Files
mini-Ichigo-llama3.2-3B-s-i…/loss_log_intruct.txt
ModelHub XC ec4995719b 初始化项目,由ModelHub XC社区提供模型
Model: homebrewltd/mini-Ichigo-llama3.2-3B-s-instruct
Source: Original Platform
2026-06-23 06:21:12 +08:00

5510 lines
570 KiB
Plaintext

Step 1 | loss:2.1742990016937256 lr:1.129032258064516e-06 tokens_per_second_per_gpu:548.469653913093
Step 2 | loss:2.0010740756988525 lr:2.258064516129032e-06 tokens_per_second_per_gpu:961.5835458815305
Step 3 | loss:2.0645954608917236 lr:3.387096774193548e-06 tokens_per_second_per_gpu:784.0305389265084
Step 4 | loss:1.9434601068496704 lr:4.516129032258064e-06 tokens_per_second_per_gpu:856.4459872420251
Step 5 | loss:1.9337503910064697 lr:5.64516129032258e-06 tokens_per_second_per_gpu:703.0841170312867
Step 6 | loss:2.149254083633423 lr:6.774193548387096e-06 tokens_per_second_per_gpu:764.7395443942615
Step 7 | loss:2.324523448944092 lr:7.903225806451612e-06 tokens_per_second_per_gpu:588.1622381700316
Step 8 | loss:2.006317377090454 lr:9.032258064516128e-06 tokens_per_second_per_gpu:681.8918938565347
Step 9 | loss:1.8419618606567383 lr:1.0161290322580644e-05 tokens_per_second_per_gpu:1111.985362976526
Step 10 | loss:1.8223600387573242 lr:1.129032258064516e-05 tokens_per_second_per_gpu:753.6760893396706
Step 11 | loss:1.7457427978515625 lr:1.2419354838709677e-05 tokens_per_second_per_gpu:901.6707450426563
Step 12 | loss:2.132134437561035 lr:1.3548387096774192e-05 tokens_per_second_per_gpu:810.7779144664007
Step 13 | loss:1.775560736656189 lr:1.4677419354838708e-05 tokens_per_second_per_gpu:923.0561549827952
Step 14 | loss:1.8616667985916138 lr:1.5806451612903223e-05 tokens_per_second_per_gpu:1355.1663286846815
Step 15 | loss:1.8847159147262573 lr:1.693548387096774e-05 tokens_per_second_per_gpu:907.440919695811
Step 16 | loss:1.8394975662231445 lr:1.8064516129032256e-05 tokens_per_second_per_gpu:937.9102924383999
Step 17 | loss:1.7849469184875488 lr:1.919354838709677e-05 tokens_per_second_per_gpu:748.3007358771708
Step 18 | loss:1.7917031049728394 lr:2.032258064516129e-05 tokens_per_second_per_gpu:1100.900650125661
Step 19 | loss:1.8965449333190918 lr:2.1451612903225803e-05 tokens_per_second_per_gpu:751.0995603130319
Step 20 | loss:1.8321805000305176 lr:2.258064516129032e-05 tokens_per_second_per_gpu:864.8769195957158
Step 21 | loss:1.9213206768035889 lr:2.3709677419354836e-05 tokens_per_second_per_gpu:1084.6336708437864
Step 22 | loss:1.8695461750030518 lr:2.4838709677419354e-05 tokens_per_second_per_gpu:743.9091403682944
Step 23 | loss:1.8677067756652832 lr:2.596774193548387e-05 tokens_per_second_per_gpu:840.2064098950523
Step 24 | loss:1.7376093864440918 lr:2.7096774193548384e-05 tokens_per_second_per_gpu:944.9412922225403
Step 25 | loss:1.524705410003662 lr:2.82258064516129e-05 tokens_per_second_per_gpu:1263.7145426421582
Step 26 | loss:1.5434813499450684 lr:2.9354838709677417e-05 tokens_per_second_per_gpu:885.3172987488526
Step 27 | loss:1.6001583337783813 lr:3.048387096774193e-05 tokens_per_second_per_gpu:1030.8959374068131
Step 28 | loss:1.8422741889953613 lr:3.1612903225806446e-05 tokens_per_second_per_gpu:742.8343870360183
Step 29 | loss:1.5194485187530518 lr:3.274193548387096e-05 tokens_per_second_per_gpu:1032.5272242788892
Step 30 | loss:1.6273659467697144 lr:3.387096774193548e-05 tokens_per_second_per_gpu:905.7854832712501
Step 31 | loss:1.6822402477264404 lr:3.5e-05 tokens_per_second_per_gpu:762.3313962939022
Step 32 | loss:1.5448408126831055 lr:3.612903225806451e-05 tokens_per_second_per_gpu:761.3907781656015
Step 33 | loss:1.5540359020233154 lr:3.7258064516129026e-05 tokens_per_second_per_gpu:833.9822316689247
Step 34 | loss:1.6765856742858887 lr:3.838709677419354e-05 tokens_per_second_per_gpu:1080.1591841384711
Step 35 | loss:1.6171495914459229 lr:3.951612903225806e-05 tokens_per_second_per_gpu:974.0088540796335
Step 36 | loss:1.7752655744552612 lr:4.064516129032258e-05 tokens_per_second_per_gpu:778.197438735832
Step 37 | loss:1.6441726684570312 lr:4.177419354838709e-05 tokens_per_second_per_gpu:927.67330627779
Step 38 | loss:1.8777766227722168 lr:4.290322580645161e-05 tokens_per_second_per_gpu:783.4173807189137
Step 39 | loss:1.6890583038330078 lr:4.403225806451613e-05 tokens_per_second_per_gpu:952.4678563631315
Step 40 | loss:1.7100039720535278 lr:4.516129032258064e-05 tokens_per_second_per_gpu:797.2911659202404
Step 41 | loss:1.471923828125 lr:4.629032258064516e-05 tokens_per_second_per_gpu:1063.5221935863974
Step 42 | loss:1.7664284706115723 lr:4.741935483870967e-05 tokens_per_second_per_gpu:854.1397671327078
Step 43 | loss:1.7166632413864136 lr:4.8548387096774194e-05 tokens_per_second_per_gpu:1014.3470982177935
Step 44 | loss:1.7919608354568481 lr:4.967741935483871e-05 tokens_per_second_per_gpu:830.5478538681824
Step 45 | loss:1.6781916618347168 lr:5.080645161290322e-05 tokens_per_second_per_gpu:813.8241454827331
Step 46 | loss:1.5597587823867798 lr:5.193548387096774e-05 tokens_per_second_per_gpu:814.9800186771137
Step 47 | loss:1.5532318353652954 lr:5.306451612903225e-05 tokens_per_second_per_gpu:933.6181317215587
Step 48 | loss:1.7898614406585693 lr:5.419354838709677e-05 tokens_per_second_per_gpu:704.4023226188532
Step 49 | loss:1.5523273944854736 lr:5.532258064516128e-05 tokens_per_second_per_gpu:884.5864828823615
Step 50 | loss:1.5065193176269531 lr:5.64516129032258e-05 tokens_per_second_per_gpu:1359.8586830105712
Step 51 | loss:1.6680551767349243 lr:5.758064516129032e-05 tokens_per_second_per_gpu:969.8778791624561
Step 52 | loss:1.632871150970459 lr:5.870967741935483e-05 tokens_per_second_per_gpu:687.8038928968936
Step 53 | loss:1.504843831062317 lr:5.983870967741935e-05 tokens_per_second_per_gpu:908.760804734065
Step 54 | loss:1.7077339887619019 lr:6.096774193548386e-05 tokens_per_second_per_gpu:909.4074401099201
Step 55 | loss:1.626071572303772 lr:6.209677419354838e-05 tokens_per_second_per_gpu:961.1829053358628
Step 56 | loss:1.6828025579452515 lr:6.322580645161289e-05 tokens_per_second_per_gpu:1068.5051774314886
Step 57 | loss:1.5778956413269043 lr:6.43548387096774e-05 tokens_per_second_per_gpu:1071.241075946676
Step 58 | loss:1.7082544565200806 lr:6.548387096774192e-05 tokens_per_second_per_gpu:866.797292641249
Step 59 | loss:1.6141303777694702 lr:6.661290322580645e-05 tokens_per_second_per_gpu:884.2562603659461
Step 60 | loss:1.5197627544403076 lr:6.774193548387096e-05 tokens_per_second_per_gpu:1082.867206455418
Step 61 | loss:1.703991174697876 lr:6.887096774193548e-05 tokens_per_second_per_gpu:828.0379764180935
Step 62 | loss:1.7141263484954834 lr:7e-05 tokens_per_second_per_gpu:885.0382688275553
Step 63 | loss:1.7276904582977295 lr:6.999999417865911e-05 tokens_per_second_per_gpu:983.6043705764929
Step 64 | loss:1.4434491395950317 lr:6.999997671463839e-05 tokens_per_second_per_gpu:948.1504856711841
Step 65 | loss:1.595259428024292 lr:6.999994760794363e-05 tokens_per_second_per_gpu:910.0224574879678
Step 66 | loss:1.6041765213012695 lr:6.999990685858453e-05 tokens_per_second_per_gpu:803.8166023114039
Step 67 | loss:1.4500466585159302 lr:6.999985446657465e-05 tokens_per_second_per_gpu:836.828100973649
Step 68 | loss:1.49815833568573 lr:6.999979043193139e-05 tokens_per_second_per_gpu:1062.7233015610148
Step 69 | loss:1.5706429481506348 lr:6.999971475467609e-05 tokens_per_second_per_gpu:701.6154676145503
Step 70 | loss:1.4724074602127075 lr:6.99996274348339e-05 tokens_per_second_per_gpu:984.3755127240661
Step 71 | loss:1.582288384437561 lr:6.999952847243387e-05 tokens_per_second_per_gpu:760.370363608151
Step 72 | loss:1.900014877319336 lr:6.999941786750891e-05 tokens_per_second_per_gpu:629.6388396027327
Step 73 | loss:1.6100542545318604 lr:6.999929562009582e-05 tokens_per_second_per_gpu:1085.6663988661242
Step 74 | loss:1.6036285161972046 lr:6.999916173023527e-05 tokens_per_second_per_gpu:867.5689422454932
Step 75 | loss:1.6224753856658936 lr:6.99990161979718e-05 tokens_per_second_per_gpu:1087.6359281635703
Step 76 | loss:1.5261365175247192 lr:6.999885902335382e-05 tokens_per_second_per_gpu:648.771406917056
Step 77 | loss:1.6586790084838867 lr:6.99986902064336e-05 tokens_per_second_per_gpu:924.0921275558014
Step 78 | loss:1.56719172000885 lr:6.999850974726731e-05 tokens_per_second_per_gpu:849.6877728933947
Step 79 | loss:1.7229080200195312 lr:6.999831764591497e-05 tokens_per_second_per_gpu:674.0433222861146
Step 80 | loss:1.5305242538452148 lr:6.99981139024405e-05 tokens_per_second_per_gpu:1093.7440596561003
Step 81 | loss:1.4544587135314941 lr:6.999789851691166e-05 tokens_per_second_per_gpu:1032.2805441919393
Step 82 | loss:1.5519049167633057 lr:6.999767148940011e-05 tokens_per_second_per_gpu:958.8132144256534
Step 83 | loss:1.6529982089996338 lr:6.999743281998134e-05 tokens_per_second_per_gpu:947.8633411393353
Step 84 | loss:1.6023069620132446 lr:6.999718250873478e-05 tokens_per_second_per_gpu:918.0119897283706
Step 85 | loss:1.6600505113601685 lr:6.999692055574368e-05 tokens_per_second_per_gpu:880.4832752929117
Step 86 | loss:1.6575697660446167 lr:6.999664696109517e-05 tokens_per_second_per_gpu:822.3024009242166
Step 87 | loss:1.6785895824432373 lr:6.999636172488027e-05 tokens_per_second_per_gpu:1326.6749337459082
Step 88 | loss:1.6220732927322388 lr:6.999606484719386e-05 tokens_per_second_per_gpu:760.4052010985336
Step 89 | loss:1.5433844327926636 lr:6.99957563281347e-05 tokens_per_second_per_gpu:1108.542149906608
Step 90 | loss:1.7126470804214478 lr:6.999543616780543e-05 tokens_per_second_per_gpu:1019.0785552208517
Step 91 | loss:1.4188913106918335 lr:6.99951043663125e-05 tokens_per_second_per_gpu:1039.4075028601153
Step 92 | loss:1.4532710313796997 lr:6.999476092376636e-05 tokens_per_second_per_gpu:834.0171291627238
Step 93 | loss:1.646336555480957 lr:6.99944058402812e-05 tokens_per_second_per_gpu:703.1370846447331
Step 94 | loss:1.6547026634216309 lr:6.999403911597514e-05 tokens_per_second_per_gpu:641.1244301137946
Step 95 | loss:1.5256538391113281 lr:6.99936607509702e-05 tokens_per_second_per_gpu:1230.999371604001
Step 96 | loss:1.656537413597107 lr:6.999327074539223e-05 tokens_per_second_per_gpu:732.099448199173
Step 97 | loss:1.7180148363113403 lr:6.999286909937094e-05 tokens_per_second_per_gpu:750.4295639501224
Step 98 | loss:1.6072369813919067 lr:6.999245581303997e-05 tokens_per_second_per_gpu:719.14144962244
Step 99 | loss:1.5059998035430908 lr:6.999203088653678e-05 tokens_per_second_per_gpu:862.5220693440218
Step 100 | loss:1.520376443862915 lr:6.999159432000274e-05 tokens_per_second_per_gpu:996.4825849930203
Step 101 | loss:1.7768564224243164 lr:6.999114611358304e-05 tokens_per_second_per_gpu:722.1058491400503
Step 102 | loss:1.6738096475601196 lr:6.999068626742681e-05 tokens_per_second_per_gpu:979.6504685666022
Step 103 | loss:1.7119721174240112 lr:6.9990214781687e-05 tokens_per_second_per_gpu:719.2407729174976
Step 104 | loss:1.5936719179153442 lr:6.998973165652044e-05 tokens_per_second_per_gpu:1002.6162311074271
Step 105 | loss:1.6068568229675293 lr:6.998923689208785e-05 tokens_per_second_per_gpu:790.2781464912238
Step 106 | loss:1.5581554174423218 lr:6.998873048855382e-05 tokens_per_second_per_gpu:904.583124557429
Step 107 | loss:1.515325665473938 lr:6.99882124460868e-05 tokens_per_second_per_gpu:1332.365217872241
Step 108 | loss:1.4969571828842163 lr:6.998768276485911e-05 tokens_per_second_per_gpu:1060.7829175449388
Step 109 | loss:1.8589524030685425 lr:6.998714144504697e-05 tokens_per_second_per_gpu:773.933068533583
Step 110 | loss:1.4987972974777222 lr:6.998658848683041e-05 tokens_per_second_per_gpu:828.8511438490493
Step 111 | loss:1.8489999771118164 lr:6.998602389039338e-05 tokens_per_second_per_gpu:640.6785604719595
Step 112 | loss:1.7067933082580566 lr:6.998544765592372e-05 tokens_per_second_per_gpu:787.8406907526296
Step 113 | loss:1.5916005373001099 lr:6.998485978361309e-05 tokens_per_second_per_gpu:848.0517469982312
Step 114 | loss:1.4837920665740967 lr:6.998426027365705e-05 tokens_per_second_per_gpu:1038.7098573544654
Step 115 | loss:1.6212735176086426 lr:6.998364912625504e-05 tokens_per_second_per_gpu:800.9937588579513
Step 116 | loss:1.5643925666809082 lr:6.998302634161033e-05 tokens_per_second_per_gpu:815.0115381721289
Step 117 | loss:1.6035295724868774 lr:6.99823919199301e-05 tokens_per_second_per_gpu:844.3997246743596
Step 118 | loss:1.64264976978302 lr:6.998174586142538e-05 tokens_per_second_per_gpu:1011.3644155342926
Step 119 | loss:1.633497714996338 lr:6.99810881663111e-05 tokens_per_second_per_gpu:864.0564285644729
Step 120 | loss:1.5561448335647583 lr:6.998041883480603e-05 tokens_per_second_per_gpu:936.6379370649786
Step 121 | loss:1.4813411235809326 lr:6.997973786713283e-05 tokens_per_second_per_gpu:725.0826731187595
Step 122 | loss:1.602975845336914 lr:6.997904526351802e-05 tokens_per_second_per_gpu:862.1939356210884
Step 123 | loss:1.4000455141067505 lr:6.997834102419197e-05 tokens_per_second_per_gpu:1251.0321505383547
Step 124 | loss:1.7196913957595825 lr:6.997762514938899e-05 tokens_per_second_per_gpu:726.598149724212
Step 125 | loss:1.4732083082199097 lr:6.997689763934717e-05 tokens_per_second_per_gpu:702.9806470131382
Step 126 | loss:1.5373691320419312 lr:6.997615849430852e-05 tokens_per_second_per_gpu:816.8217254795126
Step 127 | loss:1.461967945098877 lr:6.997540771451895e-05 tokens_per_second_per_gpu:958.666109982611
Step 128 | loss:1.6879616975784302 lr:6.997464530022816e-05 tokens_per_second_per_gpu:961.1451714568531
Step 129 | loss:1.5735927820205688 lr:6.99738712516898e-05 tokens_per_second_per_gpu:700.8796733762064
Step 130 | loss:1.6471796035766602 lr:6.997308556916135e-05 tokens_per_second_per_gpu:1033.5771577629598
Step 131 | loss:1.4290601015090942 lr:6.997228825290414e-05 tokens_per_second_per_gpu:924.951569153496
Step 132 | loss:1.7325445413589478 lr:6.997147930318344e-05 tokens_per_second_per_gpu:867.3487506333552
Step 133 | loss:1.4006657600402832 lr:6.997065872026831e-05 tokens_per_second_per_gpu:994.1065955020881
Step 134 | loss:1.4656288623809814 lr:6.996982650443173e-05 tokens_per_second_per_gpu:978.6944084757537
Step 135 | loss:1.4871076345443726 lr:6.996898265595053e-05 tokens_per_second_per_gpu:790.7005054551458
Step 136 | loss:1.6286169290542603 lr:6.99681271751054e-05 tokens_per_second_per_gpu:694.6094538073936
Step 137 | loss:1.6337043046951294 lr:6.996726006218095e-05 tokens_per_second_per_gpu:725.3625997574869
Step 138 | loss:1.6244940757751465 lr:6.99663813174656e-05 tokens_per_second_per_gpu:850.1479552954675
Step 139 | loss:1.4376118183135986 lr:6.996549094125165e-05 tokens_per_second_per_gpu:932.2500955542387
Step 140 | loss:1.4010930061340332 lr:6.996458893383532e-05 tokens_per_second_per_gpu:831.0882097305321
Step 141 | loss:1.3553869724273682 lr:6.996367529551663e-05 tokens_per_second_per_gpu:1124.3924330562934
Step 142 | loss:1.6745566129684448 lr:6.996275002659951e-05 tokens_per_second_per_gpu:846.0588567409159
Step 143 | loss:1.5781978368759155 lr:6.996181312739173e-05 tokens_per_second_per_gpu:844.3324321191162
Step 144 | loss:1.4753894805908203 lr:6.996086459820499e-05 tokens_per_second_per_gpu:735.5486785727048
Step 145 | loss:1.5407427549362183 lr:6.995990443935478e-05 tokens_per_second_per_gpu:816.9505276623479
Step 146 | loss:1.5314345359802246 lr:6.995893265116051e-05 tokens_per_second_per_gpu:642.1986761468909
Step 147 | loss:1.5995967388153076 lr:6.995794923394543e-05 tokens_per_second_per_gpu:1180.9006902552026
Step 148 | loss:1.3338483572006226 lr:6.99569541880367e-05 tokens_per_second_per_gpu:1198.9195341294717
Step 149 | loss:1.384743094444275 lr:6.995594751376529e-05 tokens_per_second_per_gpu:901.3600008342561
Step 150 | loss:1.3877229690551758 lr:6.995492921146609e-05 tokens_per_second_per_gpu:1199.3779011640117
Step 151 | loss:1.4935026168823242 lr:6.995389928147782e-05 tokens_per_second_per_gpu:997.0441410871824
Step 152 | loss:1.569211721420288 lr:6.995285772414308e-05 tokens_per_second_per_gpu:657.8038428383379
Step 153 | loss:1.6398520469665527 lr:6.995180453980837e-05 tokens_per_second_per_gpu:738.5394263271123
Step 154 | loss:1.6921911239624023 lr:6.9950739728824e-05 tokens_per_second_per_gpu:877.8250545971426
Step 155 | loss:1.608449101448059 lr:6.99496632915442e-05 tokens_per_second_per_gpu:1024.441500447337
Step 156 | loss:1.778211236000061 lr:6.994857522832704e-05 tokens_per_second_per_gpu:967.4715373717463
Step 157 | loss:1.529779076576233 lr:6.994747553953444e-05 tokens_per_second_per_gpu:1016.6030679801447
Step 158 | loss:1.4308397769927979 lr:6.994636422553223e-05 tokens_per_second_per_gpu:1071.9658568052068
Step 159 | loss:1.5498195886611938 lr:6.994524128669009e-05 tokens_per_second_per_gpu:1020.5863057619473
Step 160 | loss:1.5319161415100098 lr:6.994410672338155e-05 tokens_per_second_per_gpu:834.3816988532393
Step 161 | loss:1.4881232976913452 lr:6.994296053598403e-05 tokens_per_second_per_gpu:1200.7741110160055
Step 162 | loss:1.3962006568908691 lr:6.99418027248788e-05 tokens_per_second_per_gpu:828.142733648943
Step 163 | loss:1.6262855529785156 lr:6.994063329045102e-05 tokens_per_second_per_gpu:844.4445944846555
Step 164 | loss:1.7245620489120483 lr:6.993945223308966e-05 tokens_per_second_per_gpu:767.8397441753116
Step 165 | loss:1.6927422285079956 lr:6.993825955318764e-05 tokens_per_second_per_gpu:776.4387216865937
Step 166 | loss:1.5959572792053223 lr:6.993705525114168e-05 tokens_per_second_per_gpu:810.4960885906128
Step 167 | loss:1.71640944480896 lr:6.993583932735241e-05 tokens_per_second_per_gpu:860.2036295167903
Step 168 | loss:1.458530306816101 lr:6.993461178222427e-05 tokens_per_second_per_gpu:1077.8427599186696
Step 169 | loss:1.4464802742004395 lr:6.993337261616563e-05 tokens_per_second_per_gpu:1096.7993317871628
Step 170 | loss:1.7336957454681396 lr:6.993212182958869e-05 tokens_per_second_per_gpu:897.2522040932329
Step 171 | loss:1.4159715175628662 lr:6.993085942290951e-05 tokens_per_second_per_gpu:919.8241116882036
Step 172 | loss:1.4930012226104736 lr:6.992958539654804e-05 tokens_per_second_per_gpu:952.8921999152433
Step 173 | loss:1.5822491645812988 lr:6.992829975092807e-05 tokens_per_second_per_gpu:852.8154577248458
Step 174 | loss:1.4605530500411987 lr:6.992700248647727e-05 tokens_per_second_per_gpu:984.8927937903287
Step 175 | loss:1.7075344324111938 lr:6.992569360362719e-05 tokens_per_second_per_gpu:881.5504698576804
Step 176 | loss:1.565678596496582 lr:6.992437310281322e-05 tokens_per_second_per_gpu:834.2865024499073
Step 177 | loss:1.6125026941299438 lr:6.99230409844746e-05 tokens_per_second_per_gpu:756.869186299435
Step 178 | loss:1.6954333782196045 lr:6.992169724905448e-05 tokens_per_second_per_gpu:753.8518901411667
Step 179 | loss:1.6144452095031738 lr:6.992034189699984e-05 tokens_per_second_per_gpu:825.9048808486093
Step 180 | loss:1.7361313104629517 lr:6.991897492876155e-05 tokens_per_second_per_gpu:822.2566063555988
Step 181 | loss:1.738999605178833 lr:6.991759634479431e-05 tokens_per_second_per_gpu:700.2266880687641
Step 182 | loss:1.6851012706756592 lr:6.99162061455567e-05 tokens_per_second_per_gpu:654.0892673387308
Step 183 | loss:1.3386107683181763 lr:6.991480433151121e-05 tokens_per_second_per_gpu:1063.5357650581109
Step 184 | loss:1.4072189331054688 lr:6.99133909031241e-05 tokens_per_second_per_gpu:997.7346610295651
Step 185 | loss:1.4177030324935913 lr:6.991196586086557e-05 tokens_per_second_per_gpu:951.1852266086595
Step 186 | loss:1.4668126106262207 lr:6.991052920520964e-05 tokens_per_second_per_gpu:1141.8440920692067
Step 187 | loss:1.4368221759796143 lr:6.990908093663424e-05 tokens_per_second_per_gpu:1160.722659006549
Step 188 | loss:1.6529415845870972 lr:6.99076210556211e-05 tokens_per_second_per_gpu:828.255708557912
Step 189 | loss:1.407317876815796 lr:6.990614956265587e-05 tokens_per_second_per_gpu:814.8451540442833
Step 190 | loss:1.5548444986343384 lr:6.990466645822803e-05 tokens_per_second_per_gpu:860.0270022664878
Step 191 | loss:1.501901626586914 lr:6.990317174283093e-05 tokens_per_second_per_gpu:1320.0690406032988
Step 192 | loss:1.5812482833862305 lr:6.99016654169618e-05 tokens_per_second_per_gpu:833.9932201924443
Step 193 | loss:1.5461926460266113 lr:6.99001474811217e-05 tokens_per_second_per_gpu:948.251263187751
Step 194 | loss:1.5906845331192017 lr:6.989861793581555e-05 tokens_per_second_per_gpu:966.3947268095201
Step 195 | loss:1.7674702405929565 lr:6.98970767815522e-05 tokens_per_second_per_gpu:864.100611751623
Step 196 | loss:1.548424243927002 lr:6.989552401884427e-05 tokens_per_second_per_gpu:1083.188838615935
Step 197 | loss:1.4919466972351074 lr:6.989395964820831e-05 tokens_per_second_per_gpu:922.5171240147304
Step 198 | loss:1.5692211389541626 lr:6.989238367016469e-05 tokens_per_second_per_gpu:1071.0513241163787
Step 199 | loss:1.4429380893707275 lr:6.989079608523766e-05 tokens_per_second_per_gpu:758.975631431409
Step 200 | loss:1.4253145456314087 lr:6.988919689395532e-05 tokens_per_second_per_gpu:741.2058980081509
Step 201 | loss:1.4674817323684692 lr:6.988758609684963e-05 tokens_per_second_per_gpu:838.7349503754102
Step 202 | loss:1.6192876100540161 lr:6.988596369445646e-05 tokens_per_second_per_gpu:1059.9647410258676
Step 203 | loss:1.523248314857483 lr:6.988432968731546e-05 tokens_per_second_per_gpu:847.0696076023023
Step 204 | loss:1.5370584726333618 lr:6.988268407597019e-05 tokens_per_second_per_gpu:912.4864173580373
Step 205 | loss:1.5746548175811768 lr:6.988102686096806e-05 tokens_per_second_per_gpu:868.5150017113492
Step 206 | loss:1.559701919555664 lr:6.987935804286033e-05 tokens_per_second_per_gpu:1050.1030669657684
Step 207 | loss:1.463262915611267 lr:6.987767762220216e-05 tokens_per_second_per_gpu:862.0652016301744
Step 208 | loss:1.375932216644287 lr:6.98759855995525e-05 tokens_per_second_per_gpu:844.6819847448595
Step 209 | loss:1.4861067533493042 lr:6.987428197547422e-05 tokens_per_second_per_gpu:885.8228970576861
Step 210 | loss:1.5941404104232788 lr:6.987256675053403e-05 tokens_per_second_per_gpu:843.6081736103876
Step 211 | loss:1.6557344198226929 lr:6.987083992530248e-05 tokens_per_second_per_gpu:964.3278946726251
Step 212 | loss:1.5609114170074463 lr:6.986910150035401e-05 tokens_per_second_per_gpu:723.8814262457222
Step 213 | loss:1.2880934476852417 lr:6.986735147626689e-05 tokens_per_second_per_gpu:1065.558843489467
Step 214 | loss:1.5829898118972778 lr:6.986558985362327e-05 tokens_per_second_per_gpu:1034.675483295791
Step 215 | loss:1.7630797624588013 lr:6.986381663300916e-05 tokens_per_second_per_gpu:760.9629620940168
Step 216 | loss:1.458760142326355 lr:6.98620318150144e-05 tokens_per_second_per_gpu:884.3860507222232
Step 217 | loss:1.8102298974990845 lr:6.986023540023271e-05 tokens_per_second_per_gpu:539.0428007216642
Step 218 | loss:1.5738167762756348 lr:6.985842738926167e-05 tokens_per_second_per_gpu:713.0728951194782
Step 219 | loss:1.482662320137024 lr:6.985660778270272e-05 tokens_per_second_per_gpu:969.010394881622
Step 220 | loss:1.5874923467636108 lr:6.985477658116112e-05 tokens_per_second_per_gpu:781.904948255101
Step 221 | loss:1.506540298461914 lr:6.985293378524606e-05 tokens_per_second_per_gpu:838.2622269544025
Step 222 | loss:1.6458890438079834 lr:6.985107939557049e-05 tokens_per_second_per_gpu:610.2029816245077
Step 223 | loss:1.4284083843231201 lr:6.984921341275131e-05 tokens_per_second_per_gpu:882.7757886425429
Step 224 | loss:1.6485854387283325 lr:6.984733583740922e-05 tokens_per_second_per_gpu:988.17431451133
Step 225 | loss:1.5823767185211182 lr:6.98454466701688e-05 tokens_per_second_per_gpu:1024.2815084759459
Step 226 | loss:1.4947177171707153 lr:6.984354591165845e-05 tokens_per_second_per_gpu:1090.8479338781274
Step 227 | loss:1.5037306547164917 lr:6.984163356251049e-05 tokens_per_second_per_gpu:964.6019585242308
Step 228 | loss:1.3998370170593262 lr:6.983970962336104e-05 tokens_per_second_per_gpu:978.3129497968562
Step 229 | loss:1.55945885181427 lr:6.98377740948501e-05 tokens_per_second_per_gpu:802.0699266454362
Step 230 | loss:1.7152963876724243 lr:6.983582697762151e-05 tokens_per_second_per_gpu:632.4007065185604
Step 231 | loss:1.5049721002578735 lr:6.983386827232298e-05 tokens_per_second_per_gpu:956.4228678392225
Step 232 | loss:1.4165095090866089 lr:6.98318979796061e-05 tokens_per_second_per_gpu:1018.0901274250236
Step 233 | loss:1.6309311389923096 lr:6.982991610012622e-05 tokens_per_second_per_gpu:926.7130718079105
Step 234 | loss:1.5017359256744385 lr:6.982792263454267e-05 tokens_per_second_per_gpu:924.1969196487211
Step 235 | loss:1.7331749200820923 lr:6.982591758351854e-05 tokens_per_second_per_gpu:607.0450227286879
Step 236 | loss:1.5987502336502075 lr:6.982390094772079e-05 tokens_per_second_per_gpu:860.0943369670085
Step 237 | loss:1.5423567295074463 lr:6.98218727278203e-05 tokens_per_second_per_gpu:955.6564202739332
Step 238 | loss:1.4801902770996094 lr:6.981983292449172e-05 tokens_per_second_per_gpu:1126.5884194286555
Step 239 | loss:1.7091809511184692 lr:6.98177815384136e-05 tokens_per_second_per_gpu:822.1123710330246
Step 240 | loss:1.6220842599868774 lr:6.98157185702683e-05 tokens_per_second_per_gpu:1001.9763278026969
Step 241 | loss:1.5040488243103027 lr:6.981364402074212e-05 tokens_per_second_per_gpu:987.9487025037613
Step 242 | loss:1.650405764579773 lr:6.981155789052509e-05 tokens_per_second_per_gpu:769.9688793931103
Step 243 | loss:1.4898853302001953 lr:6.98094601803112e-05 tokens_per_second_per_gpu:980.062961262619
Step 244 | loss:1.511583685874939 lr:6.980735089079823e-05 tokens_per_second_per_gpu:956.9012146545376
Step 245 | loss:1.4910686016082764 lr:6.980523002268784e-05 tokens_per_second_per_gpu:993.7939023884701
Step 246 | loss:1.543348789215088 lr:6.980309757668554e-05 tokens_per_second_per_gpu:991.0344508179589
Step 247 | loss:1.7118194103240967 lr:6.980095355350066e-05 tokens_per_second_per_gpu:684.5379218670216
Step 248 | loss:1.4292041063308716 lr:6.979879795384643e-05 tokens_per_second_per_gpu:962.9301639663892
Step 249 | loss:1.478188157081604 lr:6.979663077843988e-05 tokens_per_second_per_gpu:1172.5585789709914
Step 250 | loss:1.5731818675994873 lr:6.979445202800195e-05 tokens_per_second_per_gpu:816.4350712051331
Step 251 | loss:1.570388913154602 lr:6.979226170325737e-05 tokens_per_second_per_gpu:941.7338542008006
Step 252 | loss:1.6071324348449707 lr:6.979005980493475e-05 tokens_per_second_per_gpu:869.0277383036434
Step 253 | loss:1.4709789752960205 lr:6.978784633376657e-05 tokens_per_second_per_gpu:1085.2495029199374
Step 254 | loss:1.5094796419143677 lr:6.978562129048909e-05 tokens_per_second_per_gpu:1032.4609211665586
Step 255 | loss:1.4953768253326416 lr:6.978338467584252e-05 tokens_per_second_per_gpu:972.2411779847247
Step 256 | loss:1.3905484676361084 lr:6.978113649057084e-05 tokens_per_second_per_gpu:846.059705664156
Step 257 | loss:1.4913915395736694 lr:6.97788767354219e-05 tokens_per_second_per_gpu:971.4623104095801
Step 258 | loss:1.6137416362762451 lr:6.977660541114742e-05 tokens_per_second_per_gpu:641.1375519687926
Step 259 | loss:1.6223844289779663 lr:6.977432251850294e-05 tokens_per_second_per_gpu:980.6421388939889
Step 260 | loss:1.5287225246429443 lr:6.977202805824785e-05 tokens_per_second_per_gpu:823.0857092757904
Step 261 | loss:1.5038204193115234 lr:6.976972203114542e-05 tokens_per_second_per_gpu:737.9846952117852
Step 262 | loss:1.655437707901001 lr:6.976740443796273e-05 tokens_per_second_per_gpu:670.7850229032795
Step 263 | loss:1.5771842002868652 lr:6.976507527947072e-05 tokens_per_second_per_gpu:860.686136152339
Step 264 | loss:1.6077855825424194 lr:6.97627345564442e-05 tokens_per_second_per_gpu:681.1113292545839
Step 265 | loss:1.4051659107208252 lr:6.976038226966178e-05 tokens_per_second_per_gpu:1012.3716110654699
Step 266 | loss:1.5400166511535645 lr:6.975801841990597e-05 tokens_per_second_per_gpu:958.9226233298585
Step 267 | loss:1.472543716430664 lr:6.975564300796308e-05 tokens_per_second_per_gpu:1160.0380324621017
Step 268 | loss:1.5389546155929565 lr:6.975325603462329e-05 tokens_per_second_per_gpu:793.2344303811348
Step 269 | loss:1.52685546875 lr:6.975085750068064e-05 tokens_per_second_per_gpu:752.1890409351107
Step 270 | loss:1.5628944635391235 lr:6.974844740693298e-05 tokens_per_second_per_gpu:778.6277478462141
Step 271 | loss:1.5800570249557495 lr:6.974602575418201e-05 tokens_per_second_per_gpu:1117.3537799488363
Step 272 | loss:1.5939648151397705 lr:6.974359254323332e-05 tokens_per_second_per_gpu:966.1050803469194
Step 273 | loss:1.5766239166259766 lr:6.974114777489629e-05 tokens_per_second_per_gpu:1017.4360761959955
Step 274 | loss:1.464521884918213 lr:6.973869144998419e-05 tokens_per_second_per_gpu:1073.2837437753776
Step 275 | loss:1.5652427673339844 lr:6.973622356931407e-05 tokens_per_second_per_gpu:1054.7503665827894
Step 276 | loss:1.3216384649276733 lr:6.973374413370692e-05 tokens_per_second_per_gpu:600.8663246023466
Step 277 | loss:1.3814414739608765 lr:6.973125314398746e-05 tokens_per_second_per_gpu:1021.3186697584135
Step 278 | loss:1.5562095642089844 lr:6.972875060098437e-05 tokens_per_second_per_gpu:655.5921915156764
Step 279 | loss:1.694250226020813 lr:6.972623650553009e-05 tokens_per_second_per_gpu:865.4847918169099
Step 280 | loss:1.5131744146347046 lr:6.972371085846092e-05 tokens_per_second_per_gpu:1014.9854545066354
Step 281 | loss:1.6601924896240234 lr:6.972117366061702e-05 tokens_per_second_per_gpu:731.0648637105031
Step 282 | loss:1.584885597229004 lr:6.971862491284239e-05 tokens_per_second_per_gpu:796.531693308557
Step 283 | loss:1.493424892425537 lr:6.971606461598485e-05 tokens_per_second_per_gpu:1074.9862869666858
Step 284 | loss:1.5328853130340576 lr:6.971349277089611e-05 tokens_per_second_per_gpu:919.2745636294057
Step 285 | loss:1.5829651355743408 lr:6.971090937843164e-05 tokens_per_second_per_gpu:899.4463969939852
Step 286 | loss:1.466881275177002 lr:6.970831443945085e-05 tokens_per_second_per_gpu:799.2082400920966
Step 287 | loss:1.5790421962738037 lr:6.970570795481692e-05 tokens_per_second_per_gpu:952.2412844366995
Step 288 | loss:1.5136933326721191 lr:6.970308992539689e-05 tokens_per_second_per_gpu:768.2888311281398
Step 289 | loss:1.6245635747909546 lr:6.970046035206163e-05 tokens_per_second_per_gpu:977.9410343104495
Step 290 | loss:1.6402101516723633 lr:6.969781923568589e-05 tokens_per_second_per_gpu:662.3519686735706
Step 291 | loss:1.555562138557434 lr:6.969516657714822e-05 tokens_per_second_per_gpu:660.4937984076325
Step 292 | loss:1.5314357280731201 lr:6.969250237733102e-05 tokens_per_second_per_gpu:1071.6225100358297
Step 293 | loss:1.584568977355957 lr:6.968982663712052e-05 tokens_per_second_per_gpu:753.6729677299178
Step 294 | loss:1.6601026058197021 lr:6.968713935740682e-05 tokens_per_second_per_gpu:526.4568585924719
Step 295 | loss:1.5559685230255127 lr:6.968444053908383e-05 tokens_per_second_per_gpu:936.5615183298461
Step 296 | loss:1.620733618736267 lr:6.96817301830493e-05 tokens_per_second_per_gpu:710.7007099167449
Step 297 | loss:1.6172351837158203 lr:6.967900829020483e-05 tokens_per_second_per_gpu:957.3884744417336
Step 298 | loss:1.511078953742981 lr:6.967627486145588e-05 tokens_per_second_per_gpu:912.816906331521
Step 299 | loss:1.4365206956863403 lr:6.967352989771167e-05 tokens_per_second_per_gpu:1032.4399984037682
Step 300 | loss:1.4246803522109985 lr:6.967077339988533e-05 tokens_per_second_per_gpu:889.5696536288073
Step 301 | loss:1.4987661838531494 lr:6.966800536889379e-05 tokens_per_second_per_gpu:945.8796910527807
Step 302 | loss:1.5682265758514404 lr:6.966522580565787e-05 tokens_per_second_per_gpu:838.5975157541772
Step 303 | loss:1.5350528955459595 lr:6.966243471110214e-05 tokens_per_second_per_gpu:757.9731983679126
Step 304 | loss:1.631470799446106 lr:6.96596320861551e-05 tokens_per_second_per_gpu:1093.0736247320551
Step 305 | loss:1.4214205741882324 lr:6.965681793174897e-05 tokens_per_second_per_gpu:769.0877368725039
Step 306 | loss:1.6964809894561768 lr:6.965399224881994e-05 tokens_per_second_per_gpu:644.0854078253578
Step 307 | loss:1.451163649559021 lr:6.965115503830793e-05 tokens_per_second_per_gpu:1076.0515019807847
Step 308 | loss:1.5099592208862305 lr:6.964830630115676e-05 tokens_per_second_per_gpu:859.6529813476984
Step 309 | loss:1.5524368286132812 lr:6.964544603831402e-05 tokens_per_second_per_gpu:1011.7474345876637
Step 310 | loss:1.3470464944839478 lr:6.96425742507312e-05 tokens_per_second_per_gpu:1055.5722000717885
Step 311 | loss:1.555511713027954 lr:6.963969093936357e-05 tokens_per_second_per_gpu:1166.9053886759395
Step 312 | loss:1.5933717489242554 lr:6.96367961051703e-05 tokens_per_second_per_gpu:1112.4287802577373
Step 313 | loss:1.4843116998672485 lr:6.963388974911431e-05 tokens_per_second_per_gpu:933.7764957677504
Step 314 | loss:1.564257264137268 lr:6.96309718721624e-05 tokens_per_second_per_gpu:841.8413003699551
Step 315 | loss:1.6782293319702148 lr:6.962804247528522e-05 tokens_per_second_per_gpu:546.545144198349
Step 316 | loss:1.6459660530090332 lr:6.96251015594572e-05 tokens_per_second_per_gpu:831.0993877353676
Step 317 | loss:1.2849496603012085 lr:6.962214912565664e-05 tokens_per_second_per_gpu:942.974061127069
Step 318 | loss:1.7010904550552368 lr:6.961918517486567e-05 tokens_per_second_per_gpu:699.4621187177714
Step 319 | loss:1.6640723943710327 lr:6.961620970807025e-05 tokens_per_second_per_gpu:748.9309570841451
Step 320 | loss:1.6050597429275513 lr:6.961322272626012e-05 tokens_per_second_per_gpu:955.577063194166
Step 321 | loss:1.4868018627166748 lr:6.961022423042895e-05 tokens_per_second_per_gpu:739.4921935305181
Step 322 | loss:1.5560009479522705 lr:6.960721422157414e-05 tokens_per_second_per_gpu:972.8659994568858
Step 323 | loss:1.3443999290466309 lr:6.960419270069699e-05 tokens_per_second_per_gpu:1282.4980371166776
Step 324 | loss:1.519376277923584 lr:6.960115966880258e-05 tokens_per_second_per_gpu:1126.3912234257568
Step 325 | loss:1.5427837371826172 lr:6.959811512689987e-05 tokens_per_second_per_gpu:734.9728465209799
Step 326 | loss:1.5395493507385254 lr:6.959505907600159e-05 tokens_per_second_per_gpu:1056.3656284270353
Step 327 | loss:1.41294264793396 lr:6.959199151712436e-05 tokens_per_second_per_gpu:1055.347185267762
Step 328 | loss:1.481369137763977 lr:6.958891245128858e-05 tokens_per_second_per_gpu:1085.0249965089315
Step 329 | loss:1.604426383972168 lr:6.958582187951851e-05 tokens_per_second_per_gpu:613.8140659232574
Step 330 | loss:1.6234022378921509 lr:6.958271980284218e-05 tokens_per_second_per_gpu:793.9418730545012
Step 331 | loss:1.412779450416565 lr:6.957960622229154e-05 tokens_per_second_per_gpu:878.7936963805076
Step 332 | loss:1.416698694229126 lr:6.957648113890229e-05 tokens_per_second_per_gpu:1042.1981021086924
Step 333 | loss:1.5887916088104248 lr:6.957334455371402e-05 tokens_per_second_per_gpu:828.0969447256646
Step 334 | loss:1.7132370471954346 lr:6.957019646777004e-05 tokens_per_second_per_gpu:893.431204673167
Step 335 | loss:1.3429412841796875 lr:6.956703688211762e-05 tokens_per_second_per_gpu:986.1808266345977
Step 336 | loss:1.4903091192245483 lr:6.956386579780775e-05 tokens_per_second_per_gpu:944.1468319987882
Step 337 | loss:1.470731258392334 lr:6.956068321589531e-05 tokens_per_second_per_gpu:732.0037013513025
Step 338 | loss:1.4606927633285522 lr:6.955748913743895e-05 tokens_per_second_per_gpu:659.3435516274891
Step 339 | loss:1.4727917909622192 lr:6.95542835635012e-05 tokens_per_second_per_gpu:1320.0621357642235
Step 340 | loss:1.6682060956954956 lr:6.955106649514839e-05 tokens_per_second_per_gpu:917.1835796325265
Step 341 | loss:1.4091004133224487 lr:6.954783793345066e-05 tokens_per_second_per_gpu:1016.50880731686
Step 342 | loss:1.3398879766464233 lr:6.954459787948198e-05 tokens_per_second_per_gpu:1047.5767523985328
Step 343 | loss:1.5514867305755615 lr:6.954134633432015e-05 tokens_per_second_per_gpu:743.450930942635
Step 344 | loss:1.9211198091506958 lr:6.95380832990468e-05 tokens_per_second_per_gpu:600.0025249535405
Step 345 | loss:1.4464994668960571 lr:6.953480877474737e-05 tokens_per_second_per_gpu:1028.0676869011677
Step 346 | loss:1.577939748764038 lr:6.953152276251113e-05 tokens_per_second_per_gpu:1009.5226512469778
Step 347 | loss:1.4645854234695435 lr:6.952822526343113e-05 tokens_per_second_per_gpu:894.5845989456484
Step 348 | loss:1.5308189392089844 lr:6.952491627860432e-05 tokens_per_second_per_gpu:785.676942243652
Step 349 | loss:1.4769388437271118 lr:6.952159580913142e-05 tokens_per_second_per_gpu:1014.7285182794939
Step 350 | loss:1.6579110622406006 lr:6.951826385611695e-05 tokens_per_second_per_gpu:737.8280247440196
Step 351 | loss:1.3760801553726196 lr:6.951492042066931e-05 tokens_per_second_per_gpu:1022.0699308146119
Step 352 | loss:1.5444934368133545 lr:6.951156550390067e-05 tokens_per_second_per_gpu:759.7013518676271
Step 353 | loss:1.4745248556137085 lr:6.950819910692703e-05 tokens_per_second_per_gpu:981.9860946731567
Step 354 | loss:1.484668254852295 lr:6.950482123086822e-05 tokens_per_second_per_gpu:757.3031629961201
Step 355 | loss:1.5375677347183228 lr:6.950143187684791e-05 tokens_per_second_per_gpu:829.4081774806666
Step 356 | loss:1.5081202983856201 lr:6.949803104599353e-05 tokens_per_second_per_gpu:819.4305714150019
Step 357 | loss:1.487257480621338 lr:6.949461873943638e-05 tokens_per_second_per_gpu:678.8548392347928
Step 358 | loss:1.4858607053756714 lr:6.949119495831153e-05 tokens_per_second_per_gpu:1034.6986887698936
Step 359 | loss:1.5773330926895142 lr:6.948775970375793e-05 tokens_per_second_per_gpu:904.1487168323937
Step 360 | loss:1.4777635335922241 lr:6.948431297691828e-05 tokens_per_second_per_gpu:934.2847647860535
Step 361 | loss:1.5936270952224731 lr:6.948085477893915e-05 tokens_per_second_per_gpu:618.3810716909637
Step 362 | loss:1.5821480751037598 lr:6.947738511097089e-05 tokens_per_second_per_gpu:896.4697283786169
Step 363 | loss:1.6692744493484497 lr:6.947390397416766e-05 tokens_per_second_per_gpu:869.4287546217588
Step 364 | loss:1.4162110090255737 lr:6.94704113696875e-05 tokens_per_second_per_gpu:806.6886066985049
Step 365 | loss:1.5115970373153687 lr:6.946690729869218e-05 tokens_per_second_per_gpu:1111.4118929312986
Step 366 | loss:1.5690240859985352 lr:6.946339176234734e-05 tokens_per_second_per_gpu:934.7458457796207
Step 367 | loss:1.408701777458191 lr:6.945986476182241e-05 tokens_per_second_per_gpu:982.1697878151788
Step 368 | loss:1.6677463054656982 lr:6.945632629829064e-05 tokens_per_second_per_gpu:918.6423827987117
Step 369 | loss:1.4871093034744263 lr:6.945277637292909e-05 tokens_per_second_per_gpu:858.8566272842298
Step 370 | loss:1.621464490890503 lr:6.944921498691864e-05 tokens_per_second_per_gpu:745.1475590104887
Step 371 | loss:1.5724531412124634 lr:6.944564214144399e-05 tokens_per_second_per_gpu:837.2884223192967
Step 372 | loss:1.540191650390625 lr:6.944205783769362e-05 tokens_per_second_per_gpu:795.0880385662786
Step 373 | loss:1.6935925483703613 lr:6.943846207685984e-05 tokens_per_second_per_gpu:670.4091485792893
Step 374 | loss:1.5947784185409546 lr:6.94348548601388e-05 tokens_per_second_per_gpu:741.791217680797
Step 375 | loss:1.345237374305725 lr:6.943123618873039e-05 tokens_per_second_per_gpu:982.7327353100424
Step 376 | loss:1.4654536247253418 lr:6.942760606383841e-05 tokens_per_second_per_gpu:921.9114685468659
Step 377 | loss:1.6039882898330688 lr:6.942396448667037e-05 tokens_per_second_per_gpu:824.139755749614
Step 378 | loss:1.6319787502288818 lr:6.942031145843765e-05 tokens_per_second_per_gpu:743.037868623723
Step 379 | loss:1.4023418426513672 lr:6.94166469803554e-05 tokens_per_second_per_gpu:1181.3607315054371
Step 380 | loss:1.6175686120986938 lr:6.941297105364265e-05 tokens_per_second_per_gpu:939.2442640309201
Step 381 | loss:1.4804455041885376 lr:6.940928367952213e-05 tokens_per_second_per_gpu:731.0729045397328
Step 382 | loss:1.6651806831359863 lr:6.94055848592205e-05 tokens_per_second_per_gpu:757.1864453117374
Step 383 | loss:1.3625235557556152 lr:6.940187459396812e-05 tokens_per_second_per_gpu:826.8357826385513
Step 384 | loss:1.5305567979812622 lr:6.939815288499922e-05 tokens_per_second_per_gpu:860.4498405203399
Step 385 | loss:1.3735322952270508 lr:6.939441973355182e-05 tokens_per_second_per_gpu:1095.7975217736719
Step 386 | loss:1.4865624904632568 lr:6.939067514086774e-05 tokens_per_second_per_gpu:1119.8283674410386
Step 387 | loss:1.473279595375061 lr:6.93869191081926e-05 tokens_per_second_per_gpu:898.3378893502023
Step 388 | loss:1.5299307107925415 lr:6.938315163677587e-05 tokens_per_second_per_gpu:739.9529653044907
Step 389 | loss:1.722416639328003 lr:6.937937272787077e-05 tokens_per_second_per_gpu:719.1413830964543
Step 390 | loss:1.678053617477417 lr:6.937558238273434e-05 tokens_per_second_per_gpu:834.847886655585
Step 391 | loss:1.472644567489624 lr:6.937178060262744e-05 tokens_per_second_per_gpu:985.7871098241962
Step 392 | loss:1.3863099813461304 lr:6.936796738881473e-05 tokens_per_second_per_gpu:811.0151465838211
Step 393 | loss:1.566141963005066 lr:6.936414274256466e-05 tokens_per_second_per_gpu:712.5190590640455
Step 394 | loss:1.6406713724136353 lr:6.936030666514949e-05 tokens_per_second_per_gpu:684.9678471907711
Step 395 | loss:1.3768755197525024 lr:6.93564591578453e-05 tokens_per_second_per_gpu:1026.6291173898724
Step 396 | loss:1.4506199359893799 lr:6.935260022193193e-05 tokens_per_second_per_gpu:964.4803798968667
Step 397 | loss:1.5396572351455688 lr:6.934872985869307e-05 tokens_per_second_per_gpu:815.0942584391457
Step 398 | loss:1.470894455909729 lr:6.934484806941617e-05 tokens_per_second_per_gpu:882.5558444083528
Step 399 | loss:1.4938737154006958 lr:6.934095485539252e-05 tokens_per_second_per_gpu:901.6406161120558
Step 400 | loss:1.666697382926941 lr:6.933705021791716e-05 tokens_per_second_per_gpu:957.910228022483
Step 401 | loss:1.6380614042282104 lr:6.9333134158289e-05 tokens_per_second_per_gpu:713.9322615283505
Step 402 | loss:1.4118309020996094 lr:6.932920667781069e-05 tokens_per_second_per_gpu:1041.0528712625455
Step 403 | loss:1.5669223070144653 lr:6.932526777778868e-05 tokens_per_second_per_gpu:1063.542489352699
Step 404 | loss:1.5610523223876953 lr:6.932131745953327e-05 tokens_per_second_per_gpu:721.9073845626899
Step 405 | loss:1.483641266822815 lr:6.931735572435851e-05 tokens_per_second_per_gpu:811.0883259844067
Step 406 | loss:1.420904517173767 lr:6.931338257358225e-05 tokens_per_second_per_gpu:1230.2702132474728
Step 407 | loss:1.5129389762878418 lr:6.930939800852618e-05 tokens_per_second_per_gpu:931.325738864547
Step 408 | loss:1.4987322092056274 lr:6.930540203051575e-05 tokens_per_second_per_gpu:1152.0170636087055
Step 409 | loss:1.6101056337356567 lr:6.930139464088018e-05 tokens_per_second_per_gpu:918.0861675447708
Step 410 | loss:1.6036624908447266 lr:6.929737584095257e-05 tokens_per_second_per_gpu:793.4246419305861
Step 411 | loss:1.671818733215332 lr:6.929334563206973e-05 tokens_per_second_per_gpu:833.0744463963368
Step 412 | loss:1.4902690649032593 lr:6.928930401557233e-05 tokens_per_second_per_gpu:1231.132583559107
Step 413 | loss:1.4949760437011719 lr:6.928525099280477e-05 tokens_per_second_per_gpu:1068.3232042387256
Step 414 | loss:1.5313208103179932 lr:6.928118656511532e-05 tokens_per_second_per_gpu:886.2982431199957
Step 415 | loss:1.7192401885986328 lr:6.927711073385597e-05 tokens_per_second_per_gpu:760.1058458588072
Step 416 | loss:1.5318173170089722 lr:6.927302350038257e-05 tokens_per_second_per_gpu:842.4993705033116
Step 417 | loss:1.6034945249557495 lr:6.926892486605469e-05 tokens_per_second_per_gpu:870.8882364579812
Step 418 | loss:1.351113200187683 lr:6.926481483223576e-05 tokens_per_second_per_gpu:1225.857941777835
Step 419 | loss:1.5995118618011475 lr:6.926069340029299e-05 tokens_per_second_per_gpu:745.8951978755086
Step 420 | loss:1.5300723314285278 lr:6.925656057159734e-05 tokens_per_second_per_gpu:829.4528885303785
Step 421 | loss:1.3998074531555176 lr:6.925241634752358e-05 tokens_per_second_per_gpu:971.328962046962
Step 422 | loss:1.4467108249664307 lr:6.924826072945029e-05 tokens_per_second_per_gpu:944.8093135473083
Step 423 | loss:1.553359866142273 lr:6.924409371875983e-05 tokens_per_second_per_gpu:767.7353833099907
Step 424 | loss:1.5116989612579346 lr:6.923991531683836e-05 tokens_per_second_per_gpu:1017.5334804965295
Step 425 | loss:1.2684221267700195 lr:6.923572552507579e-05 tokens_per_second_per_gpu:1103.4334718130544
Step 426 | loss:1.6463594436645508 lr:6.923152434486588e-05 tokens_per_second_per_gpu:725.0977935512709
Step 427 | loss:1.7313868999481201 lr:6.922731177760611e-05 tokens_per_second_per_gpu:785.9401802674229
Step 428 | loss:1.4218131303787231 lr:6.92230878246978e-05 tokens_per_second_per_gpu:1016.5012441547633
Step 429 | loss:1.507146954536438 lr:6.921885248754604e-05 tokens_per_second_per_gpu:829.4969105571838
Step 430 | loss:1.3873966932296753 lr:6.921460576755971e-05 tokens_per_second_per_gpu:982.0015191833262
Step 431 | loss:1.3968567848205566 lr:6.921034766615147e-05 tokens_per_second_per_gpu:793.230236296953
Step 432 | loss:1.5761691331863403 lr:6.920607818473774e-05 tokens_per_second_per_gpu:779.2618232753307
Step 433 | loss:1.6064120531082153 lr:6.92017973247388e-05 tokens_per_second_per_gpu:994.8268502088249
Step 434 | loss:1.6997668743133545 lr:6.919750508757865e-05 tokens_per_second_per_gpu:824.8807015812921
Step 435 | loss:1.464605450630188 lr:6.919320147468509e-05 tokens_per_second_per_gpu:1108.697230051449
Step 436 | loss:1.6270315647125244 lr:6.918888648748973e-05 tokens_per_second_per_gpu:810.9563122369145
Step 437 | loss:1.644649624824524 lr:6.91845601274279e-05 tokens_per_second_per_gpu:763.1882751573689
Step 438 | loss:1.709815502166748 lr:6.91802223959388e-05 tokens_per_second_per_gpu:838.9562564535127
Step 439 | loss:1.4667950868606567 lr:6.917587329446533e-05 tokens_per_second_per_gpu:920.884770485538
Step 440 | loss:1.5266820192337036 lr:6.917151282445424e-05 tokens_per_second_per_gpu:891.6699289267257
Step 441 | loss:1.410148024559021 lr:6.916714098735604e-05 tokens_per_second_per_gpu:1057.0570554986343
Step 442 | loss:1.6494797468185425 lr:6.916275778462495e-05 tokens_per_second_per_gpu:849.6712319689406
Step 443 | loss:1.5203392505645752 lr:6.915836321771912e-05 tokens_per_second_per_gpu:1024.665429397076
Step 444 | loss:1.4284342527389526 lr:6.915395728810033e-05 tokens_per_second_per_gpu:1240.5726049119721
Step 445 | loss:1.4634208679199219 lr:6.914953999723422e-05 tokens_per_second_per_gpu:810.3652177262856
Step 446 | loss:1.5230954885482788 lr:6.914511134659021e-05 tokens_per_second_per_gpu:1008.5161854398311
Step 447 | loss:1.637598991394043 lr:6.914067133764146e-05 tokens_per_second_per_gpu:607.0897184067259
Step 448 | loss:1.3808472156524658 lr:6.913621997186497e-05 tokens_per_second_per_gpu:1100.064475007814
Step 449 | loss:1.4318639039993286 lr:6.913175725074143e-05 tokens_per_second_per_gpu:1153.8857960267535
Step 450 | loss:1.5746833086013794 lr:6.912728317575536e-05 tokens_per_second_per_gpu:897.4726521650875
Step 451 | loss:1.5232031345367432 lr:6.912279774839509e-05 tokens_per_second_per_gpu:939.8746083295945
Step 452 | loss:1.5061553716659546 lr:6.911830097015265e-05 tokens_per_second_per_gpu:963.264974339853
Step 453 | loss:1.4440058469772339 lr:6.91137928425239e-05 tokens_per_second_per_gpu:970.8541217884123
Step 454 | loss:1.4842851161956787 lr:6.910927336700848e-05 tokens_per_second_per_gpu:845.4414251984404
Step 455 | loss:1.415619969367981 lr:6.910474254510974e-05 tokens_per_second_per_gpu:1009.6989188118714
Step 456 | loss:1.5562381744384766 lr:6.91002003783349e-05 tokens_per_second_per_gpu:1030.1236439950605
Step 457 | loss:1.514113426208496 lr:6.909564686819486e-05 tokens_per_second_per_gpu:1096.4037756110326
Step 458 | loss:1.398838996887207 lr:6.909108201620435e-05 tokens_per_second_per_gpu:1116.6381278519607
Step 459 | loss:1.5138224363327026 lr:6.908650582388187e-05 tokens_per_second_per_gpu:715.9835057248321
Step 460 | loss:1.4385327100753784 lr:6.908191829274967e-05 tokens_per_second_per_gpu:1261.5240523191806
Step 461 | loss:1.403738260269165 lr:6.907731942433379e-05 tokens_per_second_per_gpu:1078.0361536268836
Step 462 | loss:1.5861647129058838 lr:6.907270922016403e-05 tokens_per_second_per_gpu:814.7638787244355
Step 463 | loss:1.6343433856964111 lr:6.906808768177397e-05 tokens_per_second_per_gpu:829.4584146914725
Step 464 | loss:1.503650426864624 lr:6.906345481070094e-05 tokens_per_second_per_gpu:803.9743054516233
Step 465 | loss:1.522559404373169 lr:6.905881060848608e-05 tokens_per_second_per_gpu:588.3314707590691
Step 466 | loss:1.605057954788208 lr:6.905415507667426e-05 tokens_per_second_per_gpu:789.1568463863977
Step 467 | loss:1.7336822748184204 lr:6.904948821681414e-05 tokens_per_second_per_gpu:811.4837485462195
Step 468 | loss:1.4786057472229004 lr:6.904481003045814e-05 tokens_per_second_per_gpu:878.8131828864633
Step 469 | loss:1.306789517402649 lr:6.904012051916244e-05 tokens_per_second_per_gpu:1321.825330473304
Step 470 | loss:1.599853754043579 lr:6.903541968448701e-05 tokens_per_second_per_gpu:862.9000075879011
Step 471 | loss:1.5703864097595215 lr:6.903070752799556e-05 tokens_per_second_per_gpu:998.0451593529853
Step 472 | loss:1.469602108001709 lr:6.90259840512556e-05 tokens_per_second_per_gpu:939.2592734111608
Step 473 | loss:1.6150873899459839 lr:6.902124925583837e-05 tokens_per_second_per_gpu:889.6384143171933
Step 474 | loss:1.802342176437378 lr:6.90165031433189e-05 tokens_per_second_per_gpu:720.7103845475089
