535 lr:5.7200032433099285e-05 tokens_per_second_per_gpu:760.4858540479687 +Step 5197 | loss:2.0031583309173584 lr:5.71644733086051e-05 tokens_per_second_per_gpu:747.8733610021003 +Step 5198 | loss:2.0166029930114746 lr:5.7128920816390096e-05 tokens_per_second_per_gpu:759.9856962032078 +Step 5199 | loss:2.035179615020752 lr:5.709337496195881e-05 tokens_per_second_per_gpu:769.9313429792775 +Step 5200 | loss:1.9831236600875854 lr:5.7057835750814867e-05 tokens_per_second_per_gpu:780.5365717008242 +Step 5201 | loss:1.9909687042236328 lr:5.7022303188460913e-05 tokens_per_second_per_gpu:760.8396449006755 +Step 5202 | loss:1.99946928024292 lr:5.698677728039836e-05 tokens_per_second_per_gpu:775.8757857102299 +Step 5203 | loss:2.0237810611724854 lr:5.695125803212786e-05 tokens_per_second_per_gpu:747.6636595100244 +Step 5204 | loss:1.9924201965332031 lr:5.6915745449148894e-05 tokens_per_second_per_gpu:774.4042678356248 +Step 5205 | loss:2.050544261932373 lr:5.6880239536959845e-05 tokens_per_second_per_gpu:724.9788297057237 +Step 5206 | loss:2.018322467803955 lr:5.6844740301058194e-05 tokens_per_second_per_gpu:757.1012403595142 +Step 5207 | loss:2.0150551795959473 lr:5.680924774694031e-05 tokens_per_second_per_gpu:780.1003051161106 +Step 5208 | loss:2.04091215133667 lr:5.677376188010156e-05 tokens_per_second_per_gpu:775.8990864630146 +Step 5209 | loss:2.0272469520568848 lr:5.673828270603627e-05 tokens_per_second_per_gpu:776.0675223810753 +Step 5210 | loss:2.0140771865844727 lr:5.6702810230237754e-05 tokens_per_second_per_gpu:785.6228599604923 +Step 5211 | loss:2.000340461730957 lr:5.666734445819819e-05 tokens_per_second_per_gpu:772.169217593817 +Step 5212 | loss:2.013906478881836 lr:5.6631885395408825e-05 tokens_per_second_per_gpu:743.7504662215816 +Step 5213 | loss:2.016515016555786 lr:5.659643304735983e-05 tokens_per_second_per_gpu:768.4991742372008 +Step 5214 | loss:2.020956039428711 lr:5.6560987419540346e-05 tokens_per_second_per_gpu:747.1361170793347 +Step 5215 | loss:2.0454020500183105 lr:5.652554851743845e-05 tokens_per_second_per_gpu:775.32786305912 +Step 5216 | loss:1.9801006317138672 lr:5.6490116346541243e-05 tokens_per_second_per_gpu:761.3495818606577 +Step 5217 | loss:2.054917812347412 lr:5.645469091233466e-05 tokens_per_second_per_gpu:795.7495452417722 +Step 5218 | loss:1.968747615814209 lr:5.641927222030364e-05 tokens_per_second_per_gpu:733.9267649296035 +Step 5219 | loss:2.010948896408081 lr:5.6383860275932256e-05 tokens_per_second_per_gpu:762.7618324848837 +Step 5220 | loss:2.0918588638305664 lr:5.6348455084703235e-05 tokens_per_second_per_gpu:779.5758994289699 +Step 5221 | loss:2.019376039505005 lr:5.631305665209847e-05 tokens_per_second_per_gpu:773.3459548357267 +Step 5222 | loss:2.006258010864258 lr:5.6277664983598775e-05 tokens_per_second_per_gpu:766.2501571909636 +Step 5223 | loss:1.995492696762085 lr:5.624228008468377e-05 tokens_per_second_per_gpu:794.4499942231262 +Step 5224 | loss:2.0099520683288574 lr:5.620690196083227e-05 tokens_per_second_per_gpu:790.9258969380404 +Step 5225 | loss:2.0346450805664062 lr:5.6171530617521894e-05 tokens_per_second_per_gpu:771.1269081390312 +Step 5226 | loss:1.96993088722229 lr:5.613616606022918e-05 tokens_per_second_per_gpu:762.3165601743275 +Step 5227 | loss:2.0172085762023926 lr:5.6100808294429674e-05 tokens_per_second_per_gpu:767.0892166250965 +Step 5228 | loss:1.9930564165115356 lr:5.6065457325597936e-05 tokens_per_second_per_gpu:767.2940427889798 +Step 5229 | loss:2.007376194000244 lr:5.6030113159207276e-05 tokens_per_second_per_gpu:776.1365526053403 +Step 5230 | loss:1.986299991607666 lr:5.599477580073018e-05 tokens_per_second_per_gpu:757.152087918956 +Step 5231 | loss:2.028280258178711 lr:5.595944525563799e-05 tokens_per_second_per_gpu:751.6101414130812 +Step 5232 | loss:1.9700305461883545 lr:5.592412152940088e-05 tokens_per_second_per_gpu:788.6270654753005 +Step 5233 | loss:1.99920654296875 lr:5.588880462748814e-05 tokens_per_second_per_gpu:781.4377977503237 +Step 5234 | loss:1.9887374639511108 lr:5.58534945553679e-05 tokens_per_second_per_gpu:770.1719478345807 +Step 5235 | loss:1.992687702178955 lr:5.581819131850729e-05 tokens_per_second_per_gpu:765.2110579565829 +Step 5236 | loss:2.0034377574920654 lr:5.578289492237232e-05 tokens_per_second_per_gpu:756.8440740420572 +Step 5237 | loss:2.1103687286376953 lr:5.5747605372428056e-05 tokens_per_second_per_gpu:750.760332153888 +Step 5238 | loss:2.062767505645752 lr:5.571232267413833e-05 tokens_per_second_per_gpu:788.7977712627352 +Step 5239 | loss:1.9619516134262085 lr:5.5677046832966015e-05 tokens_per_second_per_gpu:790.7980206182776 +Step 5240 | loss:2.0157079696655273 lr:5.5641777854372966e-05 tokens_per_second_per_gpu:745.0781025461241 +Step 5241 | loss:2.0508222579956055 lr:5.56065157438199e-05 tokens_per_second_per_gpu:734.8028708161733 +Step 5242 | loss:2.012214183807373 lr:5.557126050676649e-05 tokens_per_second_per_gpu:775.1342723138702 +Step 5243 | loss:2.0296108722686768 lr:5.5536012148671376e-05 tokens_per_second_per_gpu:773.7293629569698 +Step 5244 | loss:2.0560519695281982 lr:5.5500770674992065e-05 tokens_per_second_per_gpu:780.3239840996123 +Step 5245 | loss:1.9896764755249023 lr:5.546553609118501e-05 tokens_per_second_per_gpu:758.7058361887061 +Step 5246 | loss:2.0278468132019043 lr:5.5430308402705754e-05 tokens_per_second_per_gpu:764.0555838613819 +Step 5247 | loss:2.032383680343628 lr:5.539508761500851e-05 tokens_per_second_per_gpu:779.2728932739229 +Step 5248 | loss:2.058716297149658 lr:5.535987373354663e-05 tokens_per_second_per_gpu:759.5685985210195 +Step 5249 | loss:1.9874927997589111 lr:5.532466676377235e-05 tokens_per_second_per_gpu:749.6773531914026 +Step 5250 | loss:2.02978515625 lr:5.528946671113668e-05 tokens_per_second_per_gpu:747.0753351933254 +Step 5251 | loss:1.994480848312378 lr:5.525427358108981e-05 tokens_per_second_per_gpu:759.011902796999 +Step 5252 | loss:1.9582509994506836 lr:5.5219087379080745e-05 tokens_per_second_per_gpu:757.5365906689474 +Step 5253 | loss:2.0411109924316406 lr:5.5183908110557336e-05 tokens_per_second_per_gpu:785.947148322629 +Step 5254 | loss:1.9776475429534912 lr:5.5148735780966456e-05 tokens_per_second_per_gpu:723.9673509749895 +Step 5255 | loss:2.010059356689453 lr:5.511357039575393e-05 tokens_per_second_per_gpu:770.016181914358 +Step 5256 | loss:1.9653818607330322 lr:5.507841196036434e-05 tokens_per_second_per_gpu:769.499033098337 +Step 5257 | loss:2.0495405197143555 lr:5.504326048024142e-05 tokens_per_second_per_gpu:772.4934851408838 +Step 5258 | loss:2.0035207271575928 lr:5.500811596082776e-05 tokens_per_second_per_gpu:751.9525772960902 +Step 5259 | loss:2.0185225009918213 lr:5.497297840756469e-05 tokens_per_second_per_gpu:787.1359499221899 +Step 5260 | loss:1.9631879329681396 lr:5.493784782589269e-05 tokens_per_second_per_gpu:761.3866917478247 +Step 5261 | loss:1.9990911483764648 lr:5.490272422125105e-05 tokens_per_second_per_gpu:764.7426617599449 +Step 5262 | loss:2.0715250968933105 lr:5.4867607599077986e-05 tokens_per_second_per_gpu:747.1045183185655 +Step 5263 | loss:2.019728660583496 lr:5.483249796481069e-05 tokens_per_second_per_gpu:767.8770247502697 +Step 5264 | loss:2.0168421268463135 lr:5.479739532388526e-05 tokens_per_second_per_gpu:755.0244430751987 +Step 5265 | loss:1.9857796430587769 lr:5.476229968173658e-05 tokens_per_second_per_gpu:767.863695931991 +Step 5266 | loss:2.0062291622161865 lr:5.4727211043798566e-05 tokens_per_second_per_gpu:773.2757657145343 +Step 5267 | loss:2.056305408477783 lr:5.469212941550417e-05 tokens_per_second_per_gpu:773.8878580482352 +Step 5268 | loss:1.9868695735931396 lr:5.465705480228498e-05 tokens_per_second_per_gpu:756.2724472233712 +Step 5269 | loss:2.0674567222595215 lr:5.4621987209571704e-05 tokens_per_second_per_gpu:785.7782987929355 +Step 5270 | loss:1.929364800453186 lr:5.458692664279393e-05 tokens_per_second_per_gpu:786.9102194297569 +Step 5271 | loss:2.0259413719177246 lr:5.4551873107380055e-05 tokens_per_second_per_gpu:783.8329209697368 +Step 5272 | loss:2.0550742149353027 lr:5.451682660875747e-05 tokens_per_second_per_gpu:786.656298009833 +Step 5273 | loss:2.0377275943756104 lr:5.448178715235257e-05 tokens_per_second_per_gpu:770.622791440272 +Step 5274 | loss:1.9866933822631836 lr:5.444675474359045e-05 tokens_per_second_per_gpu:763.9907424058528 +Step 5275 | loss:2.0642201900482178 lr:5.441172938789526e-05 tokens_per_second_per_gpu:783.2296475795685 +Step 5276 | loss:2.0614616870880127 lr:5.437671109069007e-05 tokens_per_second_per_gpu:759.9008464794618 +Step 5277 | loss:2.0279860496520996 lr:5.4341699857396665e-05 tokens_per_second_per_gpu:785.3256299772506 +Step 5278 | loss:2.0708789825439453 lr:5.4306695693436024e-05 tokens_per_second_per_gpu:777.7585216446117 +Step 5279 | loss:1.9974150657653809 lr:5.4271698604227875e-05 tokens_per_second_per_gpu:757.3791444629617 +Step 5280 | loss:2.074967622756958 lr:5.423670859519079e-05 tokens_per_second_per_gpu:754.7367199262005 +Step 5281 | loss:2.028414726257324 lr:5.420172567174233e-05 tokens_per_second_per_gpu:767.5508386403967 +Step 5282 | loss:2.0415921211242676 lr:5.416674983929897e-05 tokens_per_second_per_gpu:752.377951791045 +Step 5283 | loss:2.0349910259246826 lr:5.413178110327607e-05 tokens_per_second_per_gpu:772.6952438734777 +Step 5284 | loss:1.9683966636657715 lr:5.409681946908787e-05 tokens_per_second_per_gpu:763.2752575188797 +Step 5285 | loss:2.063187599182129 lr:5.4061864942147544e-05 tokens_per_second_per_gpu:789.2606847463206 +Step 5286 | loss:2.0273146629333496 lr:5.402691752786711e-05 tokens_per_second_per_gpu:765.3130004667775 +Step 5287 | loss:2.0257673263549805 lr:5.399197723165752e-05 tokens_per_second_per_gpu:741.2080456921911 +Step 5288 | loss:1.9868589639663696 lr:5.395704405892865e-05 tokens_per_second_per_gpu:753.319004954015 +Step 5289 | loss:2.049358606338501 lr:5.392211801508924e-05 tokens_per_second_per_gpu:772.818536258353 +Step 5290 | loss:2.005276679992676 lr:5.388719910554694e-05 tokens_per_second_per_gpu:772.8389965702777 +Step 5291 | loss:2.054722309112549 lr:5.385228733570832e-05 tokens_per_second_per_gpu:776.71571540669 +Step 5292 | loss:1.986216425895691 lr:5.3817382710978736e-05 tokens_per_second_per_gpu:755.8004943214013 +Step 5293 | loss:2.0163323879241943 lr:5.378248523676255e-05 tokens_per_second_per_gpu:772.2086040563578 +Step 5294 | loss:1.9736073017120361 lr:5.3747594918462996e-05 tokens_per_second_per_gpu:780.4038367380814 +Step 5295 | loss:1.9634679555892944 lr:5.371271176148218e-05 tokens_per_second_per_gpu:771.4343149825535 +Step 5296 | loss:2.025141477584839 lr:5.36778357712211e-05 tokens_per_second_per_gpu:769.4717390801096 +Step 5297 | loss:1.9891300201416016 lr:5.3642966953079685e-05 tokens_per_second_per_gpu:743.6638199954302 +Step 5298 | loss:2.01947021484375 lr:5.360810531245666e-05 tokens_per_second_per_gpu:752.4016546670969 +Step 5299 | loss:1.9637675285339355 lr:5.357325085474969e-05 tokens_per_second_per_gpu:729.0316996113104 +Step 5300 | loss:2.003119707107544 lr:5.3538403585355444e-05 tokens_per_second_per_gpu:743.380933923373 +Step 5301 | loss:2.0512821674346924 lr:5.350356350966925e-05 tokens_per_second_per_gpu:761.8484946699563 +Step 5302 | loss:2.006937265396118 lr:5.34687306330855e-05 tokens_per_second_per_gpu:745.0593020098363 +Step 5303 | loss:2.0376384258270264 lr:5.343390496099743e-05 tokens_per_second_per_gpu:738.5067976710604 +Step 5304 | loss:1.9753693342208862 lr:5.339908649879704e-05 tokens_per_second_per_gpu:783.160540185669 +Step 5305 | loss:1.9787397384643555 lr:5.3364275251875416e-05 tokens_per_second_per_gpu:770.2863232364513 +Step 5306 | loss:1.9869210720062256 lr:5.332947122562244e-05 tokens_per_second_per_gpu:765.1718708332155 +Step 5307 | loss:2.009282112121582 lr:5.3294674425426796e-05 tokens_per_second_per_gpu:761.7310772132229 +Step 5308 | loss:1.9859957695007324 lr:5.325988485667614e-05 tokens_per_second_per_gpu:766.2380815435351 +Step 5309 | loss:2.000711679458618 lr:5.322510252475699e-05 tokens_per_second_per_gpu:769.8361694106378 +Step 5310 | loss:2.037048816680908 lr:5.3190327435054735e-05 tokens_per_second_per_gpu:748.3005578712416 +Step 5311 | loss:2.023219347000122 lr:5.315555959295365e-05 tokens_per_second_per_gpu:796.385223869066 +Step 5312 | loss:1.9910051822662354 lr:5.312079900383693e-05 tokens_per_second_per_gpu:799.7946691552236 +Step 5313 | loss:2.0154926776885986 lr:5.308604567308653e-05 tokens_per_second_per_gpu:773.7699681411985 +Step 5314 | loss:2.0225777626037598 lr:5.305129960608335e-05 tokens_per_second_per_gpu:772.497281705489 +Step 5315 | loss:2.00285005569458 lr:5.3016560808207214e-05 tokens_per_second_per_gpu:773.872794855184 +Step 5316 | loss:2.0471949577331543 lr:5.298182928483675e-05 tokens_per_second_per_gpu:767.2387829208453 +Step 5317 | loss:2.0642874240875244 lr:5.29471050413495e-05 tokens_per_second_per_gpu:742.6020794116681 +Step 5318 | loss:2.0674102306365967 lr:5.291238808312189e-05 tokens_per_second_per_gpu:775.4283093037021 +Step 5319 | loss:2.086775302886963 lr:5.2877678415529105e-05 tokens_per_second_per_gpu:779.2504869452848 +Step 5320 | loss:2.028752088546753 lr:5.2842976043945346e-05 tokens_per_second_per_gpu:776.0742589796621 +Step 5321 | loss:1.9564692974090576 lr:5.280828097374361e-05 tokens_per_second_per_gpu:737.0941891215801 +Step 5322 | loss:2.046779155731201 lr:5.277359321029578e-05 tokens_per_second_per_gpu:776.3459902625924 +Step 5323 | loss:1.9917123317718506 lr:5.273891275897263e-05 tokens_per_second_per_gpu:780.1545864886292 +Step 5324 | loss:2.0298421382904053 lr:5.270423962514377e-05 tokens_per_second_per_gpu:796.604900019619 +Step 5325 | loss:2.038639545440674 lr:5.266957381417761e-05 tokens_per_second_per_gpu:755.6918786707257 +Step 5326 | loss:2.0093495845794678 lr:5.26349153314416e-05 tokens_per_second_per_gpu:749.4296794181182 +Step 5327 | loss:2.0116477012634277 lr:5.2600264182301975e-05 tokens_per_second_per_gpu:763.034079902625 +Step 5328 | loss:1.9735983610153198 lr:5.2565620372123724e-05 tokens_per_second_per_gpu:768.3008177959638 +Step 5329 | loss:2.0712661743164062 lr:5.253098390627082e-05 tokens_per_second_per_gpu:746.2894227811813 +Step 5330 | loss:1.965876817703247 lr:5.249635479010614e-05 tokens_per_second_per_gpu:791.1555570735599 +Step 5331 | loss:2.085677146911621 lr:5.246173302899121e-05 tokens_per_second_per_gpu:751.7316651307261 +Step 5332 | loss:2.0101981163024902 lr:5.242711862828669e-05 tokens_per_second_per_gpu:779.1216830320616 +Step 5333 | loss:1.972238302230835 lr:5.239251159335197e-05 tokens_per_second_per_gpu:758.7779450071615 +Step 5334 | loss:2.0072484016418457 lr:5.2357911929545224e-05 tokens_per_second_per_gpu:767.2464539066274 +Step 5335 | loss:1.9390243291854858 lr:5.232331964222361e-05 tokens_per_second_per_gpu:770.7956071748604 +Step 5336 | loss:2.013099193572998 lr:5.228873473674307e-05 tokens_per_second_per_gpu:771.4816304043339 +Step 5337 | loss:2.0351247787475586 lr:5.225415721845846e-05 tokens_per_second_per_gpu:765.0174628196463 +Step 5338 | loss:1.9573314189910889 lr:5.221958709272343e-05 tokens_per_second_per_gpu:759.4119819206367 +Step 5339 | loss:2.026371955871582 lr:5.218502436489059e-05 tokens_per_second_per_gpu:785.2288359722046 +Step 5340 | loss:1.9977619647979736 lr:5.215046904031122e-05 tokens_per_second_per_gpu:790.8262277148525 +Step 5341 | loss:2.0060343742370605 lr:5.211592112433563e-05 tokens_per_second_per_gpu:778.8464383687354 +Step 5342 | loss:2.066415309906006 lr:5.20813806223129e-05 tokens_per_second_per_gpu:772.5489973411189 +Step 5343 | loss:2.012221336364746 lr:5.2046847539590995e-05 tokens_per_second_per_gpu:777.8596800911153 +Step 5344 | loss:1.96694815158844 lr:5.20123218815167e-05 tokens_per_second_per_gpu:736.7732935336461 +Step 5345 | loss:2.0201244354248047 lr:5.197780365343572e-05 tokens_per_second_per_gpu:788.2811870788681 +Step 5346 | loss:2.013746738433838 lr:5.194329286069246e-05 tokens_per_second_per_gpu:785.1046211149122 +Step 5347 | loss:2.0532641410827637 lr:5.190878950863033e-05 tokens_per_second_per_gpu:762.2824177576745 +Step 5348 | loss:2.093369960784912 lr:5.187429360259152e-05 tokens_per_second_per_gpu:750.6311244428662 +Step 5349 | loss:1.9791113138198853 lr:5.1839805147917064e-05 tokens_per_second_per_gpu:768.9417598826169 +Step 5350 | loss:1.986255168914795 lr:5.180532414994688e-05 tokens_per_second_per_gpu:772.4978912664282 +Step 5351 | loss:2.0892107486724854 lr:5.1770850614019705e-05 tokens_per_second_per_gpu:798.9480563269573 +Step 5352 | loss:2.038712501525879 lr:5.173638454547303e-05 tokens_per_second_per_gpu:784.3481126183339 +Step 5353 | loss:2.044041395187378 lr:5.17019259496434e-05 tokens_per_second_per_gpu:803.1769594784287 +Step 5354 | loss:2.0139272212982178 lr:5.166747483186607e-05 tokens_per_second_per_gpu:775.7765128232011 +Step 5355 | loss:1.9948480129241943 lr:5.163303119747509e-05 tokens_per_second_per_gpu:782.1314559802485 +Step 5356 | loss:2.033607006072998 lr:5.159859505180342e-05 tokens_per_second_per_gpu:773.4128013023853 +Step 5357 | loss:2.0715980529785156 lr:5.156416640018292e-05 tokens_per_second_per_gpu:771.3681391361174 +Step 5358 | loss:2.025418519973755 lr:5.152974524794409e-05 tokens_per_second_per_gpu:749.8387447237183 +Step 5359 | loss:1.9883781671524048 lr:5.149533160041653e-05 tokens_per_second_per_gpu:762.8570321471676 +Step 5360 | loss:2.0799553394317627 lr:5.1460925462928546e-05 tokens_per_second_per_gpu:757.6842450842634 +Step 5361 | loss:1.984952449798584 lr:5.14265268408072e-05 tokens_per_second_per_gpu:750.3940500278038 +Step 5362 | loss:2.0175840854644775 lr:5.139213573937851e-05 tokens_per_second_per_gpu:780.3204437029884 +Step 5363 | loss:2.0861330032348633 lr:5.1357752163967296e-05 tokens_per_second_per_gpu:755.0261749152891 +Step 5364 | loss:1.9977877140045166 lr:5.1323376119897214e-05 tokens_per_second_per_gpu:742.309672269421 +Step 5365 | loss:2.0825860500335693 lr:5.128900761249076e-05 tokens_per_second_per_gpu:784.7925257141429 +Step 5366 | loss:2.011031150817871 lr:5.125464664706927e-05 tokens_per_second_per_gpu:766.0407622069937 +Step 5367 | loss:1.9968390464782715 lr:5.122029322895283e-05 tokens_per_second_per_gpu:776.3506789840001 +Step 5368 | loss:2.065258264541626 lr:5.118594736346047e-05 tokens_per_second_per_gpu:750.3184766461234 +Step 5369 | loss:2.0439705848693848 lr:5.1151609055910014e-05 tokens_per_second_per_gpu:770.1249632596941 +Step 5370 | loss:2.021052122116089 lr:5.1117278311618054e-05 tokens_per_second_per_gpu:793.8777475602784 +Step 5371 | loss:2.0489883422851562 lr:5.108295513590014e-05 tokens_per_second_per_gpu:780.2365656550396 +Step 5372 | loss:2.00840163230896 lr:5.104863953407053e-05 tokens_per_second_per_gpu:763.2967776802444 +Step 5373 | loss:2.0988428592681885 lr:5.101433151144234e-05 tokens_per_second_per_gpu:765.1933732319806 +Step 5374 | loss:1.9892823696136475 lr:5.098003107332754e-05 tokens_per_second_per_gpu:752.8967782471613 +Step 5375 | loss:1.9742145538330078 lr:5.09457382250369e-05 tokens_per_second_per_gpu:763.1257417322124 +Step 5376 | loss:1.9781768321990967 lr:5.0911452971880024e-05 tokens_per_second_per_gpu:764.7251467996758 +Step 5377 | loss:1.94405996799469 lr:5.087717531916536e-05 tokens_per_second_per_gpu:780.1573745044146 +Step 5378 | loss:1.9986668825149536 lr:5.084290527220019e-05 tokens_per_second_per_gpu:780.9934414678871 +Step 5379 | loss:1.9751684665679932 lr:5.080864283629048e-05 tokens_per_second_per_gpu:788.7379493639731 +Step 5380 | loss:1.975342035293579 lr:5.0774388016741234e-05 tokens_per_second_per_gpu:768.8364092058852 +Step 5381 | loss:1.9225553274154663 lr:5.0740140818856174e-05 tokens_per_second_per_gpu:762.1767549997536 +Step 5382 | loss:2.010801076889038 lr:5.0705901247937746e-05 tokens_per_second_per_gpu:788.3146128771458 +Step 5383 | loss:2.018312931060791 lr:5.067166930928737e-05 tokens_per_second_per_gpu:764.1554220967047 +Step 5384 | loss:2.0111446380615234 lr:5.063744500820521e-05 tokens_per_second_per_gpu:773.6437392756345 +Step 5385 | loss:1.9659897089004517 lr:5.060322834999025e-05 tokens_per_second_per_gpu:771.56497811431 +Step 5386 | loss:2.061948776245117 lr:5.056901933994029e-05 tokens_per_second_per_gpu:763.6184386094179 +Step 5387 | loss:2.002333879470825 lr:5.053481798335202e-05 tokens_per_second_per_gpu:736.3422946577723 +Step 5388 | loss:1.9990234375 lr:5.05006242855208e-05 tokens_per_second_per_gpu:779.4135228380984 +Step 5389 | loss:1.957227110862732 lr:5.04664382517409e-05 tokens_per_second_per_gpu:744.8619812021805 +Step 5390 | loss:1.9893699884414673 lr:5.04322598873054e-05 tokens_per_second_per_gpu:739.4125531534348 +Step 5391 | loss:2.0407261848449707 lr:5.039808919750617e-05 tokens_per_second_per_gpu:766.3970432959312 +Step 5392 | loss:1.9811890125274658 lr:5.0363926187633924e-05 tokens_per_second_per_gpu:755.3164849266644 +Step 5393 | loss:2.010103225708008 lr:5.0329770862978185e-05 tokens_per_second_per_gpu:761.5640931228927 +Step 5394 | loss:1.9580073356628418 lr:5.0295623228827194e-05 tokens_per_second_per_gpu:763.0837045232621 +Step 5395 | loss:1.9634666442871094 lr:5.02614832904681e-05 tokens_per_second_per_gpu:759.8756136293125 +Step 5396 | loss:2.0337610244750977 lr:5.022735105318686e-05 tokens_per_second_per_gpu:762.4715546450042 +Step 5397 | loss:2.0316200256347656 lr:5.0193226522268166e-05 tokens_per_second_per_gpu:785.4498886073548 +Step 5398 | loss:1.9527812004089355 lr:5.015910970299562e-05 tokens_per_second_per_gpu:777.1239015352114 +Step 5399 | loss:1.9824941158294678 lr:5.012500060065157e-05 tokens_per_second_per_gpu:773.6120671065091 +Step 5400 | loss:2.012852430343628 lr:5.009089922051706e-05 tokens_per_second_per_gpu:758.2626193231131 +Step 5401 | loss:1.9689149856567383 lr:5.0056805567872225e-05 tokens_per_second_per_gpu:763.6071547807794 +Step 5402 | loss:1.9469748735427856 lr:5.00227196479957e-05 tokens_per_second_per_gpu:761.011827169285 +Step 5403 | loss:2.029801368713379 lr:4.9988641466165074e-05 tokens_per_second_per_gpu:766.8906832270941 +Step 5404 | loss:1.9796260595321655 lr:4.995457102765675e-05 tokens_per_second_per_gpu:791.9064818691434 +Step 5405 | loss:2.0235273838043213 lr:4.992050833774591e-05 tokens_per_second_per_gpu:779.329579993516 +Step 5406 | loss:2.0667524337768555 lr:4.9886453401706414e-05 tokens_per_second_per_gpu:764.4513088221971 +Step 5407 | loss:2.0174851417541504 lr:4.9852406224811144e-05 tokens_per_second_per_gpu:752.5593990490005 +Step 5408 | loss:1.9313666820526123 lr:4.981836681233167e-05 tokens_per_second_per_gpu:789.9974656443455 +Step 5409 | loss:1.9720414876937866 lr:4.97843351695383e-05 tokens_per_second_per_gpu:791.4787230628835 +Step 5410 | loss:2.016995429992676 lr:4.97503113017002e-05 tokens_per_second_per_gpu:767.431525365339 +Step 5411 | loss:1.9633725881576538 lr:4.971629521408535e-05 tokens_per_second_per_gpu:785.262466172611 +Step 5412 | loss:2.0706679821014404 lr:4.968228691196051e-05 tokens_per_second_per_gpu:757.0137881662923 +Step 5413 | loss:2.057036876678467 lr:4.964828640059121e-05 tokens_per_second_per_gpu:775.8847267030778 +Step 5414 | loss:2.0350542068481445 lr:4.961429368524184e-05 tokens_per_second_per_gpu:772.144823126159 +Step 5415 | loss:2.038069009780884 lr:4.9580308771175454e-05 tokens_per_second_per_gpu:770.1246312121339 +Step 5416 | loss:2.0326404571533203 lr:4.9546331663654036e-05 tokens_per_second_per_gpu:784.9321799391997 +Step 5417 | loss:2.0994441509246826 lr:4.951236236793828e-05 tokens_per_second_per_gpu:783.2381658563266 +Step 5418 | loss:1.9993953704833984 lr:4.9478400889287705e-05 tokens_per_second_per_gpu:785.3093816969084 +Step 5419 | loss:2.069983959197998 lr:4.944444723296061e-05 tokens_per_second_per_gpu:780.9427891963891 +Step 5420 | loss:2.034330368041992 lr:4.9410501404214124e-05 tokens_per_second_per_gpu:747.6656901926616 +Step 5421 | loss:1.9426581859588623 lr:4.9376563408304056e-05 tokens_per_second_per_gpu:780.2734856192633 +Step 5422 | loss:1.991487979888916 lr:4.934263325048508e-05 tokens_per_second_per_gpu:753.9085442608459 +Step 5423 | loss:2.011357307434082 lr:4.9308710936010674e-05 tokens_per_second_per_gpu:755.90184518773 +Step 5424 | loss:2.0090155601501465 lr:4.9274796470133054e-05 tokens_per_second_per_gpu:791.7433884127448 +Step 5425 | loss:2.0579357147216797 lr:4.924088985810324e-05 tokens_per_second_per_gpu:720.3604083971258 +Step 5426 | loss:2.012458324432373 lr:4.9206991105171094e-05 tokens_per_second_per_gpu:738.4387981280753 +Step 5427 | loss:2.033115863800049 lr:4.9173100216585076e-05 tokens_per_second_per_gpu:742.3026237603398 +Step 5428 | loss:2.0208706855773926 lr:4.91392171975927e-05 tokens_per_second_per_gpu:776.2420279488306 +Step 5429 | loss:1.992253065109253 lr:4.910534205344001e-05 tokens_per_second_per_gpu:775.8550839236086 +Step 5430 | loss:1.9882525205612183 lr:4.9071474789371974e-05 tokens_per_second_per_gpu:750.9664433791113 +Step 5431 | loss:2.0710926055908203 lr:4.903761541063231e-05 tokens_per_second_per_gpu:755.927931979242 +Step 5432 | loss:2.0262677669525146 lr:4.900376392246354e-05 tokens_per_second_per_gpu:776.5083555569876 +Step 5433 | loss:2.011319160461426 lr:4.8969920330106813e-05 tokens_per_second_per_gpu:797.7605005673681 +Step 5434 | loss:2.0446054935455322 lr:4.89360846388023e-05 tokens_per_second_per_gpu:787.7223093619747 +Step 5435 | loss:1.994767665863037 lr:4.890225685378883e-05 tokens_per_second_per_gpu:769.3008469151101 +Step 5436 | loss:2.030381202697754 lr:4.886843698030391e-05 tokens_per_second_per_gpu:739.9156447561702 +Step 5437 | loss:1.980269432067871 lr:4.883462502358397e-05 tokens_per_second_per_gpu:794.0029047406762 +Step 5438 | loss:2.0702857971191406 lr:4.880082098886414e-05 tokens_per_second_per_gpu:772.3727982303633 +Step 5439 | loss:2.0784354209899902 lr:4.8767024881378346e-05 tokens_per_second_per_gpu:764.5920427900096 +Step 5440 | loss:2.029099941253662 lr:4.873323670635929e-05 tokens_per_second_per_gpu:746.4503802595171 +Step 5441 | loss:1.9776298999786377 lr:4.8699456469038474e-05 tokens_per_second_per_gpu:771.4287932723845 +Step 5442 | loss:1.9738991260528564 lr:4.866568417464605e-05 tokens_per_second_per_gpu:779.0873974895784 +Step 5443 | loss:2.0247583389282227 lr:4.863191982841107e-05 tokens_per_second_per_gpu:777.2973381853557 +Step 5444 | loss:2.0222058296203613 lr:4.859816343556132e-05 tokens_per_second_per_gpu:780.5107925530573 +Step 5445 | loss:1.9751230478286743 lr:4.856441500132333e-05 tokens_per_second_per_gpu:746.5470292671557 +Step 5446 | loss:2.020456075668335 lr:4.8530674530922415e-05 tokens_per_second_per_gpu:791.4188662949704 +Step 5447 | loss:2.00166654586792 lr:4.84969420295827e-05 tokens_per_second_per_gpu:773.1714197569926 +Step 5448 | loss:1.9575114250183105 lr:4.846321750252696e-05 tokens_per_second_per_gpu:792.5083182480626 +Step 5449 | loss:2.0060994625091553 lr:4.8429500954976835e-05 tokens_per_second_per_gpu:774.2112998563255 +Step 5450 | loss:2.0011723041534424 lr:4.839579239215269e-05 tokens_per_second_per_gpu:773.3459734367206 +Step 5451 | loss:1.9816142320632935 lr:4.836209181927369e-05 tokens_per_second_per_gpu:750.599555767883 +Step 5452 | loss:1.9653668403625488 lr:4.832839924155773e-05 tokens_per_second_per_gpu:784.2145722639011 +Step 5453 | loss:2.004593849182129 lr:4.8294714664221494e-05 tokens_per_second_per_gpu:783.1242491273323 +Step 5454 | loss:2.067108631134033 lr:4.826103809248031e-05 tokens_per_second_per_gpu:778.9942473290289 +Step 5455 | loss:1.9979640245437622 lr:4.8227369531548526e-05 tokens_per_second_per_gpu:752.4258079857495 +Step 5456 | loss:2.0328269004821777 lr:4.8193708986638953e-05 tokens_per_second_per_gpu:775.3704109063798 +Step 5457 | loss:1.979628562927246 lr:4.8160056462963346e-05 tokens_per_second_per_gpu:785.1565320417844 +Step 5458 | loss:1.9978880882263184 lr:4.8126411965732164e-05 tokens_per_second_per_gpu:791.6480456580955 +Step 5459 | loss:2.0084939002990723 lr:4.8092775500154666e-05 tokens_per_second_per_gpu:753.3413926546401 +Step 5460 | loss:2.0547239780426025 lr:4.8059147071438715e-05 tokens_per_second_per_gpu:772.8908267242738 +Step 5461 | loss:2.0174970626831055 lr:4.802552668479115e-05 tokens_per_second_per_gpu:773.9972762565059 +Step 5462 | loss:1.9954921007156372 lr:4.799191434541749e-05 tokens_per_second_per_gpu:771.6239540413009 +Step 5463 | loss:2.0210516452789307 lr:4.795831005852186e-05 tokens_per_second_per_gpu:780.8157567192965 +Step 5464 | loss:2.0074572563171387 lr:4.792471382930731e-05 tokens_per_second_per_gpu:778.3526770740563 +Step 5465 | loss:2.012789011001587 lr:4.789112566297559e-05 tokens_per_second_per_gpu:789.9287567656497 +Step 5466 | loss:1.959692358970642 lr:4.785754556472718e-05 tokens_per_second_per_gpu:774.846985216371 +Step 5467 | loss:1.9912505149841309 lr:4.782397353976136e-05 tokens_per_second_per_gpu:726.3865258601443 +Step 5468 | loss:2.06777286529541 lr:4.779040959327614e-05 tokens_per_second_per_gpu:749.6431777747023 +Step 5469 | loss:1.9471793174743652 lr:4.775685373046821e-05 tokens_per_second_per_gpu:763.8377544955721 +Step 5470 | loss:1.9805225133895874 lr:4.77233059565331e-05 tokens_per_second_per_gpu:782.9448637880399 +Step 5471 | loss:2.0951924324035645 lr:4.768976627666505e-05 tokens_per_second_per_gpu:756.0210572011106 +Step 5472 | loss:1.949456810951233 lr:4.7656234696057055e-05 tokens_per_second_per_gpu:754.7978566999493 +Step 5473 | loss:2.066957712173462 lr:4.762271121990085e-05 tokens_per_second_per_gpu:766.1448920387209 +Step 5474 | loss:1.9979815483093262 lr:4.7589195853386956e-05 tokens_per_second_per_gpu:784.1057252734713 +Step 5475 | loss:2.0436251163482666 lr:4.755568860170453e-05 tokens_per_second_per_gpu:770.1011956680975 +Step 5476 | loss:2.028742551803589 lr:4.752218947004158e-05 tokens_per_second_per_gpu:762.9116464792667 +Step 5477 | loss:2.020498752593994 lr:4.7488698463584804e-05 tokens_per_second_per_gpu:747.9506021703745 +Step 5478 | loss:1.979203462600708 lr:4.745521558751968e-05 tokens_per_second_per_gpu:792.1846305055979 +Step 5479 | loss:2.05822491645813 lr:4.742174084703037e-05 tokens_per_second_per_gpu:751.8474878902407 +Step 5480 | loss:1.952701449394226 lr:4.738827424729989e-05 tokens_per_second_per_gpu:774.2619755323392 +Step 5481 | loss:1.9437758922576904 lr:4.735481579350978e-05 tokens_per_second_per_gpu:792.11840957636 +Step 5482 | loss:2.006190538406372 lr:4.73213654908406e-05 tokens_per_second_per_gpu:790.7129571377003 +Step 5483 | loss:1.9908138513565063 lr:4.728792334447141e-05 tokens_per_second_per_gpu:779.2509720420474 +Step 5484 | loss:2.0789175033569336 lr:4.7254489359580126e-05 tokens_per_second_per_gpu:777.5593056546013 +Step 5485 | loss:2.0306596755981445 lr:4.722106354134337e-05 tokens_per_second_per_gpu:787.6675009676662 +Step 5486 | loss:2.0225472450256348 lr:4.718764589493651e-05 tokens_per_second_per_gpu:782.7443778223368 +Step 5487 | loss:2.034362316131592 lr:4.715423642553364e-05 tokens_per_second_per_gpu:780.2993389757596 +Step 5488 | loss:2.133183240890503 lr:4.712083513830759e-05 tokens_per_second_per_gpu:759.1981651713295 +Step 5489 | loss:1.974090576171875 lr:4.7087442038429974e-05 tokens_per_second_per_gpu:761.9887626763616 +Step 5490 | loss:1.9869532585144043 lr:4.7054057131071006e-05 tokens_per_second_per_gpu:755.4256342021074 +Step 5491 | loss:2.004333734512329 lr:4.702068042139973e-05 tokens_per_second_per_gpu:777.6489393567676 +Step 5492 | loss:1.9880388975143433 lr:4.698731191458394e-05 tokens_per_second_per_gpu:777.4710986223523 +Step 5493 | loss:2.007833480834961 lr:4.6953951615790104e-05 tokens_per_second_per_gpu:767.4851688935818 +Step 5494 | loss:2.0005381107330322 lr:4.692059953018344e-05 tokens_per_second_per_gpu:780.9840032654943 +Step 5495 | loss:2.01167368888855 lr:4.688725566292793e-05 tokens_per_second_per_gpu:769.8831554096369 +Step 5496 | loss:1.9974818229675293 lr:4.685392001918618e-05 tokens_per_second_per_gpu:791.2325483718976 +Step 5497 | loss:2.072230339050293 lr:4.682059260411963e-05 tokens_per_second_per_gpu:751.2117388796261 +Step 5498 | loss:2.037156581878662 lr:4.67872734228884e-05 tokens_per_second_per_gpu:798.4301458497669 +Step 5499 | loss:2.0172603130340576 lr:4.6753962480651336e-05 tokens_per_second_per_gpu:785.9914655650928 +Step 5500 | loss:2.0146772861480713 lr:4.672065978256601e-05 tokens_per_second_per_gpu:782.6647879508288 +Step 5501 | loss:2.0062384605407715 lr:4.6687365333788776e-05 tokens_per_second_per_gpu:770.0828960596132 +Step 5502 | loss:1.983027696609497 lr:4.665407913947454e-05 tokens_per_second_per_gpu:771.6311403241032 +Step 5503 | loss:2.0413787364959717 lr:4.662080120477719e-05 tokens_per_second_per_gpu:776.8934167778419 +Step 5504 | loss:1.9760783910751343 lr:4.6587531534849074e-05 tokens_per_second_per_gpu:772.2667776477533 +Step 5505 | loss:2.0141584873199463 lr:4.6554270134841425e-05 tokens_per_second_per_gpu:765.554724166932 +Step 5506 | loss:2.0628950595855713 lr:4.6521017009904136e-05 tokens_per_second_per_gpu:754.6778632285669 +Step 5507 | loss:2.051145076751709 lr:4.648777216518588e-05 tokens_per_second_per_gpu:794.6491906230583 +Step 5508 | loss:2.0265984535217285 lr:4.645453560583388e-05 tokens_per_second_per_gpu:759.0798602789887 +Step 5509 | loss:2.024074077606201 lr:4.642130733699434e-05 tokens_per_second_per_gpu:783.580450114037 +Step 5510 | loss:2.0355329513549805 lr:4.6388087363811935e-05 tokens_per_second_per_gpu:765.0353752822542 +Step 5511 | loss:2.0006887912750244 lr:4.635487569143019e-05 tokens_per_second_per_gpu:770.6050589008811 +Step 5512 | loss:1.997809886932373 lr:4.6321672324991306e-05 tokens_per_second_per_gpu:770.4825355089245 +Step 5513 | loss:1.9931286573410034 lr:4.62884772696362e-05 tokens_per_second_per_gpu:750.8121509505021 +Step 5514 | loss:2.0194549560546875 lr:4.625529053050451e-05 tokens_per_second_per_gpu:751.7331453027881 +Step 5515 | loss:2.0165374279022217 lr:4.622211211273458e-05 tokens_per_second_per_gpu:762.2555522763774 +Step 5516 | loss:2.0349647998809814 lr:4.618894202146351e-05 tokens_per_second_per_gpu:770.8844564294286 +Step 5517 | loss:2.048881769180298 lr:4.615578026182697e-05 tokens_per_second_per_gpu:782.0102735858171 +Step 5518 | loss:1.9759130477905273 lr:4.612262683895951e-05 tokens_per_second_per_gpu:748.8225315430941 +Step 5519 | loss:2.0193819999694824 lr:4.608948175799429e-05 tokens_per_second_per_gpu:795.1423288004418 +Step 5520 | loss:2.0026135444641113 lr:4.605634502406321e-05 tokens_per_second_per_gpu:776.9313504671701 +Step 5521 | loss:2.0275890827178955 lr:4.6023216642296885e-05 tokens_per_second_per_gpu:759.394085327586 +Step 5522 | loss:2.0166070461273193 lr:4.599009661782464e-05 tokens_per_second_per_gpu:756.8526879059134 +Step 5523 | loss:2.053161382675171 lr:4.595698495577443e-05 tokens_per_second_per_gpu:762.9104982618562 +Step 5524 | loss:1.9922802448272705 lr:4.5923881661273015e-05 tokens_per_second_per_gpu:779.7895360951419 +Step 5525 | loss:1.99817955493927 lr:4.589078673944581e-05 tokens_per_second_per_gpu:782.7978907194721 +Step 5526 | loss:2.070887565612793 lr:4.5857700195416965e-05 tokens_per_second_per_gpu:772.0893118169425 +Step 5527 | loss:1.9788234233856201 lr:4.582462203430928e-05 tokens_per_second_per_gpu:790.4172694057797 +Step 5528 | loss:2.0203630924224854 lr:4.579155226124436e-05 tokens_per_second_per_gpu:778.2599797756326 +Step 5529 | loss:2.014127731323242 lr:4.57584908813423e-05 tokens_per_second_per_gpu:772.67141326638 +Step 5530 | loss:1.989768385887146 lr:4.57254378997222e-05 tokens_per_second_per_gpu:774.2603224174115 +Step 5531 | loss:2.0748157501220703 lr:4.569239332150158e-05 tokens_per_second_per_gpu:746.859940172274 +Step 5532 | loss:2.0527491569519043 lr:4.565935715179681e-05 tokens_per_second_per_gpu:760.5286772988427 +Step 5533 | loss:2.0041542053222656 lr:4.5626329395722924e-05 tokens_per_second_per_gpu:779.661191755216 +Step 5534 | loss:1.96298086643219 lr:4.559331005839368e-05 tokens_per_second_per_gpu:773.184956180438 +Step 5535 | loss:2.032604217529297 lr:4.5560299144921403e-05 tokens_per_second_per_gpu:770.0676986985253 +Step 5536 | loss:2.0368971824645996 lr:4.552729666041736e-05 tokens_per_second_per_gpu:712.0262345937801 +Step 5537 | loss:2.0677146911621094 lr:4.5494302609991266e-05 tokens_per_second_per_gpu:770.0738219386757 +Step 5538 | loss:2.0530683994293213 lr:4.5461316998751654e-05 tokens_per_second_per_gpu:775.2013087037361 +Step 5539 | loss:2.04192852973938 lr:4.5428339831805734e-05 tokens_per_second_per_gpu:736.7954814273928 +Step 5540 | loss:2.00752329826355 lr:4.53953711142594e-05 tokens_per_second_per_gpu:769.9150288077125 +Step 5541 | loss:1.9874427318572998 lr:4.5362410851217255e-05 tokens_per_second_per_gpu:778.6623814462644 +Step 5542 | loss:1.9884661436080933 lr:4.532945904778255e-05 tokens_per_second_per_gpu:768.6898632562641 +Step 5543 | loss:2.0792996883392334 lr:4.529651570905732e-05 tokens_per_second_per_gpu:779.2154969010791 +Step 5544 | loss:2.0281383991241455 lr:4.526358084014213e-05 tokens_per_second_per_gpu:758.1984919835095 +Step 5545 | loss:2.065526008605957 lr:4.5230654446136375e-05 tokens_per_second_per_gpu:767.941528501242 +Step 5546 | loss:2.008186101913452 lr:4.519773653213809e-05 tokens_per_second_per_gpu:789.2402177630019 +Step 5547 | loss:2.0768096446990967 lr:4.5164827103244e-05 tokens_per_second_per_gpu:745.0491953086267 +Step 5548 | loss:2.0065767765045166 lr:4.51319261645495e-05 tokens_per_second_per_gpu:744.8145905255316 +Step 5549 | loss:1.9881458282470703 lr:4.509903372114874e-05 tokens_per_second_per_gpu:786.8653213024808 +Step 5550 | loss:1.9630959033966064 lr:4.506614977813441e-05 tokens_per_second_per_gpu:741.3780642440624 +Step 5551 | loss:1.973345398902893 lr:4.5033274340598016e-05 tokens_per_second_per_gpu:775.0878665819656 +Step 5552 | loss:2.002117156982422 lr:4.500040741362971e-05 tokens_per_second_per_gpu:766.7765697799272 +Step 5553 | loss:1.9500200748443604 lr:4.49675490023183e-05 tokens_per_second_per_gpu:772.2877540105898 +Step 5554 | loss:2.027252674102783 lr:4.493469911175132e-05 tokens_per_second_per_gpu:751.6328443679166 +Step 5555 | loss:2.0208513736724854 lr:4.4901857747014985e-05 