Step 475 | loss:1.4464079141616821 lr:6.901174571527595e-05 tokens_per_second_per_gpu:842.9298382922316
Step 476 | loss:1.4576433897018433 lr:6.900697697329211e-05 tokens_per_second_per_gpu:978.220634985018
Step 477 | loss:1.6869869232177734 lr:6.900219691895365e-05 tokens_per_second_per_gpu:760.6505657171477
Step 478 | loss:1.42209792137146 lr:6.899740555385069e-05 tokens_per_second_per_gpu:1009.9283810439211
Step 479 | loss:1.3503479957580566 lr:6.899260287957704e-05 tokens_per_second_per_gpu:1047.8853069302036
Step 480 | loss:1.6157517433166504 lr:6.898778889773027e-05 tokens_per_second_per_gpu:1044.4383141469784
Step 481 | loss:1.6497588157653809 lr:6.898296360991182e-05 tokens_per_second_per_gpu:899.1284521521243
Step 482 | loss:1.5276260375976562 lr:6.897812701772674e-05 tokens_per_second_per_gpu:835.5279631120131
Step 483 | loss:1.618335247039795 lr:6.897327912278396e-05 tokens_per_second_per_gpu:895.9285590296494
Step 484 | loss:1.5536435842514038 lr:6.896841992669611e-05 tokens_per_second_per_gpu:1089.5346915755044
Step 485 | loss:1.5729351043701172 lr:6.896354943107957e-05 tokens_per_second_per_gpu:1153.6660758301805
Step 486 | loss:1.6196494102478027 lr:6.895866763755452e-05 tokens_per_second_per_gpu:641.1315022423346
Step 487 | loss:1.37526535987854 lr:6.895377454774489e-05 tokens_per_second_per_gpu:1140.0559065950263
Step 488 | loss:1.6450135707855225 lr:6.894887016327832e-05 tokens_per_second_per_gpu:921.5253969693322
Step 489 | loss:1.4856890439987183 lr:6.89439544857863e-05 tokens_per_second_per_gpu:927.6397416105742
Step 490 | loss:1.5082988739013672 lr:6.893902751690397e-05 tokens_per_second_per_gpu:669.8210636925191
Step 491 | loss:1.450636625289917 lr:6.893408925827029e-05 tokens_per_second_per_gpu:915.5654950598558
Step 492 | loss:1.5598970651626587 lr:6.892913971152798e-05 tokens_per_second_per_gpu:907.1580071193846
Step 493 | loss:1.5726993083953857 lr:6.892417887832348e-05 tokens_per_second_per_gpu:896.1714606904231
Step 494 | loss:1.592546820640564 lr:6.891920676030699e-05 tokens_per_second_per_gpu:864.2036187638821
Step 495 | loss:1.4288204908370972 lr:6.891422335913251e-05 tokens_per_second_per_gpu:975.5628692485179
Step 496 | loss:1.5255258083343506 lr:6.890922867645775e-05 tokens_per_second_per_gpu:724.6561597046109
Step 497 | loss:1.3548961877822876 lr:6.890422271394416e-05 tokens_per_second_per_gpu:962.2106461106589
Step 498 | loss:1.4648406505584717 lr:6.889920547325696e-05 tokens_per_second_per_gpu:1339.0150975456224
Step 499 | loss:1.6220388412475586 lr:6.889417695606515e-05 tokens_per_second_per_gpu:977.4219711848702
Step 500 | loss:1.4498929977416992 lr:6.888913716404146e-05 tokens_per_second_per_gpu:987.9496776929725
Step 501 | loss:1.5463474988937378 lr:6.888408609886233e-05 tokens_per_second_per_gpu:641.052413650608
Step 502 | loss:1.528153657913208 lr:6.887902376220802e-05 tokens_per_second_per_gpu:915.9385871336032
Step 503 | loss:1.4832861423492432 lr:6.88739501557625e-05 tokens_per_second_per_gpu:842.0280685848054
Step 504 | loss:1.582930088043213 lr:6.88688652812135e-05 tokens_per_second_per_gpu:832.744609370747
Step 505 | loss:1.3396565914154053 lr:6.886376914025247e-05 tokens_per_second_per_gpu:1020.2693485038054
Step 506 | loss:1.4360320568084717 lr:6.885866173457466e-05 tokens_per_second_per_gpu:1003.4286658467495
Step 507 | loss:1.3843172788619995 lr:6.885354306587901e-05 tokens_per_second_per_gpu:1067.3819425008837
Step 508 | loss:1.5523581504821777 lr:6.884841313586828e-05 tokens_per_second_per_gpu:852.997701176221
Step 509 | loss:1.3935084342956543 lr:6.884327194624888e-05 tokens_per_second_per_gpu:821.6094886104315
Step 510 | loss:1.4239294528961182 lr:6.883811949873104e-05 tokens_per_second_per_gpu:838.2245271857523
Step 511 | loss:1.6262836456298828 lr:6.88329557950287e-05 tokens_per_second_per_gpu:565.077076063497
Step 512 | loss:1.42251455783844 lr:6.882778083685958e-05 tokens_per_second_per_gpu:1009.1097739213948
Step 513 | loss:1.478352427482605 lr:6.882259462594511e-05 tokens_per_second_per_gpu:920.7370672072979
Step 514 | loss:1.5867401361465454 lr:6.881739716401046e-05 tokens_per_second_per_gpu:971.8330944260778
Step 515 | loss:1.4220092296600342 lr:6.881218845278458e-05 tokens_per_second_per_gpu:1033.9254338140627
Step 516 | loss:1.7305127382278442 lr:6.88069684940001e-05 tokens_per_second_per_gpu:564.8389625106747
Step 517 | loss:1.5881125926971436 lr:6.880173728939347e-05 tokens_per_second_per_gpu:847.3823747191665
Step 518 | loss:1.545444369316101 lr:6.879649484070481e-05 tokens_per_second_per_gpu:832.7118516721617
Step 519 | loss:1.4840919971466064 lr:6.879124114967804e-05 tokens_per_second_per_gpu:922.6872783903653
Step 520 | loss:1.4727649688720703 lr:6.878597621806075e-05 tokens_per_second_per_gpu:1065.8878609443939
Step 521 | loss:1.4178290367126465 lr:6.878070004760435e-05 tokens_per_second_per_gpu:783.6284764587707
Step 522 | loss:1.5602906942367554 lr:6.877541264006391e-05 tokens_per_second_per_gpu:631.4658983318004
Step 523 | loss:1.5065429210662842 lr:6.87701139971983e-05 tokens_per_second_per_gpu:998.5305046191522
Step 524 | loss:1.4635541439056396 lr:6.876480412077011e-05 tokens_per_second_per_gpu:925.5008863883224
Step 525 | loss:1.5232641696929932 lr:6.875948301254563e-05 tokens_per_second_per_gpu:863.7022063144873
Step 526 | loss:1.4071130752563477 lr:6.875415067429495e-05 tokens_per_second_per_gpu:931.022666575831
Step 527 | loss:1.4858382940292358 lr:6.874880710779184e-05 tokens_per_second_per_gpu:1015.6022144326673
Step 528 | loss:1.5169885158538818 lr:6.874345231481383e-05 tokens_per_second_per_gpu:825.9024534238267
Step 529 | loss:1.4226945638656616 lr:6.87380862971422e-05 tokens_per_second_per_gpu:946.572286801411
Step 530 | loss:1.6368412971496582 lr:6.873270905656192e-05 tokens_per_second_per_gpu:838.5386849665086
Step 531 | loss:1.3438917398452759 lr:6.872732059486173e-05 tokens_per_second_per_gpu:1174.0879042089355
Step 532 | loss:1.7152485847473145 lr:6.872192091383408e-05 tokens_per_second_per_gpu:828.9081869727651
Step 533 | loss:1.585336446762085 lr:6.871651001527518e-05 tokens_per_second_per_gpu:933.3169149521442
Step 534 | loss:1.445300579071045 lr:6.871108790098495e-05 tokens_per_second_per_gpu:1068.940695160427
Step 535 | loss:1.66127347946167 lr:6.870565457276704e-05 tokens_per_second_per_gpu:617.659235427836
Step 536 | loss:1.1734497547149658 lr:6.870021003242884e-05 tokens_per_second_per_gpu:1423.4825222858092
Step 537 | loss:1.5042970180511475 lr:6.869475428178147e-05 tokens_per_second_per_gpu:772.1299854024311
Step 538 | loss:1.3491623401641846 lr:6.868928732263977e-05 tokens_per_second_per_gpu:898.0875417032587
Step 539 | loss:1.4749491214752197 lr:6.868380915682232e-05 tokens_per_second_per_gpu:882.1343571659942
Step 540 | loss:1.5142360925674438 lr:6.86783197861514e-05 tokens_per_second_per_gpu:854.5443832831702
Step 541 | loss:1.4741328954696655 lr:6.867281921245306e-05 tokens_per_second_per_gpu:956.1224901140247
Step 542 | loss:1.618884563446045 lr:6.866730743755705e-05 tokens_per_second_per_gpu:923.0758342234474
Step 543 | loss:1.5690115690231323 lr:6.866178446329685e-05 tokens_per_second_per_gpu:772.3812143353775
Step 544 | loss:1.4656145572662354 lr:6.865625029150967e-05 tokens_per_second_per_gpu:884.2865324105627
Step 545 | loss:1.717721700668335 lr:6.865070492403644e-05 tokens_per_second_per_gpu:816.5121979245021
Step 546 | loss:1.4527816772460938 lr:6.86451483627218e-05 tokens_per_second_per_gpu:981.2846337490503
Step 547 | loss:1.6099904775619507 lr:6.863958060941415e-05 tokens_per_second_per_gpu:776.7543851871784
Step 548 | loss:1.5022878646850586 lr:6.863400166596558e-05 tokens_per_second_per_gpu:923.2024883179611
Step 549 | loss:1.7111327648162842 lr:6.862841153423193e-05 tokens_per_second_per_gpu:632.79581136985
Step 550 | loss:1.5685734748840332 lr:6.862281021607274e-05 tokens_per_second_per_gpu:1033.5030834557315
Step 551 | loss:1.605432152748108 lr:6.861719771335125e-05 tokens_per_second_per_gpu:896.8029078714468
Step 552 | loss:1.485328197479248 lr:6.861157402793448e-05 tokens_per_second_per_gpu:898.5717959007962
Step 553 | loss:1.3894249200820923 lr:6.860593916169314e-05 tokens_per_second_per_gpu:852.7211622036652
Step 554 | loss:1.418114423751831 lr:6.860029311650164e-05 tokens_per_second_per_gpu:878.1357312986997
Step 555 | loss:1.38151216506958 lr:6.859463589423815e-05 tokens_per_second_per_gpu:962.7474686114977
Step 556 | loss:1.287707805633545 lr:6.85889674967845e-05 tokens_per_second_per_gpu:1102.0795184539759
Step 557 | loss:1.5176310539245605 lr:6.858328792602629e-05 tokens_per_second_per_gpu:1137.650851039178
Step 558 | loss:1.4631212949752808 lr:6.857759718385281e-05 tokens_per_second_per_gpu:846.8948361452708
Step 559 | loss:1.396012306213379 lr:6.857189527215709e-05 tokens_per_second_per_gpu:737.1613365558554
Step 560 | loss:1.3854551315307617 lr:6.856618219283586e-05 tokens_per_second_per_gpu:1021.2959101768548
Step 561 | loss:1.5363836288452148 lr:6.856045794778953e-05 tokens_per_second_per_gpu:958.3689221826037
Step 562 | loss:1.400917887687683 lr:6.85547225389223e-05 tokens_per_second_per_gpu:1024.6672115353954
Step 563 | loss:1.551637053489685 lr:6.854897596814203e-05 tokens_per_second_per_gpu:946.9392099998561
Step 564 | loss:1.6081229448318481 lr:6.854321823736028e-05 tokens_per_second_per_gpu:985.4114152699763
Step 565 | loss:1.3487508296966553 lr:6.85374493484924e-05 tokens_per_second_per_gpu:807.7532607328993
Step 566 | loss:1.6805880069732666 lr:6.853166930345737e-05 tokens_per_second_per_gpu:953.1019910950029
Step 567 | loss:1.5338636636734009 lr:6.852587810417788e-05 tokens_per_second_per_gpu:780.0938451717395
Step 568 | loss:1.4991507530212402 lr:6.852007575258041e-05 tokens_per_second_per_gpu:771.5001967313647
Step 569 | loss:1.4040008783340454 lr:6.851426225059509e-05 tokens_per_second_per_gpu:899.0624138887802
Step 570 | loss:1.4501286745071411 lr:6.850843760015575e-05 tokens_per_second_per_gpu:967.6809803319877
Step 571 | loss:1.4260776042938232 lr:6.850260180319997e-05 tokens_per_second_per_gpu:645.3574455614785
Step 572 | loss:1.5126266479492188 lr:6.8496754861669e-05 tokens_per_second_per_gpu:794.7969043425908
Step 573 | loss:1.5814920663833618 lr:6.849089677750783e-05 tokens_per_second_per_gpu:874.9845269080255
Step 574 | loss:1.4853739738464355 lr:6.848502755266512e-05 tokens_per_second_per_gpu:730.7357960704813
Step 575 | loss:1.4287948608398438 lr:6.847914718909329e-05 tokens_per_second_per_gpu:1025.8846754632157
Step 576 | loss:1.4690585136413574 lr:6.847325568874839e-05 tokens_per_second_per_gpu:1005.4310884641312
Step 577 | loss:1.4834349155426025 lr:6.846735305359024e-05 tokens_per_second_per_gpu:960.1866645904882
Step 578 | loss:1.3795008659362793 lr:6.846143928558234e-05 tokens_per_second_per_gpu:1350.4861495532389
Step 579 | loss:1.3774404525756836 lr:6.845551438669189e-05 tokens_per_second_per_gpu:766.1989768046942
Step 580 | loss:1.417657494544983 lr:6.844957835888979e-05 tokens_per_second_per_gpu:916.4369234624678
Step 581 | loss:1.7571561336517334 lr:6.844363120415064e-05 tokens_per_second_per_gpu:803.3717054449562
Step 582 | loss:1.6609177589416504 lr:6.843767292445278e-05 tokens_per_second_per_gpu:814.329766044142
Step 583 | loss:1.4005851745605469 lr:6.843170352177821e-05 tokens_per_second_per_gpu:692.5881223726763
Step 584 | loss:1.4518766403198242 lr:6.842572299811263e-05 tokens_per_second_per_gpu:805.952937631751
Step 585 | loss:1.5630372762680054 lr:6.841973135544544e-05 tokens_per_second_per_gpu:727.0487768537386
Step 586 | loss:1.3494473695755005 lr:6.841372859576977e-05 tokens_per_second_per_gpu:1073.5295062253633
Step 587 | loss:1.4314366579055786 lr:6.84077147210824e-05 tokens_per_second_per_gpu:955.1989222879865
Step 588 | loss:1.5816057920455933 lr:6.840168973338388e-05 tokens_per_second_per_gpu:971.332747918037
Step 589 | loss:1.4742064476013184 lr:6.839565363467836e-05 tokens_per_second_per_gpu:594.7271969386642
Step 590 | loss:1.456629753112793 lr:6.838960642697375e-05 tokens_per_second_per_gpu:991.8117174682716
Step 591 | loss:1.5059568881988525 lr:6.838354811228168e-05 tokens_per_second_per_gpu:967.9997954815686
Step 592 | loss:1.5009979009628296 lr:6.837747869261739e-05 tokens_per_second_per_gpu:787.1493662568233
Step 593 | loss:1.5120972394943237 lr:6.837139816999987e-05 tokens_per_second_per_gpu:776.2307669548792
Step 594 | loss:1.5445311069488525 lr:6.836530654645181e-05 tokens_per_second_per_gpu:959.0125450099056
Step 595 | loss:1.481900930404663 lr:6.835920382399956e-05 tokens_per_second_per_gpu:762.747756737205
Step 596 | loss:1.5329951047897339 lr:6.835309000467319e-05 tokens_per_second_per_gpu:978.6615868609775
Step 597 | loss:1.5537203550338745 lr:6.834696509050645e-05 tokens_per_second_per_gpu:760.796526951842
Step 598 | loss:1.4881620407104492 lr:6.834082908353677e-05 tokens_per_second_per_gpu:821.2130274116968
Step 599 | loss:1.3998217582702637 lr:6.83346819858053e-05 tokens_per_second_per_gpu:1053.8961817107954
Step 600 | loss:1.5811318159103394 lr:6.832852379935683e-05 tokens_per_second_per_gpu:911.6828486214239
Step 601 | loss:1.5181894302368164 lr:6.83223545262399e-05 tokens_per_second_per_gpu:814.8486285930029
Step 602 | loss:1.4163309335708618 lr:6.831617416850669e-05 tokens_per_second_per_gpu:1112.9653470365267
Step 603 | loss:1.375277042388916 lr:6.830998272821308e-05 tokens_per_second_per_gpu:910.0322672745841
Step 604 | loss:1.2727477550506592 lr:6.830378020741866e-05 tokens_per_second_per_gpu:893.7274231093911
Step 605 | loss:1.5625847578048706 lr:6.829756660818667e-05 tokens_per_second_per_gpu:1045.8951171828344
Step 606 | loss:1.4646152257919312 lr:6.829134193258405e-05 tokens_per_second_per_gpu:1034.8150767188788
Step 607 | loss:1.5307995080947876 lr:6.828510618268144e-05 tokens_per_second_per_gpu:769.8640975067736
Step 608 | loss:1.4464521408081055 lr:6.827885936055312e-05 tokens_per_second_per_gpu:1015.6122386193849
Step 609 | loss:1.4820494651794434 lr:6.827260146827713e-05 tokens_per_second_per_gpu:1037.0422899588705
Step 610 | loss:1.6318578720092773 lr:6.826633250793513e-05 tokens_per_second_per_gpu:901.6462018056926
Step 611 | loss:1.3706709146499634 lr:6.826005248161244e-05 tokens_per_second_per_gpu:964.3927510526462
Step 612 | loss:1.5443446636199951 lr:6.825376139139814e-05 tokens_per_second_per_gpu:925.5199513061156
Step 613 | loss:1.4709150791168213 lr:6.824745923938494e-05 tokens_per_second_per_gpu:1142.3887078869616
Step 614 | loss:1.4715454578399658 lr:6.824114602766923e-05 tokens_per_second_per_gpu:787.3366553389657
Step 615 | loss:1.62100350856781 lr:6.823482175835109e-05 tokens_per_second_per_gpu:819.2482378635777
Step 616 | loss:1.5392149686813354 lr:6.822848643353428e-05 tokens_per_second_per_gpu:789.5166185432735
Step 617 | loss:1.6064531803131104 lr:6.822214005532624e-05 tokens_per_second_per_gpu:548.0726427265008
Step 618 | loss:1.542294979095459 lr:6.821578262583805e-05 tokens_per_second_per_gpu:996.0225648741532
Step 619 | loss:1.3993617296218872 lr:6.820941414718453e-05 tokens_per_second_per_gpu:1134.185383503324
Step 620 | loss:1.6378731727600098 lr:6.820303462148414e-05 tokens_per_second_per_gpu:967.0194672068832
Step 621 | loss:1.5640478134155273 lr:6.819664405085899e-05 tokens_per_second_per_gpu:1198.379643578411
Step 622 | loss:1.4890092611312866 lr:6.819024243743492e-05 tokens_per_second_per_gpu:773.6409747982435
Step 623 | loss:1.59574556350708 lr:6.81838297833414e-05 tokens_per_second_per_gpu:632.0344077262898
Step 624 | loss:1.5502369403839111 lr:6.817740609071158e-05 tokens_per_second_per_gpu:943.3893996908977
Step 625 | loss:1.521416187286377 lr:6.817097136168231e-05 tokens_per_second_per_gpu:766.4868387677261
Step 626 | loss:1.6044807434082031 lr:6.816452559839407e-05 tokens_per_second_per_gpu:692.0543521697273
Step 627 | loss:1.2820281982421875 lr:6.815806880299105e-05 tokens_per_second_per_gpu:897.5211053541233
Step 628 | loss:1.5246800184249878 lr:6.815160097762107e-05 tokens_per_second_per_gpu:811.3038239920796
Step 629 | loss:1.6499714851379395 lr:6.814512212443564e-05 tokens_per_second_per_gpu:601.0882434241239
Step 630 | loss:1.605573058128357 lr:6.813863224558995e-05 tokens_per_second_per_gpu:961.605741924284
Step 631 | loss:1.4117684364318848 lr:6.813213134324285e-05 tokens_per_second_per_gpu:1093.5889688789962
Step 632 | loss:1.4549057483673096 lr:6.812561941955684e-05 tokens_per_second_per_gpu:830.9636362401417
Step 633 | loss:1.2440378665924072 lr:6.81190964766981e-05 tokens_per_second_per_gpu:1094.1831431388916
Step 634 | loss:1.3175785541534424 lr:6.811256251683648e-05 tokens_per_second_per_gpu:1026.7515038650372
Step 635 | loss:1.529625415802002 lr:6.810601754214549e-05 tokens_per_second_per_gpu:885.5581606813809
Step 636 | loss:1.495295763015747 lr:6.80994615548023e-05 tokens_per_second_per_gpu:874.6816589061567
Step 637 | loss:1.538493037223816 lr:6.809289455698773e-05 tokens_per_second_per_gpu:665.8728459574615
Step 638 | loss:1.3982343673706055 lr:6.80863165508863e-05 tokens_per_second_per_gpu:1226.506268862378
Step 639 | loss:1.2920055389404297 lr:6.807972753868618e-05 tokens_per_second_per_gpu:808.9180183955913
Step 640 | loss:1.5058817863464355 lr:6.807312752257918e-05 tokens_per_second_per_gpu:959.1368654822162
Step 641 | loss:1.5105066299438477 lr:6.806651650476076e-05 tokens_per_second_per_gpu:947.4537227946926
Step 642 | loss:1.7865533828735352 lr:6.80598944874301e-05 tokens_per_second_per_gpu:747.7168409616752
Step 643 | loss:1.5385684967041016 lr:6.805326147278996e-05 tokens_per_second_per_gpu:985.2477323770477
Step 644 | loss:1.4725143909454346 lr:6.804661746304686e-05 tokens_per_second_per_gpu:946.1230358836303
Step 645 | loss:1.4510772228240967 lr:6.803996246041084e-05 tokens_per_second_per_gpu:960.3174483273278
Step 646 | loss:1.7029368877410889 lr:6.803329646709574e-05 tokens_per_second_per_gpu:630.1658035953042
Step 647 | loss:1.6180739402770996 lr:6.802661948531895e-05 tokens_per_second_per_gpu:705.8818230151767
Step 648 | loss:1.5982694625854492 lr:6.801993151730158e-05 tokens_per_second_per_gpu:843.9477494273241
Step 649 | loss:1.5534628629684448 lr:6.801323256526834e-05 tokens_per_second_per_gpu:721.3855703313397
Step 650 | loss:1.4165189266204834 lr:6.800652263144765e-05 tokens_per_second_per_gpu:988.4654176357434
Step 651 | loss:1.5090315341949463 lr:6.799980171807155e-05 tokens_per_second_per_gpu:767.2647319268514
Step 652 | loss:1.487756371498108 lr:6.799306982737575e-05 tokens_per_second_per_gpu:1120.8051171950449
Step 653 | loss:1.4815577268600464 lr:6.798632696159956e-05 tokens_per_second_per_gpu:853.2856398680414
Step 654 | loss:1.540446400642395 lr:6.797957312298602e-05 tokens_per_second_per_gpu:731.7230435188462
Step 655 | loss:1.4904115200042725 lr:6.797280831378177e-05 tokens_per_second_per_gpu:801.0301783374871
Step 656 | loss:1.5343974828720093 lr:6.796603253623711e-05 tokens_per_second_per_gpu:974.3925664767943
Step 657 | loss:1.5273163318634033 lr:6.795924579260597e-05 tokens_per_second_per_gpu:706.9412824044645
Step 658 | loss:1.5643638372421265 lr:6.795244808514599e-05 tokens_per_second_per_gpu:852.6316402202295
Step 659 | loss:1.6294704675674438 lr:6.794563941611837e-05 tokens_per_second_per_gpu:692.7802884792766
Step 660 | loss:1.4243313074111938 lr:6.793881978778804e-05 tokens_per_second_per_gpu:949.8325850643799
Step 661 | loss:1.5626140832901 lr:6.793198920242352e-05 tokens_per_second_per_gpu:806.9801848734073
Step 662 | loss:1.5154701471328735 lr:6.792514766229697e-05 tokens_per_second_per_gpu:727.8648955017044
Step 663 | loss:1.459997296333313 lr:6.791829516968422e-05 tokens_per_second_per_gpu:780.8072086018095
Step 664 | loss:1.4639288187026978 lr:6.791143172686478e-05 tokens_per_second_per_gpu:910.4280185063925
Step 665 | loss:1.4168120622634888 lr:6.790455733612172e-05 tokens_per_second_per_gpu:1163.0646475756637
Step 666 | loss:1.4701730012893677 lr:6.78976719997418e-05 tokens_per_second_per_gpu:751.3277010174293
Step 667 | loss:1.4358954429626465 lr:6.789077572001542e-05 tokens_per_second_per_gpu:993.7960597211888
Step 668 | loss:1.339756727218628 lr:6.788386849923661e-05 tokens_per_second_per_gpu:1007.4058770782466
Step 669 | loss:1.5715261697769165 lr:6.787695033970305e-05 tokens_per_second_per_gpu:757.3047515429788
Step 670 | loss:1.5197919607162476 lr:6.787002124371605e-05 tokens_per_second_per_gpu:960.8084963253315
Step 671 | loss:1.3517844676971436 lr:6.786308121358055e-05 tokens_per_second_per_gpu:1125.0532443212956
Step 672 | loss:1.4478038549423218 lr:6.785613025160515e-05 tokens_per_second_per_gpu:893.0910664191732
Step 673 | loss:1.3986735343933105 lr:6.784916836010207e-05 tokens_per_second_per_gpu:824.0733354286136
Step 674 | loss:1.43536376953125 lr:6.784219554138716e-05 tokens_per_second_per_gpu:665.3313698008021
Step 675 | loss:1.4227516651153564 lr:6.783521179777995e-05 tokens_per_second_per_gpu:1142.5649347976832
Step 676 | loss:1.453931212425232 lr:6.782821713160351e-05 tokens_per_second_per_gpu:928.6459833329478
Step 677 | loss:1.6873211860656738 lr:6.782121154518465e-05 tokens_per_second_per_gpu:940.7261502383178
Step 678 | loss:1.3871071338653564 lr:6.781419504085375e-05 tokens_per_second_per_gpu:1082.1923642525899
Step 679 | loss:1.3290852308273315 lr:6.780716762094483e-05 tokens_per_second_per_gpu:866.7044563601286
Step 680 | loss:1.5168155431747437 lr:6.780012928779555e-05 tokens_per_second_per_gpu:801.5593146655648
Step 681 | loss:1.3659613132476807 lr:6.77930800437472e-05 tokens_per_second_per_gpu:1254.8463326844703
Step 682 | loss:1.4288158416748047 lr:6.778601989114471e-05 tokens_per_second_per_gpu:772.2783224067373
Step 683 | loss:1.667455792427063 lr:6.777894883233662e-05 tokens_per_second_per_gpu:1152.5362386452173
Step 684 | loss:1.4760183095932007 lr:6.777186686967508e-05 tokens_per_second_per_gpu:1152.535888057008
Step 685 | loss:1.4889379739761353 lr:6.776477400551591e-05 tokens_per_second_per_gpu:817.0345607863513
Step 686 | loss:1.5337647199630737 lr:6.775767024221855e-05 tokens_per_second_per_gpu:735.5786795583282
Step 687 | loss:1.4950281381607056 lr:6.775055558214602e-05 tokens_per_second_per_gpu:822.6750358527395
Step 688 | loss:1.3190486431121826 lr:6.774343002766504e-05 tokens_per_second_per_gpu:1313.3181982432177
Step 689 | loss:1.4717154502868652 lr:6.773629358114587e-05 tokens_per_second_per_gpu:1008.980438607641
Step 690 | loss:1.4445523023605347 lr:6.772914624496247e-05 tokens_per_second_per_gpu:716.0464422858886
Step 691 | loss:1.517184853553772 lr:6.772198802149236e-05 tokens_per_second_per_gpu:865.9904548862686
Step 692 | loss:1.4317636489868164 lr:6.771481891311673e-05 tokens_per_second_per_gpu:854.4415483632308
Step 693 | loss:1.406124234199524 lr:6.770763892222035e-05 tokens_per_second_per_gpu:990.5621462225624
Step 694 | loss:1.4052382707595825 lr:6.770044805119165e-05 tokens_per_second_per_gpu:818.2000518326622
Step 695 | loss:1.5679333209991455 lr:6.769324630242265e-05 tokens_per_second_per_gpu:740.2791457468065
Step 696 | loss:1.5860971212387085 lr:6.768603367830898e-05 tokens_per_second_per_gpu:935.4662876485576
Step 697 | loss:1.5208654403686523 lr:6.767881018124994e-05 tokens_per_second_per_gpu:746.8028921627764
Step 698 | loss:1.5291244983673096 lr:6.767157581364839e-05 tokens_per_second_per_gpu:850.4999998350511
Step 699 | loss:1.314714789390564 lr:6.766433057791084e-05 tokens_per_second_per_gpu:1044.7993080845229
Step 700 | loss:1.5205364227294922 lr:6.765707447644738e-05 tokens_per_second_per_gpu:854.6737631374406
Step 701 | loss:1.3369816541671753 lr:6.764980751167178e-05 tokens_per_second_per_gpu:1156.8698842898145
Step 702 | loss:1.5657312870025635 lr:6.764252968600133e-05 tokens_per_second_per_gpu:826.6723542437992
Step 703 | loss:1.5898770093917847 lr:6.763524100185703e-05 tokens_per_second_per_gpu:962.9377289224279
Step 704 | loss:1.4848867654800415 lr:6.762794146166342e-05 tokens_per_second_per_gpu:923.828591085086
Step 705 | loss:1.2649898529052734 lr:6.762063106784869e-05 tokens_per_second_per_gpu:1199.0389579509424
Step 706 | loss:1.399157166481018 lr:6.761330982284462e-05 tokens_per_second_per_gpu:995.3648464927722
Step 707 | loss:1.3489211797714233 lr:6.760597772908662e-05 tokens_per_second_per_gpu:1248.1435413088006
Step 708 | loss:1.6692448854446411 lr:6.759863478901367e-05 tokens_per_second_per_gpu:630.8328565725946
Step 709 | loss:1.3194859027862549 lr:6.759128100506841e-05 tokens_per_second_per_gpu:857.7318758521625
Step 710 | loss:1.553175687789917 lr:6.758391637969707e-05 tokens_per_second_per_gpu:864.2157786602305
Step 711 | loss:1.3107839822769165 lr:6.757654091534945e-05 tokens_per_second_per_gpu:940.6154817292047
Step 712 | loss:1.613779067993164 lr:6.756915461447899e-05 tokens_per_second_per_gpu:867.1002433170353
Step 713 | loss:1.5922468900680542 lr:6.756175747954275e-05 tokens_per_second_per_gpu:829.170939478154
Step 714 | loss:1.5594886541366577 lr:6.755434951300136e-05 tokens_per_second_per_gpu:951.6543427736674
Step 715 | loss:1.5701035261154175 lr:6.754693071731906e-05 tokens_per_second_per_gpu:935.5566882931804
Step 716 | loss:1.4283740520477295 lr:6.753950109496369e-05 tokens_per_second_per_gpu:564.8027520052559
Step 717 | loss:1.5181491374969482 lr:6.753206064840672e-05 tokens_per_second_per_gpu:966.4865521062248
Step 718 | loss:1.571433424949646 lr:6.75246093801232e-05 tokens_per_second_per_gpu:676.2434070774161
Step 719 | loss:1.4210635423660278 lr:6.751714729259175e-05 tokens_per_second_per_gpu:875.6402779282338
Step 720 | loss:1.4427464008331299 lr:6.750967438829466e-05 tokens_per_second_per_gpu:832.9040558100717
Step 721 | loss:1.5087348222732544 lr:6.750219066971774e-05 tokens_per_second_per_gpu:889.7174772995644
Step 722 | loss:1.507420539855957 lr:6.749469613935046e-05 tokens_per_second_per_gpu:719.9272397521007
Step 723 | loss:1.4527685642242432 lr:6.748719079968585e-05 tokens_per_second_per_gpu:968.4012448748315
Step 724 | loss:1.3494980335235596 lr:6.747967465322055e-05 tokens_per_second_per_gpu:841.0230710341411
Step 725 | loss:1.617998719215393 lr:6.74721477024548e-05 tokens_per_second_per_gpu:1006.2347371349654
Step 726 | loss:1.4995665550231934 lr:6.746460994989241e-05 tokens_per_second_per_gpu:1137.3368361071712
Step 727 | loss:1.4104180335998535 lr:6.74570613980408e-05 tokens_per_second_per_gpu:1007.6366609530286
Step 728 | loss:1.5288307666778564 lr:6.744950204941098e-05 tokens_per_second_per_gpu:1099.1424058290922
Step 729 | loss:1.2362126111984253 lr:6.744193190651758e-05 tokens_per_second_per_gpu:1192.0075421455213
Step 730 | loss:1.50574791431427 lr:6.743435097187875e-05 tokens_per_second_per_gpu:859.5204692782936
Step 731 | loss:1.5551481246948242 lr:6.74267592480163e-05 tokens_per_second_per_gpu:781.8753405116327
Step 732 | loss:1.5155525207519531 lr:6.741915673745559e-05 tokens_per_second_per_gpu:908.096935420683
Step 733 | loss:1.4361960887908936 lr:6.74115434427256e-05 tokens_per_second_per_gpu:946.7234625164009
Step 734 | loss:1.5214780569076538 lr:6.740391936635886e-05 tokens_per_second_per_gpu:909.9050439099984
Step 735 | loss:1.5357024669647217 lr:6.739628451089151e-05 tokens_per_second_per_gpu:888.8533143212767
Step 736 | loss:1.4583114385604858 lr:6.738863887886326e-05 tokens_per_second_per_gpu:855.6028760992145
Step 737 | loss:1.4307504892349243 lr:6.738098247281744e-05 tokens_per_second_per_gpu:975.1831704947251
Step 738 | loss:1.3426843881607056 lr:6.737331529530092e-05 tokens_per_second_per_gpu:736.5249042205252
Step 739 | loss:1.3742876052856445 lr:6.736563734886416e-05 tokens_per_second_per_gpu:1124.2806664664542
Step 740 | loss:1.3675419092178345 lr:6.735794863606122e-05 tokens_per_second_per_gpu:952.6609646661001
Step 741 | loss:1.5580453872680664 lr:6.735024915944977e-05 tokens_per_second_per_gpu:1049.1419184087895
Step 742 | loss:1.7132755517959595 lr:6.734253892159098e-05 tokens_per_second_per_gpu:620.5535893906127
Step 743 | loss:1.4155398607254028 lr:6.733481792504966e-05 tokens_per_second_per_gpu:949.0922225721855
Step 744 | loss:1.4439139366149902 lr:6.732708617239421e-05 tokens_per_second_per_gpu:973.2544997966179
Step 745 | loss:1.3471146821975708 lr:6.731934366619654e-05 tokens_per_second_per_gpu:663.925430225574
Step 746 | loss:1.4003340005874634 lr:6.73115904090322e-05 tokens_per_second_per_gpu:981.195020663626
Step 747 | loss:1.5963674783706665 lr:6.730382640348032e-05 tokens_per_second_per_gpu:1126.4210545173169
Step 748 | loss:1.3350086212158203 lr:6.729605165212354e-05 tokens_per_second_per_gpu:934.8008263006177
Step 749 | loss:1.4484987258911133 lr:6.728826615754815e-05 tokens_per_second_per_gpu:883.7670638357348
Step 750 | loss:1.45535409450531 lr:6.728046992234394e-05 tokens_per_second_per_gpu:844.7884101926062
Step 751 | loss:1.453187108039856 lr:6.727266294910435e-05 tokens_per_second_per_gpu:1020.3655057001694
Step 752 | loss:1.5155022144317627 lr:6.726484524042633e-05 tokens_per_second_per_gpu:1229.1313051290813
Step 753 | loss:1.5199717283248901 lr:6.725701679891043e-05 tokens_per_second_per_gpu:766.5694842549823
Step 754 | loss:1.4770666360855103 lr:6.724917762716079e-05 tokens_per_second_per_gpu:940.1446092803496
Step 755 | loss:1.5322729349136353 lr:6.724132772778507e-05 tokens_per_second_per_gpu:924.366025772617
Step 756 | loss:1.5200282335281372 lr:6.723346710339454e-05 tokens_per_second_per_gpu:750.4169422752892
Step 757 | loss:1.369624376296997 lr:6.7225595756604e-05 tokens_per_second_per_gpu:1000.4114377083447
Step 758 | loss:1.5097419023513794 lr:6.721771369003184e-05 tokens_per_second_per_gpu:1022.5115319698239
Step 759 | loss:1.5470821857452393 lr:6.720982090630004e-05 tokens_per_second_per_gpu:865.308355017416
Step 760 | loss:1.4090697765350342 lr:6.72019174080341e-05 tokens_per_second_per_gpu:975.86806210303
Step 761 | loss:1.5242667198181152 lr:6.719400319786311e-05 tokens_per_second_per_gpu:892.2771496044354
Step 762 | loss:1.645510196685791 lr:6.71860782784197e-05 tokens_per_second_per_gpu:856.1136908892202
Step 763 | loss:1.4270477294921875 lr:6.717814265234011e-05 tokens_per_second_per_gpu:995.3849223984374
Step 764 | loss:1.5068374872207642 lr:6.717019632226409e-05 tokens_per_second_per_gpu:875.5596523323564
Step 765 | loss:1.4514365196228027 lr:6.716223929083495e-05 tokens_per_second_per_gpu:882.6960952323092
Step 766 | loss:1.335574984550476 lr:6.715427156069964e-05 tokens_per_second_per_gpu:1198.5014654349986
Step 767 | loss:1.4961793422698975 lr:6.714629313450854e-05 tokens_per_second_per_gpu:1085.6558432568079
Step 768 | loss:1.568029761314392 lr:6.713830401491572e-05 tokens_per_second_per_gpu:744.7244275873059
Step 769 | loss:1.3249871730804443 lr:6.71303042045787e-05 tokens_per_second_per_gpu:965.3721503883444
Step 770 | loss:1.3609886169433594 lr:6.712229370615864e-05 tokens_per_second_per_gpu:1098.1079953571602
Step 771 | loss:1.542055368423462 lr:6.711427252232018e-05 tokens_per_second_per_gpu:788.542426356968
Step 772 | loss:1.4250695705413818 lr:6.710624065573157e-05 tokens_per_second_per_gpu:1029.2135785069638
Step 773 | loss:1.4103721380233765 lr:6.709819810906458e-05 tokens_per_second_per_gpu:870.9400420865614
Step 774 | loss:1.4264615774154663 lr:6.709014488499457e-05 tokens_per_second_per_gpu:906.5139248694577
Step 775 | loss:1.5691561698913574 lr:6.708208098620042e-05 tokens_per_second_per_gpu:698.5211114668361
Step 776 | loss:1.527077078819275 lr:6.707400641536457e-05 tokens_per_second_per_gpu:793.5101675456249
Step 777 | loss:1.6466450691223145 lr:6.7065921175173e-05 tokens_per_second_per_gpu:771.0624575825053
Step 778 | loss:1.3602254390716553 lr:6.705782526831527e-05 tokens_per_second_per_gpu:1135.1496263862687
Step 779 | loss:1.5777796506881714 lr:6.704971869748445e-05 tokens_per_second_per_gpu:751.3513181584528
Step 780 | loss:1.3636953830718994 lr:6.704160146537718e-05 tokens_per_second_per_gpu:869.164897301104
Step 781 | loss:1.4702701568603516 lr:6.703347357469364e-05 tokens_per_second_per_gpu:1134.0687940060573
Step 782 | loss:1.5593657493591309 lr:6.702533502813756e-05 tokens_per_second_per_gpu:657.2681695424759
Step 783 | loss:1.5843497514724731 lr:6.701718582841621e-05 tokens_per_second_per_gpu:824.8415058596516
Step 784 | loss:1.4750710725784302 lr:6.700902597824041e-05 tokens_per_second_per_gpu:849.3209548532456
Step 785 | loss:1.5076061487197876 lr:6.700085548032452e-05 tokens_per_second_per_gpu:807.5022854689321
Step 786 | loss:1.5005075931549072 lr:6.699267433738643e-05 tokens_per_second_per_gpu:810.5820816707177
Step 787 | loss:1.36058509349823 lr:6.698448255214758e-05 tokens_per_second_per_gpu:891.6658715074255
Step 788 | loss:1.4657402038574219 lr:6.697628012733297e-05 tokens_per_second_per_gpu:1020.6852251591711
Step 789 | loss:1.4217904806137085 lr:6.696806706567109e-05 tokens_per_second_per_gpu:820.9949638634458
Step 790 | loss:1.5465295314788818 lr:6.695984336989403e-05 tokens_per_second_per_gpu:765.8897292675919
Step 791 | loss:1.435875654220581 lr:6.695160904273738e-05 tokens_per_second_per_gpu:722.7372223030071
Step 792 | loss:1.492161750793457 lr:6.694336408694024e-05 tokens_per_second_per_gpu:987.4601561661236
Step 793 | loss:1.4302114248275757 lr:6.693510850524534e-05 tokens_per_second_per_gpu:1098.314169737634
Step 794 | loss:1.4498858451843262 lr:6.692684230039882e-05 tokens_per_second_per_gpu:853.0358527608346
Step 795 | loss:1.552681565284729 lr:6.691856547515045e-05 tokens_per_second_per_gpu:890.8574688498862
Step 796 | loss:1.5438028573989868 lr:6.69102780322535e-05 tokens_per_second_per_gpu:837.5045974265322
Step 797 | loss:1.6974846124649048 lr:6.690197997446478e-05 tokens_per_second_per_gpu:698.4787193078985
Step 798 | loss:1.5748575925827026 lr:6.689367130454458e-05 tokens_per_second_per_gpu:771.0157123804269
Step 799 | loss:1.5237594842910767 lr:6.688535202525681e-05 tokens_per_second_per_gpu:1114.7826244402518
Step 800 | loss:1.289263129234314 lr:6.687702213936885e-05 tokens_per_second_per_gpu:997.7369434105955
Step 801 | loss:1.433301568031311 lr:6.68686816496516e-05 tokens_per_second_per_gpu:1224.2410911466475
Step 802 | loss:1.5903772115707397 lr:6.686033055887952e-05 tokens_per_second_per_gpu:765.4848494693314
Step 803 | loss:1.3773362636566162 lr:6.68519688698306e-05 tokens_per_second_per_gpu:1135.838833079662
Step 804 | loss:1.5645780563354492 lr:6.684359658528632e-05 tokens_per_second_per_gpu:866.4440648771508
Step 805 | loss:1.2688493728637695 lr:6.68352137080317e-05 tokens_per_second_per_gpu:996.1556434708259
Step 806 | loss:1.5946439504623413 lr:6.682682024085531e-05 tokens_per_second_per_gpu:1051.1915585746178
Step 807 | loss:1.5408213138580322 lr:6.68184161865492e-05 tokens_per_second_per_gpu:643.9404993976387
Step 808 | loss:1.5530891418457031 lr:6.681000154790897e-05 tokens_per_second_per_gpu:826.2243475163976
Step 809 | loss:1.4834675788879395 lr:6.680157632773375e-05 tokens_per_second_per_gpu:794.5270101064901
Step 810 | loss:1.521824598312378 lr:6.679314052882613e-05 tokens_per_second_per_gpu:1129.1901237195761
Step 811 | loss:1.6054739952087402 lr:6.67846941539923e-05 tokens_per_second_per_gpu:705.4655925542734
Step 812 | loss:1.4867722988128662 lr:6.677623720604193e-05 tokens_per_second_per_gpu:1203.9903885302208
Step 813 | loss:1.493320107460022 lr:6.676776968778819e-05 tokens_per_second_per_gpu:665.0054119976497
Step 814 | loss:1.5603127479553223 lr:6.675929160204778e-05 tokens_per_second_per_gpu:753.8278431075139
Step 815 | loss:1.4959897994995117 lr:6.675080295164094e-05 tokens_per_second_per_gpu:711.2083964176137
Step 816 | loss:1.4414594173431396 lr:6.674230373939139e-05 tokens_per_second_per_gpu:1127.2859019550071
Step 817 | loss:1.3777594566345215 lr:6.673379396812637e-05 tokens_per_second_per_gpu:758.3009238839509
Step 818 | loss:1.445854663848877 lr:6.672527364067664e-05 tokens_per_second_per_gpu:1017.0165478300692
Step 819 | loss:1.5421262979507446 lr:6.67167427598765e-05 tokens_per_second_per_gpu:757.971743119029
Step 820 | loss:1.509584665298462 lr:6.670820132856368e-05 tokens_per_second_per_gpu:760.1913861518938
Step 821 | loss:1.4691009521484375 lr:6.669964934957951e-05 tokens_per_second_per_gpu:903.7364344897578
Step 822 | loss:1.3356730937957764 lr:6.669108682576879e-05 tokens_per_second_per_gpu:1049.2180481033192
Step 823 | loss:1.3900349140167236 lr:6.668251375997979e-05 tokens_per_second_per_gpu:1014.1705554845538
Step 824 | loss:1.6808946132659912 lr:6.667393015506437e-05 tokens_per_second_per_gpu:817.2334637918273
Step 825 | loss:1.3481245040893555 lr:6.666533601387781e-05 tokens_per_second_per_gpu:915.1707214144934
Step 826 | loss:1.4121354818344116 lr:6.665673133927895e-05 tokens_per_second_per_gpu:806.0131841368905
Step 827 | loss:1.40728759765625 lr:6.664811613413013e-05 tokens_per_second_per_gpu:929.2034445521232
Step 828 | loss:1.4630404710769653 lr:6.663949040129718e-05 tokens_per_second_per_gpu:766.0054464274534
Step 829 | loss:1.3588013648986816 lr:6.66308541436494e-05 tokens_per_second_per_gpu:973.4759598055697
Step 830 | loss:1.3691520690917969 lr:6.662220736405967e-05 tokens_per_second_per_gpu:1081.532269483596
Step 831 | loss:1.3567018508911133 lr:6.661355006540428e-05 tokens_per_second_per_gpu:753.6949441260116
Step 832 | loss:1.4572621583938599 lr:6.660488225056311e-05 tokens_per_second_per_gpu:741.6575571964245
Step 833 | loss:1.4646357297897339 lr:6.659620392241945e-05 tokens_per_second_per_gpu:763.0697897549963
Step 834 | loss:1.5007590055465698 lr:6.658751508386016e-05 tokens_per_second_per_gpu:971.7022302552467
Step 835 | loss:1.4617230892181396 lr:6.657881573777554e-05 tokens_per_second_per_gpu:879.9735788601588
Step 836 | loss:1.3910303115844727 lr:6.657010588705942e-05 tokens_per_second_per_gpu:895.7096197117919
Step 837 | loss:1.4355236291885376 lr:6.656138553460914e-05 tokens_per_second_per_gpu:905.6404064679899
Step 838 | loss:1.4029103517532349 lr:6.655265468332546e-05 tokens_per_second_per_gpu:846.1559100042317
Step 839 | loss:1.415105938911438 lr:6.654391333611272e-05 tokens_per_second_per_gpu:922.1748624864441
Step 840 | loss:1.5211392641067505 lr:6.65351614958787e-05 tokens_per_second_per_gpu:813.691506971663
Step 841 | loss:1.2961182594299316 lr:6.652639916553467e-05 tokens_per_second_per_gpu:768.8110515097713
Step 842 | loss:1.6529526710510254 lr:6.651762634799542e-05 tokens_per_second_per_gpu:777.9628143584308
Step 843 | loss:1.671109676361084 lr:6.650884304617919e-05 tokens_per_second_per_gpu:748.1310332809458
Step 844 | loss:1.3850817680358887 lr:6.650004926300777e-05 tokens_per_second_per_gpu:872.4724918232912
Step 845 | loss:1.3121132850646973 lr:6.649124500140635e-05 tokens_per_second_per_gpu:863.8330068572881
Step 846 | loss:1.4944560527801514 lr:6.648243026430367e-05 tokens_per_second_per_gpu:734.3690729242754
Step 847 | loss:1.4229077100753784 lr:6.647360505463192e-05 tokens_per_second_per_gpu:829.7521072249801
Step 848 | loss:1.5953073501586914 lr:6.646476937532681e-05 tokens_per_second_per_gpu:719.8126902963314
Step 849 | loss:1.559103012084961 lr:6.645592322932751e-05 tokens_per_second_per_gpu:1035.2047634414507
Step 850 | loss:1.614515781402588 lr:6.644706661957666e-05 tokens_per_second_per_gpu:862.3306061859466
Step 851 | loss:1.398939609527588 lr:6.64381995490204e-05 tokens_per_second_per_gpu:1077.8479620223259
Step 852 | loss:1.488055944442749 lr:6.642932202060835e-05 tokens_per_second_per_gpu:1086.4866406197334
Step 853 | loss:1.6739447116851807 lr:6.642043403729359e-05 tokens_per_second_per_gpu:832.9740161930225
Step 854 | loss:1.5443460941314697 lr:6.64115356020327e-05 tokens_per_second_per_gpu:906.1568905248309
Step 855 | loss:1.5733952522277832 lr:6.640262671778572e-05 tokens_per_second_per_gpu:839.6882807628197
Step 856 | loss:1.3944116830825806 lr:6.639370738751617e-05 tokens_per_second_per_gpu:867.822749439819
Step 857 | loss:1.4754315614700317 lr:6.638477761419106e-05 tokens_per_second_per_gpu:864.3629891649098
Step 858 | loss:1.4707365036010742 lr:6.637583740078087e-05 tokens_per_second_per_gpu:788.1501506896384
Step 859 | loss:1.5470662117004395 lr:6.63668867502595e-05 tokens_per_second_per_gpu:1027.07359483832
Step 860 | loss:1.4241647720336914 lr:6.635792566560442e-05 tokens_per_second_per_gpu:854.8656013827034
Step 861 | loss:1.6173244714736938 lr:6.63489541497965e-05 tokens_per_second_per_gpu:789.9606252388179
Step 862 | loss:1.5002086162567139 lr:6.633997220582007e-05 tokens_per_second_per_gpu:900.4214494894843
Step 863 | loss:1.3402966260910034 lr:6.633097983666299e-05 tokens_per_second_per_gpu:920.4232182048324
Step 864 | loss:1.5894304513931274 lr:6.632197704531654e-05 tokens_per_second_per_gpu:802.4148955214313
Step 865 | loss:1.3500568866729736 lr:6.631296383477549e-05 tokens_per_second_per_gpu:948.0129524942951
Step 866 | loss:1.4004645347595215 lr:6.630394020803804e-05 tokens_per_second_per_gpu:1093.5322779967903
Step 867 | loss:1.3919086456298828 lr:6.629490616810592e-05 tokens_per_second_per_gpu:1148.907664227795
Step 868 | loss:1.348287582397461 lr:6.628586171798427e-05 tokens_per_second_per_gpu:887.9998468191345
Step 869 | loss:1.6591246128082275 lr:6.627680686068169e-05 tokens_per_second_per_gpu:686.1657364611757
Step 870 | loss:1.3792707920074463 lr:6.626774159921029e-05 tokens_per_second_per_gpu:801.6795699206144
Step 871 | loss:1.4778001308441162 lr:6.625866593658558e-05 tokens_per_second_per_gpu:891.40267028296
Step 872 | loss:1.491215467453003 lr:6.624957987582659e-05 tokens_per_second_per_gpu:901.525735043039
Step 873 | loss:1.306517243385315 lr:6.624048341995579e-05 tokens_per_second_per_gpu:992.5592929292194
Step 874 | loss:1.379433274269104 lr:6.623137657199906e-05 tokens_per_second_per_gpu:1006.6234328527557
Step 875 | loss:1.4208496809005737 lr:6.622225933498578e-05 tokens_per_second_per_gpu:733.218325371981
Step 876 | loss:1.5414077043533325 lr:6.621313171194881e-05 tokens_per_second_per_gpu:694.6644495910263
Step 877 | loss:1.4477850198745728 lr:6.620399370592443e-05 tokens_per_second_per_gpu:917.7809663587741
Step 878 | loss:1.4827128648757935 lr:6.619484531995235e-05 tokens_per_second_per_gpu:815.8914086885725
Step 879 | loss:1.616342544555664 lr:6.61856865570758e-05 tokens_per_second_per_gpu:821.5447836760568
Step 880 | loss:1.480988621711731 lr:6.617651742034142e-05 tokens_per_second_per_gpu:855.0976941032441
Step 881 | loss:1.573185682296753 lr:6.616733791279927e-05 tokens_per_second_per_gpu:941.1599448980202
Step 882 | loss:1.4403704404830933 lr:6.615814803750292e-05 tokens_per_second_per_gpu:1089.8816365032706
Step 883 | loss:1.5465872287750244 lr:6.614894779750937e-05 tokens_per_second_per_gpu:794.0165814922932
Step 884 | loss:1.3100042343139648 lr:6.613973719587905e-05 tokens_per_second_per_gpu:828.626435557675
Step 885 | loss:1.54878568649292 lr:6.613051623567586e-05 tokens_per_second_per_gpu:844.8726593438
Step 886 | loss:1.5757852792739868 lr:6.612128491996712e-05 tokens_per_second_per_gpu:640.3996538775981
Step 887 | loss:1.38084077835083 lr:6.611204325182362e-05 tokens_per_second_per_gpu:1055.3788605333673
Step 888 | loss:1.398323893547058 lr:6.610279123431958e-05 tokens_per_second_per_gpu:1119.7490999674467
Step 889 | loss:1.417156457901001 lr:6.609352887053267e-05 tokens_per_second_per_gpu:1181.8004678583404
Step 890 | loss:1.5317933559417725 lr:6.608425616354399e-05 tokens_per_second_per_gpu:894.1800649149111
Step 891 | loss:1.3294774293899536 lr:6.607497311643809e-05 tokens_per_second_per_gpu:1205.8637399152162
Step 892 | loss:1.5530784130096436 lr:6.606567973230297e-05 tokens_per_second_per_gpu:743.7718466890209
Step 893 | loss:1.531588077545166 lr:6.605637601423003e-05 tokens_per_second_per_gpu:1003.9402281148332
Step 894 | loss:1.4753773212432861 lr:6.604706196531415e-05 tokens_per_second_per_gpu:741.1058014959976
Step 895 | loss:1.564588189125061 lr:6.603773758865362e-05 tokens_per_second_per_gpu:1020.9188796796327
Step 896 | loss:1.330409049987793 lr:6.60284028873502e-05 tokens_per_second_per_gpu:806.5614279210056
Step 897 | loss:1.488074779510498 lr:6.601905786450905e-05 tokens_per_second_per_gpu:797.5657538308374
Step 898 | loss:1.329121470451355 lr:6.600970252323874e-05 tokens_per_second_per_gpu:991.2018179415021
Step 899 | loss:1.4497802257537842 lr:6.600033686665136e-05 tokens_per_second_per_gpu:755.7099737934582
Step 900 | loss:1.403629183769226 lr:6.599096089786233e-05 tokens_per_second_per_gpu:856.4297776667786
Step 901 | loss:1.5696437358856201 lr:6.598157461999059e-05 tokens_per_second_per_gpu:1010.4134178726193
Step 902 | loss:1.5350160598754883 lr:6.597217803615845e-05 tokens_per_second_per_gpu:846.4194932971388
Step 903 | loss:1.4443793296813965 lr:6.596277114949164e-05 tokens_per_second_per_gpu:1055.2457776494377
Step 904 | loss:1.6954272985458374 lr:6.595335396311936e-05 tokens_per_second_per_gpu:819.7399910564316
Step 905 | loss:1.4585678577423096 lr:6.594392648017425e-05 tokens_per_second_per_gpu:888.4602424897502
Step 906 | loss:1.515691876411438 lr:6.593448870379229e-05 tokens_per_second_per_gpu:864.8725535376575
Step 907 | loss:1.4983165264129639 lr:6.592504063711297e-05 tokens_per_second_per_gpu:704.2926807052976
Step 908 | loss:1.5374810695648193 lr:6.591558228327918e-05 tokens_per_second_per_gpu:977.1990816888342
Step 909 | loss:1.4379111528396606 lr:6.590611364543719e-05 tokens_per_second_per_gpu:1017.4295981216924
Step 910 | loss:1.3396742343902588 lr:6.589663472673677e-05 tokens_per_second_per_gpu:1097.21632758293
Step 911 | loss:1.363938570022583 lr:6.5887145530331e-05 tokens_per_second_per_gpu:1122.1209751009756
Step 912 | loss:1.5698269605636597 lr:6.58776460593765e-05 tokens_per_second_per_gpu:1042.4932292404146
Step 913 | loss:1.5656203031539917 lr:6.586813631703322e-05 tokens_per_second_per_gpu:732.532334765438
Step 914 | loss:1.5410706996917725 lr:6.585861630646457e-05 tokens_per_second_per_gpu:877.4728677240629
Step 915 | loss:1.3812577724456787 lr:6.584908603083737e-05 tokens_per_second_per_gpu:766.6500566380753
Step 916 | loss:1.4896368980407715 lr:6.583954549332182e-05 tokens_per_second_per_gpu:900.8228147714804
Step 917 | loss:1.4884356260299683 lr:6.582999469709159e-05 tokens_per_second_per_gpu:771.5605129665271
Step 918 | loss:1.5534653663635254 lr:6.582043364532371e-05 tokens_per_second_per_gpu:600.7927273240152
Step 919 | loss:1.326904058456421 lr:6.581086234119867e-05 tokens_per_second_per_gpu:757.099064698384
Step 920 | loss:1.5343769788742065 lr:6.580128078790034e-05 tokens_per_second_per_gpu:913.7951242750443
Step 921 | loss:1.5505321025848389 lr:6.579168898861598e-05 tokens_per_second_per_gpu:829.4517101368278
Step 922 | loss:1.2558842897415161 lr:6.57820869465363e-05 tokens_per_second_per_gpu:1141.905631815481
Step 923 | loss:1.365797758102417 lr:6.577247466485541e-05 tokens_per_second_per_gpu:914.8387431725386
Step 924 | loss:1.5937047004699707 lr:6.576285214677082e-05 tokens_per_second_per_gpu:655.5488476910808
Step 925 | loss:1.5191527605056763 lr:6.575321939548341e-05 tokens_per_second_per_gpu:683.7430816667247
Step 926 | loss:1.4473508596420288 lr:6.574357641419753e-05 tokens_per_second_per_gpu:964.3994001168782
Step 927 | loss:1.3561720848083496 lr:6.573392320612086e-05 tokens_per_second_per_gpu:1068.4895469098403
Step 928 | loss:1.455590844154358 lr:6.572425977446458e-05 tokens_per_second_per_gpu:819.5430063831774
Step 929 | loss:1.6223145723342896 lr:6.571458612244316e-05 tokens_per_second_per_gpu:803.5113351967051
Step 930 | loss:1.6258544921875 lr:6.570490225327454e-05 tokens_per_second_per_gpu:996.3360743581602
Step 931 | loss:1.5705257654190063 lr:6.569520817018004e-05 tokens_per_second_per_gpu:587.8145025816304
Step 932 | loss:1.3774068355560303 lr:6.568550387638438e-05 tokens_per_second_per_gpu:888.0113998093575
Step 933 | loss:1.4328806400299072 lr:6.567578937511567e-05 tokens_per_second_per_gpu:1191.9449018354876
Step 934 | loss:1.5109702348709106 lr:6.566606466960542e-05 tokens_per_second_per_gpu:891.2166297205832
Step 935 | loss:1.4392648935317993 lr:6.565632976308855e-05 tokens_per_second_per_gpu:901.1841270774971
Step 936 | loss:1.4853898286819458 lr:6.564658465880333e-05 tokens_per_second_per_gpu:800.8039265940214
Step 937 | loss:1.2429474592208862 lr:6.563682935999147e-05 tokens_per_second_per_gpu:973.2881731778854
Step 938 | loss:1.5026953220367432 lr:6.562706386989805e-05 tokens_per_second_per_gpu:807.5605946542647
Step 939 | loss:1.4158331155776978 lr:6.561728819177152e-05 tokens_per_second_per_gpu:956.9355511177971
Step 940 | loss:1.4592534303665161 lr:6.560750232886375e-05 tokens_per_second_per_gpu:715.2780893815205
Step 941 | loss:1.3024272918701172 lr:6.559770628443002e-05 tokens_per_second_per_gpu:905.7519324519269
Step 942 | loss:1.3551816940307617 lr:6.558790006172892e-05 tokens_per_second_per_gpu:1299.563646190635
Step 943 | loss:1.3986300230026245 lr:6.55780836640225e-05 tokens_per_second_per_gpu:1001.661128309679
Step 944 | loss:1.3293931484222412 lr:6.556825709457616e-05 tokens_per_second_per_gpu:786.502110339474
Step 945 | loss:1.3824270963668823 lr:6.555842035665867e-05 tokens_per_second_per_gpu:977.9730697715843
Step 946 | loss:1.395117163658142 lr:6.554857345354224e-05 tokens_per_second_per_gpu:757.9757384928557
Step 947 | loss:1.4768409729003906 lr:6.553871638850237e-05 tokens_per_second_per_gpu:954.3011016475499
Step 948 | loss:1.5645167827606201 lr:6.552884916481805e-05 tokens_per_second_per_gpu:889.2153070796506
Step 949 | loss:1.4268062114715576 lr:6.551897178577155e-05 tokens_per_second_per_gpu:943.1311434213907
Step 950 | loss:1.4350168704986572 lr:6.550908425464859e-05 tokens_per_second_per_gpu:858.3136502010068
Step 951 | loss:1.5749280452728271 lr:6.549918657473822e-05 tokens_per_second_per_gpu:754.9715333710359
Step 952 | loss:1.3785533905029297 lr:6.548927874933288e-05 tokens_per_second_per_gpu:954.1944813563806
Step 953 | loss:1.3191969394683838 lr:6.547936078172841e-05 tokens_per_second_per_gpu:979.6718515324083
Step 954 | loss:1.5924696922302246 lr:6.5469432675224e-05 tokens_per_second_per_gpu:730.6077699857269
Step 955 | loss:1.4813123941421509 lr:6.545949443312218e-05 tokens_per_second_per_gpu:839.2462203960074
Step 956 | loss:1.363078236579895 lr:6.544954605872892e-05 tokens_per_second_per_gpu:1019.0066666551689
Step 957 | loss:1.513088583946228 lr:6.543958755535353e-05 tokens_per_second_per_gpu:888.8472690519147
Step 958 | loss:1.6086273193359375 lr:6.542961892630867e-05 tokens_per_second_per_gpu:673.8331734508616
Step 959 | loss:1.6884018182754517 lr:6.541964017491039e-05 tokens_per_second_per_gpu:867.4614667350155
Step 960 | loss:1.621097207069397 lr:6.54096513044781e-05 tokens_per_second_per_gpu:726.4826113557027
Step 961 | loss:1.5553138256072998 lr:6.539965231833459e-05 tokens_per_second_per_gpu:793.1861717749317
Step 962 | loss:1.5764881372451782 lr:6.5389643219806e-05 tokens_per_second_per_gpu:919.69177302238
Step 963 | loss:1.5373725891113281 lr:6.537962401222182e-05 tokens_per_second_per_gpu:1156.7674689060502
Step 964 | loss:1.5108062028884888 lr:6.536959469891494e-05 tokens_per_second_per_gpu:791.918872555158
Step 965 | loss:1.4371237754821777 lr:6.535955528322158e-05 tokens_per_second_per_gpu:947.4830212178257
Step 966 | loss:1.5007343292236328 lr:6.534950576848134e-05 tokens_per_second_per_gpu:796.8276985060324
Step 967 | loss:1.464267611503601 lr:6.533944615803716e-05 tokens_per_second_per_gpu:1122.057949226415
Step 968 | loss:1.4674526453018188 lr:6.532937645523536e-05 tokens_per_second_per_gpu:755.2128234289373
Step 969 | loss:1.468348741531372 lr:6.531929666342561e-05 tokens_per_second_per_gpu:772.2141687218564
Step 970 | loss:1.4649533033370972 lr:6.530920678596092e-05 tokens_per_second_per_gpu:971.0819305395828
Step 971 | loss:1.4991559982299805 lr:6.529910682619768e-05 tokens_per_second_per_gpu:982.9712556248937
Step 972 | loss:1.5321389436721802 lr:6.528899678749562e-05 tokens_per_second_per_gpu:973.3665191854229
Step 973 | loss:1.4815952777862549 lr:6.527887667321782e-05 tokens_per_second_per_gpu:953.4465653576603
Step 974 | loss:1.3115136623382568 lr:6.526874648673072e-05 tokens_per_second_per_gpu:1194.4811898654455
Step 975 | loss:1.3967738151550293 lr:6.52586062314041e-05 tokens_per_second_per_gpu:693.7732314355434
Step 976 | loss:1.4527561664581299 lr:6.52484559106111e-05 tokens_per_second_per_gpu:1015.5606209736276
Step 977 | loss:1.5421851873397827 lr:6.523829552772821e-05 tokens_per_second_per_gpu:660.1516302523722
Step 978 | loss:1.4351027011871338 lr:6.522812508613526e-05 tokens_per_second_per_gpu:774.4099871562395
Step 979 | loss:1.3739269971847534 lr:6.521794458921542e-05 tokens_per_second_per_gpu:943.9168936550047
Step 980 | loss:1.3513281345367432 lr:6.520775404035522e-05 tokens_per_second_per_gpu:1190.6197423167368
Step 981 | loss:1.5334995985031128 lr:6.519755344294451e-05 tokens_per_second_per_gpu:811.4249856281555
Step 982 | loss:1.349290370941162 lr:6.518734280037654e-05 tokens_per_second_per_gpu:1026.2855638777346
Step 983 | loss:1.4869253635406494 lr:6.517712211604781e-05 tokens_per_second_per_gpu:906.2896665744257
Step 984 | loss:1.3422752618789673 lr:6.516689139335825e-05 tokens_per_second_per_gpu:1127.9666070110147
Step 985 | loss:1.5163484811782837 lr:6.515665063571106e-05 tokens_per_second_per_gpu:775.0494067315237
Step 986 | loss:1.2510573863983154 lr:6.514639984651282e-05 tokens_per_second_per_gpu:934.2869319975821
Step 987 | loss:1.4396706819534302 lr:6.513613902917345e-05 tokens_per_second_per_gpu:884.0327955333651
Step 988 | loss:1.4766454696655273 lr:6.512586818710616e-05 tokens_per_second_per_gpu:726.1729891833622
Step 989 | loss:1.6361465454101562 lr:6.511558732372755e-05 tokens_per_second_per_gpu:662.0798543303783
Step 990 | loss:1.5068230628967285 lr:6.510529644245753e-05 tokens_per_second_per_gpu:785.648575491949
Step 991 | loss:1.5870110988616943 lr:6.509499554671932e-05 tokens_per_second_per_gpu:665.0170811007283
Step 992 | loss:1.3797491788864136 lr:6.508468463993952e-05 tokens_per_second_per_gpu:883.4943507403415
Step 993 | loss:1.3715732097625732 lr:6.5074363725548e-05 tokens_per_second_per_gpu:999.0108182932997
Step 994 | loss:1.5106379985809326 lr:6.506403280697804e-05 tokens_per_second_per_gpu:822.8855741114074
Step 995 | loss:1.553407073020935 lr:6.505369188766615e-05 tokens_per_second_per_gpu:629.1457534434107
Step 996 | loss:1.3595433235168457 lr:6.504334097105225e-05 tokens_per_second_per_gpu:992.3186014068433
Step 997 | loss:1.458359718322754 lr:6.503298006057954e-05 tokens_per_second_per_gpu:748.3008034673474
Step 998 | loss:1.316164255142212 lr:6.502260915969454e-05 tokens_per_second_per_gpu:1216.6871811781532
Step 999 | loss:1.5173695087432861 lr:6.501222827184715e-05 tokens_per_second_per_gpu:784.8539381203514
Step 1000 | loss:1.6210194826126099 lr:6.500183740049051e-05 tokens_per_second_per_gpu:816.5191469552798
Step 1001 | loss:1.313891887664795 lr:6.499143654908116e-05 tokens_per_second_per_gpu:1016.9933050476893
Step 1002 | loss:1.505763292312622 lr:6.498102572107889e-05 tokens_per_second_per_gpu:1085.1577333521157
Step 1003 | loss:1.470079779624939 lr:6.497060491994687e-05 tokens_per_second_per_gpu:767.2380042963241
Step 1004 | loss:1.440169095993042 lr:6.496017414915154e-05 tokens_per_second_per_gpu:897.7367495200455
Step 1005 | loss:1.4721440076828003 lr:6.494973341216268e-05 tokens_per_second_per_gpu:813.6016643749533
Step 1006 | loss:1.495092749595642 lr:6.493928271245338e-05 tokens_per_second_per_gpu:758.0091049837725
Step 1007 | loss:1.4972671270370483 lr:6.492882205350005e-05 tokens_per_second_per_gpu:862.4699395886587
Step 1008 | loss:1.4851305484771729 lr:6.49183514387824e-05 tokens_per_second_per_gpu:841.2902849037225
Step 1009 | loss:1.507521629333496 lr:6.490787087178348e-05 tokens_per_second_per_gpu:724.4679207316301
Step 1010 | loss:1.5366696119308472 lr:6.489738035598961e-05 tokens_per_second_per_gpu:605.0643064915129
Step 1011 | loss:1.4156787395477295 lr:6.488687989489043e-05 tokens_per_second_per_gpu:963.3594734809873
Step 1012 | loss:1.4078478813171387 lr:6.487636949197893e-05 tokens_per_second_per_gpu:831.5700077716918
Step 1013 | loss:1.4522831439971924 lr:6.486584915075135e-05 tokens_per_second_per_gpu:861.8264700030941
Step 1014 | loss:1.358375072479248 lr:6.485531887470727e-05 tokens_per_second_per_gpu:675.4475363461153
Step 1015 | loss:1.4500415325164795 lr:6.484477866734956e-05 tokens_per_second_per_gpu:814.3314085263574
Step 1016 | loss:1.3854724168777466 lr:6.483422853218441e-05 tokens_per_second_per_gpu:1189.4219310256813
Step 1017 | loss:1.459815502166748 lr:6.48236684727213e-05 tokens_per_second_per_gpu:840.0276293641435
Step 1018 | loss:1.4541468620300293 lr:6.4813098492473e-05 tokens_per_second_per_gpu:1265.1278472234544
Step 1019 | loss:1.2841575145721436 lr:6.48025185949556e-05 tokens_per_second_per_gpu:1116.7976162258688
Step 1020 | loss:1.2839686870574951 lr:6.479192878368849e-05 tokens_per_second_per_gpu:1167.7036077891946
Step 1021 | loss:1.421586275100708 lr:6.478132906219434e-05 tokens_per_second_per_gpu:930.7763548532013
Step 1022 | loss:1.5900168418884277 lr:6.477071943399913e-05 tokens_per_second_per_gpu:932.5422495335571
Step 1023 | loss:1.3428282737731934 lr:6.476009990263213e-05 tokens_per_second_per_gpu:851.15366520949
Step 1024 | loss:1.4679208993911743 lr:6.474947047162592e-05 tokens_per_second_per_gpu:847.5417669540967
Step 1025 | loss:1.4887968301773071 lr:6.473883114451636e-05 tokens_per_second_per_gpu:896.2163657089026
Step 1026 | loss:1.4793788194656372 lr:6.472818192484256e-05 tokens_per_second_per_gpu:1097.6145339502712
Step 1027 | loss:1.3950875997543335 lr:6.471752281614701e-05 tokens_per_second_per_gpu:944.6033246342906
Step 1028 | loss:1.407800316810608 lr:6.470685382197543e-05 tokens_per_second_per_gpu:1224.1158981016983
Step 1029 | loss:1.4838080406188965 lr:6.469617494587683e-05 tokens_per_second_per_gpu:663.1200188082101
Step 1030 | loss:1.5660971403121948 lr:6.468548619140352e-05 tokens_per_second_per_gpu:772.873157204932
Step 1031 | loss:1.5966763496398926 lr:6.467478756211109e-05 tokens_per_second_per_gpu:699.1621257890638
Step 1032 | loss:1.3779946565628052 lr:6.466407906155844e-05 tokens_per_second_per_gpu:867.4288131938745
Step 1033 | loss:1.3925073146820068 lr:6.465336069330769e-05 tokens_per_second_per_gpu:748.686512035692
Step 1034 | loss:1.5225998163223267 lr:6.464263246092434e-05 tokens_per_second_per_gpu:736.526619516893
Step 1035 | loss:1.6050975322723389 lr:6.463189436797707e-05 tokens_per_second_per_gpu:705.2174104569311
Step 1036 | loss:1.462287425994873 lr:6.46211464180379e-05 tokens_per_second_per_gpu:774.1556764179405
Step 1037 | loss:1.4159492254257202 lr:6.461038861468211e-05 tokens_per_second_per_gpu:842.4992745282699
Step 1038 | loss:1.4724705219268799 lr:6.459962096148828e-05 tokens_per_second_per_gpu:795.5137355182314
Step 1039 | loss:1.3843096494674683 lr:6.458884346203822e-05 tokens_per_second_per_gpu:891.1542220360855
Step 1040 | loss:1.5216132402420044 lr:6.457805611991708e-05 tokens_per_second_per_gpu:811.479133205282
Step 1041 | loss:1.411803960800171 lr:6.456725893871321e-05 tokens_per_second_per_gpu:968.2178904002737
Step 1042 | loss:1.3133680820465088 lr:6.45564519220183e-05 tokens_per_second_per_gpu:1067.4906770442633
Step 1043 | loss:1.4058912992477417 lr:6.454563507342729e-05 tokens_per_second_per_gpu:1213.2698258341268
Step 1044 | loss:1.497309923171997 lr:6.453480839653835e-05 tokens_per_second_per_gpu:914.1982793081887
Step 1045 | loss:1.4861575365066528 lr:6.452397189495296e-05 tokens_per_second_per_gpu:1056.838050648887
Step 1046 | loss:1.4658094644546509 lr:6.45131255722759e-05 tokens_per_second_per_gpu:1038.7065848620432
Step 1047 | loss:1.476019024848938 lr:6.450226943211513e-05 tokens_per_second_per_gpu:1064.334997685329
Step 1048 | loss:1.5445317029953003 lr:6.449140347808194e-05 tokens_per_second_per_gpu:1120.9620674809498
Step 1049 | loss:1.454906940460205 lr:6.448052771379087e-05 tokens_per_second_per_gpu:770.2711648784316
Step 1050 | loss:1.418087363243103 lr:6.446964214285974e-05 tokens_per_second_per_gpu:752.3354470523171
Step 1051 | loss:1.4369871616363525 lr:6.44587467689096e-05 tokens_per_second_per_gpu:1049.7645142483798
Step 1052 | loss:1.3706001043319702 lr:6.444784159556475e-05 tokens_per_second_per_gpu:808.8460020125832
Step 1053 | loss:1.3731950521469116 lr:6.44369266264528e-05 tokens_per_second_per_gpu:1113.9243384770684
Step 1054 | loss:1.3897640705108643 lr:6.44260018652046e-05 tokens_per_second_per_gpu:876.1493991205429
Step 1055 | loss:1.6219227313995361 lr:6.441506731545424e-05 tokens_per_second_per_gpu:709.6920517940108
Step 1056 | loss:1.3846369981765747 lr:6.440412298083908e-05 tokens_per_second_per_gpu:982.2675489635811
Step 1057 | loss:1.2929714918136597 lr:6.439316886499972e-05 tokens_per_second_per_gpu:1103.4816302924173
Step 1058 | loss:1.5130614042282104 lr:6.438220497158004e-05 tokens_per_second_per_gpu:749.4004045648487
Step 1059 | loss:1.5518296957015991 lr:6.437123130422715e-05 tokens_per_second_per_gpu:908.6649316883099
Step 1060 | loss:1.5187140703201294 lr:6.436024786659142e-05 tokens_per_second_per_gpu:908.0264785805622
Step 1061 | loss:1.2637503147125244 lr:6.434925466232647e-05 tokens_per_second_per_gpu:1147.769322632446
Step 1062 | loss:1.392638921737671 lr:6.433825169508917e-05 tokens_per_second_per_gpu:763.2201487920287
Step 1063 | loss:1.4087624549865723 lr:6.432723896853963e-05 tokens_per_second_per_gpu:1057.2596982837413
Step 1064 | loss:1.3649846315383911 lr:6.431621648634122e-05 tokens_per_second_per_gpu:872.256799435853
Step 1065 | loss:1.5034958124160767 lr:6.430518425216054e-05 tokens_per_second_per_gpu:808.2525568039314
Step 1066 | loss:1.5088857412338257 lr:6.429414226966746e-05 tokens_per_second_per_gpu:858.1773508948278
Step 1067 | loss:1.6468770503997803 lr:6.428309054253504e-05 tokens_per_second_per_gpu:887.7525917717032
Step 1068 | loss:1.4964526891708374 lr:6.427202907443963e-05 tokens_per_second_per_gpu:887.5070877612654
Step 1069 | loss:1.4634929895401 lr:6.426095786906081e-05 tokens_per_second_per_gpu:846.4536853899642
Step 1070 | loss:1.461345911026001 lr:6.424987693008141e-05 tokens_per_second_per_gpu:938.9546255796013
Step 1071 | loss:1.538916826248169 lr:6.423878626118747e-05 tokens_per_second_per_gpu:1067.504642355417
Step 1072 | loss:1.4673558473587036 lr:6.422768586606825e-05 tokens_per_second_per_gpu:971.1882019613988
Step 1073 | loss:1.5156806707382202 lr:6.421657574841632e-05 tokens_per_second_per_gpu:949.7818301627409
Step 1074 | loss:1.4488563537597656 lr:6.420545591192742e-05 tokens_per_second_per_gpu:992.3768626140853
Step 1075 | loss:1.5979313850402832 lr:6.419432636030054e-05 tokens_per_second_per_gpu:809.9530709252024
Step 1076 | loss:1.4737628698349 lr:6.41831870972379e-05 tokens_per_second_per_gpu:791.8255229626005
Step 1077 | loss:1.3987630605697632 lr:6.417203812644496e-05 tokens_per_second_per_gpu:841.8946739970272
Step 1078 | loss:1.2437111139297485 lr:6.41608794516304e-05 tokens_per_second_per_gpu:952.7524434454842
Step 1079 | loss:1.516284704208374 lr:6.414971107650615e-05 tokens_per_second_per_gpu:804.2178534764697
Step 1080 | loss:1.631575107574463 lr:6.413853300478732e-05 tokens_per_second_per_gpu:680.6933866779489
Step 1081 | loss:1.5436110496520996 lr:6.412734524019229e-05 tokens_per_second_per_gpu:932.0367266596367
Step 1082 | loss:1.612040638923645 lr:6.411614778644264e-05 tokens_per_second_per_gpu:1051.7543776268192
Step 1083 | loss:1.482555627822876 lr:6.41049406472632e-05 tokens_per_second_per_gpu:1019.4160065491566
Step 1084 | loss:1.3913613557815552 lr:6.409372382638197e-05 tokens_per_second_per_gpu:1100.4287577654911
Step 1085 | loss:1.429268479347229 lr:6.408249732753023e-05 tokens_per_second_per_gpu:782.6020243719472
Step 1086 | loss:1.334409236907959 lr:6.407126115444245e-05 tokens_per_second_per_gpu:903.618697121272
Step 1087 | loss:1.4194175004959106 lr:6.406001531085632e-05 tokens_per_second_per_gpu:1143.1832727961903
Step 1088 | loss:1.585282564163208 lr:6.404875980051274e-05 tokens_per_second_per_gpu:804.8807453600373
Step 1089 | loss:1.5485494136810303 lr:6.403749462715584e-05 tokens_per_second_per_gpu:1051.2915533968896
Step 1090 | loss:1.4693958759307861 lr:6.402621979453294e-05 tokens_per_second_per_gpu:935.0944401060149
Step 1091 | loss:1.3292646408081055 lr:6.401493530639463e-05 tokens_per_second_per_gpu:1259.9351507408128
Step 1092 | loss:1.3511630296707153 lr:6.400364116649464e-05 tokens_per_second_per_gpu:772.8715343935851
Step 1093 | loss:1.3793836832046509 lr:6.399233737858996e-05 tokens_per_second_per_gpu:1126.4858779665703
Step 1094 | loss:1.5102874040603638 lr:6.398102394644076e-05 tokens_per_second_per_gpu:866.0771871181583
Step 1095 | loss:1.3328617811203003 lr:6.396970087381044e-05 tokens_per_second_per_gpu:1222.9818511883495
Step 1096 | loss:1.634759783744812 lr:6.39583681644656e-05 tokens_per_second_per_gpu:976.1604252591569
Step 1097 | loss:1.488004446029663 lr:6.394702582217604e-05 tokens_per_second_per_gpu:984.2945740745233
Step 1098 | loss:1.6798114776611328 lr:6.393567385071475e-05 tokens_per_second_per_gpu:906.4392333579056
Step 1099 | loss:1.4612767696380615 lr:6.392431225385798e-05 tokens_per_second_per_gpu:892.0892847030925
Step 1100 | loss:1.509177565574646 lr:6.391294103538511e-05 tokens_per_second_per_gpu:742.0083361394296
Step 1101 | loss:1.3815582990646362 lr:6.390156019907876e-05 tokens_per_second_per_gpu:840.623190196625
Step 1102 | loss:1.4299801588058472 lr:6.389016974872476e-05 tokens_per_second_per_gpu:826.6347854728292
Step 1103 | loss:1.3468270301818848 lr:6.387876968811211e-05 tokens_per_second_per_gpu:1033.2759488117435
Step 1104 | loss:1.394574761390686 lr:6.386736002103301e-05 tokens_per_second_per_gpu:739.455995173948
Step 1105 | loss:1.4807687997817993 lr:6.385594075128288e-05 tokens_per_second_per_gpu:849.7302522335667
Step 1106 | loss:1.3487242460250854 lr:6.38445118826603e-05 tokens_per_second_per_gpu:566.3251695441265
Step 1107 | loss:1.3989216089248657 lr:6.383307341896707e-05 tokens_per_second_per_gpu:998.0141662199742
Step 1108 | loss:1.4001461267471313 lr:6.382162536400819e-05 tokens_per_second_per_gpu:769.6377775209338
Step 1109 | loss:1.5128684043884277 lr:6.38101677215918e-05 tokens_per_second_per_gpu:959.9668331785813
Step 1110 | loss:1.4479557275772095 lr:6.379870049552927e-05 tokens_per_second_per_gpu:689.1078385814167
Step 1111 | loss:1.4461464881896973 lr:6.378722368963518e-05 tokens_per_second_per_gpu:722.5618008840735
Step 1112 | loss:1.5666953325271606 lr:6.377573730772723e-05 tokens_per_second_per_gpu:729.3263747123624
Step 1113 | loss:1.2828387022018433 lr:6.376424135362636e-05 tokens_per_second_per_gpu:871.4839536890647
Step 1114 | loss:1.3265739679336548 lr:6.375273583115669e-05 tokens_per_second_per_gpu:997.3040375085144
Step 1115 | loss:1.2366520166397095 lr:6.374122074414547e-05 tokens_per_second_per_gpu:1298.96427047724
Step 1116 | loss:1.3286052942276 lr:6.37296960964232e-05 tokens_per_second_per_gpu:1173.7961280207076
Step 1117 | loss:1.3871395587921143 lr:6.371816189182354e-05 tokens_per_second_per_gpu:846.7044128403022
Step 1118 | loss:1.4334162473678589 lr:6.370661813418331e-05 tokens_per_second_per_gpu:934.5986329860738
Step 1119 | loss:1.4817262887954712 lr:6.36950648273425e-05 tokens_per_second_per_gpu:772.0975353799814
Step 1120 | loss:1.3108978271484375 lr:6.368350197514432e-05 tokens_per_second_per_gpu:868.4175749536221
Step 1121 | loss:1.5142241716384888 lr:6.367192958143512e-05 tokens_per_second_per_gpu:958.2370728837234
Step 1122 | loss:1.4871702194213867 lr:6.366034765006444e-05 tokens_per_second_per_gpu:899.2213081068014
Step 1123 | loss:1.4406098127365112 lr:6.364875618488498e-05 tokens_per_second_per_gpu:852.6412934424391
Step 1124 | loss:1.6014331579208374 lr:6.363715518975262e-05 tokens_per_second_per_gpu:949.6062691681949
Step 1125 | loss:1.3950294256210327 lr:6.362554466852643e-05 tokens_per_second_per_gpu:1187.7435649546796
Step 1126 | loss:1.4182721376419067 lr:6.361392462506858e-05 tokens_per_second_per_gpu:837.4321324473419
Step 1127 | loss:1.418344497680664 lr:6.360229506324449e-05 tokens_per_second_per_gpu:1179.1347009191866
Step 1128 | loss:1.3290841579437256 lr:6.35906559869227e-05 tokens_per_second_per_gpu:782.4422729210648
Step 1129 | loss:1.4486513137817383 lr:6.357900739997493e-05 tokens_per_second_per_gpu:1008.5602144097325
Step 1130 | loss:1.4920803308486938 lr:6.356734930627605e-05 tokens_per_second_per_gpu:844.0220087015051
Step 1131 | loss:1.3651502132415771 lr:6.355568170970413e-05 tokens_per_second_per_gpu:1129.8745076701862
Step 1132 | loss:1.5127501487731934 lr:6.354400461414034e-05 tokens_per_second_per_gpu:765.7178010758588
Step 1133 | loss:1.5152312517166138 lr:6.353231802346906e-05 tokens_per_second_per_gpu:729.5134515227364
Step 1134 | loss:1.4675185680389404 lr:6.352062194157782e-05 tokens_per_second_per_gpu:1119.4585644887602
Step 1135 | loss:1.5135281085968018 lr:6.350891637235727e-05 tokens_per_second_per_gpu:757.5074641966897
Step 1136 | loss:1.4689431190490723 lr:6.349720131970127e-05 tokens_per_second_per_gpu:710.9900222528087
Step 1137 | loss:1.5016456842422485 lr:6.348547678750681e-05 tokens_per_second_per_gpu:885.031442332615
Step 1138 | loss:1.4296305179595947 lr:6.347374277967401e-05 tokens_per_second_per_gpu:834.6142534629109
Step 1139 | loss:1.482594609260559 lr:6.346199930010617e-05 tokens_per_second_per_gpu:707.3730291527063
Step 1140 | loss:1.512213110923767 lr:6.345024635270977e-05 tokens_per_second_per_gpu:961.1870361052913
Step 1141 | loss:1.284346580505371 lr:6.343848394139436e-05 tokens_per_second_per_gpu:1004.0336934094738
Step 1142 | loss:1.338188886642456 lr:6.342671207007272e-05 tokens_per_second_per_gpu:1085.858394202786
Step 1143 | loss:1.5220729112625122 lr:6.341493074266072e-05 tokens_per_second_per_gpu:901.3824628847593
Step 1144 | loss:1.2174819707870483 lr:6.340313996307739e-05 tokens_per_second_per_gpu:868.1087868457062
Step 1145 | loss:1.699162244796753 lr:6.339133973524492e-05 tokens_per_second_per_gpu:797.876795989446
Step 1146 | loss:1.5249502658843994 lr:6.337953006308863e-05 tokens_per_second_per_gpu:696.4660826805838
Step 1147 | loss:1.3754136562347412 lr:6.336771095053699e-05 tokens_per_second_per_gpu:806.0363730466789
Step 1148 | loss:1.4363688230514526 lr:6.33558824015216e-05 tokens_per_second_per_gpu:782.7484717918702
Step 1149 | loss:1.523510217666626 lr:6.33440444199772e-05 tokens_per_second_per_gpu:982.9152290421282
Step 1150 | loss:1.4272404909133911 lr:6.333219700984168e-05 tokens_per_second_per_gpu:1028.6084160983116
Step 1151 | loss:1.5152846574783325 lr:6.332034017505605e-05 tokens_per_second_per_gpu:1032.7092117712727
Step 1152 | loss:1.5406571626663208 lr:6.330847391956446e-05 tokens_per_second_per_gpu:870.3069146077354
Step 1153 | loss:1.4282633066177368 lr:6.329659824731422e-05 tokens_per_second_per_gpu:971.367380306406
Step 1154 | loss:1.5078235864639282 lr:6.328471316225573e-05 tokens_per_second_per_gpu:1100.4632822878975
Step 1155 | loss:1.5188426971435547 lr:6.327281866834254e-05 tokens_per_second_per_gpu:946.9284525146722
Step 1156 | loss:1.5769466161727905 lr:6.326091476953132e-05 tokens_per_second_per_gpu:759.0620614137271
Step 1157 | loss:1.61674964427948 lr:6.324900146978191e-05 tokens_per_second_per_gpu:948.5764105644316
Step 1158 | loss:1.5680480003356934 lr:6.323707877305723e-05 tokens_per_second_per_gpu:767.8273586682576
Step 1159 | loss:1.4309368133544922 lr:6.322514668332332e-05 tokens_per_second_per_gpu:979.9728030695467
Step 1160 | loss:1.5583727359771729 lr:6.32132052045494e-05 tokens_per_second_per_gpu:925.5328789857995
Step 1161 | loss:1.4738922119140625 lr:6.320125434070776e-05 tokens_per_second_per_gpu:1101.7604872408253
Step 1162 | loss:1.4221125841140747 lr:6.318929409577384e-05 tokens_per_second_per_gpu:985.5686676501043
Step 1163 | loss:1.3632065057754517 lr:6.317732447372618e-05 tokens_per_second_per_gpu:915.5760048183694
Step 1164 | loss:1.454020619392395 lr:6.316534547854648e-05 tokens_per_second_per_gpu:681.4307801810401
Step 1165 | loss:1.0779606103897095 lr:6.31533571142195e-05 tokens_per_second_per_gpu:941.1629738526866
Step 1166 | loss:1.4404786825180054 lr:6.314135938473315e-05 tokens_per_second_per_gpu:719.4794987928246
Step 1167 | loss:1.2425791025161743 lr:6.312935229407846e-05 tokens_per_second_per_gpu:1008.9756077039564
Step 1168 | loss:1.6207478046417236 lr:6.311733584624956e-05 tokens_per_second_per_gpu:780.1555857658165
Step 1169 | loss:1.4838688373565674 lr:6.310531004524371e-05 tokens_per_second_per_gpu:825.9613289000546
Step 1170 | loss:1.4684940576553345 lr:6.309327489506126e-05 tokens_per_second_per_gpu:962.7076024779477
Step 1171 | loss:1.3003878593444824 lr:6.308123039970568e-05 tokens_per_second_per_gpu:924.4945565122496
Step 1172 | loss:1.3143736124038696 lr:6.306917656318354e-05 tokens_per_second_per_gpu:1157.0463744095216
Step 1173 | loss:1.5083613395690918 lr:6.305711338950454e-05 tokens_per_second_per_gpu:1024.105324809091
Step 1174 | loss:1.4566391706466675 lr:6.304504088268145e-05 tokens_per_second_per_gpu:1281.8241391295142
Step 1175 | loss:1.5708247423171997 lr:6.303295904673019e-05 tokens_per_second_per_gpu:809.6114846209954
Step 1176 | loss:1.3331100940704346 lr:6.302086788566975e-05 tokens_per_second_per_gpu:716.2945449379749
Step 1177 | loss:1.394670009613037 lr:6.300876740352223e-05 tokens_per_second_per_gpu:872.1929335157441
Step 1178 | loss:1.4462281465530396 lr:6.299665760431283e-05 tokens_per_second_per_gpu:806.3458774571866
Step 1179 | loss:1.4906675815582275 lr:6.298453849206986e-05 tokens_per_second_per_gpu:875.3545539264009
Step 1180 | loss:1.475247859954834 lr:6.297241007082469e-05 tokens_per_second_per_gpu:747.9147612574019
Step 1181 | loss:1.5129426717758179 lr:6.296027234461185e-05 tokens_per_second_per_gpu:828.5476183257376
Step 1182 | loss:1.4146263599395752 lr:6.294812531746892e-05 tokens_per_second_per_gpu:647.9274659339756
Step 1183 | loss:1.684096336364746 lr:6.293596899343659e-05 tokens_per_second_per_gpu:1051.1050534155677
Step 1184 | loss:1.3724690675735474 lr:6.292380337655863e-05 tokens_per_second_per_gpu:767.3455484142509
Step 1185 | loss:1.4615981578826904 lr:6.29116284708819e-05 tokens_per_second_per_gpu:980.514646958299
Step 1186 | loss:1.4968501329421997 lr:6.289944428045636e-05 tokens_per_second_per_gpu:974.3043555865913
Step 1187 | loss:1.4636701345443726 lr:6.288725080933508e-05 tokens_per_second_per_gpu:1207.2031326934386
Step 1188 | loss:1.3892548084259033 lr:6.287504806157418e-05 tokens_per_second_per_gpu:941.7073976567151
Step 1189 | loss:1.3451865911483765 lr:6.286283604123288e-05 tokens_per_second_per_gpu:837.1341881941436
Step 1190 | loss:1.3586289882659912 lr:6.285061475237347e-05 tokens_per_second_per_gpu:795.0219064940467
Step 1191 | loss:1.4817044734954834 lr:6.283838419906138e-05 tokens_per_second_per_gpu:1259.862217749858
Step 1192 | loss:1.5831685066223145 lr:6.282614438536503e-05 tokens_per_second_per_gpu:792.153209402879
Step 1193 | loss:1.1539289951324463 lr:6.281389531535599e-05 tokens_per_second_per_gpu:1416.7923379256592
Step 1194 | loss:1.4324634075164795 lr:6.280163699310892e-05 tokens_per_second_per_gpu:808.0640524778088
Step 1195 | loss:1.5199476480484009 lr:6.278936942270147e-05 tokens_per_second_per_gpu:881.6845653572401
Step 1196 | loss:1.4793384075164795 lr:6.277709260821447e-05 tokens_per_second_per_gpu:897.6619883567471
Step 1197 | loss:1.4723306894302368 lr:6.276480655373176e-05 tokens_per_second_per_gpu:1035.3347599474585
Step 1198 | loss:1.4094374179840088 lr:6.275251126334026e-05 tokens_per_second_per_gpu:888.0706412389508
Step 1199 | loss:1.255050778388977 lr:6.274020674112999e-05 tokens_per_second_per_gpu:1177.6192673703163
Step 1200 | loss:1.5295047760009766 lr:6.272789299119402e-05 tokens_per_second_per_gpu:754.5929547780752
Step 1201 | loss:1.3187344074249268 lr:6.27155700176285e-05 tokens_per_second_per_gpu:853.5068353323667
Step 1202 | loss:1.443704605102539 lr:6.270323782453265e-05 tokens_per_second_per_gpu:906.0247069980983
Step 1203 | loss:1.5228513479232788 lr:6.269089641600873e-05 tokens_per_second_per_gpu:988.4201172278662
Step 1204 | loss:1.5133860111236572 lr:6.26785457961621e-05 tokens_per_second_per_gpu:878.1587202060451
Step 1205 | loss:1.3698800802230835 lr:6.266618596910117e-05 tokens_per_second_per_gpu:841.200559418084
Step 1206 | loss:1.5722050666809082 lr:6.265381693893741e-05 tokens_per_second_per_gpu:641.4331220472874
Step 1207 | loss:1.3461177349090576 lr:6.264143870978534e-05 tokens_per_second_per_gpu:800.9837237125602
Step 1208 | loss:1.3765239715576172 lr:6.262905128576257e-05 tokens_per_second_per_gpu:712.4020597346355
Step 1209 | loss:1.3223176002502441 lr:6.261665467098975e-05 tokens_per_second_per_gpu:964.0443703784545
Step 1210 | loss:1.3939428329467773 lr:6.26042488695906e-05 tokens_per_second_per_gpu:740.9080512603509
Step 1211 | loss:1.4073034524917603 lr:6.259183388569185e-05 tokens_per_second_per_gpu:983.8851469617538
Step 1212 | loss:1.4730302095413208 lr:6.257940972342335e-05 tokens_per_second_per_gpu:870.0517374273812
Step 1213 | loss:1.4243552684783936 lr:6.256697638691798e-05 tokens_per_second_per_gpu:828.5921955845387
Step 1214 | loss:1.4467049837112427 lr:6.255453388031165e-05 tokens_per_second_per_gpu:923.7305990599533
Step 1215 | loss:1.2122114896774292 lr:6.254208220774332e-05 tokens_per_second_per_gpu:1300.7332992220893
Step 1216 | loss:1.479938268661499 lr:6.252962137335504e-05 tokens_per_second_per_gpu:1054.3148882234955
Step 1217 | loss:1.5470843315124512 lr:6.251715138129189e-05 tokens_per_second_per_gpu:885.617387437764
Step 1218 | loss:1.3983757495880127 lr:6.250467223570196e-05 tokens_per_second_per_gpu:941.9441773280568
Step 1219 | loss:1.5016199350357056 lr:6.249218394073642e-05 tokens_per_second_per_gpu:839.2160645750345
Step 1220 | loss:1.3761245012283325 lr:6.247968650054949e-05 tokens_per_second_per_gpu:811.3768280309935
Step 1221 | loss:1.402233600616455 lr:6.246717991929841e-05 tokens_per_second_per_gpu:765.6572989594258
Step 1222 | loss:1.3172197341918945 lr:6.245466420114348e-05 tokens_per_second_per_gpu:1098.9945394381282
Step 1223 | loss:1.504049301147461 lr:6.244213935024803e-05 tokens_per_second_per_gpu:730.1631026782663
Step 1224 | loss:1.127945899963379 lr:6.24296053707784e-05 tokens_per_second_per_gpu:1220.5357852248765
Step 1225 | loss:1.4972960948944092 lr:6.241706226690402e-05 tokens_per_second_per_gpu:764.6992855168309
Step 1226 | loss:1.5316475629806519 lr:6.240451004279732e-05 tokens_per_second_per_gpu:870.8759135247884
Step 1227 | loss:1.3670709133148193 lr:6.239194870263378e-05 tokens_per_second_per_gpu:1041.939183116803
Step 1228 | loss:1.4809168577194214 lr:6.237937825059189e-05 tokens_per_second_per_gpu:933.4087433812894
Step 1229 | loss:1.6301990747451782 lr:6.23667986908532e-05 tokens_per_second_per_gpu:779.7530069021182
Step 1230 | loss:1.5010887384414673 lr:6.235421002760228e-05 tokens_per_second_per_gpu:841.1475687593858
Step 1231 | loss:1.3817239999771118 lr:6.234161226502671e-05 tokens_per_second_per_gpu:823.2115592763532
Step 1232 | loss:1.2896977663040161 lr:6.232900540731712e-05 tokens_per_second_per_gpu:820.4483957754491
Step 1233 | loss:1.3246084451675415 lr:6.231638945866716e-05 tokens_per_second_per_gpu:1034.3571075791467
Step 1234 | loss:1.378740906715393 lr:6.230376442327349e-05 tokens_per_second_per_gpu:981.0905633814389
Step 1235 | loss:1.3709715604782104 lr:6.229113030533581e-05 tokens_per_second_per_gpu:1174.222296600864
Step 1236 | loss:1.578088641166687 lr:6.227848710905683e-05 tokens_per_second_per_gpu:742.1993459153598
Step 1237 | loss:1.3824167251586914 lr:6.226583483864228e-05 tokens_per_second_per_gpu:734.2850001825682
Step 1238 | loss:1.5522979497909546 lr:6.225317349830095e-05 tokens_per_second_per_gpu:781.3467294373637
Step 1239 | loss:1.447939157485962 lr:6.224050309224455e-05 tokens_per_second_per_gpu:853.8572819922999
Step 1240 | loss:1.378569483757019 lr:6.222782362468791e-05 tokens_per_second_per_gpu:796.0656601554922
Step 1241 | loss:1.3432235717773438 lr:6.221513509984883e-05 tokens_per_second_per_gpu:969.4040965795958
Step 1242 | loss:1.5323596000671387 lr:6.22024375219481e-05 tokens_per_second_per_gpu:873.454321064706
Step 1243 | loss:1.3333364725112915 lr:6.218973089520955e-05 tokens_per_second_per_gpu:882.312474397967
Step 1244 | loss:1.3575531244277954 lr:6.217701522386003e-05 tokens_per_second_per_gpu:874.57445572073
Step 1245 | loss:1.3443598747253418 lr:6.216429051212936e-05 tokens_per_second_per_gpu:918.2318191450563
Step 1246 | loss:1.4622360467910767 lr:6.215155676425041e-05 tokens_per_second_per_gpu:953.8245073835993
Step 1247 | loss:1.3964226245880127 lr:6.213881398445903e-05 tokens_per_second_per_gpu:888.3195074435727
Step 1248 | loss:1.4850900173187256 lr:6.212606217699407e-05 tokens_per_second_per_gpu:808.908791796591
Step 1249 | loss:1.479592204093933 lr:6.211330134609741e-05 tokens_per_second_per_gpu:932.1044354212871
Step 1250 | loss:1.438722014427185 lr:6.210053149601391e-05 tokens_per_second_per_gpu:718.8636403156316
Step 1251 | loss:1.6651571989059448 lr:6.208775263099146e-05 tokens_per_second_per_gpu:606.5989699562074
Step 1252 | loss:1.3867021799087524 lr:6.207496475528087e-05 tokens_per_second_per_gpu:894.0517950478319
Step 1253 | loss:1.437644124031067 lr:6.206216787313605e-05 tokens_per_second_per_gpu:958.472897270068
Step 1254 | loss:1.5223532915115356 lr:6.204936198881383e-05 tokens_per_second_per_gpu:1026.7310686338772
Step 1255 | loss:1.3840035200119019 lr:6.203654710657406e-05 tokens_per_second_per_gpu:893.8276519644852
Step 1256 | loss:1.5603795051574707 lr:6.202372323067962e-05 tokens_per_second_per_gpu:746.0825714534125
Step 1257 | loss:1.480879545211792 lr:6.201089036539633e-05 tokens_per_second_per_gpu:823.0234630964358
Step 1258 | loss:1.5098671913146973 lr:6.199804851499299e-05 tokens_per_second_per_gpu:734.3474696420409
Step 1259 | loss:1.5770022869110107 lr:6.198519768374146e-05 tokens_per_second_per_gpu:827.6172252604825
Step 1260 | loss:1.453173041343689 lr:6.197233787591652e-05 tokens_per_second_per_gpu:1115.007701594458
Step 1261 | loss:1.3786036968231201 lr:6.195946909579596e-05 tokens_per_second_per_gpu:918.0816821801413
Step 1262 | loss:1.3627369403839111 lr:6.194659134766056e-05 tokens_per_second_per_gpu:765.9332188238996
Step 1263 | loss:1.353614091873169 lr:6.193370463579407e-05 tokens_per_second_per_gpu:826.8028964051957
Step 1264 | loss:1.367957592010498 lr:6.192080896448323e-05 tokens_per_second_per_gpu:937.2217763968212
Step 1265 | loss:1.4328067302703857 lr:6.190790433801778e-05 tokens_per_second_per_gpu:656.4878698085148
Step 1266 | loss:1.5553604364395142 lr:6.18949907606904e-05 tokens_per_second_per_gpu:1162.7684749978148
Step 1267 | loss:1.323142409324646 lr:6.188206823679676e-05 tokens_per_second_per_gpu:1124.1161857684158
Step 1268 | loss:1.4029287099838257 lr:6.186913677063555e-05 tokens_per_second_per_gpu:1171.4458995487132
Step 1269 | loss:1.342341661453247 lr:6.185619636650834e-05 tokens_per_second_per_gpu:1235.9396331167836
Step 1270 | loss:1.448974609375 lr:6.184324702871978e-05 tokens_per_second_per_gpu:792.9689832707677
Step 1271 | loss:1.3332120180130005 lr:6.183028876157742e-05 tokens_per_second_per_gpu:994.9601780800132
Step 1272 | loss:1.4996833801269531 lr:6.18173215693918e-05 tokens_per_second_per_gpu:693.5531899239961
Step 1273 | loss:1.2617007493972778 lr:6.180434545647643e-05 tokens_per_second_per_gpu:886.5126717958606
Step 1274 | loss:1.3616323471069336 lr:6.179136042714781e-05 tokens_per_second_per_gpu:726.5894048156152
Step 1275 | loss:1.61592435836792 lr:6.177836648572536e-05 tokens_per_second_per_gpu:723.5245263309578
Step 1276 | loss:1.4120367765426636 lr:6.176536363653149e-05 tokens_per_second_per_gpu:833.7219693206167
Step 1277 | loss:1.5005978345870972 lr:6.175235188389159e-05 tokens_per_second_per_gpu:742.6201366569267
Step 1278 | loss:1.3023393154144287 lr:6.173933123213399e-05 tokens_per_second_per_gpu:1205.6573195193535
Step 1279 | loss:1.5372395515441895 lr:6.172630168558997e-05 tokens_per_second_per_gpu:697.2549597214028
Step 1280 | loss:1.4880623817443848 lr:6.171326324859379e-05 tokens_per_second_per_gpu:965.2452861749224
Step 1281 | loss:1.3851048946380615 lr:6.170021592548268e-05 tokens_per_second_per_gpu:726.0239794740817
Step 1282 | loss:1.409571886062622 lr:6.168715972059678e-05 tokens_per_second_per_gpu:1058.4347914918028
Step 1283 | loss:1.5173758268356323 lr:6.167409463827922e-05 tokens_per_second_per_gpu:879.3701567810422
Step 1284 | loss:1.4756262302398682 lr:6.166102068287608e-05 tokens_per_second_per_gpu:791.8204278157876
Step 1285 | loss:1.2594499588012695 lr:6.164793785873638e-05 tokens_per_second_per_gpu:817.5495704091162
Step 1286 | loss:1.386608362197876 lr:6.163484617021209e-05 tokens_per_second_per_gpu:797.485948906989
Step 1287 | loss:1.711384892463684 lr:6.162174562165815e-05 tokens_per_second_per_gpu:531.5863925440796
Step 1288 | loss:1.517608642578125 lr:6.160863621743243e-05 tokens_per_second_per_gpu:749.8842087167629
Step 1289 | loss:1.4064795970916748 lr:6.159551796189573e-05 tokens_per_second_per_gpu:671.2840816832372
Step 1290 | loss:1.5092251300811768 lr:6.158239085941182e-05 tokens_per_second_per_gpu:932.76927308082
Step 1291 | loss:1.397360920906067 lr:6.156925491434741e-05 tokens_per_second_per_gpu:934.58100645994
Step 1292 | loss:1.3939318656921387 lr:6.155611013107214e-05 tokens_per_second_per_gpu:1054.016784651177
Step 1293 | loss:1.3362104892730713 lr:6.154295651395862e-05 tokens_per_second_per_gpu:1120.8457735657921
Step 1294 | loss:1.2936224937438965 lr:6.152979406738235e-05 tokens_per_second_per_gpu:728.8031004656392
Step 1295 | loss:1.4198323488235474 lr:6.151662279572179e-05 tokens_per_second_per_gpu:876.7419899589073
Step 1296 | loss:1.3135178089141846 lr:6.150344270335836e-05 tokens_per_second_per_gpu:963.5131378346509
Step 1297 | loss:1.2865650653839111 lr:6.149025379467636e-05 tokens_per_second_per_gpu:844.3789026851322
Step 1298 | loss:1.3751444816589355 lr:6.14770560740631e-05 tokens_per_second_per_gpu:811.9865172393307
Step 1299 | loss:1.4876562356948853 lr:6.146384954590872e-05 tokens_per_second_per_gpu:633.3985485007449
Step 1300 | loss:1.4122439622879028 lr:6.14506342146064e-05 tokens_per_second_per_gpu:793.5938623128494
Step 1301 | loss:1.5084619522094727 lr:6.143741008455216e-05 tokens_per_second_per_gpu:708.3688020195292
Step 1302 | loss:1.4486933946609497 lr:6.142417716014498e-05 tokens_per_second_per_gpu:854.9755324368437
Step 1303 | loss:1.4507431983947754 lr:6.141093544578679e-05 tokens_per_second_per_gpu:692.072132797537
Step 1304 | loss:1.2433220148086548 lr:6.139768494588241e-05 tokens_per_second_per_gpu:1269.2009538659456
Step 1305 | loss:1.4481837749481201 lr:6.138442566483959e-05 tokens_per_second_per_gpu:1037.2956942152637
Step 1306 | loss:1.3467662334442139 lr:6.137115760706899e-05 tokens_per_second_per_gpu:972.8944042652896
Step 1307 | loss:1.5201704502105713 lr:6.135788077698423e-05 tokens_per_second_per_gpu:979.7687314320865
Step 1308 | loss:1.61163330078125 lr:6.134459517900181e-05 tokens_per_second_per_gpu:771.9399508877235
Step 1309 | loss:1.4065229892730713 lr:6.133130081754116e-05 tokens_per_second_per_gpu:1172.614046180616
Step 1310 | loss:1.5716460943222046 lr:6.131799769702461e-05 tokens_per_second_per_gpu:887.3396409847211
Step 1311 | loss:1.594102144241333 lr:6.130468582187745e-05 tokens_per_second_per_gpu:921.6475904987526
Step 1312 | loss:1.563899040222168 lr:6.129136519652781e-05 tokens_per_second_per_gpu:963.3257450008105
Step 1313 | loss:1.3640190362930298 lr:6.127803582540679e-05 tokens_per_second_per_gpu:1020.2018133049671
Step 1314 | loss:1.473209023475647 lr:6.126469771294839e-05 tokens_per_second_per_gpu:1024.7197976902976
Step 1315 | loss:1.4358792304992676 lr:6.125135086358947e-05 tokens_per_second_per_gpu:979.9439723228141
Step 1316 | loss:1.5200560092926025 lr:6.123799528176988e-05 tokens_per_second_per_gpu:730.7621417739094
Step 1317 | loss:1.3333399295806885 lr:6.122463097193229e-05 tokens_per_second_per_gpu:992.1299867339388
Step 1318 | loss:1.4531313180923462 lr:6.121125793852234e-05 tokens_per_second_per_gpu:1030.1041652715382
Step 1319 | loss:1.5984034538269043 lr:6.119787618598853e-05 tokens_per_second_per_gpu:600.335838421489
Step 1320 | loss:1.4286153316497803 lr:6.118448571878228e-05 tokens_per_second_per_gpu:705.5793819562869
Step 1321 | loss:1.524324655532837 lr:6.117108654135789e-05 tokens_per_second_per_gpu:666.7856723793391
Step 1322 | loss:1.200870156288147 lr:6.115767865817257e-05 tokens_per_second_per_gpu:1102.9789201597473
Step 1323 | loss:1.4047667980194092 lr:6.114426207368645e-05 tokens_per_second_per_gpu:837.1331280882725
Step 1324 | loss:1.355155348777771 lr:6.113083679236251e-05 tokens_per_second_per_gpu:1260.5614865396485
Step 1325 | loss:1.4576252698898315 lr:6.111740281866664e-05 tokens_per_second_per_gpu:1057.9748532645206
Step 1326 | loss:1.4745538234710693 lr:6.110396015706765e-05 tokens_per_second_per_gpu:712.7361692349497
Step 1327 | loss:1.4927849769592285 lr:6.109050881203718e-05 tokens_per_second_per_gpu:893.9330958680575
Step 1328 | loss:1.3167839050292969 lr:6.107704878804984e-05 tokens_per_second_per_gpu:718.3452238398031
Step 1329 | loss:1.4042288064956665 lr:6.106358008958303e-05 tokens_per_second_per_gpu:540.0802667918032
Step 1330 | loss:1.4079610109329224 lr:6.105010272111711e-05 tokens_per_second_per_gpu:855.7493465791431
Step 1331 | loss:1.5286431312561035 lr:6.103661668713531e-05 tokens_per_second_per_gpu:795.4584880984555
Step 1332 | loss:1.4893170595169067 lr:6.102312199212372e-05 tokens_per_second_per_gpu:871.6548445906192
Step 1333 | loss:1.5657391548156738 lr:6.100961864057132e-05 tokens_per_second_per_gpu:566.7734963731231
Step 1334 | loss:1.5364854335784912 lr:6.099610663696998e-05 tokens_per_second_per_gpu:761.3442877270465
Step 1335 | loss:1.4800362586975098 lr:6.098258598581446e-05 tokens_per_second_per_gpu:824.4848525051541
Step 1336 | loss:1.4696638584136963 lr:6.096905669160235e-05 tokens_per_second_per_gpu:723.1020828592956
Step 1337 | loss:1.3812487125396729 lr:6.0955518758834156e-05 tokens_per_second_per_gpu:1023.8518786495714
Step 1338 | loss:1.583933711051941 lr:6.094197219201323e-05 tokens_per_second_per_gpu:802.5008795541969
Step 1339 | loss:1.5296814441680908 lr:6.092841699564585e-05 tokens_per_second_per_gpu:915.190577366168
Step 1340 | loss:1.4215648174285889 lr:6.0914853174241074e-05 tokens_per_second_per_gpu:767.1956665159569
Step 1341 | loss:1.51499605178833 lr:6.090128073231092e-05 tokens_per_second_per_gpu:705.9621063674927
Step 1342 | loss:1.299330472946167 lr:6.0887699674370214e-05 tokens_per_second_per_gpu:975.0974834305727
Step 1343 | loss:1.4914169311523438 lr:6.087411000493668e-05 tokens_per_second_per_gpu:994.4441890699655
Step 1344 | loss:1.4648703336715698 lr:6.0860511728530884e-05 tokens_per_second_per_gpu:1036.74713830779
Step 1345 | loss:1.477566123008728 lr:6.084690484967628e-05 tokens_per_second_per_gpu:722.4520315573685
Step 1346 | loss:1.4503984451293945 lr:6.083328937289916e-05 tokens_per_second_per_gpu:862.8865864699776
Step 1347 | loss:1.6190778017044067 lr:6.081966530272869e-05 tokens_per_second_per_gpu:705.653327121891
Step 1348 | loss:1.2884925603866577 lr:6.080603264369688e-05 tokens_per_second_per_gpu:916.4942160729264
Step 1349 | loss:1.6151899099349976 lr:6.0792391400338616e-05 tokens_per_second_per_gpu:798.3532422137638
Step 1350 | loss:1.5921714305877686 lr:6.077874157719164e-05 tokens_per_second_per_gpu:848.4137101771225
Step 1351 | loss:1.5276918411254883 lr:6.0765083178796524e-05 tokens_per_second_per_gpu:782.6479939953906
Step 1352 | loss:1.4104002714157104 lr:6.0751416209696714e-05 tokens_per_second_per_gpu:1023.866741824407
Step 1353 | loss:1.461371898651123 lr:6.07377406744385e-05 tokens_per_second_per_gpu:714.7724142062632
Step 1354 | loss:1.4381132125854492 lr:6.072405657757102e-05 tokens_per_second_per_gpu:1057.2043102739328
Step 1355 | loss:1.4405725002288818 lr:6.071036392364627e-05 tokens_per_second_per_gpu:935.7697638019582
Step 1356 | loss:1.3261438608169556 lr:6.069666271721907e-05 tokens_per_second_per_gpu:1120.0421180114902
Step 1357 | loss:1.5249722003936768 lr:6.0682952962847115e-05 tokens_per_second_per_gpu:950.4127094644117
Step 1358 | loss:1.458096981048584 lr:6.066923466509092e-05 tokens_per_second_per_gpu:1042.9387120312026
Step 1359 | loss:1.4872941970825195 lr:6.065550782851385e-05 tokens_per_second_per_gpu:1082.6295468021196
Step 1360 | loss:1.5017304420471191 lr:6.064177245768211e-05 tokens_per_second_per_gpu:919.5434531901531
Step 1361 | loss:1.3121380805969238 lr:6.0628028557164754e-05 tokens_per_second_per_gpu:918.2087069163204
Step 1362 | loss:1.2394306659698486 lr:6.0614276131533654e-05 tokens_per_second_per_gpu:1084.7462612700951
Step 1363 | loss:1.4407352209091187 lr:6.060051518536352e-05 tokens_per_second_per_gpu:1055.488003360355
Step 1364 | loss:1.4856157302856445 lr:6.058674572323192e-05 tokens_per_second_per_gpu:889.0452390977124
Step 1365 | loss:1.302798867225647 lr:6.057296774971924e-05 tokens_per_second_per_gpu:1075.4393012218493
Step 1366 | loss:1.3945358991622925 lr:6.055918126940868e-05 tokens_per_second_per_gpu:988.5761865187442
Step 1367 | loss:1.4798882007598877 lr:6.05453862868863e-05 tokens_per_second_per_gpu:826.4645483522634
Step 1368 | loss:1.4205586910247803 lr:6.0531582806740965e-05 tokens_per_second_per_gpu:849.9675741234554
Step 1369 | loss:1.3636947870254517 lr:6.051777083356438e-05 tokens_per_second_per_gpu:1193.0938196933862
Step 1370 | loss:1.2653731107711792 lr:6.050395037195107e-05 tokens_per_second_per_gpu:1055.6914431936004
Step 1371 | loss:1.4654309749603271 lr:6.049012142649838e-05 tokens_per_second_per_gpu:861.4833701258912
Step 1372 | loss:1.366274118423462 lr:6.047628400180648e-05 tokens_per_second_per_gpu:919.5177517588163
Step 1373 | loss:1.404380440711975 lr:6.0462438102478386e-05 tokens_per_second_per_gpu:1160.4154655346667
Step 1374 | loss:1.464998483657837 lr:6.044858373311988e-05 tokens_per_second_per_gpu:802.5869119436182
Step 1375 | loss:1.475153923034668 lr:6.0434720898339604e-05 tokens_per_second_per_gpu:993.7438848884099
Step 1376 | loss:1.64878249168396 lr:6.042084960274901e-05 tokens_per_second_per_gpu:762.567849877241
Step 1377 | loss:1.4309704303741455 lr:6.0406969850962334e-05 tokens_per_second_per_gpu:908.6893514244789
Step 1378 | loss:1.3931150436401367 lr:6.039308164759667e-05 tokens_per_second_per_gpu:857.8573988424411
Step 1379 | loss:1.4997451305389404 lr:6.0379184997271895e-05 tokens_per_second_per_gpu:1082.3204370424216
Step 1380 | loss:1.6280694007873535 lr:6.0365279904610715e-05 tokens_per_second_per_gpu:640.7947382152379
Step 1381 | loss:1.3751815557479858 lr:6.035136637423862e-05 tokens_per_second_per_gpu:1083.4778146934823
Step 1382 | loss:1.5653053522109985 lr:6.03374444107839e-05 tokens_per_second_per_gpu:737.4949520390637
Step 1383 | loss:1.452429175376892 lr:6.0323514018877706e-05 tokens_per_second_per_gpu:958.9245509255185
Step 1384 | loss:1.5087848901748657 lr:6.030957520315392e-05 tokens_per_second_per_gpu:980.5710215015414
Step 1385 | loss:1.286583423614502 lr:6.029562796824929e-05 tokens_per_second_per_gpu:1103.6571367979616
Step 1386 | loss:1.2579600811004639 lr:6.0281672318803326e-05 tokens_per_second_per_gpu:770.5144167578244
Step 1387 | loss:1.2696696519851685 lr:6.026770825945834e-05 tokens_per_second_per_gpu:1061.8047065258231
Step 1388 | loss:1.2877874374389648 lr:6.025373579485947e-05 tokens_per_second_per_gpu:947.8009859073845
Step 1389 | loss:1.35124671459198 lr:6.0239754929654614e-05 tokens_per_second_per_gpu:851.3242063142558
Step 1390 | loss:1.4908874034881592 lr:6.0225765668494475e-05 tokens_per_second_per_gpu:1126.8730560865768
Step 1391 | loss:1.4439696073532104 lr:6.021176801603256e-05 tokens_per_second_per_gpu:840.8134733823642
Step 1392 | loss:1.633331537246704 lr:6.019776197692516e-05 tokens_per_second_per_gpu:773.6578740763583
Step 1393 | loss:1.4367886781692505 lr:6.018374755583137e-05 tokens_per_second_per_gpu:693.7474748675843
Step 1394 | loss:1.6169583797454834 lr:6.016972475741303e-05 tokens_per_second_per_gpu:655.0735995172352
Step 1395 | loss:1.445228934288025 lr:6.015569358633482e-05 tokens_per_second_per_gpu:1082.5493319059965
Step 1396 | loss:1.4601022005081177 lr:6.0141654047264176e-05 tokens_per_second_per_gpu:947.3166890906266
Step 1397 | loss:1.5431573390960693 lr:6.0127606144871325e-05 tokens_per_second_per_gpu:966.9357570162487
Step 1398 | loss:1.4616057872772217 lr:6.0113549883829265e-05 tokens_per_second_per_gpu:931.4952860749565
Step 1399 | loss:1.2886193990707397 lr:6.00994852688138e-05 tokens_per_second_per_gpu:949.1590758312207
Step 1400 | loss:1.6729357242584229 lr:6.008541230450348e-05 tokens_per_second_per_gpu:780.0400058980412
Step 1401 | loss:1.377184271812439 lr:6.007133099557966e-05 tokens_per_second_per_gpu:911.8419724013595
Step 1402 | loss:1.4807157516479492 lr:6.0057241346726456e-05 tokens_per_second_per_gpu:893.0432495831459
Step 1403 | loss:1.352781891822815 lr:6.0043143362630755e-05 tokens_per_second_per_gpu:763.910135349602
Step 1404 | loss:1.5114794969558716 lr:6.002903704798224e-05 tokens_per_second_per_gpu:745.0546307731692
Step 1405 | loss:1.3335037231445312 lr:6.0014922407473345e-05 tokens_per_second_per_gpu:1147.9673544192303
Step 1406 | loss:1.4675359725952148 lr:6.000079944579927e-05 tokens_per_second_per_gpu:753.8903355798418
Step 1407 | loss:1.409470796585083 lr:5.9986668167657994e-05 tokens_per_second_per_gpu:890.7206753903668
Step 1408 | loss:1.561524748802185 lr:5.9972528577750256e-05 tokens_per_second_per_gpu:808.2700809365222
Step 1409 | loss:1.394248366355896 lr:5.9958380680779574e-05 tokens_per_second_per_gpu:775.4445561016668
Step 1410 | loss:1.5222735404968262 lr:5.9944224481452206e-05 tokens_per_second_per_gpu:959.3884973226292
Step 1411 | loss:1.455797791481018 lr:5.993005998447718e-05 tokens_per_second_per_gpu:940.5601116839192
Step 1412 | loss:1.5565321445465088 lr:5.991588719456632e-05 tokens_per_second_per_gpu:897.4265340141374
Step 1413 | loss:1.4157402515411377 lr:5.990170611643413e-05 tokens_per_second_per_gpu:1072.220430277452
Step 1414 | loss:1.3344346284866333 lr:5.988751675479796e-05 tokens_per_second_per_gpu:960.2801135533527
Step 1415 | loss:1.388691782951355 lr:5.987331911437784e-05 tokens_per_second_per_gpu:774.0173515656272
Step 1416 | loss:1.306591510772705 lr:5.985911319989662e-05 tokens_per_second_per_gpu:993.8654476382576
Step 1417 | loss:1.363319754600525 lr:5.984489901607984e-05 tokens_per_second_per_gpu:976.3435587901673
Step 1418 | loss:1.4474468231201172 lr:5.9830676567655824e-05 tokens_per_second_per_gpu:911.0503709262543
Step 1419 | loss:1.3271938562393188 lr:5.981644585935568e-05 tokens_per_second_per_gpu:924.294852612876