tokens_per_second_per_gpu:761.579023234984 +Step 5556 | loss:2.0387582778930664 lr:4.486902491319406e-05 tokens_per_second_per_gpu:774.4948343233611 +Step 5557 | loss:1.9690608978271484 lr:4.4836200615372224e-05 tokens_per_second_per_gpu:768.8341211712736 +Step 5558 | loss:2.0290191173553467 lr:4.480338485863163e-05 tokens_per_second_per_gpu:751.5419819212603 +Step 5559 | loss:1.9951602220535278 lr:4.477057764805318e-05 tokens_per_second_per_gpu:748.7167839525553 +Step 5560 | loss:2.027251720428467 lr:4.473777898871647e-05 tokens_per_second_per_gpu:743.6252520690239 +Step 5561 | loss:1.9835853576660156 lr:4.4704988885699785e-05 tokens_per_second_per_gpu:748.9769299249575 +Step 5562 | loss:1.9695335626602173 lr:4.467220734408002e-05 tokens_per_second_per_gpu:764.7896852022159 +Step 5563 | loss:1.9642188549041748 lr:4.463943436893283e-05 tokens_per_second_per_gpu:741.90643673649 +Step 5564 | loss:1.9959805011749268 lr:4.460666996533245e-05 tokens_per_second_per_gpu:754.1879537778304 +Step 5565 | loss:2.0474905967712402 lr:4.4573914138351836e-05 tokens_per_second_per_gpu:750.2103009395291 +Step 5566 | loss:1.9857748746871948 lr:4.454116689306262e-05 tokens_per_second_per_gpu:743.9501381366304 +Step 5567 | loss:2.0473246574401855 lr:4.4508428234535114e-05 tokens_per_second_per_gpu:779.0048494410761 +Step 5568 | loss:2.0650603771209717 lr:4.4475698167838284e-05 tokens_per_second_per_gpu:769.9765699326924 +Step 5569 | loss:1.9354192018508911 lr:4.444297669803981e-05 tokens_per_second_per_gpu:771.6748180806857 +Step 5570 | loss:2.0088157653808594 lr:4.44102638302059e-05 tokens_per_second_per_gpu:743.9983854520011 +Step 5571 | loss:2.058619976043701 lr:4.437755956940158e-05 tokens_per_second_per_gpu:771.5180409362662 +Step 5572 | loss:1.957146167755127 lr:4.434486392069051e-05 tokens_per_second_per_gpu:754.1301110067624 +Step 5573 | loss:2.0362110137939453 lr:4.431217688913497e-05 tokens_per_second_per_gpu:769.7898438120752 +Step 5574 | loss:1.9875619411468506 lr:4.427949847979595e-05 tokens_per_second_per_gpu:766.6297182349526 +Step 5575 | loss:1.9720444679260254 lr:4.424682869773309e-05 tokens_per_second_per_gpu:755.5834166178124 +Step 5576 | loss:2.0212085247039795 lr:4.421416754800473e-05 tokens_per_second_per_gpu:774.5553941893354 +Step 5577 | loss:2.020555257797241 lr:4.4181515035667756e-05 tokens_per_second_per_gpu:743.6519994024504 +Step 5578 | loss:1.9564528465270996 lr:4.414887116577784e-05 tokens_per_second_per_gpu:744.201323247891 +Step 5579 | loss:2.028141498565674 lr:4.411623594338927e-05 tokens_per_second_per_gpu:775.1760851507689 +Step 5580 | loss:2.0501859188079834 lr:4.408360937355501e-05 tokens_per_second_per_gpu:733.0617933071105 +Step 5581 | loss:1.9722654819488525 lr:4.405099146132666e-05 tokens_per_second_per_gpu:787.587962721333 +Step 5582 | loss:2.024653196334839 lr:4.4018382211754546e-05 tokens_per_second_per_gpu:783.744256877631 +Step 5583 | loss:2.0100271701812744 lr:4.398578162988748e-05 tokens_per_second_per_gpu:793.7257520413989 +Step 5584 | loss:1.9943896532058716 lr:4.3953189720773194e-05 tokens_per_second_per_gpu:769.7580612608791 +Step 5585 | loss:2.001828670501709 lr:4.392060648945783e-05 tokens_per_second_per_gpu:801.5569925607227 +Step 5586 | loss:1.9486899375915527 lr:4.388803194098632e-05 tokens_per_second_per_gpu:798.4466342574407 +Step 5587 | loss:2.097923755645752 lr:4.385546608040223e-05 tokens_per_second_per_gpu:751.0265644052022 +Step 5588 | loss:2.0415565967559814 lr:4.382290891274778e-05 tokens_per_second_per_gpu:779.2922405892995 +Step 5589 | loss:2.018734931945801 lr:4.379036044306383e-05 tokens_per_second_per_gpu:761.657541990956 +Step 5590 | loss:2.002894401550293 lr:4.375782067638994e-05 tokens_per_second_per_gpu:752.0429056559193 +Step 5591 | loss:2.0711822509765625 lr:4.37252896177642e-05 tokens_per_second_per_gpu:783.6924115304452 +Step 5592 | loss:1.9741120338439941 lr:4.3692767272223486e-05 tokens_per_second_per_gpu:778.8442256753358 +Step 5593 | loss:1.9263619184494019 lr:4.366025364480327e-05 tokens_per_second_per_gpu:775.2432267114225 +Step 5594 | loss:2.0230257511138916 lr:4.362774874053768e-05 tokens_per_second_per_gpu:779.166722397006 +Step 5595 | loss:2.048288583755493 lr:4.359525256445948e-05 tokens_per_second_per_gpu:738.5165699058705 +Step 5596 | loss:2.010828733444214 lr:4.356276512160014e-05 tokens_per_second_per_gpu:801.3979407665522 +Step 5597 | loss:1.9863224029541016 lr:4.3530286416989665e-05 tokens_per_second_per_gpu:774.6018393168299 +Step 5598 | loss:2.0099236965179443 lr:4.3497816455656806e-05 tokens_per_second_per_gpu:765.421394733191 +Step 5599 | loss:1.928755760192871 lr:4.346535524262891e-05 tokens_per_second_per_gpu:763.6804089645544 +Step 5600 | loss:1.9822814464569092 lr:4.3432902782932016e-05 tokens_per_second_per_gpu:756.4590693868289 +Step 5601 | loss:2.0467140674591064 lr:4.3400459081590774e-05 tokens_per_second_per_gpu:787.2119601340216 +Step 5602 | loss:2.0174922943115234 lr:4.336802414362847e-05 tokens_per_second_per_gpu:785.9435006360634 +Step 5603 | loss:1.995692491531372 lr:4.333559797406709e-05 tokens_per_second_per_gpu:764.1655902605096 +Step 5604 | loss:1.9616774320602417 lr:4.330318057792712e-05 tokens_per_second_per_gpu:759.623751484848 +Step 5605 | loss:1.9800182580947876 lr:4.327077196022791e-05 tokens_per_second_per_gpu:766.5776357516273 +Step 5606 | loss:2.006925582885742 lr:4.323837212598724e-05 tokens_per_second_per_gpu:781.0244491281579 +Step 5607 | loss:2.052060604095459 lr:4.3205981080221644e-05 tokens_per_second_per_gpu:728.0182430586876 +Step 5608 | loss:2.023042917251587 lr:4.317359882794627e-05 tokens_per_second_per_gpu:766.4490778643772 +Step 5609 | loss:2.00913143157959 lr:4.314122537417493e-05 tokens_per_second_per_gpu:800.2913707861773 +Step 5610 | loss:2.0039901733398438 lr:4.310886072391996e-05 tokens_per_second_per_gpu:793.4742778466637 +Step 5611 | loss:1.9877111911773682 lr:4.307650488219255e-05 tokens_per_second_per_gpu:782.4117215448008 +Step 5612 | loss:1.9959019422531128 lr:4.30441578540023e-05 tokens_per_second_per_gpu:781.9176426036689 +Step 5613 | loss:2.0447781085968018 lr:4.301181964435755e-05 tokens_per_second_per_gpu:770.1549998194638 +Step 5614 | loss:2.03387451171875 lr:4.2979490258265296e-05 tokens_per_second_per_gpu:766.7623800267041 +Step 5615 | loss:1.9975380897521973 lr:4.294716970073113e-05 tokens_per_second_per_gpu:783.7194209817 +Step 5616 | loss:2.0067572593688965 lr:4.291485797675927e-05 tokens_per_second_per_gpu:748.0627809530198 +Step 5617 | loss:2.0295348167419434 lr:4.288255509135263e-05 tokens_per_second_per_gpu:797.9861796834098 +Step 5618 | loss:2.0253658294677734 lr:4.285026104951264e-05 tokens_per_second_per_gpu:775.3327305520909 +Step 5619 | loss:1.9717117547988892 lr:4.2817975856239444e-05 tokens_per_second_per_gpu:779.2567937644858 +Step 5620 | loss:2.028944969177246 lr:4.278569951653183e-05 tokens_per_second_per_gpu:774.539516298708 +Step 5621 | loss:2.067782163619995 lr:4.2753432035387163e-05 tokens_per_second_per_gpu:760.016256010863 +Step 5622 | loss:2.033233880996704 lr:4.2721173417801454e-05 tokens_per_second_per_gpu:763.9734298835481 +Step 5623 | loss:2.0592851638793945 lr:4.2688923668769395e-05 tokens_per_second_per_gpu:763.375898795557 +Step 5624 | loss:1.925544023513794 lr:4.2656682793284185e-05 tokens_per_second_per_gpu:796.5437223267896 +Step 5625 | loss:2.009007453918457 lr:4.262445079633774e-05 tokens_per_second_per_gpu:789.2218196096348 +Step 5626 | loss:2.068586587905884 lr:4.259222768292061e-05 tokens_per_second_per_gpu:766.4993172864575 +Step 5627 | loss:1.9804668426513672 lr:4.2560013458021894e-05 tokens_per_second_per_gpu:769.0540580274796 +Step 5628 | loss:1.9966007471084595 lr:4.252780812662941e-05 tokens_per_second_per_gpu:792.819070826742 +Step 5629 | loss:1.9923360347747803 lr:4.249561169372952e-05 tokens_per_second_per_gpu:788.0261839817127 +Step 5630 | loss:2.018833637237549 lr:4.2463424164307285e-05 tokens_per_second_per_gpu:754.3902530915846 +Step 5631 | loss:1.9334900379180908 lr:4.243124554334623e-05 tokens_per_second_per_gpu:789.498267029674 +Step 5632 | loss:2.09855318069458 lr:4.239907583582877e-05 tokens_per_second_per_gpu:758.9394339659275 +Step 5633 | loss:2.106083631515503 lr:4.2366915046735656e-05 tokens_per_second_per_gpu:763.1959043110024 +Step 5634 | loss:2.01037859916687 lr:4.233476318104642e-05 tokens_per_second_per_gpu:802.09291467039 +Step 5635 | loss:1.9555695056915283 lr:4.230262024373919e-05 tokens_per_second_per_gpu:773.487442135419 +Step 5636 | loss:1.989135980606079 lr:4.227048623979072e-05 tokens_per_second_per_gpu:762.0918269791922 +Step 5637 | loss:2.025773763656616 lr:4.223836117417626e-05 tokens_per_second_per_gpu:783.650842001034 +Step 5638 | loss:2.0319461822509766 lr:4.220624505186992e-05 tokens_per_second_per_gpu:763.3391327563405 +Step 5639 | loss:1.9605088233947754 lr:4.217413787784416e-05 tokens_per_second_per_gpu:777.7869283867244 +Step 5640 | loss:2.029505729675293 lr:4.214203965707022e-05 tokens_per_second_per_gpu:789.5972444166038 +Step 5641 | loss:1.9942749738693237 lr:4.2109950394517906e-05 tokens_per_second_per_gpu:771.4620991338151 +Step 5642 | loss:2.014512062072754 lr:4.207787009515564e-05 tokens_per_second_per_gpu:794.4626643491499 +Step 5643 | loss:2.05462646484375 lr:4.2045798763950465e-05 tokens_per_second_per_gpu:784.8959353879385 +Step 5644 | loss:1.9211552143096924 lr:4.201373640586803e-05 tokens_per_second_per_gpu:778.5234036526938 +Step 5645 | loss:1.944967269897461 lr:4.1981683025872566e-05 tokens_per_second_per_gpu:781.6664454738994 +Step 5646 | loss:2.020273447036743 lr:4.194963862892694e-05 tokens_per_second_per_gpu:778.5049113054914 +Step 5647 | loss:1.9500007629394531 lr:4.191760321999263e-05 tokens_per_second_per_gpu:786.9626895858261 +Step 5648 | loss:2.0195631980895996 lr:4.1885576804029734e-05 tokens_per_second_per_gpu:778.3738536915076 +Step 5649 | loss:2.0518531799316406 lr:4.1853559385996936e-05 tokens_per_second_per_gpu:792.6443968148862 +Step 5650 | loss:1.9825025796890259 lr:4.182155097085156e-05 tokens_per_second_per_gpu:757.2996323787827 +Step 5651 | loss:1.9953124523162842 lr:4.178955156354945e-05 tokens_per_second_per_gpu:780.7814141598823 +Step 5652 | loss:2.0198092460632324 lr:4.1757561169045145e-05 tokens_per_second_per_gpu:780.7137563614781 +Step 5653 | loss:2.007993698120117 lr:4.172557979229177e-05 tokens_per_second_per_gpu:772.220447107912 +Step 5654 | loss:2.077463388442993 lr:4.169360743824102e-05 tokens_per_second_per_gpu:774.6144253401828 +Step 5655 | loss:1.9537808895111084 lr:4.1661644111843235e-05 tokens_per_second_per_gpu:774.4281347867319 +Step 5656 | loss:2.025118827819824 lr:4.1629689818047326e-05 tokens_per_second_per_gpu:777.0644323929093 +Step 5657 | loss:1.9997284412384033 lr:4.1597744561800854e-05 tokens_per_second_per_gpu:783.845901789924 +Step 5658 | loss:1.9711942672729492 lr:4.156580834804984e-05 tokens_per_second_per_gpu:757.0477228597587 +Step 5659 | loss:2.0695128440856934 lr:4.153388118173915e-05 tokens_per_second_per_gpu:787.930242049774 +Step 5660 | loss:2.015627384185791 lr:4.150196306781201e-05 tokens_per_second_per_gpu:797.7791532324962 +Step 5661 | loss:2.0667221546173096 lr:4.147005401121037e-05 tokens_per_second_per_gpu:799.5921854970206 +Step 5662 | loss:2.027060031890869 lr:4.143815401687474e-05 tokens_per_second_per_gpu:781.6389679596118 +Step 5663 | loss:1.9861506223678589 lr:4.1406263089744255e-05 tokens_per_second_per_gpu:771.734698031246 +Step 5664 | loss:1.9767255783081055 lr:4.137438123475662e-05 tokens_per_second_per_gpu:795.323318028491 +Step 5665 | loss:2.007624626159668 lr:4.134250845684817e-05 tokens_per_second_per_gpu:765.1375182846372 +Step 5666 | loss:1.9957059621810913 lr:4.131064476095374e-05 tokens_per_second_per_gpu:759.0773461709675 +Step 5667 | loss:2.0721917152404785 lr:4.1278790152006874e-05 tokens_per_second_per_gpu:784.0007138573194 +Step 5668 | loss:2.0344319343566895 lr:4.124694463493966e-05 tokens_per_second_per_gpu:761.0768416844845 +Step 5669 | loss:2.049445867538452 lr:4.1215108214682763e-05 tokens_per_second_per_gpu:738.801371265622 +Step 5670 | loss:2.00111722946167 lr:4.118328089616547e-05 tokens_per_second_per_gpu:782.4713511683731 +Step 5671 | loss:1.969623327255249 lr:4.115146268431568e-05 tokens_per_second_per_gpu:738.8466943961441 +Step 5672 | loss:2.0530991554260254 lr:4.111965358405977e-05 tokens_per_second_per_gpu:793.1963575360758 +Step 5673 | loss:2.0197248458862305 lr:4.108785360032283e-05 tokens_per_second_per_gpu:781.6619709503577 +Step 5674 | loss:1.954407811164856 lr:4.105606273802848e-05 tokens_per_second_per_gpu:770.0689760038179 +Step 5675 | loss:2.001040458679199 lr:4.1024281002098955e-05 tokens_per_second_per_gpu:778.8937267208073 +Step 5676 | loss:1.9666798114776611 lr:4.099250839745503e-05 tokens_per_second_per_gpu:799.4248796448757 +Step 5677 | loss:2.0172030925750732 lr:4.096074492901617e-05 tokens_per_second_per_gpu:777.089313709985 +Step 5678 | loss:2.0581352710723877 lr:4.092899060170027e-05 tokens_per_second_per_gpu:781.9133475555236 +Step 5679 | loss:2.0626068115234375 lr:4.089724542042389e-05 tokens_per_second_per_gpu:756.2257575085833 +Step 5680 | loss:1.9865474700927734 lr:4.086550939010227e-05 tokens_per_second_per_gpu:755.0986698696677 +Step 5681 | loss:1.987177848815918 lr:4.083378251564905e-05 tokens_per_second_per_gpu:768.5015930668221 +Step 5682 | loss:2.0011544227600098 lr:4.080206480197659e-05 tokens_per_second_per_gpu:705.9064065794955 +Step 5683 | loss:1.9565716981887817 lr:4.0770356253995756e-05 tokens_per_second_per_gpu:796.594409031386 +Step 5684 | loss:1.977481484413147 lr:4.073865687661608e-05 tokens_per_second_per_gpu:775.5178918420568 +Step 5685 | loss:2.0317723751068115 lr:4.070696667474549e-05 tokens_per_second_per_gpu:788.1699116595239 +Step 5686 | loss:1.9522382020950317 lr:4.067528565329078e-05 tokens_per_second_per_gpu:779.4989213562063 +Step 5687 | loss:2.0738110542297363 lr:4.0643613817157045e-05 tokens_per_second_per_gpu:789.8732618835447 +Step 5688 | loss:2.001922607421875 lr:4.0611951171248116e-05 tokens_per_second_per_gpu:772.7740648476889 +Step 5689 | loss:2.000998020172119 lr:4.058029772046638e-05 tokens_per_second_per_gpu:762.3323811217774 +Step 5690 | loss:2.015669584274292 lr:4.054865346971274e-05 tokens_per_second_per_gpu:757.7207883685801 +Step 5691 | loss:2.042313814163208 lr:4.051701842388674e-05 tokens_per_second_per_gpu:765.8321787345253 +Step 5692 | loss:2.010005474090576 lr:4.048539258788652e-05 tokens_per_second_per_gpu:781.7650113039449 +Step 5693 | loss:2.026371717453003 lr:4.045377596660866e-05 tokens_per_second_per_gpu:755.118679673283 +Step 5694 | loss:2.083099365234375 lr:4.042216856494844e-05 tokens_per_second_per_gpu:783.1716674427556 +Step 5695 | loss:1.9755357503890991 lr:4.0390570387799666e-05 tokens_per_second_per_gpu:774.7936471604677 +Step 5696 | loss:1.9913333654403687 lr:4.0358981440054744e-05 tokens_per_second_per_gpu:788.0994192291472 +Step 5697 | loss:1.9824891090393066 lr:4.032740172660462e-05 tokens_per_second_per_gpu:758.5574303334558 +Step 5698 | loss:2.039609432220459 lr:4.0295831252338866e-05 tokens_per_second_per_gpu:765.9298331202465 +Step 5699 | loss:2.0844566822052 lr:4.026427002214549e-05 tokens_per_second_per_gpu:774.4845346755405 +Step 5700 | loss:1.9673012495040894 lr:4.023271804091121e-05 tokens_per_second_per_gpu:778.9636620177463 +Step 5701 | loss:2.053431272506714 lr:4.0201175313521245e-05 tokens_per_second_per_gpu:781.5834387104037 +Step 5702 | loss:2.064954996109009 lr:4.016964184485941e-05 tokens_per_second_per_gpu:789.1230172369728 +Step 5703 | loss:1.9849694967269897 lr:4.013811763980806e-05 tokens_per_second_per_gpu:779.3975756435404 +Step 5704 | loss:2.0533220767974854 lr:4.010660270324816e-05 tokens_per_second_per_gpu:773.5033850341766 +Step 5705 | loss:1.980333924293518 lr:4.007509704005916e-05 tokens_per_second_per_gpu:784.7296458763218 +Step 5706 | loss:2.042769432067871 lr:4.00436006551191e-05 tokens_per_second_per_gpu:776.6533849026423 +Step 5707 | loss:2.026644468307495 lr:4.001211355330472e-05 tokens_per_second_per_gpu:759.7116364953445 +Step 5708 | loss:1.991330862045288 lr:3.99806357394911e-05 tokens_per_second_per_gpu:778.634019691105 +Step 5709 | loss:2.023383378982544 lr:3.994916721855202e-05 tokens_per_second_per_gpu:770.0421793894601 +Step 5710 | loss:1.9846432209014893 lr:3.99177079953598e-05 tokens_per_second_per_gpu:749.9575067399467 +Step 5711 | loss:1.9939299821853638 lr:3.988625807478534e-05 tokens_per_second_per_gpu:782.7553675527365 +Step 5712 | loss:1.949303150177002 lr:3.985481746169798e-05 tokens_per_second_per_gpu:787.0024491213823 +Step 5713 | loss:1.956350564956665 lr:3.9823386160965836e-05 tokens_per_second_per_gpu:762.2570261038077 +Step 5714 | loss:2.013054370880127 lr:3.979196417745536e-05 tokens_per_second_per_gpu:762.0757821262533 +Step 5715 | loss:2.0531692504882812 lr:3.9760551516031675e-05 tokens_per_second_per_gpu:752.5126911897406 +Step 5716 | loss:2.026951313018799 lr:3.972914818155846e-05 tokens_per_second_per_gpu:783.6186221498023 +Step 5717 | loss:2.0015501976013184 lr:3.969775417889793e-05 tokens_per_second_per_gpu:795.0549233059734 +Step 5718 | loss:1.9946914911270142 lr:3.966636951291086e-05 tokens_per_second_per_gpu:781.5675536640604 +Step 5719 | loss:2.0384531021118164 lr:3.963499418845661e-05 tokens_per_second_per_gpu:786.6534527825601 +Step 5720 | loss:1.9807606935501099 lr:3.9603628210392994e-05 tokens_per_second_per_gpu:789.1969965041238 +Step 5721 | loss:2.016278028488159 lr:3.957227158357647e-05 tokens_per_second_per_gpu:784.0031059976484 +Step 5722 | loss:1.9749360084533691 lr:3.9540924312862046e-05 tokens_per_second_per_gpu:803.736366963752 +Step 5723 | loss:1.945577621459961 lr:3.950958640310324e-05 tokens_per_second_per_gpu:714.9127677596072 +Step 5724 | loss:1.998060941696167 lr:3.9478257859152146e-05 tokens_per_second_per_gpu:786.2471416090744 +Step 5725 | loss:2.024376153945923 lr:3.9446938685859444e-05 tokens_per_second_per_gpu:766.7957790481895 +Step 5726 | loss:1.9714163541793823 lr:3.941562888807424e-05 tokens_per_second_per_gpu:795.2594088317038 +Step 5727 | loss:1.9351186752319336 lr:3.9384328470644314e-05 tokens_per_second_per_gpu:753.3596722267858 +Step 5728 | loss:1.9716987609863281 lr:3.9353037438415955e-05 tokens_per_second_per_gpu:754.0523940856842 +Step 5729 | loss:2.0020792484283447 lr:3.9321755796233986e-05 tokens_per_second_per_gpu:797.2314299731904 +Step 5730 | loss:1.978954553604126 lr:3.929048354894177e-05 tokens_per_second_per_gpu:774.4830750104502 +Step 5731 | loss:2.069448709487915 lr:3.925922070138128e-05 tokens_per_second_per_gpu:784.0838495411314 +Step 5732 | loss:1.9934717416763306 lr:3.922796725839292e-05 tokens_per_second_per_gpu:777.553518517391 +Step 5733 | loss:2.0449821949005127 lr:3.9196723224815676e-05 tokens_per_second_per_gpu:778.1336199489758 +Step 5734 | loss:2.010100841522217 lr:3.916548860548722e-05 tokens_per_second_per_gpu:781.3552851697144 +Step 5735 | loss:2.0787858963012695 lr:3.9134263405243555e-05 tokens_per_second_per_gpu:789.3455895124793 +Step 5736 | loss:1.9428367614746094 lr:3.910304762891933e-05 tokens_per_second_per_gpu:771.9053168783119 +Step 5737 | loss:1.9661009311676025 lr:3.9071841281347746e-05 tokens_per_second_per_gpu:760.9466721766464 +Step 5738 | loss:1.9834154844284058 lr:3.9040644367360534e-05 tokens_per_second_per_gpu:795.6846598458494 +Step 5739 | loss:2.0066707134246826 lr:3.900945689178786e-05 tokens_per_second_per_gpu:774.3778124062356 +Step 5740 | loss:2.058065176010132 lr:3.897827885945866e-05 tokens_per_second_per_gpu:791.7251720638809 +Step 5741 | loss:1.9912725687026978 lr:3.8947110275200164e-05 tokens_per_second_per_gpu:794.0565200251356 +Step 5742 | loss:1.9634802341461182 lr:3.891595114383827e-05 tokens_per_second_per_gpu:777.0733342500249 +Step 5743 | loss:2.0159735679626465 lr:3.8884801470197395e-05 tokens_per_second_per_gpu:790.0203761540693 +Step 5744 | loss:1.9713656902313232 lr:3.8853661259100484e-05 tokens_per_second_per_gpu:788.8050937350922 +Step 5745 | loss:2.0154223442077637 lr:3.8822530515369e-05 tokens_per_second_per_gpu:791.2986150417149 +Step 5746 | loss:1.965789556503296 lr:3.8791409243823015e-05 tokens_per_second_per_gpu:764.8481636599271 +Step 5747 | loss:2.0334103107452393 lr:3.8760297449280994e-05 tokens_per_second_per_gpu:726.6763181166498 +Step 5748 | loss:2.015873908996582 lr:3.872919513656005e-05 tokens_per_second_per_gpu:788.7753701976694 +Step 5749 | loss:1.9942340850830078 lr:3.869810231047578e-05 tokens_per_second_per_gpu:766.8624697411803 +Step 5750 | loss:1.9603079557418823 lr:3.866701897584234e-05 tokens_per_second_per_gpu:783.8000758940277 +Step 5751 | loss:2.0523602962493896 lr:3.863594513747241e-05 tokens_per_second_per_gpu:771.5713570109666 +Step 5752 | loss:1.966602087020874 lr:3.860488080017721e-05 tokens_per_second_per_gpu:775.092813367607 +Step 5753 | loss:2.0234882831573486 lr:3.857382596876642e-05 tokens_per_second_per_gpu:773.9884104960715 +Step 5754 | loss:2.03770112991333 lr:3.854278064804832e-05 tokens_per_second_per_gpu:775.5903822150846 +Step 5755 | loss:2.0157253742218018 lr:3.851174484282969e-05 tokens_per_second_per_gpu:751.8835729855253 +Step 5756 | loss:1.9865496158599854 lr:3.848071855791585e-05 tokens_per_second_per_gpu:758.8871108502967 +Step 5757 | loss:2.009472370147705 lr:3.844970179811065e-05 tokens_per_second_per_gpu:775.8206946241075 +Step 5758 | loss:1.928945541381836 lr:3.8418694568216476e-05 tokens_per_second_per_gpu:777.3331089850949 +Step 5759 | loss:2.0088951587677 lr:3.838769687303415e-05 tokens_per_second_per_gpu:754.9718113618475 +Step 5760 | loss:2.0107083320617676 lr:3.83567087173631e-05 tokens_per_second_per_gpu:774.437340513399 +Step 5761 | loss:2.071502447128296 lr:3.832573010600134e-05 tokens_per_second_per_gpu:785.5640588789861 +Step 5762 | loss:2.058678388595581 lr:3.8294761043745245e-05 tokens_per_second_per_gpu:786.3989403541622 +Step 5763 | loss:2.0539183616638184 lr:3.826380153538981e-05 tokens_per_second_per_gpu:749.1354839164553 +Step 5764 | loss:2.0063376426696777 lr:3.8232851585728545e-05 tokens_per_second_per_gpu:768.8750685029345 +Step 5765 | loss:1.9567933082580566 lr:3.820191119955349e-05 tokens_per_second_per_gpu:759.9126388862937 +Step 5766 | loss:1.9270223379135132 lr:3.817098038165514e-05 tokens_per_second_per_gpu:780.3027408961769 +Step 5767 | loss:2.0473549365997314 lr:3.814005913682263e-05 tokens_per_second_per_gpu:778.9968334394737 +Step 5768 | loss:2.0467023849487305 lr:3.810914746984343e-05 tokens_per_second_per_gpu:748.5909008424242 +Step 5769 | loss:2.0097315311431885 lr:3.807824538550371e-05 tokens_per_second_per_gpu:776.6979282370215 +Step 5770 | loss:2.0229713916778564 lr:3.804735288858804e-05 tokens_per_second_per_gpu:754.6508718387311 +Step 5771 | loss:2.0572211742401123 lr:3.8016469983879556e-05 tokens_per_second_per_gpu:790.6531754746627 +Step 5772 | loss:2.012976884841919 lr:3.798559667615991e-05 tokens_per_second_per_gpu:781.041113506962 +Step 5773 | loss:2.03654146194458 lr:3.795473297020927e-05 tokens_per_second_per_gpu:779.89804269334 +Step 5774 | loss:2.0213894844055176 lr:3.792387887080626e-05 tokens_per_second_per_gpu:782.6383665263702 +Step 5775 | loss:2.063866138458252 lr:3.789303438272807e-05 tokens_per_second_per_gpu:793.6563600968874 +Step 5776 | loss:2.033946990966797 lr:3.786219951075041e-05 tokens_per_second_per_gpu:783.8840893095442 +Step 5777 | loss:1.9870083332061768 lr:3.7831374259647454e-05 tokens_per_second_per_gpu:770.8495826230635 +Step 5778 | loss:1.9854252338409424 lr:3.780055863419195e-05 tokens_per_second_per_gpu:784.8909847365786 +Step 5779 | loss:2.0525834560394287 lr:3.776975263915513e-05 tokens_per_second_per_gpu:773.2567020974694 +Step 5780 | loss:2.0264968872070312 lr:3.773895627930667e-05 tokens_per_second_per_gpu:768.8402921624934 +Step 5781 | loss:2.0272727012634277 lr:3.77081695594148e-05 tokens_per_second_per_gpu:796.0655424495606 +Step 5782 | loss:2.0197951793670654 lr:3.7677392484246375e-05 tokens_per_second_per_gpu:771.471167164071 +Step 5783 | loss:2.0173404216766357 lr:3.7646625058566556e-05 tokens_per_second_per_gpu:742.3140672308549 +Step 5784 | loss:2.0564260482788086 lr:3.761586728713912e-05 tokens_per_second_per_gpu:764.0925349714959 +Step 5785 | loss:1.9574066400527954 lr:3.758511917472637e-05 tokens_per_second_per_gpu:792.8830578942681 +Step 5786 | loss:1.9974783658981323 lr:3.7554380726089e-05 tokens_per_second_per_gpu:761.9646135809572 +Step 5787 | loss:1.97118079662323 lr:3.7523651945986305e-05 tokens_per_second_per_gpu:797.6453006879937 +Step 5788 | loss:2.0016493797302246 lr:3.7492932839176157e-05 tokens_per_second_per_gpu:778.6159059075568 +Step 5789 | loss:2.087924003601074 lr:3.746222341041471e-05 tokens_per_second_per_gpu:795.3303440120429 +Step 5790 | loss:1.993180513381958 lr:3.743152366445682e-05 tokens_per_second_per_gpu:786.6506298538814 +Step 5791 | loss:1.9978679418563843 lr:3.740083360605572e-05 tokens_per_second_per_gpu:775.9900635329075 +Step 5792 | loss:1.9987711906433105 lr:3.7370153239963216e-05 tokens_per_second_per_gpu:786.8601869200472 +Step 5793 | loss:2.0476436614990234 lr:3.733948257092958e-05 tokens_per_second_per_gpu:772.7265687153941 +Step 5794 | loss:1.9735392332077026 lr:3.730882160370364e-05 tokens_per_second_per_gpu:776.6502627466983 +Step 5795 | loss:1.9751986265182495 lr:3.727817034303259e-05 tokens_per_second_per_gpu:754.3596113145325 +Step 5796 | loss:2.011644124984741 lr:3.7247528793662244e-05 tokens_per_second_per_gpu:759.5845509250339 +Step 5797 | loss:2.019655466079712 lr:3.721689696033687e-05 tokens_per_second_per_gpu:772.1516200755839 +Step 5798 | loss:2.013659954071045 lr:3.718627484779923e-05 tokens_per_second_per_gpu:784.8644890324465 +Step 5799 | loss:1.9886633157730103 lr:3.7155662460790596e-05 tokens_per_second_per_gpu:784.7063194517161 +Step 5800 | loss:2.077605724334717 lr:3.7125059804050744e-05 tokens_per_second_per_gpu:757.501355857593 +Step 5801 | loss:2.012460470199585 lr:3.7094466882317855e-05 tokens_per_second_per_gpu:776.8003982521121 +Step 5802 | loss:1.9341689348220825 lr:3.7063883700328714e-05 tokens_per_second_per_gpu:781.944184269664 +Step 5803 | loss:2.025327682495117 lr:3.703331026281855e-05 tokens_per_second_per_gpu:785.3940037503364 +Step 5804 | loss:2.0319676399230957 lr:3.7002746574521086e-05 tokens_per_second_per_gpu:769.5803243139139 +Step 5805 | loss:2.0190157890319824 lr:3.697219264016854e-05 tokens_per_second_per_gpu:782.7838948210657 +Step 5806 | loss:2.0039114952087402 lr:3.694164846449164e-05 tokens_per_second_per_gpu:794.6513747672816 +Step 5807 | loss:1.9459576606750488 lr:3.691111405221952e-05 tokens_per_second_per_gpu:773.2542740904836 +Step 5808 | loss:1.9761780500411987 lr:3.688058940807986e-05 tokens_per_second_per_gpu:778.7259628309394 +Step 5809 | loss:2.008679151535034 lr:3.685007453679893e-05 tokens_per_second_per_gpu:782.3483310257423 +Step 5810 | loss:1.9943782091140747 lr:3.681956944310129e-05 tokens_per_second_per_gpu:778.4660323106468 +Step 5811 | loss:2.0466697216033936 lr:3.678907413171011e-05 tokens_per_second_per_gpu:763.7823177503218 +Step 5812 | loss:2.0506370067596436 lr:3.6758588607347056e-05 tokens_per_second_per_gpu:772.8963042194175 +Step 5813 | loss:1.9943495988845825 lr:3.6728112874732176e-05 tokens_per_second_per_gpu:778.07016613706 +Step 5814 | loss:2.057154655456543 lr:3.669764693858406e-05 tokens_per_second_per_gpu:751.6691901786307 +Step 5815 | loss:1.9424045085906982 lr:3.6667190803619886e-05 tokens_per_second_per_gpu:754.0377967605567 +Step 5816 | loss:2.018444061279297 lr:3.663674447455513e-05 tokens_per_second_per_gpu:773.3931832373438 +Step 5817 | loss:1.945890188217163 lr:3.660630795610385e-05 tokens_per_second_per_gpu:767.2429549115537 +Step 5818 | loss:1.9689759016036987 lr:3.6575881252978585e-05 tokens_per_second_per_gpu:779.1339343157006 +Step 5819 | loss:1.969038486480713 lr:3.654546436989032e-05 tokens_per_second_per_gpu:778.5903884099781 +Step 5820 | loss:1.9729375839233398 lr:3.651505731154857e-05 tokens_per_second_per_gpu:769.2081622820677 +Step 5821 | loss:2.0901079177856445 lr:3.6484660082661326e-05 tokens_per_second_per_gpu:777.9343582646114 +Step 5822 | loss:1.9780199527740479 lr:3.645427268793494e-05 tokens_per_second_per_gpu:767.1529007583816 +Step 5823 | loss:1.9830570220947266 lr:3.642389513207438e-05 tokens_per_second_per_gpu:767.5336458052951 +Step 5824 | loss:2.0570881366729736 lr:3.639352741978305e-05 tokens_per_second_per_gpu:773.8194617148058 +Step 5825 | loss:2.024566888809204 lr:3.63631695557628e-05 tokens_per_second_per_gpu:756.8165925026091 +Step 5826 | loss:2.003728151321411 lr:3.633282154471399e-05 tokens_per_second_per_gpu:793.2843014388102 +Step 5827 | loss:1.9494330883026123 lr:3.6302483391335476e-05 tokens_per_second_per_gpu:762.0717816434737 +Step 5828 | loss:2.0542361736297607 lr:3.627215510032448e-05 tokens_per_second_per_gpu:801.3116389488108 +Step 5829 | loss:2.0140159130096436 lr:3.624183667637681e-05 tokens_per_second_per_gpu:783.945015773051 +Step 5830 | loss:2.0831427574157715 lr:3.62115281241867e-05 tokens_per_second_per_gpu:791.0646366499673 +Step 5831 | loss:1.9720743894577026 lr:3.618122944844686e-05 tokens_per_second_per_gpu:744.3804335000716 +Step 5832 | loss:2.042550802230835 lr:3.6150940653848485e-05 tokens_per_second_per_gpu:752.5844570856169 +Step 5833 | loss:1.9682987928390503 lr:3.612066174508125e-05 tokens_per_second_per_gpu:796.1520996703559 +Step 5834 | loss:1.9689342975616455 lr:3.609039272683321e-05 tokens_per_second_per_gpu:796.6383370769229 +Step 5835 | loss:1.9892195463180542 lr:3.606013360379096e-05 tokens_per_second_per_gpu:788.5954091023525 +Step 5836 | loss:1.9377175569534302 lr:3.6029884380639654e-05 tokens_per_second_per_gpu:768.1444160194858 +Step 5837 | loss:1.9611589908599854 lr:3.5999645062062724e-05 tokens_per_second_per_gpu:788.7134336762907 +Step 5838 | loss:2.0243632793426514 lr:3.5969415652742186e-05 tokens_per_second_per_gpu:789.7690275826128 +Step 5839 | loss:2.002291679382324 lr:3.5939196157358554e-05 tokens_per_second_per_gpu:765.939648118587 +Step 5840 | loss:1.9749925136566162 lr:3.590898658059062e-05 tokens_per_second_per_gpu:704.4069173865963 +Step 5841 | loss:1.9585424661636353 lr:3.5878786927115895e-05 tokens_per_second_per_gpu:757.5190171234406 +Step 5842 | loss:1.960667610168457 lr:3.584859720161021e-05 tokens_per_second_per_gpu:786.7961700068621 +Step 5843 | loss:1.9986361265182495 lr:3.5818417408747826e-05 tokens_per_second_per_gpu:768.9375859562517 +Step 5844 | loss:2.007150173187256 lr:3.578824755320155e-05 tokens_per_second_per_gpu:777.1885049335111 +Step 5845 | loss:2.015462875366211 lr:3.575808763964261e-05 tokens_per_second_per_gpu:756.7898360771214 +Step 5846 | loss:2.0162150859832764 lr:3.572793767274072e-05 tokens_per_second_per_gpu:777.8547322130479 +Step 5847 | loss:2.063969612121582 lr:3.5697797657164035e-05 tokens_per_second_per_gpu:779.7973861382475 +Step 5848 | loss:1.969348430633545 lr:3.566766759757919e-05 tokens_per_second_per_gpu:777.77792984385 +Step 5849 | loss:2.0006041526794434 lr:3.5637547498651204e-05 tokens_per_second_per_gpu:783.2674951738711 +Step 5850 | loss:1.9906353950500488 lr:3.5607437365043636e-05 tokens_per_second_per_gpu:752.0462051547003 +Step 5851 | loss:1.9916489124298096 lr:3.5577337201418496e-05 tokens_per_second_per_gpu:760.5677106708457 +Step 5852 | loss:2.009826421737671 lr:3.554724701243621e-05 tokens_per_second_per_gpu:771.8630333942468 +Step 5853 | loss:2.041346549987793 lr:3.551716680275569e-05 tokens_per_second_per_gpu:763.8448804401854 +Step 5854 | loss:2.0616543292999268 lr:3.548709657703433e-05 tokens_per_second_per_gpu:759.4956073067755 +Step 5855 | loss:1.95745050907135 lr:3.545703633992786e-05 tokens_per_second_per_gpu:767.1565752476643 +Step 5856 | loss:2.0323662757873535 lr:3.542698609609059e-05 tokens_per_second_per_gpu:775.8507813839034 +Step 5857 | loss:2.04263973236084 lr:3.539694585017523e-05 tokens_per_second_per_gpu:756.5144234612608 +Step 5858 | loss:1.9247345924377441 lr:3.536691560683296e-05 tokens_per_second_per_gpu:707.0314829700727 +Step 5859 | loss:2.0055346488952637 lr:3.53368953707134e-05 tokens_per_second_per_gpu:777.1903047664775 +Step 5860 | loss:1.9622769355773926 lr:3.530688514646464e-05 tokens_per_second_per_gpu:779.8983747844885 +Step 5861 | loss:1.9674776792526245 lr:3.5276884938733145e-05 tokens_per_second_per_gpu:783.7484804478381 +Step 5862 | loss:2.0387067794799805 lr:3.5246894752163895e-05 tokens_per_second_per_gpu:766.5042183926893 +Step 5863 | loss:1.9654539823532104 lr:3.5216914591400386e-05 tokens_per_second_per_gpu:770.9630385755643 +Step 5864 | loss:2.0548295974731445 lr:3.5186944461084405e-05 tokens_per_second_per_gpu:772.1375303994661 +Step 5865 | loss:1.9868228435516357 lr:3.515698436585628e-05 tokens_per_second_per_gpu:797.6770057680503 +Step 5866 | loss:2.079611301422119 lr:3.512703431035482e-05 tokens_per_second_per_gpu:762.5229306161068 +Step 5867 | loss:2.035879135131836 lr:3.509709429921712e-05 tokens_per_second_per_gpu:780.6815915514276 +Step 5868 | loss:2.0145084857940674 lr:3.5067164337078954e-05 tokens_per_second_per_gpu:775.2659810988545 +Step 5869 | loss:2.036139726638794 lr:3.5037244428574376e-05 tokens_per_second_per_gpu:791.0223568313908 +Step 5870 | loss:1.972416639328003 lr:3.5007334578335894e-05 tokens_per_second_per_gpu:734.5639942937739 +Step 5871 | loss:2.022203207015991 lr:3.497743479099449e-05 tokens_per_second_per_gpu:771.7625459528361 +Step 5872 | loss:2.064025402069092 lr:3.494754507117964e-05 tokens_per_second_per_gpu:766.6406203487534 +Step 5873 | loss:2.0228676795959473 lr:3.4917665423519107e-05 tokens_per_second_per_gpu:768.8195682463734 +Step 5874 | loss:2.0709755420684814 lr:3.4887795852639283e-05 tokens_per_second_per_gpu:758.1588562294864 +Step 5875 | loss:2.0523738861083984 lr:3.4857936363164924e-05 tokens_per_second_per_gpu:772.8386005407615 +Step 5876 | loss:2.0242552757263184 lr:3.482808695971913e-05 tokens_per_second_per_gpu:766.7186639687604 +Step 5877 | loss:2.0031344890594482 lr:3.479824764692358e-05 tokens_per_second_per_gpu:793.4333394830734 +Step 5878 | loss:2.0114903450012207 lr:3.476841842939831e-05 tokens_per_second_per_gpu:788.1970808271958 +Step 5879 | loss:2.056781768798828 lr:3.473859931176183e-05 tokens_per_second_per_gpu:773.8228138430471 +Step 5880 | loss:1.9561371803283691 lr:3.470879029863107e-05 tokens_per_second_per_gpu:768.6433292274262 +Step 5881 | loss:2.0529468059539795 lr:3.467899139462142e-05 tokens_per_second_per_gpu:763.7291711328813 +Step 5882 | loss:1.9764554500579834 lr:3.464920260434662e-05 tokens_per_second_per_gpu:746.3416981913101 +Step 5883 | loss:1.9687535762786865 lr:3.46194239324189e-05 tokens_per_second_per_gpu:765.948271097915 +Step 5884 | loss:1.991314172744751 lr:3.458965538344906e-05 tokens_per_second_per_gpu:759.9093702920767 +Step 5885 | loss:2.00415301322937 lr:3.4559896962046066e-05 tokens_per_second_per_gpu:763.0270255875223 +Step 5886 | loss:2.0209102630615234 lr:3.453014867281752e-05 tokens_per_second_per_gpu:768.5951647002397 +Step 5887 | loss:1.989186406135559 lr:3.4500410520369385e-05 tokens_per_second_per_gpu:798.9079310936224 +Step 5888 | loss:1.9651299715042114 lr:3.447068250930601e-05 tokens_per_second_per_gpu:772.0778803325796 +Step 5889 | loss:1.981067419052124 lr:3.444096464423021e-05 tokens_per_second_per_gpu:776.6113566516567 +Step 5890 | loss:2.0455358028411865 lr:3.441125692974336e-05 tokens_per_second_per_gpu:787.1279519107431 +Step 5891 | loss:2.006345272064209 lr:3.4381559370445025e-05 tokens_per_second_per_gpu:786.9249209485106 +Step 5892 | loss:2.0045173168182373 lr:3.4351871970933355e-05 tokens_per_second_per_gpu:783.5527990500893 +Step 5893 | loss:1.9682121276855469 lr:3.432219473580492e-05 tokens_per_second_per_gpu:781.2556836746935 +Step 5894 | loss:1.986307144165039 lr:3.4292527669654597e-05 tokens_per_second_per_gpu:772.9227485724184 +Step 5895 | loss:2.05673885345459 lr:3.426287077707585e-05 tokens_per_second_per_gpu:779.3808472052465 +Step 5896 | loss:1.9940565824508667 lr:3.4233224062660504e-05 tokens_per_second_per_gpu:785.0117009111781 +Step 5897 | loss:2.000952959060669 lr:3.420358753099875e-05 tokens_per_second_per_gpu:770.0972628496609 +Step 5898 | loss:2.004117727279663 lr:3.417396118667926e-05 tokens_per_second_per_gpu:773.8940881444041 +Step 5899 | loss:2.059490442276001 lr:3.414434503428913e-05 tokens_per_second_per_gpu:786.1183926307859 +Step 5900 | loss:1.9223312139511108 lr:3.411473907841385e-05 tokens_per_second_per_gpu:779.6124261029059 +Step 5901 | loss:2.0198588371276855 lr:3.408514332363737e-05 tokens_per_second_per_gpu:784.5603364040945 +Step 5902 | loss:1.969194769859314 lr:3.405555777454206e-05 tokens_per_second_per_gpu:785.431261336669 +Step 5903 | loss:1.9463541507720947 lr:3.4025982435708625e-05 tokens_per_second_per_gpu:759.1757148617768 +Step 5904 | loss:1.9765777587890625 lr:3.3996417311716275e-05 tokens_per_second_per_gpu:779.7828613322854 +Step 5905 | loss:1.954817533493042 lr:3.396686240714263e-05 tokens_per_second_per_gpu:765.8318296130246 +Step 5906 | loss:2.0316152572631836 lr:3.393731772656371e-05 tokens_per_second_per_gpu:774.0141435616055 +Step 5907 | loss:2.008546829223633 lr:3.390778327455396e-05 tokens_per_second_per_gpu:737.1147943847999 +Step 5908 | loss:1.9874440431594849 lr:3.3878259055686255e-05 tokens_per_second_per_gpu:763.2252038173586 +Step 5909 | loss:2.0822787284851074 lr:3.384874507453182e-05 tokens_per_second_per_gpu:764.3919752545927 +Step 5910 | loss:2.0398054122924805 lr:3.381924133566032e-05 tokens_per_second_per_gpu:792.975184754071 +Step 5911 | loss:1.995902419090271 lr:3.378974784363997e-05 tokens_per_second_per_gpu:760.8352536870337 +Step 5912 | loss:2.0182480812072754 lr:3.3760264603037196e-05 tokens_per_second_per_gpu:763.4887509383047 +Step 5913 | loss:2.0740787982940674 lr:3.373079161841693e-05 tokens_per_second_per_gpu:785.2438895348683 +Step 5914 | loss:2.014767646789551 lr:3.3701328894342575e-05 