Step 1420 | loss:1.6639653444290161 lr:5.980220689591318e-05 tokens_per_second_per_gpu:819.9429771008112
Step 1421 | loss:1.3885053396224976 lr:5.97879596820649e-05 tokens_per_second_per_gpu:879.9115324873457
Step 1422 | loss:1.4291484355926514 lr:5.977370422255015e-05 tokens_per_second_per_gpu:980.9660210593916
Step 1423 | loss:1.40726900100708 lr:5.975944052211099e-05 tokens_per_second_per_gpu:1080.957261292251
Step 1424 | loss:1.4663878679275513 lr:5.974516858549221e-05 tokens_per_second_per_gpu:792.1911385062723
Step 1425 | loss:1.526298999786377 lr:5.973088841744133e-05 tokens_per_second_per_gpu:708.5008823019597
Step 1426 | loss:1.4910041093826294 lr:5.9716600022708625e-05 tokens_per_second_per_gpu:1053.9144806340855
Step 1427 | loss:1.4008678197860718 lr:5.9702303406047104e-05 tokens_per_second_per_gpu:849.9968866850576
Step 1428 | loss:1.3737224340438843 lr:5.968799857221251e-05 tokens_per_second_per_gpu:906.1124612328356
Step 1429 | loss:1.4742400646209717 lr:5.967368552596331e-05 tokens_per_second_per_gpu:932.1927201606289
Step 1430 | loss:1.4340962171554565 lr:5.965936427206072e-05 tokens_per_second_per_gpu:913.2457213463438
Step 1431 | loss:1.296404480934143 lr:5.9645034815268685e-05 tokens_per_second_per_gpu:734.404877010286
Step 1432 | loss:1.2684130668640137 lr:5.963069716035385e-05 tokens_per_second_per_gpu:1233.8361624773106
Step 1433 | loss:1.3920868635177612 lr:5.961635131208562e-05 tokens_per_second_per_gpu:944.1869906360625
Step 1434 | loss:1.4545526504516602 lr:5.9601997275236114e-05 tokens_per_second_per_gpu:1065.9974219887192
Step 1435 | loss:1.4069206714630127 lr:5.958763505458016e-05 tokens_per_second_per_gpu:758.7871265327956
Step 1436 | loss:1.457435131072998 lr:5.957326465489535e-05 tokens_per_second_per_gpu:625.057001402085
Step 1437 | loss:1.5675429105758667 lr:5.955888608096195e-05 tokens_per_second_per_gpu:697.9213098645301
Step 1438 | loss:1.4958049058914185 lr:5.954449933756296e-05 tokens_per_second_per_gpu:913.1507790730138
Step 1439 | loss:1.448143720626831 lr:5.953010442948412e-05 tokens_per_second_per_gpu:787.9392696275505
Step 1440 | loss:1.41524076461792 lr:5.951570136151386e-05 tokens_per_second_per_gpu:1046.041880315198
Step 1441 | loss:1.547141671180725 lr:5.950129013844331e-05 tokens_per_second_per_gpu:680.7893061646724
Step 1442 | loss:1.4612799882888794 lr:5.9486870765066375e-05 tokens_per_second_per_gpu:1017.7504571435564
Step 1443 | loss:1.5747205018997192 lr:5.947244324617962e-05 tokens_per_second_per_gpu:783.3392723626372
Step 1444 | loss:1.3055357933044434 lr:5.9458007586582315e-05 tokens_per_second_per_gpu:838.9171016069281
Step 1445 | loss:1.3296115398406982 lr:5.944356379107647e-05 tokens_per_second_per_gpu:1113.776273022156
Step 1446 | loss:1.4984468221664429 lr:5.942911186446676e-05 tokens_per_second_per_gpu:854.9008473787134
Step 1447 | loss:1.427472710609436 lr:5.941465181156063e-05 tokens_per_second_per_gpu:1015.4664419711494
Step 1448 | loss:1.4452402591705322 lr:5.9400183637168155e-05 tokens_per_second_per_gpu:1315.3274603653708
Step 1449 | loss:1.406059741973877 lr:5.938570734610216e-05 tokens_per_second_per_gpu:936.6597006459982
Step 1450 | loss:1.5921449661254883 lr:5.937122294317816e-05 tokens_per_second_per_gpu:750.8849707193893
Step 1451 | loss:1.2999659776687622 lr:5.9356730433214346e-05 tokens_per_second_per_gpu:973.7253845079554
Step 1452 | loss:1.3984586000442505 lr:5.934222982103164e-05 tokens_per_second_per_gpu:952.707728215968
Step 1453 | loss:1.363885521888733 lr:5.932772111145363e-05 tokens_per_second_per_gpu:852.3476680568073
Step 1454 | loss:1.5133318901062012 lr:5.931320430930661e-05 tokens_per_second_per_gpu:951.8828575365256
Step 1455 | loss:1.3227869272232056 lr:5.9298679419419576e-05 tokens_per_second_per_gpu:1034.706646897495
Step 1456 | loss:1.5055203437805176 lr:5.9284146446624206e-05 tokens_per_second_per_gpu:827.3263987706133
Step 1457 | loss:1.5235896110534668 lr:5.926960539575485e-05 tokens_per_second_per_gpu:798.5293062115596
Step 1458 | loss:1.4200676679611206 lr:5.925505627164857e-05 tokens_per_second_per_gpu:1004.5852206618117
Step 1459 | loss:1.4804893732070923 lr:5.9240499079145106e-05 tokens_per_second_per_gpu:896.0331931719667
Step 1460 | loss:1.480490803718567 lr:5.922593382308687e-05 tokens_per_second_per_gpu:870.7082641088977
Step 1461 | loss:1.3874082565307617 lr:5.921136050831897e-05 tokens_per_second_per_gpu:831.7694171956864
Step 1462 | loss:1.439263939857483 lr:5.919677913968921e-05 tokens_per_second_per_gpu:806.5363481965421
Step 1463 | loss:1.4839742183685303 lr:5.9182189722048025e-05 tokens_per_second_per_gpu:804.3504357741613
Step 1464 | loss:1.499041199684143 lr:5.9167592260248566e-05 tokens_per_second_per_gpu:947.4208777117725
Step 1465 | loss:1.4808787107467651 lr:5.915298675914665e-05 tokens_per_second_per_gpu:825.7163429222525
Step 1466 | loss:1.426181674003601 lr:5.9138373223600776e-05 tokens_per_second_per_gpu:1086.242634536622
Step 1467 | loss:1.5885777473449707 lr:5.912375165847211e-05 tokens_per_second_per_gpu:648.8431285861348
Step 1468 | loss:1.4836924076080322 lr:5.910912206862447e-05 tokens_per_second_per_gpu:811.9638000094178
Step 1469 | loss:1.4534896612167358 lr:5.909448445892437e-05 tokens_per_second_per_gpu:887.2982725287014
Step 1470 | loss:1.4058706760406494 lr:5.9079838834240995e-05 tokens_per_second_per_gpu:963.5130111515774
Step 1471 | loss:1.3780450820922852 lr:5.906518519944616e-05 tokens_per_second_per_gpu:874.5951369278279
Step 1472 | loss:1.3201154470443726 lr:5.9050523559414375e-05 tokens_per_second_per_gpu:1100.0176693266494
Step 1473 | loss:1.28048574924469 lr:5.903585391902282e-05 tokens_per_second_per_gpu:843.340679357149
Step 1474 | loss:1.2605289220809937 lr:5.9021176283151314e-05 tokens_per_second_per_gpu:901.6327344712122
Step 1475 | loss:1.3324860334396362 lr:5.900649065668233e-05 tokens_per_second_per_gpu:951.0578818790667
Step 1476 | loss:1.4288228750228882 lr:5.8991797044501036e-05 tokens_per_second_per_gpu:952.8098019665953
Step 1477 | loss:1.4566469192504883 lr:5.897709545149523e-05 tokens_per_second_per_gpu:782.2527903044523
Step 1478 | loss:1.2678844928741455 lr:5.896238588255535e-05 tokens_per_second_per_gpu:756.0168223412135
Step 1479 | loss:1.3955497741699219 lr:5.894766834257452e-05 tokens_per_second_per_gpu:1292.405254812572
Step 1480 | loss:1.5255160331726074 lr:5.89329428364485e-05 tokens_per_second_per_gpu:869.6020824126745
Step 1481 | loss:1.4161676168441772 lr:5.891820936907569e-05 tokens_per_second_per_gpu:955.7344956251092
Step 1482 | loss:1.3938689231872559 lr:5.890346794535717e-05 tokens_per_second_per_gpu:920.8596137245496
Step 1483 | loss:1.452214241027832 lr:5.888871857019663e-05 tokens_per_second_per_gpu:906.6389772571175
Step 1484 | loss:1.3700653314590454 lr:5.8873961248500424e-05 tokens_per_second_per_gpu:899.1586538252798
Step 1485 | loss:1.5025347471237183 lr:5.885919598517754e-05 tokens_per_second_per_gpu:1000.4639371107461
Step 1486 | loss:1.2521392107009888 lr:5.8844422785139635e-05 tokens_per_second_per_gpu:937.8770980639217
Step 1487 | loss:1.270290493965149 lr:5.882964165330096e-05 tokens_per_second_per_gpu:951.7823262962594
Step 1488 | loss:1.3995161056518555 lr:5.8814852594578444e-05 tokens_per_second_per_gpu:1045.7157870436847
Step 1489 | loss:1.5152531862258911 lr:5.880005561389164e-05 tokens_per_second_per_gpu:670.0447180885587
Step 1490 | loss:1.3824241161346436 lr:5.878525071616272e-05 tokens_per_second_per_gpu:1227.4957157588892
Step 1491 | loss:1.582403302192688 lr:5.877043790631652e-05 tokens_per_second_per_gpu:898.6828132322731
Step 1492 | loss:1.6208044290542603 lr:5.875561718928049e-05 tokens_per_second_per_gpu:774.0746250910424
Step 1493 | loss:1.322887659072876 lr:5.874078856998471e-05 tokens_per_second_per_gpu:801.7529508690043
Step 1494 | loss:1.3968186378479004 lr:5.8725952053361885e-05 tokens_per_second_per_gpu:945.336927377461
Step 1495 | loss:1.448630928993225 lr:5.871110764434736e-05 tokens_per_second_per_gpu:892.9633490981621
Step 1496 | loss:1.5048266649246216 lr:5.869625534787911e-05 tokens_per_second_per_gpu:783.6079809807676
Step 1497 | loss:1.4090144634246826 lr:5.868139516889769e-05 tokens_per_second_per_gpu:935.0313751177655
Step 1498 | loss:1.3732308149337769 lr:5.866652711234635e-05 tokens_per_second_per_gpu:1040.7208262096592
Step 1499 | loss:1.4764227867126465 lr:5.865165118317088e-05 tokens_per_second_per_gpu:844.7887072057628
Step 1500 | loss:1.563621997833252 lr:5.863676738631977e-05 tokens_per_second_per_gpu:974.8884037411214
Step 1501 | loss:1.450761079788208 lr:5.862187572674405e-05 tokens_per_second_per_gpu:879.009271913732
Step 1502 | loss:1.445273995399475 lr:5.860697620939743e-05 tokens_per_second_per_gpu:830.0682066369652
Step 1503 | loss:1.4310604333877563 lr:5.859206883923618e-05 tokens_per_second_per_gpu:860.7811144144214
Step 1504 | loss:1.4119917154312134 lr:5.857715362121921e-05 tokens_per_second_per_gpu:716.2041787076047
Step 1505 | loss:1.2263095378875732 lr:5.856223056030807e-05 tokens_per_second_per_gpu:841.6479632078742
Step 1506 | loss:1.3831443786621094 lr:5.854729966146686e-05 tokens_per_second_per_gpu:1153.182635935413
Step 1507 | loss:1.4326655864715576 lr:5.853236092966231e-05 tokens_per_second_per_gpu:964.8470104719222
Step 1508 | loss:1.5162734985351562 lr:5.8517414369863775e-05 tokens_per_second_per_gpu:773.171403240706
Step 1509 | loss:1.358790397644043 lr:5.850245998704319e-05 tokens_per_second_per_gpu:997.6939035581514
Step 1510 | loss:1.5151677131652832 lr:5.8487497786175104e-05 tokens_per_second_per_gpu:923.066981080346
Step 1511 | loss:1.4576280117034912 lr:5.8472527772236665e-05 tokens_per_second_per_gpu:698.9756161911396
Step 1512 | loss:1.4240940809249878 lr:5.845754995020762e-05 tokens_per_second_per_gpu:780.0535902222468
Step 1513 | loss:1.4324190616607666 lr:5.844256432507031e-05 tokens_per_second_per_gpu:772.059891355623
Step 1514 | loss:1.5190300941467285 lr:5.8427570901809674e-05 tokens_per_second_per_gpu:741.385446634768
Step 1515 | loss:1.4145811796188354 lr:5.841256968541325e-05 tokens_per_second_per_gpu:853.9380436657393
Step 1516 | loss:1.3318188190460205 lr:5.839756068087116e-05 tokens_per_second_per_gpu:1003.6716021067734
Step 1517 | loss:1.234721302986145 lr:5.8382543893176114e-05 tokens_per_second_per_gpu:877.9627305172812
Step 1518 | loss:1.2099475860595703 lr:5.8367519327323426e-05 tokens_per_second_per_gpu:1041.686184283248
Step 1519 | loss:1.4035636186599731 lr:5.835248698831098e-05 tokens_per_second_per_gpu:878.3239957244828
Step 1520 | loss:1.2448320388793945 lr:5.833744688113926e-05 tokens_per_second_per_gpu:1033.7152960054095
Step 1521 | loss:1.278461217880249 lr:5.8322399010811325e-05 tokens_per_second_per_gpu:1190.5393969962686
Step 1522 | loss:1.4042131900787354 lr:5.8307343382332825e-05 tokens_per_second_per_gpu:1120.5635305523267
Step 1523 | loss:1.5297155380249023 lr:5.829228000071198e-05 tokens_per_second_per_gpu:918.6254225289739
Step 1524 | loss:1.3718684911727905 lr:5.827720887095961e-05 tokens_per_second_per_gpu:925.4647510118511
Step 1525 | loss:1.456272840499878 lr:5.826212999808907e-05 tokens_per_second_per_gpu:1059.9897070239838
Step 1526 | loss:1.3840006589889526 lr:5.8247043387116335e-05 tokens_per_second_per_gpu:696.5007305032618
Step 1527 | loss:1.5150305032730103 lr:5.823194904305994e-05 tokens_per_second_per_gpu:898.6641601218952
Step 1528 | loss:1.4603241682052612 lr:5.821684697094097e-05 tokens_per_second_per_gpu:686.4354038621767
Step 1529 | loss:1.5387191772460938 lr:5.820173717578312e-05 tokens_per_second_per_gpu:903.7013346404356
Step 1530 | loss:1.443665623664856 lr:5.8186619662612626e-05 tokens_per_second_per_gpu:935.9062432620404
Step 1531 | loss:1.5137782096862793 lr:5.8171494436458304e-05 tokens_per_second_per_gpu:742.121820229676
Step 1532 | loss:1.428931474685669 lr:5.815636150235152e-05 tokens_per_second_per_gpu:846.8242924696592
Step 1533 | loss:1.6545780897140503 lr:5.814122086532623e-05 tokens_per_second_per_gpu:673.6241849769156
Step 1534 | loss:1.4607362747192383 lr:5.812607253041892e-05 tokens_per_second_per_gpu:796.8877070689335
Step 1535 | loss:1.4274026155471802 lr:5.811091650266867e-05 tokens_per_second_per_gpu:785.807444460844
Step 1536 | loss:1.4617654085159302 lr:5.8095752787117085e-05 tokens_per_second_per_gpu:885.9602845184055
Step 1537 | loss:1.370411992073059 lr:5.808058138880837e-05 tokens_per_second_per_gpu:881.4877661236852
Step 1538 | loss:1.222970724105835 lr:5.8065402312789244e-05 tokens_per_second_per_gpu:981.99237579327
Step 1539 | loss:1.40192449092865 lr:5.8050215564109004e-05 tokens_per_second_per_gpu:934.1387799635846
Step 1540 | loss:1.3238617181777954 lr:5.8035021147819474e-05 tokens_per_second_per_gpu:1101.0637995772029
Step 1541 | loss:1.3299460411071777 lr:5.8019819068975074e-05 tokens_per_second_per_gpu:1018.4723300008934
Step 1542 | loss:1.3980562686920166 lr:5.8004609332632733e-05 tokens_per_second_per_gpu:1243.1525098556092
Step 1543 | loss:1.429001808166504 lr:5.798939194385194e-05 tokens_per_second_per_gpu:1191.4675138580485
Step 1544 | loss:1.2722009420394897 lr:5.797416690769474e-05 tokens_per_second_per_gpu:827.598735635264
Step 1545 | loss:1.2679550647735596 lr:5.7958934229225694e-05 tokens_per_second_per_gpu:914.1226291830789
Step 1546 | loss:1.3522350788116455 lr:5.794369391351193e-05 tokens_per_second_per_gpu:972.560761803645
Step 1547 | loss:1.4073126316070557 lr:5.7928445965623105e-05 tokens_per_second_per_gpu:927.7528705299618
Step 1548 | loss:1.2827268838882446 lr:5.7913190390631435e-05 tokens_per_second_per_gpu:1044.3211135339288
Step 1549 | loss:1.3758560419082642 lr:5.789792719361165e-05 tokens_per_second_per_gpu:1112.0223930599234
Step 1550 | loss:1.4913885593414307 lr:5.7882656379641014e-05 tokens_per_second_per_gpu:734.5977803327022
Step 1551 | loss:1.389591932296753 lr:5.7867377953799334e-05 tokens_per_second_per_gpu:977.2244417620734
Step 1552 | loss:1.6261131763458252 lr:5.7852091921168954e-05 tokens_per_second_per_gpu:879.5580766844122
Step 1553 | loss:1.2848340272903442 lr:5.783679828683475e-05 tokens_per_second_per_gpu:1001.6256368582099
Step 1554 | loss:1.4505031108856201 lr:5.782149705588411e-05 tokens_per_second_per_gpu:799.8017654958395
Step 1555 | loss:1.6096142530441284 lr:5.780618823340696e-05 tokens_per_second_per_gpu:707.2452812191956
Step 1556 | loss:1.4515275955200195 lr:5.7790871824495755e-05 tokens_per_second_per_gpu:926.7056225611782
Step 1557 | loss:1.5673125982284546 lr:5.777554783424546e-05 tokens_per_second_per_gpu:615.449021523321
Step 1558 | loss:1.286451816558838 lr:5.776021626775357e-05 tokens_per_second_per_gpu:853.6346996180703
Step 1559 | loss:1.4854342937469482 lr:5.774487713012011e-05 tokens_per_second_per_gpu:1074.4225952117954
Step 1560 | loss:1.4105024337768555 lr:5.772953042644762e-05 tokens_per_second_per_gpu:827.0146489057868
Step 1561 | loss:1.490788221359253 lr:5.771417616184113e-05 tokens_per_second_per_gpu:835.8282265313874
Step 1562 | loss:1.4466924667358398 lr:5.7698814341408226e-05 tokens_per_second_per_gpu:721.4901470326706
Step 1563 | loss:1.37688410282135 lr:5.768344497025897e-05 tokens_per_second_per_gpu:807.8363282976317
Step 1564 | loss:1.449254035949707 lr:5.766806805350597e-05 tokens_per_second_per_gpu:723.051475517657
Step 1565 | loss:1.4776391983032227 lr:5.76526835962643e-05 tokens_per_second_per_gpu:728.6342734317947
Step 1566 | loss:1.4117337465286255 lr:5.763729160365161e-05 tokens_per_second_per_gpu:1001.4727699048091
Step 1567 | loss:1.5602227449417114 lr:5.7621892080788e-05 tokens_per_second_per_gpu:909.3999151002549
Step 1568 | loss:1.3230822086334229 lr:5.7606485032796076e-05 tokens_per_second_per_gpu:1034.6232288886617
Step 1569 | loss:1.3336228132247925 lr:5.759107046480098e-05 tokens_per_second_per_gpu:1367.0993649579357
Step 1570 | loss:1.4620189666748047 lr:5.757564838193032e-05 tokens_per_second_per_gpu:879.3332167353002
Step 1571 | loss:1.5247325897216797 lr:5.756021878931424e-05 tokens_per_second_per_gpu:904.6849641366658
Step 1572 | loss:1.479511022567749 lr:5.754478169208535e-05 tokens_per_second_per_gpu:668.557804595063
Step 1573 | loss:1.5780341625213623 lr:5.7529337095378796e-05 tokens_per_second_per_gpu:629.5102731663213
Step 1574 | loss:1.4697095155715942 lr:5.751388500433215e-05 tokens_per_second_per_gpu:988.3251455947403
Step 1575 | loss:1.575810194015503 lr:5.7498425424085565e-05 tokens_per_second_per_gpu:738.0048749748869
Step 1576 | loss:1.3930118083953857 lr:5.7482958359781605e-05 tokens_per_second_per_gpu:889.7432411069016
Step 1577 | loss:1.5280795097351074 lr:5.746748381656538e-05 tokens_per_second_per_gpu:736.2676483156058
Step 1578 | loss:1.3587875366210938 lr:5.745200179958446e-05 tokens_per_second_per_gpu:843.9733351234618
Step 1579 | loss:1.392958641052246 lr:5.7436512313988904e-05 tokens_per_second_per_gpu:894.4704732630137
Step 1580 | loss:1.3821769952774048 lr:5.7421015364931276e-05 tokens_per_second_per_gpu:914.2721308399897
Step 1581 | loss:1.364353060722351 lr:5.7405510957566585e-05 tokens_per_second_per_gpu:1069.5209625135578
Step 1582 | loss:1.3543009757995605 lr:5.7389999097052346e-05 tokens_per_second_per_gpu:950.8245084445217
Step 1583 | loss:1.3524583578109741 lr:5.7374479788548555e-05 tokens_per_second_per_gpu:779.9253846853916
Step 1584 | loss:1.4660385847091675 lr:5.7358953037217675e-05 tokens_per_second_per_gpu:811.7686279766784
Step 1585 | loss:1.5569441318511963 lr:5.7343418848224655e-05 tokens_per_second_per_gpu:834.7046340610999
Step 1586 | loss:1.4792479276657104 lr:5.732787722673691e-05 tokens_per_second_per_gpu:1025.1496803713892
Step 1587 | loss:1.5058627128601074 lr:5.7312328177924326e-05 tokens_per_second_per_gpu:778.939927158419
Step 1588 | loss:1.435755729675293 lr:5.7296771706959275e-05 tokens_per_second_per_gpu:784.4682515178037
Step 1589 | loss:1.2355012893676758 lr:5.7281207819016576e-05 tokens_per_second_per_gpu:977.3616439369183
Step 1590 | loss:1.3878235816955566 lr:5.726563651927353e-05 tokens_per_second_per_gpu:901.7637686152725
Step 1591 | loss:1.3962421417236328 lr:5.7250057812909905e-05 tokens_per_second_per_gpu:930.9836131078225
Step 1592 | loss:1.4071073532104492 lr:5.723447170510792e-05 tokens_per_second_per_gpu:933.7440697807867
Step 1593 | loss:1.5634102821350098 lr:5.721887820105226e-05 tokens_per_second_per_gpu:679.4785116368931
Step 1594 | loss:1.3409010171890259 lr:5.720327730593008e-05 tokens_per_second_per_gpu:799.022372271828
Step 1595 | loss:1.5002692937850952 lr:5.718766902493096e-05 tokens_per_second_per_gpu:704.9887000708715
Step 1596 | loss:1.4194120168685913 lr:5.717205336324702e-05 tokens_per_second_per_gpu:584.101998336841
Step 1597 | loss:1.392259120941162 lr:5.715643032607275e-05 tokens_per_second_per_gpu:904.9316608145604
Step 1598 | loss:1.489917516708374 lr:5.7140799918605114e-05 tokens_per_second_per_gpu:831.0012909392966
Step 1599 | loss:1.1916601657867432 lr:5.712516214604355e-05 tokens_per_second_per_gpu:1342.5569419229757
Step 1600 | loss:1.3304775953292847 lr:5.7109517013589924e-05 tokens_per_second_per_gpu:1025.9803701252579
Step 1601 | loss:1.4788358211517334 lr:5.709386452644857e-05 tokens_per_second_per_gpu:1118.693001934213
Step 1602 | loss:1.2758406400680542 lr:5.707820468982624e-05 tokens_per_second_per_gpu:1036.776229037778
Step 1603 | loss:1.3691245317459106 lr:5.706253750893215e-05 tokens_per_second_per_gpu:932.5301373273765
Step 1604 | loss:1.5241649150848389 lr:5.704686298897798e-05 tokens_per_second_per_gpu:636.4899750874164
Step 1605 | loss:1.4773257970809937 lr:5.703118113517781e-05 tokens_per_second_per_gpu:752.2969818091684
Step 1606 | loss:1.4541579484939575 lr:5.701549195274818e-05 tokens_per_second_per_gpu:638.9933558597369
Step 1607 | loss:1.4501838684082031 lr:5.699979544690806e-05 tokens_per_second_per_gpu:774.3711888733106
Step 1608 | loss:1.2879873514175415 lr:5.6984091622878875e-05 tokens_per_second_per_gpu:1078.9459010442224
Step 1609 | loss:1.3554480075836182 lr:5.696838048588448e-05 tokens_per_second_per_gpu:964.9847105091867
Step 1610 | loss:1.3331947326660156 lr:5.695266204115112e-05 tokens_per_second_per_gpu:934.4339267092537
Step 1611 | loss:1.4584710597991943 lr:5.693693629390753e-05 tokens_per_second_per_gpu:731.0345148328656
Step 1612 | loss:1.400428295135498 lr:5.692120324938485e-05 tokens_per_second_per_gpu:981.0504436381898
Step 1613 | loss:1.4059784412384033 lr:5.690546291281664e-05 tokens_per_second_per_gpu:822.1222742524299
Step 1614 | loss:1.6707475185394287 lr:5.688971528943888e-05 tokens_per_second_per_gpu:835.6297911406957
Step 1615 | loss:1.3494277000427246 lr:5.6873960384490015e-05 tokens_per_second_per_gpu:991.9944233121698
Step 1616 | loss:1.4551010131835938 lr:5.6858198203210866e-05 tokens_per_second_per_gpu:893.8141677748173
Step 1617 | loss:1.4169542789459229 lr:5.684242875084469e-05 tokens_per_second_per_gpu:1102.6859820673271
Step 1618 | loss:1.3892602920532227 lr:5.682665203263717e-05 tokens_per_second_per_gpu:780.9601410476702
Step 1619 | loss:1.2138704061508179 lr:5.681086805383639e-05 tokens_per_second_per_gpu:813.2649908132357
Step 1620 | loss:1.2608327865600586 lr:5.6795076819692874e-05 tokens_per_second_per_gpu:957.5068625660382
Step 1621 | loss:1.3707211017608643 lr:5.677927833545955e-05 tokens_per_second_per_gpu:1059.2177624436151
Step 1622 | loss:1.5286632776260376 lr:5.676347260639174e-05 tokens_per_second_per_gpu:833.1626602884555
Step 1623 | loss:1.5370781421661377 lr:5.674765963774718e-05 tokens_per_second_per_gpu:885.3911490836595
Step 1624 | loss:1.3676226139068604 lr:5.673183943478604e-05 tokens_per_second_per_gpu:858.5937414813418
Step 1625 | loss:1.4159858226776123 lr:5.6716012002770885e-05 tokens_per_second_per_gpu:672.7117381231936
Step 1626 | loss:1.5215502977371216 lr:5.670017734696665e-05 tokens_per_second_per_gpu:910.4223373057807
Step 1627 | loss:1.4663162231445312 lr:5.668433547264074e-05 tokens_per_second_per_gpu:735.5556361086494
Step 1628 | loss:1.4935513734817505 lr:5.666848638506289e-05 tokens_per_second_per_gpu:836.9333119264542
Step 1629 | loss:1.4021157026290894 lr:5.665263008950529e-05 tokens_per_second_per_gpu:1000.7676450430473
Step 1630 | loss:1.474610447883606 lr:5.6636766591242495e-05 tokens_per_second_per_gpu:742.13511940786
Step 1631 | loss:1.4852045774459839 lr:5.6620895895551474e-05 tokens_per_second_per_gpu:708.1989218019783
Step 1632 | loss:1.267444372177124 lr:5.6605018007711585e-05 tokens_per_second_per_gpu:863.9840646586357
Step 1633 | loss:1.4628859758377075 lr:5.658913293300456e-05 tokens_per_second_per_gpu:707.9675473842119
Step 1634 | loss:1.353447437286377 lr:5.6573240676714556e-05 tokens_per_second_per_gpu:864.4521433877841
Step 1635 | loss:1.5835785865783691 lr:5.6557341244128096e-05 tokens_per_second_per_gpu:666.7219123760631
Step 1636 | loss:1.4309638738632202 lr:5.6541434640534094e-05 tokens_per_second_per_gpu:791.3814446954846
Step 1637 | loss:1.5083551406860352 lr:5.652552087122385e-05 tokens_per_second_per_gpu:905.2971367523169
Step 1638 | loss:1.4888689517974854 lr:5.650959994149104e-05 tokens_per_second_per_gpu:771.2687779666336
Step 1639 | loss:1.4168133735656738 lr:5.6493671856631746e-05 tokens_per_second_per_gpu:797.3957158828541
Step 1640 | loss:1.340787649154663 lr:5.6477736621944406e-05 tokens_per_second_per_gpu:1124.5908457610533
Step 1641 | loss:1.3606537580490112 lr:5.6461794242729846e-05 tokens_per_second_per_gpu:959.7258738948665
Step 1642 | loss:1.3987491130828857 lr:5.644584472429127e-05 tokens_per_second_per_gpu:1481.5161840029623
Step 1643 | loss:1.308530569076538 lr:5.6429888071934246e-05 tokens_per_second_per_gpu:1058.5084800677487
Step 1644 | loss:1.4579226970672607 lr:5.641392429096673e-05 tokens_per_second_per_gpu:868.4080385931503
Step 1645 | loss:1.4786016941070557 lr:5.6397953386699044e-05 tokens_per_second_per_gpu:897.9648834095315
Step 1646 | loss:1.2679105997085571 lr:5.6381975364443876e-05 tokens_per_second_per_gpu:855.1982957509124
Step 1647 | loss:1.3385751247406006 lr:5.6365990229516284e-05 tokens_per_second_per_gpu:734.2738807522426
Step 1648 | loss:1.3627147674560547 lr:5.6349997987233684e-05 tokens_per_second_per_gpu:766.1002074679396
Step 1649 | loss:1.434517741203308 lr:5.633399864291588e-05 tokens_per_second_per_gpu:866.0534593872367
Step 1650 | loss:1.2889394760131836 lr:5.631799220188502e-05 tokens_per_second_per_gpu:1240.2091672685935
Step 1651 | loss:1.2776267528533936 lr:5.6301978669465585e-05 tokens_per_second_per_gpu:952.1137722758785
Step 1652 | loss:1.35426926612854 lr:5.62859580509845e-05 tokens_per_second_per_gpu:808.4440984780321
Step 1653 | loss:1.4991651773452759 lr:5.626993035177095e-05 tokens_per_second_per_gpu:1155.8338935172796
Step 1654 | loss:1.5515191555023193 lr:5.6253895577156534e-05 tokens_per_second_per_gpu:717.5360702484058
Step 1655 | loss:1.379571795463562 lr:5.623785373247519e-05 tokens_per_second_per_gpu:984.2828084717697
Step 1656 | loss:1.3884570598602295 lr:5.622180482306319e-05 tokens_per_second_per_gpu:828.4398299268469
Step 1657 | loss:1.4672430753707886 lr:5.620574885425918e-05 tokens_per_second_per_gpu:957.3689604437832
Step 1658 | loss:1.3406202793121338 lr:5.618968583140416e-05 tokens_per_second_per_gpu:889.4854721748761
Step 1659 | loss:1.326295018196106 lr:5.617361575984145e-05 tokens_per_second_per_gpu:998.4339566188736
Step 1660 | loss:1.346923828125 lr:5.615753864491674e-05 tokens_per_second_per_gpu:942.9704918081873
Step 1661 | loss:1.5534582138061523 lr:5.614145449197804e-05 tokens_per_second_per_gpu:1145.3874200081723
Step 1662 | loss:1.3954083919525146 lr:5.612536330637571e-05 tokens_per_second_per_gpu:793.0662765364442
Step 1663 | loss:1.5385409593582153 lr:5.6109265093462455e-05 tokens_per_second_per_gpu:796.4034070394765
Step 1664 | loss:1.4412733316421509 lr:5.609315985859332e-05 tokens_per_second_per_gpu:676.1027287027803
Step 1665 | loss:1.4637091159820557 lr:5.607704760712568e-05 tokens_per_second_per_gpu:887.6364030199259
Step 1666 | loss:1.3780561685562134 lr:5.6060928344419236e-05 tokens_per_second_per_gpu:861.8482647163141
Step 1667 | loss:1.5372940301895142 lr:5.6044802075836027e-05 tokens_per_second_per_gpu:763.7113394575341
Step 1668 | loss:1.4536125659942627 lr:5.602866880674043e-05 tokens_per_second_per_gpu:1052.2498868600383
Step 1669 | loss:1.4005851745605469 lr:5.6012528542499154e-05 tokens_per_second_per_gpu:938.9336160873034
Step 1670 | loss:1.4252294301986694 lr:5.599638128848122e-05 tokens_per_second_per_gpu:727.9647791686631
Step 1671 | loss:1.270036220550537 lr:5.598022705005798e-05 tokens_per_second_per_gpu:955.4477499021282
Step 1672 | loss:1.4518170356750488 lr:5.59640658326031e-05 tokens_per_second_per_gpu:935.4085609452682
Step 1673 | loss:1.3773821592330933 lr:5.594789764149259e-05 tokens_per_second_per_gpu:1190.7081649957847
Step 1674 | loss:1.3694117069244385 lr:5.593172248210477e-05 tokens_per_second_per_gpu:768.4744899142867
Step 1675 | loss:1.3639436960220337 lr:5.5915540359820266e-05 tokens_per_second_per_gpu:911.706669520541
Step 1676 | loss:1.4644792079925537 lr:5.5899351280022026e-05 tokens_per_second_per_gpu:888.90446745712
Step 1677 | loss:1.5063676834106445 lr:5.588315524809533e-05 tokens_per_second_per_gpu:1112.2197926971664
Step 1678 | loss:1.5498197078704834 lr:5.5866952269427744e-05 tokens_per_second_per_gpu:750.2146403712999
Step 1679 | loss:1.4607456922531128 lr:5.5850742349409173e-05 tokens_per_second_per_gpu:808.3371439466655
Step 1680 | loss:1.3357932567596436 lr:5.583452549343179e-05 tokens_per_second_per_gpu:796.4713744612852
Step 1681 | loss:1.4387892484664917 lr:5.581830170689013e-05 tokens_per_second_per_gpu:962.1237633086637
Step 1682 | loss:1.3173813819885254 lr:5.580207099518097e-05 tokens_per_second_per_gpu:898.2190255152458
Step 1683 | loss:1.492919921875 lr:5.578583336370346e-05 tokens_per_second_per_gpu:851.1194244200603
Step 1684 | loss:1.4988538026809692 lr:5.5769588817858994e-05 tokens_per_second_per_gpu:871.9532021140164
Step 1685 | loss:1.4487141370773315 lr:5.57533373630513e-05 tokens_per_second_per_gpu:795.1672649551917
Step 1686 | loss:1.436078667640686 lr:5.5737079004686384e-05 tokens_per_second_per_gpu:796.3055112933348
Step 1687 | loss:1.4502737522125244 lr:5.572081374817256e-05 tokens_per_second_per_gpu:842.6875841015263
Step 1688 | loss:1.4526441097259521 lr:5.570454159892043e-05 tokens_per_second_per_gpu:658.0177398651714
Step 1689 | loss:1.1830987930297852 lr:5.56882625623429e-05 tokens_per_second_per_gpu:1334.1350644894944
Step 1690 | loss:1.325423002243042 lr:5.567197664385516e-05 tokens_per_second_per_gpu:1027.6499027121383
Step 1691 | loss:1.3909213542938232 lr:5.5655683848874685e-05 tokens_per_second_per_gpu:896.2978831155642
Step 1692 | loss:1.4266647100448608 lr:5.563938418282123e-05 tokens_per_second_per_gpu:1143.5801115046556
Step 1693 | loss:1.3995702266693115 lr:5.5623077651116886e-05 tokens_per_second_per_gpu:667.7835028641443
Step 1694 | loss:1.333911657333374 lr:5.560676425918594e-05 tokens_per_second_per_gpu:754.9379536422344
Step 1695 | loss:1.3966102600097656 lr:5.559044401245504e-05 tokens_per_second_per_gpu:708.5496060896219
Step 1696 | loss:1.388167142868042 lr:5.557411691635308e-05 tokens_per_second_per_gpu:1079.0721210562792
Step 1697 | loss:1.6208311319351196 lr:5.555778297631124e-05 tokens_per_second_per_gpu:907.278171721771
Step 1698 | loss:1.4869974851608276 lr:5.554144219776295e-05 tokens_per_second_per_gpu:573.0546380255194
Step 1699 | loss:1.345929741859436 lr:5.552509458614397e-05 tokens_per_second_per_gpu:711.660863113995
Step 1700 | loss:1.5421311855316162 lr:5.5508740146892266e-05 tokens_per_second_per_gpu:872.5444119225988
Step 1701 | loss:1.2304271459579468 lr:5.5492378885448145e-05 tokens_per_second_per_gpu:1015.6580812061582
Step 1702 | loss:1.4036836624145508 lr:5.5476010807254135e-05 tokens_per_second_per_gpu:1028.2523633377864
Step 1703 | loss:1.5340309143066406 lr:5.5459635917755044e-05 tokens_per_second_per_gpu:1095.2520758440867
Step 1704 | loss:1.5715843439102173 lr:5.5443254222397945e-05 tokens_per_second_per_gpu:743.8258435616345
Step 1705 | loss:1.3550801277160645 lr:5.542686572663218e-05 tokens_per_second_per_gpu:889.0698208977343
Step 1706 | loss:1.3788834810256958 lr:5.541047043590935e-05 tokens_per_second_per_gpu:896.1083929342694
Step 1707 | loss:1.2886466979980469 lr:5.5394068355683315e-05 tokens_per_second_per_gpu:1143.1943682394124
Step 1708 | loss:1.507263422012329 lr:5.53776594914102e-05 tokens_per_second_per_gpu:798.2360687183465
Step 1709 | loss:1.076938271522522 lr:5.5361243848548376e-05 tokens_per_second_per_gpu:1035.5526596507245
Step 1710 | loss:1.4962248802185059 lr:5.534482143255848e-05 tokens_per_second_per_gpu:694.0056907005634
Step 1711 | loss:1.5338175296783447 lr:5.5328392248903385e-05 tokens_per_second_per_gpu:833.2365641496698
Step 1712 | loss:1.394320011138916 lr:5.5311956303048244e-05 tokens_per_second_per_gpu:745.8421068331747
Step 1713 | loss:1.567391276359558 lr:5.5295513600460425e-05 tokens_per_second_per_gpu:841.188308876905
Step 1714 | loss:1.4637540578842163 lr:5.527906414660958e-05 tokens_per_second_per_gpu:660.6812355623547
Step 1715 | loss:1.4095585346221924 lr:5.526260794696757e-05 tokens_per_second_per_gpu:798.6405428474314
Step 1716 | loss:1.547742486000061 lr:5.524614500700852e-05 tokens_per_second_per_gpu:843.9273740133164
Step 1717 | loss:1.3365108966827393 lr:5.522967533220881e-05 tokens_per_second_per_gpu:938.4000284150711
Step 1718 | loss:1.354875087738037 lr:5.521319892804703e-05 tokens_per_second_per_gpu:945.3970804414331
Step 1719 | loss:1.370577335357666 lr:5.519671580000403e-05 tokens_per_second_per_gpu:752.1568002084315
Step 1720 | loss:1.4192683696746826 lr:5.5180225953562884e-05 tokens_per_second_per_gpu:605.30850252425
Step 1721 | loss:1.502592921257019 lr:5.516372939420893e-05 tokens_per_second_per_gpu:1072.8377794217083
Step 1722 | loss:1.3040730953216553 lr:5.514722612742968e-05 tokens_per_second_per_gpu:918.4462448651934
Step 1723 | loss:1.3051586151123047 lr:5.513071615871494e-05 tokens_per_second_per_gpu:1174.8003901876855
Step 1724 | loss:1.4463167190551758 lr:5.511419949355672e-05 tokens_per_second_per_gpu:902.6599182151276
Step 1725 | loss:1.2688844203948975 lr:5.5097676137449236e-05 tokens_per_second_per_gpu:1153.9843682819574
Step 1726 | loss:1.3292518854141235 lr:5.508114609588896e-05 tokens_per_second_per_gpu:800.4865287206695
Step 1727 | loss:1.4876673221588135 lr:5.506460937437458e-05 tokens_per_second_per_gpu:874.5308377150196
Step 1728 | loss:1.3174901008605957 lr:5.504806597840702e-05 tokens_per_second_per_gpu:1009.4145800066966
Step 1729 | loss:1.4827163219451904 lr:5.5031515913489374e-05 tokens_per_second_per_gpu:1048.6729996601312
Step 1730 | loss:1.5442794561386108 lr:5.501495918512702e-05 tokens_per_second_per_gpu:671.2643364443257
Step 1731 | loss:1.4230552911758423 lr:5.4998395798827494e-05 tokens_per_second_per_gpu:955.9324350714476
Step 1732 | loss:1.434438705444336 lr:5.4981825760100605e-05 tokens_per_second_per_gpu:948.6170133242281
Step 1733 | loss:1.4867099523544312 lr:5.4965249074458324e-05 tokens_per_second_per_gpu:1020.9223012800815
Step 1734 | loss:1.4343680143356323 lr:5.494866574741485e-05 tokens_per_second_per_gpu:663.8921372667379
Step 1735 | loss:1.3036534786224365 lr:5.493207578448661e-05 tokens_per_second_per_gpu:823.2013723947886
Step 1736 | loss:1.4054977893829346 lr:5.491547919119222e-05 tokens_per_second_per_gpu:711.9920632437963
Step 1737 | loss:1.4546805620193481 lr:5.489887597305248e-05 tokens_per_second_per_gpu:837.8679752501911
Step 1738 | loss:1.4923107624053955 lr:5.488226613559045e-05 tokens_per_second_per_gpu:628.2952202662976
Step 1739 | loss:1.510246753692627 lr:5.486564968433134e-05 tokens_per_second_per_gpu:917.9553750487446
Step 1740 | loss:1.534691333770752 lr:5.48490266248026e-05 tokens_per_second_per_gpu:874.0349904336581
Step 1741 | loss:1.3333722352981567 lr:5.483239696253384e-05 tokens_per_second_per_gpu:694.5548696700955
Step 1742 | loss:1.302842378616333 lr:5.4815760703056884e-05 tokens_per_second_per_gpu:981.9153865400768
Step 1743 | loss:1.3252569437026978 lr:5.479911785190576e-05 tokens_per_second_per_gpu:1282.3109319210207
Step 1744 | loss:1.2881536483764648 lr:5.478246841461668e-05 tokens_per_second_per_gpu:1206.7045355837981
Step 1745 | loss:1.3642001152038574 lr:5.476581239672804e-05 tokens_per_second_per_gpu:760.4152933322595
Step 1746 | loss:1.4219906330108643 lr:5.474914980378044e-05 tokens_per_second_per_gpu:861.4850176462062
Step 1747 | loss:1.480338215827942 lr:5.4732480641316654e-05 tokens_per_second_per_gpu:734.5403662133355
Step 1748 | loss:1.2498035430908203 lr:5.471580491488166e-05 tokens_per_second_per_gpu:1166.798024553039
Step 1749 | loss:1.2908878326416016 lr:5.469912263002258e-05 tokens_per_second_per_gpu:1059.9104397215071
Step 1750 | loss:1.3117327690124512 lr:5.468243379228876e-05 tokens_per_second_per_gpu:1235.1206590461259
Step 1751 | loss:1.5177216529846191 lr:5.4665738407231714e-05 tokens_per_second_per_gpu:600.0930957735735
Step 1752 | loss:1.3747044801712036 lr:5.464903648040511e-05 tokens_per_second_per_gpu:784.7792072805737
Step 1753 | loss:1.3393267393112183 lr:5.4632328017364825e-05 tokens_per_second_per_gpu:1078.428717391243
Step 1754 | loss:1.4020788669586182 lr:5.4615613023668894e-05 tokens_per_second_per_gpu:609.0545009975917
Step 1755 | loss:1.381266474723816 lr:5.4598891504877544e-05 tokens_per_second_per_gpu:797.0724786679286
Step 1756 | loss:1.2707734107971191 lr:5.458216346655312e-05 tokens_per_second_per_gpu:1228.2459463673306
Step 1757 | loss:1.1437424421310425 lr:5.4565428914260205e-05 tokens_per_second_per_gpu:870.8038315354619
Step 1758 | loss:1.4801105260849 lr:5.4548687853565495e-05 tokens_per_second_per_gpu:779.0300362428509
Step 1759 | loss:1.38687264919281 lr:5.453194029003787e-05 tokens_per_second_per_gpu:1053.5066401501165
Step 1760 | loss:1.3707438707351685 lr:5.4515186229248394e-05 tokens_per_second_per_gpu:654.9397378500981
Step 1761 | loss:1.3915975093841553 lr:5.449842567677026e-05 tokens_per_second_per_gpu:1002.1574458122809
Step 1762 | loss:1.4251887798309326 lr:5.4481658638178816e-05 tokens_per_second_per_gpu:1023.9240526148527
Step 1763 | loss:1.3813858032226562 lr:5.4464885119051626e-05 tokens_per_second_per_gpu:840.5309841949924
Step 1764 | loss:1.5063354969024658 lr:5.444810512496834e-05 tokens_per_second_per_gpu:845.6792511251017
Step 1765 | loss:1.3062313795089722 lr:5.443131866151078e-05 tokens_per_second_per_gpu:950.7110081992909
Step 1766 | loss:1.4148675203323364 lr:5.4414525734262966e-05 tokens_per_second_per_gpu:675.6712939359139
Step 1767 | loss:1.2840467691421509 lr:5.4397726348810994e-05 tokens_per_second_per_gpu:1121.4383290962735
Step 1768 | loss:1.3772274255752563 lr:5.438092051074317e-05 tokens_per_second_per_gpu:1115.9558298565453
Step 1769 | loss:1.4095245599746704 lr:5.436410822564992e-05 tokens_per_second_per_gpu:1120.6022807370337
Step 1770 | loss:1.446786642074585 lr:5.434728949912381e-05 tokens_per_second_per_gpu:719.1396470285379
Step 1771 | loss:1.3542251586914062 lr:5.433046433675957e-05 tokens_per_second_per_gpu:893.9899417157992
Step 1772 | loss:1.4020569324493408 lr:5.431363274415405e-05 tokens_per_second_per_gpu:660.4513736552053
Step 1773 | loss:1.3888839483261108 lr:5.429679472690625e-05 tokens_per_second_per_gpu:1027.4742675516793
Step 1774 | loss:1.3054734468460083 lr:5.427995029061728e-05 tokens_per_second_per_gpu:943.7413793993753
Step 1775 | loss:1.4601103067398071 lr:5.4263099440890444e-05 tokens_per_second_per_gpu:729.1965451516489
Step 1776 | loss:1.4618364572525024 lr:5.424624218333114e-05 tokens_per_second_per_gpu:1031.1188436334135
Step 1777 | loss:1.3577581644058228 lr:5.422937852354687e-05 tokens_per_second_per_gpu:822.1052530279105
Step 1778 | loss:1.4889864921569824 lr:5.421250846714733e-05 tokens_per_second_per_gpu:833.0450617982522
Step 1779 | loss:1.4668136835098267 lr:5.4195632019744305e-05 tokens_per_second_per_gpu:630.3764480211247
Step 1780 | loss:1.321693778038025 lr:5.417874918695169e-05 tokens_per_second_per_gpu:965.7107646750952
Step 1781 | loss:1.2454729080200195 lr:5.416185997438556e-05 tokens_per_second_per_gpu:1157.0586168068326
Step 1782 | loss:1.2620760202407837 lr:5.4144964387664055e-05 tokens_per_second_per_gpu:777.8959633313531
Step 1783 | loss:1.5040761232376099 lr:5.4128062432407464e-05 tokens_per_second_per_gpu:969.8636781354517
Step 1784 | loss:1.5688045024871826 lr:5.41111541142382e-05 tokens_per_second_per_gpu:961.0640202525774
Step 1785 | loss:1.4369392395019531 lr:5.409423943878077e-05 tokens_per_second_per_gpu:1035.878137198291
Step 1786 | loss:1.3432546854019165 lr:5.407731841166181e-05 tokens_per_second_per_gpu:998.695170610321
Step 1787 | loss:1.3954474925994873 lr:5.406039103851007e-05 tokens_per_second_per_gpu:928.5757087666259
Step 1788 | loss:1.3918137550354004 lr:5.404345732495641e-05 tokens_per_second_per_gpu:1010.7427500865115
Step 1789 | loss:1.21808660030365 lr:5.4026517276633786e-05 tokens_per_second_per_gpu:1229.6095202777008
Step 1790 | loss:1.4246822595596313 lr:5.400957089917728e-05 tokens_per_second_per_gpu:972.286635869959
Step 1791 | loss:1.325645089149475 lr:5.399261819822407e-05 tokens_per_second_per_gpu:984.3791623895248
Step 1792 | loss:1.4940102100372314 lr:5.397565917941344e-05 tokens_per_second_per_gpu:859.1708116339452
Step 1793 | loss:1.4505280256271362 lr:5.395869384838677e-05 tokens_per_second_per_gpu:949.0796567472237
Step 1794 | loss:1.3054935932159424 lr:5.3941722210787556e-05 tokens_per_second_per_gpu:897.6628003470262
Step 1795 | loss:1.606629729270935 lr:5.392474427226137e-05 tokens_per_second_per_gpu:947.5582183554681
Step 1796 | loss:1.4510164260864258 lr:5.390776003845589e-05 tokens_per_second_per_gpu:752.9634209919809
Step 1797 | loss:1.1703317165374756 lr:5.38907695150209e-05 tokens_per_second_per_gpu:1012.808970352445
Step 1798 | loss:1.4608380794525146 lr:5.3873772707608243e-05 tokens_per_second_per_gpu:823.3747025154861
Step 1799 | loss:1.365464448928833 lr:5.385676962187189e-05 tokens_per_second_per_gpu:635.1424366097128
Step 1800 | loss:1.3750145435333252 lr:5.383976026346789e-05 tokens_per_second_per_gpu:814.6118917262752
Step 1801 | loss:1.268141269683838 lr:5.382274463805434e-05 tokens_per_second_per_gpu:814.758076959729
Step 1802 | loss:1.5307013988494873 lr:5.38057227512915e-05 tokens_per_second_per_gpu:789.727513552911
Step 1803 | loss:1.4278002977371216 lr:5.378869460884164e-05 tokens_per_second_per_gpu:606.4267850572776
Step 1804 | loss:1.264017939567566 lr:5.377166021636914e-05 tokens_per_second_per_gpu:1356.159737766917
Step 1805 | loss:1.4293352365493774 lr:5.3754619579540465e-05 tokens_per_second_per_gpu:1178.2952458267698
Step 1806 | loss:1.5277031660079956 lr:5.373757270402415e-05 tokens_per_second_per_gpu:1058.7741980808207
Step 1807 | loss:1.2623426914215088 lr:5.3720519595490786e-05 tokens_per_second_per_gpu:1061.0454159659196
Step 1808 | loss:1.4194062948226929 lr:5.370346025961308e-05 tokens_per_second_per_gpu:748.5149129494697
Step 1809 | loss:1.5611708164215088 lr:5.368639470206578e-05 tokens_per_second_per_gpu:860.3234963608444
Step 1810 | loss:1.4796925783157349 lr:5.3669322928525714e-05 tokens_per_second_per_gpu:999.0016173506659
Step 1811 | loss:1.266839623451233 lr:5.365224494467175e-05 tokens_per_second_per_gpu:1231.7647551902899
Step 1812 | loss:1.4603383541107178 lr:5.363516075618488e-05 tokens_per_second_per_gpu:968.222591886511
Step 1813 | loss:1.3624964952468872 lr:5.36180703687481e-05 tokens_per_second_per_gpu:1148.460453499335
Step 1814 | loss:1.4176651239395142 lr:5.360097378804651e-05 tokens_per_second_per_gpu:880.3602657031562
Step 1815 | loss:1.5666828155517578 lr:5.3583871019767256e-05 tokens_per_second_per_gpu:771.195222549583
Step 1816 | loss:1.452077865600586 lr:5.356676206959953e-05 tokens_per_second_per_gpu:907.2514111468355
Step 1817 | loss:1.311725378036499 lr:5.3549646943234584e-05 tokens_per_second_per_gpu:915.6621139264715
Step 1818 | loss:1.2397754192352295 lr:5.353252564636575e-05 tokens_per_second_per_gpu:1016.2490379160638
Step 1819 | loss:1.4366865158081055 lr:5.3515398184688386e-05 tokens_per_second_per_gpu:789.3078126853071
Step 1820 | loss:1.2859176397323608 lr:5.34982645638999e-05 tokens_per_second_per_gpu:857.378877687515
Step 1821 | loss:1.2925435304641724 lr:5.3481124789699785e-05 tokens_per_second_per_gpu:1387.0208949995663
Step 1822 | loss:1.3535786867141724 lr:5.346397886778951e-05 tokens_per_second_per_gpu:873.8120574020663
Step 1823 | loss:1.3376926183700562 lr:5.344682680387268e-05 tokens_per_second_per_gpu:935.0859758773549
Step 1824 | loss:1.313948154449463 lr:5.342966860365487e-05 tokens_per_second_per_gpu:1029.6758276517662
Step 1825 | loss:1.3299908638000488 lr:5.341250427284371e-05 tokens_per_second_per_gpu:801.1881078661165
Step 1826 | loss:1.3369512557983398 lr:5.3395333817148904e-05 tokens_per_second_per_gpu:811.5448163532346
Step 1827 | loss:1.2799280881881714 lr:5.337815724228216e-05 tokens_per_second_per_gpu:1148.9838168798035
Step 1828 | loss:1.4258500337600708 lr:5.336097455395724e-05 tokens_per_second_per_gpu:1056.4086894073605
Step 1829 | loss:1.3929908275604248 lr:5.334378575788992e-05 tokens_per_second_per_gpu:783.188979078575
Step 1830 | loss:1.378490924835205 lr:5.332659085979802e-05 tokens_per_second_per_gpu:1065.0154681394224
Step 1831 | loss:1.2851154804229736 lr:5.330938986540142e-05 tokens_per_second_per_gpu:931.0232482666925
Step 1832 | loss:1.3250268697738647 lr:5.3292182780421946e-05 tokens_per_second_per_gpu:918.3006472027151
Step 1833 | loss:1.4919133186340332 lr:5.327496961058355e-05 tokens_per_second_per_gpu:683.5085983616638
Step 1834 | loss:1.474355936050415 lr:5.325775036161212e-05 tokens_per_second_per_gpu:896.2084279688004
Step 1835 | loss:1.4390443563461304 lr:5.3240525039235625e-05 tokens_per_second_per_gpu:927.9547422752729
Step 1836 | loss:1.334085464477539 lr:5.322329364918403e-05 tokens_per_second_per_gpu:780.6256645665821
Step 1837 | loss:1.407544493675232 lr:5.320605619718933e-05 tokens_per_second_per_gpu:814.107325313915
Step 1838 | loss:1.5150011777877808 lr:5.3188812688985525e-05 tokens_per_second_per_gpu:789.0541879196217
Step 1839 | loss:1.4757356643676758 lr:5.317156313030864e-05 tokens_per_second_per_gpu:622.2672810304126
Step 1840 | loss:1.5542619228363037 lr:5.31543075268967e-05 tokens_per_second_per_gpu:745.613233725401
Step 1841 | loss:1.4756790399551392 lr:5.3137045884489746e-05 tokens_per_second_per_gpu:808.3800353488804
Step 1842 | loss:1.5053755044937134 lr:5.3119778208829826e-05 tokens_per_second_per_gpu:746.6619062253199
Step 1843 | loss:1.313555121421814 lr:5.3102504505661024e-05 tokens_per_second_per_gpu:837.8948777517301
Step 1844 | loss:1.4823700189590454 lr:5.308522478072938e-05 tokens_per_second_per_gpu:835.1071527298492
Step 1845 | loss:1.413381576538086 lr:5.306793903978297e-05 tokens_per_second_per_gpu:948.5490477329997
Step 1846 | loss:1.4333857297897339 lr:5.305064728857185e-05 tokens_per_second_per_gpu:815.6341023616167
Step 1847 | loss:1.5198354721069336 lr:5.3033349532848105e-05 tokens_per_second_per_gpu:886.9431250921965
Step 1848 | loss:1.489051342010498 lr:5.301604577836578e-05 tokens_per_second_per_gpu:953.3091897396481
Step 1849 | loss:1.3554694652557373 lr:5.2998736030880954e-05 tokens_per_second_per_gpu:822.5213958301655
Step 1850 | loss:1.3192522525787354 lr:5.298142029615167e-05 tokens_per_second_per_gpu:778.3741444159098
Step 1851 | loss:1.3050287961959839 lr:5.296409857993798e-05 tokens_per_second_per_gpu:900.1171123154958
Step 1852 | loss:1.362031102180481 lr:5.2946770888001916e-05 tokens_per_second_per_gpu:941.140738459213
Step 1853 | loss:1.4097692966461182 lr:5.2929437226107486e-05 tokens_per_second_per_gpu:852.8711711584676
Step 1854 | loss:1.4305713176727295 lr:5.2912097600020735e-05 tokens_per_second_per_gpu:815.096379783675
Step 1855 | loss:1.3720365762710571 lr:5.2894752015509616e-05 tokens_per_second_per_gpu:863.8660093898151
Step 1856 | loss:1.2987642288208008 lr:5.287740047834413e-05 tokens_per_second_per_gpu:832.8721383902391
Step 1857 | loss:1.514517903327942 lr:5.2860042994296226e-05 tokens_per_second_per_gpu:969.5472850275936
Step 1858 | loss:1.3508055210113525 lr:5.284267956913983e-05 tokens_per_second_per_gpu:901.6955537459502
Step 1859 | loss:1.3077744245529175 lr:5.2825310208650864e-05 tokens_per_second_per_gpu:1101.0896110108588
Step 1860 | loss:1.480183482170105 lr:5.28079349186072e-05 tokens_per_second_per_gpu:930.3754488525102
Step 1861 | loss:1.3555333614349365 lr:5.279055370478869e-05 tokens_per_second_per_gpu:1001.4445218668501
Step 1862 | loss:1.3999807834625244 lr:5.277316657297718e-05 tokens_per_second_per_gpu:986.1141058587727
Step 1863 | loss:1.4081603288650513 lr:5.2755773528956456e-05 tokens_per_second_per_gpu:1109.2728699042584
Step 1864 | loss:1.3942351341247559 lr:5.273837457851227e-05 tokens_per_second_per_gpu:719.2847656126761
Step 1865 | loss:1.2943295240402222 lr:5.272096972743238e-05 tokens_per_second_per_gpu:896.3695442942674
Step 1866 | loss:1.3059104681015015 lr:5.2703558981506434e-05 tokens_per_second_per_gpu:913.4879332808412
Step 1867 | loss:1.403855562210083 lr:5.2686142346526104e-05 tokens_per_second_per_gpu:711.1996650953098
Step 1868 | loss:1.375383973121643 lr:5.2668719828285e-05 tokens_per_second_per_gpu:855.0355260678767
Step 1869 | loss:1.1677086353302002 lr:5.265129143257869e-05 tokens_per_second_per_gpu:1224.100471902443
Step 1870 | loss:1.386122226715088 lr:5.2633857165204696e-05 tokens_per_second_per_gpu:911.0231784590624
Step 1871 | loss:1.4808292388916016 lr:5.26164170319625e-05 tokens_per_second_per_gpu:742.2106803899467
Step 1872 | loss:1.4033645391464233 lr:5.2598971038653505e-05 tokens_per_second_per_gpu:966.8605753742527
Step 1873 | loss:1.3546788692474365 lr:5.2581519191081095e-05 tokens_per_second_per_gpu:907.5876031874981
Step 1874 | loss:1.3311916589736938 lr:5.25640614950506e-05 tokens_per_second_per_gpu:968.2823837743127
Step 1875 | loss:1.434667706489563 lr:5.25465979563693e-05 tokens_per_second_per_gpu:861.890359330743
Step 1876 | loss:1.3245267868041992 lr:5.252912858084639e-05 tokens_per_second_per_gpu:1029.5267440516338
Step 1877 | loss:1.388329029083252 lr:5.251165337429302e-05 tokens_per_second_per_gpu:1063.4968372494532
Step 1878 | loss:1.4881649017333984 lr:5.2494172342522295e-05 tokens_per_second_per_gpu:772.6575925861066
Step 1879 | loss:1.3068231344223022 lr:5.2476685491349234e-05 tokens_per_second_per_gpu:731.8978341179039
Step 1880 | loss:1.5517648458480835 lr:5.245919282659082e-05 tokens_per_second_per_gpu:946.730095969464
Step 1881 | loss:1.2568092346191406 lr:5.244169435406595e-05 tokens_per_second_per_gpu:844.1302946159316
Step 1882 | loss:1.3208428621292114 lr:5.2424190079595454e-05 tokens_per_second_per_gpu:817.3953120730831
Step 1883 | loss:1.2178246974945068 lr:5.240668000900208e-05 tokens_per_second_per_gpu:1501.6572818167551
Step 1884 | loss:1.3143302202224731 lr:5.238916414811055e-05 tokens_per_second_per_gpu:1173.7723437067402
Step 1885 | loss:1.5742394924163818 lr:5.237164250274746e-05 tokens_per_second_per_gpu:688.5472436832146
Step 1886 | loss:1.2034318447113037 lr:5.235411507874134e-05 tokens_per_second_per_gpu:944.2232709312559
Step 1887 | loss:1.3722467422485352 lr:5.2336581881922686e-05 tokens_per_second_per_gpu:1017.1525406380108
Step 1888 | loss:1.4624890089035034 lr:5.231904291812385e-05 tokens_per_second_per_gpu:981.2428687863832
Step 1889 | loss:1.450231671333313 lr:5.2301498193179154e-05 tokens_per_second_per_gpu:778.7249546140181
Step 1890 | loss:1.3548693656921387 lr:5.2283947712924814e-05 tokens_per_second_per_gpu:833.7313679694213
Step 1891 | loss:1.2766603231430054 lr:5.226639148319895e-05 tokens_per_second_per_gpu:1108.9016656938627
Step 1892 | loss:1.4192931652069092 lr:5.224882950984162e-05 tokens_per_second_per_gpu:874.5666044204584
Step 1893 | loss:1.4451011419296265 lr:5.223126179869478e-05 tokens_per_second_per_gpu:942.5630899303122
Step 1894 | loss:1.263082504272461 lr:5.221368835560229e-05 tokens_per_second_per_gpu:1198.1615235651911
Step 1895 | loss:1.3968541622161865 lr:5.219610918640993e-05 tokens_per_second_per_gpu:833.738589898787
Step 1896 | loss:1.5108577013015747 lr:5.217852429696537e-05 tokens_per_second_per_gpu:591.7209447707618
Step 1897 | loss:1.287419080734253 lr:5.2160933693118185e-05 tokens_per_second_per_gpu:1087.1292643287038
Step 1898 | loss:1.4409140348434448 lr:5.214333738071985e-05 tokens_per_second_per_gpu:758.3474055178541
Step 1899 | loss:1.4462641477584839 lr:5.212573536562376e-05 tokens_per_second_per_gpu:1086.2616209679777
Step 1900 | loss:1.6614787578582764 lr:5.210812765368519e-05 tokens_per_second_per_gpu:578.0149670832008
Step 1901 | loss:1.4112874269485474 lr:5.209051425076131e-05 tokens_per_second_per_gpu:892.0861837085057
Step 1902 | loss:1.3837108612060547 lr:5.207289516271117e-05 tokens_per_second_per_gpu:981.6022073950701
Step 1903 | loss:1.446234941482544 lr:5.205527039539573e-05 tokens_per_second_per_gpu:929.3654677302441
Step 1904 | loss:1.4454833269119263 lr:5.203763995467784e-05 tokens_per_second_per_gpu:708.4453950565301
Step 1905 | loss:1.4408131837844849 lr:5.202000384642224e-05 tokens_per_second_per_gpu:819.5246714682373
Step 1906 | loss:1.4491024017333984 lr:5.200236207649554e-05 tokens_per_second_per_gpu:1067.1103658493762
Step 1907 | loss:1.509042739868164 lr:5.1984714650766234e-05 tokens_per_second_per_gpu:763.3830647774948
Step 1908 | loss:1.397641658782959 lr:5.196706157510471e-05 tokens_per_second_per_gpu:880.5063556753951
Step 1909 | loss:1.1840447187423706 lr:5.194940285538323e-05 tokens_per_second_per_gpu:990.0934632449886
Step 1910 | loss:1.434632420539856 lr:5.1931738497475914e-05 tokens_per_second_per_gpu:844.919486545273
Step 1911 | loss:1.1961816549301147 lr:5.19140685072588e-05 tokens_per_second_per_gpu:1138.49845421887
Step 1912 | loss:1.2692536115646362 lr:5.189639289060978e-05 tokens_per_second_per_gpu:1164.469538937658
Step 1913 | loss:1.4061667919158936 lr:5.1878711653408593e-05 tokens_per_second_per_gpu:921.9392171173064
Step 1914 | loss:1.3694024085998535 lr:5.186102480153687e-05 tokens_per_second_per_gpu:1039.812763362073
Step 1915 | loss:1.4568169116973877 lr:5.184333234087813e-05 tokens_per_second_per_gpu:728.469332752901
Step 1916 | loss:1.3190724849700928 lr:5.1825634277317706e-05 tokens_per_second_per_gpu:905.0338164572296
Step 1917 | loss:1.522696614265442 lr:5.1807930616742854e-05 tokens_per_second_per_gpu:690.6915284734198
Step 1918 | loss:1.5126944780349731 lr:5.179022136504264e-05 tokens_per_second_per_gpu:775.7753247145317
Step 1919 | loss:1.4105052947998047 lr:5.177250652810801e-05 tokens_per_second_per_gpu:1154.1625622191366
Step 1920 | loss:1.2310376167297363 lr:5.1754786111831784e-05 tokens_per_second_per_gpu:723.3511206310063
Step 1921 | loss:1.2879908084869385 lr:5.173706012210862e-05 tokens_per_second_per_gpu:765.6708698516944
Step 1922 | loss:1.4440333843231201 lr:5.1719328564835025e-05 tokens_per_second_per_gpu:744.8614173724923
Step 1923 | loss:1.4357805252075195 lr:5.170159144590939e-05 tokens_per_second_per_gpu:897.0225924666785
Step 1924 | loss:1.3454660177230835 lr:5.168384877123191e-05 tokens_per_second_per_gpu:822.5436286390245
Step 1925 | loss:1.3851032257080078 lr:5.166610054670465e-05 tokens_per_second_per_gpu:1165.413105170079
Step 1926 | loss:1.4694141149520874 lr:5.164834677823154e-05 tokens_per_second_per_gpu:907.420491592696
Step 1927 | loss:1.2913269996643066 lr:5.163058747171833e-05 tokens_per_second_per_gpu:950.6857461028013
Step 1928 | loss:1.3985941410064697 lr:5.1612822633072616e-05 tokens_per_second_per_gpu:808.0642726622947
Step 1929 | loss:1.4623767137527466 lr:5.159505226820382e-05 tokens_per_second_per_gpu:1025.153888925583
Step 1930 | loss:1.2075481414794922 lr:5.157727638302325e-05 tokens_per_second_per_gpu:1094.3485400557297
Step 1931 | loss:1.2343993186950684 lr:5.1559494983444e-05 tokens_per_second_per_gpu:934.6631696636513
Step 1932 | loss:1.231298804283142 lr:5.1541708075381037e-05 tokens_per_second_per_gpu:874.4461540655367
Step 1933 | loss:1.322921872138977 lr:5.152391566475112e-05 tokens_per_second_per_gpu:849.8740241642492
Step 1934 | loss:1.4111151695251465 lr:5.150611775747287e-05 tokens_per_second_per_gpu:872.01838911897
Step 1935 | loss:1.2996693849563599 lr:5.148831435946672e-05 tokens_per_second_per_gpu:1294.4377827123544
Step 1936 | loss:1.5414129495620728 lr:5.147050547665494e-05 tokens_per_second_per_gpu:784.3606863604806
Step 1937 | loss:1.3712048530578613 lr:5.145269111496162e-05 tokens_per_second_per_gpu:1019.5497218214645
Step 1938 | loss:1.3844385147094727 lr:5.143487128031267e-05 tokens_per_second_per_gpu:731.5827987951426
Step 1939 | loss:1.336748719215393 lr:5.1417045978635835e-05 tokens_per_second_per_gpu:1049.0070187620884
Step 1940 | loss:1.4476361274719238 lr:5.139921521586065e-05 tokens_per_second_per_gpu:897.0258071413174
Step 1941 | loss:1.2508673667907715 lr:5.1381378997918486e-05 tokens_per_second_per_gpu:943.2293235319336
Step 1942 | loss:1.4403066635131836 lr:5.136353733074254e-05 tokens_per_second_per_gpu:974.9275137960342
Step 1943 | loss:1.418709397315979 lr:5.13456902202678e-05 tokens_per_second_per_gpu:1141.3728830769903
Step 1944 | loss:1.2785708904266357 lr:5.132783767243106e-05 tokens_per_second_per_gpu:863.0794386710419
Step 1945 | loss:1.4403096437454224 lr:5.130997969317096e-05 tokens_per_second_per_gpu:770.6676391235644
Step 1946 | loss:1.3018690347671509 lr:5.1292116288427905e-05 tokens_per_second_per_gpu:963.7301851861629
Step 1947 | loss:1.3364728689193726 lr:5.1274247464144124e-05 tokens_per_second_per_gpu:1085.3086235783621
Step 1948 | loss:1.4552412033081055 lr:5.125637322626364e-05 tokens_per_second_per_gpu:729.0437901226858
Step 1949 | loss:1.374151349067688 lr:5.12384935807323e-05 tokens_per_second_per_gpu:1029.1026200996341
Step 1950 | loss:1.3260042667388916 lr:5.122060853349773e-05 tokens_per_second_per_gpu:961.5927495771192
Step 1951 | loss:1.414236068725586 lr:5.1202718090509346e-05 tokens_per_second_per_gpu:995.1072967858761
Step 1952 | loss:1.312798261642456 lr:5.1184822257718365e-05 tokens_per_second_per_gpu:884.6685996966188
Step 1953 | loss:1.4539660215377808 lr:5.1166921041077815e-05 tokens_per_second_per_gpu:1003.6710548767358
Step 1954 | loss:1.4551818370819092 lr:5.1149014446542494e-05 tokens_per_second_per_gpu:888.1867187758481
Step 1955 | loss:1.397847056388855 lr:5.1131102480069e-05 tokens_per_second_per_gpu:878.205597393774
Step 1956 | loss:1.5418438911437988 lr:5.1113185147615714e-05 tokens_per_second_per_gpu:596.1694394243221
Step 1957 | loss:1.3147006034851074 lr:5.10952624551428e-05 tokens_per_second_per_gpu:999.8393926965471
Step 1958 | loss:1.371715784072876 lr:5.1077334408612196e-05 tokens_per_second_per_gpu:850.5201884406472
Step 1959 | loss:1.2890266180038452 lr:5.105940101398764e-05 tokens_per_second_per_gpu:1015.3972031445082
Step 1960 | loss:1.309507131576538 lr:5.1041462277234655e-05 tokens_per_second_per_gpu:790.3162764104183
Step 1961 | loss:1.3241280317306519 lr:5.102351820432051e-05 tokens_per_second_per_gpu:637.8663160421586
Step 1962 | loss:1.520279049873352 lr:5.100556880121426e-05 tokens_per_second_per_gpu:857.2106564598763
Step 1963 | loss:1.4606132507324219 lr:5.0987614073886756e-05 tokens_per_second_per_gpu:896.2023223372654
Step 1964 | loss:1.3578643798828125 lr:5.0969654028310594e-05 tokens_per_second_per_gpu:747.0306605516288
Step 1965 | loss:1.451793909072876 lr:5.095168867046016e-05 tokens_per_second_per_gpu:1090.936462347573
Step 1966 | loss:1.3411308526992798 lr:5.093371800631156e-05 tokens_per_second_per_gpu:940.7356081174605
Step 1967 | loss:1.4285410642623901 lr:5.091574204184274e-05 tokens_per_second_per_gpu:646.5107929483712
Step 1968 | loss:1.6312705278396606 lr:5.089776078303336e-05 tokens_per_second_per_gpu:863.6063980365981
Step 1969 | loss:1.2578538656234741 lr:5.087977423586484e-05 tokens_per_second_per_gpu:960.0758721440867
Step 1970 | loss:1.270063877105713 lr:5.0861782406320376e-05 tokens_per_second_per_gpu:894.2538414112915
Step 1971 | loss:1.34048330783844 lr:5.0843785300384915e-05 tokens_per_second_per_gpu:754.6292778208189
Step 1972 | loss:1.389078140258789 lr:5.082578292404515e-05 tokens_per_second_per_gpu:1160.8077141031383
Step 1973 | loss:1.3470155000686646 lr:5.0807775283289556e-05 tokens_per_second_per_gpu:1095.2751926248552
Step 1974 | loss:1.3194129467010498 lr:5.078976238410832e-05 tokens_per_second_per_gpu:1010.9061402912047
Step 1975 | loss:1.339553952217102 lr:5.0771744232493414e-05 tokens_per_second_per_gpu:1029.8945519833717
Step 1976 | loss:1.420068383216858 lr:5.075372083443853e-05 tokens_per_second_per_gpu:780.1992128016302
Step 1977 | loss:1.3224906921386719 lr:5.0735692195939125e-05 tokens_per_second_per_gpu:1158.4269450336676
Step 1978 | loss:1.4167561531066895 lr:5.0717658322992374e-05 tokens_per_second_per_gpu:729.1735063477017
Step 1979 | loss:1.3988255262374878 lr:5.0699619221597226e-05 tokens_per_second_per_gpu:742.8216846792086
Step 1980 | loss:1.3517720699310303 lr:5.068157489775435e-05 tokens_per_second_per_gpu:982.8944977565726
Step 1981 | loss:1.290408968925476 lr:5.0663525357466154e-05 tokens_per_second_per_gpu:1009.2072267574038
Step 1982 | loss:1.352484941482544 lr:5.064547060673679e-05 tokens_per_second_per_gpu:836.7798475512642
Step 1983 | loss:1.617356538772583 lr:5.062741065157211e-05 tokens_per_second_per_gpu:658.4412395685769
Step 1984 | loss:1.2968904972076416 lr:5.060934549797974e-05 tokens_per_second_per_gpu:1062.280201911792
Step 1985 | loss:1.5170865058898926 lr:5.059127515196903e-05 tokens_per_second_per_gpu:930.0794399820489
Step 1986 | loss:1.4688239097595215 lr:5.0573199619551024e-05 tokens_per_second_per_gpu:612.6124005166207
Step 1987 | loss:1.3171411752700806 lr:5.0555118906738534e-05 tokens_per_second_per_gpu:873.008778264987
Step 1988 | loss:1.3011605739593506 lr:5.053703301954604e-05 tokens_per_second_per_gpu:1005.1153864448548
Step 1989 | loss:1.3752483129501343 lr:5.051894196398982e-05 tokens_per_second_per_gpu:850.4410747035664
Step 1990 | loss:1.3433525562286377 lr:5.0500845746087795e-05 tokens_per_second_per_gpu:847.4750922328153
Step 1991 | loss:1.3487375974655151 lr:5.048274437185965e-05 tokens_per_second_per_gpu:707.8555816930982
Step 1992 | loss:1.5333983898162842 lr:5.046463784732677e-05 tokens_per_second_per_gpu:860.2281333390265
Step 1993 | loss:1.2112770080566406 lr:5.044652617851227e-05 tokens_per_second_per_gpu:1189.2771416438914
Step 1994 | loss:1.4792382717132568 lr:5.042840937144093e-05 tokens_per_second_per_gpu:553.9339377018101
Step 1995 | loss:1.318347454071045 lr:5.04102874321393e-05 tokens_per_second_per_gpu:881.1686707332516
Step 1996 | loss:1.4055222272872925 lr:5.039216036663559e-05 tokens_per_second_per_gpu:716.6018075631532
Step 1997 | loss:1.4675419330596924 lr:5.037402818095974e-05 tokens_per_second_per_gpu:836.631195288541
Step 1998 | loss:1.4211926460266113 lr:5.035589088114338e-05 tokens_per_second_per_gpu:715.1440912223206
Step 1999 | loss:1.196458339691162 lr:5.033774847321986e-05 tokens_per_second_per_gpu:952.4403962402044
Step 2000 | loss:1.5657678842544556 lr:5.031960096322421e-05 tokens_per_second_per_gpu:853.3844101086605
Step 2001 | loss:1.4577507972717285 lr:5.0301448357193154e-05 tokens_per_second_per_gpu:995.8745726981052
Step 2002 | loss:1.295089602470398 lr:5.028329066116513e-05 tokens_per_second_per_gpu:1021.8477370174693
Step 2003 | loss:1.3766247034072876 lr:5.026512788118027e-05 tokens_per_second_per_gpu:1023.3178639999867
Step 2004 | loss:1.280433177947998 lr:5.024696002328036e-05 tokens_per_second_per_gpu:1084.9951246729893
Step 2005 | loss:1.5059328079223633 lr:5.022878709350893e-05 tokens_per_second_per_gpu:609.4405338864029
Step 2006 | loss:1.4519672393798828 lr:5.0210609097911155e-05 tokens_per_second_per_gpu:1075.5918637267828
Step 2007 | loss:1.470609188079834 lr:5.0192426042533924e-05 tokens_per_second_per_gpu:661.8799186007091
Step 2008 | loss:1.2506091594696045 lr:5.0174237933425774e-05 tokens_per_second_per_gpu:1182.498930468557
Step 2009 | loss:1.4502218961715698 lr:5.015604477663696e-05 tokens_per_second_per_gpu:771.8258436997702
Step 2010 | loss:1.2584909200668335 lr:5.01378465782194e-05 tokens_per_second_per_gpu:805.4108539162416
Step 2011 | loss:1.5591853857040405 lr:5.011964334422668e-05 tokens_per_second_per_gpu:991.6031147001692
Step 2012 | loss:1.2880008220672607 lr:5.010143508071408e-05 tokens_per_second_per_gpu:803.34886979841
Step 2013 | loss:1.4567855596542358 lr:5.008322179373852e-05 tokens_per_second_per_gpu:777.0797729957826
Step 2014 | loss:1.342159628868103 lr:5.006500348935865e-05 tokens_per_second_per_gpu:1065.6744838500115
Step 2015 | loss:1.3541738986968994 lr:5.004678017363472e-05 tokens_per_second_per_gpu:804.864379942005
Step 2016 | loss:1.4042210578918457 lr:5.0028551852628715e-05 tokens_per_second_per_gpu:800.9392957982667
Step 2017 | loss:1.2057294845581055 lr:5.0010318532404226e-05 tokens_per_second_per_gpu:1060.5366218523832
Step 2018 | loss:1.487689733505249 lr:4.9992080219026536e-05 tokens_per_second_per_gpu:1206.1244401540216
Step 2019 | loss:1.4924911260604858 lr:4.997383691856259e-05 tokens_per_second_per_gpu:694.7091953251453
Step 2020 | loss:1.3948547840118408 lr:4.995558863708097e-05 tokens_per_second_per_gpu:925.1125061181334
Step 2021 | loss:1.409760594367981 lr:4.993733538065195e-05 tokens_per_second_per_gpu:1068.4515340957448
Step 2022 | loss:1.3367763757705688 lr:4.991907715534743e-05 tokens_per_second_per_gpu:807.3192590827119
Step 2023 | loss:1.5371854305267334 lr:4.9900813967240994e-05 tokens_per_second_per_gpu:988.8113612697504
Step 2024 | loss:1.473641276359558 lr:4.9882545822407814e-05 tokens_per_second_per_gpu:991.0916524844793
Step 2025 | loss:1.4973297119140625 lr:4.98642727269248e-05 tokens_per_second_per_gpu:1136.7263411651516
Step 2026 | loss:1.2588003873825073 lr:4.984599468687042e-05 tokens_per_second_per_gpu:809.5060776154695
Step 2027 | loss:1.4169546365737915 lr:4.982771170832485e-05 tokens_per_second_per_gpu:726.219307817124
Step 2028 | loss:1.3883030414581299 lr:4.9809423797369895e-05 tokens_per_second_per_gpu:973.7886465158405
Step 2029 | loss:1.3646363019943237 lr:4.9791130960088976e-05 tokens_per_second_per_gpu:823.8745614372045
Step 2030 | loss:1.2848033905029297 lr:4.977283320256717e-05 tokens_per_second_per_gpu:792.9317081796064
Step 2031 | loss:1.1856476068496704 lr:4.97545305308912e-05 tokens_per_second_per_gpu:955.7196925973901
Step 2032 | loss:1.4311259984970093 lr:4.973622295114942e-05 tokens_per_second_per_gpu:944.1127664471725
Step 2033 | loss:1.4312055110931396 lr:4.9717910469431786e-05 tokens_per_second_per_gpu:811.219686156268
Step 2034 | loss:1.3437336683273315 lr:4.969959309182993e-05 tokens_per_second_per_gpu:1027.3606108265967
Step 2035 | loss:1.5222551822662354 lr:4.9681270824437096e-05 tokens_per_second_per_gpu:850.2940195764496
Step 2036 | loss:1.4130563735961914 lr:4.9662943673348136e-05 tokens_per_second_per_gpu:913.1079524974089
Step 2037 | loss:1.4292830228805542 lr:4.964461164465954e-05 tokens_per_second_per_gpu:924.0676816117887
Step 2038 | loss:1.53044593334198 lr:4.962627474446943e-05 tokens_per_second_per_gpu:706.4987263015449
Step 2039 | loss:1.271200180053711 lr:4.9607932978877546e-05 tokens_per_second_per_gpu:1006.1967129486152
Step 2040 | loss:1.4386425018310547 lr:4.958958635398522e-05 tokens_per_second_per_gpu:850.3925421073138
Step 2041 | loss:1.4223840236663818 lr:4.9571234875895436e-05 tokens_per_second_per_gpu:901.1800281315749
Step 2042 | loss:1.310952067375183 lr:4.955287855071278e-05 tokens_per_second_per_gpu:753.2527726134904
Step 2043 | loss:1.2465531826019287 lr:4.9534517384543435e-05 tokens_per_second_per_gpu:1083.4674884659207
Step 2044 | loss:1.4085948467254639 lr:4.951615138349522e-05 tokens_per_second_per_gpu:845.9834908480608
Step 2045 | loss:1.2530440092086792 lr:4.949778055367755e-05 tokens_per_second_per_gpu:841.2951208718789
Step 2046 | loss:1.3297529220581055 lr:4.947940490120142e-05 tokens_per_second_per_gpu:915.0677364989359
Step 2047 | loss:1.4256871938705444 lr:4.94610244321795e-05 tokens_per_second_per_gpu:734.0330337551133
Step 2048 | loss:1.318668007850647 lr:4.944263915272598e-05 tokens_per_second_per_gpu:753.5073548001127
Step 2049 | loss:1.3502576351165771 lr:4.94242490689567e-05 tokens_per_second_per_gpu:700.9664012133165
Step 2050 | loss:1.2874619960784912 lr:4.9405854186989084e-05 tokens_per_second_per_gpu:1080.7043767199095
Step 2051 | loss:1.407087802886963 lr:4.938745451294215e-05 tokens_per_second_per_gpu:947.0060436753955
Step 2052 | loss:1.5147429704666138 lr:4.936905005293652e-05 tokens_per_second_per_gpu:665.9607312880291
Step 2053 | loss:1.4661452770233154 lr:4.93506408130944e-05 tokens_per_second_per_gpu:791.6511150224338
Step 2054 | loss:1.4362043142318726 lr:4.933222679953959e-05 tokens_per_second_per_gpu:991.8922140063389
Step 2055 | loss:1.349900245666504 lr:4.9313808018397485e-05 tokens_per_second_per_gpu:811.7824350981722
Step 2056 | loss:1.3062736988067627 lr:4.9295384475795034e-05 tokens_per_second_per_gpu:958.2478539988334
Step 2057 | loss:1.4227783679962158 lr:4.927695617786081e-05 tokens_per_second_per_gpu:802.2691529590305
Step 2058 | loss:1.336319088935852 lr:4.9258523130724925e-05 tokens_per_second_per_gpu:1073.2170683008287
Step 2059 | loss:1.3142260313034058 lr:4.924008534051913e-05 tokens_per_second_per_gpu:1004.9984436276102
Step 2060 | loss:1.396413803100586 lr:4.92216428133767e-05 tokens_per_second_per_gpu:951.5679322034828
Step 2061 | loss:1.3667538166046143 lr:4.920319555543252e-05 tokens_per_second_per_gpu:756.2324844976293
Step 2062 | loss:1.3310871124267578 lr:4.918474357282302e-05 tokens_per_second_per_gpu:788.73048519797
Step 2063 | loss:1.2527227401733398 lr:4.916628687168622e-05 tokens_per_second_per_gpu:1163.4641640879117
Step 2064 | loss:1.3048540353775024 lr:4.914782545816171e-05 tokens_per_second_per_gpu:952.3130155495692
Step 2065 | loss:1.363195538520813 lr:4.9129359338390644e-05 tokens_per_second_per_gpu:803.3523583564781
Step 2066 | loss:1.3647257089614868 lr:4.911088851851572e-05 tokens_per_second_per_gpu:966.6741331483681
Step 2067 | loss:1.282881736755371 lr:4.9092413004681246e-05 tokens_per_second_per_gpu:893.1404156861485
Step 2068 | loss:1.4769587516784668 lr:4.907393280303307e-05 tokens_per_second_per_gpu:1040.6632130377
Step 2069 | loss:1.275281310081482 lr:4.9055447919718565e-05 tokens_per_second_per_gpu:1249.363595056608
Step 2070 | loss:1.523107886314392 lr:4.903695836088671e-05 tokens_per_second_per_gpu:893.0871096656413
Step 2071 | loss:1.3945088386535645 lr:4.901846413268802e-05 tokens_per_second_per_gpu:827.7795251336604
Step 2072 | loss:1.4238346815109253 lr:4.899996524127457e-05 tokens_per_second_per_gpu:986.7450849009322
Step 2073 | loss:1.3410123586654663 lr:4.8981461692799976e-05 tokens_per_second_per_gpu:1018.5337681677622
Step 2074 | loss:1.2806768417358398 lr:4.8962953493419396e-05 tokens_per_second_per_gpu:1124.9732490117992
Step 2075 | loss:1.1992888450622559 lr:4.8944440649289556e-05 tokens_per_second_per_gpu:1394.937006763385
Step 2076 | loss:1.51705002784729 lr:4.892592316656872e-05 tokens_per_second_per_gpu:735.8805672608323
Step 2077 | loss:1.3500312566757202 lr:4.890740105141668e-05 tokens_per_second_per_gpu:637.7791213216551
Step 2078 | loss:1.4313760995864868 lr:4.8888874309994795e-05 tokens_per_second_per_gpu:763.2385977934972
Step 2079 | loss:1.4580761194229126 lr:4.887034294846595e-05 tokens_per_second_per_gpu:662.3984844530788
Step 2080 | loss:1.4287357330322266 lr:4.8851806972994555e-05 tokens_per_second_per_gpu:754.3977727763566
Step 2081 | loss:1.3414353132247925 lr:4.883326638974657e-05 tokens_per_second_per_gpu:982.6130090982539
Step 2082 | loss:1.4020283222198486 lr:4.88147212048895e-05 tokens_per_second_per_gpu:1008.0206790457758
Step 2083 | loss:1.3842551708221436 lr:4.879617142459233e-05 tokens_per_second_per_gpu:630.2542155490895
Step 2084 | loss:1.4142214059829712 lr:4.8777617055025644e-05 tokens_per_second_per_gpu:697.629367945687
Step 2085 | loss:1.4981943368911743 lr:4.8759058102361496e-05 tokens_per_second_per_gpu:785.6062423329395
Step 2086 | loss:1.545040249824524 lr:4.874049457277349e-05 tokens_per_second_per_gpu:702.7144790299878
Step 2087 | loss:1.3361644744873047 lr:4.872192647243675e-05 tokens_per_second_per_gpu:668.4717793221795
Step 2088 | loss:1.3918195962905884 lr:4.8703353807527924e-05 tokens_per_second_per_gpu:1011.0192424043738
Step 2089 | loss:1.3914775848388672 lr:4.868477658422516e-05 tokens_per_second_per_gpu:1096.1954352863652
Step 2090 | loss:1.3038103580474854 lr:4.8666194808708144e-05 tokens_per_second_per_gpu:929.3213629012267
Step 2091 | loss:1.3133137226104736 lr:4.8647608487158064e-05 tokens_per_second_per_gpu:1072.6832762927777
Step 2092 | loss:1.342785358428955 lr:4.862901762575763e-05 tokens_per_second_per_gpu:772.7612722202099
Step 2093 | loss:1.3262789249420166 lr:4.861042223069104e-05 tokens_per_second_per_gpu:835.4737633696799
Step 2094 | loss:1.4627231359481812 lr:4.859182230814404e-05 tokens_per_second_per_gpu:815.4842290387809
Step 2095 | loss:1.4145760536193848 lr:4.857321786430382e-05 tokens_per_second_per_gpu:897.9341958342742
Step 2096 | loss:1.3642480373382568 lr:4.8554608905359154e-05 tokens_per_second_per_gpu:697.9386361945415
Step 2097 | loss:1.5598832368850708 lr:4.853599543750026e-05 tokens_per_second_per_gpu:611.1299979111545
Step 2098 | loss:1.5392934083938599 lr:4.851737746691886e-05 tokens_per_second_per_gpu:757.1333107964064
Step 2099 | loss:1.390616536140442 lr:4.8498754999808205e-05 tokens_per_second_per_gpu:785.6415234781683
Step 2100 | loss:1.3390145301818848 lr:4.8480128042363005e-05 tokens_per_second_per_gpu:956.9350009897919
Step 2101 | loss:1.3236231803894043 lr:4.846149660077949e-05 tokens_per_second_per_gpu:1036.0858344285618
Step 2102 | loss:1.142000675201416 lr:4.844286068125537e-05 tokens_per_second_per_gpu:1290.6764353579622
Step 2103 | loss:1.3688116073608398 lr:4.8424220289989865e-05 tokens_per_second_per_gpu:993.9367778910702
Step 2104 | loss:1.410944938659668 lr:4.8405575433183635e-05 tokens_per_second_per_gpu:800.9787043857017
Step 2105 | loss:1.2765002250671387 lr:4.8386926117038866e-05 tokens_per_second_per_gpu:1030.2340104138993
Step 2106 | loss:1.2258729934692383 lr:4.836827234775923e-05 tokens_per_second_per_gpu:1174.887564325307
Step 2107 | loss:1.4184486865997314 lr:4.834961413154985e-05 tokens_per_second_per_gpu:678.5835585771483
Step 2108 | loss:1.2983717918395996 lr:4.833095147461735e-05 tokens_per_second_per_gpu:950.9707128889894
Step 2109 | loss:1.426999807357788 lr:4.831228438316984e-05 tokens_per_second_per_gpu:717.0000000325745
Step 2110 | loss:1.3380438089370728 lr:4.829361286341687e-05 tokens_per_second_per_gpu:768.9612631004042
Step 2111 | loss:1.419592022895813 lr:4.82749369215695e-05 tokens_per_second_per_gpu:725.2454826015795
Step 2112 | loss:1.3144932985305786 lr:4.8256256563840235e-05 tokens_per_second_per_gpu:864.8165728922436
Step 2113 | loss:1.1746472120285034 lr:4.8237571796443065e-05 tokens_per_second_per_gpu:1044.9468970682435
Step 2114 | loss:1.3304417133331299 lr:4.8218882625593447e-05 tokens_per_second_per_gpu:1018.4680284608733
Step 2115 | loss:1.382201075553894 lr:4.820018905750829e-05 tokens_per_second_per_gpu:1013.5707284718594
Step 2116 | loss:1.4579328298568726 lr:4.8181491098405965e-05 tokens_per_second_per_gpu:932.7804878012226
Step 2117 | loss:1.3332428932189941 lr:4.816278875450634e-05 tokens_per_second_per_gpu:913.9988446310861
Step 2118 | loss:1.4612998962402344 lr:4.8144082032030676e-05 tokens_per_second_per_gpu:753.3583555581623
Step 2119 | loss:1.3211220502853394 lr:4.8125370937201756e-05 tokens_per_second_per_gpu:779.6949128474098
Step 2120 | loss:1.4737931489944458 lr:4.810665547624377e-05 tokens_per_second_per_gpu:654.9891975161829
Step 2121 | loss:1.418421745300293 lr:4.80879356553824e-05 tokens_per_second_per_gpu:986.4189542566564
Step 2122 | loss:1.3469295501708984 lr:4.806921148084474e-05 tokens_per_second_per_gpu:860.6811641597836
Step 2123 | loss:1.4546597003936768 lr:4.805048295885936e-05 tokens_per_second_per_gpu:792.3366515845123
Step 2124 | loss:1.2726706266403198 lr:4.803175009565627e-05 tokens_per_second_per_gpu:1072.8106519885105
Step 2125 | loss:1.3692704439163208 lr:4.801301289746691e-05 tokens_per_second_per_gpu:946.4878377473744
Step 2126 | loss:1.260880947113037 lr:4.799427137052418e-05 tokens_per_second_per_gpu:920.3274388743687
Step 2127 | loss:1.3750375509262085 lr:4.79755255210624e-05 tokens_per_second_per_gpu:1228.189059692843
Step 2128 | loss:1.3038393259048462 lr:4.7956775355317344e-05 tokens_per_second_per_gpu:871.96767792063
Step 2129 | loss:1.3787076473236084 lr:4.793802087952624e-05 tokens_per_second_per_gpu:1082.1499903895315
Step 2130 | loss:1.2600290775299072 lr:4.79192620999277e-05 tokens_per_second_per_gpu:1047.2530449768963
Step 2131 | loss:1.5083088874816895 lr:4.7900499022761805e-05 tokens_per_second_per_gpu:1017.1078353865894
Step 2132 | loss:1.4805114269256592 lr:4.788173165427006e-05 tokens_per_second_per_gpu:1067.5080165205193
Step 2133 | loss:1.3568545579910278 lr:4.786296000069539e-05 tokens_per_second_per_gpu:826.8087583010673
Step 2134 | loss:1.3407503366470337 lr:4.784418406828215e-05 tokens_per_second_per_gpu:1057.7600545337707
Step 2135 | loss:1.4171525239944458 lr:4.7825403863276125e-05 tokens_per_second_per_gpu:774.1211779486425
Step 2136 | loss:1.3070130348205566 lr:4.7806619391924506e-05 tokens_per_second_per_gpu:745.8400985514738
Step 2137 | loss:1.370403528213501 lr:4.77878306604759e-05 tokens_per_second_per_gpu:869.6965918759635
Step 2138 | loss:1.3640278577804565 lr:4.7769037675180354e-05 tokens_per_second_per_gpu:1074.2099494991505
Step 2139 | loss:1.3532253503799438 lr:4.775024044228932e-05 tokens_per_second_per_gpu:982.54542020406
Step 2140 | loss:1.3820821046829224 lr:4.773143896805566e-05 tokens_per_second_per_gpu:895.3555934760484
Step 2141 | loss:1.3287473917007446 lr:4.771263325873364e-05 tokens_per_second_per_gpu:1281.2665609483138
Step 2142 | loss:1.397413730621338 lr:4.7693823320578955e-05 tokens_per_second_per_gpu:844.4285763684339
Step 2143 | loss:1.3191707134246826 lr:4.767500915984869e-05 tokens_per_second_per_gpu:917.1329003508114
Step 2144 | loss:1.2449252605438232 lr:4.765619078280131e-05 tokens_per_second_per_gpu:1087.2151413086265
Step 2145 | loss:1.3699098825454712 lr:4.7637368195696755e-05 tokens_per_second_per_gpu:903.1947147145085
Step 2146 | loss:1.4359080791473389 lr:4.7618541404796304e-05 tokens_per_second_per_gpu:792.9129599648605
Step 2147 | loss:1.2271759510040283 lr:4.7599710416362655e-05 tokens_per_second_per_gpu:1147.4274478117675
Step 2148 | loss:1.427527904510498 lr:4.75808752366599e-05 tokens_per_second_per_gpu:586.3467228007835
Step 2149 | loss:1.3815264701843262 lr:4.7562035871953516e-05 tokens_per_second_per_gpu:845.8647770338736
Step 2150 | loss:1.328653335571289 lr:4.7543192328510386e-05 tokens_per_second_per_gpu:927.3220695671664
Step 2151 | loss:1.4159584045410156 lr:4.752434461259877e-05 tokens_per_second_per_gpu:820.9949426425885
Step 2152 | loss:1.470374584197998 lr:4.750549273048835e-05 tokens_per_second_per_gpu:1152.061576662869
Step 2153 | loss:1.340821623802185 lr:4.7486636688450143e-05 tokens_per_second_per_gpu:760.1250241694452
Step 2154 | loss:1.4621471166610718 lr:4.7467776492756586e-05 tokens_per_second_per_gpu:1031.8774523384886
Step 2155 | loss:1.4883097410202026 lr:4.744891214968148e-05 tokens_per_second_per_gpu:814.7284424733957
Step 2156 | loss:1.3854199647903442 lr:4.7430043665500006e-05 tokens_per_second_per_gpu:578.216610890868
Step 2157 | loss:1.249372124671936 lr:4.741117104648874e-05 tokens_per_second_per_gpu:1024.2591242442452
Step 2158 | loss:1.4296358823776245 lr:4.7392294298925625e-05 tokens_per_second_per_gpu:1041.9064321966862
Step 2159 | loss:1.3235301971435547 lr:4.737341342908997e-05 tokens_per_second_per_gpu:864.3510139778919
Step 2160 | loss:1.4060972929000854 lr:4.735452844326245e-05 tokens_per_second_per_gpu:788.342612167147
Step 2161 | loss:1.345934510231018 lr:4.733563934772513e-05 tokens_per_second_per_gpu:823.0791056325048
Step 2162 | loss:1.2673265933990479 lr:4.731674614876143e-05 tokens_per_second_per_gpu:869.199744452228
Step 2163 | loss:1.3937430381774902 lr:4.7297848852656126e-05 tokens_per_second_per_gpu:834.9905877132368
Step 2164 | loss:1.304653286933899 lr:4.727894746569538e-05 tokens_per_second_per_gpu:867.3287378898104
Step 2165 | loss:1.3344004154205322 lr:4.7260041994166694e-05 tokens_per_second_per_gpu:1059.5611374901089
Step 2166 | loss:1.361536979675293 lr:4.724113244435894e-05 tokens_per_second_per_gpu:979.3728099050951
Step 2167 | loss:1.356931447982788 lr:4.722221882256234e-05 tokens_per_second_per_gpu:1124.6917729639786
Step 2168 | loss:1.4415099620819092 lr:4.720330113506847e-05 tokens_per_second_per_gpu:890.6099491105541
Step 2169 | loss:1.368404746055603 lr:4.718437938817026e-05 tokens_per_second_per_gpu:861.131148101636
Step 2170 | loss:1.4790303707122803 lr:4.716545358816201e-05 tokens_per_second_per_gpu:679.6048900095857
Step 2171 | loss:1.2966197729110718 lr:4.714652374133933e-05 tokens_per_second_per_gpu:795.98073363516
Step 2172 | loss:1.4209403991699219 lr:4.712758985399921e-05 tokens_per_second_per_gpu:838.3690311486856
Step 2173 | loss:1.3871527910232544 lr:4.710865193243997e-05 tokens_per_second_per_gpu:966.1915092796379
Step 2174 | loss:1.4568041563034058 lr:4.7089709982961266e-05 tokens_per_second_per_gpu:829.9627324355428
Step 2175 | loss:1.5520217418670654 lr:4.707076401186409e-05 tokens_per_second_per_gpu:655.2840589431312
Step 2176 | loss:1.458883285522461 lr:4.705181402545081e-05 tokens_per_second_per_gpu:719.0868423803704
Step 2177 | loss:1.3830472230911255 lr:4.703286003002509e-05 tokens_per_second_per_gpu:933.5089665995873
Step 2178 | loss:1.2605043649673462 lr:4.701390203189193e-05 tokens_per_second_per_gpu:987.715307375425
Step 2179 | loss:1.237850308418274 lr:4.699494003735767e-05 tokens_per_second_per_gpu:1033.9167562717696
Step 2180 | loss:1.3853791952133179 lr:4.6975974052730004e-05 tokens_per_second_per_gpu:988.486656734048
Step 2181 | loss:1.3002879619598389 lr:4.695700408431791e-05 tokens_per_second_per_gpu:936.3866783356932
Step 2182 | loss:1.3068264722824097 lr:4.6938030138431705e-05 tokens_per_second_per_gpu:1053.937727396232
Step 2183 | loss:1.425322413444519 lr:4.691905222138306e-05 tokens_per_second_per_gpu:821.6028174467217
Step 2184 | loss:1.4686846733093262 lr:4.690007033948492e-05 tokens_per_second_per_gpu:785.4150606389743
Step 2185 | loss:1.3058480024337769 lr:4.6881084499051576e-05 tokens_per_second_per_gpu:1083.3000890709945
Step 2186 | loss:1.3807563781738281 lr:4.686209470639864e-05 tokens_per_second_per_gpu:985.3801484131291
Step 2187 | loss:1.4690954685211182 lr:4.6843100967843026e-05 tokens_per_second_per_gpu:772.864060581839
Step 2188 | loss:1.3810862302780151 lr:4.682410328970295e-05 tokens_per_second_per_gpu:982.7203418751858
Step 2189 | loss:1.316838264465332 lr:4.680510167829797e-05 tokens_per_second_per_gpu:802.8491235200802
Step 2190 | loss:1.491682529449463 lr:4.678609613994893e-05 tokens_per_second_per_gpu:999.0674114091754
Step 2191 | loss:1.417432188987732 lr:4.676708668097799e-05 tokens_per_second_per_gpu:946.9089039265812
Step 2192 | loss:1.4562897682189941 lr:4.67480733077086e-05 tokens_per_second_per_gpu:763.168917476645
Step 2193 | loss:1.2957650423049927 lr:4.672905602646552e-05 tokens_per_second_per_gpu:1025.6672986698272
Step 2194 | loss:1.4334871768951416 lr:4.671003484357481e-05 tokens_per_second_per_gpu:861.5127569410361
Step 2195 | loss:1.3497568368911743 lr:4.669100976536385e-05 tokens_per_second_per_gpu:1107.5254160461498
Step 2196 | loss:1.5141335725784302 lr:4.6671980798161276e-05 tokens_per_second_per_gpu:645.9498601242898
Step 2197 | loss:1.491092324256897 lr:4.665294794829704e-05 tokens_per_second_per_gpu:741.0229673330152
Step 2198 | loss:1.1951433420181274 lr:4.6633911222102384e-05 tokens_per_second_per_gpu:1202.4179633058739
Step 2199 | loss:1.3577114343643188 lr:4.6614870625909844e-05 tokens_per_second_per_gpu:920.195977623784
Step 2200 | loss:1.4959895610809326 lr:4.659582616605322e-05 tokens_per_second_per_gpu:989.1449049191899
Step 2201 | loss:1.3512701988220215 lr:4.6576777848867636e-05 tokens_per_second_per_gpu:923.3980355062477
Step 2202 | loss:1.2619452476501465 lr:4.6557725680689464e-05 tokens_per_second_per_gpu:1146.9598990321435
Step 2203 | loss:1.3122661113739014 lr:4.653866966785638e-05 tokens_per_second_per_gpu:923.0055275927967
Step 2204 | loss:1.446866512298584 lr:4.651960981670732e-05 tokens_per_second_per_gpu:721.0706358897748
Step 2205 | loss:1.3219605684280396 lr:4.650054613358251e-05 tokens_per_second_per_gpu:756.8083575164637
Step 2206 | loss:1.2122796773910522 lr:4.6481478624823434e-05 tokens_per_second_per_gpu:1062.0441544775265
Step 2207 | loss:1.328419804573059 lr:4.64624072967729e-05 tokens_per_second_per_gpu:1053.2331462115703
Step 2208 | loss:1.5468170642852783 lr:4.64433321557749e-05 tokens_per_second_per_gpu:923.7744087966176
Step 2209 | loss:1.3262816667556763 lr:4.6424253208174786e-05 tokens_per_second_per_gpu:940.4164300620499
Step 2210 | loss:1.3989007472991943 lr:4.64051704603191e-05 tokens_per_second_per_gpu:793.4095353917855
Step 2211 | loss:1.4487063884735107 lr:4.638608391855569e-05 tokens_per_second_per_gpu:859.9021418992937
Step 2212 | loss:1.3297683000564575 lr:4.636699358923366e-05 tokens_per_second_per_gpu:1057.3401447695403
Step 2213 | loss:1.352120041847229 lr:4.6347899478703375e-05 tokens_per_second_per_gpu:718.0512793194899
Step 2214 | loss:1.4705005884170532 lr:4.632880159331645e-05 tokens_per_second_per_gpu:936.2714636133227
Step 2215 | loss:1.3045196533203125 lr:4.6309699939425755e-05 tokens_per_second_per_gpu:801.2708322401903
Step 2216 | loss:1.3970462083816528 lr:4.629059452338542e-05 tokens_per_second_per_gpu:932.1291125790236
Step 2217 | loss:1.4380496740341187 lr:4.627148535155084e-05 tokens_per_second_per_gpu:745.2249563733193
Step 2218 | loss:1.4321486949920654 lr:4.62523724302786e-05 tokens_per_second_per_gpu:926.2152464979026
Step 2219 | loss:1.2579115629196167 lr:4.6233255765926636e-05 tokens_per_second_per_gpu:970.2753055934079
Step 2220 | loss:1.4037504196166992 lr:4.6214135364854025e-05 tokens_per_second_per_gpu:900.0133700274121
Step 2221 | loss:1.300761103630066 lr:4.6195011233421156e-05 tokens_per_second_per_gpu:1108.9338139971799
Step 2222 | loss:1.4105981588363647 lr:4.617588337798961e-05 tokens_per_second_per_gpu:947.0773980668002
Step 2223 | loss:1.202515721321106 lr:4.615675180492225e-05 tokens_per_second_per_gpu:1242.0287059780824
Step 2224 | loss:1.3482977151870728 lr:4.613761652058316e-05 tokens_per_second_per_gpu:699.3984824757342
Step 2225 | loss:1.2507376670837402 lr:4.611847753133762e-05 tokens_per_second_per_gpu:998.9984198149261
Step 2226 | loss:1.2973747253417969 lr:4.6099334843552225e-05 tokens_per_second_per_gpu:1297.9827230732194
Step 2227 | loss:1.3310118913650513 lr:4.608018846359472e-05 tokens_per_second_per_gpu:991.8607682764059
Step 2228 | loss:1.3197516202926636 lr:4.6061038397834125e-05 tokens_per_second_per_gpu:998.2045976658248
Step 2229 | loss:1.4113012552261353 lr:4.604188465264067e-05 tokens_per_second_per_gpu:1036.08991418525
Step 2230 | loss:1.355202555656433 lr:4.602272723438581e-05 tokens_per_second_per_gpu:841.7690287089279
Step 2231 | loss:1.373995304107666 lr:4.600356614944221e-05 tokens_per_second_per_gpu:954.9503023485014
Step 2232 | loss:1.4262064695358276 lr:4.598440140418379e-05 tokens_per_second_per_gpu:938.6166306126192
Step 2233 | loss:1.483078122138977 lr:4.596523300498566e-05 tokens_per_second_per_gpu:610.9411678496186
Step 2234 | loss:1.310582160949707 lr:4.5946060958224136e-05 tokens_per_second_per_gpu:1045.6742134655078
Step 2235 | loss:1.5031765699386597 lr:4.5926885270276776e-05 tokens_per_second_per_gpu:905.9351656060616
Step 2236 | loss:1.5720973014831543 lr:4.5907705947522335e-05 tokens_per_second_per_gpu:1043.7416043302228
Step 2237 | loss:1.429440975189209 lr:4.5888522996340766e-05 tokens_per_second_per_gpu:618.6209843366843
Step 2238 | loss:1.4630835056304932 lr:4.5869336423113255e-05 tokens_per_second_per_gpu:975.3481592266819
Step 2239 | loss:1.5534337759017944 lr:4.585014623422217e-05 tokens_per_second_per_gpu:740.4012455837631
Step 2240 | loss:1.4096490144729614 lr:4.583095243605109e-05 tokens_per_second_per_gpu:931.2279397580194
Step 2241 | loss:1.3994301557540894 lr:4.5811755034984796e-05 tokens_per_second_per_gpu:896.0321868092753
Step 2242 | loss:1.4664371013641357 lr:4.579255403740925e-05 tokens_per_second_per_gpu:817.0369333379497
Step 2243 | loss:1.3760533332824707 lr:4.5773349449711664e-05 tokens_per_second_per_gpu:1105.5934529753563
Step 2244 | loss:1.4623011350631714 lr:4.575414127828037e-05 tokens_per_second_per_gpu:1047.199167566511
Step 2245 | loss:1.4278745651245117 lr:4.573492952950495e-05 tokens_per_second_per_gpu:1122.6988403761172
Step 2246 | loss:1.4528648853302002 lr:4.571571420977614e-05 tokens_per_second_per_gpu:730.349705496159
Step 2247 | loss:1.4204528331756592 lr:4.569649532548589e-05 tokens_per_second_per_gpu:683.6120097151005
Step 2248 | loss:1.244286060333252 lr:4.5677272883027335e-05 tokens_per_second_per_gpu:969.3184201091143
Step 2249 | loss:1.3148317337036133 lr:4.565804688879475e-05 tokens_per_second_per_gpu:991.0575300395785
Step 2250 | loss:1.4961758852005005 lr:4.5638817349183655e-05 tokens_per_second_per_gpu:784.7562359319918
Step 2251 | loss:1.374563455581665 lr:4.561958427059071e-05 tokens_per_second_per_gpu:1071.0660479498765
Step 2252 | loss:1.339327096939087 lr:4.560034765941375e-05 tokens_per_second_per_gpu:1066.0604503474167
Step 2253 | loss:1.2035874128341675 lr:4.558110752205181e-05 tokens_per_second_per_gpu:948.8041372570933
Step 2254 | loss:1.2367680072784424 lr:4.556186386490508e-05 tokens_per_second_per_gpu:1044.1542338962722
Step 2255 | loss:1.734541416168213 lr:4.5542616694374913e-05 tokens_per_second_per_gpu:688.20589120959
Step 2256 | loss:1.383890151977539 lr:4.5523366016863856e-05 tokens_per_second_per_gpu:838.0505957659959
Step 2257 | loss:1.2594478130340576 lr:4.5504111838775616e-05 tokens_per_second_per_gpu:1053.713012199032
Step 2258 | loss:1.2419761419296265 lr:4.5484854166515046e-05 tokens_per_second_per_gpu:1251.7439769872244
Step 2259 | loss:1.5078428983688354 lr:4.546559300648817e-05 tokens_per_second_per_gpu:471.01763991077
Step 2260 | loss:1.4440401792526245 lr:4.544632836510219e-05 tokens_per_second_per_gpu:666.9030739422453
Step 2261 | loss:1.3910114765167236 lr:4.542706024876544e-05 tokens_per_second_per_gpu:1032.467126075819
Step 2262 | loss:1.370592474937439 lr:4.540778866388742e-05 tokens_per_second_per_gpu:799.284950284218
Step 2263 | loss:1.3563436269760132 lr:4.5388513616878784e-05 tokens_per_second_per_gpu:1028.8935777093775
Step 2264 | loss:1.4350159168243408 lr:4.536923511415136e-05 tokens_per_second_per_gpu:1147.13481018348
Step 2265 | loss:1.4363282918930054 lr:4.534995316211808e-05 tokens_per_second_per_gpu:774.251081642014
Step 2266 | loss:1.3663581609725952 lr:4.533066776719306e-05 tokens_per_second_per_gpu:713.4506484086343
Step 2267 | loss:1.200542688369751 lr:4.531137893579154e-05 tokens_per_second_per_gpu:1090.4558851979364
Step 2268 | loss:1.351564884185791 lr:4.529208667432991e-05 tokens_per_second_per_gpu:1094.3404581252173
Step 2269 | loss:1.3732059001922607 lr:4.527279098922572e-05 tokens_per_second_per_gpu:998.0989896358057
Step 2270 | loss:1.473535180091858 lr:4.5253491886897636e-05 tokens_per_second_per_gpu:694.134205670996
Step 2271 | loss:1.4430618286132812 lr:4.523418937376545e-05 tokens_per_second_per_gpu:816.8872268110862
Step 2272 | loss:1.5096654891967773 lr:4.5214883456250136e-05 tokens_per_second_per_gpu:621.6815278435793
Step 2273 | loss:1.3091559410095215 lr:4.519557414077374e-05 tokens_per_second_per_gpu:781.5418517193879
Step 2274 | loss:1.3811287879943848 lr:4.5176261433759484e-05 tokens_per_second_per_gpu:856.4698617444833
Step 2275 | loss:1.3571213483810425 lr:4.51569453416317e-05 tokens_per_second_per_gpu:798.045116452863
Step 2276 | loss:1.3473787307739258 lr:4.5137625870815845e-05 tokens_per_second_per_gpu:756.9203053466997
Step 2277 | loss:1.432120680809021 lr:4.511830302773852e-05 tokens_per_second_per_gpu:783.0959130708959
Step 2278 | loss:1.3912302255630493 lr:4.50989768188274e-05 tokens_per_second_per_gpu:918.2010471300771
Step 2279 | loss:1.5217902660369873 lr:4.5079647250511325e-05 tokens_per_second_per_gpu:584.3360336915002
Step 2280 | loss:1.4869472980499268 lr:4.506031432922025e-05 tokens_per_second_per_gpu:768.6263597201961
Step 2281 | loss:1.3956691026687622 lr:4.504097806138522e-05 tokens_per_second_per_gpu:822.396344459254
Step 2282 | loss:1.3638737201690674 lr:4.5021638453438414e-05 tokens_per_second_per_gpu:904.3131156438628
Step 2283 | loss:1.4136128425598145 lr:4.500229551181311e-05 tokens_per_second_per_gpu:826.2808013457942
Step 2284 | loss:1.4146676063537598 lr:4.498294924294371e-05 tokens_per_second_per_gpu:895.5380051453185
Step 2285 | loss:1.3487250804901123 lr:4.496359965326569e-05 tokens_per_second_per_gpu:759.673745213043
Step 2286 | loss:1.3168967962265015 lr:4.494424674921567e-05 tokens_per_second_per_gpu:889.1106784789688
Step 2287 | loss:1.4213333129882812 lr:4.492489053723136e-05 tokens_per_second_per_gpu:770.9699353589863
Step 2288 | loss:1.3878540992736816 lr:4.490553102375156e-05 tokens_per_second_per_gpu:1044.3085201849824
Step 2289 | loss:1.3731834888458252 lr:4.4886168215216174e-05 tokens_per_second_per_gpu:926.8500943477014
Step 2290 | loss:1.359366536140442 lr:4.48668021180662e-05 tokens_per_second_per_gpu:855.4552203318835
Step 2291 | loss:1.3658910989761353 lr:4.484743273874375e-05 tokens_per_second_per_gpu:678.933833299659
Step 2292 | loss:1.352139949798584 lr:4.4828060083691974e-05 tokens_per_second_per_gpu:1043.9156510229539
Step 2293 | loss:1.244815468788147 lr:4.4808684159355174e-05 tokens_per_second_per_gpu:1004.6591519658748
Step 2294 | loss:1.3120476007461548 lr:4.478930497217871e-05 tokens_per_second_per_gpu:884.2202609329718
Step 2295 | loss:1.3973324298858643 lr:4.476992252860903e-05 tokens_per_second_per_gpu:642.541767625152
Step 2296 | loss:1.3884916305541992 lr:4.475053683509367e-05 tokens_per_second_per_gpu:961.4220807842136
Step 2297 | loss:1.4550946950912476 lr:4.473114789808124e-05 tokens_per_second_per_gpu:939.5075140155686
Step 2298 | loss:1.4687074422836304 lr:4.471175572402143e-05 tokens_per_second_per_gpu:1049.366322649818
Step 2299 | loss:1.583827018737793 lr:4.4692360319364994e-05 tokens_per_second_per_gpu:708.9395377118356
Step 2300 | loss:1.371145486831665 lr:4.4672961690563814e-05 tokens_per_second_per_gpu:885.4172682207528
Step 2301 | loss:1.4084393978118896 lr:4.465355984407077e-05 tokens_per_second_per_gpu:1077.9379954434714
Step 2302 | loss:1.3486812114715576 lr:4.4634154786339866e-05 tokens_per_second_per_gpu:902.7801824352008
Step 2303 | loss:1.359327793121338 lr:4.461474652382615e-05 tokens_per_second_per_gpu:1097.283347175834
Step 2304 | loss:1.4217755794525146 lr:4.459533506298575e-05 tokens_per_second_per_gpu:730.034281176288
Step 2305 | loss:1.5200653076171875 lr:4.457592041027585e-05 tokens_per_second_per_gpu:743.402068032036
Step 2306 | loss:1.2937321662902832 lr:4.455650257215468e-05 tokens_per_second_per_gpu:926.8788929870143
Step 2307 | loss:1.3625737428665161 lr:4.453708155508156e-05 tokens_per_second_per_gpu:965.7592529189337
Step 2308 | loss:1.382940649986267 lr:4.451765736551686e-05 tokens_per_second_per_gpu:936.6106151284197
Step 2309 | loss:1.3765857219696045 lr:4.449823000992198e-05 tokens_per_second_per_gpu:853.7623843151954
Step 2310 | loss:1.3381757736206055 lr:4.447879949475941e-05 tokens_per_second_per_gpu:986.4782573033109
Step 2311 | loss:1.2902312278747559 lr:4.4459365826492663e-05 tokens_per_second_per_gpu:929.7869221419331
Step 2312 | loss:1.3711669445037842 lr:4.4439929011586313e-05 tokens_per_second_per_gpu:1143.33774866878
Step 2313 | loss:1.408919334411621 lr:4.4420489056505984e-05 tokens_per_second_per_gpu:656.3675065114136
Step 2314 | loss:1.4343019723892212 lr:4.4401045967718324e-05 tokens_per_second_per_gpu:731.5562527923951
Step 2315 | loss:1.2847874164581299 lr:4.438159975169106e-05 tokens_per_second_per_gpu:930.0686722698182
Step 2316 | loss:1.4370787143707275 lr:4.4362150414892916e-05 tokens_per_second_per_gpu:797.3189741182431
Step 2317 | loss:1.5232930183410645 lr:4.4342697963793684e-05 tokens_per_second_per_gpu:738.7594412519372
Step 2318 | loss:1.3479820489883423 lr:4.43232424048642e-05 tokens_per_second_per_gpu:1027.0552093720894
Step 2319 | loss:1.4096397161483765 lr:4.43037837445763e-05 tokens_per_second_per_gpu:897.723802547301
Step 2320 | loss:1.3762133121490479 lr:4.428432198940288e-05 tokens_per_second_per_gpu:1033.4639104637442
Step 2321 | loss:1.394327163696289 lr:4.426485714581783e-05 tokens_per_second_per_gpu:792.2307818904096
Step 2322 | loss:1.407347559928894 lr:4.424538922029613e-05 tokens_per_second_per_gpu:727.5422696350881
Step 2323 | loss:1.3203562498092651 lr:4.4225918219313705e-05 tokens_per_second_per_gpu:1153.1503038219946
Step 2324 | loss:1.2314212322235107 lr:4.420644414934759e-05 tokens_per_second_per_gpu:1025.258909103779
Step 2325 | loss:1.3689022064208984 lr:4.418696701687576e-05 tokens_per_second_per_gpu:844.7126422773241
Step 2326 | loss:1.4060431718826294 lr:4.416748682837727e-05 tokens_per_second_per_gpu:812.3952484532226
Step 2327 | loss:1.5425059795379639 lr:4.414800359033216e-05 tokens_per_second_per_gpu:753.9037261218036
Step 2328 | loss:1.5038493871688843 lr:4.412851730922148e-05 tokens_per_second_per_gpu:780.0674949091307
Step 2329 | loss:1.3840880393981934 lr:4.410902799152731e-05 tokens_per_second_per_gpu:765.3807385263359
Step 2330 | loss:1.329350233078003 lr:4.4089535643732735e-05 tokens_per_second_per_gpu:852.9299707432366
Step 2331 | loss:1.2832564115524292 lr:4.407004027232186e-05 tokens_per_second_per_gpu:807.1604325820704
Step 2332 | loss:1.41408371925354 lr:4.405054188377976e-05 tokens_per_second_per_gpu:947.824460148248
Step 2333 | loss:1.4995973110198975 lr:4.4031040484592545e-05 tokens_per_second_per_gpu:956.8192795290462
Step 2334 | loss:1.530217170715332 lr:4.401153608124732e-05 tokens_per_second_per_gpu:782.352808389175
Step 2335 | loss:1.2904919385910034 lr:4.399202868023219e-05 tokens_per_second_per_gpu:985.4587864629594
Step 2336 | loss:1.4242615699768066 lr:4.3972518288036226e-05 tokens_per_second_per_gpu:628.4432024569186
Step 2337 | loss:1.5465576648712158 lr:4.3953004911149555e-05 tokens_per_second_per_gpu:830.5299760830823
Step 2338 | loss:1.393799066543579 lr:4.3933488556063255e-05 tokens_per_second_per_gpu:581.1235196422356
Step 2339 | loss:1.3762117624282837 lr:4.3913969229269405e-05 tokens_per_second_per_gpu:1299.5705173491476
Step 2340 | loss:1.2557615041732788 lr:4.389444693726107e-05 tokens_per_second_per_gpu:987.523496499794
Step 2341 | loss:1.421260118484497 lr:4.387492168653229e-05 tokens_per_second_per_gpu:891.4935347766585
Step 2342 | loss:1.498110055923462 lr:4.385539348357811e-05 tokens_per_second_per_gpu:962.8224687488835
Step 2343 | loss:1.483972430229187 lr:4.383586233489455e-05 tokens_per_second_per_gpu:863.3857523955386
Step 2344 | loss:1.3771941661834717 lr:4.381632824697862e-05 tokens_per_second_per_gpu:947.165970988273
Step 2345 | loss:1.2869694232940674 lr:4.379679122632827e-05 tokens_per_second_per_gpu:1075.0543172006537
Step 2346 | loss:1.3125907182693481 lr:4.3777251279442476e-05 tokens_per_second_per_gpu:1015.1308956894842
Step 2347 | loss:1.364055871963501 lr:4.375770841282115e-05 tokens_per_second_per_gpu:787.9716543158473
Step 2348 | loss:1.445378065109253 lr:4.3738162632965194e-05 tokens_per_second_per_gpu:764.477544487277
Step 2349 | loss:1.2351871728897095 lr:4.371861394637647e-05 tokens_per_second_per_gpu:962.4673636320052
Step 2350 | loss:1.310762882232666 lr:4.369906235955781e-05 tokens_per_second_per_gpu:868.4005616029173
Step 2351 | loss:1.2629258632659912 lr:4.3679507879013015e-05 tokens_per_second_per_gpu:1080.6114994319444
Step 2352 | loss:1.456302285194397 lr:4.365995051124685e-05 tokens_per_second_per_gpu:742.2235391867454
Step 2353 | loss:1.3339595794677734 lr:4.3640390262765025e-05 tokens_per_second_per_gpu:714.8950514522761
Step 2354 | loss:1.429652214050293 lr:4.362082714007422e-05 tokens_per_second_per_gpu:600.5874702467958
Step 2355 | loss:1.4164314270019531 lr:4.3601261149682064e-05 tokens_per_second_per_gpu:742.7556887622528