tokens_per_second_per_gpu:773.499520921555 +Step 5915 | loss:1.9594694375991821 lr:3.3671876435375795e-05 tokens_per_second_per_gpu:787.696547939257 +Step 5916 | loss:1.9939219951629639 lr:3.364243424607676e-05 tokens_per_second_per_gpu:785.1947454784955 +Step 5917 | loss:2.001084327697754 lr:3.361300233100414e-05 tokens_per_second_per_gpu:720.6717259019827 +Step 5918 | loss:2.0504724979400635 lr:3.3583580694714814e-05 tokens_per_second_per_gpu:770.9547809379718 +Step 5919 | loss:2.0565590858459473 lr:3.355416934176421e-05 tokens_per_second_per_gpu:769.33129474106 +Step 5920 | loss:2.024958610534668 lr:3.3524768276706155e-05 tokens_per_second_per_gpu:778.4563640188492 +Step 5921 | loss:2.0065717697143555 lr:3.349537750409275e-05 tokens_per_second_per_gpu:764.5105100620327 +Step 5922 | loss:1.9957695007324219 lr:3.3465997028474706e-05 tokens_per_second_per_gpu:759.6200297603024 +Step 5923 | loss:2.046785831451416 lr:3.343662685440105e-05 tokens_per_second_per_gpu:772.7316749859754 +Step 5924 | loss:2.0163955688476562 lr:3.3407266986419125e-05 tokens_per_second_per_gpu:756.439642175469 +Step 5925 | loss:1.9506747722625732 lr:3.33779174290748e-05 tokens_per_second_per_gpu:758.7128260958737 +Step 5926 | loss:2.0690622329711914 lr:3.3348578186912295e-05 tokens_per_second_per_gpu:799.6200584340913 +Step 5927 | loss:2.045828342437744 lr:3.331924926447425e-05 tokens_per_second_per_gpu:775.5813132477372 +Step 5928 | loss:2.0118494033813477 lr:3.328993066630169e-05 tokens_per_second_per_gpu:753.2498058819245 +Step 5929 | loss:2.009565830230713 lr:3.326062239693409e-05 tokens_per_second_per_gpu:756.4811792226964 +Step 5930 | loss:2.0208935737609863 lr:3.323132446090923e-05 tokens_per_second_per_gpu:755.7706828073422 +Step 5931 | loss:2.0734543800354004 lr:3.320203686276336e-05 tokens_per_second_per_gpu:746.9214323546846 +Step 5932 | loss:2.013123035430908 lr:3.3172759607031125e-05 tokens_per_second_per_gpu:782.5178393008082 +Step 5933 | loss:2.0456464290618896 lr:3.314349269824557e-05 tokens_per_second_per_gpu:788.853671584764 +Step 5934 | loss:2.048732280731201 lr:3.3114236140938104e-05 tokens_per_second_per_gpu:795.9710037807163 +Step 5935 | loss:2.0373504161834717 lr:3.308498993963861e-05 tokens_per_second_per_gpu:788.9897441174385 +Step 5936 | loss:1.995728611946106 lr:3.3055754098875244e-05 tokens_per_second_per_gpu:786.4322799990798 +Step 5937 | loss:1.97873055934906 lr:3.302652862317464e-05 tokens_per_second_per_gpu:780.3398516335958 +Step 5938 | loss:1.996376633644104 lr:3.2997313517061876e-05 tokens_per_second_per_gpu:772.4599756637156 +Step 5939 | loss:2.046234369277954 lr:3.296810878506031e-05 tokens_per_second_per_gpu:745.6735386152699 +Step 5940 | loss:2.0035178661346436 lr:3.293891443169176e-05 tokens_per_second_per_gpu:753.6382694032994 +Step 5941 | loss:1.9881423711776733 lr:3.290973046147645e-05 tokens_per_second_per_gpu:766.67320659036 +Step 5942 | loss:2.0317180156707764 lr:3.288055687893289e-05 tokens_per_second_per_gpu:728.6491797283895 +Step 5943 | loss:1.9995598793029785 lr:3.285139368857816e-05 tokens_per_second_per_gpu:788.8012302197089 +Step 5944 | loss:1.9447054862976074 lr:3.2822240894927614e-05 tokens_per_second_per_gpu:783.0870762117246 +Step 5945 | loss:1.9635910987854004 lr:3.279309850249497e-05 tokens_per_second_per_gpu:743.7494028303502 +Step 5946 | loss:2.0223636627197266 lr:3.27639665157924e-05 tokens_per_second_per_gpu:780.0822043754267 +Step 5947 | loss:1.9887654781341553 lr:3.27348449393305e-05 tokens_per_second_per_gpu:757.6295662673886 +Step 5948 | loss:2.010647773742676 lr:3.270573377761809e-05 tokens_per_second_per_gpu:770.4671357354079 +Step 5949 | loss:2.019867181777954 lr:3.2676633035162576e-05 tokens_per_second_per_gpu:774.2599981570048 +Step 5950 | loss:2.06954288482666 lr:3.264754271646968e-05 tokens_per_second_per_gpu:748.8735734756458 +Step 5951 | loss:2.0061147212982178 lr:3.2618462826043426e-05 tokens_per_second_per_gpu:786.9431617503832 +Step 5952 | loss:1.9845483303070068 lr:3.258939336838631e-05 tokens_per_second_per_gpu:789.6052169516672 +Step 5953 | loss:2.026662826538086 lr:3.256033434799921e-05 tokens_per_second_per_gpu:794.5862513100731 +Step 5954 | loss:1.9866060018539429 lr:3.253128576938136e-05 tokens_per_second_per_gpu:794.6301088458885 +Step 5955 | loss:2.0035862922668457 lr:3.250224763703038e-05 tokens_per_second_per_gpu:785.4181001663887 +Step 5956 | loss:1.9749425649642944 lr:3.2473219955442334e-05 tokens_per_second_per_gpu:752.7057104382382 +Step 5957 | loss:2.037682294845581 lr:3.244420272911154e-05 tokens_per_second_per_gpu:776.3488907068039 +Step 5958 | loss:1.9415738582611084 lr:3.241519596253081e-05 tokens_per_second_per_gpu:765.9467104826823 +Step 5959 | loss:2.0017483234405518 lr:3.2386199660191285e-05 tokens_per_second_per_gpu:743.8921429295176 +Step 5960 | loss:2.014547109603882 lr:3.235721382658252e-05 tokens_per_second_per_gpu:784.8198104667 +Step 5961 | loss:1.9707567691802979 lr:3.232823846619241e-05 tokens_per_second_per_gpu:776.740072546864 +Step 5962 | loss:1.954398512840271 lr:3.2299273583507286e-05 tokens_per_second_per_gpu:762.2203484806398 +Step 5963 | loss:2.0238215923309326 lr:3.227031918301174e-05 tokens_per_second_per_gpu:762.2477236976705 +Step 5964 | loss:2.0074586868286133 lr:3.2241375269188844e-05 tokens_per_second_per_gpu:800.9252645968508 +Step 5965 | loss:1.9453980922698975 lr:3.2212441846520115e-05 tokens_per_second_per_gpu:782.731858711748 +Step 5966 | loss:1.9586472511291504 lr:3.218351891948522e-05 tokens_per_second_per_gpu:781.415980324217 +Step 5967 | loss:1.9971201419830322 lr:3.2154606492562414e-05 tokens_per_second_per_gpu:764.2958264643921 +Step 5968 | loss:2.0168299674987793 lr:3.2125704570228246e-05 tokens_per_second_per_gpu:773.7791606742264 +Step 5969 | loss:2.0454459190368652 lr:3.209681315695754e-05 tokens_per_second_per_gpu:778.8904137739714 +Step 5970 | loss:1.9985746145248413 lr:3.20679322572237e-05 tokens_per_second_per_gpu:785.1896843356263 +Step 5971 | loss:2.0434563159942627 lr:3.203906187549839e-05 tokens_per_second_per_gpu:779.8131798316078 +Step 5972 | loss:2.0331382751464844 lr:3.201020201625158e-05 tokens_per_second_per_gpu:746.8532656269178 +Step 5973 | loss:1.9635909795761108 lr:3.19813526839517e-05 tokens_per_second_per_gpu:777.7755189812068 +Step 5974 | loss:2.0010414123535156 lr:3.195251388306559e-05 tokens_per_second_per_gpu:785.1885346911639 +Step 5975 | loss:1.9945623874664307 lr:3.192368561805828e-05 tokens_per_second_per_gpu:783.5420660486941 +Step 5976 | loss:1.997220516204834 lr:3.1894867893393386e-05 tokens_per_second_per_gpu:777.650511508256 +Step 5977 | loss:2.024731397628784 lr:3.186606071353278e-05 tokens_per_second_per_gpu:776.2081742036834 +Step 5978 | loss:2.088108777999878 lr:3.183726408293669e-05 tokens_per_second_per_gpu:760.7270332292964 +Step 5979 | loss:1.975927472114563 lr:3.180847800606374e-05 tokens_per_second_per_gpu:788.7859497946087 +Step 5980 | loss:1.9908567667007446 lr:3.17797024873709e-05 tokens_per_second_per_gpu:789.5133346640704 +Step 5981 | loss:2.017364978790283 lr:3.175093753131354e-05 tokens_per_second_per_gpu:791.2677221682504 +Step 5982 | loss:1.9948211908340454 lr:3.172218314234538e-05 tokens_per_second_per_gpu:795.7520666720891 +Step 5983 | loss:1.9964866638183594 lr:3.1693439324918515e-05 tokens_per_second_per_gpu:778.1666559541916 +Step 5984 | loss:2.053713798522949 lr:3.166470608348334e-05 tokens_per_second_per_gpu:735.7983728703504 +Step 5985 | loss:2.0135512351989746 lr:3.163598342248864e-05 tokens_per_second_per_gpu:787.3290087102289 +Step 5986 | loss:2.0518813133239746 lr:3.1607271346381695e-05 tokens_per_second_per_gpu:789.7836263744216 +Step 5987 | loss:2.052311420440674 lr:3.157856985960792e-05 tokens_per_second_per_gpu:787.4390679149251 +Step 5988 | loss:1.9744846820831299 lr:3.1549878966611245e-05 tokens_per_second_per_gpu:745.9431564651587 +Step 5989 | loss:2.0378050804138184 lr:3.1521198671833954e-05 tokens_per_second_per_gpu:752.9097866861503 +Step 5990 | loss:2.022759199142456 lr:3.149252897971657e-05 tokens_per_second_per_gpu:771.8554958329961 +Step 5991 | loss:2.0336811542510986 lr:3.1463869894698084e-05 tokens_per_second_per_gpu:774.4164861261291 +Step 5992 | loss:2.002027988433838 lr:3.1435221421215896e-05 tokens_per_second_per_gpu:755.6483631333269 +Step 5993 | loss:1.9688010215759277 lr:3.1406583563705595e-05 tokens_per_second_per_gpu:786.817931079153 +Step 5994 | loss:2.035449504852295 lr:3.137795632660126e-05 tokens_per_second_per_gpu:758.4341768237182 +Step 5995 | loss:2.027634620666504 lr:3.1349339714335277e-05 tokens_per_second_per_gpu:777.3138881907744 +Step 5996 | loss:2.04606294631958 lr:3.132073373133835e-05 tokens_per_second_per_gpu:769.4298815996651 +Step 5997 | loss:1.9620288610458374 lr:3.129213838203964e-05 tokens_per_second_per_gpu:766.8822912219001 +Step 5998 | loss:2.0157124996185303 lr:3.1263553670866596e-05 tokens_per_second_per_gpu:729.2458013026392 +Step 5999 | loss:1.9664894342422485 lr:3.123497960224498e-05 tokens_per_second_per_gpu:755.5502777011914 +Step 6000 | loss:2.075007915496826 lr:3.1206416180598995e-05 tokens_per_second_per_gpu:764.1470242983435 +Step 6001 | loss:2.0371317863464355 lr:3.1177863410351126e-05 tokens_per_second_per_gpu:769.6090379164198 +Step 6002 | loss:1.990850567817688 lr:3.1149321295922243e-05 tokens_per_second_per_gpu:778.8840814871268 +Step 6003 | loss:2.033982753753662 lr:3.1120789841731556e-05 tokens_per_second_per_gpu:790.3147265883468 +Step 6004 | loss:2.0324487686157227 lr:3.1092269052196666e-05 tokens_per_second_per_gpu:767.4276884690167 +Step 6005 | loss:2.011793613433838 lr:3.1063758931733414e-05 tokens_per_second_per_gpu:751.6692625270001 +Step 6006 | loss:2.008716344833374 lr:3.1035259484756094e-05 tokens_per_second_per_gpu:776.4142323566681 +Step 6007 | loss:2.023188591003418 lr:3.10067707156773e-05 tokens_per_second_per_gpu:739.9555114828555 +Step 6008 | loss:1.9714301824569702 lr:3.0978292628908004e-05 tokens_per_second_per_gpu:765.5896632268411 +Step 6009 | loss:2.0118672847747803 lr:3.094982522885749e-05 tokens_per_second_per_gpu:739.9149376152056 +Step 6010 | loss:2.0146589279174805 lr:3.0921368519933425e-05 tokens_per_second_per_gpu:780.2601281715955 +Step 6011 | loss:2.031313419342041 lr:3.089292250654175e-05 tokens_per_second_per_gpu:762.7275907407017 +Step 6012 | loss:1.984296441078186 lr:3.086448719308681e-05 tokens_per_second_per_gpu:782.940329735324 +Step 6013 | loss:2.0324697494506836 lr:3.0836062583971345e-05 tokens_per_second_per_gpu:785.540506112836 +Step 6014 | loss:1.9610321521759033 lr:3.080764868359629e-05 tokens_per_second_per_gpu:776.120826273186 +Step 6015 | loss:2.0416340827941895 lr:3.0779245496361044e-05 tokens_per_second_per_gpu:750.7468645771709 +Step 6016 | loss:1.9880415201187134 lr:3.075085302666334e-05 tokens_per_second_per_gpu:767.0379555152531 +Step 6017 | loss:1.966144323348999 lr:3.072247127889915e-05 tokens_per_second_per_gpu:758.3308476508514 +Step 6018 | loss:2.0580053329467773 lr:3.0694100257462855e-05 tokens_per_second_per_gpu:746.0385617584674 +Step 6019 | loss:2.02573823928833 lr:3.066573996674728e-05 tokens_per_second_per_gpu:784.1838473742939 +Step 6020 | loss:2.0057284832000732 lr:3.063739041114339e-05 tokens_per_second_per_gpu:788.4849127538312 +Step 6021 | loss:2.06765079498291 lr:3.0609051595040595e-05 tokens_per_second_per_gpu:791.9269665403276 +Step 6022 | loss:1.9820849895477295 lr:3.058072352282668e-05 tokens_per_second_per_gpu:789.1420084275585 +Step 6023 | loss:1.991084098815918 lr:3.055240619888763e-05 tokens_per_second_per_gpu:752.3356342628887 +Step 6024 | loss:2.0714526176452637 lr:3.0524099627607916e-05 tokens_per_second_per_gpu:760.1101329589618 +Step 6025 | loss:1.996704339981079 lr:3.0495803813370315e-05 tokens_per_second_per_gpu:782.3697559536571 +Step 6026 | loss:2.0166985988616943 lr:3.046751876055581e-05 tokens_per_second_per_gpu:756.0507415897702 +Step 6027 | loss:1.9844017028808594 lr:3.043924447354387e-05 tokens_per_second_per_gpu:792.182270525839 +Step 6028 | loss:1.9887782335281372 lr:3.041098095671223e-05 tokens_per_second_per_gpu:788.3368327160679 +Step 6029 | loss:1.9638316631317139 lr:3.038272821443696e-05 tokens_per_second_per_gpu:777.641554078555 +Step 6030 | loss:2.0516722202301025 lr:3.0354486251092472e-05 tokens_per_second_per_gpu:784.1276183897497 +Step 6031 | loss:2.0173985958099365 lr:3.0326255071051534e-05 tokens_per_second_per_gpu:764.678043385581 +Step 6032 | loss:2.042801856994629 lr:3.029803467868515e-05 tokens_per_second_per_gpu:759.9589432026257 +Step 6033 | loss:2.076321601867676 lr:3.0269825078362756e-05 tokens_per_second_per_gpu:787.3477008897628 +Step 6034 | loss:2.0682015419006348 lr:3.0241626274452085e-05 tokens_per_second_per_gpu:745.5917870006482 +Step 6035 | loss:2.027721881866455 lr:3.0213438271319193e-05 tokens_per_second_per_gpu:749.474457153057 +Step 6036 | loss:2.0291061401367188 lr:3.0185261073328452e-05 tokens_per_second_per_gpu:777.7549078465686 +Step 6037 | loss:1.9979599714279175 lr:3.0157094684842614e-05 tokens_per_second_per_gpu:785.1922276432107 +Step 6038 | loss:2.022768974304199 lr:3.0128939110222655e-05 tokens_per_second_per_gpu:756.9649222432344 +Step 6039 | loss:1.987294316291809 lr:3.0100794353827934e-05 tokens_per_second_per_gpu:775.7984048571028 +Step 6040 | loss:1.993889570236206 lr:3.007266042001623e-05 tokens_per_second_per_gpu:740.9785708037222 +Step 6041 | loss:2.057576894760132 lr:3.0044537313143474e-05 tokens_per_second_per_gpu:799.4572739323246 +Step 6042 | loss:1.9745228290557861 lr:3.0016425037564032e-05 tokens_per_second_per_gpu:761.1537855677847 +Step 6043 | loss:1.9703903198242188 lr:2.9988323597630586e-05 tokens_per_second_per_gpu:797.0509282171593 +Step 6044 | loss:2.055544853210449 lr:2.9960232997694026e-05 tokens_per_second_per_gpu:788.7071248848492 +Step 6045 | loss:2.047729015350342 lr:2.9932153242103744e-05 tokens_per_second_per_gpu:746.6647479845285 +Step 6046 | loss:1.962615728378296 lr:2.9904084335207383e-05 tokens_per_second_per_gpu:800.6731196549159 +Step 6047 | loss:2.0210747718811035 lr:2.98760262813508e-05 tokens_per_second_per_gpu:777.0760195115336 +Step 6048 | loss:2.0854992866516113 lr:2.9847979084878318e-05 tokens_per_second_per_gpu:755.6822681589714 +Step 6049 | loss:1.9691545963287354 lr:2.9819942750132534e-05 tokens_per_second_per_gpu:794.3160216904008 +Step 6050 | loss:2.0013809204101562 lr:2.979191728145425e-05 tokens_per_second_per_gpu:753.5586802142766 +Step 6051 | loss:2.0537571907043457 lr:2.9763902683182786e-05 tokens_per_second_per_gpu:783.2346636585937 +Step 6052 | loss:2.023510456085205 lr:2.9735898959655694e-05 tokens_per_second_per_gpu:794.0533553585396 +Step 6053 | loss:2.03926420211792 lr:2.970790611520874e-05 tokens_per_second_per_gpu:776.4312025076688 +Step 6054 | loss:2.034433603286743 lr:2.967992415417613e-05 tokens_per_second_per_gpu:782.5685111252466 +Step 6055 | loss:1.9790387153625488 lr:2.965195308089035e-05 tokens_per_second_per_gpu:791.3745885679177 +Step 6056 | loss:2.0388343334198 lr:2.9623992899682195e-05 tokens_per_second_per_gpu:786.7719847013921 +Step 6057 | loss:1.987181305885315 lr:2.9596043614880776e-05 tokens_per_second_per_gpu:737.1292838252996 +Step 6058 | loss:1.9974315166473389 lr:2.9568105230813547e-05 tokens_per_second_per_gpu:738.1756624811154 +Step 6059 | loss:1.9953351020812988 lr:2.9540177751806186e-05 tokens_per_second_per_gpu:737.9352350341153 +Step 6060 | loss:2.08415150642395 lr:2.951226118218273e-05 tokens_per_second_per_gpu:754.8171874869727 +Step 6061 | loss:1.9147355556488037 lr:2.9484355526265638e-05 tokens_per_second_per_gpu:786.9629240418757 +Step 6062 | loss:1.992659091949463 lr:2.9456460788375484e-05 tokens_per_second_per_gpu:770.7028983582693 +Step 6063 | loss:2.018538236618042 lr:2.9428576972831278e-05 tokens_per_second_per_gpu:765.0372855761926 +Step 6064 | loss:2.0386033058166504 lr:2.9400704083950335e-05 tokens_per_second_per_gpu:779.7322028392651 +Step 6065 | loss:2.063626289367676 lr:2.9372842126048185e-05 tokens_per_second_per_gpu:771.7728368386067 +Step 6066 | loss:2.0158851146698 lr:2.9344991103438735e-05 tokens_per_second_per_gpu:761.8099713620653 +Step 6067 | loss:2.0711593627929688 lr:2.9317151020434287e-05 tokens_per_second_per_gpu:796.3608157584828 +Step 6068 | loss:2.027050018310547 lr:2.9289321881345254e-05 tokens_per_second_per_gpu:786.3782277741875 +Step 6069 | loss:2.0025575160980225 lr:2.926150369048051e-05 tokens_per_second_per_gpu:780.6124297093138 +Step 6070 | loss:2.0253429412841797 lr:2.9233696452147187e-05 tokens_per_second_per_gpu:774.673227991566 +Step 6071 | loss:2.011821985244751 lr:2.9205900170650635e-05 tokens_per_second_per_gpu:792.8435731992573 +Step 6072 | loss:2.062845230102539 lr:2.917811485029468e-05 tokens_per_second_per_gpu:742.2119766031819 +Step 6073 | loss:2.0107080936431885 lr:2.915034049538137e-05 tokens_per_second_per_gpu:777.662196131152 +Step 6074 | loss:2.0010969638824463 lr:2.912257711021096e-05 tokens_per_second_per_gpu:762.6350247127552 +Step 6075 | loss:1.9711618423461914 lr:2.9094824699082123e-05 tokens_per_second_per_gpu:764.6357884021136 +Step 6076 | loss:2.0215046405792236 lr:2.906708326629184e-05 tokens_per_second_per_gpu:801.4752265666194 +Step 6077 | loss:2.009941339492798 lr:2.903935281613527e-05 tokens_per_second_per_gpu:762.3129236959103 +Step 6078 | loss:2.0197129249572754 lr:2.901163335290602e-05 tokens_per_second_per_gpu:763.3005724038209 +Step 6079 | loss:2.0110673904418945 lr:2.8983924880895964e-05 tokens_per_second_per_gpu:769.1208108621587 +Step 6080 | loss:2.025099039077759 lr:2.895622740439514e-05 tokens_per_second_per_gpu:756.4171044142389 +Step 6081 | loss:2.009172201156616 lr:2.8928540927692038e-05 tokens_per_second_per_gpu:777.5809242831322 +Step 6082 | loss:2.028818130493164 lr:2.8900865455073388e-05 tokens_per_second_per_gpu:757.6984368994018 +Step 6083 | loss:2.0263478755950928 lr:2.8873200990824224e-05 tokens_per_second_per_gpu:787.6832373544379 +Step 6084 | loss:1.9902838468551636 lr:2.8845547539227848e-05 tokens_per_second_per_gpu:791.2125126736445 +Step 6085 | loss:2.0351223945617676 lr:2.8817905104565934e-05 tokens_per_second_per_gpu:738.4945794684329 +Step 6086 | loss:2.0230178833007812 lr:2.879027369111832e-05 tokens_per_second_per_gpu:742.7169945836305 +Step 6087 | loss:1.997922658920288 lr:2.8762653303163222e-05 tokens_per_second_per_gpu:772.6218377264038 +Step 6088 | loss:2.0404767990112305 lr:2.8735043944977223e-05 tokens_per_second_per_gpu:782.6295928647469 +Step 6089 | loss:1.969318151473999 lr:2.8707445620835027e-05 tokens_per_second_per_gpu:780.4025884326528 +Step 6090 | loss:2.005406618118286 lr:2.8679858335009745e-05 tokens_per_second_per_gpu:768.6856228712701 +Step 6091 | loss:1.9906625747680664 lr:2.86522820917728e-05 tokens_per_second_per_gpu:789.7793447018908 +Step 6092 | loss:2.039771318435669 lr:2.8624716895393766e-05 tokens_per_second_per_gpu:771.6734682393579 +Step 6093 | loss:1.9688842296600342 lr:2.8597162750140615e-05 tokens_per_second_per_gpu:772.7093281762211 +Step 6094 | loss:2.0097551345825195 lr:2.856961966027968e-05 tokens_per_second_per_gpu:768.8260312872884 +Step 6095 | loss:2.062190294265747 lr:2.85420876300754e-05 tokens_per_second_per_gpu:768.3910436222021 +Step 6096 | loss:1.9446756839752197 lr:2.851456666379063e-05 tokens_per_second_per_gpu:743.1368970281593 +Step 6097 | loss:1.9844077825546265 lr:2.8487056765686505e-05 tokens_per_second_per_gpu:772.2077706015112 +Step 6098 | loss:1.9690732955932617 lr:2.8459557940022318e-05 tokens_per_second_per_gpu:769.6738649384728 +Step 6099 | loss:2.01513934135437 lr:2.8432070191055836e-05 tokens_per_second_per_gpu:790.7613166245659 +Step 6100 | loss:2.022401809692383 lr:2.8404593523043045e-05 tokens_per_second_per_gpu:768.9759746085938 +Step 6101 | loss:2.016307830810547 lr:2.83771279402381e-05 tokens_per_second_per_gpu:762.2730956319167 +Step 6102 | loss:1.9663041830062866 lr:2.8349673446893597e-05 tokens_per_second_per_gpu:784.2329069261677 +Step 6103 | loss:1.9688518047332764 lr:2.8322230047260322e-05 tokens_per_second_per_gpu:784.1350494706231 +Step 6104 | loss:1.9976216554641724 lr:2.8294797745587386e-05 tokens_per_second_per_gpu:777.5945216786193 +Step 6105 | loss:2.002288579940796 lr:2.826737654612216e-05 tokens_per_second_per_gpu:770.4971801810395 +Step 6106 | loss:2.050765037536621 lr:2.8239966453110332e-05 tokens_per_second_per_gpu:743.9828386248846 +Step 6107 | loss:1.9810785055160522 lr:2.821256747079579e-05 tokens_per_second_per_gpu:759.9959474143245 +Step 6108 | loss:2.0418457984924316 lr:2.8185179603420785e-05 tokens_per_second_per_gpu:793.1035417440968 +Step 6109 | loss:2.018561363220215 lr:2.81578028552258e-05 tokens_per_second_per_gpu:777.7356352945059 +Step 6110 | loss:1.9711167812347412 lr:2.8130437230449624e-05 tokens_per_second_per_gpu:730.4365399905804 +Step 6111 | loss:2.0039267539978027 lr:2.810308273332931e-05 tokens_per_second_per_gpu:769.7316859539092 +Step 6112 | loss:2.0326712131500244 lr:2.807573936810023e-05 tokens_per_second_per_gpu:789.3921355854362 +Step 6113 | loss:2.043473243713379 lr:2.80484071389959e-05 tokens_per_second_per_gpu:775.835985659758 +Step 6114 | loss:2.0439553260803223 lr:2.8021086050248234e-05 tokens_per_second_per_gpu:781.09406388456 +Step 6115 | loss:1.9894282817840576 lr:2.7993776106087476e-05 tokens_per_second_per_gpu:769.7007410014315 +Step 6116 | loss:2.0069100856781006 lr:2.7966477310741956e-05 tokens_per_second_per_gpu:732.4718433825504 +Step 6117 | loss:2.0285916328430176 lr:2.7939189668438414e-05 tokens_per_second_per_gpu:790.5570422844964 +Step 6118 | loss:2.0040478706359863 lr:2.7911913183401883e-05 tokens_per_second_per_gpu:787.469251110784 +Step 6119 | loss:2.0107765197753906 lr:2.7884647859855494e-05 tokens_per_second_per_gpu:763.5953286782596 +Step 6120 | loss:2.012523651123047 lr:2.7857393702020886e-05 tokens_per_second_per_gpu:764.7909057011402 +Step 6121 | loss:2.014864921569824 lr:2.783015071411784e-05 tokens_per_second_per_gpu:790.3344733914315 +Step 6122 | loss:2.0292298793792725 lr:2.780291890036437e-05 tokens_per_second_per_gpu:768.3844380635854 +Step 6123 | loss:2.01047945022583 lr:2.7775698264976846e-05 tokens_per_second_per_gpu:798.9500947567578 +Step 6124 | loss:1.9806733131408691 lr:2.7748488812169892e-05 tokens_per_second_per_gpu:771.2271197173964 +Step 6125 | loss:2.0204436779022217 lr:2.7721290546156298e-05 tokens_per_second_per_gpu:735.5713290186369 +Step 6126 | loss:2.0091629028320312 lr:2.7694103471147292e-05 tokens_per_second_per_gpu:763.972553112685 +Step 6127 | loss:2.056335210800171 lr:2.76669275913523e-05 tokens_per_second_per_gpu:761.7229868067375 +Step 6128 | loss:1.9750518798828125 lr:2.7639762910978916e-05 tokens_per_second_per_gpu:732.3104121488788 +Step 6129 | loss:2.0284535884857178 lr:2.7612609434233126e-05 tokens_per_second_per_gpu:793.1823650442201 +Step 6130 | loss:2.0036020278930664 lr:2.7585467165319136e-05 tokens_per_second_per_gpu:790.905379990948 +Step 6131 | loss:1.9905768632888794 lr:2.755833610843941e-05 tokens_per_second_per_gpu:793.9222986540941 +Step 6132 | loss:2.0299291610717773 lr:2.753121626779469e-05 tokens_per_second_per_gpu:779.1834723559225 +Step 6133 | loss:2.0222740173339844 lr:2.750410764758401e-05 tokens_per_second_per_gpu:766.4927153133593 +Step 6134 | loss:2.0002198219299316 lr:2.7477010252004566e-05 tokens_per_second_per_gpu:753.7527800777515 +Step 6135 | loss:2.0269346237182617 lr:2.744992408525191e-05 tokens_per_second_per_gpu:766.6048892494649 +Step 6136 | loss:1.9709134101867676 lr:2.7422849151519824e-05 tokens_per_second_per_gpu:788.1893821222349 +Step 6137 | loss:2.016252040863037 lr:2.739578545500038e-05 tokens_per_second_per_gpu:738.1811766546516 +Step 6138 | loss:1.959152102470398 lr:2.736873299988385e-05 tokens_per_second_per_gpu:774.4520323247033 +Step 6139 | loss:1.980726957321167 lr:2.734169179035885e-05 tokens_per_second_per_gpu:769.039906844073 +Step 6140 | loss:2.003526210784912 lr:2.7314661830612144e-05 tokens_per_second_per_gpu:772.4547629312048 +Step 6141 | loss:1.9896897077560425 lr:2.728764312482881e-05 tokens_per_second_per_gpu:790.815558377981 +Step 6142 | loss:1.9937468767166138 lr:2.726063567719228e-05 tokens_per_second_per_gpu:774.3811214333075 +Step 6143 | loss:2.0111191272735596 lr:2.7233639491884067e-05 tokens_per_second_per_gpu:744.3818478774758 +Step 6144 | loss:2.0094752311706543 lr:2.7206654573084046e-05 tokens_per_second_per_gpu:792.8485018268991 +Step 6145 | loss:2.0057482719421387 lr:2.717968092497035e-05 tokens_per_second_per_gpu:764.9074337827842 +Step 6146 | loss:2.025167226791382 lr:2.7152718551719282e-05 tokens_per_second_per_gpu:746.3690785414132 +Step 6147 | loss:1.964081048965454 lr:2.7125767457505514e-05 tokens_per_second_per_gpu:748.8091713072392 +Step 6148 | loss:2.0045065879821777 lr:2.7098827646501945e-05 tokens_per_second_per_gpu:782.3775933246344 +Step 6149 | loss:1.985705852508545 lr:2.707189912287963e-05 tokens_per_second_per_gpu:763.1021249275991 +Step 6150 | loss:2.0381722450256348 lr:2.7044981890807987e-05 tokens_per_second_per_gpu:793.2321180375858 +Step 6151 | loss:1.9788422584533691 lr:2.7018075954454658e-05 tokens_per_second_per_gpu:788.8060617162831 +Step 6152 | loss:2.036722183227539 lr:2.6991181317985436e-05 tokens_per_second_per_gpu:797.4294063014684 +Step 6153 | loss:1.990837812423706 lr:2.6964297985564556e-05 tokens_per_second_per_gpu:767.106572427898 +Step 6154 | loss:1.9683806896209717 lr:2.6937425961354378e-05 tokens_per_second_per_gpu:793.1367045499096 +Step 6155 | loss:1.9517842531204224 lr:2.6910565249515497e-05 tokens_per_second_per_gpu:744.5779753062418 +Step 6156 | loss:2.0254526138305664 lr:2.6883715854206804e-05 tokens_per_second_per_gpu:788.8572886959685 +Step 6157 | loss:2.0031213760375977 lr:2.6856877779585432e-05 tokens_per_second_per_gpu:787.2243592844194 +Step 6158 | loss:1.9850870370864868 lr:2.6830051029806746e-05 tokens_per_second_per_gpu:778.533923646115 +Step 6159 | loss:1.9642887115478516 lr:2.680323560902437e-05 tokens_per_second_per_gpu:749.8227951601908 +Step 6160 | loss:2.0866942405700684 lr:2.67764315213902e-05 tokens_per_second_per_gpu:788.4155152104761 +Step 6161 | loss:1.9937121868133545 lr:2.6749638771054298e-05 tokens_per_second_per_gpu:745.1396555352353 +Step 6162 | loss:2.044130563735962 lr:2.6722857362165e-05 tokens_per_second_per_gpu:793.0607784589048 +Step 6163 | loss:2.0054306983947754 lr:2.6696087298869e-05 tokens_per_second_per_gpu:768.9224694583592 +Step 6164 | loss:2.0503034591674805 lr:2.666932858531107e-05 tokens_per_second_per_gpu:743.9978814547628 +Step 6165 | loss:1.9365670680999756 lr:2.66425812256343e-05 tokens_per_second_per_gpu:776.4911378031887 +Step 6166 | loss:2.034609079360962 lr:2.661584522398006e-05 tokens_per_second_per_gpu:787.0877295564517 +Step 6167 | loss:2.0191597938537598 lr:2.658912058448787e-05 tokens_per_second_per_gpu:766.2655347671974 +Step 6168 | loss:2.0068721771240234 lr:2.6562407311295512e-05 tokens_per_second_per_gpu:774.2600081537829 +Step 6169 | loss:1.9575040340423584 lr:2.6535705408539157e-05 tokens_per_second_per_gpu:753.1579836543015 +Step 6170 | loss:2.002150297164917 lr:2.650901488035298e-05 tokens_per_second_per_gpu:764.950309116018 +Step 6171 | loss:1.9924466609954834 lr:2.6482335730869556e-05 tokens_per_second_per_gpu:764.8148633694681 +Step 6172 | loss:1.993588924407959 lr:2.6455667964219665e-05 tokens_per_second_per_gpu:756.457271076107 +Step 6173 | loss:1.9918811321258545 lr:2.6429011584532237e-05 tokens_per_second_per_gpu:748.1157388210602 +Step 6174 | loss:2.017685890197754 lr:2.64023665959346e-05 tokens_per_second_per_gpu:779.3477427862807 +Step 6175 | loss:1.9816137552261353 lr:2.6375733002552228e-05 tokens_per_second_per_gpu:764.3417412625212 +Step 6176 | loss:2.0324952602386475 lr:2.634911080850878e-05 tokens_per_second_per_gpu:797.3485591624922 +Step 6177 | loss:1.9659664630889893 lr:2.632250001792622e-05 tokens_per_second_per_gpu:763.8557347247186 +Step 6178 | loss:2.0910682678222656 lr:2.6295900634924754e-05 tokens_per_second_per_gpu:770.9514361410714 +Step 6179 | loss:2.036553144454956 lr:2.626931266362277e-05 tokens_per_second_per_gpu:775.6765005682254 +Step 6180 | loss:1.978617787361145 lr:2.6242736108136933e-05 tokens_per_second_per_gpu:761.3362615821457 +Step 6181 | loss:2.0351462364196777 lr:2.6216170972582166e-05 tokens_per_second_per_gpu:801.6323361148684 +Step 6182 | loss:2.044722080230713 lr:2.6189617261071496e-05 tokens_per_second_per_gpu:785.558235054425 +Step 6183 | loss:1.9994503259658813 lr:2.6163074977716317e-05 tokens_per_second_per_gpu:765.9694337574837 +Step 6184 | loss:2.0021109580993652 lr:2.6136544126626204e-05 tokens_per_second_per_gpu:773.2693996573453 +Step 6185 | loss:1.958931803703308 lr:2.6110024711908954e-05 tokens_per_second_per_gpu:748.1537271086356 +Step 6186 | loss:1.9630413055419922 lr:2.608351673767061e-05 tokens_per_second_per_gpu:773.4175480227333 +Step 6187 | loss:2.060042381286621 lr:2.605702020801546e-05 tokens_per_second_per_gpu:779.8169433106596 +Step 6188 | loss:1.9874980449676514 lr:2.603053512704593e-05 tokens_per_second_per_gpu:785.4564684509021 +Step 6189 | loss:2.022719621658325 lr:2.6004061498862752e-05 tokens_per_second_per_gpu:792.0996946182383 +Step 6190 | loss:1.9910829067230225 lr:2.597759932756495e-05 tokens_per_second_per_gpu:775.7036446446994 +Step 6191 | loss:2.036179780960083 lr:2.595114861724962e-05 tokens_per_second_per_gpu:770.9347057288103 +Step 6192 | loss:2.024613618850708 lr:2.592470937201217e-05 tokens_per_second_per_gpu:773.8817012606121 +Step 6193 | loss:1.9284045696258545 lr:2.589828159594626e-05 tokens_per_second_per_gpu:793.6358991022091 +Step 6194 | loss:1.9749633073806763 lr:2.5871865293143693e-05 tokens_per_second_per_gpu:784.7415881302294 +Step 6195 | loss:2.001108407974243 lr:2.5845460467694516e-05 tokens_per_second_per_gpu:779.6458318108929 +Step 6196 | loss:2.0170509815216064 lr:2.5819067123687113e-05 tokens_per_second_per_gpu:777.4249282859512 +Step 6197 | loss:1.9467952251434326 lr:2.5792685265207927e-05 tokens_per_second_per_gpu:782.2410312656308 +Step 6198 | loss:2.0285732746124268 lr:2.5766314896341702e-05 tokens_per_second_per_gpu:773.6039520829331 +Step 6199 | loss:2.0193819999694824 lr:2.573995602117144e-05 tokens_per_second_per_gpu:742.1800905979728 +Step 6200 | loss:2.046950101852417 lr:2.571360864377823e-05 tokens_per_second_per_gpu:770.081802703447 +Step 6201 | loss:2.0001063346862793 lr:2.5687272768241553e-05 tokens_per_second_per_gpu:779.6323397317403 +Step 6202 | loss:1.9950588941574097 lr:2.566094839863904e-05 tokens_per_second_per_gpu:772.0552845862271 +Step 6203 | loss:1.9460487365722656 lr:2.5634635539046447e-05 tokens_per_second_per_gpu:765.6693016281552 +Step 6204 | loss:2.011979818344116 lr:2.5608334193537863e-05 tokens_per_second_per_gpu:756.3528764375392 +Step 6205 | loss:2.0237338542938232 lr:2.5582044366185574e-05 tokens_per_second_per_gpu:750.8025939102228 +Step 6206 | loss:2.017183780670166 lr:2.5555766061060048e-05 tokens_per_second_per_gpu:785.1796140817441 +Step 6207 | loss:2.0528640747070312 lr:2.5529499282229996e-05 tokens_per_second_per_gpu:777.2832943727866 +Step 6208 | loss:2.0209598541259766 lr:2.5503244033762364e-05 tokens_per_second_per_gpu:756.6234518125067 +Step 6209 | loss:1.9628403186798096 lr:2.5477000319722232e-05 tokens_per_second_per_gpu:800.0529509567892 +Step 6210 | loss:2.045872926712036 lr:2.5450768144172976e-05 tokens_per_second_per_gpu:788.901816195893 +Step 6211 | loss:2.02587628364563 lr:2.5424547511176156e-05 tokens_per_second_per_gpu:766.4359110036555 +Step 6212 | loss:1.9890018701553345 lr:2.5398338424791547e-05 tokens_per_second_per_gpu:749.9862549528923 +Step 6213 | loss:2.015178680419922 lr:2.537214088907712e-05 tokens_per_second_per_gpu:762.0559694537714 +Step 6214 | loss:2.0152640342712402 lr:2.534595490808913e-05 tokens_per_second_per_gpu:781.3587917624558 +Step 6215 | loss:2.05888295173645 lr:2.5319780485881907e-05 tokens_per_second_per_gpu:766.2063297344573 +Step 6216 | loss:1.9852359294891357 lr:2.529361762650807e-05 tokens_per_second_per_gpu:752.725477370627 +Step 6217 | loss:2.035982131958008 lr:2.526746633401855e-05 tokens_per_second_per_gpu:788.6918436364035 +Step 6218 | loss:2.034778118133545 lr:2.524132661246229e-05 tokens_per_second_per_gpu:790.2021775714343 +Step 6219 | loss:2.0320026874542236 lr:2.521519846588656e-05 tokens_per_second_per_gpu:755.5823810867967 +Step 6220 | loss:1.9653090238571167 lr:2.5189081898336852e-05 tokens_per_second_per_gpu:763.5358266782805 +Step 6221 | loss:2.0179171562194824 lr:2.516297691385673e-05 tokens_per_second_per_gpu:785.2198634488346 +Step 6222 | loss:1.982413411140442 lr:2.513688351648815e-05 tokens_per_second_per_gpu:752.0870571137922 +Step 6223 | loss:1.9842065572738647 lr:2.5110801710271204e-05 tokens_per_second_per_gpu:748.0571735456261 +Step 6224 | loss:2.0447402000427246 lr:2.5084731499244098e-05 tokens_per_second_per_gpu:775.9341791855502 +Step 6225 | loss:2.038054943084717 lr:2.5058672887443335e-05 tokens_per_second_per_gpu:771.7180979476944 +Step 6226 | loss:1.994079351425171 lr:2.503262587890365e-05 tokens_per_second_per_gpu:784.8112501933617 +Step 6227 | loss:1.9828377962112427 lr:2.5006590477657842e-05 tokens_per_second_per_gpu:780.3861584825263 +Step 6228 | loss:2.030921697616577 lr:2.4980566687737095e-05 tokens_per_second_per_gpu:746.0021011958828 +Step 6229 | loss:1.9958232641220093 lr:2.4954554513170704e-05 tokens_per_second_per_gpu:789.4298071056129 +Step 6230 | loss:2.0181517601013184 lr:2.49285539579861e-05 tokens_per_second_per_gpu:799.7449193775517 +Step 6231 | loss:1.967909336090088 lr:2.4902565026209014e-05 tokens_per_second_per_gpu:733.5088826923252 +Step 6232 | loss:2.002155303955078 lr:2.4876587721863354e-05 tokens_per_second_per_gpu:759.1888605417203 +Step 6233 | loss:2.0312533378601074 lr:2.4850622048971216e-05 tokens_per_second_per_gpu:763.3384230061612 +Step 6234 | loss:1.9840182065963745 lr:2.4824668011552898e-05 tokens_per_second_per_gpu:737.138551658303 +Step 6235 | loss:2.008084774017334 lr:2.479872561362693e-05 tokens_per_second_per_gpu:730.9626225657812 +Step 6236 | loss:2.003202199935913 lr:2.4772794859209935e-05 tokens_per_second_per_gpu:793.5061042390748 +Step 6237 | loss:2.0138280391693115 lr:2.4746875752316846e-05 tokens_per_second_per_gpu:733.5462497218708 +Step 6238 | loss:2.001875638961792 lr:2.4720968296960744e-05 tokens_per_second_per_gpu:772.2429675027106 +Step 6239 | loss:2.0286307334899902 lr:2.4695072497152917e-05 tokens_per_second_per_gpu:785.5573967199714 +Step 6240 | loss:2.0082545280456543 lr:2.466918835690285e-05 tokens_per_second_per_gpu:777.6134455847383 +Step 6241 | loss:2.0498290061950684 lr:2.464331588021823e-05 tokens_per_second_per_gpu:782.4414390979028 +Step 6242 | loss:1.964327096939087 lr:2.461745507110489e-05 tokens_per_second_per_gpu:752.9614876950699 +Step 6243 | loss:2.007883071899414 lr:2.4591605933566864e-05 tokens_per_second_per_gpu:778.4894879359709 +Step 6244 | loss:1.9976872205734253 lr:2.4565768471606522e-05 tokens_per_second_per_gpu:784.7896669061838 +Step 6245 | loss:2.031057596206665 lr:2.4539942689224204e-05 tokens_per_second_per_gpu:735.9301261172051 +Step 6246 | loss:2.0502331256866455 lr:2.4514128590418596e-05 tokens_per_second_per_gpu:762.4320242333366 +Step 6247 | loss:2.0156400203704834 lr:2.448832617918654e-05 tokens_per_second_per_gpu:738.5969418718068 +Step 6248 | loss:2.0656652450561523 lr:2.4462535459522974e-05 tokens_per_second_per_gpu:770.1245302810875 +Step 6249 | loss:2.0219671726226807 lr:2.4436756435421192e-05 tokens_per_second_per_gpu:759.669181933115 +Step 6250 | loss:2.0083863735198975 lr:2.4410989110872605e-05 tokens_per_second_per_gpu:768.7822024285931 +Step 6251 | loss:1.9918498992919922 lr:2.438523348986673e-05 tokens_per_second_per_gpu:783.8933407202168 +Step 6252 | loss:1.9883384704589844 lr:2.435948957639138e-05 tokens_per_second_per_gpu:771.7584911320582 +Step 6253 | loss:1.9650769233703613 lr:2.4333757374432554e-05 tokens_per_second_per_gpu:763.2671575885004 +Step 6254 | loss:2.02390718460083 lr:2.4308036887974295e-05 tokens_per_second_per_gpu:776.0945683703984 +Step 6255 | loss:2.054678440093994 lr:2.4282328120999032e-05 tokens_per_second_per_gpu:759.2117613350456 +Step 6256 | loss:2.0253944396972656 lr:2.425663107748729e-05 tokens_per_second_per_gpu:785.2674095848919 +Step 6257 | loss:1.9607210159301758 lr:2.423094576141771e-05 tokens_per_second_per_gpu:760.4583525304246 +Step 6258 | loss:2.034644603729248 lr:2.4205272176767225e-05 tokens_per_second_per_gpu:789.2867818816171 +Step 6259 | loss:2.0150818824768066 lr:2.4179610327510905e-05 tokens_per_second_per_gpu:773.7047163169068 +Step 6260 | loss:1.951737642288208 lr:2.4153960217621995e-05 tokens_per_second_per_gpu:766.2526990795129 +Step 6261 | loss:1.992459774017334 lr:2.4128321851071944e-05 tokens_per_second_per_gpu:753.8364785929284 +Step 6262 | loss:1.9842274188995361 lr:2.4102695231830395e-05 tokens_per_second_per_gpu:762.575643226808 +Step 6263 | loss:1.975247859954834 lr:2.4077080363865112e-05 tokens_per_second_per_gpu:786.1546806851399 +Step 6264 | loss:2.018958568572998 lr:2.4051477251142052e-05 tokens_per_second_per_gpu:789.4389660931937 +Step 6265 | loss:2.0007290840148926 lr:2.4025885897625465e-05 tokens_per_second_per_gpu:787.9462611719516 +Step 6266 | loss:2.0540409088134766 lr:2.400030630727763e-05 tokens_per_second_per_gpu:797.513401780734 +Step 6267 | loss:2.043581962585449 lr:2.397473848405908e-05 tokens_per_second_per_gpu:781.9485494746054 +Step 6268 | loss:2.0353755950927734 lr:2.394918243192854e-05 tokens_per_second_per_gpu:784.6029352460146 +Step 6269 | loss:2.0265283584594727 lr:2.3923638154842844e-05 tokens_per_second_per_gpu:749.4477286214684 +Step 6270 | loss:1.988132119178772 lr:2.389810565675702e-05 tokens_per_second_per_gpu:763.7216733952357 +Step 6271 | loss:2.038633108139038 lr:2.387258494162441e-05 tokens_per_second_per_gpu:789.7595686536814 +Step 6272 | loss:2.015934705734253 lr:2.384707601339631e-05 