Step 2356 | loss:1.4505091905593872 lr:4.358169229809717e-05 tokens_per_second_per_gpu:702.0417046102029
Step 2357 | loss:1.4185395240783691 lr:4.356212059182905e-05 tokens_per_second_per_gpu:768.9358158032147
Step 2358 | loss:1.5339924097061157 lr:4.3542546037388215e-05 tokens_per_second_per_gpu:574.6621223013505
Step 2359 | loss:1.4311310052871704 lr:4.3522968641286085e-05 tokens_per_second_per_gpu:960.4995151571298
Step 2360 | loss:1.2767497301101685 lr:4.3503388410035044e-05 tokens_per_second_per_gpu:1186.2761268331392
Step 2361 | loss:1.279551386833191 lr:4.348380535014843e-05 tokens_per_second_per_gpu:903.9378181267007
Step 2362 | loss:1.4780433177947998 lr:4.346421946814051e-05 tokens_per_second_per_gpu:957.5665327111237
Step 2363 | loss:1.3621172904968262 lr:4.344463077052648e-05 tokens_per_second_per_gpu:732.4362217639007
Step 2364 | loss:1.4345301389694214 lr:4.342503926382249e-05 tokens_per_second_per_gpu:964.5966527320097
Step 2365 | loss:1.2549426555633545 lr:4.34054449545456e-05 tokens_per_second_per_gpu:1026.39024835751
Step 2366 | loss:1.340080976486206 lr:4.338584784921385e-05 tokens_per_second_per_gpu:847.8175657221493
Step 2367 | loss:1.321789026260376 lr:4.336624795434615e-05 tokens_per_second_per_gpu:1185.9584126498437
Step 2368 | loss:1.5474976301193237 lr:4.334664527646237e-05 tokens_per_second_per_gpu:820.849837456077
Step 2369 | loss:1.5251505374908447 lr:4.332703982208332e-05 tokens_per_second_per_gpu:865.2992392916166
Step 2370 | loss:1.427056908607483 lr:4.33074315977307e-05 tokens_per_second_per_gpu:775.7165805699664
Step 2371 | loss:1.4510424137115479 lr:4.328782060992715e-05 tokens_per_second_per_gpu:766.7424384916449
Step 2372 | loss:1.2999296188354492 lr:4.326820686519623e-05 tokens_per_second_per_gpu:857.7752147516817
Step 2373 | loss:1.5905004739761353 lr:4.324859037006242e-05 tokens_per_second_per_gpu:747.3612524036948
Step 2374 | loss:1.5012567043304443 lr:4.32289711310511e-05 tokens_per_second_per_gpu:720.1142814144013
Step 2375 | loss:1.4680726528167725 lr:4.320934915468857e-05 tokens_per_second_per_gpu:710.9412693454116
Step 2376 | loss:1.1663275957107544 lr:4.318972444750205e-05 tokens_per_second_per_gpu:1002.370711288122
Step 2377 | loss:1.249560832977295 lr:4.3170097016019663e-05 tokens_per_second_per_gpu:869.150391525406
Step 2378 | loss:1.2546395063400269 lr:4.315046686677043e-05 tokens_per_second_per_gpu:986.2392861994139
Step 2379 | loss:1.4298957586288452 lr:4.313083400628426e-05 tokens_per_second_per_gpu:715.6613638977013
Step 2380 | loss:1.3847836256027222 lr:4.3111198441092024e-05 tokens_per_second_per_gpu:853.0017589128105
Step 2381 | loss:1.294724941253662 lr:4.309156017772544e-05 tokens_per_second_per_gpu:889.4293414719283
Step 2382 | loss:1.2697588205337524 lr:4.307191922271714e-05 tokens_per_second_per_gpu:722.9052793759317
Step 2383 | loss:1.4753592014312744 lr:4.305227558260064e-05 tokens_per_second_per_gpu:1020.339008622691
Step 2384 | loss:1.5139756202697754 lr:4.303262926391036e-05 tokens_per_second_per_gpu:842.1065088172164
Step 2385 | loss:1.2995401620864868 lr:4.3012980273181605e-05 tokens_per_second_per_gpu:967.9488208084317
Step 2386 | loss:1.4725338220596313 lr:4.2993328616950586e-05 tokens_per_second_per_gpu:744.6758590856715
Step 2387 | loss:1.4237064123153687 lr:4.2973674301754404e-05 tokens_per_second_per_gpu:941.8847533875459
Step 2388 | loss:1.3681167364120483 lr:4.295401733413099e-05 tokens_per_second_per_gpu:808.363069823316
Step 2389 | loss:1.4305055141448975 lr:4.2934357720619225e-05 tokens_per_second_per_gpu:848.3135710968785
Step 2390 | loss:1.3220356702804565 lr:4.291469546775883e-05 tokens_per_second_per_gpu:1241.6111727499103
Step 2391 | loss:1.3737783432006836 lr:4.28950305820904e-05 tokens_per_second_per_gpu:1018.2627309644101
Step 2392 | loss:1.4599049091339111 lr:4.2875363070155455e-05 tokens_per_second_per_gpu:826.1209277940095
Step 2393 | loss:1.3439608812332153 lr:4.285569293849633e-05 tokens_per_second_per_gpu:1108.637482707934
Step 2394 | loss:1.1064443588256836 lr:4.283602019365627e-05 tokens_per_second_per_gpu:1268.6690856503474
Step 2395 | loss:1.1872766017913818 lr:4.281634484217936e-05 tokens_per_second_per_gpu:1053.9896678926289
Step 2396 | loss:1.2869783639907837 lr:4.279666689061058e-05 tokens_per_second_per_gpu:929.3074782775471
Step 2397 | loss:1.5203825235366821 lr:4.277698634549574e-05 tokens_per_second_per_gpu:699.9932567866713
Step 2398 | loss:1.3044811487197876 lr:4.2757303213381565e-05 tokens_per_second_per_gpu:861.3414108329897
Step 2399 | loss:1.508851408958435 lr:4.2737617500815605e-05 tokens_per_second_per_gpu:735.9280849385913
Step 2400 | loss:1.281383752822876 lr:4.2717929214346254e-05 tokens_per_second_per_gpu:1053.6217249635718
Step 2401 | loss:1.5748013257980347 lr:4.2698238360522804e-05 tokens_per_second_per_gpu:739.6733531490422
Step 2402 | loss:1.3006808757781982 lr:4.267854494589537e-05 tokens_per_second_per_gpu:982.7256194521419
Step 2403 | loss:1.507541298866272 lr:4.265884897701493e-05 tokens_per_second_per_gpu:736.3439071249279
Step 2404 | loss:1.1522634029388428 lr:4.2639150460433286e-05 tokens_per_second_per_gpu:1215.0209774000177
Step 2405 | loss:1.3939648866653442 lr:4.261944940270315e-05 tokens_per_second_per_gpu:938.3152041835118
Step 2406 | loss:1.251791000366211 lr:4.2599745810378025e-05 tokens_per_second_per_gpu:1000.3445545730533
Step 2407 | loss:1.2616426944732666 lr:4.2580039690012265e-05 tokens_per_second_per_gpu:863.0086458669596
Step 2408 | loss:1.2207505702972412 lr:4.256033104816108e-05 tokens_per_second_per_gpu:929.3850094930903
Step 2409 | loss:1.2228981256484985 lr:4.254061989138051e-05 tokens_per_second_per_gpu:1034.408454634095
Step 2410 | loss:1.3793506622314453 lr:4.252090622622743e-05 tokens_per_second_per_gpu:907.9383979654285
Step 2411 | loss:1.380271315574646 lr:4.2501190059259555e-05 tokens_per_second_per_gpu:1021.0502947678252
Step 2412 | loss:1.3934454917907715 lr:4.248147139703543e-05 tokens_per_second_per_gpu:980.1679963351402
Step 2413 | loss:1.4451427459716797 lr:4.2461750246114426e-05 tokens_per_second_per_gpu:966.1521235633131
Step 2414 | loss:1.3178911209106445 lr:4.2442026613056754e-05 tokens_per_second_per_gpu:966.2118011345717
Step 2415 | loss:1.4472901821136475 lr:4.242230050442344e-05 tokens_per_second_per_gpu:578.0705826055741
Step 2416 | loss:1.3329299688339233 lr:4.2402571926776315e-05 tokens_per_second_per_gpu:1011.1641324315823
Step 2417 | loss:1.446144461631775 lr:4.238284088667808e-05 tokens_per_second_per_gpu:964.935954162905
Step 2418 | loss:1.4267430305480957 lr:4.236310739069222e-05 tokens_per_second_per_gpu:745.3837080634755
Step 2419 | loss:1.4210087060928345 lr:4.234337144538303e-05 tokens_per_second_per_gpu:834.2334061840008
Step 2420 | loss:1.23905611038208 lr:4.232363305731564e-05 tokens_per_second_per_gpu:1038.8872090399036
Step 2421 | loss:1.5488611459732056 lr:4.2303892233056004e-05 tokens_per_second_per_gpu:698.1564978983115
Step 2422 | loss:1.3384946584701538 lr:4.228414897917085e-05 tokens_per_second_per_gpu:766.1993527318
Step 2423 | loss:1.3269234895706177 lr:4.2264403302227735e-05 tokens_per_second_per_gpu:1235.4098970672972
Step 2424 | loss:1.4083075523376465 lr:4.224465520879501e-05 tokens_per_second_per_gpu:1056.9732197679373
Step 2425 | loss:1.3797202110290527 lr:4.222490470544187e-05 tokens_per_second_per_gpu:922.86178663546
Step 2426 | loss:1.3996267318725586 lr:4.220515179873826e-05 tokens_per_second_per_gpu:828.9124649354316
Step 2427 | loss:1.2927653789520264 lr:4.218539649525495e-05 tokens_per_second_per_gpu:925.0869903955155
Step 2428 | loss:1.467900037765503 lr:4.21656388015635e-05 tokens_per_second_per_gpu:1084.5724157754491
Step 2429 | loss:1.4702684879302979 lr:4.214587872423626e-05 tokens_per_second_per_gpu:782.7782852314956
Step 2430 | loss:1.277693271636963 lr:4.2126116269846415e-05 tokens_per_second_per_gpu:1026.1088247707878
Step 2431 | loss:1.4437952041625977 lr:4.2106351444967874e-05 tokens_per_second_per_gpu:547.7811200704944
Step 2432 | loss:1.2590967416763306 lr:4.208658425617537e-05 tokens_per_second_per_gpu:991.0839367454115
Step 2433 | loss:1.6604557037353516 lr:4.2066814710044437e-05 tokens_per_second_per_gpu:599.078949304816
Step 2434 | loss:1.374800205230713 lr:4.2047042813151345e-05 tokens_per_second_per_gpu:751.077827967606
Step 2435 | loss:1.5204522609710693 lr:4.202726857207323e-05 tokens_per_second_per_gpu:660.7144490651548
Step 2436 | loss:1.3705220222473145 lr:4.2007491993387904e-05 tokens_per_second_per_gpu:849.9067815467698
Step 2437 | loss:1.5463786125183105 lr:4.198771308367403e-05 tokens_per_second_per_gpu:594.7928797750031
Step 2438 | loss:1.3986546993255615 lr:4.196793184951102e-05 tokens_per_second_per_gpu:641.8880728953791
Step 2439 | loss:1.5366790294647217 lr:4.194814829747906e-05 tokens_per_second_per_gpu:791.2974527072282
Step 2440 | loss:1.2160148620605469 lr:4.1928362434159123e-05 tokens_per_second_per_gpu:1037.6333254272022
Step 2441 | loss:1.5055744647979736 lr:4.190857426613291e-05 tokens_per_second_per_gpu:861.9010027898065
Step 2442 | loss:1.4270029067993164 lr:4.188878379998295e-05 tokens_per_second_per_gpu:743.4790558439867
Step 2443 | loss:1.348697304725647 lr:4.186899104229248e-05 tokens_per_second_per_gpu:955.3209948661224
Step 2444 | loss:1.4459092617034912 lr:4.184919599964554e-05 tokens_per_second_per_gpu:997.3026697074907
Step 2445 | loss:1.4097857475280762 lr:4.182939867862689e-05 tokens_per_second_per_gpu:856.8021297710468
Step 2446 | loss:1.4700316190719604 lr:4.180959908582209e-05 tokens_per_second_per_gpu:687.9683050460633
Step 2447 | loss:1.3681247234344482 lr:4.1789797227817415e-05 tokens_per_second_per_gpu:1035.98101640462
Step 2448 | loss:1.4450637102127075 lr:4.1769993111199945e-05 tokens_per_second_per_gpu:666.6952613780093
Step 2449 | loss:1.4259755611419678 lr:4.175018674255745e-05 tokens_per_second_per_gpu:890.0125161570782
Step 2450 | loss:1.3477836847305298 lr:4.17303781284785e-05 tokens_per_second_per_gpu:922.4364411670637
Step 2451 | loss:1.3834775686264038 lr:4.171056727555239e-05 tokens_per_second_per_gpu:1007.9371689375799
Step 2452 | loss:1.4204822778701782 lr:4.1690754190369156e-05 tokens_per_second_per_gpu:887.8915781254325
Step 2453 | loss:1.3523766994476318 lr:4.167093887951957e-05 tokens_per_second_per_gpu:723.55230372034
Step 2454 | loss:1.3049805164337158 lr:4.1651121349595186e-05 tokens_per_second_per_gpu:957.1331378684364
Step 2455 | loss:1.264622449874878 lr:4.163130160718824e-05 tokens_per_second_per_gpu:1166.347663488811
Step 2456 | loss:1.4202145338058472 lr:4.161147965889175e-05 tokens_per_second_per_gpu:912.3369457025082
Step 2457 | loss:1.3850725889205933 lr:4.159165551129943e-05 tokens_per_second_per_gpu:1027.148037377673
Step 2458 | loss:1.3565285205841064 lr:4.157182917100576e-05 tokens_per_second_per_gpu:703.8967167851073
Step 2459 | loss:1.339213490486145 lr:4.155200064460592e-05 tokens_per_second_per_gpu:999.1953771650085
Step 2460 | loss:1.3048845529556274 lr:4.153216993869584e-05 tokens_per_second_per_gpu:858.910153550206
Step 2461 | loss:1.3280179500579834 lr:4.151233705987217e-05 tokens_per_second_per_gpu:1028.0829478391986
Step 2462 | loss:1.33629310131073 lr:4.149250201473227e-05 tokens_per_second_per_gpu:845.7355549557747
Step 2463 | loss:1.415727972984314 lr:4.1472664809874223e-05 tokens_per_second_per_gpu:725.585128154614
Step 2464 | loss:1.4216898679733276 lr:4.145282545189686e-05 tokens_per_second_per_gpu:733.7585696999967
Step 2465 | loss:1.442417860031128 lr:4.143298394739967e-05 tokens_per_second_per_gpu:806.0978857218063
Step 2466 | loss:1.368229627609253 lr:4.141314030298292e-05 tokens_per_second_per_gpu:867.2990842083517
Step 2467 | loss:1.448106288909912 lr:4.139329452524754e-05 tokens_per_second_per_gpu:723.577233523511
Step 2468 | loss:1.4127748012542725 lr:4.137344662079521e-05 tokens_per_second_per_gpu:738.965192527463
Step 2469 | loss:1.1779465675354004 lr:4.1353596596228286e-05 tokens_per_second_per_gpu:1067.8594860519486
Step 2470 | loss:1.3119269609451294 lr:4.1333744458149836e-05 tokens_per_second_per_gpu:1082.5272847200843
Step 2471 | loss:1.3570613861083984 lr:4.131389021316363e-05 tokens_per_second_per_gpu:716.8400745007121
Step 2472 | loss:1.3982771635055542 lr:4.129403386787417e-05 tokens_per_second_per_gpu:846.999959859051
Step 2473 | loss:1.2144436836242676 lr:4.12741754288866e-05 tokens_per_second_per_gpu:1245.151378336862
Step 2474 | loss:1.3896658420562744 lr:4.125431490280681e-05 tokens_per_second_per_gpu:776.9799304044641
Step 2475 | loss:1.3581726551055908 lr:4.123445229624136e-05 tokens_per_second_per_gpu:1045.6157717229821
Step 2476 | loss:1.4898875951766968 lr:4.12145876157975e-05 tokens_per_second_per_gpu:725.3810605903517
Step 2477 | loss:1.2767302989959717 lr:4.119472086808319e-05 tokens_per_second_per_gpu:1251.4649868409776
Step 2478 | loss:1.3878638744354248 lr:4.117485205970705e-05 tokens_per_second_per_gpu:824.6354696889334
Step 2479 | loss:1.4645869731903076 lr:4.1154981197278415e-05 tokens_per_second_per_gpu:620.8518296252597
Step 2480 | loss:1.290454387664795 lr:4.1135108287407285e-05 tokens_per_second_per_gpu:1018.1095578086216
Step 2481 | loss:1.4668755531311035 lr:4.1115233336704344e-05 tokens_per_second_per_gpu:783.5720356031854
Step 2482 | loss:1.3956379890441895 lr:4.109535635178095e-05 tokens_per_second_per_gpu:848.4568566505258
Step 2483 | loss:1.2427432537078857 lr:4.107547733924915e-05 tokens_per_second_per_gpu:1092.394753304371
Step 2484 | loss:1.517040491104126 lr:4.105559630572166e-05 tokens_per_second_per_gpu:911.860927011743
Step 2485 | loss:1.3672343492507935 lr:4.103571325781186e-05 tokens_per_second_per_gpu:1045.8926158969323
Step 2486 | loss:1.3797792196273804 lr:4.1015828202133806e-05 tokens_per_second_per_gpu:1133.4158830487359
Step 2487 | loss:1.247459888458252 lr:4.0995941145302224e-05 tokens_per_second_per_gpu:933.231258478228
Step 2488 | loss:1.4667518138885498 lr:4.0976052093932516e-05 tokens_per_second_per_gpu:737.4333124500567
Step 2489 | loss:1.2496321201324463 lr:4.0956161054640726e-05 tokens_per_second_per_gpu:773.2606811151293
Step 2490 | loss:1.404646396636963 lr:4.093626803404358e-05 tokens_per_second_per_gpu:761.2071332691369
Step 2491 | loss:1.4215213060379028 lr:4.091637303875844e-05 tokens_per_second_per_gpu:944.1006139170063
Step 2492 | loss:1.3556392192840576 lr:4.089647607540333e-05 tokens_per_second_per_gpu:1074.7991872182765
Step 2493 | loss:1.3688801527023315 lr:4.087657715059696e-05 tokens_per_second_per_gpu:780.3695836685351
Step 2494 | loss:1.231467366218567 lr:4.085667627095865e-05 tokens_per_second_per_gpu:1117.6692844892268
Step 2495 | loss:1.3258148431777954 lr:4.08367734431084e-05 tokens_per_second_per_gpu:898.6406577205313
Step 2496 | loss:1.4758474826812744 lr:4.081686867366683e-05 tokens_per_second_per_gpu:832.7512849875498
Step 2497 | loss:1.487052321434021 lr:4.079696196925525e-05 tokens_per_second_per_gpu:748.6563073848589
Step 2498 | loss:1.40642511844635 lr:4.0777053336495566e-05 tokens_per_second_per_gpu:981.2388234866721
Step 2499 | loss:1.382960319519043 lr:4.075714278201035e-05 tokens_per_second_per_gpu:1153.9181761927741
Step 2500 | loss:1.3832974433898926 lr:4.073723031242281e-05 tokens_per_second_per_gpu:1106.0510005410815
Step 2501 | loss:1.1995922327041626 lr:4.071731593435679e-05 tokens_per_second_per_gpu:1109.9005751276961
Step 2502 | loss:1.4201191663742065 lr:4.069739965443677e-05 tokens_per_second_per_gpu:1013.6309634171903
Step 2503 | loss:1.6507173776626587 lr:4.067748147928786e-05 tokens_per_second_per_gpu:632.4189698805495
Step 2504 | loss:1.1636407375335693 lr:4.0657561415535806e-05 tokens_per_second_per_gpu:803.9662395896172
Step 2505 | loss:1.461578130722046 lr:4.063763946980697e-05 tokens_per_second_per_gpu:783.6903641008229
Step 2506 | loss:1.1790920495986938 lr:4.061771564872836e-05 tokens_per_second_per_gpu:1058.7056450986406
Step 2507 | loss:1.4186910390853882 lr:4.0597789958927595e-05 tokens_per_second_per_gpu:794.9671750883563
Step 2508 | loss:1.415615439414978 lr:4.057786240703289e-05 tokens_per_second_per_gpu:1125.8916810793403
Step 2509 | loss:1.3078327178955078 lr:4.0557932999673144e-05 tokens_per_second_per_gpu:872.2410196467454
Step 2510 | loss:1.4899425506591797 lr:4.053800174347782e-05 tokens_per_second_per_gpu:753.2310856591718
Step 2511 | loss:1.3367670774459839 lr:4.0518068645077016e-05 tokens_per_second_per_gpu:867.3439801530031
Step 2512 | loss:1.2904928922653198 lr:4.049813371110143e-05 tokens_per_second_per_gpu:943.7270709157833
Step 2513 | loss:1.4356824159622192 lr:4.047819694818238e-05 tokens_per_second_per_gpu:754.2187556341476
Step 2514 | loss:1.4844918251037598 lr:4.0458258362951806e-05 tokens_per_second_per_gpu:808.2380878546211
Step 2515 | loss:1.2926087379455566 lr:4.043831796204221e-05 tokens_per_second_per_gpu:780.2363067856595
Step 2516 | loss:1.3922673463821411 lr:4.041837575208675e-05 tokens_per_second_per_gpu:956.4637609723833
Step 2517 | loss:1.3137726783752441 lr:4.0398431739719166e-05 tokens_per_second_per_gpu:861.1632295885979
Step 2518 | loss:1.3264878988265991 lr:4.037848593157377e-05 tokens_per_second_per_gpu:1134.865838054708
Step 2519 | loss:1.3351609706878662 lr:4.035853833428553e-05 tokens_per_second_per_gpu:755.6462435876964
Step 2520 | loss:1.368463397026062 lr:4.033858895448995e-05 tokens_per_second_per_gpu:770.3383653531853
Step 2521 | loss:1.3572194576263428 lr:4.0318637798823164e-05 tokens_per_second_per_gpu:778.4526122260179
Step 2522 | loss:1.4338836669921875 lr:4.029868487392188e-05 tokens_per_second_per_gpu:1064.4428726160224
Step 2523 | loss:1.2384471893310547 lr:4.0278730186423413e-05 tokens_per_second_per_gpu:938.5450300557985
Step 2524 | loss:1.4136558771133423 lr:4.025877374296563e-05 tokens_per_second_per_gpu:820.8994944508705
Step 2525 | loss:1.4189149141311646 lr:4.023881555018701e-05 tokens_per_second_per_gpu:966.9719234299805
Step 2526 | loss:1.2618076801300049 lr:4.021885561472661e-05 tokens_per_second_per_gpu:902.0489710699687
Step 2527 | loss:1.3183284997940063 lr:4.019889394322406e-05 tokens_per_second_per_gpu:959.1904610397196
Step 2528 | loss:1.2657663822174072 lr:4.0178930542319585e-05 tokens_per_second_per_gpu:979.4013779074741
Step 2529 | loss:1.306494116783142 lr:4.015896541865396e-05 tokens_per_second_per_gpu:1063.6719508795447
Step 2530 | loss:1.491801142692566 lr:4.0138998578868534e-05 tokens_per_second_per_gpu:700.2522425204352
Step 2531 | loss:1.409979224205017 lr:4.011903002960526e-05 tokens_per_second_per_gpu:797.8983169479594
Step 2532 | loss:1.4130767583847046 lr:4.0099059777506624e-05 tokens_per_second_per_gpu:731.4579137418903
Step 2533 | loss:1.4749621152877808 lr:4.007908782921568e-05 tokens_per_second_per_gpu:710.8804291354585
Step 2534 | loss:1.2593218088150024 lr:4.005911419137608e-05 tokens_per_second_per_gpu:857.4158501935341
Step 2535 | loss:1.4044086933135986 lr:4.003913887063201e-05 tokens_per_second_per_gpu:908.5051115941786
Step 2536 | loss:1.3445502519607544 lr:4.001916187362821e-05 tokens_per_second_per_gpu:891.4764933260351
Step 2537 | loss:1.3272963762283325 lr:3.999918320701e-05 tokens_per_second_per_gpu:816.6616541687381
Step 2538 | loss:1.5409537553787231 lr:3.9979202877423246e-05 tokens_per_second_per_gpu:580.9342692316345
Step 2539 | loss:1.3666683435440063 lr:3.9959220891514344e-05 tokens_per_second_per_gpu:770.5023504310594
Step 2540 | loss:1.5721687078475952 lr:3.99392372559303e-05 tokens_per_second_per_gpu:573.6641775326692
Step 2541 | loss:1.3420038223266602 lr:3.99192519773186e-05 tokens_per_second_per_gpu:1066.4848669826688
Step 2542 | loss:1.399198055267334 lr:3.9899265062327324e-05 tokens_per_second_per_gpu:885.665416219536
Step 2543 | loss:1.4655522108078003 lr:3.9879276517605074e-05 tokens_per_second_per_gpu:817.4771307223285
Step 2544 | loss:1.372615098953247 lr:3.985928634980099e-05 tokens_per_second_per_gpu:749.4429892007308
Step 2545 | loss:1.4774082899093628 lr:3.9839294565564793e-05 tokens_per_second_per_gpu:704.4751883554042
Step 2546 | loss:1.3685966730117798 lr:3.9819301171546685e-05 tokens_per_second_per_gpu:927.0413495028802
Step 2547 | loss:1.3610975742340088 lr:3.9799306174397436e-05 tokens_per_second_per_gpu:992.5386776269914
Step 2548 | loss:1.3518239259719849 lr:3.977930958076835e-05 tokens_per_second_per_gpu:894.4806251777788
Step 2549 | loss:1.2211593389511108 lr:3.975931139731124e-05 tokens_per_second_per_gpu:1002.4457621843583
Step 2550 | loss:1.4319367408752441 lr:3.973931163067846e-05 tokens_per_second_per_gpu:772.1509477949838
Step 2551 | loss:1.3202930688858032 lr:3.971931028752293e-05 tokens_per_second_per_gpu:1034.848918125161
Step 2552 | loss:1.2259215116500854 lr:3.969930737449801e-05 tokens_per_second_per_gpu:1057.3263527853992
Step 2553 | loss:1.3713691234588623 lr:3.967930289825767e-05 tokens_per_second_per_gpu:921.8563843502723
Step 2554 | loss:1.2995858192443848 lr:3.965929686545634e-05 tokens_per_second_per_gpu:895.6817269212083
Step 2555 | loss:1.3883711099624634 lr:3.9639289282748985e-05 tokens_per_second_per_gpu:1022.3926939137913
Step 2556 | loss:1.54242742061615 lr:3.961928015679109e-05 tokens_per_second_per_gpu:939.0289010258027
Step 2557 | loss:1.247553825378418 lr:3.959926949423866e-05 tokens_per_second_per_gpu:950.7933074017433
Step 2558 | loss:1.4079638719558716 lr:3.957925730174819e-05 tokens_per_second_per_gpu:694.1479501562554
Step 2559 | loss:1.4411793947219849 lr:3.955924358597672e-05 tokens_per_second_per_gpu:780.6891075073124
Step 2560 | loss:1.1840755939483643 lr:3.9539228353581746e-05 tokens_per_second_per_gpu:1253.8835671780923
Step 2561 | loss:1.459360957145691 lr:3.9519211611221315e-05 tokens_per_second_per_gpu:719.2783242421359
Step 2562 | loss:1.3496484756469727 lr:3.9499193365553945e-05 tokens_per_second_per_gpu:866.3752527530343
Step 2563 | loss:1.484666347503662 lr:3.947917362323868e-05 tokens_per_second_per_gpu:918.8494458228562
Step 2564 | loss:1.3693996667861938 lr:3.945915239093503e-05 tokens_per_second_per_gpu:808.408519657691
Step 2565 | loss:1.4647696018218994 lr:3.943912967530304e-05 tokens_per_second_per_gpu:698.6253892733665
Step 2566 | loss:1.3356465101242065 lr:3.9419105483003215e-05 tokens_per_second_per_gpu:796.5789627433754
Step 2567 | loss:1.2688850164413452 lr:3.939907982069657e-05 tokens_per_second_per_gpu:881.5086359117589
Step 2568 | loss:1.2391866445541382 lr:3.937905269504459e-05 tokens_per_second_per_gpu:737.4200636639671
Step 2569 | loss:1.470150113105774 lr:3.935902411270927e-05 tokens_per_second_per_gpu:735.2114500885735
Step 2570 | loss:1.3287421464920044 lr:3.933899408035307e-05 tokens_per_second_per_gpu:884.9741758043883
Step 2571 | loss:1.2679705619812012 lr:3.9318962604638955e-05 tokens_per_second_per_gpu:1014.5675143223342
Step 2572 | loss:1.3816230297088623 lr:3.929892969223034e-05 tokens_per_second_per_gpu:932.3646230321364
Step 2573 | loss:1.254123330116272 lr:3.927889534979116e-05 tokens_per_second_per_gpu:802.8087060373317
Step 2574 | loss:1.4071693420410156 lr:3.925885958398577e-05 tokens_per_second_per_gpu:712.6899195410501
Step 2575 | loss:1.3467108011245728 lr:3.923882240147904e-05 tokens_per_second_per_gpu:812.6117444977007
Step 2576 | loss:1.4522696733474731 lr:3.92187838089363e-05 tokens_per_second_per_gpu:1184.2095997081362
Step 2577 | loss:1.3454310894012451 lr:3.919874381302336e-05 tokens_per_second_per_gpu:910.2414029354551
Step 2578 | loss:1.3188517093658447 lr:3.917870242040647e-05 tokens_per_second_per_gpu:1185.7918578735982
Step 2579 | loss:1.4252432584762573 lr:3.9158659637752366e-05 tokens_per_second_per_gpu:985.0627970627874
Step 2580 | loss:1.346513032913208 lr:3.913861547172824e-05 tokens_per_second_per_gpu:821.5909493202198
Step 2581 | loss:1.2680267095565796 lr:3.9118569929001746e-05 tokens_per_second_per_gpu:1000.4674390495769
Step 2582 | loss:1.362415075302124 lr:3.9098523016240984e-05 tokens_per_second_per_gpu:1122.3932718065769
Step 2583 | loss:1.4552384614944458 lr:3.907847474011454e-05 tokens_per_second_per_gpu:887.5950412489668
Step 2584 | loss:1.361559510231018 lr:3.905842510729142e-05 tokens_per_second_per_gpu:751.1701619035382
Step 2585 | loss:1.3876451253890991 lr:3.9038374124441104e-05 tokens_per_second_per_gpu:1062.3742862056902
Step 2586 | loss:1.4761954545974731 lr:3.9018321798233505e-05 tokens_per_second_per_gpu:716.8225812380999
Step 2587 | loss:1.2471978664398193 lr:3.8998268135338994e-05 tokens_per_second_per_gpu:1011.6219686842995
Step 2588 | loss:1.3182008266448975 lr:3.897821314242838e-05 tokens_per_second_per_gpu:752.5805797791426
Step 2589 | loss:1.4916290044784546 lr:3.895815682617291e-05 tokens_per_second_per_gpu:885.347231141683
Step 2590 | loss:1.465512752532959 lr:3.89380991932443e-05 tokens_per_second_per_gpu:754.3779542045808
Step 2591 | loss:1.4628493785858154 lr:3.8918040250314674e-05 tokens_per_second_per_gpu:749.1674134304752
Step 2592 | loss:1.4350981712341309 lr:3.889798000405659e-05 tokens_per_second_per_gpu:999.2990429726052
Step 2593 | loss:1.3445345163345337 lr:3.887791846114305e-05 tokens_per_second_per_gpu:602.9676306750239
Step 2594 | loss:1.4031902551651 lr:3.8857855628247505e-05 tokens_per_second_per_gpu:523.184130542356
Step 2595 | loss:1.2647968530654907 lr:3.8837791512043795e-05 tokens_per_second_per_gpu:952.0767745813681
Step 2596 | loss:1.437500238418579 lr:3.881772611920622e-05 tokens_per_second_per_gpu:1050.0923157101715
Step 2597 | loss:1.5006550550460815 lr:3.87976594564095e-05 tokens_per_second_per_gpu:707.6756039900071
Step 2598 | loss:1.4160386323928833 lr:3.8777591530328766e-05 tokens_per_second_per_gpu:949.4502664870994
Step 2599 | loss:1.2901623249053955 lr:3.875752234763957e-05 tokens_per_second_per_gpu:861.3608264461836
Step 2600 | loss:1.4663292169570923 lr:3.8737451915017884e-05 tokens_per_second_per_gpu:750.7401052523594
Step 2601 | loss:1.4193625450134277 lr:3.871738023914011e-05 tokens_per_second_per_gpu:939.2236816920503
Step 2602 | loss:1.2832688093185425 lr:3.869730732668304e-05 tokens_per_second_per_gpu:907.098426172393
Step 2603 | loss:1.5046459436416626 lr:3.8677233184323903e-05 tokens_per_second_per_gpu:1094.7556317941276
Step 2604 | loss:1.3639894723892212 lr:3.865715781874031e-05 tokens_per_second_per_gpu:831.6759922929862
Step 2605 | loss:1.4521135091781616 lr:3.8637081236610296e-05 tokens_per_second_per_gpu:883.33630156435
Step 2606 | loss:1.3693972826004028 lr:3.861700344461231e-05 tokens_per_second_per_gpu:902.4772450110594
Step 2607 | loss:1.5555540323257446 lr:3.8596924449425174e-05 tokens_per_second_per_gpu:917.4478064325469
Step 2608 | loss:1.3293076753616333 lr:3.857684425772813e-05 tokens_per_second_per_gpu:671.9659725065438
Step 2609 | loss:1.4881420135498047 lr:3.855676287620082e-05 tokens_per_second_per_gpu:945.3114583230243
Step 2610 | loss:1.319309949874878 lr:3.853668031152326e-05 tokens_per_second_per_gpu:924.4183988394512
Step 2611 | loss:1.3220230340957642 lr:3.85165965703759e-05 tokens_per_second_per_gpu:716.1574287296504
Step 2612 | loss:1.2624025344848633 lr:3.849651165943955e-05 tokens_per_second_per_gpu:947.7847137813918
Step 2613 | loss:1.3542253971099854 lr:3.847642558539539e-05 tokens_per_second_per_gpu:681.4616590247266
Step 2614 | loss:1.419989824295044 lr:3.845633835492505e-05 tokens_per_second_per_gpu:1133.750352440419
Step 2615 | loss:1.4152977466583252 lr:3.8436249974710496e-05 tokens_per_second_per_gpu:913.9375569517491
Step 2616 | loss:1.2239247560501099 lr:3.841616045143408e-05 tokens_per_second_per_gpu:932.3187452111245
Step 2617 | loss:1.333746075630188 lr:3.839606979177856e-05 tokens_per_second_per_gpu:864.6345886188413
Step 2618 | loss:1.3397973775863647 lr:3.837597800242704e-05 tokens_per_second_per_gpu:927.0412552443976
Step 2619 | loss:1.2971493005752563 lr:3.8355885090063e-05 tokens_per_second_per_gpu:1343.2133161246356
Step 2620 | loss:1.322746753692627 lr:3.833579106137035e-05 tokens_per_second_per_gpu:780.4645174864578
Step 2621 | loss:1.4027842283248901 lr:3.83156959230333e-05 tokens_per_second_per_gpu:788.2032925376017
Step 2622 | loss:1.5126841068267822 lr:3.829559968173646e-05 tokens_per_second_per_gpu:916.0440902787567
Step 2623 | loss:1.3347667455673218 lr:3.8275502344164816e-05 tokens_per_second_per_gpu:899.178621030614
Step 2624 | loss:1.3427330255508423 lr:3.82554039170037e-05 tokens_per_second_per_gpu:756.7501797569057
Step 2625 | loss:1.3371790647506714 lr:3.823530440693882e-05 tokens_per_second_per_gpu:767.2850032443442
Step 2626 | loss:1.2800871133804321 lr:3.821520382065622e-05 tokens_per_second_per_gpu:839.2631757209062
Step 2627 | loss:1.4352765083312988 lr:3.819510216484235e-05 tokens_per_second_per_gpu:839.7063819519677
Step 2628 | loss:1.3956422805786133 lr:3.8174999446183967e-05 tokens_per_second_per_gpu:684.5359749102442
Step 2629 | loss:1.352017879486084 lr:3.815489567136822e-05 tokens_per_second_per_gpu:746.5947960185401
Step 2630 | loss:1.3922464847564697 lr:3.813479084708257e-05 tokens_per_second_per_gpu:1218.0300099621127
Step 2631 | loss:1.2665412425994873 lr:3.8114684980014856e-05 tokens_per_second_per_gpu:712.844012719125
Step 2632 | loss:1.5185174942016602 lr:3.809457807685324e-05 tokens_per_second_per_gpu:996.9778766185138
Step 2633 | loss:1.5188076496124268 lr:3.807447014428628e-05 tokens_per_second_per_gpu:616.8074613319144
Step 2634 | loss:1.2182668447494507 lr:3.805436118900282e-05 tokens_per_second_per_gpu:1094.6115395442555
Step 2635 | loss:1.3192304372787476 lr:3.803425121769206e-05 tokens_per_second_per_gpu:909.2051935146955
Step 2636 | loss:1.4403071403503418 lr:3.801414023704354e-05 tokens_per_second_per_gpu:968.2616712622188
Step 2637 | loss:1.4533416032791138 lr:3.799402825374715e-05 tokens_per_second_per_gpu:851.0963847749409
Step 2638 | loss:1.3494515419006348 lr:3.797391527449309e-05 tokens_per_second_per_gpu:893.6470557866229
Step 2639 | loss:1.3674637079238892 lr:3.795380130597192e-05 tokens_per_second_per_gpu:875.1037418462608
Step 2640 | loss:1.2486974000930786 lr:3.79336863548745e-05 tokens_per_second_per_gpu:975.5191635450486
Step 2641 | loss:1.4980577230453491 lr:3.7913570427892036e-05 tokens_per_second_per_gpu:1005.5390205024515
Step 2642 | loss:1.4097261428833008 lr:3.789345353171605e-05 tokens_per_second_per_gpu:842.3976451128674
Step 2643 | loss:1.4086135625839233 lr:3.787333567303839e-05 tokens_per_second_per_gpu:954.3738404144045
Step 2644 | loss:1.160728931427002 lr:3.78532168585512e-05 tokens_per_second_per_gpu:1188.651624242417
Step 2645 | loss:1.270033359527588 lr:3.783309709494701e-05 tokens_per_second_per_gpu:1062.420858231564
Step 2646 | loss:1.3698278665542603 lr:3.781297638891858e-05 tokens_per_second_per_gpu:1109.1051867931844
Step 2647 | loss:1.326851725578308 lr:3.779285474715904e-05 tokens_per_second_per_gpu:907.5524803732603
Step 2648 | loss:1.3208470344543457 lr:3.7772732176361813e-05 tokens_per_second_per_gpu:765.2065783095936
Step 2649 | loss:1.373321294784546 lr:3.7752608683220635e-05 tokens_per_second_per_gpu:823.7383727737885
Step 2650 | loss:1.4769105911254883 lr:3.773248427442953e-05 tokens_per_second_per_gpu:980.3533323637997
Step 2651 | loss:1.338515043258667 lr:3.771235895668287e-05 tokens_per_second_per_gpu:862.2894872189044
Step 2652 | loss:1.2981281280517578 lr:3.769223273667529e-05 tokens_per_second_per_gpu:949.5632009428898
Step 2653 | loss:1.3237097263336182 lr:3.767210562110174e-05 tokens_per_second_per_gpu:786.8253336074537
Step 2654 | loss:1.237055778503418 lr:3.765197761665746e-05 tokens_per_second_per_gpu:942.5329942246105
Step 2655 | loss:1.2038015127182007 lr:3.7631848730038004e-05 tokens_per_second_per_gpu:1075.5761199321782
Step 2656 | loss:1.2937922477722168 lr:3.7611718967939176e-05 tokens_per_second_per_gpu:998.6781034922702
Step 2657 | loss:1.3206062316894531 lr:3.759158833705714e-05 tokens_per_second_per_gpu:1030.767432057151
Step 2658 | loss:1.4919291734695435 lr:3.75714568440883e-05 tokens_per_second_per_gpu:705.5350844767306
Step 2659 | loss:1.279175043106079 lr:3.755132449572935e-05 tokens_per_second_per_gpu:800.7781643627043
Step 2660 | loss:1.3808685541152954 lr:3.753119129867728e-05 tokens_per_second_per_gpu:970.0440662781883
Step 2661 | loss:1.5306220054626465 lr:3.751105725962936e-05 tokens_per_second_per_gpu:869.2321155880446
Step 2662 | loss:1.3445335626602173 lr:3.749092238528314e-05 tokens_per_second_per_gpu:747.0028389936405
Step 2663 | loss:1.2109436988830566 lr:3.747078668233643e-05 tokens_per_second_per_gpu:1050.884120934453
Step 2664 | loss:1.3529349565505981 lr:3.745065015748736e-05 tokens_per_second_per_gpu:795.4930654850406
Step 2665 | loss:1.3360446691513062 lr:3.743051281743428e-05 tokens_per_second_per_gpu:821.7926832297721
Step 2666 | loss:1.2334420680999756 lr:3.741037466887586e-05 tokens_per_second_per_gpu:956.3245809906078
Step 2667 | loss:1.1977896690368652 lr:3.7390235718510994e-05 tokens_per_second_per_gpu:906.669424156502
Step 2668 | loss:1.2835383415222168 lr:3.7370095973038886e-05 tokens_per_second_per_gpu:1014.1584505523208
Step 2669 | loss:1.4295408725738525 lr:3.734995543915897e-05 tokens_per_second_per_gpu:683.2002408514237
Step 2670 | loss:1.3199583292007446 lr:3.732981412357096e-05 tokens_per_second_per_gpu:969.183316239494
Step 2671 | loss:1.238895058631897 lr:3.7309672032974826e-05 tokens_per_second_per_gpu:981.8671091933431
Step 2672 | loss:1.3092459440231323 lr:3.728952917407079e-05 tokens_per_second_per_gpu:903.8707400432093
Step 2673 | loss:1.5912600755691528 lr:3.726938555355934e-05 tokens_per_second_per_gpu:596.0161672690693
Step 2674 | loss:1.3669672012329102 lr:3.72492411781412e-05 tokens_per_second_per_gpu:795.4434145830749
Step 2675 | loss:1.4076030254364014 lr:3.7229096054517366e-05 tokens_per_second_per_gpu:913.4922461089484
Step 2676 | loss:1.2563114166259766 lr:3.7208950189389085e-05 tokens_per_second_per_gpu:1168.59817517151
Step 2677 | loss:1.4043222665786743 lr:3.7188803589457824e-05 tokens_per_second_per_gpu:975.9251750969313
Step 2678 | loss:1.3180278539657593 lr:3.7168656261425316e-05 tokens_per_second_per_gpu:972.7521643040839
Step 2679 | loss:1.4989005327224731 lr:3.714850821199353e-05 tokens_per_second_per_gpu:780.6585004286967
Step 2680 | loss:1.3477160930633545 lr:3.7128359447864676e-05 tokens_per_second_per_gpu:875.7858430707013
Step 2681 | loss:1.2984684705734253 lr:3.710820997574119e-05 tokens_per_second_per_gpu:1038.5703662313567
Step 2682 | loss:1.2629083395004272 lr:3.708805980232578e-05 tokens_per_second_per_gpu:888.7889012793936
Step 2683 | loss:1.5059407949447632 lr:3.706790893432134e-05 tokens_per_second_per_gpu:742.54735526799
Step 2684 | loss:1.3144792318344116 lr:3.704775737843103e-05 tokens_per_second_per_gpu:939.7117698633189
Step 2685 | loss:1.3401727676391602 lr:3.7027605141358216e-05 tokens_per_second_per_gpu:1086.7833868530568
Step 2686 | loss:1.477976679801941 lr:3.7007452229806506e-05 tokens_per_second_per_gpu:972.6338859300439
Step 2687 | loss:1.3523825407028198 lr:3.6987298650479716e-05 tokens_per_second_per_gpu:764.1496570592321
Step 2688 | loss:1.4495457410812378 lr:3.6967144410081915e-05 tokens_per_second_per_gpu:683.5319462534778
Step 2689 | loss:1.234515905380249 lr:3.6946989515317356e-05 tokens_per_second_per_gpu:1089.4382377279587
Step 2690 | loss:1.3652524948120117 lr:3.6926833972890534e-05 tokens_per_second_per_gpu:1230.3892256581219
Step 2691 | loss:1.2548035383224487 lr:3.690667778950614e-05 tokens_per_second_per_gpu:848.9648724755993
Step 2692 | loss:1.419849157333374 lr:3.6886520971869105e-05 tokens_per_second_per_gpu:1081.8953407532383
Step 2693 | loss:1.4067918062210083 lr:3.686636352668453e-05 tokens_per_second_per_gpu:798.256987622258
Step 2694 | loss:1.448163390159607 lr:3.684620546065778e-05 tokens_per_second_per_gpu:741.6708861303897
Step 2695 | loss:1.4771614074707031 lr:3.682604678049438e-05 tokens_per_second_per_gpu:891.503254781336
Step 2696 | loss:1.5361460447311401 lr:3.6805887492900084e-05 tokens_per_second_per_gpu:642.4341331086439
Step 2697 | loss:1.5382297039031982 lr:3.678572760458082e-05 tokens_per_second_per_gpu:643.1529130542633
Step 2698 | loss:1.3208513259887695 lr:3.676556712224276e-05 tokens_per_second_per_gpu:1034.1252295961435
Step 2699 | loss:1.4201558828353882 lr:3.6745406052592234e-05 tokens_per_second_per_gpu:847.4476676116718
Step 2700 | loss:1.4650756120681763 lr:3.6725244402335784e-05 tokens_per_second_per_gpu:786.9743136725431
Step 2701 | loss:1.3968663215637207 lr:3.6705082178180156e-05 tokens_per_second_per_gpu:717.686248656519
Step 2702 | loss:1.292030930519104 lr:3.668491938683226e-05 tokens_per_second_per_gpu:916.0252525786713
Step 2703 | loss:1.3218176364898682 lr:3.666475603499921e-05 tokens_per_second_per_gpu:943.3179666183107
Step 2704 | loss:1.4091122150421143 lr:3.664459212938832e-05 tokens_per_second_per_gpu:930.6575505098767
Step 2705 | loss:1.4119421243667603 lr:3.6624427676707065e-05 tokens_per_second_per_gpu:694.8844929008321
Step 2706 | loss:1.2935106754302979 lr:3.660426268366309e-05 tokens_per_second_per_gpu:1054.1911702154719
Step 2707 | loss:1.3761283159255981 lr:3.658409715696427e-05 tokens_per_second_per_gpu:670.900833495798
Step 2708 | loss:1.325924038887024 lr:3.656393110331863e-05 tokens_per_second_per_gpu:899.2917212579468
Step 2709 | loss:1.4529590606689453 lr:3.654376452943435e-05 tokens_per_second_per_gpu:944.2398140174389
Step 2710 | loss:1.4361562728881836 lr:3.652359744201981e-05 tokens_per_second_per_gpu:808.6669074605212
Step 2711 | loss:1.3767365217208862 lr:3.650342984778355e-05 tokens_per_second_per_gpu:806.6190674262502
Step 2712 | loss:1.3294072151184082 lr:3.648326175343427e-05 tokens_per_second_per_gpu:886.5335840027024
Step 2713 | loss:1.3124247789382935 lr:3.646309316568088e-05 tokens_per_second_per_gpu:965.7341879691812
Step 2714 | loss:1.3565908670425415 lr:3.644292409123238e-05 tokens_per_second_per_gpu:702.1556931430448
Step 2715 | loss:1.3537846803665161 lr:3.642275453679801e-05 tokens_per_second_per_gpu:1044.5289087367958
Step 2716 | loss:1.3859703540802002 lr:3.640258450908711e-05 tokens_per_second_per_gpu:915.2544731111346
Step 2717 | loss:1.180673599243164 lr:3.6382414014809217e-05 tokens_per_second_per_gpu:1020.3563335463311
Step 2718 | loss:1.1671761274337769 lr:3.636224306067398e-05 tokens_per_second_per_gpu:1094.1546242658035
Step 2719 | loss:1.4193181991577148 lr:3.634207165339125e-05 tokens_per_second_per_gpu:784.0615783676552
Step 2720 | loss:1.322934865951538 lr:3.6321899799671004e-05 tokens_per_second_per_gpu:930.9530204062348
Step 2721 | loss:1.428245186805725 lr:3.6301727506223365e-05 tokens_per_second_per_gpu:853.9428151199743
Step 2722 | loss:1.4779378175735474 lr:3.628155477975861e-05 tokens_per_second_per_gpu:755.6419801801716
Step 2723 | loss:1.2799060344696045 lr:3.6261381626987157e-05 tokens_per_second_per_gpu:779.5378650436382
Step 2724 | loss:1.4501699209213257 lr:3.624120805461956e-05 tokens_per_second_per_gpu:757.2009818780546
Step 2725 | loss:1.318139910697937 lr:3.622103406936653e-05 tokens_per_second_per_gpu:856.2013875424113
Step 2726 | loss:1.3659989833831787 lr:3.620085967793889e-05 tokens_per_second_per_gpu:875.9489157686479
Step 2727 | loss:1.5377321243286133 lr:3.6180684887047624e-05 tokens_per_second_per_gpu:869.4917048340988
Step 2728 | loss:1.4903510808944702 lr:3.616050970340383e-05 tokens_per_second_per_gpu:718.3132569347548
Step 2729 | loss:1.349128246307373 lr:3.6140334133718737e-05 tokens_per_second_per_gpu:985.1926327818077
Step 2730 | loss:1.2199797630310059 lr:3.6120158184703725e-05 tokens_per_second_per_gpu:1238.6009226417584
Step 2731 | loss:1.279956579208374 lr:3.609998186307028e-05 tokens_per_second_per_gpu:960.9151610592261
Step 2732 | loss:1.1829756498336792 lr:3.6079805175530014e-05 tokens_per_second_per_gpu:1000.6545720504721
Step 2733 | loss:1.3973520994186401 lr:3.605962812879465e-05 tokens_per_second_per_gpu:738.0665382697404
Step 2734 | loss:1.2928147315979004 lr:3.6039450729576063e-05 tokens_per_second_per_gpu:858.3215151980272
Step 2735 | loss:1.3875927925109863 lr:3.601927298458622e-05 tokens_per_second_per_gpu:964.314483812863
Step 2736 | loss:1.4816842079162598 lr:3.59990949005372e-05 tokens_per_second_per_gpu:850.8296721058986
Step 2737 | loss:1.3473782539367676 lr:3.59789164841412e-05 tokens_per_second_per_gpu:882.2225779954656
Step 2738 | loss:1.35379159450531 lr:3.5958737742110556e-05 tokens_per_second_per_gpu:814.6269128106248
Step 2739 | loss:1.3361769914627075 lr:3.5938558681157665e-05 tokens_per_second_per_gpu:816.2220863026516
Step 2740 | loss:1.3140439987182617 lr:3.591837930799505e-05 tokens_per_second_per_gpu:785.184121886507
Step 2741 | loss:1.3336243629455566 lr:3.589819962933537e-05 tokens_per_second_per_gpu:953.0342073571456
Step 2742 | loss:1.449002981185913 lr:3.587801965189132e-05 tokens_per_second_per_gpu:780.884989090823
Step 2743 | loss:1.4157114028930664 lr:3.585783938237573e-05 tokens_per_second_per_gpu:902.5203063926325
Step 2744 | loss:1.3858659267425537 lr:3.583765882750156e-05 tokens_per_second_per_gpu:900.073201714195
Step 2745 | loss:1.2888649702072144 lr:3.581747799398181e-05 tokens_per_second_per_gpu:935.9625345234108
Step 2746 | loss:1.4444971084594727 lr:3.57972968885296e-05 tokens_per_second_per_gpu:1251.798822432619
Step 2747 | loss:1.4140490293502808 lr:3.577711551785813e-05 tokens_per_second_per_gpu:936.2551623160444
Step 2748 | loss:1.2983124256134033 lr:3.5756933888680704e-05 tokens_per_second_per_gpu:1067.7955021129783
Step 2749 | loss:1.2425947189331055 lr:3.5736752007710685e-05 tokens_per_second_per_gpu:817.643704665084
Step 2750 | loss:1.4095830917358398 lr:3.5716569881661556e-05 tokens_per_second_per_gpu:861.9942959168201
Step 2751 | loss:1.3298391103744507 lr:3.5696387517246846e-05 tokens_per_second_per_gpu:811.7543252280514
Step 2752 | loss:1.437114953994751 lr:3.56762049211802e-05 tokens_per_second_per_gpu:761.2919102704169
Step 2753 | loss:1.45225191116333 lr:3.565602210017529e-05 tokens_per_second_per_gpu:682.9398283344299
Step 2754 | loss:1.3412851095199585 lr:3.563583906094592e-05 tokens_per_second_per_gpu:729.5585597299623
Step 2755 | loss:1.2995615005493164 lr:3.561565581020591e-05 tokens_per_second_per_gpu:1201.534152851382
Step 2756 | loss:1.2718971967697144 lr:3.559547235466921e-05 tokens_per_second_per_gpu:936.2317579257455
Step 2757 | loss:1.3880279064178467 lr:3.557528870104978e-05 tokens_per_second_per_gpu:1220.118335590868
Step 2758 | loss:1.256054162979126 lr:3.5555104856061694e-05 tokens_per_second_per_gpu:876.8562613016159
Step 2759 | loss:1.3395682573318481 lr:3.553492082641906e-05 tokens_per_second_per_gpu:795.6780196970675
Step 2760 | loss:1.3430275917053223 lr:3.551473661883605e-05 tokens_per_second_per_gpu:899.8182335781999
Step 2761 | loss:1.2088556289672852 lr:3.54945522400269e-05 tokens_per_second_per_gpu:1033.8482848920357
Step 2762 | loss:1.306043267250061 lr:3.547436769670592e-05 tokens_per_second_per_gpu:721.1753336762808
Step 2763 | loss:1.319920539855957 lr:3.545418299558746e-05 tokens_per_second_per_gpu:1215.0448333192076
Step 2764 | loss:1.3883402347564697 lr:3.54339981433859e-05 tokens_per_second_per_gpu:730.1350424578059
Step 2765 | loss:1.2872819900512695 lr:3.5413813146815704e-05 tokens_per_second_per_gpu:967.6503443062757
Step 2766 | loss:1.2155004739761353 lr:3.539362801259138e-05 tokens_per_second_per_gpu:995.6360819526207
Step 2767 | loss:1.267104148864746 lr:3.5373442747427454e-05 tokens_per_second_per_gpu:932.3260614026833
Step 2768 | loss:1.2445448637008667 lr:3.535325735803853e-05 tokens_per_second_per_gpu:964.9110802292718
Step 2769 | loss:1.459825038909912 lr:3.533307185113924e-05 tokens_per_second_per_gpu:774.2838076612846
Step 2770 | loss:1.3926304578781128 lr:3.531288623344424e-05 tokens_per_second_per_gpu:816.2392055975414
Step 2771 | loss:1.4220898151397705 lr:3.529270051166825e-05 tokens_per_second_per_gpu:678.0581420697389
Step 2772 | loss:1.3889495134353638 lr:3.5272514692526e-05 tokens_per_second_per_gpu:1330.832436067572
Step 2773 | loss:1.350151777267456 lr:3.5252328782732275e-05 tokens_per_second_per_gpu:1061.1011249242215
Step 2774 | loss:1.3720897436141968 lr:3.5232142789001865e-05 tokens_per_second_per_gpu:1059.245128240326
Step 2775 | loss:1.2860549688339233 lr:3.521195671804961e-05 tokens_per_second_per_gpu:1201.9485828827337
Step 2776 | loss:1.2466448545455933 lr:3.519177057659037e-05 tokens_per_second_per_gpu:994.4214788081156
Step 2777 | loss:1.204500436782837 lr:3.5171584371339024e-05 tokens_per_second_per_gpu:1158.437650438688
Step 2778 | loss:1.498856782913208 lr:3.515139810901047e-05 tokens_per_second_per_gpu:573.6179857338522
Step 2779 | loss:1.4778681993484497 lr:3.513121179631963e-05 tokens_per_second_per_gpu:796.1665667162217
Step 2780 | loss:1.3909728527069092 lr:3.511102543998144e-05 tokens_per_second_per_gpu:1096.0607353238283
Step 2781 | loss:1.4954038858413696 lr:3.5090839046710844e-05 tokens_per_second_per_gpu:716.7321271077687
Step 2782 | loss:1.310019850730896 lr:3.5070652623222826e-05 tokens_per_second_per_gpu:1178.5755725702438
Step 2783 | loss:1.5439194440841675 lr:3.505046617623235e-05 tokens_per_second_per_gpu:690.7507798161712
Step 2784 | loss:1.3990246057510376 lr:3.5030279712454406e-05 tokens_per_second_per_gpu:696.6662977580338
Step 2785 | loss:1.4489164352416992 lr:3.501009323860396e-05 tokens_per_second_per_gpu:784.2222281990335
Step 2786 | loss:1.4230401515960693 lr:3.498990676139604e-05 tokens_per_second_per_gpu:935.9275442750405
Step 2787 | loss:1.434396505355835 lr:3.4969720287545595e-05 tokens_per_second_per_gpu:954.4817284022657
Step 2788 | loss:1.3264918327331543 lr:3.494953382376765e-05 tokens_per_second_per_gpu:1111.6533983247018
Step 2789 | loss:1.166684865951538 lr:3.492934737677716e-05 tokens_per_second_per_gpu:1044.2386403739183
Step 2790 | loss:1.1980040073394775 lr:3.490916095328915e-05 tokens_per_second_per_gpu:843.8766332627596
Step 2791 | loss:1.3428270816802979 lr:3.488897456001856e-05 tokens_per_second_per_gpu:1077.1001711875174
Step 2792 | loss:1.2642639875411987 lr:3.486878820368037e-05 tokens_per_second_per_gpu:1023.8099269929575
Step 2793 | loss:1.308508276939392 lr:3.4848601890989525e-05 tokens_per_second_per_gpu:887.7783156026142
Step 2794 | loss:1.3928942680358887 lr:3.482841562866098e-05 tokens_per_second_per_gpu:832.4947490542509
Step 2795 | loss:1.4728319644927979 lr:3.480822942340962e-05 tokens_per_second_per_gpu:946.1802792066293
Step 2796 | loss:1.4521510601043701 lr:3.478804328195038e-05 tokens_per_second_per_gpu:663.7064359075545
Step 2797 | loss:1.4534344673156738 lr:3.4767857210998135e-05 tokens_per_second_per_gpu:697.01014940655
Step 2798 | loss:1.2446544170379639 lr:3.474767121726772e-05 tokens_per_second_per_gpu:937.3557015425795
Step 2799 | loss:1.2355828285217285 lr:3.4727485307474e-05 tokens_per_second_per_gpu:757.2503943545997
Step 2800 | loss:1.2873263359069824 lr:3.470729948833175e-05 tokens_per_second_per_gpu:1110.6527891789121
Step 2801 | loss:1.4278826713562012 lr:3.468711376655575e-05 tokens_per_second_per_gpu:1085.8431698921167
Step 2802 | loss:1.2877956628799438 lr:3.4666928148860763e-05 tokens_per_second_per_gpu:751.2477570749919
Step 2803 | loss:1.2424074411392212 lr:3.464674264196146e-05 tokens_per_second_per_gpu:1165.5259163882638
Step 2804 | loss:1.3170140981674194 lr:3.462655725257255e-05 tokens_per_second_per_gpu:904.060623562986
Step 2805 | loss:1.4960172176361084 lr:3.4606371987408616e-05 tokens_per_second_per_gpu:735.9062820541128
Step 2806 | loss:1.4676839113235474 lr:3.4586186853184296e-05 tokens_per_second_per_gpu:840.1173344152826
Step 2807 | loss:1.2942324876785278 lr:3.45660018566141e-05 tokens_per_second_per_gpu:1015.0487397397198
Step 2808 | loss:1.3849459886550903 lr:3.454581700441254e-05 tokens_per_second_per_gpu:751.2142359814065
Step 2809 | loss:1.2302656173706055 lr:3.452563230329407e-05 tokens_per_second_per_gpu:1002.8702629206535
Step 2810 | loss:1.2511500120162964 lr:3.4505447759973083e-05 tokens_per_second_per_gpu:904.4801996169854
Step 2811 | loss:1.3525198698043823 lr:3.448526338116395e-05 tokens_per_second_per_gpu:964.0556271808897
Step 2812 | loss:1.3129456043243408 lr:3.4465079173580936e-05 tokens_per_second_per_gpu:851.7424557771219
Step 2813 | loss:1.4621765613555908 lr:3.4444895143938314e-05 tokens_per_second_per_gpu:903.5030523673204
Step 2814 | loss:1.3156204223632812 lr:3.4424711298950215e-05 tokens_per_second_per_gpu:1167.116045375386
Step 2815 | loss:1.2938822507858276 lr:3.440452764533079e-05 tokens_per_second_per_gpu:872.0486133263746
Step 2816 | loss:1.2615737915039062 lr:3.4384344189794085e-05 tokens_per_second_per_gpu:893.8438864831847
Step 2817 | loss:1.2025203704833984 lr:3.436416093905408e-05 tokens_per_second_per_gpu:908.719321445586
Step 2818 | loss:1.4702075719833374 lr:3.4343977899824715e-05 tokens_per_second_per_gpu:809.6937351195276
Step 2819 | loss:1.4776253700256348 lr:3.43237950788198e-05 tokens_per_second_per_gpu:753.6968076587258
Step 2820 | loss:1.4393670558929443 lr:3.4303612482753134e-05 tokens_per_second_per_gpu:649.2972217445134
Step 2821 | loss:1.3234753608703613 lr:3.4283430118338444e-05 tokens_per_second_per_gpu:887.5819012640538
Step 2822 | loss:1.6731032133102417 lr:3.42632479922893e-05 tokens_per_second_per_gpu:750.9152917797362
Step 2823 | loss:1.4238156080245972 lr:3.42430661113193e-05 tokens_per_second_per_gpu:910.8175794858959
Step 2824 | loss:1.366012692451477 lr:3.4222884482141864e-05 tokens_per_second_per_gpu:909.7070456259004