tokens_per_second_per_gpu:740.9235237740646 +Step 6273 | loss:1.9813448190689087 lr:2.3821578876022344e-05 tokens_per_second_per_gpu:755.6501031906156 +Step 6274 | loss:2.0540685653686523 lr:2.379609353345028e-05 tokens_per_second_per_gpu:773.5400874273292 +Step 6275 | loss:2.0482420921325684 lr:2.3770619989625985e-05 tokens_per_second_per_gpu:785.9931735791957 +Step 6276 | loss:1.9903883934020996 lr:2.3745158248493625e-05 tokens_per_second_per_gpu:754.3637825664644 +Step 6277 | loss:2.023852825164795 lr:2.371970831399547e-05 tokens_per_second_per_gpu:772.3179802948373 +Step 6278 | loss:2.032047986984253 lr:2.3694270190071933e-05 tokens_per_second_per_gpu:772.7605781005966 +Step 6279 | loss:2.0140812397003174 lr:2.366884388066164e-05 tokens_per_second_per_gpu:775.9213893935099 +Step 6280 | loss:1.9504079818725586 lr:2.3643429389701377e-05 tokens_per_second_per_gpu:788.8438074953376 +Step 6281 | loss:1.992828369140625 lr:2.361802672112611e-05 tokens_per_second_per_gpu:788.6311551886329 +Step 6282 | loss:2.013822078704834 lr:2.3592635878868973e-05 tokens_per_second_per_gpu:778.1772899724521 +Step 6283 | loss:2.031248092651367 lr:2.3567256866861277e-05 tokens_per_second_per_gpu:777.8840847259971 +Step 6284 | loss:2.026516914367676 lr:2.3541889689032438e-05 tokens_per_second_per_gpu:773.3880804848685 +Step 6285 | loss:2.025829553604126 lr:2.3516534349310117e-05 tokens_per_second_per_gpu:742.4994382242699 +Step 6286 | loss:1.9951038360595703 lr:2.3491190851620104e-05 tokens_per_second_per_gpu:796.2980071448355 +Step 6287 | loss:2.0051512718200684 lr:2.3465859199886375e-05 tokens_per_second_per_gpu:773.932584598504 +Step 6288 | loss:1.9523169994354248 lr:2.344053939803106e-05 tokens_per_second_per_gpu:785.4053997173841 +Step 6289 | loss:2.0631325244903564 lr:2.3415231449974483e-05 tokens_per_second_per_gpu:766.7712263065399 +Step 6290 | loss:2.0165669918060303 lr:2.338993535963505e-05 tokens_per_second_per_gpu:772.2848130868302 +Step 6291 | loss:1.965528964996338 lr:2.3364651130929416e-05 tokens_per_second_per_gpu:756.2131432594908 +Step 6292 | loss:2.0758070945739746 lr:2.3339378767772356e-05 tokens_per_second_per_gpu:797.6327950582503 +Step 6293 | loss:1.996674656867981 lr:2.3314118274076857e-05 tokens_per_second_per_gpu:766.6304664449266 +Step 6294 | loss:2.0044405460357666 lr:2.3288869653753996e-05 tokens_per_second_per_gpu:772.4202712914263 +Step 6295 | loss:1.9833940267562866 lr:2.3263632910713097e-05 tokens_per_second_per_gpu:777.8816627602015 +Step 6296 | loss:2.002598524093628 lr:2.323840804886154e-05 tokens_per_second_per_gpu:790.6790018891201 +Step 6297 | loss:2.0254037380218506 lr:2.321319507210492e-05 tokens_per_second_per_gpu:778.1451653814321 +Step 6298 | loss:2.043151617050171 lr:2.3187993984347078e-05 tokens_per_second_per_gpu:767.875528001688 +Step 6299 | loss:2.013653039932251 lr:2.3162804789489834e-05 tokens_per_second_per_gpu:761.4381770148452 +Step 6300 | loss:1.9812133312225342 lr:2.313762749143331e-05 tokens_per_second_per_gpu:763.9107545615369 +Step 6301 | loss:2.011117935180664 lr:2.311246209407577e-05 tokens_per_second_per_gpu:753.8733903559367 +Step 6302 | loss:1.9801279306411743 lr:2.3087308601313494e-05 tokens_per_second_per_gpu:784.1464552443258 +Step 6303 | loss:1.9976882934570312 lr:2.3062167017041148e-05 tokens_per_second_per_gpu:756.0360490649254 +Step 6304 | loss:1.9418013095855713 lr:2.3037037345151402e-05 tokens_per_second_per_gpu:779.6930342295504 +Step 6305 | loss:2.040759801864624 lr:2.301191958953508e-05 tokens_per_second_per_gpu:784.5086378878854 +Step 6306 | loss:1.9888570308685303 lr:2.2986813754081216e-05 tokens_per_second_per_gpu:733.3087502761491 +Step 6307 | loss:1.985864520072937 lr:2.2961719842676988e-05 tokens_per_second_per_gpu:779.2754204132877 +Step 6308 | loss:1.9840583801269531 lr:2.293663785920771e-05 tokens_per_second_per_gpu:793.1629737598173 +Step 6309 | loss:1.993212103843689 lr:2.2911567807556854e-05 tokens_per_second_per_gpu:763.8290520562211 +Step 6310 | loss:2.018510580062866 lr:2.2886509691606084e-05 tokens_per_second_per_gpu:784.258561338557 +Step 6311 | loss:2.0152554512023926 lr:2.2861463515235115e-05 tokens_per_second_per_gpu:765.116762387838 +Step 6312 | loss:1.9666494131088257 lr:2.2836429282321915e-05 tokens_per_second_per_gpu:766.614466871583 +Step 6313 | loss:2.009242534637451 lr:2.2811406996742568e-05 tokens_per_second_per_gpu:727.5787308573845 +Step 6314 | loss:2.0686113834381104 lr:2.278639666237129e-05 tokens_per_second_per_gpu:772.7987857347849 +Step 6315 | loss:2.0059049129486084 lr:2.276139828308048e-05 tokens_per_second_per_gpu:790.9454284823933 +Step 6316 | loss:2.0218944549560547 lr:2.2736411862740704e-05 tokens_per_second_per_gpu:748.1219420301742 +Step 6317 | loss:1.9906407594680786 lr:2.271143740522056e-05 tokens_per_second_per_gpu:784.7198799517978 +Step 6318 | loss:1.9847939014434814 lr:2.2686474914386913e-05 tokens_per_second_per_gpu:777.1217622046079 +Step 6319 | loss:2.000365972518921 lr:2.266152439410475e-05 tokens_per_second_per_gpu:756.4731410653044 +Step 6320 | loss:1.989744782447815 lr:2.263658584823717e-05 tokens_per_second_per_gpu:790.8005344682489 +Step 6321 | loss:2.021843910217285 lr:2.2611659280645458e-05 tokens_per_second_per_gpu:767.163026014258 +Step 6322 | loss:2.055088996887207 lr:2.2586744695189043e-05 tokens_per_second_per_gpu:778.6240191643853 +Step 6323 | loss:2.0266895294189453 lr:2.2561842095725405e-05 tokens_per_second_per_gpu:788.308994444786 +Step 6324 | loss:2.023566246032715 lr:2.2536951486110325e-05 tokens_per_second_per_gpu:746.0379990014873 +Step 6325 | loss:1.9746249914169312 lr:2.2512072870197653e-05 tokens_per_second_per_gpu:785.1996155404565 +Step 6326 | loss:2.033392906188965 lr:2.248720625183932e-05 tokens_per_second_per_gpu:791.0666615852559 +Step 6327 | loss:1.9901468753814697 lr:2.246235163488547e-05 tokens_per_second_per_gpu:781.9315475008993 +Step 6328 | loss:1.9888362884521484 lr:2.243750902318442e-05 tokens_per_second_per_gpu:796.9211829130172 +Step 6329 | loss:1.9848517179489136 lr:2.24126784205825e-05 tokens_per_second_per_gpu:730.3428999490295 +Step 6330 | loss:1.9791135787963867 lr:2.238785983092434e-05 tokens_per_second_per_gpu:792.9899177764169 +Step 6331 | loss:2.045811653137207 lr:2.2363053258052634e-05 tokens_per_second_per_gpu:790.781840414172 +Step 6332 | loss:2.013704776763916 lr:2.2338258705808158e-05 tokens_per_second_per_gpu:770.5185501381366 +Step 6333 | loss:2.0344314575195312 lr:2.2313476178029913e-05 tokens_per_second_per_gpu:717.3978531222625 +Step 6334 | loss:2.031562089920044 lr:2.228870567855501e-05 tokens_per_second_per_gpu:781.5139408745054 +Step 6335 | loss:2.007791519165039 lr:2.2263947211218694e-05 tokens_per_second_per_gpu:749.6609656800063 +Step 6336 | loss:2.022700786590576 lr:2.2239200779854363e-05 tokens_per_second_per_gpu:779.9876389258596 +Step 6337 | loss:1.9756793975830078 lr:2.2214466388293553e-05 tokens_per_second_per_gpu:776.5558514642192 +Step 6338 | loss:2.0155138969421387 lr:2.2189744040365866e-05 tokens_per_second_per_gpu:780.1503065832379 +Step 6339 | loss:1.9621646404266357 lr:2.216503373989913e-05 tokens_per_second_per_gpu:767.1761458530295 +Step 6340 | loss:2.015146493911743 lr:2.2140335490719276e-05 tokens_per_second_per_gpu:775.2588882291894 +Step 6341 | loss:2.055464029312134 lr:2.211564929665034e-05 tokens_per_second_per_gpu:756.8417808675013 +Step 6342 | loss:1.9786088466644287 lr:2.209097516151455e-05 tokens_per_second_per_gpu:783.891297309091 +Step 6343 | loss:2.024996519088745 lr:2.206631308913224e-05 tokens_per_second_per_gpu:750.3711394904684 +Step 6344 | loss:2.042037010192871 lr:2.204166308332183e-05 tokens_per_second_per_gpu:770.6014807513811 +Step 6345 | loss:1.981377363204956 lr:2.2017025147899916e-05 tokens_per_second_per_gpu:754.8816515081851 +Step 6346 | loss:2.033470630645752 lr:2.1992399286681242e-05 tokens_per_second_per_gpu:761.0814396289921 +Step 6347 | loss:2.069730758666992 lr:2.1967785503478656e-05 tokens_per_second_per_gpu:749.0471674493062 +Step 6348 | loss:2.0031492710113525 lr:2.194318380210313e-05 tokens_per_second_per_gpu:788.3442834136 +Step 6349 | loss:1.9757592678070068 lr:2.1918594186363827e-05 tokens_per_second_per_gpu:781.166509998391 +Step 6350 | loss:1.9950361251831055 lr:2.1894016660067884e-05 tokens_per_second_per_gpu:759.220201445757 +Step 6351 | loss:1.9708671569824219 lr:2.1869451227020765e-05 tokens_per_second_per_gpu:777.8785636042015 +Step 6352 | loss:1.9940065145492554 lr:2.184489789102596e-05 tokens_per_second_per_gpu:734.9127157956085 +Step 6353 | loss:1.9685657024383545 lr:2.1820356655885053e-05 tokens_per_second_per_gpu:786.7382298608248 +Step 6354 | loss:2.006507396697998 lr:2.1795827525397806e-05 tokens_per_second_per_gpu:777.6732086521921 +Step 6355 | loss:2.005720615386963 lr:2.177131050336213e-05 tokens_per_second_per_gpu:760.9621737128863 +Step 6356 | loss:2.005916118621826 lr:2.1746805593573937e-05 tokens_per_second_per_gpu:780.0880119187622 +Step 6357 | loss:1.9634419679641724 lr:2.172231279982745e-05 tokens_per_second_per_gpu:796.9782905452938 +Step 6358 | loss:2.005122661590576 lr:2.169783212591491e-05 tokens_per_second_per_gpu:739.8779279875648 +Step 6359 | loss:2.0064613819122314 lr:2.1673363575626627e-05 tokens_per_second_per_gpu:780.2540784449216 +Step 6360 | loss:2.015209674835205 lr:2.164890715275115e-05 tokens_per_second_per_gpu:787.3305149634258 +Step 6361 | loss:1.9980692863464355 lr:2.162446286107508e-05 tokens_per_second_per_gpu:799.2186943166987 +Step 6362 | loss:2.045966863632202 lr:2.1600030704383155e-05 tokens_per_second_per_gpu:776.4239467665724 +Step 6363 | loss:2.0416479110717773 lr:2.1575610686458246e-05 tokens_per_second_per_gpu:769.1877039688301 +Step 6364 | loss:1.9590015411376953 lr:2.1551202811081362e-05 tokens_per_second_per_gpu:772.3336313967039 +Step 6365 | loss:2.017599582672119 lr:2.1526807082031554e-05 tokens_per_second_per_gpu:766.9442426312911 +Step 6366 | loss:2.047813892364502 lr:2.1502423503086056e-05 tokens_per_second_per_gpu:786.283144007834 +Step 6367 | loss:2.004282236099243 lr:2.1478052078020217e-05 tokens_per_second_per_gpu:762.6652580668202 +Step 6368 | loss:1.972795009613037 lr:2.1453692810607507e-05 tokens_per_second_per_gpu:784.7255514960655 +Step 6369 | loss:1.9820241928100586 lr:2.1429345704619487e-05 tokens_per_second_per_gpu:786.6862994854265 +Step 6370 | loss:2.026721954345703 lr:2.1405010763825882e-05 tokens_per_second_per_gpu:772.7443146786724 +Step 6371 | loss:2.0157735347747803 lr:2.1380687991994452e-05 tokens_per_second_per_gpu:764.653330234691 +Step 6372 | loss:1.9796154499053955 lr:2.135637739289115e-05 tokens_per_second_per_gpu:788.0026811194241 +Step 6373 | loss:2.016688346862793 lr:2.133207897028001e-05 tokens_per_second_per_gpu:774.6516622961194 +Step 6374 | loss:1.9352445602416992 lr:2.1307792727923192e-05 tokens_per_second_per_gpu:774.6696162615256 +Step 6375 | loss:1.9778082370758057 lr:2.128351866958096e-05 tokens_per_second_per_gpu:758.4124835411262 +Step 6376 | loss:1.973182201385498 lr:2.125925679901174e-05 tokens_per_second_per_gpu:761.1356670804586 +Step 6377 | loss:2.004655361175537 lr:2.123500711997193e-05 tokens_per_second_per_gpu:778.5978219111391 +Step 6378 | loss:2.0192723274230957 lr:2.121076963621622e-05 tokens_per_second_per_gpu:744.8056741064684 +Step 6379 | loss:2.016451120376587 lr:2.118654435149735e-05 tokens_per_second_per_gpu:779.0310407401194 +Step 6380 | loss:1.995937466621399 lr:2.116233126956608e-05 tokens_per_second_per_gpu:764.584749554758 +Step 6381 | loss:1.9806838035583496 lr:2.1138130394171385e-05 tokens_per_second_per_gpu:761.4806007725225 +Step 6382 | loss:2.057358503341675 lr:2.1113941729060306e-05 tokens_per_second_per_gpu:764.0916787886804 +Step 6383 | loss:1.9911739826202393 lr:2.1089765277978023e-05 tokens_per_second_per_gpu:775.5130571595796 +Step 6384 | loss:2.0247669219970703 lr:2.1065601044667805e-05 tokens_per_second_per_gpu:783.4354786739378 +Step 6385 | loss:2.003767967224121 lr:2.104144903287104e-05 tokens_per_second_per_gpu:758.9503119689688 +Step 6386 | loss:1.9598702192306519 lr:2.1017309246327177e-05 tokens_per_second_per_gpu:753.7690097840908 +Step 6387 | loss:1.9802805185317993 lr:2.0993181688773832e-05 tokens_per_second_per_gpu:770.328317844829 +Step 6388 | loss:2.0269453525543213 lr:2.09690663639467e-05 tokens_per_second_per_gpu:770.896802095905 +Step 6389 | loss:1.9732329845428467 lr:2.09449632755796e-05 tokens_per_second_per_gpu:744.320118155517 +Step 6390 | loss:2.072347640991211 lr:2.0920872427404438e-05 tokens_per_second_per_gpu:775.4725773713915 +Step 6391 | loss:1.9686906337738037 lr:2.089679382315125e-05 tokens_per_second_per_gpu:776.2525311527778 +Step 6392 | loss:2.011127471923828 lr:2.0872727466548114e-05 tokens_per_second_per_gpu:783.6946796240996 +Step 6393 | loss:2.0172317028045654 lr:2.084867336132128e-05 tokens_per_second_per_gpu:768.1416864202137 +Step 6394 | loss:1.9830431938171387 lr:2.082463151119507e-05 tokens_per_second_per_gpu:764.3296455261467 +Step 6395 | loss:1.9887101650238037 lr:2.0800601919891914e-05 tokens_per_second_per_gpu:755.4413208987048 +Step 6396 | loss:2.019064426422119 lr:2.0776584591132354e-05 tokens_per_second_per_gpu:768.930196336153 +Step 6397 | loss:2.0014491081237793 lr:2.0752579528635042e-05 tokens_per_second_per_gpu:785.6875055312045 +Step 6398 | loss:2.028439521789551 lr:2.0728586736116627e-05 tokens_per_second_per_gpu:766.7309829009689 +Step 6399 | loss:1.9963455200195312 lr:2.0704606217292067e-05 tokens_per_second_per_gpu:784.8301607272799 +Step 6400 | loss:2.067500352859497 lr:2.0680637975874195e-05 tokens_per_second_per_gpu:736.3174185172718 +Step 6401 | loss:1.9959057569503784 lr:2.0656682015574092e-05 tokens_per_second_per_gpu:772.4977229601051 +Step 6402 | loss:2.0364489555358887 lr:2.0632738340100876e-05 tokens_per_second_per_gpu:785.6887533262782 +Step 6403 | loss:1.972456455230713 lr:2.0608806953161806e-05 tokens_per_second_per_gpu:795.969991356841 +Step 6404 | loss:1.9705860614776611 lr:2.0584887858462144e-05 tokens_per_second_per_gpu:780.2988561873112 +Step 6405 | loss:2.017144203186035 lr:2.0560981059705363e-05 tokens_per_second_per_gpu:775.6542326542351 +Step 6406 | loss:2.044009208679199 lr:2.053708656059301e-05 tokens_per_second_per_gpu:770.3374698777039 +Step 6407 | loss:2.023167610168457 lr:2.0513204364824635e-05 tokens_per_second_per_gpu:758.9198699486029 +Step 6408 | loss:2.0187010765075684 lr:2.0489334476097975e-05 tokens_per_second_per_gpu:752.3362757237375 +Step 6409 | loss:1.9812713861465454 lr:2.0465476898108848e-05 tokens_per_second_per_gpu:770.944744612165 +Step 6410 | loss:1.9920704364776611 lr:2.044163163455114e-05 tokens_per_second_per_gpu:774.3469322198748 +Step 6411 | loss:1.9972184896469116 lr:2.0417798689116852e-05 tokens_per_second_per_gpu:771.8294128967788 +Step 6412 | loss:2.0670979022979736 lr:2.039397806549608e-05 tokens_per_second_per_gpu:789.9956686908442 +Step 6413 | loss:2.016796112060547 lr:2.0370169767376968e-05 tokens_per_second_per_gpu:776.4190284983991 +Step 6414 | loss:2.0561487674713135 lr:2.0346373798445794e-05 tokens_per_second_per_gpu:784.6384307954073 +Step 6415 | loss:2.03412127494812 lr:2.0322590162386933e-05 tokens_per_second_per_gpu:773.688640969825 +Step 6416 | loss:1.9649285078048706 lr:2.029881886288284e-05 tokens_per_second_per_gpu:785.2292768706317 +Step 6417 | loss:2.0849783420562744 lr:2.0275059903614036e-05 tokens_per_second_per_gpu:776.2576379335526 +Step 6418 | loss:1.9953724145889282 lr:2.025131328825919e-05 tokens_per_second_per_gpu:784.9382098914882 +Step 6419 | loss:2.0251171588897705 lr:2.0227579020494957e-05 tokens_per_second_per_gpu:780.8716829294382 +Step 6420 | loss:2.0237174034118652 lr:2.020385710399618e-05 tokens_per_second_per_gpu:783.6960300522514 +Step 6421 | loss:2.0324666500091553 lr:2.0180147542435758e-05 tokens_per_second_per_gpu:766.0028123782982 +Step 6422 | loss:1.9990789890289307 lr:2.015645033948467e-05 tokens_per_second_per_gpu:787.6802820480178 +Step 6423 | loss:1.9995592832565308 lr:2.013276549881197e-05 tokens_per_second_per_gpu:773.6589987813294 +Step 6424 | loss:1.9517390727996826 lr:2.0109093024084848e-05 tokens_per_second_per_gpu:743.7331271091155 +Step 6425 | loss:1.989283800125122 lr:2.008543291896847e-05 tokens_per_second_per_gpu:744.1008532826083 +Step 6426 | loss:2.0082345008850098 lr:2.006178518712626e-05 tokens_per_second_per_gpu:784.333843226099 +Step 6427 | loss:2.0636377334594727 lr:2.0038149832219545e-05 tokens_per_second_per_gpu:782.8595281209609 +Step 6428 | loss:2.016986846923828 lr:2.0014526857907855e-05 tokens_per_second_per_gpu:771.0142643084929 +Step 6429 | loss:1.967329978942871 lr:1.9990916267848747e-05 tokens_per_second_per_gpu:736.0025484489122 +Step 6430 | loss:1.984662652015686 lr:1.9967318065697915e-05 tokens_per_second_per_gpu:785.027607844327 +Step 6431 | loss:2.0058231353759766 lr:1.994373225510903e-05 tokens_per_second_per_gpu:758.0791302696018 +Step 6432 | loss:2.0183629989624023 lr:1.992015883973397e-05 tokens_per_second_per_gpu:771.1774806036808 +Step 6433 | loss:2.023735761642456 lr:1.989659782322265e-05 tokens_per_second_per_gpu:781.633222276426 +Step 6434 | loss:2.0583786964416504 lr:1.9873049209222994e-05 tokens_per_second_per_gpu:761.2064695080804 +Step 6435 | loss:1.9539082050323486 lr:1.9849513001381103e-05 tokens_per_second_per_gpu:787.14650349259 +Step 6436 | loss:1.947222113609314 lr:1.98259892033411e-05 tokens_per_second_per_gpu:780.7848908577823 +Step 6437 | loss:2.0643467903137207 lr:1.9802477818745224e-05 tokens_per_second_per_gpu:773.1672852911408 +Step 6438 | loss:2.008101224899292 lr:1.9778978851233754e-05 tokens_per_second_per_gpu:781.1982296754518 +Step 6439 | loss:2.0231211185455322 lr:1.97554923044451e-05 tokens_per_second_per_gpu:764.2132520456989 +Step 6440 | loss:2.018712043762207 lr:1.9732018182015667e-05 tokens_per_second_per_gpu:780.4754963880556 +Step 6441 | loss:2.044724225997925 lr:1.9708556487579997e-05 tokens_per_second_per_gpu:786.2798203489784 +Step 6442 | loss:2.0051023960113525 lr:1.9685107224770704e-05 tokens_per_second_per_gpu:792.627937612359 +Step 6443 | loss:2.053572654724121 lr:1.966167039721846e-05 tokens_per_second_per_gpu:776.9787259397734 +Step 6444 | loss:1.9908324480056763 lr:1.9638246008552018e-05 tokens_per_second_per_gpu:782.2659238231955 +Step 6445 | loss:1.956565499305725 lr:1.9614834062398248e-05 tokens_per_second_per_gpu:772.6665621331543 +Step 6446 | loss:1.9761154651641846 lr:1.9591434562381982e-05 tokens_per_second_per_gpu:784.2768223835701 +Step 6447 | loss:2.0097222328186035 lr:1.9568047512126232e-05 tokens_per_second_per_gpu:783.8198503994446 +Step 6448 | loss:1.9922093152999878 lr:1.9544672915252028e-05 tokens_per_second_per_gpu:779.0843097474302 +Step 6449 | loss:1.982212781906128 lr:1.95213107753785e-05 tokens_per_second_per_gpu:747.9855858522818 +Step 6450 | loss:1.9780261516571045 lr:1.9497961096122842e-05 tokens_per_second_per_gpu:778.0494382785832 +Step 6451 | loss:2.0085813999176025 lr:1.947462388110034e-05 tokens_per_second_per_gpu:750.8051973210161 +Step 6452 | loss:1.9921455383300781 lr:1.945129913392424e-05 tokens_per_second_per_gpu:775.161602336533 +Step 6453 | loss:2.123828411102295 lr:1.9427986858206036e-05 tokens_per_second_per_gpu:792.2025718708029 +Step 6454 | loss:2.041424512863159 lr:1.940468705755515e-05 tokens_per_second_per_gpu:779.2845314620434 +Step 6455 | loss:2.060319185256958 lr:1.938139973557912e-05 tokens_per_second_per_gpu:773.3420814128846 +Step 6456 | loss:1.994344711303711 lr:1.9358124895883556e-05 tokens_per_second_per_gpu:785.362584357255 +Step 6457 | loss:2.060779333114624 lr:1.933486254207216e-05 tokens_per_second_per_gpu:723.9229711925766 +Step 6458 | loss:1.951992392539978 lr:1.9311612677746605e-05 tokens_per_second_per_gpu:793.6129008792229 +Step 6459 | loss:2.0000052452087402 lr:1.9288375306506758e-05 tokens_per_second_per_gpu:759.0798581513859 +Step 6460 | loss:1.9986774921417236 lr:1.9265150431950496e-05 tokens_per_second_per_gpu:776.9067373615932 +Step 6461 | loss:1.9916253089904785 lr:1.9241938057673704e-05 tokens_per_second_per_gpu:775.3541170019993 +Step 6462 | loss:2.002869129180908 lr:1.9218738187270413e-05 tokens_per_second_per_gpu:785.058543336732 +Step 6463 | loss:2.057455539703369 lr:1.9195550824332687e-05 tokens_per_second_per_gpu:751.3234217034129 +Step 6464 | loss:1.99882173538208 lr:1.917237597245065e-05 tokens_per_second_per_gpu:736.5780875092098 +Step 6465 | loss:2.0061731338500977 lr:1.9149213635212503e-05 tokens_per_second_per_gpu:783.443470803785 +Step 6466 | loss:2.0057826042175293 lr:1.912606381620452e-05 tokens_per_second_per_gpu:770.0101143028334 +Step 6467 | loss:2.045440673828125 lr:1.9102926519010966e-05 tokens_per_second_per_gpu:761.1651892285827 +Step 6468 | loss:1.9622992277145386 lr:1.9079801747214244e-05 tokens_per_second_per_gpu:764.3046256170799 +Step 6469 | loss:1.9606742858886719 lr:1.9056689504394788e-05 tokens_per_second_per_gpu:772.0053875325513 +Step 6470 | loss:2.023186445236206 lr:1.90335897941311e-05 tokens_per_second_per_gpu:755.5324002234282 +Step 6471 | loss:1.9728286266326904 lr:1.9010502619999738e-05 tokens_per_second_per_gpu:759.1736070810795 +Step 6472 | loss:2.0217461585998535 lr:1.8987427985575344e-05 tokens_per_second_per_gpu:766.1162774172592 +Step 6473 | loss:1.9615017175674438 lr:1.8964365894430548e-05 tokens_per_second_per_gpu:780.0275294808356 +Step 6474 | loss:1.9784106016159058 lr:1.8941316350136097e-05 tokens_per_second_per_gpu:768.9238451960161 +Step 6475 | loss:1.9715721607208252 lr:1.891827935626078e-05 tokens_per_second_per_gpu:779.6628720614322 +Step 6476 | loss:1.9839152097702026 lr:1.8895254916371453e-05 tokens_per_second_per_gpu:779.209573777557 +Step 6477 | loss:2.001281261444092 lr:1.887224303403302e-05 tokens_per_second_per_gpu:751.0061504436112 +Step 6478 | loss:2.0352790355682373 lr:1.884924371280846e-05 tokens_per_second_per_gpu:783.8146077590807 +Step 6479 | loss:1.9836214780807495 lr:1.8826256956258716e-05 tokens_per_second_per_gpu:758.8792389595878 +Step 6480 | loss:2.0173420906066895 lr:1.8803282767942954e-05 tokens_per_second_per_gpu:785.1087993361945 +Step 6481 | loss:1.9967460632324219 lr:1.8780321151418223e-05 tokens_per_second_per_gpu:763.2629301503962 +Step 6482 | loss:2.055388927459717 lr:1.8757372110239723e-05 tokens_per_second_per_gpu:735.7285082119203 +Step 6483 | loss:2.0162124633789062 lr:1.873443564796068e-05 tokens_per_second_per_gpu:776.4265874833053 +Step 6484 | loss:1.9997565746307373 lr:1.8711511768132383e-05 tokens_per_second_per_gpu:772.0219602743456 +Step 6485 | loss:1.9640204906463623 lr:1.8688600474304162e-05 tokens_per_second_per_gpu:751.64621528117 +Step 6486 | loss:2.019061326980591 lr:1.86657017700234e-05 tokens_per_second_per_gpu:783.0208850252787 +Step 6487 | loss:2.0112452507019043 lr:1.8642815658835557e-05 tokens_per_second_per_gpu:774.1778682490415 +Step 6488 | loss:1.9287651777267456 lr:1.8619942144284076e-05 tokens_per_second_per_gpu:789.7951201971454 +Step 6489 | loss:2.0401551723480225 lr:1.8597081229910505e-05 tokens_per_second_per_gpu:788.9328476617658 +Step 6490 | loss:1.990748405456543 lr:1.8574232919254453e-05 tokens_per_second_per_gpu:749.72402067061 +Step 6491 | loss:1.9610099792480469 lr:1.8551397215853518e-05 tokens_per_second_per_gpu:789.3759915428608 +Step 6492 | loss:1.9799917936325073 lr:1.8528574123243402e-05 tokens_per_second_per_gpu:768.6565083628662 +Step 6493 | loss:1.9546678066253662 lr:1.8505763644957863e-05 tokens_per_second_per_gpu:769.2515771229631 +Step 6494 | loss:1.9684789180755615 lr:1.8482965784528617e-05 tokens_per_second_per_gpu:789.5104502044962 +Step 6495 | loss:2.0132837295532227 lr:1.8460180545485507e-05 tokens_per_second_per_gpu:770.7597285340152 +Step 6496 | loss:2.031140089035034 lr:1.843740793135641e-05 tokens_per_second_per_gpu:760.863822020659 +Step 6497 | loss:2.0207290649414062 lr:1.841464794566723e-05 tokens_per_second_per_gpu:713.2083710640403 +Step 6498 | loss:2.0264503955841064 lr:1.8391900591941934e-05 tokens_per_second_per_gpu:789.7598300379523 +Step 6499 | loss:2.0263214111328125 lr:1.8369165873702543e-05 tokens_per_second_per_gpu:761.4255925885095 +Step 6500 | loss:2.001732110977173 lr:1.8346443794469025e-05 tokens_per_second_per_gpu:778.3022221154761 +Step 6501 | loss:2.0069632530212402 lr:1.832373435775958e-05 tokens_per_second_per_gpu:772.0448260344319 +Step 6502 | loss:2.008298873901367 lr:1.830103756709025e-05 tokens_per_second_per_gpu:791.4720808765085 +Step 6503 | loss:1.9796948432922363 lr:1.8278353425975237e-05 tokens_per_second_per_gpu:743.6597265823025 +Step 6504 | loss:2.037930488586426 lr:1.8255681937926762e-05 tokens_per_second_per_gpu:770.4782550753872 +Step 6505 | loss:2.0037336349487305 lr:1.8233023106455104e-05 tokens_per_second_per_gpu:779.593257485167 +Step 6506 | loss:2.0364644527435303 lr:1.8210376935068475e-05 tokens_per_second_per_gpu:775.1531864088204 +Step 6507 | loss:2.0527539253234863 lr:1.818774342727332e-05 tokens_per_second_per_gpu:790.3144591949945 +Step 6508 | loss:2.010526657104492 lr:1.8165122586573924e-05 tokens_per_second_per_gpu:750.8214354338431 +Step 6509 | loss:1.9784495830535889 lr:1.8142514416472744e-05 tokens_per_second_per_gpu:769.9490543056719 +Step 6510 | loss:2.005824089050293 lr:1.8119918920470224e-05 tokens_per_second_per_gpu:796.2196765996753 +Step 6511 | loss:2.01316499710083 lr:1.8097336102064853e-05 tokens_per_second_per_gpu:741.443015072561 +Step 6512 | loss:2.0275719165802 lr:1.807476596475316e-05 tokens_per_second_per_gpu:748.1761340029916 +Step 6513 | loss:1.9792524576187134 lr:1.80522085120297e-05 tokens_per_second_per_gpu:777.8109864883647 +Step 6514 | loss:2.0307273864746094 lr:1.8029663747387104e-05 tokens_per_second_per_gpu:790.5446365509048 +Step 6515 | loss:2.0336811542510986 lr:1.8007131674315957e-05 tokens_per_second_per_gpu:745.7987449727113 +Step 6516 | loss:2.004082679748535 lr:1.798461229630496e-05 tokens_per_second_per_gpu:765.2334622236335 +Step 6517 | loss:1.9896249771118164 lr:1.7962105616840806e-05 tokens_per_second_per_gpu:781.3627845311925 +Step 6518 | loss:2.015995502471924 lr:1.7939611639408228e-05 tokens_per_second_per_gpu:761.5293823439835 +Step 6519 | loss:1.9864425659179688 lr:1.7917130367490008e-05 tokens_per_second_per_gpu:788.706277808756 +Step 6520 | loss:2.0155365467071533 lr:1.789466180456698e-05 tokens_per_second_per_gpu:789.4281401515764 +Step 6521 | loss:2.0171477794647217 lr:1.7872205954117917e-05 tokens_per_second_per_gpu:762.6927807509794 +Step 6522 | loss:1.9507503509521484 lr:1.784976281961972e-05 tokens_per_second_per_gpu:782.9226793281796 +Step 6523 | loss:1.9846848249435425 lr:1.782733240454728e-05 tokens_per_second_per_gpu:758.6669555458863 +Step 6524 | loss:1.9877171516418457 lr:1.7804914712373534e-05 tokens_per_second_per_gpu:770.5230516234117 +Step 6525 | loss:2.028430700302124 lr:1.778250974656944e-05 tokens_per_second_per_gpu:759.3604358178458 +Step 6526 | loss:2.0209720134735107 lr:1.7760117510604013e-05 tokens_per_second_per_gpu:744.68751049724 +Step 6527 | loss:2.031010866165161 lr:1.7737738007944195e-05 tokens_per_second_per_gpu:758.2811270339956 +Step 6528 | loss:2.038806676864624 lr:1.7715371242055135e-05 tokens_per_second_per_gpu:747.3853117180186 +Step 6529 | loss:1.977381706237793 lr:1.769301721639982e-05 tokens_per_second_per_gpu:759.3009134968906 +Step 6530 | loss:1.9944078922271729 lr:1.7670675934439407e-05 tokens_per_second_per_gpu:777.8005843026613 +Step 6531 | loss:1.9898680448532104 lr:1.764834739963299e-05 tokens_per_second_per_gpu:765.4490238308733 +Step 6532 | loss:2.057363510131836 lr:1.7626031615437777e-05 tokens_per_second_per_gpu:770.5056765966484 +Step 6533 | loss:2.044215679168701 lr:1.7603728585308856e-05 tokens_per_second_per_gpu:780.9515315146167 +Step 6534 | loss:1.9971966743469238 lr:1.758143831269955e-05 tokens_per_second_per_gpu:785.6767105955579 +Step 6535 | loss:2.0171196460723877 lr:1.7559160801061003e-05 tokens_per_second_per_gpu:792.7145331891801 +Step 6536 | loss:1.9547464847564697 lr:1.753689605384249e-05 tokens_per_second_per_gpu:757.4383369801243 +Step 6537 | loss:1.9404468536376953 lr:1.7514644074491303e-05 tokens_per_second_per_gpu:783.1523175550682 +Step 6538 | loss:1.9883370399475098 lr:1.749240486645275e-05 tokens_per_second_per_gpu:783.8163926867079 +Step 6539 | loss:1.9857292175292969 lr:1.7470178433170136e-05 tokens_per_second_per_gpu:777.8062624418463 +Step 6540 | loss:2.0437283515930176 lr:1.7447964778084826e-05 tokens_per_second_per_gpu:783.5391541767082 +Step 6541 | loss:2.011854887008667 lr:1.7425763904636196e-05 tokens_per_second_per_gpu:760.498704102399 +Step 6542 | loss:2.019599676132202 lr:1.7403575816261598e-05 tokens_per_second_per_gpu:765.4190375531069 +Step 6543 | loss:1.9820125102996826 lr:1.738140051639646e-05 tokens_per_second_per_gpu:790.8027012504724 +Step 6544 | loss:1.9540705680847168 lr:1.735923800847422e-05 tokens_per_second_per_gpu:769.0318696848562 +Step 6545 | loss:1.9727418422698975 lr:1.733708829592633e-05 tokens_per_second_per_gpu:754.3944754093504 +Step 6546 | loss:1.9473645687103271 lr:1.7314951382182244e-05 tokens_per_second_per_gpu:754.1412934191329 +Step 6547 | loss:1.9975991249084473 lr:1.7292827270669475e-05 tokens_per_second_per_gpu:776.8084094721975 +Step 6548 | loss:2.0238170623779297 lr:1.727071596481349e-05 tokens_per_second_per_gpu:771.4856705096288 +Step 6549 | loss:2.021209478378296 lr:1.7248617468037832e-05 tokens_per_second_per_gpu:783.8217625126068 +Step 6550 | loss:2.020745277404785 lr:1.722653178376403e-05 tokens_per_second_per_gpu:765.9532438189073 +Step 6551 | loss:2.0610525608062744 lr:1.7204458915411646e-05 tokens_per_second_per_gpu:762.5436943654104 +Step 6552 | loss:2.0553488731384277 lr:1.7182398866398253e-05 tokens_per_second_per_gpu:728.122677414284 +Step 6553 | loss:2.019972085952759 lr:1.716035164013945e-05 tokens_per_second_per_gpu:772.6055070689699 +Step 6554 | loss:2.007328510284424 lr:1.7138317240048773e-05 tokens_per_second_per_gpu:769.1717958954623 +Step 6555 | loss:1.9869029521942139 lr:1.711629566953793e-05 tokens_per_second_per_gpu:758.1574699197963 +Step 6556 | loss:2.0312557220458984 lr:1.709428693201649e-05 tokens_per_second_per_gpu:749.6975030017402 +Step 6557 | loss:1.9921200275421143 lr:1.7072291030892086e-05 tokens_per_second_per_gpu:793.3793402057071 +Step 6558 | loss:1.9641540050506592 lr:1.70503079695704e-05 tokens_per_second_per_gpu:775.7416510326882 +Step 6559 | loss:2.0489914417266846 lr:1.7028337751455093e-05 tokens_per_second_per_gpu:769.7946274153452 +Step 6560 | loss:1.9984811544418335 lr:1.700638037994783e-05 tokens_per_second_per_gpu:789.3373180827201 +Step 6561 | loss:2.0178117752075195 lr:1.6984435858448334e-05 tokens_per_second_per_gpu:782.2968354335121 +Step 6562 | loss:2.0683248043060303 lr:1.6962504190354246e-05 tokens_per_second_per_gpu:779.3311166697789 +Step 6563 | loss:2.0323596000671387 lr:1.6940585379061302e-05 tokens_per_second_per_gpu:766.75843589805 +Step 6564 | loss:2.044671058654785 lr:1.6918679427963224e-05 tokens_per_second_per_gpu:738.1757390760386 +Step 6565 | loss:2.055294990539551 lr:1.6896786340451743e-05 tokens_per_second_per_gpu:779.9242849160015 +Step 6566 | loss:1.9852149486541748 lr:1.6874906119916568e-05 tokens_per_second_per_gpu:757.8102209813948 +Step 6567 | loss:2.018395185470581 lr:1.6853038769745467e-05 tokens_per_second_per_gpu:749.6664731271627 +Step 6568 | loss:1.9748808145523071 lr:1.6831184293324208e-05 tokens_per_second_per_gpu:748.0254663727806 +Step 6569 | loss:2.0180325508117676 lr:1.68093426940365e-05 tokens_per_second_per_gpu:765.0169946891605 +Step 6570 | loss:2.0062408447265625 lr:1.6787513975264114e-05 tokens_per_second_per_gpu:785.9132082280898 +Step 6571 | loss:2.0661165714263916 lr:1.6765698140386843e-05 tokens_per_second_per_gpu:744.7505460954015 +Step 6572 | loss:1.9990211725234985 lr:1.6743895192782443e-05 tokens_per_second_per_gpu:735.6978485464703 +Step 6573 | loss:2.038872718811035 lr:1.6722105135826694e-05 tokens_per_second_per_gpu:760.9792333412225 +Step 6574 | loss:2.0367777347564697 lr:1.6700327972893404e-05 tokens_per_second_per_gpu:746.4106094739287 +Step 6575 | loss:1.993865966796875 lr:1.6678563707354323e-05 tokens_per_second_per_gpu:749.5327660501919 +Step 6576 | loss:1.962436318397522 lr:1.6656812342579242e-05 tokens_per_second_per_gpu:771.832544403139 +Step 6577 | loss:2.028043270111084 lr:1.663507388193597e-05 tokens_per_second_per_gpu:795.4599318640263 +Step 6578 | loss:2.0753631591796875 lr:1.661334832879029e-05 tokens_per_second_per_gpu:793.4280991121501 +Step 6579 | loss:1.9913055896759033 lr:1.6591635686506002e-05 tokens_per_second_per_gpu:769.2335233083105 +Step 6580 | loss:1.9441587924957275 lr:1.6569935958444927e-05 tokens_per_second_per_gpu:766.532351197006 +Step 6581 | loss:1.9984015226364136 lr:1.654824914796679e-05 tokens_per_second_per_gpu:782.0646343315932 +Step 6582 | loss:2.054171085357666 lr:1.6526575258429478e-05 tokens_per_second_per_gpu:774.8781247579503 +Step 6583 | loss:1.998415231704712 lr:1.6504914293188722e-05 tokens_per_second_per_gpu:799.0229393103597 +Step 6584 | loss:2.055879831314087 lr:1.648326625559834e-05 tokens_per_second_per_gpu:769.8115547077922 +Step 6585 | loss:1.9646921157836914 lr:1.6461631149010114e-05 tokens_per_second_per_gpu:769.470553484837 +Step 6586 | loss:2.026059865951538 lr:1.6440008976773845e-05 tokens_per_second_per_gpu:778.5362318980124 +Step 6587 | loss:2.0272417068481445 lr:1.6418399742237322e-05 tokens_per_second_per_gpu:764.9788375853766 +Step 6588 | loss:2.035151243209839 lr:1.6396803448746346e-05 tokens_per_second_per_gpu:777.2654906781312 +Step 6589 | loss:2.0108413696289062 lr:1.637522009964466e-05 tokens_per_second_per_gpu:777.1050410376628 +Step 6590 | loss:1.9850413799285889 lr:1.6353649698274066e-05 tokens_per_second_per_gpu:759.2345373030726 +Step 6591 | loss:1.9545044898986816 lr:1.633209224797433e-05 tokens_per_second_per_gpu:779.8931440481161 +Step 6592 | loss:2.10522198677063 lr:1.6310547752083228e-05 tokens_per_second_per_gpu:761.5518929205278 +Step 6593 | loss:1.9827415943145752 lr:1.6289016213936504e-05 tokens_per_second_per_gpu:763.9275105460355 +Step 6594 | loss:2.0862646102905273 lr:1.6267497636867957e-05 tokens_per_second_per_gpu:785.9672231108426 +Step 6595 | loss:2.0267162322998047 lr:1.6245992024209277e-05 tokens_per_second_per_gpu:771.2042762271001 +Step 6596 | loss:2.0196423530578613 lr:1.6224499379290238e-05 tokens_per_second_per_gpu:737.1683595818416 +Step 6597 | loss:1.9690728187561035 lr:1.6203019705438562e-05 tokens_per_second_per_gpu:791.534064265011 +Step 6598 | loss:1.9766145944595337 lr:1.6181553005979987e-05 tokens_per_second_per_gpu:779.9268755235747 +Step 6599 | loss:1.9909147024154663 lr:1.6160099284238218e-05 tokens_per_second_per_gpu:783.074887272903 +Step 6600 | loss:2.0222229957580566 lr:1.6138658543534968e-05 tokens_per_second_per_gpu:782.0946094782482 +Step 6601 | loss:2.0322680473327637 lr:1.6117230787189952e-05 tokens_per_second_per_gpu:767.4675951338564 +Step 6602 | loss:2.0186848640441895 lr:1.6095816018520792e-05 tokens_per_second_per_gpu:789.6428480179651 +Step 6603 | loss:2.027749538421631 lr:1.607441424084326e-05 tokens_per_second_per_gpu:770.538049357828 +Step 6604 | loss:1.9489307403564453 lr:1.605302545747095e-05 tokens_per_second_per_gpu:784.0720499711853 +Step 6605 | loss:1.9820799827575684 lr:1.603164967171552e-05 tokens_per_second_per_gpu:784.0304802034718 +Step 6606 | loss:1.990004301071167 lr:1.601028688688664e-05 tokens_per_second_per_gpu:782.1381030925197 +Step 6607 | loss:2.003615379333496 lr:1.5988937106291935e-05 tokens_per_second_per_gpu:795.6523301208263 +Step 6608 | loss:1.9934526681900024 lr:1.5967600333236964e-05 tokens_per_second_per_gpu:782.2760261417716 +Step 6609 | loss:1.9776493310928345 lr:1.594627657102541e-05 tokens_per_second_per_gpu:770.6816425576278 +Step 6610 | loss:2.0153188705444336 lr:1.5924965822958802e-05 tokens_per_second_per_gpu:760.6302428726227 +Step 6611 | loss:2.023785352706909 lr:1.5903668092336722e-05 tokens_per_second_per_gpu:747.0796113331268 +Step 6612 | loss:2.012352228164673 lr:1.5882383382456723e-05 tokens_per_second_per_gpu:747.2091652401554 +Step 6613 | loss:1.9375487565994263 lr:1.586111169661435e-05 tokens_per_second_per_gpu:752.2897893506964 +Step 6614 | loss:1.9910881519317627 lr:1.5839853038103125e-05 tokens_per_second_per_gpu:764.4324293504045 +Step 6615 | loss:1.981395959854126 lr:1.581860741021457e-05 tokens_per_second_per_gpu:795.4001460418662 +Step 6616 | loss:1.9722338914871216 lr:1.579737481623813e-05 tokens_per_second_per_gpu:774.1918112297583 +Step 6617 | loss:1.9534647464752197 lr:1.57761552594613e-05 tokens_per_second_per_gpu:789.1000714246093 +Step 6618 | loss:2.019439697265625 lr:1.575494874316954e-05 tokens_per_second_per_gpu:769.2543710867641 +Step 6619 | loss:2.0150229930877686 lr:1.5733755270646256e-05 tokens_per_second_per_gpu:770.8962364752825 +Step 6620 | loss:2.005812168121338 lr:1.5712574845172888e-05 tokens_per_second_per_gpu:786.2178577666701 +Step 6621 | loss:1.9794843196868896 lr:1.569140747002883e-05 tokens_per_second_per_gpu:728.4806109586466 +Step 6622 | loss:1.9994972944259644 lr:1.567025314849142e-05 tokens_per_second_per_gpu:767.9281518828658 +Step 6623 | loss:2.0309574604034424 lr:1.5649111883836033e-05 tokens_per_second_per_gpu:786.8853171821324 +Step 6624 | loss:2.0543017387390137 lr:1.562798367933599e-05 tokens_per_second_per_gpu:790.5927729663438 +Step 6625 | loss:1.9867472648620605 lr:1.5606868538262598e-05 tokens_per_second_per_gpu:791.138280346213 +Step 6626 | loss:2.023887872695923 lr:1.5585766463885155e-05 tokens_per_second_per_gpu:790.2662567490986 +Step 6627 | loss:1.9805423021316528 lr:1.55646774594709e-05 tokens_per_second_per_gpu:775.6814627175686 +Step 6628 | loss:1.9862346649169922 lr:1.5543601528285102e-05 tokens_per_second_per_gpu:776.8353906758794 +Step 6629 | loss:1.9882155656814575 lr:1.5522538673590913e-05 tokens_per_second_per_gpu:751.8673424259363 +Step 6630 | loss:1.9860105514526367 lr:1.5501488898649608e-05 tokens_per_second_per_gpu:788.2094574879891 +Step 6631 | loss:1.9923341274261475 lr:1.5480452206720285e-05 tokens_per_second_per_gpu:778.6605259287045 +Step 6632 | loss:2.0174405574798584 lr:1.54594286010601e-05 tokens_per_second_per_gpu:765.2341487032512 +Step 6633 | loss:2.015913248062134 lr:1.5438418084924154e-05 tokens_per_second_per_gpu:757.9832179125029 +Step 6634 | loss:1.9807969331741333 lr:1.5417420661565584e-05 tokens_per_second_per_gpu:743.6500510389832 +Step 6635 | loss:1.9470555782318115 lr:1.5396436334235354e-05 tokens_per_second_per_gpu:755.8384039421373 +Step 6636 | loss:2.0072240829467773 lr:1.5375465106182596e-05 tokens_per_second_per_gpu:745.9607425718838 +Step 6637 | loss:2.0368001461029053 lr:1.5354506980654238e-05 tokens_per_second_per_gpu:765.6546607369107 +Step 6638 | loss:2.022052764892578 lr:1.5333561960895282e-05 tokens_per_second_per_gpu:762.8290055392199 +Step 6639 | loss:1.9919036626815796 lr:1.531263005014867e-05 tokens_per_second_per_gpu:767.1060143246852 +Step 6640 | loss:1.9635212421417236 lr:1.5291711251655316e-05 tokens_per_second_per_gpu:788.0026480136332 +Step 6641 | loss:1.9633029699325562 lr:1.5270805568654102e-05 tokens_per_second_per_gpu:780.4004833521218 +Step 6642 | loss:1.965606927871704 lr:1.52499130043819e-05 tokens_per_second_per_gpu:794.8702535830568 +Step 6643 | loss:2.068732738494873 lr:1.5229033562073503e-05 tokens_per_second_per_gpu:769.8650731574918 +Step 6644 | loss:2.048773765563965 lr:1.5208167244961712e-05 tokens_per_second_per_gpu:789.639108191435 +Step 6645 | loss:2.0072505474090576 lr:1.518731405627728e-05 tokens_per_second_per_gpu:782.8472757798174 +Step 6646 | loss:1.9801726341247559 lr:1.5166473999248953e-05 tokens_per_second_per_gpu:745.8143122167669 +Step 6647 | loss:1.933821201324463 lr:1.5145647077103398e-05 tokens_per_second_per_gpu:750.938508281436 +Step 6648 | loss:2.078313112258911 lr:1.512483329306532e-05 tokens_per_second_per_gpu:788.0323673049968 +Step 6649 | loss:2.0189199447631836 lr:1.5104032650357281e-05 tokens_per_second_per_gpu:739.9197977416541 +Step 6650 | loss:2.017225742340088 lr:1.5083245152199899e-05 tokens_per_second_per_gpu:767.4751048769243 +Step 6651 | loss:2.04742169380188 lr:1.5062470801811735e-05 tokens_per_second_per_gpu:795.6797338799327 +Step 6652 | loss:2.039809226989746 lr:1.5041709602409303e-05 tokens_per_second_per_gpu:767.2069394354886 +Step 6653 | loss:2.014815092086792 lr:1.5020961557207091e-05 tokens_per_second_per_gpu:777.8116420233513 +Step 6654 | loss:1.9764491319656372 lr:1.5000226669417528e-05 tokens_per_second_per_gpu:796.8388257783839 +Step 6655 | loss:2.034956216812134 lr:1.4979504942251065e-05 tokens_per_second_per_gpu:758.5970672788069 +Step 6656 | loss:2.0163426399230957 lr:1.4958796378916007e-05 tokens_per_second_per_gpu:757.0539764437151 +Step 6657 | loss:1.9945437908172607 lr:1.4938100982618763e-05 tokens_per_second_per_gpu:752.6448508970997 +Step 6658 | loss:2.0032777786254883 lr:1.4917418756563562e-05 tokens_per_second_per_gpu:758.6352684275635 +Step 6659 | loss:1.9735015630722046 lr:1.4896749703952684e-05 tokens_per_second_per_gpu:781.3589074278948 +Step 6660 | loss:1.9862043857574463 lr:1.487609382798636e-05 tokens_per_second_per_gpu:762.1633246244063 +Step 6661 | loss:2.030426502227783 lr:1.4855451131862741e-05 tokens_per_second_per_gpu:751.8231699380223 +Step 6662 | loss:1.9789952039718628 lr:1.4834821618777973e-05 tokens_per_second_per_gpu:748.5972302461329 +Step 6663 | loss:1.9883131980895996 lr:1.4814205291926175e-05 tokens_per_second_per_gpu:773.8385025988965 +Step 6664 | loss:1.9603757858276367 lr:1.4793602154499352e-05 tokens_per_second_per_gpu:727.2830772625849 +Step 6665 | loss:1.9484730958938599 lr:1.4773012209687543e-05 tokens_per_second_per_gpu:778.1208441672886 +Step 6666 | loss:2.042752742767334 lr:1.4752435460678705e-05 tokens_per_second_per_gpu:784.8145895506976 +Step 6667 | loss:2.0200746059417725 lr:1.4731871910658756e-05 tokens_per_second_per_gpu:805.7363544724761 +Step 6668 | loss:2.0218923091888428 lr:1.4711321562811597e-05 tokens_per_second_per_gpu:762.311843620354 +Step 6669 | loss:1.9413847923278809 lr:1.469078442031907e-05 tokens_per_second_per_gpu:756.6092369668339 +Step 6670 | loss:2.02024507522583 lr:1.4670260486360931e-05 tokens_per_second_per_gpu:774.7486507618596 +Step 6671 | loss:1.9866856336593628 lr:1.4649749764114951e-05 tokens_per_second_per_gpu:765.7162328123137 +Step 6672 | loss:2.0175371170043945 lr:1.4629252256756821e-05 tokens_per_second_per_gpu:801.725323548382 +Step 6673 | loss:1.9841121435165405 lr:1.4608767967460202e-05 tokens_per_second_per_gpu:778.4435066995674 +Step 6674 | loss:2.014345169067383 lr:1.4588296899396703e-05 tokens_per_second_per_gpu:780.6243825950556 +Step 6675 | loss:2.0700201988220215 lr:1.456783905573591e-05 tokens_per_second_per_gpu:764.3468042833437 +Step 6676 | loss:2.019559144973755 lr:1.454739443964529e-05 tokens_per_second_per_gpu:785.6721144511358 +Step 6677 | loss:2.004288911819458 lr:1.452696305429031e-05 tokens_per_second_per_gpu:782.8095116868083 +Step 6678 | loss:2.045473098754883 lr:1.450654490283445e-05 tokens_per_second_per_gpu:760.3565697200925 +Step 6679 | loss:2.0469117164611816 lr:1.4486139988439008e-05 tokens_per_second_per_gpu:755.1414713226916 +Step 6680 | loss:2.0336625576019287 lr:1.4465748314263339e-05 tokens_per_second_per_gpu:745.0330182202915 +Step 6681 | loss:2.0136168003082275 lr:1.444536988346471e-05 tokens_per_second_per_gpu:774.734778620456 +Step 6682 | loss:1.951150894165039 lr:1.4425004699198341e-05 tokens_per_second_per_gpu:776.0070075559053 +Step 6683 | loss:1.973935842514038 lr:1.4404652764617355e-05 tokens_per_second_per_gpu:759.780878646876 +Step 6684 | loss:2.03387451171875 lr:1.4384314082872952e-05 tokens_per_second_per_gpu:794.7954365645545 +Step 6685 | loss:2.011545419692993 lr:1.4363988657114124e-05 tokens_per_second_per_gpu:780.3321307457982 +Step 6686 | loss:1.9896292686462402 lr:1.4343676490487912e-05 tokens_per_second_per_gpu:773.2474725153352 +Step 6687 | loss:2.0195043087005615 lr:1.4323377586139276e-05 tokens_per_second_per_gpu:775.549771829417 +Step 6688 | loss:1.9614686965942383 lr:1.4303091947211101e-05 tokens_per_second_per_gpu:799.0585619164406 +Step 6689 | loss:2.0464632511138916 lr:1.4282819576844264e-05 tokens_per_second_per_gpu:765.2429100672034 +Step 6690 | loss:2.021003007888794 lr:1.4262560478177567e-05 tokens_per_second_per_gpu:765.631679279444 +Step 6691 | loss:2.056602716445923 lr:1.424231465434771e-05 tokens_per_second_per_gpu:777.741701903685 +Step 6692 | loss:2.0052528381347656 lr:1.422208210848941e-05 tokens_per_second_per_gpu:769.0682205700451 +Step 6693 | loss:2.0046329498291016 lr:1.4201862843735292e-05 tokens_per_second_per_gpu:788.3526372199659 +Step 6694 | loss:1.9831271171569824 lr:1.4181656863215932e-05 tokens_per_second_per_gpu:783.2958206110081 +Step 6695 | loss:1.9794137477874756 lr:1.4161464170059846e-05 tokens_per_second_per_gpu:769.7479068060562 +Step 6696 | loss:2.099452495574951 lr:1.4141284767393526e-05 tokens_per_second_per_gpu:746.5935462676294 +Step 6697 | loss:2.054914712905884 lr:1.4121118658341315e-05 tokens_per_second_per_gpu:775.1158476262455 +Step 6698 | loss:2.0229134559631348 lr:1.4100965846025581e-05 tokens_per_second_per_gpu:771.134461246766 +Step 6699 | loss:2.0478007793426514 lr:1.4080826333566621e-05 tokens_per_second_per_gpu:782.3811030978679 +Step 6700 | loss:1.961928129196167 lr:1.406070012408266e-05 tokens_per_second_per_gpu:783.8424601085 +Step 6701 | loss:2.0112032890319824 lr:1.404058722068986e-05 tokens_per_second_per_gpu:750.5415458833584 +Step 6702 | loss:2.035953998565674 lr:1.4020487626502343e-05 tokens_per_second_per_gpu:772.7290457515717 +Step 6703 | loss:2.02961802482605 lr:1.4000401344632119e-05 tokens_per_second_per_gpu:764.0838294796278 +Step 6704 | loss:1.9981529712677002 lr:1.3980328378189178e-05 tokens_per_second_per_gpu:763.9454261898833 +Step 6705 | loss:2.0297815799713135 lr:1.396026873028149e-05 tokens_per_second_per_gpu:792.4768914846767 +Step 6706 | loss:2.0184786319732666 lr:1.3940222404014869e-05 tokens_per_second_per_gpu:781.3976416740979 +Step 6707 | loss:1.994747519493103 lr:1.3920189402493134e-05 tokens_per_second_per_gpu:770.20634637911 +Step 6708 | loss:2.0053820610046387 lr:1.3900169728818002e-05 tokens_per_second_per_gpu:782.9473018795458 +Step 6709 | loss:2.0014514923095703 lr:1.3880163386089185e-05 tokens_per_second_per_gpu:779.1305272927927 +Step 6710 | loss:2.1016082763671875 lr:1.3860170377404213e-05 tokens_per_second_per_gpu:745.5799807023008 +Step 6711 | loss:2.034250497817993 lr:1.3840190705858724e-05 tokens_per_second_per_gpu:782.7051813613334 +Step 6712 | loss:1.9675246477127075 lr:1.3820224374546132e-05 tokens_per_second_per_gpu:760.3966580653135 +Step 6713 | loss:2.0083870887756348 lr:1.3800271386557873e-05 tokens_per_second_per_gpu:764.9163584595152 +Step 6714 | loss:2.06406569480896 lr:1.3780331744983277e-05 tokens_per_second_per_gpu:757.0682353773484 +Step 6715 | loss:1.9705209732055664 lr:1.376040545290963e-05 tokens_per_second_per_gpu:771.5900816714259 +Step 6716 | loss:1.9399715662002563 lr:1.3740492513422165e-05 tokens_per_second_per_gpu:795.969454769141 +Step 6717 | loss:2.012096881866455 lr:1.3720592929604026e-05 tokens_per_second_per_gpu:755.4988942062822 +Step 6718 | loss:2.1049065589904785 lr:1.370070670453626e-05 tokens_per_second_per_gpu:792.7346955665836 +Step 6719 | loss:1.99855375289917 lr:1.368083384129789e-05 tokens_per_second_per_gpu:764.2752542112582 +Step 6720 | loss:2.0009732246398926 lr:1.366097434296587e-05 tokens_per_second_per_gpu:767.7289037912711 +Step 6721 | loss:2.0054385662078857 lr:1.364112821261505e-05 tokens_per_second_per_gpu:766.4564203120818 +Step 6722 | loss:2.0666255950927734 lr:1.362129545331825e-05 tokens_per_second_per_gpu:782.3075210591854 +Step 6723 | loss:2.0918731689453125 lr:1.3601476068146224e-05 tokens_per_second_per_gpu:789.5891555474028 +Step 6724 | loss:2.007601499557495 lr:1.3581670060167573e-05 tokens_per_second_per_gpu:792.7265608115372 +Step 6725 | loss:2.0309934616088867 lr:1.3561877432448922e-05 tokens_per_second_per_gpu:778.1524965045805 +Step 6726 | loss:2.0163872241973877 lr:1.3542098188054785e-05 tokens_per_second_per_gpu:783.4310464237741 +Step 6727 | loss:2.0103836059570312 lr:1.3522332330047604e-05 tokens_per_second_per_gpu:771.7591584227998 +Step 6728 | loss:1.9948580265045166 lr:1.3502579861487764e-05 tokens_per_second_per_gpu:758.4765551904067 +Step 6729 | loss:2.034099578857422 lr:1.3482840785433559e-05 tokens_per_second_per_gpu:768.7619484465339 +Step 6730 | loss:2.0527493953704834 lr:1.3463115104941205e-05 tokens_per_second_per_gpu:773.2128748337902 +Step 6731 | loss:2.000209331512451 lr:1.3443402823064832e-05 tokens_per_second_per_gpu:783.2078765443448 +Step 6732 | loss:2.0085389614105225 lr:1.3423703942856592e-05 tokens_per_second_per_gpu:769.3505343576253 +Step 6733 | loss:1.9980018138885498 lr:1.340401846736643e-05 tokens_per_second_per_gpu:707.4201474966189 +Step 6734 | loss:2.0019075870513916 lr:1.3384346399642278e-05 tokens_per_second_per_gpu:770.4575798658046 +Step 6735 | loss:1.9833236932754517 lr:1.3364687742729986e-05 tokens_per_second_per_gpu:770.1929014020596 +Step 6736 | loss:1.9788299798965454 lr:1.3345042499673377e-05 tokens_per_second_per_gpu:796.0021042367267 +Step 6737 | loss:2.074328899383545 lr:1.332541067351406e-05 tokens_per_second_per_gpu:768.045918726265 +Step 6738 | loss:1.9568572044372559 lr:1.3305792267291738e-05 tokens_per_second_per_gpu:785.5998156539658 +Step 6739 | loss:1.9434821605682373 lr:1.3286187284043916e-05 tokens_per_second_per_gpu:731.443411117314 +Step 6740 | loss:1.968727469444275 lr:1.3266595726806052e-05 tokens_per_second_per_gpu:776.0415565229607 +Step 6741 | loss:1.9042472839355469 lr:1.3247017598611543e-05 tokens_per_second_per_gpu:778.2711694270581 +Step 6742 | loss:2.0150413513183594 lr:1.322745290249171e-05 tokens_per_second_per_gpu:787.604187138134 +Step 6743 | loss:1.9809082746505737 lr:1.3207901641475751e-05 tokens_per_second_per_gpu:786.9150364337665 +Step 6744 | loss:2.0660524368286133 lr:1.3188363818590854e-05 tokens_per_second_per_gpu:768.7525329229087 +Step 6745 | loss:2.0424392223358154 lr:1.3168839436862045e-05 tokens_per_second_per_gpu:776.1518806057794 +Step 6746 | loss:1.9878928661346436 lr:1.3149328499312308e-05 tokens_per_second_per_gpu:789.138097416915 +Step 6747 | loss:1.98175048828125 lr:1.3129831008962568e-05 tokens_per_second_per_gpu:722.0861881565511 +Step 6748 | loss:2.0472779273986816 lr:1.3110346968831643e-05 tokens_per_second_per_gpu:770.3173929281224 +Step 6749 | loss:2.0093865394592285 lr:1.3090876381936268e-05 tokens_per_second_per_gpu:783.8299029255717 +Step 6750 | loss:1.9611032009124756 lr:1.3071419251291106e-05 tokens_per_second_per_gpu:784.3869538591962 +Step 6751 | loss:2.013211965560913 lr:1.3051975579908715e-05 tokens_per_second_per_gpu:760.3970824054143 +Step 6752 | loss:2.012031078338623 lr:1.3032545370799587e-05 tokens_per_second_per_gpu:787.8143747217317 +Step 6753 | loss:2.058259963989258 lr:1.3013128626972126e-05 tokens_per_second_per_gpu:784.705920423501 +Step 6754 | loss:2.0086536407470703 lr:1.299372535143265e-05 tokens_per_second_per_gpu:773.7821218764097 +Step 6755 | loss:1.9450494050979614 lr:1.2974335547185401e-05 tokens_per_second_per_gpu:773.7661184110872 +Step 6756 | loss:1.9995572566986084 lr:1.2954959217232543e-05 tokens_per_second_per_gpu:770.2118647882223 +Step 6757 | loss:1.9836156368255615 lr:1.2935596364574098e-05 tokens_per_second_per_gpu:759.1255191459308 +Step 6758 | loss:2.0340819358825684 lr:1.2916246992208036e-05 tokens_per_second_per_gpu:781.4992238655703 +Step 6759 | loss:2.01546049118042 lr:1.2896911103130327e-05 tokens_per_second_per_gpu:782.7978688472684 +Step 6760 | loss:2.0096235275268555 lr:1.2877588700334675e-05 tokens_per_second_per_gpu:778.813583760426 +Step 6761 | loss:2.0318541526794434 lr:1.2858279786812843e-05 tokens_per_second_per_gpu:784.1204112826044 +Step 6762 | loss:1.9927974939346313 lr:1.283898436555444e-05 tokens_per_second_per_gpu:787.340447607475 +Step 6763 | loss:2.0469329357147217 lr:1.2819702439546998e-05 tokens_per_second_per_gpu:775.624710784238 +Step 6764 | loss:2.0065855979919434 lr:1.2800434011775975e-05 tokens_per_second_per_gpu:776.6437646230526 +Step 6765 | loss:2.0490739345550537 lr:1.2781179085224736e-05 tokens_per_second_per_gpu:777.266129666762 +Step 6766 | loss:1.99495267868042 lr:1.2761937662874512e-05 tokens_per_second_per_gpu:777.4031184716365 +Step 6767 | loss:1.9771530628204346 lr:1.2742709747704496e-05 tokens_per_second_per_gpu:775.0403080906448 +Step 6768 | loss:1.9734108448028564 lr:1.272349534269176e-05 tokens_per_second_per_gpu:784.4431121016935 +Step 6769 | loss:1.9773818254470825 lr:1.2704294450811306e-05 tokens_per_second_per_gpu:755.1341316795756 +Step 6770 | loss:2.0433459281921387 lr:1.2685107075036029e-05 tokens_per_second_per_gpu:787.0889296463796 +Step 6771 | loss:1.9840054512023926 lr:1.2665933218336768e-05 tokens_per_second_per_gpu:740.7625802862889 +Step 6772 | loss:1.992041826248169 lr:1.2646772883682168e-05 tokens_per_second_per_gpu:727.4476058952561 +Step 6773 | loss:2.0690534114837646 lr:1.262762607403889e-05 tokens_per_second_per_gpu:768.0099315744228 +Step 6774 | loss:1.9816608428955078 lr:1.260849279237145e-05 tokens_per_second_per_gpu:778.8180865855544 +Step 6775 | loss:2.040370464324951 lr:1.2589373041642272e-05 tokens_per_second_per_gpu:775.594694545778 +Step 6776 | loss:2.016507148742676 lr:1.2570266824811716e-05 tokens_per_second_per_gpu:773.8090981520278 +Step 6777 | loss:1.9868518114089966 lr:1.2551174144838018e-05 tokens_per_second_per_gpu:763.308459909395 +Step 6778 | loss:1.9898831844329834 lr:1.253209500467728e-05 tokens_per_second_per_gpu:737.9783804592764 +Step 6779 | loss:1.9850811958312988 lr:1.2513029407283571e-05 tokens_per_second_per_gpu:767.4153293107713 +Step 6780 | loss:2.0560450553894043 lr:1.2493977355608888e-05 tokens_per_second_per_gpu:777.2696419818603 +Step 6781 | loss:2.057161331176758 lr:1.2474938852603024e-05 tokens_per_second_per_gpu:783.1578962010714 +Step 6782 | loss:2.0549354553222656 lr:1.2455913901213756e-05 tokens_per_second_per_gpu:776.5791193092373 +Step 6783 | loss:2.0148847103118896 lr:1.2436902504386761e-05 tokens_per_second_per_gpu:778.2885489564928 +Step 6784 | loss:1.9798043966293335 lr:1.2417904665065572e-05 tokens_per_second_per_gpu:747.5960717633344 +Step 6785 | loss:1.9840205907821655 lr:1.2398920386191615e-05 tokens_per_second_per_gpu:780.7142414140707 +Step 6786 | loss:2.046009063720703 lr:1.237994967070435e-05 tokens_per_second_per_gpu:783.1264164123755 +Step 6787 | loss:1.9818007946014404 lr:1.2360992521540948e-05 tokens_per_second_per_gpu:774.0914856727255 +Step 6788 | loss:2.03582763671875 lr:1.2342048941636596e-05 tokens_per_second_per_gpu:777.0584062588254 +Step 6789 | loss:1.9593234062194824 lr:1.232311893392436e-05 tokens_per_second_per_gpu:781.6739719357097 +Step 6790 | loss:1.9994219541549683 lr:1.2304202501335183e-05 tokens_per_second_per_gpu:767.4846210017777 +Step 6791 | loss:2.0066819190979004 lr:1.2285299646797943e-05 tokens_per_second_per_gpu:781.4751349085569 +Step 6792 | loss:1.9861189126968384 lr:1.226641037323939e-05 tokens_per_second_per_gpu:774.424212437696 +Step 6793 | loss:1.9629260301589966 lr:1.224753468358415e-05 tokens_per_second_per_gpu:781.9040488449164 +Step 6794 | loss:2.0044798851013184 lr:1.2228672580754775e-05 tokens_per_second_per_gpu:766.5564743983412 +Step 6795 | loss:2.047598123550415 lr:1.2209824067671727e-05 tokens_per_second_per_gpu:775.3465182203973 +Step 6796 | loss:2.0261924266815186 lr:1.219098914725333e-05 tokens_per_second_per_gpu:754.5806067313052 +Step 6797 | loss:1.9971137046813965 lr:1.2172167822415815e-05 tokens_per_second_per_gpu:778.9113730543429 +Step 6798 | loss:1.9761109352111816 lr:1.2153360096073352e-05 tokens_per_second_per_gpu:767.0120478078925 +Step 6799 | loss:1.9622738361358643 lr:1.2134565971137912e-05 tokens_per_second_per_gpu:782.9642195886681 +Step 6800 | loss:1.9665285348892212 lr:1.2115785450519434e-05 tokens_per_second_per_gpu:740.6189776334209 +Step 6801 | loss:1.9949802160263062 lr:1.2097018537125737e-05 tokens_per_second_per_gpu:759.2290865868928 +Step 6802 | loss:1.924048662185669 lr:1.2078265233862517e-05 tokens_per_second_per_gpu:756.1623310936956 +Step 6803 | loss:1.993729829788208 lr:1.2059525543633366e-05 tokens_per_second_per_gpu:790.7576293284391 +Step 6804 | loss:1.973958134651184 lr:1.2040799469339815e-05 tokens_per_second_per_gpu:768.4964934711875 +Step 6805 | loss:1.9856103658676147 lr:1.2022087013881189e-05 tokens_per_second_per_gpu:773.6296960596364 +Step 6806 | loss:2.0204148292541504 lr:1.2003388180154761e-05 tokens_per_second_per_gpu:768.541266779228 +Step 6807 | loss:2.038738250732422 lr:1.1984702971055772e-05 tokens_per_second_per_gpu:747.7254887051967 +Step 6808 | loss:1.9829894304275513 lr:1.1966031389477194e-05 tokens_per_second_per_gpu:775.8821333023652 +Step 6809 | loss:1.9855109453201294 lr:1.1947373438310005e-05 tokens_per_second_per_gpu:777.0997137710882 +Step 6810 | loss:1.9960522651672363 lr:1.1928729120443071e-05 tokens_per_second_per_gpu:769.8988599400124 +Step 6811 | loss:2.005805253982544 lr:1.191009843876305e-05 tokens_per_second_per_gpu:792.9496424913198 +Step 6812 | loss:2.100339412689209 lr:1.1891481396154558e-05 tokens_per_second_per_gpu:762.1698692202224 +Step 6813 | loss:1.9480865001678467 lr:1.1872877995500176e-05 tokens_per_second_per_gpu:784.9995311962999 +Step 6814 | loss:2.019680976867676 lr:1.1854288239680212e-05 tokens_per_second_per_gpu:766.7595908774142 +Step 6815 | loss:1.9922029972076416 lr:1.1835712131572974e-05 tokens_per_second_per_gpu:773.7626178856721 +Step 6816 | loss:1.9896187782287598 lr:1.1817149674054618e-05 tokens_per_second_per_gpu:763.6505365478982 +Step 6817 | loss:1.9953358173370361 lr:1.17986008699992e-05 tokens_per_second_per_gpu:788.6544284513802 +Step 6818 | loss:2.038587808609009 lr:1.1780065722278643e-05 tokens_per_second_per_gpu:788.744587565953 +Step 6819 | loss:2.0676991939544678 lr:1.1761544233762789e-05 tokens_per_second_per_gpu:777.9261288267829 +Step 6820 | loss:1.9345546960830688 lr:1.174303640731932e-05 tokens_per_second_per_gpu:733.5127056533366 +Step 6821 | loss:1.957409143447876 lr:1.172454224581383e-05 tokens_per_second_per_gpu:796.5342579885767 +Step 6822 | loss:2.0101571083068848 lr:1.1706061752109798e-05 tokens_per_second_per_gpu:760.1348552094905 +Step 6823 | loss:1.938889503479004 lr:1.168759492906858e-05 tokens_per_second_per_gpu:753.9414843265049 +Step 6824 | loss:2.0108861923217773 lr:1.166914177954942e-05 tokens_per_second_per_gpu:799.1178487336118 +Step 6825 | loss:2.0249266624450684 lr:1.1650702306409467e-05 tokens_per_second_per_gpu:792.3244618515663 +Step 6826 | loss:2.0025601387023926 lr:1.1632276512503681e-05 tokens_per_second_per_gpu:791.1735789817353 +Step 6827 | loss:1.9871702194213867 lr:1.161386440068497e-05 tokens_per_second_per_gpu:791.7898005642251 +Step 6828 | loss:1.9877136945724487 lr:1.159546597380412e-05 tokens_per_second_per_gpu:792.0984686031746 +Step 6829 | loss:2.018587112426758 lr:1.1577081234709763e-05 tokens_per_second_per_gpu:723.4860943648941 +Step 6830 | loss:2.064424753189087 lr:1.1558710186248444e-05 tokens_per_second_per_gpu:764.6047054766223 +Step 6831 | loss:2.0416135787963867 lr:1.15403528312646e-05 tokens_per_second_per_gpu:767.0734674756407 +Step 6832 | loss:2.015308141708374 lr:1.1522009172600468e-05 tokens_per_second_per_gpu:783.6089338732704 +Step 6833 | loss:1.9578542709350586 lr:1.1503679213096219e-05 tokens_per_second_per_gpu:770.568412716587 +Step 6834 | loss:1.9933444261550903 lr:1.1485362955589984e-05 tokens_per_second_per_gpu:760.2628030932657 +Step 6835 | loss:2.0072312355041504 lr:1.1467060402917618e-05 tokens_per_second_per_gpu:790.8940783128409 +Step 6836 | loss:1.9735171794891357 lr:1.1448771557912952e-05 tokens_per_second_per_gpu:775.780404925137 +Step 6837 | loss:1.9915376901626587 lr:1.1430496423407688e-05 tokens_per_second_per_gpu:786.635178054888 +Step 6838 | loss:2.0654218196868896 lr:1.1412235002231342e-05 tokens_per_second_per_gpu:787.0485925950405 +Step 6839 | loss:2.0362725257873535 lr:1.1393987297211395e-05 tokens_per_second_per_gpu:764.5728353494878 +Step 6840 | loss:2.0367624759674072 lr:1.1375753311173166e-05 tokens_per_second_per_gpu:772.0976869598977 +Step 6841 | loss:1.9872137308120728 lr:1.1357533046939816e-05 tokens_per_second_per_gpu:775.7176810146123 +Step 6842 | loss:1.9796829223632812 lr:1.1339326507332414e-05 tokens_per_second_per_gpu:757.563319235527 +Step 6843 | loss:1.9905946254730225 lr:1.1321133695169927e-05 tokens_per_second_per_gpu:785.1289750879756 +Step 6844 | loss:2.005105972290039 lr:1.1302954613269156e-05 tokens_per_second_per_gpu:784.2942567211016 +Step 6845 | loss:2.0376973152160645 lr:1.1284789264444785e-05 tokens_per_second_per_gpu:775.071317285919 +Step 6846 | loss:1.9452970027923584 lr:1.1266637651509416e-05 tokens_per_second_per_gpu:791.0246422987307 +Step 6847 | loss:2.0058765411376953 lr:1.1248499777273424e-05 tokens_per_second_per_gpu:761.0630077818543 +Step 6848 | loss:2.0364205837249756 lr:1.1230375644545166e-05 tokens_per_second_per_gpu:789.0471465652921 +Step 6849 | loss:1.971888542175293 lr:1.1212265256130793e-05 tokens_per_second_per_gpu:769.1032630762461 +Step 6850 | loss:1.9822381734848022 lr:1.1194168614834389e-05 tokens_per_second_per_gpu:765.8101292193921 +Step 6851 | loss:1.9856181144714355 lr:1.1176085723457862e-05 tokens_per_second_per_gpu:784.0208765211447 +Step 6852 | loss:2.0044138431549072 lr:1.1158016584801045e-05 tokens_per_second_per_gpu:795.5834331077381 +Step 6853 | loss:2.0173420906066895 lr:1.1139961201661541e-05 tokens_per_second_per_gpu:782.3586491695694 +Step 6854 | loss:1.9710520505905151 lr:1.1121919576834927e-05 tokens_per_second_per_gpu:773.4843804395035 +Step 6855 | loss:2.0418431758880615 lr:1.1103891713114612e-05 tokens_per_second_per_gpu:761.5832346269295 +Step 6856 | loss:2.024958848953247 lr:1.1085877613291861e-05 tokens_per_second_per_gpu:792.5977593615895 +Step 6857 | loss:1.9691267013549805 lr:1.1067877280155836e-05 tokens_per_second_per_gpu:771.8881591093359 +Step 6858 | loss:2.061739444732666 lr:1.1049890716493549e-05 tokens_per_second_per_gpu:789.3038666532165 +Step 6859 | loss:2.0537548065185547 lr:1.1031917925089862e-05 tokens_per_second_per_gpu:765.3018762698398 +Step 6860 | loss:2.002080202102661 lr:1.1013958908727517e-05 tokens_per_second_per_gpu:762.9710715064904 +Step 6861 | loss:1.9778882265090942 lr:1.099601367018719e-05 tokens_per_second_per_gpu:753.2402692409399 +Step 6862 | loss:2.006582260131836 lr:1.0978082212247308e-05 tokens_per_second_per_gpu:777.286453510076 +Step 6863 | loss:1.954000473022461 lr:1.0960164537684247e-05 tokens_per_second_per_gpu:763.6021630942688 +Step 6864 | loss:2.016036033630371 lr:1.0942260649272229e-05 tokens_per_second_per_gpu:793.8608858432101 +Step 6865 | loss:1.9975448846817017 lr:1.0924370549783292e-05 tokens_per_second_per_gpu:799.1393099931469 +Step 6866 | loss:2.0200512409210205 lr:1.090649424198743e-05 tokens_per_second_per_gpu:781.2804127065972 +Step 6867 | loss:1.9989668130874634 lr:1.0888631728652465e-05 tokens_per_second_per_gpu:776.164988108095 +Step 6868 | loss:2.040652275085449 lr:1.0870783012544027e-05 tokens_per_second_per_gpu:765.3286800576809 +Step 6869 | loss:1.97214674949646 lr:1.0852948096425675e-05 tokens_per_second_per_gpu:779.757835819741 +Step 6870 | loss:1.9998540878295898 lr:1.0835126983058829e-05 tokens_per_second_per_gpu:770.1713612253017 +Step 6871 | loss:2.0310401916503906 lr:1.0817319675202698e-05 tokens_per_second_per_gpu:777.2760911505558 +Step 6872 | loss:2.024739980697632 lr:1.0799526175614472e-05 tokens_per_second_per_gpu:782.780633610049 +Step 6873 | loss:1.9907848834991455 lr:1.0781746487049138e-05 tokens_per_second_per_gpu:774.2047307183725 +Step 6874 | loss:1.9447741508483887 lr:1.0763980612259517e-05 tokens_per_second_per_gpu:758.2983424744973 +Step 6875 | loss:2.0195395946502686 lr:1.074622855399633e-05 tokens_per_second_per_gpu:790.2840031492037 +Step 6876 | loss:2.08754563331604 lr:1.0728490315008155e-05 tokens_per_second_per_gpu:771.4968890597827 +Step 6877 | loss:1.9732697010040283 lr:1.0710765898041419e-05 tokens_per_second_per_gpu:751.3347984607191 +Step 6878 | loss:1.997190237045288 lr:1.0693055305840439e-05 tokens_per_second_per_gpu:735.7113933036596 +Step 6879 | loss:2.033860206604004 lr:1.0675358541147362e-05 tokens_per_second_per_gpu:767.0443878033807 +Step 6880 | loss:2.0328755378723145 lr:1.0657675606702166e-05 tokens_per_second_per_gpu:781.0331550149475 +Step 6881 | loss:1.962654948234558 lr:1.0640006505242738e-05 tokens_per_second_per_gpu:779.7224037147076 +Step 6882 | loss:1.9296938180923462 lr:1.0622351239504857e-05 tokens_per_second_per_gpu:780.0221767341793 +Step 6883 | loss:1.967712163925171 lr:1.0604709812222046e-05 tokens_per_second_per_gpu:759.3062801184233 +Step 6884 | loss:2.0359911918640137 lr:1.0587082226125777e-05 tokens_per_second_per_gpu:742.9912340291756 +Step 6885 | loss:2.02123761177063 lr:1.0569468483945366e-05 tokens_per_second_per_gpu:763.4582632342191 +Step 6886 | loss:2.036902666091919 lr:1.055186858840793e-05 tokens_per_second_per_gpu:783.4345797853679 +Step 6887 | loss:2.075212240219116 lr:1.0534282542238494e-05 tokens_per_second_per_gpu:779.0403139890141 +Step 6888 | loss:2.0042312145233154 lr:1.0516710348159985e-05 tokens_per_second_per_gpu:775.1981927026161 +Step 6889 | loss:2.0645906925201416 lr:1.0499152008893055e-05 tokens_per_second_per_gpu:757.4146236604754 +Step 6890 | loss:2.0153183937072754 lr:1.0481607527156324e-05 tokens_per_second_per_gpu:763.614891972736 +Step 6891 | loss:2.0048656463623047 lr:1.0464076905666221e-05 tokens_per_second_per_gpu:757.9394235281753 +Step 6892 | loss:1.964820384979248 lr:1.0446560147136997e-05 tokens_per_second_per_gpu:797.757624803176 +Step 6893 | loss:2.010019063949585 lr:1.042905725428085e-05 tokens_per_second_per_gpu:778.3489307456629 +Step 6894 | loss:1.9893832206726074 lr:1.0411568229807756e-05 tokens_per_second_per_gpu:773.5564739654111 +Step 6895 | loss:2.012418746948242 lr:1.0394093076425549e-05 tokens_per_second_per_gpu:799.4664390507563 +Step 6896 | loss:1.99705171585083 lr:1.0376631796839941e-05 tokens_per_second_per_gpu:727.3672420212202 +Step 6897 | loss:2.041205883026123 lr:1.0359184393754474e-05 tokens_per_second_per_gpu:719.5833209458581 +Step 6898 | loss:1.9931713342666626 lr:1.034175086987057e-05 tokens_per_second_per_gpu:768.3754912255698 +Step 6899 | loss:2.0101826190948486 lr:1.0324331227887462e-05 tokens_per_second_per_gpu:779.2562628371533 +Step 6900 | loss:2.0252108573913574 lr:1.0306925470502294e-05 tokens_per_second_per_gpu:791.8240968502809 +Step 6901 | loss:2.0492899417877197 lr:1.0289533600409962e-05 tokens_per_second_per_gpu:766.6934154591731 +Step 6902 | loss:2.0424697399139404 lr:1.0272155620303315e-05 tokens_per_second_per_gpu:793.6549831981229 +Step 6903 | loss:2.0156161785125732 lr:1.0254791532872987e-05 tokens_per_second_per_gpu:776.2183143885404 +Step 6904 | loss:2.00809907913208 lr:1.0237441340807496e-05 tokens_per_second_per_gpu:794.6044992684004 +Step 6905 | loss:2.0354251861572266 lr:1.0220105046793182e-05 tokens_per_second_per_gpu:747.6411585518175 +Step 6906 | loss:2.0224781036376953 lr:1.0202782653514287e-05 tokens_per_second_per_gpu:755.5124761176553 +Step 6907 | loss:2.0093533992767334 lr:1.0185474163652786e-05 tokens_per_second_per_gpu:771.6515444505284 +Step 6908 | loss:2.042694568634033 lr:1.0168179579888605e-05 tokens_per_second_per_gpu:757.9860150414328 +Step 6909 | loss:2.019383430480957 lr:1.015089890489953e-05 tokens_per_second_per_gpu:787.4760418797201 +Step 6910 | loss:2.021148920059204 lr:1.0133632141361093e-05 tokens_per_second_per_gpu:788.376836622403 +Step 6911 | loss:2.004573106765747 lr:1.0116379291946754e-05 tokens_per_second_per_gpu:741.536831428431 +Step 6912 | loss:2.0871424674987793 lr:1.009914035932782e-05 tokens_per_second_per_gpu:794.563474518462 +Step 6913 | loss:2.0162975788116455 lr:1.0081915346173353e-05 tokens_per_second_per_gpu:744.9845429144483 +Step 6914 | loss:1.9542813301086426 lr:1.0064704255150337e-05 tokens_per_second_per_gpu:771.9237742972379 +Step 6915 | loss:1.994227409362793 lr:1.0047507088923647e-05 tokens_per_second_per_gpu:781.8794182766561 +Step 6916 | loss:2.0050134658813477 lr:1.0030323850155887e-05 tokens_per_second_per_gpu:787.024423072094 +Step 6917 | loss:2.0070388317108154 lr:1.0013154541507586e-05 tokens_per_second_per_gpu:752.6162613498179 +Step 6918 | loss:2.002486228942871 lr:9.995999165637082e-06 tokens_per_second_per_gpu:779.1114339594491 +Step 6919 | loss:2.02878475189209 lr:9.97885772520053e-06 tokens_per_second_per_gpu:742.9230017531017 +Step 6920 | loss:2.0003418922424316 lr:9.961730222852005e-06 tokens_per_second_per_gpu:784.6651459690213 +Step 6921 | loss:1.9484179019927979 lr:9.9446166612434e-06 tokens_per_second_per_gpu:771.7384294772373 +Step 6922 | loss:1.982316017150879 lr:9.92751704302437e-06 tokens_per_second_per_gpu:769.2514150233869 +Step 6923 | loss:1.9733519554138184 lr:9.910431370842487e-06 tokens_per_second_per_gpu:785.3675690247758 +Step 6924 | loss:1.9743435382843018 lr:9.89335964734317e-06 tokens_per_second_per_gpu:782.6162111363204 +Step 6925 | loss:2.0346574783325195 lr:9.876301875169647e-06 tokens_per_second_per_gpu:789.7454683785681 +Step 6926 | loss:2.065227746963501 lr:9.859258056962983e-06 tokens_per_second_per_gpu:778.3272223496097 +Step 6927 | loss:2.008275270462036 lr:9.842228195362114e-06 tokens_per_second_per_gpu:750.3238479492145 +Step 6928 | loss:1.9809550046920776 lr:9.825212293003772e-06 tokens_per_second_per_gpu:752.1943384620972 +Step 6929 | loss:1.9903608560562134 lr:9.808210352522562e-06 tokens_per_second_per_gpu:785.8733311800258 +Step 6930 | loss:2.0415163040161133 lr:9.791222376550923e-06 tokens_per_second_per_gpu:753.5610529714712 +Step 6931 | loss:1.9988625049591064 lr:9.774248367719108e-06 tokens_per_second_per_gpu:774.8509769525313 +Step 6932 | loss:2.0236430168151855 lr:9.757288328655234e-06 tokens_per_second_per_gpu:801.5020251443627 +Step 6933 | loss:1.987239956855774 lr:9.740342261985268e-06 tokens_per_second_per_gpu:776.6216942289464 +Step 6934 | loss:2.0003738403320312 lr:9.723410170332959e-06 tokens_per_second_per_gpu:769.5737141586601 +Step 6935 | loss:1.9848393201828003 lr:9.706492056319904e-06 tokens_per_second_per_gpu:787.6482678053745 +Step 6936 | loss:1.9929426908493042 lr:9.689587922565624e-06 tokens_per_second_per_gpu:785.6625259686431 +Step 6937 | loss:1.9733284711837769 lr:9.672697771687356e-06 tokens_per_second_per_gpu:788.3465216398877 +Step 6938 | loss:1.9745242595672607 lr:9.65582160630023e-06 tokens_per_second_per_gpu:790.9796936751324 +Step 6939 | loss:1.9869565963745117 lr:9.638959429017236e-06 tokens_per_second_per_gpu:771.9426546992073 +Step 6940 | loss:2.0095374584198 lr:9.622111242449106e-06 tokens_per_second_per_gpu:744.1582512851076 +Step 6941 | loss:2.039262294769287 lr:9.605277049204508e-06 tokens_per_second_per_gpu:778.3823665029136 +Step 6942 | loss:2.0307729244232178 lr:9.588456851889927e-06 tokens_per_second_per_gpu:755.1634789508133 +Step 6943 | loss:1.9855952262878418 lr:9.57165065310961e-06 tokens_per_second_per_gpu:757.9832781640152 +Step 6944 | loss:2.037576198577881 lr:9.554858455465688e-06 tokens_per_second_per_gpu:796.7979818501404 +Step 6945 | loss:2.0539186000823975 lr:9.538080261558146e-06 tokens_per_second_per_gpu:801.1962702428472 +Step 6946 | loss:2.045931339263916 lr:9.52131607398471e-06 tokens_per_second_per_gpu:768.7593270045868 +Step 6947 | loss:1.935957908630371 lr:9.504565895341077e-06 tokens_per_second_per_gpu:783.9075688270301 +Step 6948 | loss:2.020775318145752 lr:9.487829728220676e-06 tokens_per_second_per_gpu:787.1424254837044 +Step 6949 | loss:2.042630195617676 lr:9.471107575214754e-06 tokens_per_second_per_gpu:758.1683053590772 +Step 6950 | loss:2.0281875133514404 lr:9.454399438912454e-06 tokens_per_second_per_gpu:772.9393198675835 +Step 6951 | loss:1.978161096572876 lr:9.437705321900714e-06 tokens_per_second_per_gpu:774.9514071241847 +Step 6952 | loss:2.023693323135376 lr:9.421025226764301e-06 tokens_per_second_per_gpu:784.7393671110746 +Step 6953 | loss:2.0096492767333984 lr:9.404359156085818e-06 tokens_per_second_per_gpu:768.9424531762932 +Step 6954 | loss:2.0348360538482666 lr:9.38770711244572e-06 tokens_per_second_per_gpu:783.5641786582037 +Step 6955 | loss:2.013289451599121 lr:9.371069098422214e-06 tokens_per_second_per_gpu:773.3671821557692 +Step 6956 | loss:2.0382919311523438 lr:9.354445116591403e-06 tokens_per_second_per_gpu:763.619240350298 +Step 6957 | loss:1.977094292640686 lr:9.33783516952721e-06 tokens_per_second_per_gpu:793.2557527909904 +Step 6958 | loss:1.9761687517166138 lr:9.321239259801363e-06 tokens_per_second_per_gpu:747.1343455202975 +Step 6959 | loss:2.011059284210205 lr:9.30465738998344e-06 tokens_per_second_per_gpu:780.543681823169 +Step 6960 | loss:2.0085086822509766 lr:9.288089562640844e-06 tokens_per_second_per_gpu:790.4677554941045 +Step 6961 | loss:2.0529425144195557 lr:9.271535780338759e-06 tokens_per_second_per_gpu:760.4802361419246 +Step 6962 | loss:2.0429415702819824 lr:9.25499604564023e-06 tokens_per_second_per_gpu:790.8269428929711 +Step 6963 | loss:1.997677206993103 lr:9.238470361106166e-06 tokens_per_second_per_gpu:747.1306210895822 +Step 6964 | loss:1.9970824718475342 lr:9.221958729295221e-06 tokens_per_second_per_gpu:783.4106053029004 +Step 6965 | loss:1.9662009477615356 lr:9.205461152763927e-06 tokens_per_second_per_gpu:763.6235160304362 +Step 6966 | loss:2.055051803588867 lr:9.188977634066642e-06 tokens_per_second_per_gpu:776.0632950974905 +Step 6967 | loss:2.0003623962402344 lr:9.172508175755468e-06 tokens_per_second_per_gpu:766.9583657546427 +Step 6968 | loss:2.016279935836792 lr:9.156052780380464e-06 tokens_per_second_per_gpu:778.3698135058883 +Step 6969 | loss:1.9797132015228271 lr:9.139611450489416e-06 tokens_per_second_per_gpu:782.088335850018 +Step 6970 | loss:1.9848675727844238 lr:9.123184188627943e-06 tokens_per_second_per_gpu:761.5658497338181 +Step 6971 | loss:1.9720929861068726 lr:9.106770997339498e-06 tokens_per_second_per_gpu:734.7943785749363 +Step 6972 | loss:2.0164220333099365 lr:9.090371879165394e-06 tokens_per_second_per_gpu:755.5609412962381 +Step 6973 | loss:2.0619187355041504 lr:9.073986836644654e-06 tokens_per_second_per_gpu:759.74819169397 +Step 6974 | loss:2.0222489833831787 lr:9.057615872314252e-06 tokens_per_second_per_gpu:775.247185419301 +Step 6975 | loss:2.019622564315796 lr:9.041258988708945e-06 tokens_per_second_per_gpu:769.7987449162788 +Step 6976 | loss:2.0038540363311768 lr:9.024916188361233e-06 tokens_per_second_per_gpu:761.9298351976732 +Step 6977 | loss:1.987379789352417 lr:9.008587473801511e-06 tokens_per_second_per_gpu:750.8033704709073 +Step 6978 | loss:2.0280466079711914 lr:8.992272847557981e-06 tokens_per_second_per_gpu:781.6692668261073 +Step 6979 | loss:1.9890376329421997 lr:8.975972312156666e-06 tokens_per_second_per_gpu:804.3548071315961 +Step 6980 | loss:1.953931212425232 lr:8.959685870121382e-06 tokens_per_second_per_gpu:787.419546827246 +Step 6981 | loss:2.031839609146118 lr:8.943413523973809e-06 tokens_per_second_per_gpu:756.7958701294206 +Step 6982 | loss:1.981562852859497 lr:8.927155276233379e-06 tokens_per_second_per_gpu:781.4098572665619 +Step 6983 | loss:1.9875216484069824 lr:8.910911129417376e-06 tokens_per_second_per_gpu:779.4709547117604 +Step 6984 | loss:2.0325000286102295 lr:8.894681086040946e-06 tokens_per_second_per_gpu:757.2295767712973 +Step 6985 | loss:2.018446922302246 lr:8.878465148616966e-06 tokens_per_second_per_gpu:789.305655246079 +Step 6986 | loss:1.9895793199539185 lr:8.862263319656172e-06 tokens_per_second_per_gpu:782.1986602049046 +Step 6987 | loss:1.987954020500183 lr:8.846075601667159e-06 tokens_per_second_per_gpu:776.394706962212 +Step 6988 | loss:2.0103440284729004 