Step 2825 | loss:1.2981643676757812 lr:3.420270311147041e-05 tokens_per_second_per_gpu:827.7242343347569
Step 2826 | loss:1.1557683944702148 lr:3.418252200601819e-05 tokens_per_second_per_gpu:1175.014790755036
Step 2827 | loss:1.2719521522521973 lr:3.416234117249843e-05 tokens_per_second_per_gpu:873.4906204719887
Step 2828 | loss:1.4344528913497925 lr:3.414216061762427e-05 tokens_per_second_per_gpu:1095.4457334280319
Step 2829 | loss:1.4234775304794312 lr:3.412198034810868e-05 tokens_per_second_per_gpu:1218.0934896622762
Step 2830 | loss:1.3442407846450806 lr:3.4101800370664646e-05 tokens_per_second_per_gpu:953.2245241460066
Step 2831 | loss:1.259817123413086 lr:3.408162069200494e-05 tokens_per_second_per_gpu:1064.814207445709
Step 2832 | loss:1.380410075187683 lr:3.406144131884233e-05 tokens_per_second_per_gpu:1007.0373418024589
Step 2833 | loss:1.2768172025680542 lr:3.4041262257889445e-05 tokens_per_second_per_gpu:1099.732018923003
Step 2834 | loss:1.4458726644515991 lr:3.4021083515858785e-05 tokens_per_second_per_gpu:892.7359563259458
Step 2835 | loss:1.370725154876709 lr:3.4000905099462805e-05 tokens_per_second_per_gpu:852.4172026482345
Step 2836 | loss:1.238867998123169 lr:3.398072701541378e-05 tokens_per_second_per_gpu:953.5207299966104
Step 2837 | loss:1.3044047355651855 lr:3.3960549270423944e-05 tokens_per_second_per_gpu:1198.5739717336658
Step 2838 | loss:1.3689303398132324 lr:3.394037187120534e-05 tokens_per_second_per_gpu:918.626546463519
Step 2839 | loss:1.2290644645690918 lr:3.3920194824469986e-05 tokens_per_second_per_gpu:835.0627288604718
Step 2840 | loss:1.3572981357574463 lr:3.390001813692972e-05 tokens_per_second_per_gpu:772.5469540244511
Step 2841 | loss:1.4308964014053345 lr:3.387984181529627e-05 tokens_per_second_per_gpu:810.5516998430461
Step 2842 | loss:1.2909643650054932 lr:3.385966586628126e-05 tokens_per_second_per_gpu:973.9140466241508
Step 2843 | loss:1.3446216583251953 lr:3.383949029659617e-05 tokens_per_second_per_gpu:760.8973724094526
Step 2844 | loss:1.2741689682006836 lr:3.381931511295238e-05 tokens_per_second_per_gpu:835.5299408250435
Step 2845 | loss:1.2620196342468262 lr:3.3799140322061106e-05 tokens_per_second_per_gpu:943.5905577298524
Step 2846 | loss:1.2299758195877075 lr:3.377896593063347e-05 tokens_per_second_per_gpu:1013.4233264531305
Step 2847 | loss:1.3041902780532837 lr:3.375879194538043e-05 tokens_per_second_per_gpu:1009.5907155391504
Step 2848 | loss:1.3606741428375244 lr:3.3738618373012844e-05 tokens_per_second_per_gpu:752.6753693511232
Step 2849 | loss:1.42697012424469 lr:3.371844522024139e-05 tokens_per_second_per_gpu:774.8048080783644
Step 2850 | loss:1.301574468612671 lr:3.369827249377663e-05 tokens_per_second_per_gpu:1088.029061071122
Step 2851 | loss:1.3128752708435059 lr:3.367810020032899e-05 tokens_per_second_per_gpu:877.264604835626
Step 2852 | loss:1.3224667310714722 lr:3.365792834660875e-05 tokens_per_second_per_gpu:925.5017685610751
Step 2853 | loss:1.3777188062667847 lr:3.3637756939326014e-05 tokens_per_second_per_gpu:801.5336824545755
Step 2854 | loss:1.4379459619522095 lr:3.36175859851908e-05 tokens_per_second_per_gpu:850.3596602093729
Step 2855 | loss:1.3818103075027466 lr:3.3597415490912885e-05 tokens_per_second_per_gpu:875.0974837206023
Step 2856 | loss:1.5034335851669312 lr:3.357724546320199e-05 tokens_per_second_per_gpu:944.6029706398213
Step 2857 | loss:1.2517282962799072 lr:3.355707590876761e-05 tokens_per_second_per_gpu:884.1856978688769
Step 2858 | loss:1.2750033140182495 lr:3.3536906834319115e-05 tokens_per_second_per_gpu:1076.44098636509
Step 2859 | loss:1.3342937231063843 lr:3.351673824656573e-05 tokens_per_second_per_gpu:855.2232261273493
Step 2860 | loss:1.2836213111877441 lr:3.349657015221645e-05 tokens_per_second_per_gpu:1006.1437760697107
Step 2861 | loss:1.3291192054748535 lr:3.34764025579802e-05 tokens_per_second_per_gpu:821.0178120009085
Step 2862 | loss:1.4533867835998535 lr:3.345623547056565e-05 tokens_per_second_per_gpu:1019.7493845232686
Step 2863 | loss:1.4659078121185303 lr:3.3436068896681366e-05 tokens_per_second_per_gpu:829.9016383602157
Step 2864 | loss:1.3889185190200806 lr:3.341590284303572e-05 tokens_per_second_per_gpu:834.8916473304657
Step 2865 | loss:1.432976484298706 lr:3.33957373163369e-05 tokens_per_second_per_gpu:794.2477906289803
Step 2866 | loss:1.409643292427063 lr:3.337557232329295e-05 tokens_per_second_per_gpu:757.9079485170643
Step 2867 | loss:1.454203724861145 lr:3.335540787061168e-05 tokens_per_second_per_gpu:709.8104327886304
Step 2868 | loss:1.2899490594863892 lr:3.3335243965000794e-05 tokens_per_second_per_gpu:996.1090857061065
Step 2869 | loss:1.3907380104064941 lr:3.331508061316774e-05 tokens_per_second_per_gpu:1148.4675068124336
Step 2870 | loss:1.37362539768219 lr:3.329491782181984e-05 tokens_per_second_per_gpu:769.9714468954801
Step 2871 | loss:1.2874733209609985 lr:3.327475559766421e-05 tokens_per_second_per_gpu:647.4403736826365
Step 2872 | loss:1.3617968559265137 lr:3.325459394740776e-05 tokens_per_second_per_gpu:790.5775990819083
Step 2873 | loss:1.3100444078445435 lr:3.323443287775724e-05 tokens_per_second_per_gpu:764.8109080201177
Step 2874 | loss:1.4100689888000488 lr:3.321427239541917e-05 tokens_per_second_per_gpu:856.9059991879902
Step 2875 | loss:1.2904008626937866 lr:3.319411250709991e-05 tokens_per_second_per_gpu:846.5162574631015
Step 2876 | loss:1.4471044540405273 lr:3.3173953219505616e-05 tokens_per_second_per_gpu:853.7862074884389
Step 2877 | loss:1.368263840675354 lr:3.315379453934221e-05 tokens_per_second_per_gpu:1089.0178984361596
Step 2878 | loss:1.4200536012649536 lr:3.313363647331546e-05 tokens_per_second_per_gpu:983.0073039858224
Step 2879 | loss:1.3428289890289307 lr:3.3113479028130896e-05 tokens_per_second_per_gpu:1106.0912368808506
Step 2880 | loss:1.4362006187438965 lr:3.309332221049386e-05 tokens_per_second_per_gpu:800.9650990988853
Step 2881 | loss:1.3802021741867065 lr:3.3073166027109466e-05 tokens_per_second_per_gpu:892.6511564044043
Step 2882 | loss:1.3928393125534058 lr:3.305301048468264e-05 tokens_per_second_per_gpu:967.6158116178267
Step 2883 | loss:1.476175308227539 lr:3.3032855589918085e-05 tokens_per_second_per_gpu:835.9665514202791
Step 2884 | loss:1.376705527305603 lr:3.301270134952027e-05 tokens_per_second_per_gpu:881.3183205785012
Step 2885 | loss:1.3070201873779297 lr:3.29925477701935e-05 tokens_per_second_per_gpu:906.4455714445156
Step 2886 | loss:1.2942965030670166 lr:3.2972394858641784e-05 tokens_per_second_per_gpu:866.0476662430902
Step 2887 | loss:1.3494391441345215 lr:3.295224262156897e-05 tokens_per_second_per_gpu:799.4666469625205
Step 2888 | loss:1.2787779569625854 lr:3.2932091065678655e-05 tokens_per_second_per_gpu:750.456376633218
Step 2889 | loss:1.441023826599121 lr:3.291194019767421e-05 tokens_per_second_per_gpu:648.7214042797624
Step 2890 | loss:1.530344009399414 lr:3.28917900242588e-05 tokens_per_second_per_gpu:726.8994535546748
Step 2891 | loss:1.2625008821487427 lr:3.287164055213532e-05 tokens_per_second_per_gpu:770.9892482493874
Step 2892 | loss:1.3527443408966064 lr:3.285149178800648e-05 tokens_per_second_per_gpu:928.9286129478157
Step 2893 | loss:1.4458606243133545 lr:3.2831343738574684e-05 tokens_per_second_per_gpu:642.1957981500195
Step 2894 | loss:1.3246824741363525 lr:3.2811196410542176e-05 tokens_per_second_per_gpu:1098.4935458490195
Step 2895 | loss:1.3018462657928467 lr:3.2791049810610916e-05 tokens_per_second_per_gpu:956.831249728029
Step 2896 | loss:1.558058738708496 lr:3.277090394548263e-05 tokens_per_second_per_gpu:592.5579092751972
Step 2897 | loss:1.4016212224960327 lr:3.2750758821858806e-05 tokens_per_second_per_gpu:914.3859532878167
Step 2898 | loss:1.3635112047195435 lr:3.273061444644066e-05 tokens_per_second_per_gpu:1030.5773241838885
Step 2899 | loss:1.3092451095581055 lr:3.271047082592921e-05 tokens_per_second_per_gpu:1043.2629013626643
Step 2900 | loss:1.4229133129119873 lr:3.269032796702517e-05 tokens_per_second_per_gpu:843.3954176753009
Step 2901 | loss:1.4177420139312744 lr:3.267018587642903e-05 tokens_per_second_per_gpu:773.4862079582526
Step 2902 | loss:1.3081251382827759 lr:3.265004456084102e-05 tokens_per_second_per_gpu:1204.060811997438
Step 2903 | loss:1.6052452325820923 lr:3.262990402696111e-05 tokens_per_second_per_gpu:703.953839671577
Step 2904 | loss:1.4262057542800903 lr:3.2609764281489e-05 tokens_per_second_per_gpu:824.4693065600093
Step 2905 | loss:1.3467860221862793 lr:3.258962533112414e-05 tokens_per_second_per_gpu:706.3416373808526
Step 2906 | loss:1.3407896757125854 lr:3.256948718256571e-05 tokens_per_second_per_gpu:866.6426458003406
Step 2907 | loss:1.2007358074188232 lr:3.2549349842512635e-05 tokens_per_second_per_gpu:1228.6347037395933
Step 2908 | loss:1.3532236814498901 lr:3.252921331766356e-05 tokens_per_second_per_gpu:1031.6027697785112
Step 2909 | loss:1.2922756671905518 lr:3.250907761471686e-05 tokens_per_second_per_gpu:809.1210198673419
Step 2910 | loss:1.3189759254455566 lr:3.2488942740370637e-05 tokens_per_second_per_gpu:951.9105974835932
Step 2911 | loss:1.1840044260025024 lr:3.246880870132272e-05 tokens_per_second_per_gpu:838.7397309005394
Step 2912 | loss:1.2814011573791504 lr:3.244867550427065e-05 tokens_per_second_per_gpu:915.5429166577782
Step 2913 | loss:1.376953363418579 lr:3.242854315591169e-05 tokens_per_second_per_gpu:691.189250104522
Step 2914 | loss:1.4631099700927734 lr:3.2408411662942855e-05 tokens_per_second_per_gpu:753.8836575035793
Step 2915 | loss:1.484009027481079 lr:3.238828103206081e-05 tokens_per_second_per_gpu:875.2474597970885
Step 2916 | loss:1.466633677482605 lr:3.2368151269962e-05 tokens_per_second_per_gpu:927.399963811953
Step 2917 | loss:1.349614143371582 lr:3.234802238334254e-05 tokens_per_second_per_gpu:1028.802416549897
Step 2918 | loss:1.3794785737991333 lr:3.2327894378898264e-05 tokens_per_second_per_gpu:921.7463024513362
Step 2919 | loss:1.4837417602539062 lr:3.230776726332471e-05 tokens_per_second_per_gpu:1046.6990544965684
Step 2920 | loss:1.328494906425476 lr:3.228764104331712e-05 tokens_per_second_per_gpu:998.9854111883193
Step 2921 | loss:1.3932173252105713 lr:3.2267515725570466e-05 tokens_per_second_per_gpu:755.330278877418
Step 2922 | loss:1.4170315265655518 lr:3.2247391316779366e-05 tokens_per_second_per_gpu:970.9322150194307
Step 2923 | loss:1.2989474534988403 lr:3.2227267823638194e-05 tokens_per_second_per_gpu:973.5666882151309
Step 2924 | loss:1.4099653959274292 lr:3.220714525284096e-05 tokens_per_second_per_gpu:787.5821408193045
Step 2925 | loss:1.4680460691452026 lr:3.2187023611081415e-05 tokens_per_second_per_gpu:1188.230056251764
Step 2926 | loss:1.4176908731460571 lr:3.2166902905052994e-05 tokens_per_second_per_gpu:730.5234589520456
Step 2927 | loss:1.4280035495758057 lr:3.2146783141448785e-05 tokens_per_second_per_gpu:695.6246246942753
Step 2928 | loss:1.310760498046875 lr:3.2126664326961616e-05 tokens_per_second_per_gpu:1128.1491764607922
Step 2929 | loss:1.1601817607879639 lr:3.210654646828395e-05 tokens_per_second_per_gpu:911.9955591570103
Step 2930 | loss:1.3195209503173828 lr:3.2086429572107965e-05 tokens_per_second_per_gpu:1052.1041181299413
Step 2931 | loss:1.2267284393310547 lr:3.206631364512549e-05 tokens_per_second_per_gpu:867.0868341422944
Step 2932 | loss:1.2384870052337646 lr:3.204619869402807e-05 tokens_per_second_per_gpu:902.9828031967872
Step 2933 | loss:1.318438172340393 lr:3.2026084725506905e-05 tokens_per_second_per_gpu:1023.2977464967827
Step 2934 | loss:1.4048978090286255 lr:3.200597174625285e-05 tokens_per_second_per_gpu:822.752509023955
Step 2935 | loss:1.3147271871566772 lr:3.198585976295647e-05 tokens_per_second_per_gpu:947.4376806400052
Step 2936 | loss:1.300288200378418 lr:3.1965748782307944e-05 tokens_per_second_per_gpu:755.6835165839324
Step 2937 | loss:1.2523504495620728 lr:3.1945638810997176e-05 tokens_per_second_per_gpu:715.3901751566608
Step 2938 | loss:1.2948459386825562 lr:3.192552985571372e-05 tokens_per_second_per_gpu:976.1846544219505
Step 2939 | loss:1.1903406381607056 lr:3.1905421923146744e-05 tokens_per_second_per_gpu:929.0987122670335
Step 2940 | loss:1.4167327880859375 lr:3.188531501998515e-05 tokens_per_second_per_gpu:775.4249847594374
Step 2941 | loss:1.2301186323165894 lr:3.1865209152917425e-05 tokens_per_second_per_gpu:1113.092547321434
Step 2942 | loss:1.3338618278503418 lr:3.1845104328631784e-05 tokens_per_second_per_gpu:949.0189135887235
Step 2943 | loss:1.4875999689102173 lr:3.182500055381603e-05 tokens_per_second_per_gpu:898.0936158464399
Step 2944 | loss:1.4257633686065674 lr:3.180489783515764e-05 tokens_per_second_per_gpu:811.4613696059373
Step 2945 | loss:1.3532685041427612 lr:3.178479617934377e-05 tokens_per_second_per_gpu:762.3966607741964
Step 2946 | loss:1.3582632541656494 lr:3.176469559306118e-05 tokens_per_second_per_gpu:1007.0802882599169
Step 2947 | loss:1.4430817365646362 lr:3.174459608299631e-05 tokens_per_second_per_gpu:762.3885382164254
Step 2948 | loss:1.2778137922286987 lr:3.1724497655835184e-05 tokens_per_second_per_gpu:881.3666733749357
Step 2949 | loss:1.324215292930603 lr:3.170440031826353e-05 tokens_per_second_per_gpu:675.164879226856
Step 2950 | loss:1.3786966800689697 lr:3.16843040769667e-05 tokens_per_second_per_gpu:905.0700196964551
Step 2951 | loss:1.5943853855133057 lr:3.166420893862964e-05 tokens_per_second_per_gpu:841.2458271802358
Step 2952 | loss:1.265604019165039 lr:3.164411490993699e-05 tokens_per_second_per_gpu:810.7812924275787
Step 2953 | loss:1.321862816810608 lr:3.162402199757296e-05 tokens_per_second_per_gpu:771.2458326235654
Step 2954 | loss:1.236114501953125 lr:3.160393020822145e-05 tokens_per_second_per_gpu:1045.4384105502086
Step 2955 | loss:1.4612663984298706 lr:3.1583839548565914e-05 tokens_per_second_per_gpu:1032.077966176656
Step 2956 | loss:1.4166194200515747 lr:3.1563750025289504e-05 tokens_per_second_per_gpu:660.7082294757765
Step 2957 | loss:1.2979729175567627 lr:3.1543661645074944e-05 tokens_per_second_per_gpu:938.1393620361703
Step 2958 | loss:1.3927712440490723 lr:3.15235744146046e-05 tokens_per_second_per_gpu:867.2418135107959
Step 2959 | loss:1.4651439189910889 lr:3.150348834056047e-05 tokens_per_second_per_gpu:1103.1447292516468
Step 2960 | loss:1.2449822425842285 lr:3.1483403429624095e-05 tokens_per_second_per_gpu:1360.215248764533
Step 2961 | loss:1.2628601789474487 lr:3.146331968847675e-05 tokens_per_second_per_gpu:833.4481695463601
Step 2962 | loss:1.1897263526916504 lr:3.144323712379918e-05 tokens_per_second_per_gpu:949.9751240040575
Step 2963 | loss:1.383542537689209 lr:3.142315574227187e-05 tokens_per_second_per_gpu:1048.1829703442756
Step 2964 | loss:1.4657858610153198 lr:3.140307555057483e-05 tokens_per_second_per_gpu:817.1183118510035
Step 2965 | loss:1.364851474761963 lr:3.138299655538769e-05 tokens_per_second_per_gpu:758.1614668955664
Step 2966 | loss:1.2505682706832886 lr:3.13629187633897e-05 tokens_per_second_per_gpu:1003.5052108911108
Step 2967 | loss:1.277479887008667 lr:3.1342842181259686e-05 tokens_per_second_per_gpu:693.1014967466647
Step 2968 | loss:1.3348664045333862 lr:3.132276681567609e-05 tokens_per_second_per_gpu:1042.3644883718077
Step 2969 | loss:1.3615871667861938 lr:3.130269267331696e-05 tokens_per_second_per_gpu:749.1094196278851
Step 2970 | loss:1.3716940879821777 lr:3.1282619760859884e-05 tokens_per_second_per_gpu:788.3518155883077
Step 2971 | loss:1.4347079992294312 lr:3.126254808498211e-05 tokens_per_second_per_gpu:815.2207926389577
Step 2972 | loss:1.3234519958496094 lr:3.124247765236043e-05 tokens_per_second_per_gpu:950.6839378946753
Step 2973 | loss:1.3039644956588745 lr:3.122240846967124e-05 tokens_per_second_per_gpu:1007.1621334261063
Step 2974 | loss:1.2886366844177246 lr:3.1202340543590496e-05 tokens_per_second_per_gpu:1229.5061459876588
Step 2975 | loss:1.4048893451690674 lr:3.118227388079377e-05 tokens_per_second_per_gpu:669.4699429704382
Step 2976 | loss:1.1468427181243896 lr:3.1162208487956206e-05 tokens_per_second_per_gpu:1202.8724806980101
Step 2977 | loss:1.2311127185821533 lr:3.1142144371752496e-05 tokens_per_second_per_gpu:1382.0099366018703
Step 2978 | loss:1.3498057126998901 lr:3.112208153885695e-05 tokens_per_second_per_gpu:1130.396865305872
Step 2979 | loss:1.4601293802261353 lr:3.110201999594341e-05 tokens_per_second_per_gpu:1014.2797001952445
Step 2980 | loss:1.276840329170227 lr:3.108195974968532e-05 tokens_per_second_per_gpu:929.8307100355082
Step 2981 | loss:1.422768235206604 lr:3.10619008067557e-05 tokens_per_second_per_gpu:925.8684276610695
Step 2982 | loss:1.3681713342666626 lr:3.1041843173827074e-05 tokens_per_second_per_gpu:760.0068607868532
Step 2983 | loss:1.3142688274383545 lr:3.1021786857571626e-05 tokens_per_second_per_gpu:972.038806350805
Step 2984 | loss:1.271079659461975 lr:3.1001731864661e-05 tokens_per_second_per_gpu:844.2888887703582
Step 2985 | loss:1.4127429723739624 lr:3.09816782017665e-05 tokens_per_second_per_gpu:740.9959533396272
Step 2986 | loss:1.4054234027862549 lr:3.0961625875558896e-05 tokens_per_second_per_gpu:957.5664501847771
Step 2987 | loss:1.3415226936340332 lr:3.094157489270857e-05 tokens_per_second_per_gpu:1123.7637112607713
Step 2988 | loss:1.3251984119415283 lr:3.0921525259885463e-05 tokens_per_second_per_gpu:937.5210499854516
Step 2989 | loss:1.5465145111083984 lr:3.090147698375901e-05 tokens_per_second_per_gpu:826.1475133985807
Step 2990 | loss:1.4076964855194092 lr:3.088143007099826e-05 tokens_per_second_per_gpu:918.154408115155
Step 2991 | loss:1.481111764907837 lr:3.086138452827176e-05 tokens_per_second_per_gpu:707.1279842048001
Step 2992 | loss:1.2551052570343018 lr:3.084134036224764e-05 tokens_per_second_per_gpu:1244.962014029479
Step 2993 | loss:1.361176609992981 lr:3.082129757959353e-05 tokens_per_second_per_gpu:982.3650784811147
Step 2994 | loss:1.3166533708572388 lr:3.0801256186976634e-05 tokens_per_second_per_gpu:1226.0932442776902
Step 2995 | loss:1.2865636348724365 lr:3.07812161910637e-05 tokens_per_second_per_gpu:722.7013788029805
Step 2996 | loss:1.4582842588424683 lr:3.076117759852096e-05 tokens_per_second_per_gpu:895.7090114501862
Step 2997 | loss:1.3348336219787598 lr:3.0741140416014234e-05 tokens_per_second_per_gpu:1039.371637992621
Step 2998 | loss:1.3410627841949463 lr:3.072110465020884e-05 tokens_per_second_per_gpu:1138.7047769869891
Step 2999 | loss:1.2460331916809082 lr:3.0701070307769646e-05 tokens_per_second_per_gpu:951.7331182842012
Step 3000 | loss:1.244443655014038 lr:3.0681037395361045e-05 tokens_per_second_per_gpu:942.1338510056055
Step 3001 | loss:1.2426996231079102 lr:3.0661005919646924e-05 tokens_per_second_per_gpu:1151.7915515995142
Step 3002 | loss:1.3252038955688477 lr:3.0640975887290734e-05 tokens_per_second_per_gpu:901.454704436898
Step 3003 | loss:1.344317078590393 lr:3.062094730495541e-05 tokens_per_second_per_gpu:1155.8231546623515
Step 3004 | loss:1.3035862445831299 lr:3.060092017930344e-05 tokens_per_second_per_gpu:1003.9054554619144
Step 3005 | loss:1.2886308431625366 lr:3.058089451699678e-05 tokens_per_second_per_gpu:898.6886792117062
Step 3006 | loss:1.4324017763137817 lr:3.0560870324696947e-05 tokens_per_second_per_gpu:938.0307255785696
Step 3007 | loss:1.2529217004776 lr:3.054084760906496e-05 tokens_per_second_per_gpu:821.6344710128452
Step 3008 | loss:1.4317240715026855 lr:3.052082637676132e-05 tokens_per_second_per_gpu:761.0741402162287
Step 3009 | loss:1.2884695529937744 lr:3.0500806634446056e-05 tokens_per_second_per_gpu:1010.9001667794546
Step 3010 | loss:1.312328815460205 lr:3.0480788388778682e-05 tokens_per_second_per_gpu:1080.7350105944456
Step 3011 | loss:1.3844135999679565 lr:3.046077164641824e-05 tokens_per_second_per_gpu:913.3431011579863
Step 3012 | loss:1.4185254573822021 lr:3.0440756414023282e-05 tokens_per_second_per_gpu:678.4716481903698
Step 3013 | loss:1.3701376914978027 lr:3.0420742698251796e-05 tokens_per_second_per_gpu:915.5359522462448
Step 3014 | loss:1.3910616636276245 lr:3.0400730505761344e-05 tokens_per_second_per_gpu:914.7897367823226
Step 3015 | loss:1.5374964475631714 lr:3.038071984320891e-05 tokens_per_second_per_gpu:711.1770792222504
Step 3016 | loss:1.3702671527862549 lr:3.0360710717251023e-05 tokens_per_second_per_gpu:878.3490438770244
Step 3017 | loss:1.382182002067566 lr:3.0340703134543663e-05 tokens_per_second_per_gpu:786.6157290682138
Step 3018 | loss:1.4164884090423584 lr:3.0320697101742326e-05 tokens_per_second_per_gpu:896.2248572154678
Step 3019 | loss:1.3288142681121826 lr:3.030069262550198e-05 tokens_per_second_per_gpu:1209.5010871638585
Step 3020 | loss:1.4735063314437866 lr:3.0280689712477074e-05 tokens_per_second_per_gpu:893.5571240750312
Step 3021 | loss:1.3626627922058105 lr:3.0260688369321527e-05 tokens_per_second_per_gpu:785.0920462843951
Step 3022 | loss:1.426220417022705 lr:3.0240688602688757e-05 tokens_per_second_per_gpu:686.1219857834706
Step 3023 | loss:1.1967133283615112 lr:3.022069041923165e-05 tokens_per_second_per_gpu:1119.35349794908
Step 3024 | loss:1.3902831077575684 lr:3.0200693825602554e-05 tokens_per_second_per_gpu:932.691207700489
Step 3025 | loss:1.497757911682129 lr:3.018069882845331e-05 tokens_per_second_per_gpu:939.6155955125777
Step 3026 | loss:1.399024486541748 lr:3.01607054344352e-05 tokens_per_second_per_gpu:826.631780708188
Step 3027 | loss:1.3020720481872559 lr:3.0140713650198997e-05 tokens_per_second_per_gpu:1112.2826170105707
Step 3028 | loss:1.2448617219924927 lr:3.0120723482394927e-05 tokens_per_second_per_gpu:825.1321937336885
Step 3029 | loss:1.451857089996338 lr:3.0100734937672677e-05 tokens_per_second_per_gpu:915.6949784466849
Step 3030 | loss:1.4292939901351929 lr:3.008074802268139e-05 tokens_per_second_per_gpu:847.9834085725355
Step 3031 | loss:1.2339709997177124 lr:3.0060762744069704e-05 tokens_per_second_per_gpu:807.8239881717932
Step 3032 | loss:1.368245244026184 lr:3.0040779108485643e-05 tokens_per_second_per_gpu:906.8029350408627
Step 3033 | loss:1.2631648778915405 lr:3.002079712257676e-05 tokens_per_second_per_gpu:972.0423350193183
Step 3034 | loss:1.189917802810669 lr:3.0000816792989995e-05 tokens_per_second_per_gpu:913.8463104331998
Step 3035 | loss:1.401140809059143 lr:2.998083812637179e-05 tokens_per_second_per_gpu:878.7101396181569
Step 3036 | loss:1.3994005918502808 lr:2.9960861129367992e-05 tokens_per_second_per_gpu:861.4154888446525
Step 3037 | loss:1.2188270092010498 lr:2.9940885808623912e-05 tokens_per_second_per_gpu:1024.7569844960608
Step 3038 | loss:1.2878047227859497 lr:2.992091217078432e-05 tokens_per_second_per_gpu:1128.9273261976377
Step 3039 | loss:1.3724608421325684 lr:2.990094022249338e-05 tokens_per_second_per_gpu:876.8941150954233
Step 3040 | loss:1.4262776374816895 lr:2.9880969970394744e-05 tokens_per_second_per_gpu:832.6474522020426
Step 3041 | loss:1.3382023572921753 lr:2.986100142113146e-05 tokens_per_second_per_gpu:1138.4290642233263
Step 3042 | loss:1.5237963199615479 lr:2.9841034581346034e-05 tokens_per_second_per_gpu:739.6331421427307
Step 3043 | loss:1.3481072187423706 lr:2.9821069457680413e-05 tokens_per_second_per_gpu:821.1973035825829
Step 3044 | loss:1.2005693912506104 lr:2.9801106056775922e-05 tokens_per_second_per_gpu:1214.0534651002483
Step 3045 | loss:1.456040382385254 lr:2.978114438527339e-05 tokens_per_second_per_gpu:900.249247957976
Step 3046 | loss:1.2264395952224731 lr:2.9761184449812983e-05 tokens_per_second_per_gpu:918.6879875768238
Step 3047 | loss:1.394782543182373 lr:2.9741226257034377e-05 tokens_per_second_per_gpu:735.6726573592649
Step 3048 | loss:1.2922254800796509 lr:2.972126981357659e-05 tokens_per_second_per_gpu:844.1916223914332
Step 3049 | loss:1.4048435688018799 lr:2.9701315126078107e-05 tokens_per_second_per_gpu:884.6348489538237
Step 3050 | loss:1.3753376007080078 lr:2.9681362201176833e-05 tokens_per_second_per_gpu:840.6611241346334
Step 3051 | loss:1.4614181518554688 lr:2.966141104551004e-05 tokens_per_second_per_gpu:841.9135057785578
Step 3052 | loss:1.2997349500656128 lr:2.9641461665714473e-05 tokens_per_second_per_gpu:875.1457760006266
Step 3053 | loss:1.3533076047897339 lr:2.962151406842622e-05 tokens_per_second_per_gpu:918.3366872074813
Step 3054 | loss:1.2667262554168701 lr:2.960156826028083e-05 tokens_per_second_per_gpu:753.5341612970067
Step 3055 | loss:1.4611551761627197 lr:2.9581624247913253e-05 tokens_per_second_per_gpu:955.5544913155765
Step 3056 | loss:1.2906872034072876 lr:2.9561682037957785e-05 tokens_per_second_per_gpu:851.4759086571186
Step 3057 | loss:1.387764811515808 lr:2.9541741637048205e-05 tokens_per_second_per_gpu:698.6560597179916
Step 3058 | loss:1.5634987354278564 lr:2.9521803051817614e-05 tokens_per_second_per_gpu:1189.9938562155198
Step 3059 | loss:1.4197142124176025 lr:2.9501866288898574e-05 tokens_per_second_per_gpu:837.1707946472027
Step 3060 | loss:1.330687403678894 lr:2.9481931354922978e-05 tokens_per_second_per_gpu:935.9932808037354
Step 3061 | loss:1.3384652137756348 lr:2.9461998256522164e-05 tokens_per_second_per_gpu:829.4284993499208
Step 3062 | loss:1.282615065574646 lr:2.9442067000326847e-05 tokens_per_second_per_gpu:1045.5209818758524
Step 3063 | loss:1.3912954330444336 lr:2.9422137592967097e-05 tokens_per_second_per_gpu:844.8707514061665
Step 3064 | loss:1.3742117881774902 lr:2.9402210041072416e-05 tokens_per_second_per_gpu:1092.8251790319505
Step 3065 | loss:1.361764669418335 lr:2.9382284351271635e-05 tokens_per_second_per_gpu:937.5753016022378
Step 3066 | loss:1.3526694774627686 lr:2.9362360530193035e-05 tokens_per_second_per_gpu:960.287892414067
Step 3067 | loss:1.1865944862365723 lr:2.9342438584464195e-05 tokens_per_second_per_gpu:884.0390632733073
Step 3068 | loss:1.3150761127471924 lr:2.9322518520712134e-05 tokens_per_second_per_gpu:1335.0973685389952
Step 3069 | loss:1.4486716985702515 lr:2.930260034556323e-05 tokens_per_second_per_gpu:1279.2160607657725
Step 3070 | loss:1.3359931707382202 lr:2.9282684065643203e-05 tokens_per_second_per_gpu:880.415283980088
Step 3071 | loss:1.297813057899475 lr:2.9262769687577195e-05 tokens_per_second_per_gpu:952.8899945223658
Step 3072 | loss:1.4035099744796753 lr:2.9242857217989648e-05 tokens_per_second_per_gpu:728.416831666492
Step 3073 | loss:1.3383877277374268 lr:2.9222946663504428e-05 tokens_per_second_per_gpu:836.0969233450742
Step 3074 | loss:1.3507094383239746 lr:2.920303803074475e-05 tokens_per_second_per_gpu:1041.9063404500903
Step 3075 | loss:1.3706833124160767 lr:2.9183131326333155e-05 tokens_per_second_per_gpu:641.3402487102865
Step 3076 | loss:1.4204562902450562 lr:2.9163226556891603e-05 tokens_per_second_per_gpu:623.6307433188733
Step 3077 | loss:1.6290748119354248 lr:2.9143323729041345e-05 tokens_per_second_per_gpu:578.4570211334619
Step 3078 | loss:1.2533550262451172 lr:2.9123422849403047e-05 tokens_per_second_per_gpu:1192.830657103684
Step 3079 | loss:1.2225388288497925 lr:2.910352392459667e-05 tokens_per_second_per_gpu:1074.678578056798
Step 3080 | loss:1.487231731414795 lr:2.9083626961241566e-05 tokens_per_second_per_gpu:923.0515626742465
Step 3081 | loss:1.3896362781524658 lr:2.9063731965956423e-05 tokens_per_second_per_gpu:944.8530583299806
Step 3082 | loss:1.4220449924468994 lr:2.904383894535927e-05 tokens_per_second_per_gpu:849.3507136396707
Step 3083 | loss:1.4369351863861084 lr:2.902394790606748e-05 tokens_per_second_per_gpu:783.2296392418978
Step 3084 | loss:1.2136152982711792 lr:2.9004058854697776e-05 tokens_per_second_per_gpu:990.3410843332088
Step 3085 | loss:1.5582623481750488 lr:2.8984171797866188e-05 tokens_per_second_per_gpu:816.4453540782648
Step 3086 | loss:1.2478941679000854 lr:2.896428674218814e-05 tokens_per_second_per_gpu:1057.0413622937167
Step 3087 | loss:1.502173900604248 lr:2.894440369427834e-05 tokens_per_second_per_gpu:887.8744080991607
Step 3088 | loss:1.3116579055786133 lr:2.8924522660750843e-05 tokens_per_second_per_gpu:858.2579029173504
Step 3089 | loss:1.2907600402832031 lr:2.8904643648219046e-05 tokens_per_second_per_gpu:1037.271154350033
Step 3090 | loss:1.176173210144043 lr:2.8884766663295653e-05 tokens_per_second_per_gpu:997.2518374780565
Step 3091 | loss:1.3128663301467896 lr:2.8864891712592712e-05 tokens_per_second_per_gpu:1013.9936515538085
Step 3092 | loss:1.456488847732544 lr:2.8845018802721572e-05 tokens_per_second_per_gpu:781.6519612731616
Step 3093 | loss:1.3482688665390015 lr:2.8825147940292947e-05 tokens_per_second_per_gpu:856.8052646721693
Step 3094 | loss:1.3438841104507446 lr:2.880527913191681e-05 tokens_per_second_per_gpu:795.8950014513593
Step 3095 | loss:1.1880146265029907 lr:2.8785412384202503e-05 tokens_per_second_per_gpu:998.6396491162128
Step 3096 | loss:1.455906867980957 lr:2.8765547703758642e-05 tokens_per_second_per_gpu:972.3758745513475
Step 3097 | loss:1.4723708629608154 lr:2.874568509719319e-05 tokens_per_second_per_gpu:678.2329131495452
Step 3098 | loss:1.3573840856552124 lr:2.8725824571113402e-05 tokens_per_second_per_gpu:901.5743485448029
Step 3099 | loss:1.4708433151245117 lr:2.8705966132125826e-05 tokens_per_second_per_gpu:798.0371389851791
Step 3100 | loss:1.3230149745941162 lr:2.8686109786836363e-05 tokens_per_second_per_gpu:743.7748592740771
Step 3101 | loss:1.2746291160583496 lr:2.8666255541850162e-05 tokens_per_second_per_gpu:841.7348480765753
Step 3102 | loss:1.3717035055160522 lr:2.864640340377172e-05 tokens_per_second_per_gpu:829.8451110274705
Step 3103 | loss:1.2095810174942017 lr:2.8626553379204785e-05 tokens_per_second_per_gpu:1186.4722671211432
Step 3104 | loss:1.2906948328018188 lr:2.8606705474752445e-05 tokens_per_second_per_gpu:1106.3675721641453
Step 3105 | loss:1.2884762287139893 lr:2.8586859697017083e-05 tokens_per_second_per_gpu:1082.4574899394836
Step 3106 | loss:1.3244842290878296 lr:2.8567016052600326e-05 tokens_per_second_per_gpu:969.9486717004712
Step 3107 | loss:1.3990037441253662 lr:2.854717454810315e-05 tokens_per_second_per_gpu:1038.4966931049094
Step 3108 | loss:1.3125534057617188 lr:2.852733519012577e-05 tokens_per_second_per_gpu:793.2148782116781
Step 3109 | loss:1.4775851964950562 lr:2.8507497985267738e-05 tokens_per_second_per_gpu:719.627680018609
Step 3110 | loss:1.266894817352295 lr:2.848766294012783e-05 tokens_per_second_per_gpu:1010.6959804031534
Step 3111 | loss:1.337516188621521 lr:2.8467830061304146e-05 tokens_per_second_per_gpu:858.7393741003118
Step 3112 | loss:1.2503069639205933 lr:2.844799935539408e-05 tokens_per_second_per_gpu:1138.391991398872
Step 3113 | loss:1.3652039766311646 lr:2.8428170828994237e-05 tokens_per_second_per_gpu:763.5142699535271
Step 3114 | loss:1.4758073091506958 lr:2.8408344488700572e-05 tokens_per_second_per_gpu:656.125262418898
Step 3115 | loss:1.4859066009521484 lr:2.8388520341108248e-05 tokens_per_second_per_gpu:848.5245863058122
Step 3116 | loss:1.3580995798110962 lr:2.8368698392811746e-05 tokens_per_second_per_gpu:909.6761900585286
Step 3117 | loss:1.2171447277069092 lr:2.8348878650404815e-05 tokens_per_second_per_gpu:898.0677557376033
Step 3118 | loss:1.2883391380310059 lr:2.8329061120480414e-05 tokens_per_second_per_gpu:902.1738594251643
Step 3119 | loss:1.476719617843628 lr:2.8309245809630845e-05 tokens_per_second_per_gpu:932.0691591668829
Step 3120 | loss:1.1798664331436157 lr:2.8289432724447603e-05 tokens_per_second_per_gpu:989.223713474651
Step 3121 | loss:1.2835522890090942 lr:2.82696218715215e-05 tokens_per_second_per_gpu:855.045094690822
Step 3122 | loss:1.4811214208602905 lr:2.8249813257442543e-05 tokens_per_second_per_gpu:1015.9652662517996
Step 3123 | loss:1.3762495517730713 lr:2.823000688880005e-05 tokens_per_second_per_gpu:1097.5167138491774
Step 3124 | loss:1.1873847246170044 lr:2.821020277218258e-05 tokens_per_second_per_gpu:1328.2606090431827
Step 3125 | loss:1.4604471921920776 lr:2.8190400914177907e-05 tokens_per_second_per_gpu:627.0919034956775
Step 3126 | loss:1.3269548416137695 lr:2.8170601321373113e-05 tokens_per_second_per_gpu:839.7909001692018
Step 3127 | loss:1.3046072721481323 lr:2.8150804000354462e-05 tokens_per_second_per_gpu:971.0019512030261
Step 3128 | loss:1.4142297506332397 lr:2.813100895770751e-05 tokens_per_second_per_gpu:701.5590414991343
Step 3129 | loss:1.3634953498840332 lr:2.811121620001705e-05 tokens_per_second_per_gpu:600.4278057914595
Step 3130 | loss:1.2416361570358276 lr:2.8091425733867077e-05 tokens_per_second_per_gpu:960.8567839629865
Step 3131 | loss:1.2541624307632446 lr:2.8071637565840887e-05 tokens_per_second_per_gpu:1068.7624968815608
Step 3132 | loss:1.3602807521820068 lr:2.8051851702520935e-05 tokens_per_second_per_gpu:941.008356529481
Step 3133 | loss:1.1841709613800049 lr:2.8032068150488987e-05 tokens_per_second_per_gpu:984.8983711905255
Step 3134 | loss:1.3092148303985596 lr:2.801228691632597e-05 tokens_per_second_per_gpu:894.6305501656002
Step 3135 | loss:1.250101089477539 lr:2.7992508006612097e-05 tokens_per_second_per_gpu:1168.5588906598778
Step 3136 | loss:1.377395510673523 lr:2.7972731427926776e-05 tokens_per_second_per_gpu:943.0108413766459
Step 3137 | loss:1.499973177909851 lr:2.7952957186848638e-05 tokens_per_second_per_gpu:697.4056891687054
Step 3138 | loss:1.351324200630188 lr:2.7933185289955574e-05 tokens_per_second_per_gpu:818.7236191374402
Step 3139 | loss:1.2837165594100952 lr:2.7913415743824626e-05 tokens_per_second_per_gpu:1230.8634742425763
Step 3140 | loss:1.2113542556762695 lr:2.7893648555032137e-05 tokens_per_second_per_gpu:1347.212420316459
Step 3141 | loss:1.2570080757141113 lr:2.787388373015359e-05 tokens_per_second_per_gpu:1246.0175448279324
Step 3142 | loss:1.4273003339767456 lr:2.785412127576373e-05 tokens_per_second_per_gpu:775.6331563763853
Step 3143 | loss:1.4138991832733154 lr:2.78343611984365e-05 tokens_per_second_per_gpu:829.3679125820861
Step 3144 | loss:1.2009581327438354 lr:2.781460350474505e-05 tokens_per_second_per_gpu:1016.4972429667916
Step 3145 | loss:1.3207159042358398 lr:2.7794848201261742e-05 tokens_per_second_per_gpu:685.2380930261828
Step 3146 | loss:1.369956135749817 lr:2.7775095294558127e-05 tokens_per_second_per_gpu:919.8693983683032
Step 3147 | loss:1.3479551076889038 lr:2.7755344791204974e-05 tokens_per_second_per_gpu:987.3256537736762
Step 3148 | loss:1.3052855730056763 lr:2.7735596697772262e-05 tokens_per_second_per_gpu:1083.2962941393341
Step 3149 | loss:1.158212661743164 lr:2.771585102082915e-05 tokens_per_second_per_gpu:899.0592802111045
Step 3150 | loss:1.4227864742279053 lr:2.769610776694399e-05 tokens_per_second_per_gpu:740.8599443649191
Step 3151 | loss:1.3267048597335815 lr:2.7676366942684348e-05 tokens_per_second_per_gpu:965.6357617868142
Step 3152 | loss:1.1646710634231567 lr:2.765662855461697e-05 tokens_per_second_per_gpu:1009.1526146197962
Step 3153 | loss:1.3217227458953857 lr:2.7636892609307785e-05 tokens_per_second_per_gpu:838.5002504401307
Step 3154 | loss:1.329770803451538 lr:2.761715911332191e-05 tokens_per_second_per_gpu:857.6413840071008
Step 3155 | loss:1.353236436843872 lr:2.7597428073223685e-05 tokens_per_second_per_gpu:838.7938022721743
Step 3156 | loss:1.3784213066101074 lr:2.757769949557656e-05 tokens_per_second_per_gpu:974.0608563612841
Step 3157 | loss:1.478559136390686 lr:2.755797338694325e-05 tokens_per_second_per_gpu:876.2770824168115
Step 3158 | loss:1.4241797924041748 lr:2.7538249753885565e-05 tokens_per_second_per_gpu:759.3593222689922
Step 3159 | loss:1.2707442045211792 lr:2.751852860296456e-05 tokens_per_second_per_gpu:1150.7765612482149
Step 3160 | loss:1.3920881748199463 lr:2.7498809940740446e-05 tokens_per_second_per_gpu:725.1306583194377
Step 3161 | loss:1.1745566129684448 lr:2.7479093773772563e-05 tokens_per_second_per_gpu:1020.6705222575531
Step 3162 | loss:1.3329344987869263 lr:2.7459380108619492e-05 tokens_per_second_per_gpu:872.6047361373122
Step 3163 | loss:1.355647325515747 lr:2.7439668951838916e-05 tokens_per_second_per_gpu:888.1920247023886
Step 3164 | loss:1.4347833395004272 lr:2.741996030998774e-05 tokens_per_second_per_gpu:708.1928588817585
Step 3165 | loss:1.388589859008789 lr:2.7400254189621973e-05 tokens_per_second_per_gpu:639.6341047317526
Step 3166 | loss:1.4658950567245483 lr:2.738055059729684e-05 tokens_per_second_per_gpu:711.6165810329824
Step 3167 | loss:1.322270393371582 lr:2.7360849539566707e-05 tokens_per_second_per_gpu:1229.0377354189518
Step 3168 | loss:1.4744817018508911 lr:2.7341151022985074e-05 tokens_per_second_per_gpu:981.3945212091005
Step 3169 | loss:1.5125240087509155 lr:2.7321455054104636e-05 tokens_per_second_per_gpu:900.2671776086236
Step 3170 | loss:1.3582258224487305 lr:2.730176163947719e-05 tokens_per_second_per_gpu:838.9775099544022
Step 3171 | loss:1.2409240007400513 lr:2.7282070785653747e-05 tokens_per_second_per_gpu:991.4475467410394
Step 3172 | loss:1.6224371194839478 lr:2.7262382499184396e-05 tokens_per_second_per_gpu:696.8922075885674
Step 3173 | loss:1.4807308912277222 lr:2.724269678661842e-05 tokens_per_second_per_gpu:773.2636243598014
Step 3174 | loss:1.3942760229110718 lr:2.7223013654504255e-05 tokens_per_second_per_gpu:831.1719231451657
Step 3175 | loss:1.3687264919281006 lr:2.720333310938942e-05 tokens_per_second_per_gpu:667.0217490649684
Step 3176 | loss:1.5021436214447021 lr:2.7183655157820645e-05 tokens_per_second_per_gpu:755.7306980710008
Step 3177 | loss:1.4460253715515137 lr:2.7163979806343733e-05 tokens_per_second_per_gpu:841.8488105673636
Step 3178 | loss:1.3234648704528809 lr:2.7144307061503658e-05 tokens_per_second_per_gpu:1015.2403218791218
Step 3179 | loss:1.3281197547912598 lr:2.7124636929844543e-05 tokens_per_second_per_gpu:1037.8962697449413
Step 3180 | loss:1.1995662450790405 lr:2.7104969417909587e-05 tokens_per_second_per_gpu:950.7389070217837
Step 3181 | loss:1.4757124185562134 lr:2.708530453224118e-05 tokens_per_second_per_gpu:934.2600153585486
Step 3182 | loss:1.2852146625518799 lr:2.7065642279380772e-05 tokens_per_second_per_gpu:980.590611998637
Step 3183 | loss:1.2404247522354126 lr:2.7045982665869014e-05 tokens_per_second_per_gpu:1101.5780139330789
Step 3184 | loss:1.1544785499572754 lr:2.70263256982456e-05 tokens_per_second_per_gpu:1005.5221285748527
Step 3185 | loss:1.2896918058395386 lr:2.7006671383049397e-05 tokens_per_second_per_gpu:953.5706224954383
Step 3186 | loss:1.3312735557556152 lr:2.6987019726818396e-05 tokens_per_second_per_gpu:848.3614129059447
Step 3187 | loss:1.3417937755584717 lr:2.6967370736089642e-05 tokens_per_second_per_gpu:841.7020522644568
Step 3188 | loss:1.4163581132888794 lr:2.6947724417399373e-05 tokens_per_second_per_gpu:867.1186180661163
Step 3189 | loss:1.3302875757217407 lr:2.6928080777282866e-05 tokens_per_second_per_gpu:913.0837546040221
Step 3190 | loss:1.3213931322097778 lr:2.6908439822274555e-05 tokens_per_second_per_gpu:1059.9080274727814
Step 3191 | loss:1.4386054277420044 lr:2.6888801558907977e-05 tokens_per_second_per_gpu:996.8450922734738
Step 3192 | loss:1.228380799293518 lr:2.686916599371573e-05 tokens_per_second_per_gpu:1094.7141813985604
Step 3193 | loss:1.3543591499328613 lr:2.6849533133229587e-05 tokens_per_second_per_gpu:1195.300138753917
Step 3194 | loss:1.2097538709640503 lr:2.682990298398034e-05 tokens_per_second_per_gpu:1184.3381928114788
Step 3195 | loss:1.2256202697753906 lr:2.6810275552497953e-05 tokens_per_second_per_gpu:1070.988985615795
Step 3196 | loss:1.5033127069473267 lr:2.6790650845311428e-05 tokens_per_second_per_gpu:628.6442885975124
Step 3197 | loss:1.375327229499817 lr:2.67710288689489e-05 tokens_per_second_per_gpu:828.7830244940378
Step 3198 | loss:1.3436384201049805 lr:2.675140962993758e-05 tokens_per_second_per_gpu:1247.0268899526993
Step 3199 | loss:1.175992727279663 lr:2.6731793134803767e-05 tokens_per_second_per_gpu:829.895606285331
Step 3200 | loss:1.373653531074524 lr:2.6712179390072852e-05 tokens_per_second_per_gpu:896.0622595947341
Step 3201 | loss:1.3716614246368408 lr:2.6692568402269298e-05 tokens_per_second_per_gpu:818.9618579201084
Step 3202 | loss:1.2479254007339478 lr:2.667296017791668e-05 tokens_per_second_per_gpu:1058.802610690862
Step 3203 | loss:1.4270832538604736 lr:2.6653354723537623e-05 tokens_per_second_per_gpu:685.4937884362397
Step 3204 | loss:1.3529324531555176 lr:2.663375204565385e-05 tokens_per_second_per_gpu:876.4287297698722
Step 3205 | loss:1.2490792274475098 lr:2.6614152150786148e-05 tokens_per_second_per_gpu:837.527930921487
Step 3206 | loss:1.4764832258224487 lr:2.6594555045454388e-05 tokens_per_second_per_gpu:575.0818415282397
Step 3207 | loss:1.145652174949646 lr:2.6574960736177506e-05 tokens_per_second_per_gpu:1050.8549091096809
Step 3208 | loss:1.5149717330932617 lr:2.6555369229473516e-05 tokens_per_second_per_gpu:694.6492907303618
Step 3209 | loss:1.4918437004089355 lr:2.6535780531859478e-05 tokens_per_second_per_gpu:743.3590728754783
Step 3210 | loss:1.1752852201461792 lr:2.6516194649851564e-05 tokens_per_second_per_gpu:984.0016437522951
Step 3211 | loss:1.2929953336715698 lr:2.649661158996495e-05 tokens_per_second_per_gpu:1137.2648240478213
Step 3212 | loss:1.4821360111236572 lr:2.647703135871392e-05 tokens_per_second_per_gpu:793.6917665240092
Step 3213 | loss:1.2490748167037964 lr:2.645745396261179e-05 tokens_per_second_per_gpu:891.1440494935837
Step 3214 | loss:1.384793996810913 lr:2.643787940817095e-05 tokens_per_second_per_gpu:887.7563380810466
Step 3215 | loss:1.3353478908538818 lr:2.641830770190283e-05 tokens_per_second_per_gpu:1041.917892762781
Step 3216 | loss:1.2858275175094604 lr:2.6398738850317923e-05 tokens_per_second_per_gpu:995.0148176827835
Step 3217 | loss:1.3459866046905518 lr:2.6379172859925785e-05 tokens_per_second_per_gpu:1165.4155995095623
Step 3218 | loss:1.4918060302734375 lr:2.6359609737234972e-05 tokens_per_second_per_gpu:649.2786765473847
Step 3219 | loss:1.385230302810669 lr:2.6340049488753155e-05 tokens_per_second_per_gpu:887.153485588385
Step 3220 | loss:1.416266918182373 lr:2.632049212098698e-05 tokens_per_second_per_gpu:827.4765660501401
Step 3221 | loss:1.4180136919021606 lr:2.6300937640442176e-05 tokens_per_second_per_gpu:785.2744278718801
Step 3222 | loss:1.2439500093460083 lr:2.6281386053623532e-05 tokens_per_second_per_gpu:972.6676558530631
Step 3223 | loss:1.1950010061264038 lr:2.62618373670348e-05 tokens_per_second_per_gpu:808.8038685755878
Step 3224 | loss:1.3328629732131958 lr:2.6242291587178855e-05 tokens_per_second_per_gpu:968.9395032970773
Step 3225 | loss:1.4266077280044556 lr:2.6222748720557518e-05 tokens_per_second_per_gpu:1108.2947309218303
Step 3226 | loss:1.4013655185699463 lr:2.6203208773671734e-05 tokens_per_second_per_gpu:854.9673506416864
Step 3227 | loss:1.2054131031036377 lr:2.6183671753021383e-05 tokens_per_second_per_gpu:888.3937725788991
Step 3228 | loss:1.371446132659912 lr:2.616413766510544e-05 tokens_per_second_per_gpu:936.3555493845669
Step 3229 | loss:1.2246551513671875 lr:2.6144606516421893e-05 tokens_per_second_per_gpu:1005.6821368443285
Step 3230 | loss:1.4448723793029785 lr:2.612507831346771e-05 tokens_per_second_per_gpu:971.3902336444376
Step 3231 | loss:1.2828712463378906 lr:2.6105553062738942e-05 tokens_per_second_per_gpu:782.8312876687114
Step 3232 | loss:1.2983782291412354 lr:2.6086030770730592e-05 tokens_per_second_per_gpu:1111.5303440496245
Step 3233 | loss:1.511053204536438 lr:2.6066511443936732e-05 tokens_per_second_per_gpu:614.2521815231764
Step 3234 | loss:1.3099961280822754 lr:2.604699508885044e-05 tokens_per_second_per_gpu:696.7654414685586
Step 3235 | loss:1.2214149236679077 lr:2.6027481711963768e-05 tokens_per_second_per_gpu:648.341907328726
Step 3236 | loss:1.2673124074935913 lr:2.6007971319767826e-05 tokens_per_second_per_gpu:974.8883228594798
Step 3237 | loss:1.3363265991210938 lr:2.598846391875268e-05 tokens_per_second_per_gpu:962.9618741338301
Step 3238 | loss:1.3086557388305664 lr:2.596895951540746e-05 tokens_per_second_per_gpu:1051.0635325968644
Step 3239 | loss:1.3155676126480103 lr:2.594945811622024e-05 tokens_per_second_per_gpu:1049.0692557130328
Step 3240 | loss:1.31247878074646 lr:2.5929959727678136e-05 tokens_per_second_per_gpu:983.4934790551688
Step 3241 | loss:1.2881163358688354 lr:2.5910464356267255e-05 tokens_per_second_per_gpu:872.3113645666313
Step 3242 | loss:1.421421766281128 lr:2.589097200847268e-05 tokens_per_second_per_gpu:719.5277171178212
Step 3243 | loss:1.397413730621338 lr:2.5871482690778525e-05 tokens_per_second_per_gpu:1093.3452612029275
Step 3244 | loss:1.3956995010375977 lr:2.5851996409667842e-05 tokens_per_second_per_gpu:851.1978359266388
Step 3245 | loss:1.3845574855804443 lr:2.5832513171622735e-05 tokens_per_second_per_gpu:980.093369896389
Step 3246 | loss:1.3807904720306396 lr:2.5813032983124236e-05 tokens_per_second_per_gpu:911.7554454019274
Step 3247 | loss:1.2062608003616333 lr:2.5793555850652407e-05 tokens_per_second_per_gpu:812.6282927931366
Step 3248 | loss:1.2437998056411743 lr:2.5774081780686296e-05 tokens_per_second_per_gpu:1110.8219280257924
Step 3249 | loss:1.272648811340332 lr:2.5754610779703873e-05 tokens_per_second_per_gpu:1043.7560757001106
Step 3250 | loss:1.3354414701461792 lr:2.5735142854182175e-05 tokens_per_second_per_gpu:1114.8730102543077
Step 3251 | loss:1.2328170537948608 lr:2.5715678010597126e-05 tokens_per_second_per_gpu:961.6326486936057
Step 3252 | loss:1.263615369796753 lr:2.569621625542369e-05 tokens_per_second_per_gpu:918.9659677680677
Step 3253 | loss:1.2885916233062744 lr:2.5676757595135798e-05 tokens_per_second_per_gpu:762.592668699792
Step 3254 | loss:1.4921010732650757 lr:2.56573020362063e-05 tokens_per_second_per_gpu:983.7704391501657
Step 3255 | loss:1.3760490417480469 lr:2.5637849585107085e-05 tokens_per_second_per_gpu:865.8379780701973
Step 3256 | loss:1.3150928020477295 lr:2.5618400248308937e-05 tokens_per_second_per_gpu:1179.1880994714572
Step 3257 | loss:1.3295401334762573 lr:2.5598954032281673e-05 tokens_per_second_per_gpu:783.6239483118488
Step 3258 | loss:1.444968581199646 lr:2.5579510943494017e-05 tokens_per_second_per_gpu:704.6537626121388
Step 3259 | loss:1.290733814239502 lr:2.5560070988413684e-05 tokens_per_second_per_gpu:948.9473972869235
Step 3260 | loss:1.3289865255355835 lr:2.5540634173507334e-05 tokens_per_second_per_gpu:807.1073671499696
Step 3261 | loss:1.4114047288894653 lr:2.5521200505240586e-05 tokens_per_second_per_gpu:732.1808067399216
Step 3262 | loss:1.1871435642242432 lr:2.5501769990078017e-05 tokens_per_second_per_gpu:955.8066747754508
Step 3263 | loss:1.2465486526489258 lr:2.548234263448314e-05 tokens_per_second_per_gpu:873.5239338844042
Step 3264 | loss:1.234493374824524 lr:2.546291844491843e-05 tokens_per_second_per_gpu:1141.3577281945643
Step 3265 | loss:1.2533012628555298 lr:2.5443497427845317e-05 tokens_per_second_per_gpu:1113.7739490964336
Step 3266 | loss:1.2563549280166626 lr:2.5424079589724154e-05 tokens_per_second_per_gpu:921.3567131527626
Step 3267 | loss:1.3218976259231567 lr:2.540466493701425e-05 tokens_per_second_per_gpu:732.1717879958767
Step 3268 | loss:1.3276926279067993 lr:2.538525347617385e-05 tokens_per_second_per_gpu:832.4191434453477
Step 3269 | loss:1.2625513076782227 lr:2.5365845213660134e-05 tokens_per_second_per_gpu:793.0753655648651
Step 3270 | loss:1.2216558456420898 lr:2.534644015592923e-05 tokens_per_second_per_gpu:910.9805265079601
Step 3271 | loss:1.5051296949386597 lr:2.5327038309436183e-05 tokens_per_second_per_gpu:741.3598853619292
Step 3272 | loss:1.319096326828003 lr:2.5307639680635e-05 tokens_per_second_per_gpu:837.2537196124281
Step 3273 | loss:1.260589599609375 lr:2.5288244275978574e-05 tokens_per_second_per_gpu:920.4478950065433
Step 3274 | loss:1.333802342414856 lr:2.5268852101918765e-05 tokens_per_second_per_gpu:839.557382479072
Step 3275 | loss:1.5422178506851196 lr:2.5249463164906325e-05 tokens_per_second_per_gpu:703.1205797259347
Step 3276 | loss:1.1938968896865845 lr:2.5230077471390957e-05 tokens_per_second_per_gpu:1076.3649364405162
Step 3277 | loss:1.3631168603897095 lr:2.521069502782129e-05 tokens_per_second_per_gpu:1095.3320746103382
Step 3278 | loss:1.322277307510376 lr:2.519131584064482e-05 tokens_per_second_per_gpu:1046.809744399031
Step 3279 | loss:1.3004200458526611 lr:2.5171939916308027e-05 tokens_per_second_per_gpu:748.2122805206885
Step 3280 | loss:1.3455449342727661 lr:2.5152567261256254e-05 tokens_per_second_per_gpu:1081.72674620216
Step 3281 | loss:1.302565336227417 lr:2.51331978819338e-05 tokens_per_second_per_gpu:1021.1889921475104
Step 3282 | loss:1.3169502019882202 lr:2.511383178478382e-05 tokens_per_second_per_gpu:1048.9499253120243
Step 3283 | loss:1.2464852333068848 lr:2.5094468976248427e-05 tokens_per_second_per_gpu:930.2568053113354
Step 3284 | loss:1.248455286026001 lr:2.5075109462768632e-05 tokens_per_second_per_gpu:727.4481762310716
Step 3285 | loss:1.3571749925613403 lr:2.5055753250784317e-05 tokens_per_second_per_gpu:985.9034132874897
Step 3286 | loss:1.5324690341949463 lr:2.503640034673431e-05 tokens_per_second_per_gpu:670.7982769760401
Step 3287 | loss:1.4766298532485962 lr:2.501705075705629e-05 tokens_per_second_per_gpu:691.4933485040671
Step 3288 | loss:1.4355695247650146 lr:2.4997704488186894e-05 tokens_per_second_per_gpu:639.2462976416284
Step 3289 | loss:1.347099781036377 lr:2.4978361546561583e-05 tokens_per_second_per_gpu:739.2065621648985
Step 3290 | loss:1.4307206869125366 lr:2.4959021938614766e-05 tokens_per_second_per_gpu:784.907970102631
Step 3291 | loss:1.3608895540237427 lr:2.4939685670779753e-05 tokens_per_second_per_gpu:988.3301649166807