lr:8.829901997156231e-06 tokens_per_second_per_gpu:765.3016170799815 +Step 6989 | loss:1.9602004289627075 lr:8.813742508627576e-06 tokens_per_second_per_gpu:754.8473420914569 +Step 6990 | loss:1.9552892446517944 lr:8.797597138583235e-06 tokens_per_second_per_gpu:777.681474527612 +Step 6991 | loss:2.0382046699523926 lr:8.781465889522988e-06 tokens_per_second_per_gpu:788.0934848859547 +Step 6992 | loss:2.016615390777588 lr:8.765348763944448e-06 tokens_per_second_per_gpu:789.8471824947981 +Step 6993 | loss:2.0149776935577393 lr:8.749245764343072e-06 tokens_per_second_per_gpu:759.9731891608144 +Step 6994 | loss:2.008939743041992 lr:8.733156893212068e-06 tokens_per_second_per_gpu:760.1492281104324 +Step 6995 | loss:2.025908946990967 lr:8.717082153042534e-06 tokens_per_second_per_gpu:799.4850651411165 +Step 6996 | loss:1.994304895401001 lr:8.701021546323352e-06 tokens_per_second_per_gpu:777.3680769749963 +Step 6997 | loss:2.0654828548431396 lr:8.684975075541169e-06 tokens_per_second_per_gpu:775.016902908694 +Step 6998 | loss:2.0090041160583496 lr:8.668942743180497e-06 tokens_per_second_per_gpu:800.8402338165607 +Step 6999 | loss:2.055818796157837 lr:8.65292455172364e-06 tokens_per_second_per_gpu:787.073939500615 +Step 7000 | loss:1.9533231258392334 lr:8.636920503650713e-06 tokens_per_second_per_gpu:766.0370728101606 +Step 7001 | loss:1.9435701370239258 lr:8.620930601439659e-06 tokens_per_second_per_gpu:784.8288613161048 +Step 7002 | loss:1.9963383674621582 lr:8.604954847566216e-06 tokens_per_second_per_gpu:770.0170573299081 +Step 7003 | loss:1.9709705114364624 lr:8.588993244503907e-06 tokens_per_second_per_gpu:805.6831830360433 +Step 7004 | loss:2.0081963539123535 lr:8.573045794724088e-06 tokens_per_second_per_gpu:781.4462668087824 +Step 7005 | loss:2.0066380500793457 lr:8.557112500695942e-06 tokens_per_second_per_gpu:740.4054678366216 +Step 7006 | loss:1.9710661172866821 lr:8.541193364886425e-06 tokens_per_second_per_gpu:745.2706749519454 +Step 7007 | loss:1.9995756149291992 lr:8.525288389760322e-06 tokens_per_second_per_gpu:766.0061510240765 +Step 7008 | loss:2.0631208419799805 lr:8.509397577780254e-06 tokens_per_second_per_gpu:789.2832008075859 +Step 7009 | loss:2.002636194229126 lr:8.493520931406552e-06 tokens_per_second_per_gpu:774.4582788029078 +Step 7010 | loss:1.9972199201583862 lr:8.477658453097448e-06 tokens_per_second_per_gpu:758.3531741510963 +Step 7011 | loss:2.0399868488311768 lr:8.46181014530898e-06 tokens_per_second_per_gpu:762.2469218550597 +Step 7012 | loss:2.072815179824829 lr:8.445976010494905e-06 tokens_per_second_per_gpu:783.2463878397017 +Step 7013 | loss:2.021711826324463 lr:8.430156051106886e-06 tokens_per_second_per_gpu:753.013512391621 +Step 7014 | loss:2.0397391319274902 lr:8.41435026959434e-06 tokens_per_second_per_gpu:767.5861750218824 +Step 7015 | loss:1.9883965253829956 lr:8.398558668404478e-06 tokens_per_second_per_gpu:767.948066530499 +Step 7016 | loss:2.017199993133545 lr:8.382781249982318e-06 tokens_per_second_per_gpu:793.3693004494298 +Step 7017 | loss:1.9927685260772705 lr:8.367018016770767e-06 tokens_per_second_per_gpu:761.9089526257965 +Step 7018 | loss:1.9870935678482056 lr:8.351268971210401e-06 tokens_per_second_per_gpu:792.1436450472282 +Step 7019 | loss:2.0230233669281006 lr:8.335534115739696e-06 tokens_per_second_per_gpu:778.2469681282315 +Step 7020 | loss:2.113574743270874 lr:8.3198134527949e-06 tokens_per_second_per_gpu:739.5056410713594 +Step 7021 | loss:2.0495216846466064 lr:8.304106984810022e-06 tokens_per_second_per_gpu:758.0373416759596 +Step 7022 | loss:2.0224127769470215 lr:8.288414714216963e-06 tokens_per_second_per_gpu:793.7490782663391 +Step 7023 | loss:2.0118565559387207 lr:8.272736643445378e-06 tokens_per_second_per_gpu:782.1820118624813 +Step 7024 | loss:1.9807895421981812 lr:8.25707277492268e-06 tokens_per_second_per_gpu:757.4310310398708 +Step 7025 | loss:1.9796618223190308 lr:8.241423111074165e-06 tokens_per_second_per_gpu:755.4895754051113 +Step 7026 | loss:2.005553960800171 lr:8.22578765432287e-06 tokens_per_second_per_gpu:779.5276530854625 +Step 7027 | loss:1.9758167266845703 lr:8.210166407089659e-06 tokens_per_second_per_gpu:783.8626271521981 +Step 7028 | loss:1.9821888208389282 lr:8.194559371793187e-06 tokens_per_second_per_gpu:776.6907824670338 +Step 7029 | loss:1.9638466835021973 lr:8.178966550849931e-06 tokens_per_second_per_gpu:778.4082600550147 +Step 7030 | loss:2.0066330432891846 lr:8.163387946674117e-06 tokens_per_second_per_gpu:794.0161539373308 +Step 7031 | loss:1.9882395267486572 lr:8.147823561677815e-06 tokens_per_second_per_gpu:785.031130432568 +Step 7032 | loss:1.9998036623001099 lr:8.132273398270873e-06 tokens_per_second_per_gpu:783.1183521242572 +Step 7033 | loss:2.0065464973449707 lr:8.116737458860945e-06 tokens_per_second_per_gpu:767.2315075647114 +Step 7034 | loss:2.008288860321045 lr:8.101215745853485e-06 tokens_per_second_per_gpu:761.375095990374 +Step 7035 | loss:1.9858522415161133 lr:8.085708261651748e-06 tokens_per_second_per_gpu:761.6421012090893 +Step 7036 | loss:1.9462605714797974 lr:8.070215008656757e-06 tokens_per_second_per_gpu:767.9614615609532 +Step 7037 | loss:2.037123203277588 lr:8.054735989267336e-06 tokens_per_second_per_gpu:782.3522173843878 +Step 7038 | loss:1.9592714309692383 lr:8.039271205880184e-06 tokens_per_second_per_gpu:771.2169441843556 +Step 7039 | loss:1.9563045501708984 lr:8.02382066088968e-06 tokens_per_second_per_gpu:791.813330352895 +Step 7040 | loss:2.078606128692627 lr:8.008384356688058e-06 tokens_per_second_per_gpu:778.2678670085692 +Step 7041 | loss:1.9604637622833252 lr:7.992962295665374e-06 tokens_per_second_per_gpu:787.1066165950602 +Step 7042 | loss:1.9451754093170166 lr:7.977554480209382e-06 tokens_per_second_per_gpu:726.9217580388275 +Step 7043 | loss:2.015380859375 lr:7.962160912705752e-06 tokens_per_second_per_gpu:789.7249059458242 +Step 7044 | loss:1.961629867553711 lr:7.946781595537889e-06 tokens_per_second_per_gpu:786.2527947058966 +Step 7045 | loss:1.9871070384979248 lr:7.931416531086955e-06 tokens_per_second_per_gpu:782.6202477800913 +Step 7046 | loss:2.0712687969207764 lr:7.916065721731958e-06 tokens_per_second_per_gpu:781.5006007591203 +Step 7047 | loss:1.9839544296264648 lr:7.900729169849708e-06 tokens_per_second_per_gpu:786.136882224195 +Step 7048 | loss:1.9542537927627563 lr:7.885406877814716e-06 tokens_per_second_per_gpu:784.3697050283109 +Step 7049 | loss:1.97475266456604 lr:7.87009884799943e-06 tokens_per_second_per_gpu:780.5980080173271 +Step 7050 | loss:2.030923843383789 lr:7.854805082773986e-06 tokens_per_second_per_gpu:726.5275182586132 +Step 7051 | loss:2.0348339080810547 lr:7.839525584506314e-06 tokens_per_second_per_gpu:763.2081030931918 +Step 7052 | loss:2.001101016998291 lr:7.824260355562174e-06 tokens_per_second_per_gpu:786.3695580546708 +Step 7053 | loss:1.9510785341262817 lr:7.809009398305101e-06 tokens_per_second_per_gpu:746.8001146506176 +Step 7054 | loss:1.9912567138671875 lr:7.793772715096415e-06 tokens_per_second_per_gpu:796.0048131231705 +Step 7055 | loss:2.0278375148773193 lr:7.778550308295241e-06 tokens_per_second_per_gpu:779.0992988296817 +Step 7056 | loss:1.9933412075042725 lr:7.763342180258493e-06 tokens_per_second_per_gpu:768.9839104445432 +Step 7057 | loss:1.9802559614181519 lr:7.748148333340832e-06 tokens_per_second_per_gpu:747.4169384079842 +Step 7058 | loss:1.9627043008804321 lr:7.732968769894744e-06 tokens_per_second_per_gpu:797.9075463450098 +Step 7059 | loss:1.9752311706542969 lr:7.717803492270547e-06 tokens_per_second_per_gpu:738.8361421386495 +Step 7060 | loss:2.015655994415283 lr:7.702652502816254e-06 tokens_per_second_per_gpu:758.9583264490849 +Step 7061 | loss:2.011770486831665 lr:7.687515803877731e-06 tokens_per_second_per_gpu:767.9617181006772 +Step 7062 | loss:1.9671638011932373 lr:7.672393397798616e-06 tokens_per_second_per_gpu:791.2555023175624 +Step 7063 | loss:2.0287909507751465 lr:7.657285286920313e-06 tokens_per_second_per_gpu:766.1695643664929 +Step 7064 | loss:1.9665660858154297 lr:7.642191473582016e-06 tokens_per_second_per_gpu:771.744216583972 +Step 7065 | loss:1.9810962677001953 lr:7.6271119601207805e-06 tokens_per_second_per_gpu:763.3175826158106 +Step 7066 | loss:2.0298945903778076 lr:7.612046748871327e-06 tokens_per_second_per_gpu:719.0415625063093 +Step 7067 | loss:2.0105183124542236 lr:7.596995842166243e-06 tokens_per_second_per_gpu:750.1347592426459 +Step 7068 | loss:1.957828402519226 lr:7.581959242335901e-06 tokens_per_second_per_gpu:756.3345802582488 +Step 7069 | loss:2.0033886432647705 lr:7.566936951708381e-06 tokens_per_second_per_gpu:756.3745600687866 +Step 7070 | loss:2.0638766288757324 lr:7.551928972609656e-06 tokens_per_second_per_gpu:762.5930577737807 +Step 7071 | loss:2.096872091293335 lr:7.536935307363424e-06 tokens_per_second_per_gpu:767.4570132385224 +Step 7072 | loss:1.9838192462921143 lr:7.521955958291149e-06 tokens_per_second_per_gpu:782.928851836741 +Step 7073 | loss:1.9943976402282715 lr:7.50699092771211e-06 tokens_per_second_per_gpu:757.6076048588393 +Step 7074 | loss:1.995242953300476 lr:7.492040217943386e-06 tokens_per_second_per_gpu:762.4956676888602 +Step 7075 | loss:2.0500175952911377 lr:7.477103831299759e-06 tokens_per_second_per_gpu:770.7085149742549 +Step 7076 | loss:1.9645566940307617 lr:7.462181770093912e-06 tokens_per_second_per_gpu:780.2224292290482 +Step 7077 | loss:2.0438482761383057 lr:7.447274036636231e-06 tokens_per_second_per_gpu:777.3123879462058 +Step 7078 | loss:2.0453057289123535 lr:7.43238063323487e-06 tokens_per_second_per_gpu:752.1169733396308 +Step 7079 | loss:1.9452226161956787 lr:7.417501562195805e-06 tokens_per_second_per_gpu:793.0188967167938 +Step 7080 | loss:1.9987239837646484 lr:7.402636825822795e-06 tokens_per_second_per_gpu:767.640872595173 +Step 7081 | loss:1.995725393295288 lr:7.387786426417365e-06 tokens_per_second_per_gpu:779.3207304756371 +Step 7082 | loss:2.003662586212158 lr:7.372950366278808e-06 tokens_per_second_per_gpu:784.1916685462338 +Step 7083 | loss:2.0040831565856934 lr:7.358128647704243e-06 tokens_per_second_per_gpu:762.9270117058053 +Step 7084 | loss:1.9943695068359375 lr:7.3433212729884796e-06 tokens_per_second_per_gpu:759.3742914599719 +Step 7085 | loss:2.0137336254119873 lr:7.328528244424182e-06 tokens_per_second_per_gpu:788.580271457095 +Step 7086 | loss:2.0656423568725586 lr:7.31374956430182e-06 tokens_per_second_per_gpu:798.3056515235547 +Step 7087 | loss:2.0076866149902344 lr:7.29898523490955e-06 tokens_per_second_per_gpu:788.184974119381 +Step 7088 | loss:1.990905523300171 lr:7.284235258533357e-06 tokens_per_second_per_gpu:762.4363114407068 +Step 7089 | loss:1.9883270263671875 lr:7.269499637457011e-06 tokens_per_second_per_gpu:752.4669502994079 +Step 7090 | loss:2.0014872550964355 lr:7.254778373962034e-06 tokens_per_second_per_gpu:758.0973474568107 +Step 7091 | loss:2.078714370727539 lr:7.240071470327725e-06 tokens_per_second_per_gpu:763.2843964403366 +Step 7092 | loss:1.9627670049667358 lr:7.225378928831216e-06 tokens_per_second_per_gpu:801.2875093325716 +Step 7093 | loss:2.0382585525512695 lr:7.210700751747346e-06 tokens_per_second_per_gpu:750.2078547631347 +Step 7094 | loss:1.986469030380249 lr:7.196036941348749e-06 tokens_per_second_per_gpu:772.6104624795931 +Step 7095 | loss:2.0118589401245117 lr:7.181387499905867e-06 tokens_per_second_per_gpu:771.3025670140843 +Step 7096 | loss:1.9825553894042969 lr:7.16675242968684e-06 tokens_per_second_per_gpu:760.9194611257549 +Step 7097 | loss:2.0440821647644043 lr:7.152131732957678e-06 tokens_per_second_per_gpu:768.5813237307544 +Step 7098 | loss:2.00955867767334 lr:7.137525411982138e-06 tokens_per_second_per_gpu:769.9339389286007 +Step 7099 | loss:1.98025643825531 lr:7.122933469021687e-06 tokens_per_second_per_gpu:769.0523891966824 +Step 7100 | loss:2.0042600631713867 lr:7.10835590633564e-06 tokens_per_second_per_gpu:786.0168094552729 +Step 7101 | loss:1.9704434871673584 lr:7.093792726181059e-06 tokens_per_second_per_gpu:788.2817066701543 +Step 7102 | loss:1.9382919073104858 lr:7.079243930812774e-06 tokens_per_second_per_gpu:789.9133480269157 +Step 7103 | loss:1.9365267753601074 lr:7.064709522483403e-06 tokens_per_second_per_gpu:797.6235671657096 +Step 7104 | loss:1.9553067684173584 lr:7.050189503443327e-06 tokens_per_second_per_gpu:762.274671270329 +Step 7105 | loss:2.010303020477295 lr:7.0356838759406905e-06 tokens_per_second_per_gpu:787.004889307609 +Step 7106 | loss:1.9936943054199219 lr:7.021192642221408e-06 tokens_per_second_per_gpu:784.4096390888328 +Step 7107 | loss:2.0212485790252686 lr:7.006715804529196e-06 tokens_per_second_per_gpu:755.3434020108164 +Step 7108 | loss:1.964399814605713 lr:6.992253365105506e-06 tokens_per_second_per_gpu:762.7472725998394 +Step 7109 | loss:2.047462224960327 lr:6.97780532618959e-06 tokens_per_second_per_gpu:783.3916603019051 +Step 7110 | loss:2.010692596435547 lr:6.963371690018461e-06 tokens_per_second_per_gpu:775.8025140368785 +Step 7111 | loss:2.011589527130127 lr:6.9489524588268736e-06 tokens_per_second_per_gpu:794.2787378614396 +Step 7112 | loss:2.0422778129577637 lr:6.934547634847377e-06 tokens_per_second_per_gpu:771.0533668467411 +Step 7113 | loss:1.9953986406326294 lr:6.9201572203103195e-06 tokens_per_second_per_gpu:757.8077988256975 +Step 7114 | loss:1.9793702363967896 lr:6.905781217443763e-06 tokens_per_second_per_gpu:780.0028434014657 +Step 7115 | loss:2.009322166442871 lr:6.891419628473561e-06 tokens_per_second_per_gpu:779.9995313839308 +Step 7116 | loss:2.0256423950195312 lr:6.877072455623368e-06 tokens_per_second_per_gpu:776.9544265890739 +Step 7117 | loss:2.078244686126709 lr:6.8627397011145064e-06 tokens_per_second_per_gpu:781.8272858632022 +Step 7118 | loss:2.0252113342285156 lr:6.848421367166202e-06 tokens_per_second_per_gpu:744.31182317577 +Step 7119 | loss:2.0170981884002686 lr:6.834117455995359e-06 tokens_per_second_per_gpu:765.5471528256938 +Step 7120 | loss:1.969323992729187 lr:6.819827969816661e-06 tokens_per_second_per_gpu:772.0239085664999 +Step 7121 | loss:2.0220179557800293 lr:6.805552910842583e-06 tokens_per_second_per_gpu:773.0994994262801 +Step 7122 | loss:1.9871983528137207 lr:6.791292281283346e-06 tokens_per_second_per_gpu:779.2865391578982 +Step 7123 | loss:2.0058932304382324 lr:6.777046083346905e-06 tokens_per_second_per_gpu:795.3726950383834 +Step 7124 | loss:2.043667793273926 lr:6.762814319239075e-06 tokens_per_second_per_gpu:771.314075836796 +Step 7125 | loss:1.9722100496292114 lr:6.748596991163359e-06 tokens_per_second_per_gpu:750.3981421499449 +Step 7126 | loss:1.9904789924621582 lr:6.734394101321018e-06 tokens_per_second_per_gpu:791.9319459119276 +Step 7127 | loss:2.0381617546081543 lr:6.720205651911127e-06 tokens_per_second_per_gpu:783.1076762674368 +Step 7128 | loss:2.0335464477539062 lr:6.706031645130506e-06 tokens_per_second_per_gpu:790.8691788277212 +Step 7129 | loss:1.9988163709640503 lr:6.691872083173711e-06 tokens_per_second_per_gpu:740.8759702229333 +Step 7130 | loss:2.012251615524292 lr:6.677726968233111e-06 tokens_per_second_per_gpu:787.1416682984692 +Step 7131 | loss:1.9151272773742676 lr:6.66359630249882e-06 tokens_per_second_per_gpu:766.4821906136651 +Step 7132 | loss:1.9481229782104492 lr:6.6494800881586664e-06 tokens_per_second_per_gpu:764.4783097951024 +Step 7133 | loss:2.025603771209717 lr:6.6353783273983e-06 tokens_per_second_per_gpu:782.5242177712054 +Step 7134 | loss:2.0405948162078857 lr:6.621291022401121e-06 tokens_per_second_per_gpu:685.6538503513528 +Step 7135 | loss:1.9917519092559814 lr:6.607218175348273e-06 tokens_per_second_per_gpu:799.0871578456242 +Step 7136 | loss:1.9524366855621338 lr:6.59315978841869e-06 tokens_per_second_per_gpu:775.1879824436459 +Step 7137 | loss:2.000979423522949 lr:6.579115863789053e-06 tokens_per_second_per_gpu:771.0987043689698 +Step 7138 | loss:1.9973467588424683 lr:6.56508640363378e-06 tokens_per_second_per_gpu:772.5136270323856 +Step 7139 | loss:2.0299034118652344 lr:6.5510714101250535e-06 tokens_per_second_per_gpu:794.3260442927256 +Step 7140 | loss:1.995288372039795 lr:6.537070885432906e-06 tokens_per_second_per_gpu:786.7654358323565 +Step 7141 | loss:1.989843726158142 lr:6.52308483172498e-06 tokens_per_second_per_gpu:783.451255701913 +Step 7142 | loss:2.078688383102417 lr:6.5091132511667875e-06 tokens_per_second_per_gpu:791.8075298731635 +Step 7143 | loss:2.016008138656616 lr:6.495156145921566e-06 tokens_per_second_per_gpu:744.7158026377375 +Step 7144 | loss:2.039970874786377 lr:6.4812135181502865e-06 tokens_per_second_per_gpu:798.3818286101172 +Step 7145 | loss:1.9605827331542969 lr:6.467285370011744e-06 tokens_per_second_per_gpu:783.6454565217388 +Step 7146 | loss:1.9993393421173096 lr:6.453371703662436e-06 tokens_per_second_per_gpu:774.2556310479509 +Step 7147 | loss:1.9830694198608398 lr:6.439472521256618e-06 tokens_per_second_per_gpu:773.8809950818959 +Step 7148 | loss:2.0580787658691406 lr:6.425587824946333e-06 tokens_per_second_per_gpu:793.5292005641338 +Step 7149 | loss:1.9812226295471191 lr:6.4117176168813745e-06 tokens_per_second_per_gpu:773.747513717905 +Step 7150 | loss:2.0026252269744873 lr:6.397861899209245e-06 tokens_per_second_per_gpu:773.7588670585072 +Step 7151 | loss:2.0659358501434326 lr:6.3840206740752864e-06 tokens_per_second_per_gpu:788.6240447329149 +Step 7152 | loss:2.097754955291748 lr:6.370193943622549e-06 tokens_per_second_per_gpu:785.5202479548981 +Step 7153 | loss:2.0137176513671875 lr:6.356381709991821e-06 tokens_per_second_per_gpu:805.7155469001741 +Step 7154 | loss:2.031982660293579 lr:6.34258397532167e-06 tokens_per_second_per_gpu:759.592721634663 +Step 7155 | loss:1.9945228099822998 lr:6.328800741748431e-06 tokens_per_second_per_gpu:789.180538980431 +Step 7156 | loss:2.0185725688934326 lr:6.315032011406163e-06 tokens_per_second_per_gpu:787.3330590021452 +Step 7157 | loss:1.9822173118591309 lr:6.301277786426718e-06 tokens_per_second_per_gpu:776.2616554577027 +Step 7158 | loss:2.0382189750671387 lr:6.2875380689396805e-06 tokens_per_second_per_gpu:761.885721301925 +Step 7159 | loss:2.0205161571502686 lr:6.2738128610723704e-06 tokens_per_second_per_gpu:746.9301475818725 +Step 7160 | loss:2.0569710731506348 lr:6.2601021649498545e-06 tokens_per_second_per_gpu:771.8989948886024 +Step 7161 | loss:2.0110933780670166 lr:6.246405982695047e-06 tokens_per_second_per_gpu:744.3436602824532 +Step 7162 | loss:1.9889252185821533 lr:6.2327243164284955e-06 tokens_per_second_per_gpu:758.7963229334898 +Step 7163 | loss:1.9824199676513672 lr:6.21905716826856e-06 tokens_per_second_per_gpu:765.0377206006276 +Step 7164 | loss:1.974417805671692 lr:6.20540454033135e-06 tokens_per_second_per_gpu:788.2375567550405 +Step 7165 | loss:1.9403297901153564 lr:6.191766434730705e-06 tokens_per_second_per_gpu:762.9515100501368 +Step 7166 | loss:1.91537344455719 lr:6.178142853578217e-06 tokens_per_second_per_gpu:759.0630050490953 +Step 7167 | loss:1.9832572937011719 lr:6.164533798983307e-06 tokens_per_second_per_gpu:787.9159644453528 +Step 7168 | loss:1.9551514387130737 lr:6.1509392730530136e-06 tokens_per_second_per_gpu:773.2658990858898 +Step 7169 | loss:1.9841893911361694 lr:6.137359277892218e-06 tokens_per_second_per_gpu:785.892283333445 +Step 7170 | loss:1.9371612071990967 lr:6.1237938156035404e-06 tokens_per_second_per_gpu:785.1904278620867 +Step 7171 | loss:2.0641841888427734 lr:6.1102428882873094e-06 tokens_per_second_per_gpu:796.7324003930914 +Step 7172 | loss:2.0289406776428223 lr:6.09670649804166e-06 tokens_per_second_per_gpu:796.0414786267952 +Step 7173 | loss:1.9889047145843506 lr:6.083184646962448e-06 tokens_per_second_per_gpu:771.0242478260069 +Step 7174 | loss:2.003291606903076 lr:6.0696773371432646e-06 tokens_per_second_per_gpu:794.1436534002665 +Step 7175 | loss:2.0093441009521484 lr:6.056184570675461e-06 tokens_per_second_per_gpu:774.2644742000547 +Step 7176 | loss:1.9978408813476562 lr:6.042706349648153e-06 tokens_per_second_per_gpu:772.4900867848448 +Step 7177 | loss:2.037731647491455 lr:6.029242676148194e-06 tokens_per_second_per_gpu:793.8310329341865 +Step 7178 | loss:2.03776478767395 lr:6.015793552260162e-06 tokens_per_second_per_gpu:780.719676871257 +Step 7179 | loss:1.9470610618591309 lr:6.0023589800664245e-06 tokens_per_second_per_gpu:791.9355275619431 +Step 7180 | loss:1.994181513786316 lr:5.988938961647062e-06 tokens_per_second_per_gpu:776.048083976202 +Step 7181 | loss:2.000117301940918 lr:5.975533499079899e-06 tokens_per_second_per_gpu:761.7054040737663 +Step 7182 | loss:1.9805173873901367 lr:5.962142594440545e-06 tokens_per_second_per_gpu:757.5559369577069 +Step 7183 | loss:2.034817695617676 lr:5.948766249802307e-06 tokens_per_second_per_gpu:793.2073627348499 +Step 7184 | loss:1.9851666688919067 lr:5.9354044672362826e-06 tokens_per_second_per_gpu:794.5356856927901 +Step 7185 | loss:1.9780170917510986 lr:5.922057248811308e-06 tokens_per_second_per_gpu:759.7232111306291 +Step 7186 | loss:2.042329788208008 lr:5.908724596593906e-06 tokens_per_second_per_gpu:769.9237725041698 +Step 7187 | loss:2.021334648132324 lr:5.895406512648394e-06 tokens_per_second_per_gpu:792.4657410606738 +Step 7188 | loss:1.949784517288208 lr:5.882102999036876e-06 tokens_per_second_per_gpu:781.7256173386153 +Step 7189 | loss:1.9438071250915527 lr:5.8688140578191055e-06 tokens_per_second_per_gpu:784.4803110672161 +Step 7190 | loss:2.0536274909973145 lr:5.8555396910526365e-06 tokens_per_second_per_gpu:771.9222541021517 +Step 7191 | loss:1.9990100860595703 lr:5.842279900792769e-06 tokens_per_second_per_gpu:781.9918965937428 +Step 7192 | loss:2.0604441165924072 lr:5.829034689092516e-06 tokens_per_second_per_gpu:785.4573032208297 +Step 7193 | loss:1.9445594549179077 lr:5.81580405800265e-06 tokens_per_second_per_gpu:790.9722932731861 +Step 7194 | loss:2.0282037258148193 lr:5.802588009571719e-06 tokens_per_second_per_gpu:759.0521617558388 +Step 7195 | loss:2.0263147354125977 lr:5.789386545845943e-06 tokens_per_second_per_gpu:786.7061183835172 +Step 7196 | loss:2.016292095184326 lr:5.776199668869331e-06 tokens_per_second_per_gpu:754.5915468001118 +Step 7197 | loss:2.0058794021606445 lr:5.76302738068365e-06 tokens_per_second_per_gpu:787.0299806151481 +Step 7198 | loss:2.034681558609009 lr:5.7498696833283236e-06 tokens_per_second_per_gpu:775.7079484625475 +Step 7199 | loss:2.008455514907837 lr:5.736726578840635e-06 tokens_per_second_per_gpu:777.9096199217681 +Step 7200 | loss:2.000612258911133 lr:5.7235980692555314e-06 tokens_per_second_per_gpu:779.9137339067901 +Step 7201 | loss:1.9604129791259766 lr:5.710484156605689e-06 tokens_per_second_per_gpu:781.8664761530115 +Step 7202 | loss:1.9905251264572144 lr:5.697384842921583e-06 tokens_per_second_per_gpu:776.4915791672627 +Step 7203 | loss:1.92352294921875 lr:5.684300130231379e-06 tokens_per_second_per_gpu:790.2859203817258 +Step 7204 | loss:2.002884864807129 lr:5.671230020561014e-06 tokens_per_second_per_gpu:784.2197546617299 +Step 7205 | loss:2.023496627807617 lr:5.658174515934134e-06 tokens_per_second_per_gpu:787.057958353126 +Step 7206 | loss:2.030656337738037 lr:5.645133618372167e-06 tokens_per_second_per_gpu:788.289322506833 +Step 7207 | loss:1.9882218837738037 lr:5.632107329894221e-06 tokens_per_second_per_gpu:757.5218281407946 +Step 7208 | loss:2.073059558868408 lr:5.619095652517181e-06 tokens_per_second_per_gpu:760.7853220714295 +Step 7209 | loss:2.061704635620117 lr:5.606098588255659e-06 tokens_per_second_per_gpu:748.9120262524309 +Step 7210 | loss:2.0163180828094482 lr:5.593116139122024e-06 tokens_per_second_per_gpu:777.2645660858177 +Step 7211 | loss:2.00767183303833 lr:5.580148307126343e-06 tokens_per_second_per_gpu:754.927433044965 +Step 7212 | loss:2.014160394668579 lr:5.567195094276478e-06 tokens_per_second_per_gpu:790.0063899491972 +Step 7213 | loss:2.023092031478882 lr:5.554256502577948e-06 tokens_per_second_per_gpu:736.330512796601 +Step 7214 | loss:2.0112268924713135 lr:5.541332534034049e-06 tokens_per_second_per_gpu:781.5374426910479 +Step 7215 | loss:1.9824860095977783 lr:5.52842319064587e-06 tokens_per_second_per_gpu:777.7283472847513 +Step 7216 | loss:2.044994354248047 lr:5.515528474412135e-06 tokens_per_second_per_gpu:776.1785231547542 +Step 7217 | loss:1.9529727697372437 lr:5.502648387329357e-06 tokens_per_second_per_gpu:759.9792037454035 +Step 7218 | loss:1.9973063468933105 lr:5.4897829313917955e-06 tokens_per_second_per_gpu:768.6075780002052 +Step 7219 | loss:2.025883913040161 lr:5.4769321085913925e-06 tokens_per_second_per_gpu:790.1203291848964 +Step 7220 | loss:2.0123860836029053 lr:5.4640959209178774e-06 tokens_per_second_per_gpu:774.0024420520836 +Step 7221 | loss:1.9995797872543335 lr:5.4512743703587165e-06 tokens_per_second_per_gpu:740.5227731471629 +Step 7222 | loss:2.029517650604248 lr:5.438467458899043e-06 tokens_per_second_per_gpu:790.9601507753832 +Step 7223 | loss:1.9648154973983765 lr:5.425675188521784e-06 tokens_per_second_per_gpu:789.2788084337425 +Step 7224 | loss:2.0052661895751953 lr:5.412897561207597e-06 tokens_per_second_per_gpu:770.1291834745268 +Step 7225 | loss:2.011451005935669 lr:5.400134578934824e-06 tokens_per_second_per_gpu:779.1370313959461 +Step 7226 | loss:2.0375454425811768 lr:5.387386243679615e-06 tokens_per_second_per_gpu:752.7468480891093 +Step 7227 | loss:2.0024523735046387 lr:5.374652557415793e-06 tokens_per_second_per_gpu:788.7219582247681 +Step 7228 | loss:2.020047664642334 lr:5.361933522114926e-06 tokens_per_second_per_gpu:772.0387542122857 +Step 7229 | loss:2.022111177444458 lr:5.349229139746325e-06 tokens_per_second_per_gpu:766.0545893312673 +Step 7230 | loss:2.020597457885742 lr:5.3365394122770195e-06 tokens_per_second_per_gpu:760.3236131440568 +Step 7231 | loss:1.9798424243927002 lr:5.32386434167178e-06 tokens_per_second_per_gpu:792.222712872844 +Step 7232 | loss:2.033672571182251 lr:5.311203929893105e-06 tokens_per_second_per_gpu:762.696569880733 +Step 7233 | loss:2.0304908752441406 lr:5.298558178901236e-06 tokens_per_second_per_gpu:771.3166810629123 +Step 7234 | loss:2.014211893081665 lr:5.285927090654097e-06 tokens_per_second_per_gpu:746.1803392277212 +Step 7235 | loss:1.9923717975616455 lr:5.2733106671074e-06 tokens_per_second_per_gpu:784.712677768519 +Step 7236 | loss:1.9828602075576782 lr:5.2607089102145516e-06 tokens_per_second_per_gpu:752.4314513770253 +Step 7237 | loss:2.0303125381469727 lr:5.248121821926699e-06 tokens_per_second_per_gpu:781.5500255452142 +Step 7238 | loss:1.9708284139633179 lr:5.23554940419273e-06 tokens_per_second_per_gpu:750.455275675272 +Step 7239 | loss:1.9916176795959473 lr:5.222991658959253e-06 tokens_per_second_per_gpu:771.4875218521742 +Step 7240 | loss:2.001105308532715 lr:5.2104485881705575e-06 tokens_per_second_per_gpu:761.9023462559444 +Step 7241 | loss:2.0528464317321777 lr:5.197920193768724e-06 tokens_per_second_per_gpu:774.8147468711422 +Step 7242 | loss:1.9681553840637207 lr:5.185406477693578e-06 tokens_per_second_per_gpu:790.4880259812707 +Step 7243 | loss:2.075157642364502 lr:5.172907441882591e-06 tokens_per_second_per_gpu:786.021949383366 +Step 7244 | loss:1.9648686647415161 lr:5.1604230882710155e-06 tokens_per_second_per_gpu:777.9597797665324 +Step 7245 | loss:2.0182647705078125 lr:5.147953418791829e-06 tokens_per_second_per_gpu:763.9940806454493 +Step 7246 | loss:1.9899659156799316 lr:5.135498435375685e-06 tokens_per_second_per_gpu:769.7867514548357 +Step 7247 | loss:1.9932293891906738 lr:5.123058139951065e-06 tokens_per_second_per_gpu:776.266377730466 +Step 7248 | loss:1.9660570621490479 lr:5.110632534444093e-06 tokens_per_second_per_gpu:780.5465016367268 +Step 7249 | loss:2.018968343734741 lr:5.0982216207786205e-06 tokens_per_second_per_gpu:771.4538251201731 +Step 7250 | loss:2.016261339187622 lr:5.085825400876265e-06 tokens_per_second_per_gpu:778.6285855503035 +Step 7251 | loss:2.0059823989868164 lr:5.073443876656359e-06 tokens_per_second_per_gpu:799.5231447564057 +Step 7252 | loss:2.029264211654663 lr:5.061077050035912e-06 tokens_per_second_per_gpu:768.9000089118247 +Step 7253 | loss:1.9864912033081055 lr:5.048724922929726e-06 tokens_per_second_per_gpu:734.6218176961609 +Step 7254 | loss:2.0347750186920166 lr:5.0363874972503055e-06 tokens_per_second_per_gpu:764.8029876362842 +Step 7255 | loss:2.009248733520508 lr:5.024064774907844e-06 tokens_per_second_per_gpu:777.7624815098578 +Step 7256 | loss:1.9789544343948364 lr:5.0117567578102935e-06 tokens_per_second_per_gpu:760.6079392633616 +Step 7257 | loss:2.032243251800537 lr:4.999463447863317e-06 tokens_per_second_per_gpu:775.4201856044585 +Step 7258 | loss:1.9764927625656128 lr:4.987184846970317e-06 tokens_per_second_per_gpu:758.4648069093136 +Step 7259 | loss:2.0239522457122803 lr:4.9749209570323805e-06 tokens_per_second_per_gpu:778.8507790764368 +Step 7260 | loss:1.975675106048584 lr:4.96267177994838e-06 tokens_per_second_per_gpu:775.2699843730272 +Step 7261 | loss:1.9882967472076416 lr:4.950437317614831e-06 tokens_per_second_per_gpu:770.6146136674098 +Step 7262 | loss:2.0127453804016113 lr:4.938217571926007e-06 tokens_per_second_per_gpu:774.1358309175671 +Step 7263 | loss:2.0319039821624756 lr:4.926012544773962e-06 tokens_per_second_per_gpu:762.2647191643464 +Step 7264 | loss:2.0797035694122314 lr:4.91382223804836e-06 tokens_per_second_per_gpu:790.0782906521255 +Step 7265 | loss:2.0101051330566406 lr:4.90164665363666e-06 tokens_per_second_per_gpu:773.2849523978707 +Step 7266 | loss:1.9989984035491943 lr:4.8894857934240425e-06 tokens_per_second_per_gpu:757.7695079737591 +Step 7267 | loss:1.9752929210662842 lr:4.877339659293367e-06 tokens_per_second_per_gpu:776.3556634614846 +Step 7268 | loss:2.001995086669922 lr:4.865208253125208e-06 tokens_per_second_per_gpu:796.3892730737984 +Step 7269 | loss:1.9808242321014404 lr:4.853091576797964e-06 tokens_per_second_per_gpu:759.3777374171403 +Step 7270 | loss:2.0315914154052734 lr:4.840989632187609e-06 tokens_per_second_per_gpu:759.4765444906996 +Step 7271 | loss:2.0424611568450928 lr:4.828902421167913e-06 tokens_per_second_per_gpu:759.7312942662006 +Step 7272 | loss:2.0145914554595947 lr:4.8168299456103905e-06 tokens_per_second_per_gpu:761.6236774950532 +Step 7273 | loss:1.979180097579956 lr:4.804772207384178e-06 tokens_per_second_per_gpu:755.7819724367039 +Step 7274 | loss:2.0460548400878906 lr:4.79272920835625e-06 tokens_per_second_per_gpu:764.5478886655818 +Step 7275 | loss:2.057480573654175 lr:4.780700950391215e-06 tokens_per_second_per_gpu:788.8121428069086 +Step 7276 | loss:1.9878132343292236 lr:4.768687435351415e-06 tokens_per_second_per_gpu:775.9237690288602 +Step 7277 | loss:1.9504417181015015 lr:4.75668866509692e-06 tokens_per_second_per_gpu:764.8612151897203 +Step 7278 | loss:1.9496408700942993 lr:4.74470464148552e-06 tokens_per_second_per_gpu:770.4089405978475 +Step 7279 | loss:1.9237816333770752 lr:4.73273536637272e-06 tokens_per_second_per_gpu:729.0544765456282 +Step 7280 | loss:2.0402495861053467 lr:4.720780841611738e-06 tokens_per_second_per_gpu:750.0951667747394 +Step 7281 | loss:2.0469143390655518 lr:4.708841069053516e-06 tokens_per_second_per_gpu:795.8022355291209 +Step 7282 | loss:2.048098087310791 lr:4.696916050546685e-06 tokens_per_second_per_gpu:781.318925382387 +Step 7283 | loss:1.9157679080963135 lr:4.685005787937613e-06 tokens_per_second_per_gpu:786.4311187191694 +Step 7284 | loss:1.9603359699249268 lr:4.673110283070381e-06 tokens_per_second_per_gpu:752.2951329365347 +Step 7285 | loss:2.0166592597961426 lr:4.661229537786804e-06 tokens_per_second_per_gpu:771.41616102496 +Step 7286 | loss:2.0400123596191406 lr:4.649363553926367e-06 tokens_per_second_per_gpu:743.1020339051398 +Step 7287 | loss:1.9725254774093628 lr:4.637512333326333e-06 tokens_per_second_per_gpu:772.5108346080546 +Step 7288 | loss:1.9809842109680176 lr:4.6256758778216e-06 tokens_per_second_per_gpu:732.5351900353392 +Step 7289 | loss:2.007887363433838 lr:4.613854189244837e-06 tokens_per_second_per_gpu:791.547098921744 +Step 7290 | loss:1.9609708786010742 lr:4.602047269426413e-06 tokens_per_second_per_gpu:788.892288665353 +Step 7291 | loss:1.997974157333374 lr:4.590255120194409e-06 tokens_per_second_per_gpu:793.621740293504 +Step 7292 | loss:2.02838134765625 lr:4.57847774337462e-06 tokens_per_second_per_gpu:786.4306214705015 +Step 7293 | loss:2.045884370803833 lr:4.566715140790567e-06 tokens_per_second_per_gpu:756.3345403429211 +Step 7294 | loss:1.9331612586975098 lr:4.554967314263436e-06 tokens_per_second_per_gpu:738.2384778478028 +Step 7295 | loss:2.068338394165039 lr:4.543234265612151e-06 tokens_per_second_per_gpu:754.6441023446512 +Step 7296 | loss:2.05515718460083 lr:4.531515996653413e-06 tokens_per_second_per_gpu:759.5408667447502 +Step 7297 | loss:2.008368492126465 lr:4.519812509201527e-06 tokens_per_second_per_gpu:768.7688531459484 +Step 7298 | loss:2.009507179260254 lr:4.508123805068565e-06 tokens_per_second_per_gpu:740.2054254714087 +Step 7299 | loss:1.9948787689208984 lr:4.496449886064335e-06 tokens_per_second_per_gpu:795.4998975104453 +Step 7300 | loss:1.933646321296692 lr:4.4847907539962705e-06 tokens_per_second_per_gpu:772.1785247676327 +Step 7301 | loss:2.0358214378356934 lr:4.473146410669615e-06 tokens_per_second_per_gpu:773.6889671939015 +Step 7302 | loss:1.9734766483306885 lr:4.461516857887271e-06 tokens_per_second_per_gpu:781.9094806852794 +Step 7303 | loss:2.0655009746551514 lr:4.449902097449843e-06 tokens_per_second_per_gpu:767.0397353917673 +Step 7304 | loss:1.9925565719604492 lr:4.438302131155658e-06 tokens_per_second_per_gpu:756.7019067466141 +Step 7305 | loss:1.9635697603225708 lr:4.42671696080077e-06 tokens_per_second_per_gpu:773.3233416214891 +Step 7306 | loss:1.9945558309555054 lr:4.415146588178909e-06 tokens_per_second_per_gpu:748.8248226378469 +Step 7307 | loss:1.9714760780334473 lr:4.403591015081532e-06 tokens_per_second_per_gpu:785.2633768593937 +Step 7308 | loss:1.9731507301330566 lr:4.392050243297829e-06 tokens_per_second_per_gpu:769.4645773912886 +Step 7309 | loss:2.0220179557800293 lr:4.380524274614639e-06 tokens_per_second_per_gpu:782.7450163178808 +Step 7310 | loss:2.013700246810913 lr:4.369013110816555e-06 tokens_per_second_per_gpu:759.7235666597802 +Step 7311 | loss:1.9961893558502197 lr:4.357516753685864e-06 tokens_per_second_per_gpu:777.892633804487 +Step 7312 | loss:2.061678409576416 lr:4.346035205002563e-06 tokens_per_second_per_gpu:768.5561197105542 +Step 7313 | loss:2.0000624656677246 lr:4.334568466544364e-06 tokens_per_second_per_gpu:769.4312636309303 +Step 7314 | loss:2.0321474075317383 lr:4.323116540086669e-06 tokens_per_second_per_gpu:780.9274204654438 +Step 7315 | loss:2.0079567432403564 lr:4.311679427402582e-06 tokens_per_second_per_gpu:775.0798075169472 +Step 7316 | loss:2.0125741958618164 lr:4.300257130262941e-06 tokens_per_second_per_gpu:772.3895839823244 +Step 7317 | loss:1.9649676084518433 lr:4.288849650436267e-06 tokens_per_second_per_gpu:777.5349109652717 +Step 7318 | loss:1.9178459644317627 lr:4.277456989688799e-06 tokens_per_second_per_gpu:773.2853223793647 +Step 7319 | loss:1.940294861793518 lr:4.266079149784475e-06 tokens_per_second_per_gpu:778.038044152911 +Step 7320 | loss:2.032172203063965 lr:4.254716132484959e-06 tokens_per_second_per_gpu:796.6610764551152 +Step 7321 | loss:1.9667400121688843 lr:4.243367939549558e-06 tokens_per_second_per_gpu:774.9076129716931 +Step 7322 | loss:1.946351408958435 lr:4.232034572735355e-06 tokens_per_second_per_gpu:750.5736922270397 +Step 7323 | loss:2.024477005004883 lr:4.220716033797134e-06 tokens_per_second_per_gpu:768.2145393844762 +Step 7324 | loss:1.9429513216018677 lr:4.209412324487316e-06 tokens_per_second_per_gpu:785.710125560674 +Step 7325 | loss:1.9820044040679932 lr:4.198123446556079e-06 tokens_per_second_per_gpu:760.9987062008445 +Step 7326 | loss:1.9822664260864258 lr:4.186849401751325e-06 tokens_per_second_per_gpu:774.9637428256899 +Step 7327 | loss:2.021305561065674 lr:4.175590191818568e-06 tokens_per_second_per_gpu:737.7464169232336 +Step 7328 | loss:2.063725233078003 lr:4.164345818501136e-06 tokens_per_second_per_gpu:727.8273958565733 +Step 7329 | loss:1.9762516021728516 lr:4.153116283540015e-06 tokens_per_second_per_gpu:769.6239396020411 +Step 7330 | loss:2.018350839614868 lr:4.141901588673857e-06 tokens_per_second_per_gpu:773.8488478623873 +Step 7331 | loss:2.0512709617614746 lr:4.1307017356390535e-06 tokens_per_second_per_gpu:759.6893148254189 +Step 7332 | loss:1.9921354055404663 lr:4.119516726169703e-06 tokens_per_second_per_gpu:743.5939726426757 +Step 7333 | loss:2.0233237743377686 lr:4.108346561997589e-06 tokens_per_second_per_gpu:737.2728704823794 +Step 7334 | loss:1.980358362197876 lr:4.097191244852194e-06 tokens_per_second_per_gpu:796.5974644325678 +Step 7335 | loss:1.9851984977722168 lr:4.086050776460748e-06 tokens_per_second_per_gpu:778.0547754221594 +Step 7336 | loss:2.018294334411621 lr:4.074925158548093e-06 tokens_per_second_per_gpu:760.5760695619693 +Step 7337 | loss:2.026059865951538 lr:4.06381439283684e-06 tokens_per_second_per_gpu:787.5267501829474 +Step 7338 | loss:1.9664161205291748 lr:4.0527184810472905e-06 tokens_per_second_per_gpu:763.3081994356403 +Step 7339 | loss:2.023540735244751 lr:4.041637424897438e-06 tokens_per_second_per_gpu:777.6910391499129 +Step 7340 | loss:2.0692410469055176 lr:4.030571226102975e-06 tokens_per_second_per_gpu:786.9433969449731 +Step 7341 | loss:2.0965585708618164 lr:4.01951988637731e-06 tokens_per_second_per_gpu:753.5342514042017 +Step 7342 | loss:2.0182008743286133 lr:4.008483407431496e-06 tokens_per_second_per_gpu:761.738435837399 +Step 7343 | loss:2.035490036010742 lr:3.997461790974355e-06 tokens_per_second_per_gpu:775.0231705173821 +Step 7344 | loss:2.0219130516052246 lr:3.986455038712378e-06 tokens_per_second_per_gpu:772.8682696472712 +Step 7345 | loss:2.019381046295166 lr:3.9754631523497455e-06 tokens_per_second_per_gpu:783.516752165523 +Step 7346 | loss:2.02386474609375 lr:3.964486133588341e-06 tokens_per_second_per_gpu:788.0605988785805 +Step 7347 | loss:1.9867039918899536 lr:3.953523984127783e-06 tokens_per_second_per_gpu:771.8899425948791 +Step 7348 | loss:1.9970704317092896 lr:3.942576705665291e-06 tokens_per_second_per_gpu:762.1501973215363 +Step 7349 | loss:2.003838062286377 lr:3.931644299895909e-06 tokens_per_second_per_gpu:768.6758356435753 +Step 7350 | loss:2.062309503555298 lr:3.920726768512295e-06 tokens_per_second_per_gpu:783.3792843165081 +Step 7351 | loss:1.9942973852157593 lr:3.909824113204807e-06 tokens_per_second_per_gpu:776.3978346259189 +Step 7352 | loss:1.972722053527832 lr:3.898936335661541e-06 tokens_per_second_per_gpu:766.2318266212368 +Step 7353 | loss:2.083559989929199 lr:3.888063437568257e-06 tokens_per_second_per_gpu:791.6006487912396 +Step 7354 | loss:2.0100865364074707 lr:3.877205420608399e-06 tokens_per_second_per_gpu:801.4731172368234 +Step 7355 | loss:1.9958442449569702 lr:3.866362286463154e-06 tokens_per_second_per_gpu:765.7384141596448 +Step 7356 | loss:1.9985735416412354 lr:3.855534036811392e-06 tokens_per_second_per_gpu:760.6746469253529 +Step 7357 | loss:1.9933018684387207 lr:3.844720673329616e-06 tokens_per_second_per_gpu:783.397082996034 +Step 7358 | loss:2.0834293365478516 lr:3.833922197692108e-06 tokens_per_second_per_gpu:788.1735013687008 +Step 7359 | loss:1.958237648010254 lr:3.823138611570798e-06 tokens_per_second_per_gpu:785.0286159424123 +Step 7360 | loss:2.0213003158569336 lr:3.812369916635328e-06 tokens_per_second_per_gpu:778.9534933214261 +Step 7361 | loss:1.9581736326217651 lr:3.8016161145530303e-06 tokens_per_second_per_gpu:750.0590364418707 +Step 7362 | loss:1.975293517112732 lr:3.7908772069889407e-06 tokens_per_second_per_gpu:786.5428539073714 +Step 7363 | loss:2.0234127044677734 lr:3.78015319560574e-06 tokens_per_second_per_gpu:770.6768552910535 +Step 7364 | loss:2.0355374813079834 lr:3.7694440820638776e-06 tokens_per_second_per_gpu:737.6294537336996 +Step 7365 | loss:1.9989383220672607 lr:3.758749868021427e-06 tokens_per_second_per_gpu:786.3817188030332 +Step 7366 | loss:1.9414576292037964 lr:3.7480705551342198e-06 tokens_per_second_per_gpu:767.3984400380741 +Step 7367 | loss:2.026183843612671 lr:3.737406145055733e-06 tokens_per_second_per_gpu:749.5495699906214 +Step 7368 | loss:2.035489797592163 lr:3.7267566394371567e-06 tokens_per_second_per_gpu:756.4746235245528 +Step 7369 | loss:1.9889189004898071 lr:3.7161220399273498e-06 tokens_per_second_per_gpu:786.2458198227587 +Step 7370 | loss:2.0207691192626953 lr:3.7055023481728955e-06 tokens_per_second_per_gpu:794.1705217085909 +Step 7371 | loss:2.017819881439209 lr:3.6948975658180563e-06 tokens_per_second_per_gpu:781.1993177692468 +Step 7372 | loss:2.0405526161193848 lr:3.684307694504774e-06 tokens_per_second_per_gpu:783.680720831717 +Step 7373 | loss:2.020339250564575 lr:3.6737327358726925e-06 tokens_per_second_per_gpu:747.1663078757346 +Step 7374 | loss:2.0304200649261475 lr:3.6631726915591693e-06 tokens_per_second_per_gpu:776.7604154362159 +Step 7375 | loss:2.036290407180786 lr:3.6526275631991846e-06 tokens_per_second_per_gpu:770.3570573434076 +Step 7376 | loss:2.047093152999878 lr:3.6420973524254998e-06 tokens_per_second_per_gpu:790.8927079152733 +Step 7377 | loss:1.9972774982452393 lr:3.631582060868499e-06 tokens_per_second_per_gpu:731.3039437126115 +Step 7378 | loss:1.9602445363998413 lr:3.6210816901562803e-06 tokens_per_second_per_gpu:772.6703429749577 +Step 7379 | loss:2.036522388458252 lr:3.610596241914621e-06 tokens_per_second_per_gpu:792.5290666335536 +Step 7380 | loss:2.0007855892181396 lr:3.6001257177670113e-06 tokens_per_second_per_gpu:782.1424084359527 +Step 7381 | loss:2.0597314834594727 lr:3.589670119334609e-06 tokens_per_second_per_gpu:782.4652434895203 +Step 7382 | loss:2.04866361618042 lr:3.5792294482362655e-06 tokens_per_second_per_gpu:762.4500521217842 +Step 7383 | loss:2.0080301761627197 lr:3.5688037060885413e-06 tokens_per_second_per_gpu:698.223495548702 +Step 7384 | loss:1.979656457901001 lr:3.5583928945056464e-06 tokens_per_second_per_gpu:787.4822849984017 +Step 7385 | loss:2.0158753395080566 lr:3.5479970150994913e-06 tokens_per_second_per_gpu:756.7731682479498 +Step 7386 | loss:2.0505528450012207 lr:3.53761606947971e-06 tokens_per_second_per_gpu:793.4112753306813 +Step 7387 | loss:2.027890205383301 lr:3.5272500592535727e-06 tokens_per_second_per_gpu:780.7054869111909 +Step 7388 | loss:2.1026272773742676 lr:3.516898986026085e-06 tokens_per_second_per_gpu:772.0946516844592 +Step 7389 | loss:2.0053911209106445 lr:3.5065628513999195e-06 tokens_per_second_per_gpu:736.0158857323511 +Step 7390 | loss:2.004746437072754 lr:3.4962416569753966e-06 tokens_per_second_per_gpu:796.1818043828999 +Step 7391 | loss:1.9836328029632568 lr:3.4859354043505933e-06 tokens_per_second_per_gpu:766.2627554465352 +Step 7392 | loss:2.040997266769409 lr:3.475644095121222e-06 tokens_per_second_per_gpu:781.4951237366815 +Step 7393 | loss:1.9755842685699463 lr:3.465367730880709e-06 tokens_per_second_per_gpu:788.7345081030755 +Step 7394 | loss:1.9699958562850952 lr:3.455106313220158e-06 tokens_per_second_per_gpu:777.9733394021615 +Step 7395 | loss:1.953070044517517 lr:3.4448598437283653e-06 tokens_per_second_per_gpu:764.6354292592276 +Step 7396 | loss:1.977473497390747 lr:3.434628323991773e-06 tokens_per_second_per_gpu:760.591758212193 +Step 7397 | loss:1.9467136859893799 lr:3.42441175559457e-06 tokens_per_second_per_gpu:761.9328294585644 +Step 7398 | loss:1.983994960784912 lr:3.41421014011859e-06 tokens_per_second_per_gpu:767.7845081053587 +Step 7399 | loss:2.0613179206848145 lr:3.40402347914337e-06 tokens_per_second_per_gpu:755.1129336944691 +Step 7400 | loss:2.0253758430480957 lr:3.393851774246104e-06 tokens_per_second_per_gpu:744.8291801824182 +Step 7401 | loss:2.014375925064087 lr:3.383695027001721e-06 tokens_per_second_per_gpu:762.9690508958881 +Step 7402 | loss:2.0065393447875977 lr:3.373553238982763e-06 tokens_per_second_per_gpu:744.8315631145463 +Step 7403 | loss:1.969127893447876 lr:3.3634264117595294e-06 tokens_per_second_per_gpu:769.5544336831974 +Step 7404 | loss:1.9388865232467651 lr:3.353314546899966e-06 tokens_per_second_per_gpu:737.0439720664651 +Step 7405 | loss:2.0044169425964355 lr:3.3432176459696985e-06 tokens_per_second_per_gpu:737.5616320055371 +Step 7406 | loss:1.9791626930236816 lr:3.3331357105320316e-06 tokens_per_second_per_gpu:761.8719897096482 +Step 7407 | loss:1.9962260723114014 lr:3.3230687421479833e-06 tokens_per_second_per_gpu:777.7180790425442 +Step 7408 | loss:2.0260565280914307 lr:3.313016742376218e-06 tokens_per_second_per_gpu:783.5575894325509 +Step 7409 | loss:2.037773609161377 lr:3.3029797127731133e-06 tokens_per_second_per_gpu:781.8464958623586 +Step 7410 | loss:1.9649032354354858 lr:3.2929576548927253e-06 tokens_per_second_per_gpu:759.182643163758 +Step 7411 | loss:1.9181090593338013 lr:3.2829505702867467e-06 tokens_per_second_per_gpu:794.0986970298968 +Step 7412 | loss:1.9321037530899048 lr:3.272958460504616e-06 tokens_per_second_per_gpu:765.285075715315 +Step 7413 | loss:2.0937604904174805 lr:3.262981327093417e-06 tokens_per_second_per_gpu:791.8119235654221 +Step 7414 | loss:2.0554027557373047 lr:3.2530191715979153e-06 tokens_per_second_per_gpu:769.5447753718013 +Step 7415 | loss:1.989891529083252 lr:3.243071995560576e-06 tokens_per_second_per_gpu:796.1907372472451 +Step 7416 | loss:1.9637441635131836 lr:3.2331398005215342e-06 tokens_per_second_per_gpu:759.1927965263485 +Step 7417 | loss:1.9977259635925293 lr:3.223222588018582e-06 tokens_per_second_per_gpu:791.8951256358093 +Step 7418 | loss:2.032991409301758 lr:3.2133203595872353e-06 tokens_per_second_per_gpu:759.5413579904337 +Step 7419 | loss:2.0086653232574463 lr:3.2034331167606567e-06 tokens_per_second_per_gpu:749.5775226745484 +Step 7420 | loss:1.9853577613830566 lr:3.193560861069711e-06 tokens_per_second_per_gpu:776.310095770246 +Step 7421 | loss:2.005660057067871 lr:3.1837035940429304e-06 tokens_per_second_per_gpu:751.0304030576079 +Step 7422 | loss:2.0456717014312744 lr:3.1738613172065278e-06 tokens_per_second_per_gpu:760.018235953772 +Step 7423 | loss:1.981675148010254 lr:3.1640340320843733e-06 tokens_per_second_per_gpu:763.3710705711816 +Step 7424 | loss:2.076457977294922 lr:3.1542217401980824e-06 tokens_per_second_per_gpu:773.1617138296687 +Step 7425 | loss:1.9421404600143433 lr:3.1444244430668734e-06 tokens_per_second_per_gpu:781.5403037501778 +Step 7426 | loss:2.0194156169891357 lr:3.1346421422076664e-06 tokens_per_second_per_gpu:772.5655791065146 +Step 7427 | loss:2.013612985610962 lr:3.124874839135095e-06 tokens_per_second_per_gpu:772.3090548403259 +Step 7428 | loss:1.9997751712799072 lr:3.1151225353614367e-06 tokens_per_second_per_gpu:778.9669395888192 +Step 7429 | loss:2.0694847106933594 lr:3.1053852323966293e-06 tokens_per_second_per_gpu:772.7863561105537 +Step 7430 | loss:2.0401670932769775 lr:3.095662931748333e-06 tokens_per_second_per_gpu:777.0764896161679 +Step 7431 | loss:2.032100200653076 lr:3.0859556349218666e-06 tokens_per_second_per_gpu:785.2968998471237 +Step 7432 | loss:2.0638654232025146 lr:3.076263343420216e-06 tokens_per_second_per_gpu:776.5864378462263 +Step 7433 | loss:2.006328582763672 lr:3.0665860587440478e-06 tokens_per_second_per_gpu:771.3272576672805 +Step 7434 | loss:2.001816511154175 lr:3.0569237823917074e-06 tokens_per_second_per_gpu:779.0322227985041 +Step 7435 | loss:1.9990638494491577 lr:3.047276515859232e-06 tokens_per_second_per_gpu:759.7672344440085 +Step 7436 | loss:1.9385446310043335 lr:3.0376442606403044e-06 tokens_per_second_per_gpu:775.0948431947118 +Step 7437 | loss:2.0185437202453613 lr:3.0280270182263094e-06 tokens_per_second_per_gpu:747.0803145766936 +Step 7438 | loss:2.01312255859375 lr:3.0184247901062888e-06 tokens_per_second_per_gpu:773.5828180258645 +Step 7439 | loss:2.0306832790374756 lr:3.008837577766965e-06 tokens_per_second_per_gpu:758.7975187404214 +Step 7440 | loss:2.032320737838745 lr:2.9992653826927508e-06 tokens_per_second_per_gpu:793.6781159811808 +Step 7441 | loss:1.9445527791976929 lr:2.9897082063657156e-06 tokens_per_second_per_gpu:788.0691431528705 +Step 7442 | loss:2.0005452632904053 lr:2.9801660502656094e-06 tokens_per_second_per_gpu:760.6581968386892 +Step 7443 | loss:2.000931739807129 lr:2.970638915869861e-06 tokens_per_second_per_gpu:780.152777678313 +Step 7444 | loss:2.022371768951416 lr:2.9611268046535466e-06 tokens_per_second_per_gpu:794.4833723407218 +Step 7445 | loss:2.057021379470825 lr:2.951629718089466e-06 tokens_per_second_per_gpu:799.9658398326887 +Step 7446 | loss:2.0698671340942383 lr:2.942147657648053e-06 tokens_per_second_per_gpu:726.9146783824905 +Step 7447 | loss:2.040440797805786 lr:2.932680624797424e-06 tokens_per_second_per_gpu:761.5130518682154 +Step 7448 | loss:1.976271390914917 lr:2.923228621003382e-06 tokens_per_second_per_gpu:770.1333746342135 +Step 7449 | loss:1.9775021076202393 lr:2.9137916477293913e-06 tokens_per_second_per_gpu:782.1713439102464 +Step 7450 | loss:1.9934043884277344 lr:2.9043697064365715e-06 tokens_per_second_per_gpu:792.6257535650881 +Step 7451 | loss:2.013920783996582 lr:2.894962798583756e-06 tokens_per_second_per_gpu:770.3543421144179 +Step 7452 | loss:1.9730241298675537 lr:2.8855709256274234e-06 tokens_per_second_per_gpu:786.2329404988101 +Step 7453 | loss:2.0493197441101074 lr:2.876194089021722e-06 tokens_per_second_per_gpu:783.2977190950074 +Step 7454 | loss:2.023566246032715 lr:2.8668322902184907e-06 tokens_per_second_per_gpu:780.4588822493225 +Step 7455 | loss:1.9839003086090088 lr:2.8574855306672256e-06 tokens_per_second_per_gpu:732.5491455294186 +Step 7456 | loss:1.9593572616577148 lr:2.8481538118150684e-06 tokens_per_second_per_gpu:745.2814066825541 +Step 7457 | loss:1.966239094734192 lr:2.8388371351069086e-06 tokens_per_second_per_gpu:775.3521935133097 +Step 7458 | loss:1.940438151359558 lr:2.8295355019852366e-06 tokens_per_second_per_gpu:751.2038852053518 +Step 7459 | loss:1.9412789344787598 lr:2.8202489138902333e-06 tokens_per_second_per_gpu:776.7282250608866 +Step 7460 | loss:2.0942790508270264 lr:2.810977372259749e-06 tokens_per_second_per_gpu:765.2419485100154 +Step 7461 | loss:1.939276099205017 lr:2.8017208785293235e-06 tokens_per_second_per_gpu:772.8607212559507 +Step 7462 | loss:2.009223461151123 lr:2.792479434132134e-06 tokens_per_second_per_gpu:783.2089941305564 +Step 7463 | loss:1.9618762731552124 lr:2.7832530404990566e-06 tokens_per_second_per_gpu:786.5650954477185 +Step 7464 | loss:2.0429365634918213 lr:2.774041699058638e-06 tokens_per_second_per_gpu:785.5252949459397 +Step 7465 | loss:2.0064139366149902 lr:2.7648454112370602e-06 tokens_per_second_per_gpu:768.2765272634451 +Step 7466 | loss:1.991400122642517 lr:2.755664178458195e-06 tokens_per_second_per_gpu:772.9678685916831 +Step 7467 | loss:1.9772663116455078 lr:2.7464980021435937e-06 tokens_per_second_per_gpu:790.5880912735894 +Step 7468 | loss:2.0243237018585205 lr:2.737346883712466e-06 tokens_per_second_per_gpu:781.1183441088334 +Step 7469 | loss:1.963975191116333 lr:2.7282108245817006e-06 tokens_per_second_per_gpu:794.8276453065874 +Step 7470 | loss:2.015596389770508 lr:2.7190898261658326e-06 tokens_per_second_per_gpu:791.3520373165449 +Step 7471 | loss:1.9681825637817383 lr:2.709983889877077e-06 tokens_per_second_per_gpu:774.2751217850027 +Step 7472 | loss:1.9808549880981445 lr:2.7008930171253277e-06 tokens_per_second_per_gpu:769.6841331128535 +Step 7473 | loss:2.036280393600464 lr:2.691817209318126e-06 tokens_per_second_per_gpu:763.4839361674997 +Step 7474 | loss:2.035263776779175 lr:2.682756467860692e-06 tokens_per_second_per_gpu:797.2580376534453 +Step 7475 | loss:2.025712728500366 lr:2.673710794155915e-06 tokens_per_second_per_gpu:776.5668271275543 +Step 7476 | loss:2.003296375274658 lr:2.6646801896043518e-06 tokens_per_second_per_gpu:774.9365672288986 +Step 7477 | loss:2.0145463943481445 lr:2.6556646556042064e-06 tokens_per_second_per_gpu:771.7169796702989 +Step 7478 | loss:1.987589716911316 lr:2.646664193551396e-06 tokens_per_second_per_gpu:770.0160576066143 +Step 7479 | loss:2.00531268119812 lr:2.6376788048394384e-06 tokens_per_second_per_gpu:745.6138224554634 +Step 7480 | loss:1.9765334129333496 lr:2.628708490859577e-06 tokens_per_second_per_gpu:787.9667288337821 +Step 7481 | loss:1.9993724822998047 lr:2.6197532530006785e-06 tokens_per_second_per_gpu:760.4345152146615 +Step 7482 | loss:2.0002479553222656 lr:2.6108130926493114e-06 tokens_per_second_per_gpu:780.4656250430035 +Step 7483 | loss:2.01759672164917 lr:2.6018880111896903e-06 tokens_per_second_per_gpu:762.8645404974994 +Step 7484 | loss:2.101325273513794 lr:2.592978010003688e-06 tokens_per_second_per_gpu:772.3141757359933 +Step 7485 | loss:1.9586230516433716 lr:2.584083090470857e-06 tokens_per_second_per_gpu:786.1933449879643 +Step 7486 | loss:1.9983105659484863 lr:2.5752032539684058e-06 tokens_per_second_per_gpu:768.2336749915416 +Step 7487 | loss:1.9731372594833374 lr:2.566338501871213e-06 tokens_per_second_per_gpu:782.0027148581737 +Step 7488 | loss:2.0531210899353027 lr:2.5574888355518135e-06 tokens_per_second_per_gpu:769.8331211460195 +Step 7489 | loss:1.9844768047332764 lr:2.5486542563804117e-06 tokens_per_second_per_gpu:772.707314358673 +Step 7490 | loss:1.9955472946166992 lr:2.5398347657248912e-06 tokens_per_second_per_gpu:763.0606836506275 +Step 7491 | loss:2.029865026473999 lr:2.531030364950782e-06 tokens_per_second_per_gpu:770.4660820812152 +Step 7492 | loss:2.017573356628418 lr:2.5222410554212707e-06 tokens_per_second_per_gpu:748.3284032464354 +Step 7493 | loss:1.962221622467041 lr:2.5134668384972138e-06 tokens_per_second_per_gpu:773.7828957743075 +Step 7494 | loss:1.975932002067566 lr:2.504707715537147e-06 tokens_per_second_per_gpu:785.7403053305023 +Step 7495 | loss:1.945352554321289 lr:2.4959636878972514e-06 tokens_per_second_per_gpu:769.007878480003 +Step 7496 | loss:2.0507328510284424 lr:2.487234756931378e-06 tokens_per_second_per_gpu:780.8129119034554 +Step 7497 | loss:2.0316033363342285 lr:2.4785209239910458e-06 tokens_per_second_per_gpu:789.6321054646692 +Step 7498 | loss:2.0638298988342285 lr:2.469822190425397e-06 tokens_per_second_per_gpu:772.7512340959263 +Step 7499 | loss:2.0510289669036865 lr:2.4611385575813107e-06 tokens_per_second_per_gpu:775.3706836327842 +Step 7500 | loss:2.0550906658172607 lr:2.452470026803244e-06 tokens_per_second_per_gpu:785.8230659411518 +Step 7501 | loss:1.9810965061187744 lr:2.4438165994333907e-06 tokens_per_second_per_gpu:781.8426974082322 +Step 7502 | loss:2.043396472930908 lr:2.435178276811556e-06 tokens_per_second_per_gpu:758.5920724369093 +Step 7503 | loss:2.005903482437134 lr:2.4265550602752262e-06 tokens_per_second_per_gpu:745.3136926423296 +Step 7504 | loss:2.0197510719299316 lr:2.417946951159522e-06 tokens_per_second_per_gpu:758.524182796652 +Step 7505 | loss:2.0042896270751953 lr:2.4093539507972996e-06 tokens_per_second_per_gpu:777.3789518679088 +Step 7506 | loss:2.0308806896209717 lr:2.4007760605189724e-06 tokens_per_second_per_gpu:795.484213127166 +Step 7507 | loss:2.0631251335144043 lr:2.392213281652689e-06 tokens_per_second_per_gpu:723.1055704391898 +Step 7508 | loss:1.9880952835083008 lr:2.3836656155242444e-06 tokens_per_second_per_gpu:772.7462031362313 +Step 7509 | loss:2.0253593921661377 lr:2.375133063457058e-06 tokens_per_second_per_gpu:776.642619566218 +Step 7510 | loss:1.9318697452545166 lr:2.3666156267722616e-06 tokens_per_second_per_gpu:780.9480634551082 +Step 7511 | loss:1.971692442893982 lr:2.358113306788601e-06 tokens_per_second_per_gpu:764.9272979983263 +Step 7512 | loss:2.0091562271118164 lr:2.349626104822533e-06 tokens_per_second_per_gpu:790.2221587434813 +Step 7513 | loss:1.9822226762771606 lr:2.341154022188097e-06 tokens_per_second_per_gpu:768.1446152092931 +Step 7514 | loss:1.963811993598938 lr:2.3326970601970644e-06 tokens_per_second_per_gpu:750.0335658466779 +Step 7515 | loss:2.0123066902160645 lr:2.324255220158833e-06 tokens_per_second_per_gpu:748.086511257955 +Step 7516 | loss:2.012319803237915 lr:2.3158285033804682e-06 tokens_per_second_per_gpu:777.442812642203 +Step 7517 | loss:2.0012478828430176 lr:2.307416911166671e-06 tokens_per_second_per_gpu:732.9320997360019 +Step 7518 | loss:2.0403478145599365 lr:2.299020444819844e-06 tokens_per_second_per_gpu:766.458618572704 +Step 7519 | loss:2.021289110183716 lr:2.2906391056400024e-06 tokens_per_second_per_gpu:772.8423031633845 +Step 7520 | loss:2.0123462677001953 lr:2.2822728949248527e-06 tokens_per_second_per_gpu:774.0967054063923 +Step 7521 | loss:1.9915767908096313 lr:2.2739218139697373e-06 tokens_per_second_per_gpu:747.2572110082052 +Step 7522 | loss:2.016561508178711 lr:2.265585864067665e-06 tokens_per_second_per_gpu:780.9940697735395 +Step 7523 | loss:1.9787005186080933 lr:2.257265046509305e-06 tokens_per_second_per_gpu:789.9779622858649 +Step 7524 | loss:1.9697282314300537 lr:2.2489593625829918e-06 tokens_per_second_per_gpu:761.3779999066409 +Step 7525 | loss:2.0077857971191406 lr:2.2406688135746757e-06 tokens_per_second_per_gpu:785.0430481215217 +Step 7526 | loss:2.045292854309082 lr:2.232393400768018e-06 tokens_per_second_per_gpu:758.145564922287 +Step 7527 | loss:2.0324594974517822 lr:2.2241331254443054e-06 tokens_per_second_per_gpu:746.4640246054577 +Step 7528 | loss:1.9565057754516602 lr:2.215887988882481e-06 tokens_per_second_per_gpu:763.3715586495329 +Step 7529 | loss:1.9821064472198486 lr:2.2076579923591578e-06 tokens_per_second_per_gpu:785.4946025872506 +Step 7530 | loss:1.9984371662139893 lr:2.1994431371485935e-06 tokens_per_second_per_gpu:771.1710971078331 +Step 7531 | loss:2.008004665374756 lr:2.1912434245226933e-06 tokens_per_second_per_gpu:766.0521961343384 +Step 7532 | loss:2.012878894805908 lr:2.183058855751052e-06 tokens_per_second_per_gpu:788.4698177533381 +Step 7533 | loss:1.9772365093231201 lr:2.1748894321008794e-06 tokens_per_second_per_gpu:777.976923603263 +Step 7534 | loss:2.0203425884246826 lr:2.1667351548370517e-06 tokens_per_second_per_gpu:787.5261519756648 +Step 7535 | loss:1.968733310699463 lr:2.158596025222126e-06 tokens_per_second_per_gpu:786.6989946510089 +Step 7536 | loss:2.054955244064331 lr:2.150472044516294e-06 tokens_per_second_per_gpu:791.3142794590215 +Step 7537 | loss:2.028480052947998 lr:2.142363213977383e-06 tokens_per_second_per_gpu:764.5326617235634 +Step 7538 | loss:1.9922641515731812 lr:2.1342695348609e-06 tokens_per_second_per_gpu:788.9533502146297 +Step 7539 | loss:1.9916911125183105 lr:2.12619100842002e-06 tokens_per_second_per_gpu:791.0259210614378 +Step 7540 | loss:2.045119285583496 lr:2.1181276359055202e-06 tokens_per_second_per_gpu:792.8362381073604 +Step 7541 | loss:2.0058298110961914 lr:2.1100794185658803e-06 tokens_per_second_per_gpu:763.8130705379631 +Step 7542 | loss:1.987098217010498 lr:2.102046357647214e-06 tokens_per_second_per_gpu:794.7479093432969 +Step 7543 | loss:2.033700704574585 lr:2.094028454393282e-06 tokens_per_second_per_gpu:781.1120807885322 +Step 7544 | loss:2.0560860633850098 lr:2.086025710045525e-06 tokens_per_second_per_gpu:741.0143443504855 +Step 7545 | loss:1.987607479095459 lr:2.078038125843007e-06 tokens_per_second_per_gpu:767.7855783224385 +Step 7546 | loss:2.052377939224243 lr:2.0700657030224503e-06 tokens_per_second_per_gpu:721.2108830526789 +Step 7547 | loss:1.9906432628631592 lr:2.0621084428182445e-06 tokens_per_second_per_gpu:764.3097680708134 +Step 7548 | loss:1.9889553785324097 lr:2.0541663464624163e-06 tokens_per_second_per_gpu:792.2192574043897 +Step 7549 | loss:2.045361280441284 lr:2.0462394151846476e-06 tokens_per_second_per_gpu:795.161572092939 +Step 7550 | loss:1.9936785697937012 lr:2.0383276502122793e-06 tokens_per_second_per_gpu:749.3266244493436 +Step 7551 | loss:1.9677784442901611 lr:2.0304310527703206e-06 tokens_per_second_per_gpu:782.2164735060459 +Step 7552 | loss:2.0412755012512207 lr:2.022549624081371e-06 tokens_per_second_per_gpu:759.8936061005298 +Step 7553 | loss:1.986876130104065 lr:2.014683365365755e-06 tokens_per_second_per_gpu:785.3892466330784 +Step 7554 | loss:1.9742023944854736 lr:2.0068322778414083e-06 tokens_per_second_per_gpu:785.6247667006104 +Step 7555 | loss:2.0703184604644775 lr:1.998996362723904e-06 tokens_per_second_per_gpu:800.3497987293879 +Step 7556 | loss:1.9679597616195679 lr:1.9911756212265153e-06 tokens_per_second_per_gpu:765.0915689194162 +Step 7557 | loss:1.9840903282165527 lr:1.9833700545601187e-06 tokens_per_second_per_gpu:780.3414020175927 +Step 7558 | loss:2.0602474212646484 lr:1.975579663933269e-06 tokens_per_second_per_gpu:762.3326320265095 +Step 7559 | loss:1.9759172201156616 lr:1.967804450552169e-06 tokens_per_second_per_gpu:771.7300573653706 +Step 7560 | loss:2.041130304336548 lr:1.9600444156206542e-06 tokens_per_second_per_gpu:765.3637523907507 +Step 7561 | loss:1.974281668663025 lr:1.9522995603402205e-06 tokens_per_second_per_gpu:765.4834861572438 +Step 7562 | loss:1.9757550954818726 lr:1.944569885910008e-06 tokens_per_second_per_gpu:751.4969921819896 +Step 7563 | loss:2.05442476272583 lr:1.9368553935268264e-06 tokens_per_second_per_gpu:783.7215491024931 +Step 7564 | loss:1.9935674667358398 lr:1.9291560843851086e-06 tokens_per_second_per_gpu:764.34357042141 +Step 7565 | loss:2.0110366344451904 lr:1.921471959676957e-06 tokens_per_second_per_gpu:779.5621014383147 +Step 7566 | loss:2.016216278076172 lr:1.91380302059212e-06 tokens_per_second_per_gpu:786.0947354909341 +Step 7567 | loss:2.029914379119873 lr:1.9061492683179694e-06 tokens_per_second_per_gpu:784.7664366797229 +Step 7568 | loss:1.989902377128601 lr:1.8985107040395467e-06 tokens_per_second_per_gpu:768.8902119030604 +Step 7569 | loss:2.04960036277771 lr:1.8908873289395613e-06 tokens_per_second_per_gpu:773.5712629702482 +Step 7570 | loss:2.040684223175049 lr:1.8832791441983355e-06 tokens_per_second_per_gpu:754.411065334326 +Step 7571 | loss:1.9920910596847534 lr:1.8756861509938606e-06 tokens_per_second_per_gpu:758.0577607407365 +Step 7572 | loss:1.967630386352539 lr:1.8681083505017738e-06 tokens_per_second_per_gpu:768.2117143492502 +Step 7573 | loss:1.9917619228363037 lr:1.8605457438953477e-06 tokens_per_second_per_gpu:781.711074230779 +Step 7574 | loss:2.0256035327911377 lr:1.8529983323455013e-06 tokens_per_second_per_gpu:789.7222130909649 +Step 7575 | loss:1.9885013103485107 lr:1.8454661170208222e-06 tokens_per_second_per_gpu:764.244362614833 +Step 7576 | loss:2.0289523601531982 lr:1.8379490990875215e-06 tokens_per_second_per_gpu:773.3291962102329 +Step 7577 | loss:1.9977004528045654 lr:1.8304472797094796e-06 tokens_per_second_per_gpu:766.4354457503357 +Step 7578 | loss:2.020094394683838 lr:1.822960660048223e-06 tokens_per_second_per_gpu:785.2209369990129 +Step 7579 | loss:2.01716685295105 lr:1.815489241262891e-06 tokens_per_second_per_gpu:770.1781804905345 +Step 7580 | loss:2.0302393436431885 lr:1.8080330245103139e-06 tokens_per_second_per_gpu:767.2438956194194 +Step 7581 | loss:2.0624961853027344 lr:1.8005920109449237e-06 tokens_per_second_per_gpu:761.9486566247384 +Step 7582 | loss:1.9998093843460083 lr:1.7931662017188433e-06 tokens_per_second_per_gpu:768.8766744348459 +Step 7583 | loss:1.9288250207901 lr:1.7857555979818085e-06 tokens_per_second_per_gpu:775.1779736850536 +Step 7584 | loss:1.9925806522369385 lr:1.7783602008812239e-06 tokens_per_second_per_gpu:783.591519532517 +Step 7585 | loss:1.9902498722076416 lr:1.7709800115621066e-06 tokens_per_second_per_gpu:767.0084600683427 +Step 7586 | loss:2.012505292892456 lr:1.7636150311671763e-06 tokens_per_second_per_gpu:782.2892072245054 +Step 7587 | loss:2.027808904647827 lr:1.7562652608367313e-06 tokens_per_second_per_gpu:799.5643886371721 +Step 7588 | loss:1.9147871732711792 lr:1.7489307017087508e-06 tokens_per_second_per_gpu:788.7948392753627 +Step 7589 | loss:2.022822856903076 lr:1.7416113549188485e-06 tokens_per_second_per_gpu:759.0279624162936 +Step 7590 | loss:2.002556562423706 lr:1.7343072216003176e-06 tokens_per_second_per_gpu:788.8096805951384 +Step 7591 | loss:2.0651793479919434 lr:1.7270183028840314e-06 tokens_per_second_per_gpu:771.0024321020919 +Step 7592 | loss:2.033186912536621 lr:1.719744599898576e-06 tokens_per_second_per_gpu:761.7078020879882 +Step 7593 | loss:1.9986377954483032 lr:1.7124861137701175e-06 tokens_per_second_per_gpu:797.6302918459058 +Step 7594 | loss:1.9917221069335938 lr:1.7052428456225011e-06 tokens_per_second_per_gpu:766.9056699391128 +Step 7595 | loss:2.0001602172851562 lr:1.6980147965772296e-06 tokens_per_second_per_gpu:764.6736100996359 +Step 7596 | loss:1.9461458921432495 lr:1.6908019677534193e-06 tokens_per_second_per_gpu:750.9568405760017 +Step 7597 | loss:1.970839500427246 lr:1.683604360267843e-06 tokens_per_second_per_gpu:782.9150329344129 +Step 7598 | loss:2.012356758117676 lr:1.6764219752349097e-06 tokens_per_second_per_gpu:725.6267379084918 +Step 7599 | loss:2.0866763591766357 lr:1.6692548137666963e-06 tokens_per_second_per_gpu:759.500012511914 +Step 7600 | loss:1.998495101928711 lr:1.662102876972882e-06 tokens_per_second_per_gpu:762.4809593243402 +Step 7601 | loss:1.987668752670288 lr:1.654966165960825e-06 tokens_per_second_per_gpu:781.3900166312378 +Step 7602 | loss:2.0042812824249268 lr:1.6478446818354975e-06 tokens_per_second_per_gpu:754.478348373656 +Step 7603 | loss:2.0276570320129395 lr:1.6407384256995285e-06 tokens_per_second_per_gpu:776.5488032519255 +Step 7604 | loss:1.975053310394287 lr:1.6336473986532042e-06 tokens_per_second_per_gpu:729.3153996793723 +Step 7605 | loss:2.0677804946899414 lr:1.6265716017944354e-06 tokens_per_second_per_gpu:760.7526890916108 +Step 7606 | loss:1.9632482528686523 lr:1.6195110362187572e-06 tokens_per_second_per_gpu:776.958112041135 +Step 7607 | loss:1.9712551832199097 lr:1.6124657030193835e-06 tokens_per_second_per_gpu:767.1854623119822 +Step 7608 | loss:2.029780626296997 lr:1.605435603287153e-06 tokens_per_second_per_gpu:749.9146665331131 +Step 7609 | loss:2.01544189453125 lr:1.5984207381105288e-06 tokens_per_second_per_gpu:753.7696721410172 +Step 7610 | loss:2.0028858184814453 lr:1.5914211085756415e-06 tokens_per_second_per_gpu:735.4289667720451 +Step 7611 | loss:2.0015668869018555 lr:1.5844367157662577e-06 tokens_per_second_per_gpu:760.7858826068722 +Step 7612 | loss:1.9858049154281616 lr:1.577467560763779e-06 tokens_per_second_per_gpu:773.1609511860148 +Step 7613 | loss:2.032503366470337 lr:1.5705136446472424e-06 tokens_per_second_per_gpu:784.076711825389 +Step 7614 | loss:2.036442518234253 lr:1.563574968493331e-06 tokens_per_second_per_gpu:773.9775395423487 +Step 7615 | loss:2.0173845291137695 lr:1.5566515333763743e-06 tokens_per_second_per_gpu:789.6054896808713 +Step 7616 | loss:2.0394158363342285 lr:1.549743340368337e-06 tokens_per_second_per_gpu:743.3395501653943 +Step 7617 | loss:1.9892578125 lr:1.5428503905388082e-06 tokens_per_second_per_gpu:786.3131744459631 +Step 7618 | loss:2.0001254081726074 lr:1.535972684955056e-06 tokens_per_second_per_gpu:777.7642953356518 +Step 7619 | loss:2.032410144805908 lr:1.529110224681951e-06 tokens_per_second_per_gpu:769.1681968633318 +Step 7620 | loss:2.060642719268799 lr:1.5222630107820214e-06 tokens_per_second_per_gpu:765.6575152257759 +Step 7621 | loss:1.9536633491516113 lr:1.5154310443154184e-06 tokens_per_second_per_gpu:779.593997126166 +Step 7622 | loss:1.949138879776001 lr:1.5086143263399522e-06 tokens_per_second_per_gpu:751.741813112529 +Step 7623 | loss:2.010449171066284 lr:1.5018128579110669e-06 tokens_per_second_per_gpu:793.0655639089853 +Step 7624 | loss:1.9791574478149414 lr:1.4950266400818424e-06 tokens_per_second_per_gpu:777.2438429188217 +Step 7625 | loss:1.9559738636016846 lr:1.4882556739029941e-06 tokens_per_second_per_gpu:759.9180538499445 +Step 7626 | loss:2.038179636001587 lr:1.4814999604228829e-06 tokens_per_second_per_gpu:770.4604443176931 +Step 7627 | loss:1.9935551881790161 lr:1.4747595006874948e-06 tokens_per_second_per_gpu:787.2306755678146 +Step 7628 | loss:2.0022966861724854 lr:1.4680342957404836e-06 tokens_per_second_per_gpu:737.8646062382867 +Step 7629 | loss:1.9787362813949585 lr:1.461324346623094e-06 tokens_per_second_per_gpu:772.9447513066399 +Step 7630 | loss:2.0060768127441406 lr:1.4546296543742622e-06 tokens_per_second_per_gpu:776.8884086388042 +Step 7631 | loss:2.0072314739227295 lr:1.447950220030514e-06 tokens_per_second_per_gpu:784.1287089717135 +Step 7632 | loss:2.0511977672576904 lr:1.4412860446260557e-06 tokens_per_second_per_gpu:769.6536817644386 +Step 7633 | loss:2.0662083625793457 lr:1.434637129192684e-06 tokens_per_second_per_gpu:773.5857388715381 +Step 7634 | loss:2.0501880645751953 lr:1.4280034747598868e-06 tokens_per_second_per_gpu:765.5918957256763 +Step 7635 | loss:2.0074102878570557 lr:1.4213850823547426e-06 tokens_per_second_per_gpu:757.3726946142523 +Step 7636 | loss:1.932565450668335 lr:1.4147819530019978e-06 tokens_per_second_per_gpu:748.6880110044299 +Step 7637 | loss:1.9849674701690674 lr:1.408194087724013e-06 tokens_per_second_per_gpu:775.740002936398 +Step 7638 | loss:2.0707919597625732 lr:1.401621487540794e-06 tokens_per_second_per_gpu:778.5027640442374 +Step 7639 | loss:1.9617271423339844 lr:1.3950641534699937e-06 tokens_per_second_per_gpu:765.2118287361875 +Step 7640 | loss:2.079895496368408 lr:1.3885220865269e-06 tokens_per_second_per_gpu:771.3466394702037 +Step 7641 | loss:2.043853521347046 lr:1.3819952877244135e-06 tokens_per_second_per_gpu:768.1344041988095 +Step 7642 | loss:1.9776781797409058 lr:1.3754837580730928e-06 tokens_per_second_per_gpu:772.8925929326762 +Step 7643 | loss:2.0326082706451416 lr:1.3689874985811202e-06 tokens_per_second_per_gpu:760.4017405143147 +Step 7644 | loss:2.061837673187256 lr:1.3625065102543244e-06 tokens_per_second_per_gpu:771.9413273470316 +Step 7645 | loss:1.9775409698486328 lr:1.3560407940961696e-06 tokens_per_second_per_gpu:771.4071923956587 +Step 7646 | loss:2.0268852710723877 lr:1.3495903511077545e-06 tokens_per_second_per_gpu:791.9895810715462 +Step 7647 | loss:2.012690544128418 lr:1.343155182287792e-06 tokens_per_second_per_gpu:792.5735010077434 +Step 7648 | loss:2.0179834365844727 lr:1.3367352886326622e-06 tokens_per_second_per_gpu:769.0746948603912 +Step 7649 | loss:2.0456905364990234 lr:1.3303306711363594e-06 tokens_per_second_per_gpu:753.1398603706459 +Step 7650 | loss:1.9872546195983887 lr:1.3239413307905125e-06 tokens_per_second_per_gpu:753.4716325513662 +Step 7651 | loss:1.98867666721344 lr:1.3175672685844076e-06 tokens_per_second_per_gpu:779.4703517320792 +Step 7652 | loss:2.012659788131714 lr:1.3112084855049333e-06 tokens_per_second_per_gpu:748.9266025850371 +Step 7653 | loss:1.9993313550949097 lr:1.3048649825366466e-06 tokens_per_second_per_gpu:761.654450153242 +Step 7654 | loss:1.9938088655471802 lr:1.298536760661695e-06 tokens_per_second_per_gpu:764.5716039583424 +Step 7655 | loss:1.9839164018630981 lr:1.2922238208599168e-06 tokens_per_second_per_gpu:779.5558012257106 +Step 7656 | loss:2.00449800491333 lr:1.2859261641087195e-06 tokens_per_second_per_gpu:787.1785613358006 +Step 7657 | loss:2.0321033000946045 lr:1.2796437913832004e-06 tokens_per_second_per_gpu:794.0570590221896 +Step 7658 | loss:1.981825590133667 lr:1.2733767036560484e-06 tokens_per_second_per_gpu:772.9099318476742 +Step 7659 | loss:2.022829294204712 lr:1.2671249018976206e-06 tokens_per_second_per_gpu:765.6920127204406 +Step 7660 | loss:1.99515962600708 lr:1.260888387075887e-06 tokens_per_second_per_gpu:792.549974648234 +Step 7661 | loss:2.043020009994507 lr:1.254667160156453e-06 tokens_per_second_per_gpu:771.4447484779987 +Step 7662 | loss:2.027097225189209 lr:1.2484612221025593e-06 tokens_per_second_per_gpu:757.4938885540142 +Step 7663 | loss:1.979920506477356 lr:1.2422705738750816e-06 tokens_per_second_per_gpu:786.0078228407988 +Step 7664 | loss:2.019540548324585 lr:1.2360952164325311e-06 tokens_per_second_per_gpu:736.4455541104743 +Step 7665 | loss:2.003268241882324 lr:1.2299351507310319e-06 tokens_per_second_per_gpu:766.1085027460236 +Step 7666 | loss:2.0097415447235107 lr:1.2237903777243542e-06 tokens_per_second_per_gpu:739.836440565022 +Step 7667 | loss:2.026320457458496 lr:1.2176608983639258e-06 tokens_per_second_per_gpu:790.5336841633309 +Step 7668 | loss:2.0367624759674072 lr:1.2115467135987546e-06 tokens_per_second_per_gpu:767.8920652893181 +Step 7669 | loss:2.0242905616760254 lr:1.2054478243755274e-06 tokens_per_second_per_gpu:769.5416122108741 +Step 7670 | loss:1.980071783065796 lr:1.1993642316385223e-06 tokens_per_second_per_gpu:750.825061493076 +Step 7671 | loss:2.002429962158203 lr:1.193295936329686e-06 tokens_per_second_per_gpu:766.9064927949489 +Step 7672 | loss:2.086193799972534 lr:1.1872429393885775e-06 tokens_per_second_per_gpu:795.1923733607823 +Step 7673 | loss:2.011016607284546 lr:1.1812052417523921e-06 tokens_per_second_per_gpu:776.810243045493 +Step 7674 | loss:2.096163511276245 lr:1.1751828443559377e-06 tokens_per_second_per_gpu:796.73712748765 +Step 7675 | loss:1.9604705572128296 lr:1.16917574813169e-06 tokens_per_second_per_gpu:755.1773514180769 +Step 7676 | loss:1.972327470779419 lr:1.1631839540097277e-06 tokens_per_second_per_gpu:771.0380179319659 +Step 7677 | loss:1.9985606670379639 lr:1.1572074629177643e-06 tokens_per_second_per_gpu:766.5971221946417 +Step 7678 | loss:1.9785648584365845 lr:1.1512462757811593e-06 tokens_per_second_per_gpu:752.6134838044177 +Step 7679 | loss:2.060648202896118 lr:1.1453003935228746e-06 tokens_per_second_per_gpu:789.4540917367041 +Step 7680 | loss:2.015932083129883 lr:1.139369817063529e-06 tokens_per_second_per_gpu:747.401285607608 +Step 7681 | loss:2.108071804046631 lr:1.1334545473213554e-06 tokens_per_second_per_gpu:761.5744846540476 +Step 7682 | loss:2.025826930999756 lr:1.1275545852122427e-06 tokens_per_second_per_gpu:726.891371141361 +Step 7683 | loss:1.9351093769073486 lr:1.1216699316496494e-06 tokens_per_second_per_gpu:761.2133821366963 +Step 7684 | loss:2.0356125831604004 lr:1.1158005875447465e-06 tokens_per_second_per_gpu:777.6767475963053 +Step 7685 | loss:2.0002224445343018 lr:1.1099465538062627e-06 tokens_per_second_per_gpu:772.4922383615585 +Step 7686 | loss:2.0452582836151123 lr:1.104107831340595e-06 tokens_per_second_per_gpu:755.27399905374 +Step 7687 | loss:2.023556709289551 lr:1.098284421051765e-06 tokens_per_second_per_gpu:749.6246692303307 +Step 7688 | loss:2.0471103191375732 lr:1.0924763238414183e-06 tokens_per_second_per_gpu:761.5146246161162 +Step 7689 | loss:2.0212674140930176 lr:1.086683540608824e-06 tokens_per_second_per_gpu:787.5097373514103 +Step 7690 | loss:2.028247117996216 lr:1.0809060722508756e-06 tokens_per_second_per_gpu:787.692440801127 +Step 7691 | loss:2.0236058235168457 lr:1.075143919662136e-06 tokens_per_second_per_gpu:734.2063082571811 +Step 7692 | loss:1.985102891921997 lr:1.0693970837347356e-06 tokens_per_second_per_gpu:792.958893820484 +Step 7693 | loss:1.9547832012176514 lr:1.0636655653584849e-06 tokens_per_second_per_gpu:762.4885946682363 +Step 7694 | loss:2.0291943550109863 lr:1.0579493654208073e-06 tokens_per_second_per_gpu:767.0047409992357 +Step 7695 | loss:1.9796080589294434 lr:1.0522484848067171e-06 tokens_per_second_per_gpu:753.6873783241045 +Step 7696 | loss:1.9853684902191162 lr:1.0465629243989195e-06 tokens_per_second_per_gpu:766.8954739609835 +Step 7697 | loss:1.981635570526123 lr:1.04089268507771e-06 tokens_per_second_per_gpu:791.0483149336884 +Step 7698 | loss:2.0364203453063965 lr:1.035237767721009e-06 tokens_per_second_per_gpu:779.8996479647857 +Step 7699 | loss:1.9951457977294922 lr:1.0295981732043824e-06 tokens_per_second_per_gpu:791.4041116696889 +Step 7700 | loss:1.992972731590271 lr:1.0239739024010208e-06 tokens_per_second_per_gpu:804.5071414753381 +Step 7701 | loss:2.01387095451355 lr:1.0183649561817277e-06 tokens_per_second_per_gpu:767.606161196122 +Step 7702 | loss:2.0092034339904785 lr:1.0127713354149305e-06 tokens_per_second_per_gpu:790.0720576674225 +Step 7703 | loss:2.0481152534484863 lr:1.0071930409667363e-06 tokens_per_second_per_gpu:780.1148003866839 +Step 7704 | loss:2.045508861541748 lr:1.0016300737007989e-06 tokens_per_second_per_gpu:756.7483314667802 +Step 7705 | loss:1.9725679159164429 lr:9.960824344784736e-07 tokens_per_second_per_gpu:778.574620052481 +Step 7706 | loss:1.9456212520599365 lr:9.905501241586734e-07 tokens_per_second_per_gpu:763.8109015534851 +Step 7707 | loss:2.022728443145752 lr:9.85033143598013e-07 tokens_per_second_per_gpu:778.4858675390897 +Step 7708 | loss:2.0286879539489746 lr:9.79531493650654e-07 tokens_per_second_per_gpu:766.8828771087111 +Step 7709 | loss:2.0225398540496826 lr:9.740451751684475e-07 tokens_per_second_per_gpu:778.0478886855137 +Step 7710 | loss:2.0462677478790283 lr:9.68574189000837e-07 tokens_per_second_per_gpu:779.1247544954003 +Step 7711 | loss:1.9708468914031982 lr:9.631185359949113e-07 tokens_per_second_per_gpu:786.5975776954989 +Step 7712 | loss:2.0022056102752686 lr:9.576782169953725e-07 tokens_per_second_per_gpu:793.1652986829165 +Step 7713 | loss:2.0440852642059326 lr:9.522532328445466e-07 tokens_per_second_per_gpu:803.2874490097931 +Step 7714 | loss:2.0159530639648438 lr:9.468435843823953e-07 tokens_per_second_per_gpu:761.2578698093371 +Step 7715 | loss:1.9940434694290161 lr:9.41449272446504e-07 tokens_per_second_per_gpu:777.8357953954762 +Step 7716 | loss:1.9978358745574951 lr:9.360702978720825e-07 tokens_per_second_per_gpu:755.9360659597164 +Step 7717 | loss:1.9995574951171875 lr:9.307066614919535e-07 tokens_per_second_per_gpu:749.747580563478 +Step 7718 | loss:1.998439073562622 lr:9.25358364136586e-07 tokens_per_second_per_gpu:779.5426556867585 +Step 7719 | loss:1.9306397438049316 lr:9.200254066340508e-07 tokens_per_second_per_gpu:774.0940962835298 +Step 7720 | loss:2.012925386428833 lr:9.147077898100653e-07 tokens_per_second_per_gpu:767.3016813571379 +Step 7721 | loss:1.9299708604812622 lr:9.094055144879821e-07 tokens_per_second_per_gpu:756.8123330571048 +Step 7722 | loss:1.9907134771347046 lr:9.04118581488722e-07 tokens_per_second_per_gpu:768.7718612605311 +Step 7723 | loss:2.040334701538086 lr:8.988469916308861e-07 tokens_per_second_per_gpu:791.0490656835226 +Step 7724 | loss:2.002457857131958 lr:8.93590745730688e-07 tokens_per_second_per_gpu:765.2882924378471 +Step 7725 | loss:2.045077085494995 lr:8.883498446019544e-07 tokens_per_second_per_gpu:765.694918458145 +Step 7726 | loss:2.0343799591064453 lr:8.831242890561253e-07 tokens_per_second_per_gpu:742.5195237692377 +Step 7727 | loss:2.038239002227783 lr:8.779140799023089e-07 tokens_per_second_per_gpu:755.135145146353 +Step 7728 | loss:2.0066683292388916 lr:8.727192179471822e-07 tokens_per_second_per_gpu:753.5105403024055 +Step 7729 | loss:2.042387008666992 lr:8.675397039950795e-07 tokens_per_second_per_gpu:772.3269444095596 +Step 7730 | loss:1.9735997915267944 lr:8.623755388479593e-07 tokens_per_second_per_gpu:799.6932737771436 +Step 7731 | loss:1.9935765266418457 lr:8.572267233053933e-07 tokens_per_second_per_gpu:776.1312097939417 +Step 7732 | loss:1.972245693206787 lr:8.520932581645769e-07 tokens_per_second_per_gpu:783.4810818886843 +Step 7733 | loss:1.9566230773925781 lr:8.469751442203299e-07 tokens_per_second_per_gpu:771.6239584468336 +Step 7734 | loss:2.0436782836914062 lr:8.418723822650964e-07 tokens_per_second_per_gpu:770.4912119434697 +Step 7735 | loss:2.0667948722839355 lr:8.367849730889443e-07 tokens_per_second_per_gpu:778.0677338699209 +Step 7736 | loss:1.99497652053833 lr:8.317129174795657e-07 tokens_per_second_per_gpu:740.33850086476 +Step 7737 | loss:1.9713282585144043 lr:8.266562162222769e-07 tokens_per_second_per_gpu:785.3107372924438 +Step 7738 | loss:2.0008554458618164 lr:8.21614870100007e-07 tokens_per_second_per_gpu:727.5215147045589 +Step 7739 | loss:2.0743730068206787 lr:8.165888798933097e-07 tokens_per_second_per_gpu:776.6671308933394 +Step 7740 | loss:1.9997973442077637 lr:8.115782463803733e-07 tokens_per_second_per_gpu:770.9339273790952 +Step 7741 | loss:2.0022389888763428 lr:8.065829703369998e-07 tokens_per_second_per_gpu:771.1652429939828 +Step 7742 | loss:2.0133907794952393 lr:8.016030525366147e-07 tokens_per_second_per_gpu:784.6035892010703 +Step 7743 | loss:1.9382529258728027 lr:7.966384937502569e-07 tokens_per_second_per_gpu:766.2179908206551 +Step 7744 | loss:2.031790018081665 lr:7.916892947466004e-07 tokens_per_second_per_gpu:787.5085435549821 +Step 7745 | loss:1.9851725101470947 lr:7.867554562919433e-07 tokens_per_second_per_gpu:758.9632491624072 +Step 7746 | loss:2.0273454189300537 lr:7.818369791501856e-07 tokens_per_second_per_gpu:773.8450719416292 +Step 7747 | loss:1.9713852405548096 lr:7.769338640828739e-07 tokens_per_second_per_gpu:777.3060960803161 +Step 7748 | loss:2.01357364654541 lr:7.720461118491673e-07 tokens_per_second_per_gpu:766.9714917935237 +Step 7749 | loss:1.9674930572509766 lr:7.671737232058163e-07 tokens_per_second_per_gpu:753.5371841161806 +Step 7750 | loss:2.037719964981079 lr:7.623166989072394e-07 tokens_per_second_per_gpu:767.3412493408938 +Step 7751 | loss:2.0755274295806885 lr:7.574750397054576e-07 tokens_per_second_per_gpu:776.0958724985073 +Step 7752 | loss:2.024254560470581 lr:7.526487463501041e-07 tokens_per_second_per_gpu:793.7461587778907 +Step 7753 | loss:2.057830572128296 lr:7.478378195884372e-07 tokens_per_second_per_gpu:782.3780364431227 +Step 7754 | loss:1.9705584049224854 lr:7.430422601653497e-07 tokens_per_second_per_gpu:778.5243531992184 +Step 7755 | loss:2.0175564289093018 lr:7.382620688233366e-07 tokens_per_second_per_gpu:786.1985415619703 +Step 7756 | loss:2.0588762760162354 lr:7.334972463025059e-07 tokens_per_second_per_gpu:765.0400168254889 +Step 7757 | loss:2.0605106353759766 lr:7.287477933406339e-07 tokens_per_second_per_gpu:769.8994505429805 +Step 7758 | loss:2.00445818901062 lr:7.24013710673066e-07 tokens_per_second_per_gpu:779.1817971389693 +Step 7759 | loss:1.990795373916626 lr:7.192949990327935e-07 tokens_per_second_per_gpu:776.7707183189485 +Step 7760 | loss:1.9866399765014648 lr:7.145916591504098e-07 tokens_per_second_per_gpu:763.6096699813841 +Step 7761 | loss:1.985886573791504 lr:7.099036917541324e-07 tokens_per_second_per_gpu:772.2660025258679 +Step 7762 | loss:1.9285330772399902 lr:7.052310975698362e-07 tokens_per_second_per_gpu:786.8513471360104 +Step 7763 | loss:2.0327019691467285 lr:7.005738773209647e-07 tokens_per_second_per_gpu:778.3093698347307 +Step 7764 | loss:2.0071964263916016 lr:6.959320317285856e-07 tokens_per_second_per_gpu:784.8170094008675 +Step 7765 | loss:1.9907443523406982 lr:6.91305561511435e-07 tokens_per_second_per_gpu:786.234770876072 +Step 7766 | loss:2.010006904602051 lr:6.866944673858066e-07 tokens_per_second_per_gpu:770.9548517272076 +Step 7767 | loss:2.0750625133514404 lr:6.820987500656629e-07 tokens_per_second_per_gpu:778.3620928924948 +Step 7768 | loss:1.973226547241211 lr:6.775184102625564e-07 tokens_per_second_per_gpu:759.9305543427503 +Step 7769 | loss:2.005984306335449 lr:6.729534486856648e-07 tokens_per_second_per_gpu:763.8297646645727 +Step 7770 | loss:1.9803576469421387 lr:6.684038660417891e-07 tokens_per_second_per_gpu:772.406745469278 +Step 7771 | loss:1.9349761009216309 lr:6.638696630353436e-07 tokens_per_second_per_gpu:777.6872484410121 +Step 7772 | loss:1.9657155275344849 lr:6.593508403683668e-07 tokens_per_second_per_gpu:805.8121922651984 +Step 7773 | loss:2.0137908458709717 lr:6.548473987405101e-07 tokens_per_second_per_gpu:765.3801921087182 +Step 7774 | loss:2.024873733520508 lr:6.503593388490603e-07 tokens_per_second_per_gpu:771.5404985364435 +Step 7775 | loss:1.9448447227478027 lr:6.458866613889059e-07 tokens_per_second_per_gpu:778.9431392733551 +Step 7776 | loss:1.95701003074646 lr:6.414293670525484e-07 tokens_per_second_per_gpu:790.8689329892836 +Step 7777 | loss:1.9447457790374756 lr:6.369874565301026e-07 tokens_per_second_per_gpu:779.9636345483174 +Step 7778 | loss:1.9950404167175293 lr:6.325609305093516e-07 tokens_per_second_per_gpu:782.4315850430245 +Step 7779 | loss:2.0171427726745605 lr:6.281497896756361e-07 tokens_per_second_per_gpu:777.6197617021722 +Step 7780 | loss:2.0354652404785156 lr:6.23754034711943e-07 tokens_per_second_per_gpu:767.768243246636 +Step 7781 | loss:1.9464678764343262 lr:6.193736662988725e-07 tokens_per_second_per_gpu:775.5630502352182 +Step 7782 | loss:1.994558334350586 lr:6.150086851146486e-07 tokens_per_second_per_gpu:781.3560911312493 +Step 7783 | loss:2.022934675216675 lr:6.106590918350863e-07 tokens_per_second_per_gpu:783.9926035039922 +Step 7784 | loss:2.004201650619507 lr:6.063248871336691e-07 tokens_per_second_per_gpu:755.6112376060895 +Step 7785 | loss:2.0422167778015137 lr:6.02006071681449e-07 tokens_per_second_per_gpu:755.206867900734 +Step 7786 | loss:2.0008983612060547 lr:5.977026461471136e-07 tokens_per_second_per_gpu:785.0807909368856 +Step 7787 | loss:1.9245061874389648 lr:5.934146111969741e-07 tokens_per_second_per_gpu:771.9649834667563 +Step 7788 | loss:1.9670510292053223 lr:5.89141967494955e-07 tokens_per_second_per_gpu:766.9310110015618 +Step 7789 | loss:2.0454089641571045 lr:5.848847157025827e-07 tokens_per_second_per_gpu:777.7328249576329 +Step 7790 | loss:2.0088157653808594 lr:5.80642856479019e-07 tokens_per_second_per_gpu:785.1216317744822 +Step 7791 | loss:2.0246150493621826 lr:5.764163904810382e-07 tokens_per_second_per_gpu:763.7264962120593 +Step 7792 | loss:1.9842612743377686 lr:5.722053183630283e-07 tokens_per_second_per_gpu:782.7650867476004 +Step 7793 | loss:1.9266512393951416 lr:5.680096407769897e-07 tokens_per_second_per_gpu:794.8993231392099 +Step 7794 | loss:2.0039329528808594 lr:5.638293583725584e-07 tokens_per_second_per_gpu:792.2904546365946 +Step 7795 | loss:2.015425682067871 lr:5.596644717969612e-07 tokens_per_second_per_gpu:781.8214704812821 +Step 7796 | loss:2.06532883644104 lr:5.5551498169506e-07 tokens_per_second_per_gpu:774.4126748188522 +Step 7797 | loss:2.031517267227173 lr:5.513808887093186e-07 tokens_per_second_per_gpu:778.2592177016026 +Step 7798 | loss:2.015306234359741 lr:5.47262193479825e-07 tokens_per_second_per_gpu:782.8816799858507 +Step 7799 | loss:2.006765842437744 lr:5.431588966442802e-07 tokens_per_second_per_gpu:777.8585978892386 +Step 7800 | loss:2.035612106323242 lr:5.390709988380094e-07 tokens_per_second_per_gpu:754.9424312385013 +Step 7801 | loss:2.0234522819519043 lr:5.349985006939506e-07 tokens_per_second_per_gpu:746.9923218273708 +Step 7802 | loss:1.9953229427337646 lr:5.309414028426441e-07 tokens_per_second_per_gpu:771.4080466612661 +Step 7803 | loss:2.0736231803894043 lr:5.268997059122538e-07 tokens_per_second_per_gpu:779.1869938216132 +Step 7804 | loss:1.9476226568222046 lr:5.228734105285682e-07 tokens_per_second_per_gpu:773.7562992681723 +Step 7805 | loss:2.002429962158203 lr:5.188625173149886e-07 tokens_per_second_per_gpu:763.4519920740519 +Step 7806 | loss:1.990434169769287 lr:5.148670268925071e-07 tokens_per_second_per_gpu:733.0008795019797 +Step 7807 | loss:2.010119915008545 lr:5.108869398797733e-07 tokens_per_second_per_gpu:766.7028294253279 +Step 7808 | loss:1.9826109409332275 lr:5.069222568930166e-07 tokens_per_second_per_gpu:791.838608701816 +Step 7809 | loss:1.996933937072754 lr:5.029729785460902e-07 tokens_per_second_per_gpu:770.3580883176691 +Step 7810 | loss:1.9746837615966797 lr:4.990391054504717e-07 tokens_per_second_per_gpu:760.023548742723 +Step 7811 | loss:1.9934868812561035 lr:4.951206382152518e-07 tokens_per_second_per_gpu:784.1408993320787 +Step 7812 | loss:2.037480354309082 lr:4.91217577447134e-07 tokens_per_second_per_gpu:750.8930147108077 +Step 7813 | loss:2.038126230239868 lr:4.873299237504125e-07 tokens_per_second_per_gpu:769.1180676870156 +Step 7814 | loss:1.9763286113739014 lr:4.834576777270394e-07 tokens_per_second_per_gpu:771.1762555971837 +Step 7815 | loss:2.018394947052002 lr:4.796008399765572e-07 tokens_per_second_per_gpu:763.1935793508605 +Step 7816 | loss:2.027604579925537 lr:4.7575941109612167e-07 tokens_per_second_per_gpu:760.5242987061558 +Step 7817 | loss:1.9626657962799072 lr:4.7193339168050133e-07 tokens_per_second_per_gpu:762.1765697621684 +Step 7818 | loss:1.969151496887207 lr:4.6812278232208906e-07 tokens_per_second_per_gpu:765.5737120769758 +Step 7819 | loss:2.079512596130371 lr:4.643275836108796e-07 tokens_per_second_per_gpu:740.1980206338955 +Step 7820 | loss:1.9706568717956543 lr:4.6054779613450283e-07 tokens_per_second_per_gpu:759.052857768584 +Step 7821 | loss:1.996918797492981 lr:4.5678342047817954e-07 tokens_per_second_per_gpu:757.1735483022633 +Step 7822 | loss:2.0061416625976562 lr:4.5303445722474357e-07 tokens_per_second_per_gpu:798.8849052688757 +Step 7823 | loss:2.025284767150879 lr:4.4930090695466387e-07 tokens_per_second_per_gpu:776.0177746871336 +Step 7824 | loss:2.0629425048828125 lr:4.4558277024601134e-07 tokens_per_second_per_gpu:740.6124336305646 +Step 7825 | loss:2.0164551734924316 lr:4.4188004767445887e-07 tokens_per_second_per_gpu:735.2661170644727 +Step 7826 | loss:1.9882665872573853 lr:4.3819273981331454e-07 tokens_per_second_per_gpu:799.1170097857752 +Step 7827 | loss:1.9805797338485718 lr:4.3452084723347717e-07 tokens_per_second_per_gpu:768.0881463076588 +Step 7828 | loss:2.0077080726623535 lr:4.3086437050349206e-07 tokens_per_second_per_gpu:793.6867936255843 +Step 7829 | loss:1.9985321760177612 lr:4.2722331018947293e-07 tokens_per_second_per_gpu:764.3499589280343 +Step 7830 | loss:2.0017647743225098 lr:4.2359766685518e-07 tokens_per_second_per_gpu:775.05067884031 +Step 7831 | loss:2.000448226928711 lr:4.199874410619753e-07 tokens_per_second_per_gpu:771.9577981224518 +Step 7832 | loss:1.9812281131744385 lr:4.1639263336884506e-07 tokens_per_second_per_gpu:774.7542645565352 +Step 7833 | loss:1.9876353740692139 lr:4.1281324433235515e-07 tokens_per_second_per_gpu:752.2132913633399 +Step 7834 | loss:2.0263547897338867 lr:4.0924927450671777e-07 tokens_per_second_per_gpu:752.6300390096825 +Step 7835 | loss:1.9850668907165527 lr:4.057007244437583e-07 tokens_per_second_per_gpu:774.8012510211995 +Step 7836 | loss:2.0149638652801514 lr:4.0216759469289266e-07 tokens_per_second_per_gpu:781.1008819864666 +Step 7837 | loss:1.9754509925842285 lr:3.9864988580116113e-07 tokens_per_second_per_gpu:770.1449808856089 +Step 7838 | loss:2.0132389068603516 lr:3.951475983132058e-07 tokens_per_second_per_gpu:763.6778024518081 +Step 7839 | loss:2.0121710300445557 lr:3.91660732771304e-07 tokens_per_second_per_gpu:782.5482669681263 +Step 7840 | loss:2.0053110122680664 lr:3.88189289715335e-07 tokens_per_second_per_gpu:742.9213555652774 +Step 7841 | loss:2.053135633468628 lr:3.847332696827688e-07 tokens_per_second_per_gpu:724.7136308437475 +Step 7842 | loss:1.9997249841690063 lr:3.8129267320872184e-07 tokens_per_second_per_gpu:786.0829997943308 +Step 7843 | loss:1.9616715908050537 lr:3.778675008258903e-07 tokens_per_second_per_gpu:764.1131806261619 +Step 7844 | loss:2.0000715255737305 lr:3.744577530646165e-07 tokens_per_second_per_gpu:784.0897883349161 +Step 7845 | loss:2.0077362060546875 lr:3.7106343045282264e-07 tokens_per_second_per_gpu:770.4606958708277 +Step 7846 | loss:1.9991849660873413 lr:3.6768453351605503e-07 tokens_per_second_per_gpu:772.1290232502008 +Step 7847 | loss:2.028286933898926 lr:3.6432106277748404e-07 tokens_per_second_per_gpu:772.6410378664508 +Step 7848 | loss:2.0417439937591553 lr:3.6097301875787084e-07 tokens_per_second_per_gpu:735.5800060514716 +Step 7849 | loss:1.9510765075683594 lr:3.576404019756008e-07 tokens_per_second_per_gpu:792.9144776936862 +Step 7850 | loss:2.0104222297668457 lr:3.5432321294666114e-07 tokens_per_second_per_gpu:791.0672894756577 +Step 7851 | loss:2.0029854774475098 lr:3.510214521846744e-07 tokens_per_second_per_gpu:760.8456201959735 +Step 7852 | loss:1.9743447303771973 lr:3.4773512020083167e-07 tokens_per_second_per_gpu:775.1202230334342 +Step 7853 | loss:2.028643846511841 lr:3.444642175039814e-07 tokens_per_second_per_gpu:734.3650691423449 +Step 7854 | loss:1.9396957159042358 lr:3.4120874460054077e-07 tokens_per_second_per_gpu:782.1496906165324 +Step 7855 | loss:2.027444362640381 lr:3.379687019945732e-07 tokens_per_second_per_gpu:783.9237787618407 +Step 7856 | loss:1.9997389316558838 lr:3.347440901877441e-07 tokens_per_second_per_gpu:758.815974443452 +Step 7857 | loss:2.0356764793395996 lr:3.3153490967930965e-07 tokens_per_second_per_gpu:758.6173634618341 +Step 7858 | loss:2.031811475753784 lr:3.283411609661613e-07 tokens_per_second_per_gpu:768.6198726744207 +Step 7859 | loss:1.9872934818267822 lr:3.2516284454278123e-07 tokens_per_second_per_gpu:755.1023217219326 +Step 7860 | loss:2.063962936401367 lr:3.219999609012869e-07 tokens_per_second_per_gpu:760.6977204834236 +Step 7861 | loss:1.9739274978637695 lr:3.1885251053137556e-07 tokens_per_second_per_gpu:794.487080773089 +Step 7862 | loss:2.0620601177215576 lr:3.157204939203795e-07 tokens_per_second_per_gpu:775.3904821217443 +Step 7863 | loss:2.000598430633545 lr:3.126039115532331e-07 tokens_per_second_per_gpu:724.3897493452832 +Step 7864 | loss:2.0369651317596436 lr:3.0950276391247257e-07 tokens_per_second_per_gpu:785.4105678115151 +Step 7865 | loss:2.0319442749023438 lr:3.064170514782694e-07 tokens_per_second_per_gpu:763.4856560099593 +Step 7866 | loss:1.9605097770690918 lr:3.033467747283858e-07 tokens_per_second_per_gpu:786.3927120798003 +Step 7867 | loss:2.018195867538452 lr:3.002919341381749e-07 tokens_per_second_per_gpu:766.7237302084283 +Step 7868 | loss:1.989344835281372 lr:2.9725253018064726e-07 tokens_per_second_per_gpu:789.9893093076948 +Step 7869 | loss:1.9762238264083862 lr:2.9422856332637083e-07 tokens_per_second_per_gpu:762.1568429403287 +Step 7870 | loss:1.9541302919387817 lr:2.912200340435711e-07 tokens_per_second_per_gpu:775.1607817753807 +Step 7871 | loss:2.0381598472595215 lr:2.882269427980644e-07 tokens_per_second_per_gpu:780.109971778811 +Step 7872 | loss:1.9798513650894165 lr:2.8524929005326885e-07 tokens_per_second_per_gpu:750.8185179243949 +Step 7873 | loss:2.0227277278900146 lr:2.8228707627020457e-07 tokens_per_second_per_gpu:765.7066002511483 +Step 7874 | loss:2.0360851287841797 lr:2.7934030190753804e-07 tokens_per_second_per_gpu:778.6080470910418 +Step 7875 | loss:2.034270763397217 lr:2.764089674215042e-07 tokens_per_second_per_gpu:759.8817410621511 +Step 7876 | loss:2.0212929248809814 lr:2.734930732659735e-07 tokens_per_second_per_gpu:758.958213880041 +Step 7877 | loss:1.9644815921783447 lr:2.7059261989241805e-07 tokens_per_second_per_gpu:756.1881546814029 +Step 7878 | loss:1.988227128982544 lr:2.67707607749923e-07 tokens_per_second_per_gpu:752.0768061673152 +Step 7879 | loss:1.9779088497161865 lr:2.6483803728516445e-07 tokens_per_second_per_gpu:748.5151720314498 +Step 7880 | loss:1.9705874919891357 lr:2.619839089424536e-07 tokens_per_second_per_gpu:744.6960666246584 +Step 7881 | loss:1.9523353576660156 lr:2.591452231636926e-07 tokens_per_second_per_gpu:755.1814592560393 +Step 7882 | loss:2.0102548599243164 lr:2.563219803884076e-07 tokens_per_second_per_gpu:755.0526581196057 +Step 7883 | loss:2.0467166900634766 lr:2.535141810537156e-07 tokens_per_second_per_gpu:773.9570307475004 +Step 7884 | loss:2.0527005195617676 lr:2.507218255943467e-07 tokens_per_second_per_gpu:775.2415126523629 +Step 7885 | loss:1.9733293056488037 lr:2.479449144426549e-07 tokens_per_second_per_gpu:789.051051079303 +Step 7886 | loss:1.9911011457443237 lr:2.451834480285964e-07 tokens_per_second_per_gpu:760.313239993407 +Step 7887 | loss:2.005434513092041 lr:2.424374267797291e-07 tokens_per_second_per_gpu:759.4697357138349 +Step 7888 | loss:1.9988620281219482 lr:2.3970685112121304e-07 tokens_per_second_per_gpu:774.2739497264425 +Step 7889 | loss:1.9691275358200073 lr:2.3699172147584326e-07 tokens_per_second_per_gpu:769.3236523289942 +Step 7890 | loss:1.9937113523483276 lr:2.342920382639835e-07 tokens_per_second_per_gpu:778.637914005787 +Step 7891 | loss:2.0267622470855713 lr:2.3160780190365494e-07 tokens_per_second_per_gpu:756.4062170054455 +Step 7892 | loss:2.0428614616394043 lr:2.289390128104474e-07 tokens_per_second_per_gpu:781.7130726115024 +Step 7893 | loss:1.9731416702270508 lr:2.2628567139758582e-07 tokens_per_second_per_gpu:747.7311919919333 +Step 7894 | loss:1.9663515090942383 lr:2.236477780758639e-07 tokens_per_second_per_gpu:764.9935827886246 +Step 7895 | loss:1.9960839748382568 lr:2.2102533325373264e-07 tokens_per_second_per_gpu:738.2408474464311 +Step 7896 | loss:1.9273241758346558 lr:2.1841833733722284e-07 tokens_per_second_per_gpu:741.8776070217336 +Step 7897 | loss:1.9770679473876953 lr:2.1582679072997826e-07 tokens_per_second_per_gpu:772.5322982624181 +Step 7898 | loss:1.9842230081558228 lr:2.1325069383324458e-07 tokens_per_second_per_gpu:791.9490401358629 +Step 7899 | loss:2.0103392601013184 lr:2.106900470458917e-07 tokens_per_second_per_gpu:789.3876228276699 +Step 7900 | loss:2.0434012413024902 lr:2.0814485076439128e-07 tokens_per_second_per_gpu:771.9064050390114 +Step 7901 | loss:2.0301074981689453 lr:2.0561510538280592e-07 tokens_per_second_per_gpu:758.1011100474832 +Step 7902 | loss:2.052462577819824 lr:2.0310081129283341e-07 tokens_per_second_per_gpu:758.835251956459 +Step 7903 | loss:1.9540846347808838 lr:2.0060196888375127e-07 tokens_per_second_per_gpu:787.6348787743923 +Step 7904 | loss:2.0016837120056152 lr:1.9811857854247217e-07 tokens_per_second_per_gpu:757.1866353996738 +Step 7905 | loss:1.9655120372772217 lr:1.956506406534886e-07 tokens_per_second_per_gpu:785.2800187627255 +Step 7906 | loss:1.9686591625213623 lr:1.9319815559892817e-07 tokens_per_second_per_gpu:783.1547852951005 +Step 7907 | loss:2.0604867935180664 lr:1.907611237584983e-07 tokens_per_second_per_gpu:793.9052347753567 +Step 7908 | loss:1.9875119924545288 lr:1.8833954550954158e-07 tokens_per_second_per_gpu:782.5738741700802 +Step 7909 | loss:1.9843106269836426 lr:1.859334212269803e-07 tokens_per_second_per_gpu:769.4196145877673 +Step 7910 | loss:2.008770227432251 lr:1.8354275128337205e-07 tokens_per_second_per_gpu:792.8053983911813 +Step 7911 | loss:2.0307793617248535 lr:1.8116753604885406e-07 tokens_per_second_per_gpu:758.0730612268121 +Step 7912 | loss:1.9876205921173096 lr:1.7880777589119878e-07 tokens_per_second_per_gpu:771.18383974983 +Step 7913 | loss:1.9849413633346558 lr:1.7646347117575846e-07 tokens_per_second_per_gpu:781.229113014193 +Step 7914 | loss:2.039973735809326 lr:1.7413462226550936e-07 tokens_per_second_per_gpu:750.3788184139934 +Step 7915 | loss:2.002047538757324 lr:1.7182122952101865e-07 tokens_per_second_per_gpu:789.758800042141 +Step 7916 | loss:1.9625067710876465 lr:1.6952329330049977e-07 tokens_per_second_per_gpu:776.5791884804304 +Step 7917 | loss:1.974139928817749 lr:1.672408139597126e-07 tokens_per_second_per_gpu:747.4801864055933 +Step 7918 | loss:1.9742259979248047 lr:1.6497379185208551e-07 tokens_per_second_per_gpu:759.6462946825644 +Step 7919 | loss:1.9965938329696655 lr:1.6272222732860442e-07 tokens_per_second_per_gpu:766.2543818938985 +Step 7920 | loss:2.0219082832336426 lr:1.604861207378794e-07 tokens_per_second_per_gpu:782.5149814817233 +Step 7921 | loss:2.0223028659820557 lr:1.5826547242614454e-07 tokens_per_second_per_gpu:772.6785312650036 +Step 7922 | loss:2.0129611492156982 lr:1.5606028273722484e-07 tokens_per_second_per_gpu:786.4330260738462 +Step 7923 | loss:2.002260208129883 lr:1.5387055201254718e-07 tokens_per_second_per_gpu:763.5101025754029 +Step 7924 | loss:2.016545057296753 lr:1.5169628059114037e-07 tokens_per_second_per_gpu:754.7702426043594 +Step 7925 | loss:1.9854971170425415 lr:1.4953746880966845e-07 tokens_per_second_per_gpu:781.1853258983814 +Step 7926 | loss:2.048417091369629 lr:1.4739411700237516e-07 tokens_per_second_per_gpu:783.39656277441 +Step 7927 | loss:1.9888547658920288 lr:1.4526622550111723e-07 tokens_per_second_per_gpu:764.0548694073321 +Step 7928 | loss:1.9654549360275269 lr:1.4315379463535339e-07 tokens_per_second_per_gpu:779.9159362264272 +Step 7929 | loss:2.0934953689575195 lr:1.410568247321553e-07 tokens_per_second_per_gpu:760.4798750703571 +Step 7930 | loss:2.036231517791748 lr:1.3897531611620773e-07 tokens_per_second_per_gpu:766.9388363907783 +Step 7931 | loss:2.025700330734253 lr:1.3690926910979728e-07 tokens_per_second_per_gpu:733.8571839517568 +Step 7932 | loss:2.01282000541687 lr:1.3485868403280145e-07 tokens_per_second_per_gpu:793.4911689420537 +Step 7933 | loss:2.040020227432251 lr:1.3282356120271068e-07 tokens_per_second_per_gpu:758.809750325742 +Step 7934 | loss:2.0214526653289795 lr:1.3080390093463957e-07 tokens_per_second_per_gpu:768.9363452316693 +Step 7935 | loss:2.000490188598633 lr:1.2879970354129357e-07 tokens_per_second_per_gpu:793.3356000193936 +Step 7936 | loss:2.014622688293457 lr:1.2681096933296887e-07 tokens_per_second_per_gpu:753.1789588913717 +Step 7937 | loss:1.9981615543365479 lr:1.2483769861759699e-07 tokens_per_second_per_gpu:771.1533076126657 +Step 7938 | loss:2.005767583847046 lr:1.2287989170070014e-07 tokens_per_second_per_gpu:769.9255776069438 +Step 7939 | loss:2.004401683807373 lr:1.2093754888541365e-07 tokens_per_second_per_gpu:775.6459393315894 +Step 7940 | loss:1.9248522520065308 lr:1.1901067047246361e-07 tokens_per_second_per_gpu:735.0750714635021 +Step 7941 | loss:1.9997446537017822 lr:1.1709925676018918e-07 tokens_per_second_per_gpu:769.8749257373091 +Step 7942 | loss:1.956862449645996 lr:1.152033080445536e-07 tokens_per_second_per_gpu:779.6260065566862 +Step 7943 | loss:1.9221104383468628 lr:1.1332282461908872e-07 tokens_per_second_per_gpu:750.4698284799078 +Step 7944 | loss:1.9887357950210571 lr:1.1145780677496164e-07 tokens_per_second_per_gpu:777.8394967910355 +Step 7945 | loss:1.9791412353515625 lr:1.0960825480093029e-07 tokens_per_second_per_gpu:786.1136387254994 +Step 7946 | loss:2.064669132232666 lr:1.0777416898337666e-07 tokens_per_second_per_gpu:783.7395959936381 +Step 7947 | loss:1.951812982559204 lr:1.0595554960626253e-07 tokens_per_second_per_gpu:790.637779552506 +Step 7948 | loss:2.056312084197998 lr:1.0415239695116264e-07 tokens_per_second_per_gpu:793.4845362828162 +Step 7949 | loss:2.035430669784546 lr:1.0236471129727588e-07 tokens_per_second_per_gpu:761.1403660898535 +Step 7950 | loss:1.9868228435516357 lr:1.0059249292138084e-07 tokens_per_second_per_gpu:776.8387324303038 +Step 7951 | loss:1.9959735870361328 lr:9.883574209788027e-08 tokens_per_second_per_gpu:790.1414164612357 +Step 7952 | loss:2.084737777709961 lr:9.709445909876769e-08 tokens_per_second_per_gpu:793.6294186906052 +Step 7953 | loss:2.0037622451782227 lr:9.536864419366076e-08 tokens_per_second_per_gpu:778.1160919195507 +Step 7954 | loss:2.002581834793091 lr:9.365829764974576e-08 tokens_per_second_per_gpu:773.326209803345 +Step 7955 | loss:1.9557318687438965 lr:9.19634197318553e-08 tokens_per_second_per_gpu:764.1395805028461 +Step 7956 | loss:2.0377037525177 lr:9.028401070241276e-08 tokens_per_second_per_gpu:771.1995509357498 +Step 7957 | loss:1.9534246921539307 lr:8.862007082143242e-08 tokens_per_second_per_gpu:782.5168065578897 +Step 7958 | loss:2.0390448570251465 lr:8.69716003465415e-08 tokens_per_second_per_gpu:776.6018489207397 +Step 7959 | loss:1.9930548667907715 lr:8.533859953299139e-08 tokens_per_second_per_gpu:737.780298913284 +Step 7960 | loss:2.011702537536621 lr:8.372106863360208e-08 tokens_per_second_per_gpu:739.3681189136852 +Step 7961 | loss:2.019404411315918 lr:8.211900789882876e-08 tokens_per_second_per_gpu:748.7307421327016 +Step 7962 | loss:2.032996654510498 lr:8.053241757672857e-08 tokens_per_second_per_gpu:762.6113059201191 +Step 7963 | loss:2.0360050201416016 lr:7.896129791293838e-08 tokens_per_second_per_gpu:793.5772183436447 +Step 7964 | loss:2.016366958618164 lr:7.740564915071913e-08 tokens_per_second_per_gpu:762.76851981456 +Step 7965 | loss:2.056185007095337 lr:7.586547153094481e-08 tokens_per_second_per_gpu:793.9016343419773 +Step 7966 | loss:1.991417646408081 lr:7.434076529208023e-08 tokens_per_second_per_gpu:786.2692663824427 +Step 7967 | loss:2.0239453315734863 lr:7.283153067019211e-08 tokens_per_second_per_gpu:713.8438004231881 +Step 7968 | loss:1.9808098077774048 lr:7.133776789896018e-08 tokens_per_second_per_gpu:751.3049385934088 +Step 7969 | loss:2.040055274963379 lr:6.985947720966612e-08 tokens_per_second_per_gpu:779.8659672488352 +Step 7970 | loss:2.0034432411193848 lr:6.83966588311935e-08 tokens_per_second_per_gpu:782.70938610416 +Step 7971 | loss:2.0332820415496826 lr:6.694931299002782e-08 tokens_per_second_per_gpu:768.020406053419 +Step 7972 | loss:2.043173313140869 lr:6.55174399102787e-08 tokens_per_second_per_gpu:788.5363987544068 +Step 7973 | loss:1.9498108625411987 lr:6.410103981362436e-08 tokens_per_second_per_gpu:763.9850839662247 +Step 7974 | loss:1.9760746955871582 lr:6.270011291938938e-08 tokens_per_second_per_gpu:705.5217551484532 +Step 7975 | loss:1.981687307357788 lr:6.13146594444669e-08 tokens_per_second_per_gpu:777.0989870161959 +Step 7976 | loss:1.956174612045288 lr:5.994467960336314e-08 tokens_per_second_per_gpu:783.396982506739 +Step 7977 | loss:1.9997304677963257 lr:5.85901736082195e-08 tokens_per_second_per_gpu:741.3398320408077 +Step 7978 | loss:2.043203115463257 lr:5.7251141668723806e-08 tokens_per_second_per_gpu:763.0897275527263 +Step 7979 | loss:2.0806167125701904 lr:5.592758399222131e-08 tokens_per_second_per_gpu:781.3352286428062 +Step 7980 | loss:1.9648017883300781 lr:5.461950078363698e-08 tokens_per_second_per_gpu:773.114741370272 +Step 7981 | loss:1.948166847229004 lr:5.3326892245497694e-08 tokens_per_second_per_gpu:766.6760446263571 +Step 7982 | loss:1.997986078262329 lr:5.2049758577943367e-08 tokens_per_second_per_gpu:784.8826243350055 +Step 7983 | loss:2.017082452774048 lr:5.078809997870471e-08 tokens_per_second_per_gpu:752.0267067453598 +Step 7984 | loss:2.0021986961364746 lr:4.954191664313657e-08 tokens_per_second_per_gpu:774.9225830126056 +Step 7985 | loss:1.9580717086791992 lr:4.83112087641957e-08 tokens_per_second_per_gpu:771.6921563364318 +Step 7986 | loss:2.033564329147339 lr:4.709597653241859e-08 tokens_per_second_per_gpu:764.2217690914497 +Step 7987 | loss:2.044079303741455 lr:4.589622013595474e-08 tokens_per_second_per_gpu:792.5517639953628 +Step 7988 | loss:1.9795114994049072 lr:4.471193976058885e-08 tokens_per_second_per_gpu:760.8136010570147 +Step 7989 | loss:2.0310134887695312 lr:4.3543135589663166e-08 tokens_per_second_per_gpu:774.867901820208 +Step 7990 | loss:1.9923242330551147 lr:4.238980780415513e-08 tokens_per_second_per_gpu:755.0339577868866 +Step 7991 | loss:2.0698981285095215 lr:4.125195658263303e-08 tokens_per_second_per_gpu:771.7345623970389 +Step 7992 | loss:1.982459545135498 lr:4.012958210126705e-08 tokens_per_second_per_gpu:765.7479277139541 +Step 7993 | loss:2.067720890045166 lr:3.902268453385149e-08 tokens_per_second_per_gpu:749.3389426767429 +Step 7994 | loss:2.04436993598938 lr:3.7931264051749295e-08 tokens_per_second_per_gpu:768.0433463866583 +Step 7995 | loss:2.047945022583008 lr:3.6855320823958596e-08 tokens_per_second_per_gpu:777.3572376985777 +Step 7996 | loss:1.9972805976867676 lr:3.579485501706836e-08 tokens_per_second_per_gpu:762.3654197428882 +Step 7997 | loss:1.995005488395691 lr:3.474986679526948e-08 tokens_per_second_per_gpu:790.6687275723625 +Step 7998 | loss:2.00405216217041 lr:3.372035632035475e-08 tokens_per_second_per_gpu:761.9821979422481 +Step 7999 | loss:2.038869857788086 lr:3.270632375173e-08 tokens_per_second_per_gpu:763.7938079651035 +Step 8000 | loss:1.9495350122451782 lr:3.170776924639185e-08 tokens_per_second_per_gpu:759.1059119477642 +Step 8001 | loss:1.9977580308914185 lr:3.072469295896108e-08 tokens_per_second_per_gpu:777.1079195530697 +Step 8002 | loss:1.9767813682556152 lr:2.975709504163815e-08 tokens_per_second_per_gpu:794.5433669794928 +Step 8003 | loss:2.0365755558013916 lr:2.8804975644247665e-08 tokens_per_second_per_gpu:777.9059360259032 +Step 8004 | loss:1.9575512409210205 lr:2.7868334914193937e-08 tokens_per_second_per_gpu:762.2743723251352 +Step 8005 | loss:2.0255215167999268 lr:2.69471729965054e-08 tokens_per_second_per_gpu:756.3053036272869 +Step 8006 | loss:2.040454387664795 lr:2.60414900338124e-08 tokens_per_second_per_gpu:782.0544578916342 +Step 8007 | loss:2.036947250366211 lr:2.5151286166325004e-08 tokens_per_second_per_gpu:792.5697096392361 +Step 8008 | loss:2.0477547645568848 lr:2.4276561531888508e-08 tokens_per_second_per_gpu:780.576325554005 +Step 8009 | loss:1.9415621757507324 lr:2.3417316265939016e-08 tokens_per_second_per_gpu:754.9424411979296 +Step 8010 | loss:2.0124220848083496 lr:2.257355050151455e-08 tokens_per_second_per_gpu:777.4133444752415 +Step 8011 | loss:1.9141931533813477 lr:2.1745264369243958e-08 tokens_per_second_per_gpu:761.4309712162288 +Step 8012 | loss:2.0413906574249268 lr:2.0932457997391296e-08 tokens_per_second_per_gpu:766.7050950826367 +Step 8013 | loss:2.038914918899536 lr:2.013513151178925e-08 tokens_per_second_per_gpu:739.199901384188 +Step 8014 | loss:1.9759072065353394 lr:1.9353285035883518e-08 tokens_per_second_per_gpu:744.6834438435258 +Step 8015 | loss:1.985212802886963 lr:1.8586918690755018e-08 tokens_per_second_per_gpu:777.7775505819812 +Step 8016 | loss:1.9446678161621094 lr:1.7836032595031082e-08 tokens_per_second_per_gpu:760.8996995087634 +Step 8017 | loss:2.011288642883301 lr:1.7100626864996473e-08 tokens_per_second_per_gpu:759.7700252100286 +Step 8018 | loss:2.0255441665649414 lr:1.6380701614493455e-08 tokens_per_second_per_gpu:773.2169426286143 +Step 8019 | loss:2.081327199935913 lr:1.5676256955010626e-08 tokens_per_second_per_gpu:746.4493842574018 +Step 8020 | loss:1.9798699617385864 lr:1.4987292995594093e-08 tokens_per_second_per_gpu:777.2062899716293 +Step 8021 | loss:2.067760705947876 lr:1.431380984294739e-08 tokens_per_second_per_gpu:779.3959927829314 +Step 8022 | loss:1.9653761386871338 lr:1.3655807601320458e-08 tokens_per_second_per_gpu:780.0635699334758 +Step 8023 | loss:2.0304031372070312 lr:1.3013286372598465e-08 tokens_per_second_per_gpu:781.7271491163724 +Step 8024 | loss:2.0144684314727783 lr:1.2386246256268496e-08 tokens_per_second_per_gpu:773.8755791357482 +Step 8025 | loss:2.0082108974456787 lr:1.1774687349408453e-08 tokens_per_second_per_gpu:758.5657232302378 +Step 8026 | loss:1.9954246282577515 lr:1.1178609746720359e-08 tokens_per_second_per_gpu:742.7139308905337 +Step 8027 | loss:2.033475875854492 lr:1.0598013540497053e-08 tokens_per_second_per_gpu:763.370534038258 +Step 8028 | loss:2.0112462043762207 lr:1.0032898820611091e-08 tokens_per_second_per_gpu:757.9876217582441 +Step 8029 | loss:2.0703623294830322 lr:9.483265674581353e-09 tokens_per_second_per_gpu:773.308543428111 +Step 8030 | loss:1.9391348361968994 lr:8.949114187495333e-09 tokens_per_second_per_gpu:762.9064781530067 +Step 8031 | loss:2.052992343902588 lr:8.430444442053542e-09 tokens_per_second_per_gpu:788.7394910992978 +Step 8032 | loss:2.0163068771362305 lr:7.927256518580617e-09 tokens_per_second_per_gpu:790.0567059249729 +Step 8033 | loss:1.9553790092468262 lr:7.4395504949698044e-09 tokens_per_second_per_gpu:755.3023783975854 +Step 8034 | loss:2.0627365112304688 lr:6.967326446738476e-09 tokens_per_second_per_gpu:779.7218877865236 +Step 8035 | loss:2.0581207275390625 lr:6.510584447005918e-09 tokens_per_second_per_gpu:746.4869806664807 +Step 8036 | loss:1.977726697921753 lr:6.069324566471135e-09 tokens_per_second_per_gpu:783.3657142351402 +Step 8037 | loss:1.9812498092651367 lr:5.643546873490557e-09 tokens_per_second_per_gpu:786.8535255827088 +Step 8038 | loss:1.993045687675476 lr:5.233251433944819e-09 tokens_per_second_per_gpu:786.9841731608778 +Step 8039 | loss:1.9538288116455078 lr:4.838438311394189e-09 tokens_per_second_per_gpu:757.5932155950054 +Step 8040 | loss:1.9870463609695435 lr:4.459107566956444e-09 tokens_per_second_per_gpu:762.03886084099 +Step 8041 | loss:1.9281222820281982 lr:4.095259259362383e-09 tokens_per_second_per_gpu:757.5922758566286 +Step 8042 | loss:2.0609898567199707 lr:3.746893444955823e-09 tokens_per_second_per_gpu:747.4495960866057 +Step 8043 | loss:1.9810444116592407 lr:3.4140101776602984e-09 tokens_per_second_per_gpu:784.4353300337428 +Step 8044 | loss:1.9774928092956543 lr:3.0966095090234626e-09 tokens_per_second_per_gpu:750.8778737220612 +Step 8045 | loss:1.9821642637252808 lr:2.794691488183787e-09 tokens_per_second_per_gpu:762.0323070116846 +Step 8046 | loss:1.9965205192565918 lr:2.5082561618927634e-09 tokens_per_second_per_gpu:760.6035216801419 +Step 8047 | loss:2.0040555000305176 lr:2.2373035745038017e-09 tokens_per_second_per_gpu:774.6321932591208 +Step 8048 | loss:1.9962995052337646 lr:1.98183376797223e-09 tokens_per_second_per_gpu:745.2921087689864 +Step 8049 | loss:1.9855672121047974 lr:1.7418467818330898e-09 tokens_per_second_per_gpu:768.2393570070898 +Step 8050 | loss:1.9799096584320068 lr:1.5173426532677504e-09 tokens_per_second_per_gpu:764.6774618656613 +Step 8051 | loss:2.0067458152770996 lr:1.3083214170150904e-09 tokens_per_second_per_gpu:760.8224716260547 +Step 8052 | loss:1.9994604587554932 lr:1.114783105449213e-09 tokens_per_second_per_gpu:776.9307912051464 +Step 8053 | loss:2.0086300373077393 lr:9.36727748535038e-10 tokens_per_second_per_gpu:741.0953036528255 +Step 8054 | loss:2.006633758544922 lr:7.741553738394025e-10 tokens_per_second_per_gpu:771.648563195649 +Step 8055 | loss:2.0369503498077393 lr:6.27066006531063e-10 tokens_per_second_per_gpu:764.974274763898 +Step 8056 | loss:2.0552704334259033 lr:4.954596693917956e-10 tokens_per_second_per_gpu:786.8706889231885 +Step 8057 | loss:2.0277395248413086 lr:3.7933638279419316e-10 tokens_per_second_per_gpu:742.0824771810017 +Step 8058 | loss:2.0152804851531982 lr:2.786961647238684e-10 tokens_per_second_per_gpu:775.9879819716041 +Step 8059 | loss:1.9594755172729492 lr:1.935390307461482e-10 tokens_per_second_per_gpu:775.8974937038117 +Step 8060 | loss:2.001201868057251 lr:1.2386499406158437e-10 tokens_per_second_per_gpu:767.2456883869912 +Step 8061 | loss:1.908940315246582 lr:6.967406545044242e-11 tokens_per_second_per_gpu:749.639460584363 +Step 8062 | loss:2.0030922889709473 lr:3.096625330600844e-11 tokens_per_second_per_gpu:790.7302907019746 +Step 8063 | loss:2.0453476905822754 lr:7.74156362348677e-12 tokens_per_second_per_gpu:764.4262083193638 +Step 8064 | loss:1.9859586954116821 lr:0.0 tokens_per_second_per_gpu:695.5233108682681