Step 3292 | loss:1.3966755867004395 lr:2.4920352749488665e-05 tokens_per_second_per_gpu:937.5878946735263
Step 3293 | loss:1.3541467189788818 lr:2.4901023181172606e-05 tokens_per_second_per_gpu:1218.0537914644578
Step 3294 | loss:1.285922884941101 lr:2.4881696972261485e-05 tokens_per_second_per_gpu:862.5653667731092
Step 3295 | loss:1.443711757659912 lr:2.486237412918414e-05 tokens_per_second_per_gpu:819.2762329302933
Step 3296 | loss:1.2857741117477417 lr:2.4843054658368298e-05 tokens_per_second_per_gpu:982.4582500287918
Step 3297 | loss:1.427632212638855 lr:2.4823738566240507e-05 tokens_per_second_per_gpu:803.5049405138485
Step 3298 | loss:1.2516753673553467 lr:2.4804425859226262e-05 tokens_per_second_per_gpu:801.055763187727
Step 3299 | loss:1.3550376892089844 lr:2.478511654374986e-05 tokens_per_second_per_gpu:1038.6967536950042
Step 3300 | loss:1.2338271141052246 lr:2.4765810626234548e-05 tokens_per_second_per_gpu:1148.3652939752328
Step 3301 | loss:1.4485987424850464 lr:2.4746508113102364e-05 tokens_per_second_per_gpu:738.6981858956925
Step 3302 | loss:1.238429069519043 lr:2.472720901077427e-05 tokens_per_second_per_gpu:783.1678221842487
Step 3303 | loss:1.4258317947387695 lr:2.4707913325670087e-05 tokens_per_second_per_gpu:710.0743904261458
Step 3304 | loss:1.3720308542251587 lr:2.468862106420846e-05 tokens_per_second_per_gpu:922.25745620728
Step 3305 | loss:1.2885593175888062 lr:2.466933223280695e-05 tokens_per_second_per_gpu:786.3639223846059
Step 3306 | loss:1.3154886960983276 lr:2.465004683788192e-05 tokens_per_second_per_gpu:984.539574571363
Step 3307 | loss:1.392663598060608 lr:2.463076488584863e-05 tokens_per_second_per_gpu:928.5945384091575
Step 3308 | loss:1.3997200727462769 lr:2.461148638312121e-05 tokens_per_second_per_gpu:877.4454949842038
Step 3309 | loss:1.4849324226379395 lr:2.459221133611258e-05 tokens_per_second_per_gpu:1046.3998269529461
Step 3310 | loss:1.330552577972412 lr:2.4572939751234568e-05 tokens_per_second_per_gpu:932.5920258870489
Step 3311 | loss:1.2203571796417236 lr:2.455367163489781e-05 tokens_per_second_per_gpu:1170.614022969397
Step 3312 | loss:1.4025077819824219 lr:2.4534406993511832e-05 tokens_per_second_per_gpu:740.0859175619561
Step 3313 | loss:1.3963372707366943 lr:2.4515145833484955e-05 tokens_per_second_per_gpu:843.5837396084127
Step 3314 | loss:1.412762999534607 lr:2.449588816122438e-05 tokens_per_second_per_gpu:1197.4034086573852
Step 3315 | loss:1.3964917659759521 lr:2.447663398313614e-05 tokens_per_second_per_gpu:866.3432020600791
Step 3316 | loss:1.3848222494125366 lr:2.4457383305625084e-05 tokens_per_second_per_gpu:1245.110193156586
Step 3317 | loss:1.3440911769866943 lr:2.443813613509493e-05 tokens_per_second_per_gpu:656.1658827023526
Step 3318 | loss:1.1674208641052246 lr:2.441889247794819e-05 tokens_per_second_per_gpu:1018.140867358472
Step 3319 | loss:1.427626371383667 lr:2.439965234058625e-05 tokens_per_second_per_gpu:1235.0441795929346
Step 3320 | loss:1.4325835704803467 lr:2.4380415729409292e-05 tokens_per_second_per_gpu:766.7097294830946
Step 3321 | loss:1.348076581954956 lr:2.436118265081634e-05 tokens_per_second_per_gpu:750.2361315656823
Step 3322 | loss:1.4578330516815186 lr:2.434195311120524e-05 tokens_per_second_per_gpu:948.5275954324775
Step 3323 | loss:1.273364543914795 lr:2.4322727116972665e-05 tokens_per_second_per_gpu:796.9810520253885
Step 3324 | loss:1.3258233070373535 lr:2.43035046745141e-05 tokens_per_second_per_gpu:1075.3268301823205
Step 3325 | loss:1.326210618019104 lr:2.4284285790223853e-05 tokens_per_second_per_gpu:745.2481557658012
Step 3326 | loss:1.3060762882232666 lr:2.4265070470495046e-05 tokens_per_second_per_gpu:726.0548773051979
Step 3327 | loss:1.2954591512680054 lr:2.4245858721719623e-05 tokens_per_second_per_gpu:929.9524980845061
Step 3328 | loss:1.334389567375183 lr:2.4226650550288333e-05 tokens_per_second_per_gpu:803.0290820192647
Step 3329 | loss:1.433325171470642 lr:2.4207445962590743e-05 tokens_per_second_per_gpu:868.1815020409658
Step 3330 | loss:1.3709745407104492 lr:2.4188244965015208e-05 tokens_per_second_per_gpu:999.960459630429
Step 3331 | loss:1.4413784742355347 lr:2.4169047563948912e-05 tokens_per_second_per_gpu:846.4790466079359
Step 3332 | loss:1.3529808521270752 lr:2.414985376577783e-05 tokens_per_second_per_gpu:1008.2308289884136
Step 3333 | loss:1.4158515930175781 lr:2.4130663576886742e-05 tokens_per_second_per_gpu:1152.6268929530029
Step 3334 | loss:1.4213770627975464 lr:2.411147700365923e-05 tokens_per_second_per_gpu:669.8342544588564
Step 3335 | loss:1.3498151302337646 lr:2.409229405247766e-05 tokens_per_second_per_gpu:1116.0141962110913
Step 3336 | loss:1.2815489768981934 lr:2.4073114729723224e-05 tokens_per_second_per_gpu:772.2082611928473
Step 3337 | loss:1.3321681022644043 lr:2.4053939041775862e-05 tokens_per_second_per_gpu:933.7860785621565
Step 3338 | loss:1.2233396768569946 lr:2.4034766995014336e-05 tokens_per_second_per_gpu:1091.6948690666782
Step 3339 | loss:1.1989331245422363 lr:2.4015598595816205e-05 tokens_per_second_per_gpu:1320.8536346810833
Step 3340 | loss:1.4570541381835938 lr:2.399643385055778e-05 tokens_per_second_per_gpu:755.3761660726692
Step 3341 | loss:1.444172978401184 lr:2.39772727656142e-05 tokens_per_second_per_gpu:1003.1081324414371
Step 3342 | loss:1.2585299015045166 lr:2.395811534735933e-05 tokens_per_second_per_gpu:906.7248381285413
Step 3343 | loss:1.501636266708374 lr:2.3938961602165882e-05 tokens_per_second_per_gpu:783.1479030274861
Step 3344 | loss:1.3279119729995728 lr:2.3919811536405282e-05 tokens_per_second_per_gpu:723.6398352828481
Step 3345 | loss:1.2859033346176147 lr:2.3900665156447772e-05 tokens_per_second_per_gpu:874.2790447073883
Step 3346 | loss:1.312913179397583 lr:2.3881522468662376e-05 tokens_per_second_per_gpu:674.1450240678798
Step 3347 | loss:1.4156980514526367 lr:2.3862383479416847e-05 tokens_per_second_per_gpu:870.3368923004641
Step 3348 | loss:1.3975855112075806 lr:2.3843248195077753e-05 tokens_per_second_per_gpu:840.5888537211844
Step 3349 | loss:1.4164491891860962 lr:2.3824116622010383e-05 tokens_per_second_per_gpu:921.8204452010382
Step 3350 | loss:1.4663276672363281 lr:2.3804988766578838e-05 tokens_per_second_per_gpu:887.1476896563498
Step 3351 | loss:1.1849287748336792 lr:2.378586463514597e-05 tokens_per_second_per_gpu:1200.5025019021007
Step 3352 | loss:1.3536449670791626 lr:2.3766744234073355e-05 tokens_per_second_per_gpu:834.5297792235434
Step 3353 | loss:1.2368826866149902 lr:2.3747627569721387e-05 tokens_per_second_per_gpu:1068.839462101783
Step 3354 | loss:1.2216278314590454 lr:2.372851464844916e-05 tokens_per_second_per_gpu:968.9914496453181
Step 3355 | loss:1.3582032918930054 lr:2.3709405476614578e-05 tokens_per_second_per_gpu:1098.626403379374
Step 3356 | loss:1.2654951810836792 lr:2.369030006057424e-05 tokens_per_second_per_gpu:1247.5555262985567
Step 3357 | loss:1.3866631984710693 lr:2.3671198406683543e-05 tokens_per_second_per_gpu:900.213283137381
Step 3358 | loss:1.3476436138153076 lr:2.3652100521296626e-05 tokens_per_second_per_gpu:1167.2290603094857
Step 3359 | loss:1.3188351392745972 lr:2.363300641076633e-05 tokens_per_second_per_gpu:899.6262209562116
Step 3360 | loss:1.1783781051635742 lr:2.3613916081444313e-05 tokens_per_second_per_gpu:861.1321394859989
Step 3361 | loss:1.3517638444900513 lr:2.3594829539680902e-05 tokens_per_second_per_gpu:981.3136562012999
Step 3362 | loss:1.3016561269760132 lr:2.3575746791825225e-05 tokens_per_second_per_gpu:910.4883659668507
Step 3363 | loss:1.3223696947097778 lr:2.3556667844225095e-05 tokens_per_second_per_gpu:901.6457034713877
Step 3364 | loss:1.3584285974502563 lr:2.3537592703227096e-05 tokens_per_second_per_gpu:779.5390923193773
Step 3365 | loss:1.3599014282226562 lr:2.3518521375176557e-05 tokens_per_second_per_gpu:836.5520669053184
Step 3366 | loss:1.372406005859375 lr:2.349945386641749e-05 tokens_per_second_per_gpu:801.3728054147223
Step 3367 | loss:1.2938847541809082 lr:2.3480390183292687e-05 tokens_per_second_per_gpu:1083.3243184876133
Step 3368 | loss:1.2800861597061157 lr:2.3461330332143622e-05 tokens_per_second_per_gpu:882.072897081922
Step 3369 | loss:1.2887459993362427 lr:2.3442274319310526e-05 tokens_per_second_per_gpu:880.7349356517467
Step 3370 | loss:1.1918060779571533 lr:2.342322215113236e-05 tokens_per_second_per_gpu:1174.3499492789888
Step 3371 | loss:1.388392448425293 lr:2.340417383394677e-05 tokens_per_second_per_gpu:857.2582460315704
Step 3372 | loss:1.336906909942627 lr:2.3385129374090163e-05 tokens_per_second_per_gpu:886.9593226940441
Step 3373 | loss:1.471813678741455 lr:2.3366088777897614e-05 tokens_per_second_per_gpu:803.190891348808
Step 3374 | loss:1.1481183767318726 lr:2.3347052051702966e-05 tokens_per_second_per_gpu:1077.5524096190024
Step 3375 | loss:1.2783253192901611 lr:2.332801920183873e-05 tokens_per_second_per_gpu:1027.6285890140794
Step 3376 | loss:1.4144432544708252 lr:2.3308990234636152e-05 tokens_per_second_per_gpu:729.0126001103231
Step 3377 | loss:1.339280366897583 lr:2.3289965156425186e-05 tokens_per_second_per_gpu:1272.981017430505
Step 3378 | loss:1.440298318862915 lr:2.327094397353448e-05 tokens_per_second_per_gpu:775.7796099636618
Step 3379 | loss:1.3601073026657104 lr:2.325192669229141e-05 tokens_per_second_per_gpu:984.3430172811571
Step 3380 | loss:1.2381491661071777 lr:2.323291331902201e-05 tokens_per_second_per_gpu:1149.3951703771754
Step 3381 | loss:1.386893630027771 lr:2.321390386005106e-05 tokens_per_second_per_gpu:853.5378408692353
Step 3382 | loss:1.3246424198150635 lr:2.3194898321702024e-05 tokens_per_second_per_gpu:886.4194494697306
Step 3383 | loss:1.2379345893859863 lr:2.3175896710297044e-05 tokens_per_second_per_gpu:944.5623664790477
Step 3384 | loss:1.311063528060913 lr:2.3156899032156978e-05 tokens_per_second_per_gpu:838.3812500727137
Step 3385 | loss:1.280455470085144 lr:2.313790529360136e-05 tokens_per_second_per_gpu:1224.759424568745
Step 3386 | loss:1.3374582529067993 lr:2.311891550094842e-05 tokens_per_second_per_gpu:1058.0916384855775
Step 3387 | loss:1.198858618736267 lr:2.309992966051508e-05 tokens_per_second_per_gpu:732.3129098306142
Step 3388 | loss:1.472798228263855 lr:2.3080947778616937e-05 tokens_per_second_per_gpu:647.3246017165576
Step 3389 | loss:1.313118815422058 lr:2.3061969861568292e-05 tokens_per_second_per_gpu:1066.0428472161484
Step 3390 | loss:1.3999074697494507 lr:2.304299591568209e-05 tokens_per_second_per_gpu:1079.4584505032385
Step 3391 | loss:1.5034507513046265 lr:2.3024025947269996e-05 tokens_per_second_per_gpu:751.4720805064294
Step 3392 | loss:1.3494361639022827 lr:2.300505996264232e-05 tokens_per_second_per_gpu:793.4381348335147
Step 3393 | loss:1.3085243701934814 lr:2.2986097968108072e-05 tokens_per_second_per_gpu:833.1139523979314
Step 3394 | loss:1.4455673694610596 lr:2.2967139969974913e-05 tokens_per_second_per_gpu:774.5486144018198
Step 3395 | loss:1.3000171184539795 lr:2.2948185974549184e-05 tokens_per_second_per_gpu:923.7181130328007
Step 3396 | loss:1.313148021697998 lr:2.2929235988135903e-05 tokens_per_second_per_gpu:935.2473029170953
Step 3397 | loss:1.2454317808151245 lr:2.2910290017038734e-05 tokens_per_second_per_gpu:819.5823302854361
Step 3398 | loss:1.3446054458618164 lr:2.2891348067560032e-05 tokens_per_second_per_gpu:943.9803877199917
Step 3399 | loss:1.3891396522521973 lr:2.287241014600078e-05 tokens_per_second_per_gpu:728.8127208586398
Step 3400 | loss:1.2146728038787842 lr:2.2853476258660655e-05 tokens_per_second_per_gpu:1380.996790921249
Step 3401 | loss:1.516797661781311 lr:2.2834546411837985e-05 tokens_per_second_per_gpu:915.0982811250792
Step 3402 | loss:1.4805335998535156 lr:2.2815620611829726e-05 tokens_per_second_per_gpu:645.9082119486777
Step 3403 | loss:1.3622528314590454 lr:2.279669886493153e-05 tokens_per_second_per_gpu:943.5670993489252
Step 3404 | loss:1.226808786392212 lr:2.2777781177437656e-05 tokens_per_second_per_gpu:812.9263201282747
Step 3405 | loss:1.3174753189086914 lr:2.275886755564106e-05 tokens_per_second_per_gpu:852.4380730252036
Step 3406 | loss:1.466181993484497 lr:2.27399580058333e-05 tokens_per_second_per_gpu:856.7670860800238
Step 3407 | loss:1.36091148853302 lr:2.2721052534304606e-05 tokens_per_second_per_gpu:660.4927367332938
Step 3408 | loss:1.3627612590789795 lr:2.2702151147343868e-05 tokens_per_second_per_gpu:933.2631477739748
Step 3409 | loss:1.3947430849075317 lr:2.2683253851238562e-05 tokens_per_second_per_gpu:892.8013141921548
Step 3410 | loss:1.3788052797317505 lr:2.2664360652274872e-05 tokens_per_second_per_gpu:888.3460851195755
Step 3411 | loss:1.3191355466842651 lr:2.2645471556737544e-05 tokens_per_second_per_gpu:1011.3758671912395
Step 3412 | loss:1.3168041706085205 lr:2.262658657091002e-05 tokens_per_second_per_gpu:807.7448395571912
Step 3413 | loss:1.258087158203125 lr:2.2607705701074372e-05 tokens_per_second_per_gpu:854.7656040074404
Step 3414 | loss:1.3778271675109863 lr:2.258882895351125e-05 tokens_per_second_per_gpu:801.2272814513075
Step 3415 | loss:1.2699155807495117 lr:2.2569956334499994e-05 tokens_per_second_per_gpu:933.1178195321123
Step 3416 | loss:1.335634469985962 lr:2.2551087850318523e-05 tokens_per_second_per_gpu:847.8353287468692
Step 3417 | loss:1.3649933338165283 lr:2.2532223507243424e-05 tokens_per_second_per_gpu:632.5053640757753
Step 3418 | loss:1.388769268989563 lr:2.2513363311549857e-05 tokens_per_second_per_gpu:822.6407152017767
Step 3419 | loss:1.2581945657730103 lr:2.2494507269511646e-05 tokens_per_second_per_gpu:918.9517518596269
Step 3420 | loss:1.4312446117401123 lr:2.2475655387401224e-05 tokens_per_second_per_gpu:859.0633472687458
Step 3421 | loss:1.3095899820327759 lr:2.245680767148961e-05 tokens_per_second_per_gpu:832.8977302617903
Step 3422 | loss:1.357344627380371 lr:2.2437964128046488e-05 tokens_per_second_per_gpu:1125.8073279219686
Step 3423 | loss:1.3633781671524048 lr:2.24191247633401e-05 tokens_per_second_per_gpu:1074.9986111575379
Step 3424 | loss:1.401974081993103 lr:2.2400289583637332e-05 tokens_per_second_per_gpu:784.587802406322
Step 3425 | loss:1.3248000144958496 lr:2.238145859520369e-05 tokens_per_second_per_gpu:797.5661383385632
Step 3426 | loss:1.2794744968414307 lr:2.236263180430323e-05 tokens_per_second_per_gpu:1029.8797724834797
Step 3427 | loss:1.3485609292984009 lr:2.2343809217198688e-05 tokens_per_second_per_gpu:716.6703548174551
Step 3428 | loss:1.5624476671218872 lr:2.2324990840151316e-05 tokens_per_second_per_gpu:694.4611067962127
Step 3429 | loss:1.6120095252990723 lr:2.2306176679421052e-05 tokens_per_second_per_gpu:508.61596359209244
Step 3430 | loss:1.43614661693573 lr:2.2287366741266355e-05 tokens_per_second_per_gpu:832.3779513722362
Step 3431 | loss:1.3894706964492798 lr:2.226856103194433e-05 tokens_per_second_per_gpu:840.1512916113834
Step 3432 | loss:1.331661581993103 lr:2.2249759557710676e-05 tokens_per_second_per_gpu:1226.1925788433964
Step 3433 | loss:1.1444687843322754 lr:2.2230962324819636e-05 tokens_per_second_per_gpu:892.4253561677793
Step 3434 | loss:1.3740150928497314 lr:2.2212169339524103e-05 tokens_per_second_per_gpu:697.4650971575318
Step 3435 | loss:1.3937928676605225 lr:2.2193380608075495e-05 tokens_per_second_per_gpu:813.5982652706122
Step 3436 | loss:1.351823329925537 lr:2.2174596136723876e-05 tokens_per_second_per_gpu:1000.6383764258011
Step 3437 | loss:1.3484805822372437 lr:2.215581593171784e-05 tokens_per_second_per_gpu:1066.3887371622704
Step 3438 | loss:1.6527862548828125 lr:2.21370399993046e-05 tokens_per_second_per_gpu:804.503151827743
Step 3439 | loss:1.2737040519714355 lr:2.211826834572994e-05 tokens_per_second_per_gpu:913.5955483393949
Step 3440 | loss:1.4608659744262695 lr:2.2099500977238195e-05 tokens_per_second_per_gpu:747.2999960782466
Step 3441 | loss:1.5585516691207886 lr:2.2080737900072302e-05 tokens_per_second_per_gpu:811.0621741973812
Step 3442 | loss:1.4284684658050537 lr:2.2061979120473763e-05 tokens_per_second_per_gpu:688.1375364912722
Step 3443 | loss:1.3966529369354248 lr:2.2043224644682646e-05 tokens_per_second_per_gpu:616.759964395243
Step 3444 | loss:1.2900328636169434 lr:2.20244744789376e-05 tokens_per_second_per_gpu:1195.6286657835499
Step 3445 | loss:1.4010604619979858 lr:2.2005728629475823e-05 tokens_per_second_per_gpu:1065.274624250844
Step 3446 | loss:1.245774269104004 lr:2.198698710253309e-05 tokens_per_second_per_gpu:893.0800539424043
Step 3447 | loss:1.3237800598144531 lr:2.1968249904343727e-05 tokens_per_second_per_gpu:890.9541909054165
Step 3448 | loss:1.1979268789291382 lr:2.194951704114063e-05 tokens_per_second_per_gpu:1110.5970251363178
Step 3449 | loss:1.2966920137405396 lr:2.1930788519155256e-05 tokens_per_second_per_gpu:665.0504615900691
Step 3450 | loss:1.3477952480316162 lr:2.191206434461759e-05 tokens_per_second_per_gpu:924.99489506362
Step 3451 | loss:1.3566794395446777 lr:2.1893344523756222e-05 tokens_per_second_per_gpu:760.6156421433261
Step 3452 | loss:1.344017505645752 lr:2.1874629062798238e-05 tokens_per_second_per_gpu:983.1823743812821
Step 3453 | loss:1.1700050830841064 lr:2.1855917967969318e-05 tokens_per_second_per_gpu:928.9449066396737
Step 3454 | loss:1.283284068107605 lr:2.1837211245493663e-05 tokens_per_second_per_gpu:1157.3974158481171
Step 3455 | loss:1.482614278793335 lr:2.181850890159402e-05 tokens_per_second_per_gpu:800.1824397968933
Step 3456 | loss:1.2949230670928955 lr:2.1799810942491715e-05 tokens_per_second_per_gpu:990.6316782400766
Step 3457 | loss:1.3074917793273926 lr:2.178111737440655e-05 tokens_per_second_per_gpu:937.4520555627589
Step 3458 | loss:1.59983229637146 lr:2.1762428203556935e-05 tokens_per_second_per_gpu:796.783941689547
Step 3459 | loss:1.3971281051635742 lr:2.1743743436159763e-05 tokens_per_second_per_gpu:823.2651401525379
Step 3460 | loss:1.281197428703308 lr:2.172506307843051e-05 tokens_per_second_per_gpu:708.8329160865488
Step 3461 | loss:1.254899263381958 lr:2.1706387136583125e-05 tokens_per_second_per_gpu:1086.968791192564
Step 3462 | loss:1.2672282457351685 lr:2.168771561683015e-05 tokens_per_second_per_gpu:1013.3393441460202
Step 3463 | loss:1.4022473096847534 lr:2.166904852538264e-05 tokens_per_second_per_gpu:719.6306152896419
Step 3464 | loss:1.292449712753296 lr:2.1650385868450142e-05 tokens_per_second_per_gpu:1031.426757356237
Step 3465 | loss:1.433441162109375 lr:2.163172765224077e-05 tokens_per_second_per_gpu:854.2968818892907
Step 3466 | loss:1.4615240097045898 lr:2.1613073882961125e-05 tokens_per_second_per_gpu:811.3600702041515
Step 3467 | loss:1.3623378276824951 lr:2.1594424566816373e-05 tokens_per_second_per_gpu:979.017606955999
Step 3468 | loss:1.3277781009674072 lr:2.1575779710010135e-05 tokens_per_second_per_gpu:888.6370571749251
Step 3469 | loss:1.286874532699585 lr:2.1557139318744614e-05 tokens_per_second_per_gpu:1062.3518483477787
Step 3470 | loss:1.451695442199707 lr:2.1538503399220505e-05 tokens_per_second_per_gpu:848.3842391925964
Step 3471 | loss:1.371694564819336 lr:2.1519871957636986e-05 tokens_per_second_per_gpu:716.0442761699418
Step 3472 | loss:1.4255049228668213 lr:2.15012450001918e-05 tokens_per_second_per_gpu:854.2846282933281
Step 3473 | loss:1.2048866748809814 lr:2.1482622533081134e-05 tokens_per_second_per_gpu:957.3815367610929
Step 3474 | loss:1.3367341756820679 lr:2.1464004562499734e-05 tokens_per_second_per_gpu:927.8180081596755
Step 3475 | loss:1.3939942121505737 lr:2.144539109464084e-05 tokens_per_second_per_gpu:734.8897587007469
Step 3476 | loss:1.2672855854034424 lr:2.1426782135696166e-05 tokens_per_second_per_gpu:1093.8530214119771
Step 3477 | loss:1.403802514076233 lr:2.1408177691855976e-05 tokens_per_second_per_gpu:944.4031898258125
Step 3478 | loss:1.3573274612426758 lr:2.1389577769308956e-05 tokens_per_second_per_gpu:828.961932672526
Step 3479 | loss:1.4806880950927734 lr:2.1370982374242382e-05 tokens_per_second_per_gpu:775.5052905397297
Step 3480 | loss:1.3120718002319336 lr:2.1352391512841937e-05 tokens_per_second_per_gpu:874.3669407317835
Step 3481 | loss:1.2506465911865234 lr:2.133380519129185e-05 tokens_per_second_per_gpu:1014.2730653495748
Step 3482 | loss:1.1463968753814697 lr:2.1315223415774838e-05 tokens_per_second_per_gpu:899.903715822325
Step 3483 | loss:1.344269871711731 lr:2.129664619247207e-05 tokens_per_second_per_gpu:728.0128792715244
Step 3484 | loss:1.2800829410552979 lr:2.127807352756325e-05 tokens_per_second_per_gpu:894.9775954241229
Step 3485 | loss:1.3207658529281616 lr:2.1259505427226504e-05 tokens_per_second_per_gpu:839.0714013299201
Step 3486 | loss:1.3525243997573853 lr:2.1240941897638494e-05 tokens_per_second_per_gpu:1073.6371592293822
Step 3487 | loss:1.4474611282348633 lr:2.122238294497436e-05 tokens_per_second_per_gpu:790.0522067478871
Step 3488 | loss:1.3273632526397705 lr:2.1203828575407657e-05 tokens_per_second_per_gpu:979.286631300313
Step 3489 | loss:1.4589605331420898 lr:2.118527879511051e-05 tokens_per_second_per_gpu:809.6511051070676
Step 3490 | loss:1.2948365211486816 lr:2.116673361025342e-05 tokens_per_second_per_gpu:1108.7437563953663
Step 3491 | loss:1.4316166639328003 lr:2.114819302700545e-05 tokens_per_second_per_gpu:888.2596544464284
Step 3492 | loss:1.1909167766571045 lr:2.112965705153405e-05 tokens_per_second_per_gpu:1066.2118485926546
Step 3493 | loss:1.32477605342865 lr:2.1111125690005196e-05 tokens_per_second_per_gpu:1009.7581766477637
Step 3494 | loss:1.2627131938934326 lr:2.1092598948583317e-05 tokens_per_second_per_gpu:1038.7413386035075
Step 3495 | loss:1.3017446994781494 lr:2.107407683343128e-05 tokens_per_second_per_gpu:1093.0169479167719
Step 3496 | loss:1.3685503005981445 lr:2.1055559350710444e-05 tokens_per_second_per_gpu:1008.2843632480655
Step 3497 | loss:1.3307745456695557 lr:2.10370465065806e-05 tokens_per_second_per_gpu:753.321516642505
Step 3498 | loss:1.2699899673461914 lr:2.1018538307200025e-05 tokens_per_second_per_gpu:996.9975634847596
Step 3499 | loss:1.45008385181427 lr:2.1000034758725424e-05 tokens_per_second_per_gpu:670.6108228422743
Step 3500 | loss:1.2647559642791748 lr:2.0981535867311968e-05 tokens_per_second_per_gpu:974.7254242187015
Step 3501 | loss:1.3002554178237915 lr:2.0963041639113282e-05 tokens_per_second_per_gpu:699.0901154667722
Step 3502 | loss:1.2334059476852417 lr:2.0944552080281435e-05 tokens_per_second_per_gpu:1176.3181613556467
Step 3503 | loss:1.2059133052825928 lr:2.0926067196966933e-05 tokens_per_second_per_gpu:805.5389559274969
Step 3504 | loss:1.3380011320114136 lr:2.0907586995318748e-05 tokens_per_second_per_gpu:609.7925469193058
Step 3505 | loss:1.337631106376648 lr:2.088911148148427e-05 tokens_per_second_per_gpu:801.9997353158711
Step 3506 | loss:1.3950194120407104 lr:2.0870640661609357e-05 tokens_per_second_per_gpu:985.3810323997342
Step 3507 | loss:1.3070473670959473 lr:2.0852174541838285e-05 tokens_per_second_per_gpu:958.0480055422023
Step 3508 | loss:1.361006259918213 lr:2.0833713128313774e-05 tokens_per_second_per_gpu:955.1781504202805
Step 3509 | loss:1.3617042303085327 lr:2.0815256427176974e-05 tokens_per_second_per_gpu:1039.6880627146413
Step 3510 | loss:1.4196536540985107 lr:2.0796804444567477e-05 tokens_per_second_per_gpu:745.1688528038559
Step 3511 | loss:1.427312970161438 lr:2.077835718662329e-05 tokens_per_second_per_gpu:969.6454528569212
Step 3512 | loss:1.3238308429718018 lr:2.075991465948086e-05 tokens_per_second_per_gpu:626.336683684697
Step 3513 | loss:1.326399326324463 lr:2.0741476869275072e-05 tokens_per_second_per_gpu:898.4615266832703
Step 3514 | loss:1.311389684677124 lr:2.0723043822139193e-05 tokens_per_second_per_gpu:937.2251601090379
Step 3515 | loss:1.3000088930130005 lr:2.070461552420497e-05 tokens_per_second_per_gpu:852.7089631361903
Step 3516 | loss:1.38066828250885 lr:2.0686191981602516e-05 tokens_per_second_per_gpu:947.6945284587009
Step 3517 | loss:1.3336334228515625 lr:2.066777320046039e-05 tokens_per_second_per_gpu:695.7276714051842
Step 3518 | loss:1.4925131797790527 lr:2.0649359186905593e-05 tokens_per_second_per_gpu:875.9920783825136
Step 3519 | loss:1.2783852815628052 lr:2.063094994706347e-05 tokens_per_second_per_gpu:825.1594127706635
Step 3520 | loss:1.3617010116577148 lr:2.0612545487057852e-05 tokens_per_second_per_gpu:859.1947321112203
Step 3521 | loss:1.2921210527420044 lr:2.0594145813010917e-05 tokens_per_second_per_gpu:760.59836510784
Step 3522 | loss:1.3196269273757935 lr:2.057575093104331e-05 tokens_per_second_per_gpu:728.8931544293491
Step 3523 | loss:1.3896629810333252 lr:2.055736084727402e-05 tokens_per_second_per_gpu:1042.0331342914592
Step 3524 | loss:1.40684974193573 lr:2.0538975567820496e-05 tokens_per_second_per_gpu:978.0119470919358
Step 3525 | loss:1.3704227209091187 lr:2.052059509879857e-05 tokens_per_second_per_gpu:944.4108321305345
Step 3526 | loss:1.2824369668960571 lr:2.050221944632245e-05 tokens_per_second_per_gpu:886.1073866711109
Step 3527 | loss:1.2394371032714844 lr:2.048384861650478e-05 tokens_per_second_per_gpu:981.9186411518041
Step 3528 | loss:1.206642985343933 lr:2.0465482615456555e-05 tokens_per_second_per_gpu:1017.2555556268422
Step 3529 | loss:1.3483985662460327 lr:2.044712144928721e-05 tokens_per_second_per_gpu:1077.830144096287
Step 3530 | loss:1.2252578735351562 lr:2.042876512410456e-05 tokens_per_second_per_gpu:1059.7426293489132
Step 3531 | loss:1.3428829908370972 lr:2.0410413646014782e-05 tokens_per_second_per_gpu:982.0703307841712
Step 3532 | loss:1.2458080053329468 lr:2.039206702112246e-05 tokens_per_second_per_gpu:1129.2899323221466
Step 3533 | loss:1.2846794128417969 lr:2.0373725255530568e-05 tokens_per_second_per_gpu:1007.4427434637964
Step 3534 | loss:1.3929669857025146 lr:2.0355388355340464e-05 tokens_per_second_per_gpu:726.6570656909395
Step 3535 | loss:1.412021517753601 lr:2.033705632665187e-05 tokens_per_second_per_gpu:894.2196946961055
Step 3536 | loss:1.2845520973205566 lr:2.0318729175562898e-05 tokens_per_second_per_gpu:747.3972501711005
Step 3537 | loss:1.42227041721344 lr:2.0300406908170057e-05 tokens_per_second_per_gpu:840.55373753162
Step 3538 | loss:1.3034923076629639 lr:2.0282089530568204e-05 tokens_per_second_per_gpu:750.1095306326013
Step 3539 | loss:1.4840993881225586 lr:2.0263777048850577e-05 tokens_per_second_per_gpu:731.5029778893443
Step 3540 | loss:1.1533808708190918 lr:2.024546946910879e-05 tokens_per_second_per_gpu:1003.6933296941816
Step 3541 | loss:1.4666157960891724 lr:2.0227166797432828e-05 tokens_per_second_per_gpu:1010.2974497579308
Step 3542 | loss:1.325239658355713 lr:2.0208869039911024e-05 tokens_per_second_per_gpu:938.0266110074376
Step 3543 | loss:1.4453060626983643 lr:2.019057620263011e-05 tokens_per_second_per_gpu:879.5087080576931
Step 3544 | loss:1.2588436603546143 lr:2.0172288291675145e-05 tokens_per_second_per_gpu:881.6669475115153
Step 3545 | loss:1.2414898872375488 lr:2.0154005313129582e-05 tokens_per_second_per_gpu:1109.9056003252138
Step 3546 | loss:1.335450291633606 lr:2.0135727273075214e-05 tokens_per_second_per_gpu:1132.4430428748096
Step 3547 | loss:1.3231756687164307 lr:2.0117454177592186e-05 tokens_per_second_per_gpu:804.0801341538668
Step 3548 | loss:1.3775465488433838 lr:2.0099186032759003e-05 tokens_per_second_per_gpu:827.1895527165274
Step 3549 | loss:1.2674791812896729 lr:2.0080922844652567e-05 tokens_per_second_per_gpu:1381.1272912619283
Step 3550 | loss:1.3254094123840332 lr:2.0062664619348043e-05 tokens_per_second_per_gpu:946.270160017273
Step 3551 | loss:1.4844021797180176 lr:2.0044411362919036e-05 tokens_per_second_per_gpu:974.2867899110669
Step 3552 | loss:1.2181520462036133 lr:2.002616308143741e-05 tokens_per_second_per_gpu:1216.7944419344085
Step 3553 | loss:1.3666856288909912 lr:2.0007919780973475e-05 tokens_per_second_per_gpu:811.8177049139431
Step 3554 | loss:1.3337494134902954 lr:1.9989681467595767e-05 tokens_per_second_per_gpu:955.18919621388
Step 3555 | loss:1.3342047929763794 lr:1.9971448147371283e-05 tokens_per_second_per_gpu:853.728391781412
Step 3556 | loss:1.345993995666504 lr:1.995321982636527e-05 tokens_per_second_per_gpu:950.5877316942742
Step 3557 | loss:1.561888337135315 lr:1.993499651064135e-05 tokens_per_second_per_gpu:904.5235607769458
Step 3558 | loss:1.363518476486206 lr:1.991677820626148e-05 tokens_per_second_per_gpu:965.7560306064534
Step 3559 | loss:1.3803761005401611 lr:1.989856491928593e-05 tokens_per_second_per_gpu:795.4256000327256
Step 3560 | loss:1.400883674621582 lr:1.988035665577331e-05 tokens_per_second_per_gpu:784.2174938798036
Step 3561 | loss:1.3889851570129395 lr:1.9862153421780607e-05 tokens_per_second_per_gpu:1028.1019038082609
Step 3562 | loss:1.3072876930236816 lr:1.9843955223363027e-05 tokens_per_second_per_gpu:919.9790498316139
Step 3563 | loss:1.3338720798492432 lr:1.9825762066574227e-05 tokens_per_second_per_gpu:881.5090727528842
Step 3564 | loss:1.0959781408309937 lr:1.980757395746607e-05 tokens_per_second_per_gpu:1017.0406445487619
Step 3565 | loss:1.323003888130188 lr:1.9789390902088852e-05 tokens_per_second_per_gpu:1132.6108008742603
Step 3566 | loss:1.2485980987548828 lr:1.977121290649106e-05 tokens_per_second_per_gpu:872.3908103294183
Step 3567 | loss:1.422735571861267 lr:1.9753039976719633e-05 tokens_per_second_per_gpu:774.3413604331025
Step 3568 | loss:1.3429023027420044 lr:1.9734872118819735e-05 tokens_per_second_per_gpu:949.1645933248894
Step 3569 | loss:1.2976070642471313 lr:1.9716709338834868e-05 tokens_per_second_per_gpu:953.2759876629216
Step 3570 | loss:1.4548900127410889 lr:1.969855164280685e-05 tokens_per_second_per_gpu:785.7279890526554
Step 3571 | loss:1.4461479187011719 lr:1.9680399036775795e-05 tokens_per_second_per_gpu:924.7083759461001
Step 3572 | loss:1.328386902809143 lr:1.9662251526780143e-05 tokens_per_second_per_gpu:1183.357474963278
Step 3573 | loss:1.5533676147460938 lr:1.9644109118856617e-05 tokens_per_second_per_gpu:953.430879073158
Step 3574 | loss:1.4086226224899292 lr:1.962597181904025e-05 tokens_per_second_per_gpu:916.6941943254934
Step 3575 | loss:1.3884942531585693 lr:1.960783963336441e-05 tokens_per_second_per_gpu:871.4962214744916
Step 3576 | loss:1.4123923778533936 lr:1.958971256786069e-05 tokens_per_second_per_gpu:885.8344287881747
Step 3577 | loss:1.3785302639007568 lr:1.9571590628559067e-05 tokens_per_second_per_gpu:933.189440737686
Step 3578 | loss:1.292140007019043 lr:1.9553473821487722e-05 tokens_per_second_per_gpu:740.6581979298968
Step 3579 | loss:1.3903273344039917 lr:1.9535362152673212e-05 tokens_per_second_per_gpu:657.9712348809098
Step 3580 | loss:1.2796539068222046 lr:1.9517255628140335e-05 tokens_per_second_per_gpu:878.1313470878614
Step 3581 | loss:1.227217197418213 lr:1.94991542539122e-05 tokens_per_second_per_gpu:1059.475219541989
Step 3582 | loss:1.3988754749298096 lr:1.948105803601018e-05 tokens_per_second_per_gpu:726.649246464341
Step 3583 | loss:1.2958966493606567 lr:1.946296698045395e-05 tokens_per_second_per_gpu:718.0718585545685
Step 3584 | loss:1.270841360092163 lr:1.944488109326147e-05 tokens_per_second_per_gpu:1038.0181895452604
Step 3585 | loss:1.2824938297271729 lr:1.942680038044897e-05 tokens_per_second_per_gpu:955.1794507370782
Step 3586 | loss:1.3049806356430054 lr:1.940872484803097e-05 tokens_per_second_per_gpu:1064.9306639174451
Step 3587 | loss:1.2540113925933838 lr:1.9390654502020258e-05 tokens_per_second_per_gpu:971.7328809108882
Step 3588 | loss:1.3161664009094238 lr:1.937258934842788e-05 tokens_per_second_per_gpu:896.6605308734565
Step 3589 | loss:1.2457244396209717 lr:1.935452939326322e-05 tokens_per_second_per_gpu:909.2221275738867
Step 3590 | loss:1.289925456047058 lr:1.9336474642533833e-05 tokens_per_second_per_gpu:1122.7552729143972
Step 3591 | loss:1.546040415763855 lr:1.9318425102245638e-05 tokens_per_second_per_gpu:864.8749624858409
Step 3592 | loss:1.451037049293518 lr:1.930038077840276e-05 tokens_per_second_per_gpu:814.6271450759454
Step 3593 | loss:1.3144813776016235 lr:1.928234167700762e-05 tokens_per_second_per_gpu:974.8341367248125
Step 3594 | loss:1.3231397867202759 lr:1.9264307804060872e-05 tokens_per_second_per_gpu:942.0522156384717
Step 3595 | loss:1.3754055500030518 lr:1.9246279165561465e-05 tokens_per_second_per_gpu:670.5586794384521
Step 3596 | loss:1.3139708042144775 lr:1.9228255767506583e-05 tokens_per_second_per_gpu:936.915088986294
Step 3597 | loss:1.3408856391906738 lr:1.921023761589168e-05 tokens_per_second_per_gpu:771.9783308176011
Step 3598 | loss:1.315141201019287 lr:1.9192224716710445e-05 tokens_per_second_per_gpu:1089.5379507001765
Step 3599 | loss:1.2674224376678467 lr:1.917421707595485e-05 tokens_per_second_per_gpu:902.8358088879166
Step 3600 | loss:1.3137532472610474 lr:1.9156214699615092e-05 tokens_per_second_per_gpu:827.8601596779209
Step 3601 | loss:1.4386497735977173 lr:1.913821759367963e-05 tokens_per_second_per_gpu:830.1850022672327
Step 3602 | loss:1.2607473134994507 lr:1.912022576413517e-05 tokens_per_second_per_gpu:749.3287126911279
Step 3603 | loss:1.4411885738372803 lr:1.9102239216966637e-05 tokens_per_second_per_gpu:851.2191024084095
Step 3604 | loss:1.285072684288025 lr:1.9084257958157265e-05 tokens_per_second_per_gpu:906.8805967034104
Step 3605 | loss:1.2742711305618286 lr:1.906628199368843e-05 tokens_per_second_per_gpu:1146.6811670168322
Step 3606 | loss:1.2606112957000732 lr:1.904831132953986e-05 tokens_per_second_per_gpu:721.7922565533411
Step 3607 | loss:1.345051884651184 lr:1.9030345971689407e-05 tokens_per_second_per_gpu:946.5639522333433
Step 3608 | loss:1.4210621118545532 lr:1.9012385926113254e-05 tokens_per_second_per_gpu:1048.8031548265287
Step 3609 | loss:1.3822702169418335 lr:1.8994431198785735e-05 tokens_per_second_per_gpu:885.7496785772944
Step 3610 | loss:1.5125774145126343 lr:1.8976481795679493e-05 tokens_per_second_per_gpu:905.4724995755589
Step 3611 | loss:1.2803168296813965 lr:1.8958537722765346e-05 tokens_per_second_per_gpu:897.826111587888
Step 3612 | loss:1.3640704154968262 lr:1.8940598986012352e-05 tokens_per_second_per_gpu:930.8756273745212
Step 3613 | loss:1.272953987121582 lr:1.8922665591387804e-05 tokens_per_second_per_gpu:955.5715144524862
Step 3614 | loss:1.2524983882904053 lr:1.8904737544857206e-05 tokens_per_second_per_gpu:881.2622483406296
Step 3615 | loss:1.5267081260681152 lr:1.888681485238429e-05 tokens_per_second_per_gpu:600.2518672946659
Step 3616 | loss:1.2371169328689575 lr:1.8868897519931e-05 tokens_per_second_per_gpu:1076.357041178803
Step 3617 | loss:1.41598641872406 lr:1.8850985553457493e-05 tokens_per_second_per_gpu:1178.1259477210076
Step 3618 | loss:1.3659522533416748 lr:1.883307895892219e-05 tokens_per_second_per_gpu:976.204396270286
Step 3619 | loss:1.3880966901779175 lr:1.881517774228163e-05 tokens_per_second_per_gpu:942.5457354963978
Step 3620 | loss:1.2244683504104614 lr:1.879728190949067e-05 tokens_per_second_per_gpu:916.2342289216223
Step 3621 | loss:1.3010835647583008 lr:1.877939146650227e-05 tokens_per_second_per_gpu:804.6475495733479
Step 3622 | loss:1.200376033782959 lr:1.876150641926769e-05 tokens_per_second_per_gpu:941.835255219543
Step 3623 | loss:1.384993076324463 lr:1.8743626773736353e-05 tokens_per_second_per_gpu:732.9893916680933
Step 3624 | loss:1.3679754734039307 lr:1.8725752535855877e-05 tokens_per_second_per_gpu:895.5135761960821
Step 3625 | loss:1.3415958881378174 lr:1.8707883711572095e-05 tokens_per_second_per_gpu:1083.7337318698842
Step 3626 | loss:1.366997480392456 lr:1.8690020306829042e-05 tokens_per_second_per_gpu:899.6712497398292
Step 3627 | loss:1.3445651531219482 lr:1.8672162327568935e-05 tokens_per_second_per_gpu:900.7903854763308
Step 3628 | loss:1.3126801252365112 lr:1.8654309779732205e-05 tokens_per_second_per_gpu:809.1677615493921
Step 3629 | loss:1.375692367553711 lr:1.8636462669257448e-05 tokens_per_second_per_gpu:785.4132137640588
Step 3630 | loss:1.4259467124938965 lr:1.8618621002081515e-05 tokens_per_second_per_gpu:822.6824381884059
Step 3631 | loss:1.172196388244629 lr:1.860078478413934e-05 tokens_per_second_per_gpu:865.864965865616
Step 3632 | loss:1.311134934425354 lr:1.8582954021364172e-05 tokens_per_second_per_gpu:717.3238907714742
Step 3633 | loss:1.3198556900024414 lr:1.856512871968732e-05 tokens_per_second_per_gpu:1204.116310341649
Step 3634 | loss:1.41946280002594 lr:1.8547308885038373e-05 tokens_per_second_per_gpu:904.190250697625
Step 3635 | loss:1.2730927467346191 lr:1.8529494523345056e-05 tokens_per_second_per_gpu:783.281237273327
Step 3636 | loss:1.3355962038040161 lr:1.8511685640533277e-05 tokens_per_second_per_gpu:1015.2531167662178
Step 3637 | loss:1.4411604404449463 lr:1.8493882242527132e-05 tokens_per_second_per_gpu:637.7003612285337
Step 3638 | loss:1.1001381874084473 lr:1.8476084335248875e-05 tokens_per_second_per_gpu:1023.4642925854552
Step 3639 | loss:1.1620259284973145 lr:1.8458291924618957e-05 tokens_per_second_per_gpu:1273.5221995150832
Step 3640 | loss:1.3869950771331787 lr:1.844050501655599e-05 tokens_per_second_per_gpu:809.7674471423963
Step 3641 | loss:1.3914542198181152 lr:1.842272361697673e-05 tokens_per_second_per_gpu:878.7894814824755
Step 3642 | loss:1.3642024993896484 lr:1.8404947731796174e-05 tokens_per_second_per_gpu:876.0851294871967
Step 3643 | loss:1.4602160453796387 lr:1.838717736692738e-05 tokens_per_second_per_gpu:720.5249120425774
Step 3644 | loss:1.3156079053878784 lr:1.8369412528281676e-05 tokens_per_second_per_gpu:1138.450918661188
Step 3645 | loss:1.4092795848846436 lr:1.8351653221768452e-05 tokens_per_second_per_gpu:1077.2052151461671
Step 3646 | loss:1.523850917816162 lr:1.8333899453295355e-05 tokens_per_second_per_gpu:697.010538472212
Step 3647 | loss:1.4742109775543213 lr:1.8316151228768087e-05 tokens_per_second_per_gpu:760.3356005997821
Step 3648 | loss:1.316204309463501 lr:1.8298408554090603e-05 tokens_per_second_per_gpu:944.8774583609636
Step 3649 | loss:1.3045321702957153 lr:1.8280671435164962e-05 tokens_per_second_per_gpu:924.511312615089
Step 3650 | loss:1.3405770063400269 lr:1.8262939877891375e-05 tokens_per_second_per_gpu:803.3318576634565
Step 3651 | loss:1.3159114122390747 lr:1.824521388816821e-05 tokens_per_second_per_gpu:945.8077268361391
Step 3652 | loss:1.2256274223327637 lr:1.8227493471891988e-05 tokens_per_second_per_gpu:1007.4908290012207
Step 3653 | loss:1.4374312162399292 lr:1.8209778634957364e-05 tokens_per_second_per_gpu:1051.6301766525849
Step 3654 | loss:1.404792070388794 lr:1.819206938325715e-05 tokens_per_second_per_gpu:855.6820687543607
Step 3655 | loss:1.3829175233840942 lr:1.8174365722682288e-05 tokens_per_second_per_gpu:816.6603937725114
Step 3656 | loss:1.2494511604309082 lr:1.815666765912187e-05 tokens_per_second_per_gpu:786.056132348403
Step 3657 | loss:1.3423316478729248 lr:1.813897519846313e-05 tokens_per_second_per_gpu:1044.155428892255
Step 3658 | loss:1.2662887573242188 lr:1.8121288346591414e-05 tokens_per_second_per_gpu:880.6591501172435
Step 3659 | loss:1.4289010763168335 lr:1.8103607109390226e-05 tokens_per_second_per_gpu:672.4414477391365
Step 3660 | loss:1.2967791557312012 lr:1.8085931492741184e-05 tokens_per_second_per_gpu:855.8279666206831
Step 3661 | loss:1.4641122817993164 lr:1.8068261502524093e-05 tokens_per_second_per_gpu:850.4422213911155
Step 3662 | loss:1.461912751197815 lr:1.8050597144616776e-05 tokens_per_second_per_gpu:558.2236900184809
Step 3663 | loss:1.330225944519043 lr:1.8032938424895293e-05 tokens_per_second_per_gpu:1003.678926698073
Step 3664 | loss:1.4749337434768677 lr:1.8015285349233764e-05 tokens_per_second_per_gpu:916.0262795311966
Step 3665 | loss:1.2995474338531494 lr:1.7997637923504457e-05 tokens_per_second_per_gpu:888.2566459069933
Step 3666 | loss:1.4585168361663818 lr:1.7979996153577756e-05 tokens_per_second_per_gpu:771.6390761193022
Step 3667 | loss:1.2701685428619385 lr:1.7962360045322155e-05 tokens_per_second_per_gpu:1024.5317546152085
Step 3668 | loss:1.4328407049179077 lr:1.7944729604604268e-05 tokens_per_second_per_gpu:775.1030207705401
Step 3669 | loss:1.5172441005706787 lr:1.7927104837288837e-05 tokens_per_second_per_gpu:528.7736926606806
Step 3670 | loss:1.2323411703109741 lr:1.7909485749238705e-05 tokens_per_second_per_gpu:1001.3297717337069
Step 3671 | loss:1.4087191820144653 lr:1.7891872346314815e-05 tokens_per_second_per_gpu:904.3749740050994
Step 3672 | loss:1.2977120876312256 lr:1.787426463437623e-05 tokens_per_second_per_gpu:980.5988147769039
Step 3673 | loss:1.2390881776809692 lr:1.785666261928015e-05 tokens_per_second_per_gpu:787.7731304715292
Step 3674 | loss:1.205788016319275 lr:1.7839066306881816e-05 tokens_per_second_per_gpu:1088.3386225084184
Step 3675 | loss:1.3129924535751343 lr:1.7821475703034646e-05 tokens_per_second_per_gpu:1061.3630500609377
Step 3676 | loss:1.3473787307739258 lr:1.7803890813590064e-05 tokens_per_second_per_gpu:995.4363436738885
Step 3677 | loss:1.270747423171997 lr:1.7786311644397705e-05 tokens_per_second_per_gpu:967.6802884409731
Step 3678 | loss:1.3696630001068115 lr:1.7768738201305215e-05 tokens_per_second_per_gpu:968.440675567172
Step 3679 | loss:1.4488605260849 lr:1.7751170490158375e-05 tokens_per_second_per_gpu:1115.8193753383423
Step 3680 | loss:1.3783429861068726 lr:1.773360851680105e-05 tokens_per_second_per_gpu:1117.0636303444703
Step 3681 | loss:1.3163928985595703 lr:1.771605228707519e-05 tokens_per_second_per_gpu:719.1564224688942
Step 3682 | loss:1.313560962677002 lr:1.7698501806820847e-05 tokens_per_second_per_gpu:719.6805777624754
Step 3683 | loss:1.2031437158584595 lr:1.768095708187615e-05 tokens_per_second_per_gpu:1154.6906913152313
Step 3684 | loss:1.3362905979156494 lr:1.7663418118077304e-05 tokens_per_second_per_gpu:829.4361451789622
Step 3685 | loss:1.1883318424224854 lr:1.764588492125866e-05 tokens_per_second_per_gpu:926.0951246763726
Step 3686 | loss:1.2105777263641357 lr:1.7628357497252533e-05 tokens_per_second_per_gpu:865.0465477706002
Step 3687 | loss:1.3086862564086914 lr:1.7610835851889455e-05 tokens_per_second_per_gpu:859.5424675951513
Step 3688 | loss:1.2636194229125977 lr:1.7593319990997904e-05 tokens_per_second_per_gpu:941.844321832662
Step 3689 | loss:1.4449083805084229 lr:1.757580992040455e-05 tokens_per_second_per_gpu:891.1047303228926
Step 3690 | loss:1.4722789525985718 lr:1.7558305645934042e-05 tokens_per_second_per_gpu:564.8073518640658
Step 3691 | loss:1.373587965965271 lr:1.7540807173409168e-05 tokens_per_second_per_gpu:860.2866733331554
Step 3692 | loss:1.2362357378005981 lr:1.7523314508650753e-05 tokens_per_second_per_gpu:846.9885224678413
Step 3693 | loss:1.39735746383667 lr:1.7505827657477705e-05 tokens_per_second_per_gpu:702.9036455556225
Step 3694 | loss:1.5078715085983276 lr:1.748834662570698e-05 tokens_per_second_per_gpu:863.2788020067119
Step 3695 | loss:1.4610607624053955 lr:1.7470871419153613e-05 tokens_per_second_per_gpu:818.9705817333727
Step 3696 | loss:1.2351176738739014 lr:1.745340204363069e-05 tokens_per_second_per_gpu:1039.9520175329333
Step 3697 | loss:1.171618103981018 lr:1.7435938504949392e-05 tokens_per_second_per_gpu:1083.6089754639318
Step 3698 | loss:1.4484000205993652 lr:1.7418480808918892e-05 tokens_per_second_per_gpu:906.6441274032
Step 3699 | loss:1.3366022109985352 lr:1.7401028961346503e-05 tokens_per_second_per_gpu:940.4859493616167
Step 3700 | loss:1.255730152130127 lr:1.7383582968037497e-05 tokens_per_second_per_gpu:1024.17792911237
Step 3701 | loss:1.3845027685165405 lr:1.7366142834795304e-05 tokens_per_second_per_gpu:795.3624509641166
Step 3702 | loss:1.4893214702606201 lr:1.7348708567421297e-05 tokens_per_second_per_gpu:733.4166555007686
Step 3703 | loss:1.4170657396316528 lr:1.7331280171714988e-05 tokens_per_second_per_gpu:932.4408492865895
Step 3704 | loss:1.38693106174469 lr:1.731385765347389e-05 tokens_per_second_per_gpu:698.2104722986705
Step 3705 | loss:1.344706654548645 lr:1.7296441018493563e-05 tokens_per_second_per_gpu:639.464729414471
Step 3706 | loss:1.360446572303772 lr:1.7279030272567624e-05 tokens_per_second_per_gpu:989.9464033587367
Step 3707 | loss:1.3252376317977905 lr:1.726162542148772e-05 tokens_per_second_per_gpu:891.1900843537088
Step 3708 | loss:1.4321630001068115 lr:1.7244226471043544e-05 tokens_per_second_per_gpu:800.7730276505478
Step 3709 | loss:1.2800465822219849 lr:1.7226833427022817e-05 tokens_per_second_per_gpu:962.2271092083748
Step 3710 | loss:1.482567548751831 lr:1.7209446295211308e-05 tokens_per_second_per_gpu:626.6691936860275
Step 3711 | loss:1.2912147045135498 lr:1.7192065081392807e-05 tokens_per_second_per_gpu:855.8337084170186
Step 3712 | loss:1.4091143608093262 lr:1.717468979134914e-05 tokens_per_second_per_gpu:1070.655408110062
Step 3713 | loss:1.3050230741500854 lr:1.7157320430860172e-05 tokens_per_second_per_gpu:897.4671335245713
Step 3714 | loss:1.381973385810852 lr:1.7139957005703782e-05 tokens_per_second_per_gpu:959.499930079629
Step 3715 | loss:1.1397159099578857 lr:1.712259952165586e-05 tokens_per_second_per_gpu:907.274172733868
Step 3716 | loss:1.303225040435791 lr:1.7105247984490374e-05 tokens_per_second_per_gpu:1017.7106610589469
Step 3717 | loss:1.2634400129318237 lr:1.7087902399979266e-05 tokens_per_second_per_gpu:894.9199709083864
Step 3718 | loss:1.2295383214950562 lr:1.7070562773892504e-05 tokens_per_second_per_gpu:834.0093274145959
Step 3719 | loss:1.3340792655944824 lr:1.7053229111998085e-05 tokens_per_second_per_gpu:1089.7309415896186
Step 3720 | loss:1.2982558012008667 lr:1.703590142006202e-05 tokens_per_second_per_gpu:911.5131008387176
Step 3721 | loss:1.3625102043151855 lr:1.7018579703848325e-05 tokens_per_second_per_gpu:681.1912712875984
Step 3722 | loss:1.3643985986709595 lr:1.7001263969119043e-05 tokens_per_second_per_gpu:1129.3071880601328
Step 3723 | loss:1.3202102184295654 lr:1.6983954221634217e-05 tokens_per_second_per_gpu:841.4580551017954
Step 3724 | loss:1.348940134048462 lr:1.6966650467151902e-05 tokens_per_second_per_gpu:1206.6905114896306
Step 3725 | loss:1.3465396165847778 lr:1.6949352711428152e-05 tokens_per_second_per_gpu:909.418205463892
Step 3726 | loss:1.382068395614624 lr:1.6932060960217034e-05 tokens_per_second_per_gpu:675.4283763740082
Step 3727 | loss:1.445529580116272 lr:1.691477521927061e-05 tokens_per_second_per_gpu:780.6954791392203
Step 3728 | loss:1.2373180389404297 lr:1.6897495494338977e-05 tokens_per_second_per_gpu:1030.5796163449165
Step 3729 | loss:1.3758115768432617 lr:1.6880221791170158e-05 tokens_per_second_per_gpu:1004.7210060903378
Step 3730 | loss:1.343191146850586 lr:1.686295411551026e-05 tokens_per_second_per_gpu:823.8829468374021
Step 3731 | loss:1.435380458831787 lr:1.68456924731033e-05 tokens_per_second_per_gpu:721.7774956503414
Step 3732 | loss:1.3041291236877441 lr:1.682843686969137e-05 tokens_per_second_per_gpu:1032.9308106701005
Step 3733 | loss:1.0952000617980957 lr:1.681118731101447e-05 tokens_per_second_per_gpu:1158.8775827688264
Step 3734 | loss:1.212396264076233 lr:1.6793943802810664e-05 tokens_per_second_per_gpu:977.9803483533799
Step 3735 | loss:1.4378105401992798 lr:1.677670635081597e-05 tokens_per_second_per_gpu:759.128519940662
Step 3736 | loss:1.4438209533691406 lr:1.675947496076438e-05 tokens_per_second_per_gpu:682.1039126503707
Step 3737 | loss:1.5071368217468262 lr:1.6742249638387886e-05 tokens_per_second_per_gpu:1007.973691201571
Step 3738 | loss:1.384565830230713 lr:1.672503038941646e-05 tokens_per_second_per_gpu:915.6188210913284
Step 3739 | loss:1.3696966171264648 lr:1.670781721957804e-05 tokens_per_second_per_gpu:959.6303969968955
Step 3740 | loss:1.174075722694397 lr:1.669061013459859e-05 tokens_per_second_per_gpu:1201.8529065253151
Step 3741 | loss:1.432377576828003 lr:1.6673409140201964e-05 tokens_per_second_per_gpu:879.7294954223114
Step 3742 | loss:1.2724928855895996 lr:1.6656214242110083e-05 tokens_per_second_per_gpu:906.9898593675483
Step 3743 | loss:1.311488389968872 lr:1.6639025446042755e-05 tokens_per_second_per_gpu:980.5696048889265
Step 3744 | loss:1.3951064348220825 lr:1.6621842757717845e-05 tokens_per_second_per_gpu:934.159616851037
Step 3745 | loss:1.218253254890442 lr:1.660466618285109e-05 tokens_per_second_per_gpu:795.7105803461859
Step 3746 | loss:1.2627488374710083 lr:1.6587495727156284e-05 tokens_per_second_per_gpu:786.0409570153993
Step 3747 | loss:1.2940133810043335 lr:1.6570331396345135e-05 tokens_per_second_per_gpu:1133.1451865314696
Step 3748 | loss:1.3949772119522095 lr:1.6553173196127317e-05 tokens_per_second_per_gpu:1371.259682302612
Step 3749 | loss:1.2936855554580688 lr:1.653602113221048e-05 tokens_per_second_per_gpu:950.7382083394134
Step 3750 | loss:1.2424836158752441 lr:1.6518875210300216e-05 tokens_per_second_per_gpu:807.2171829358475
Step 3751 | loss:1.1709243059158325 lr:1.6501735436100077e-05 tokens_per_second_per_gpu:1097.5189312725524
Step 3752 | loss:1.3649617433547974 lr:1.648460181531161e-05 tokens_per_second_per_gpu:784.4659908405214
Step 3753 | loss:1.4080169200897217 lr:1.646747435363424e-05 tokens_per_second_per_gpu:690.7482905873338
Step 3754 | loss:1.3769571781158447 lr:1.6450353056765416e-05 tokens_per_second_per_gpu:880.7101225837417
Step 3755 | loss:1.3421095609664917 lr:1.6433237930400466e-05 tokens_per_second_per_gpu:629.2505294563309
Step 3756 | loss:1.3532929420471191 lr:1.6416128980232748e-05 tokens_per_second_per_gpu:602.382812493807
Step 3757 | loss:1.4337948560714722 lr:1.639902621195348e-05 tokens_per_second_per_gpu:744.5831245774802
Step 3758 | loss:1.3801252841949463 lr:1.638192963125189e-05 tokens_per_second_per_gpu:842.0865225314689
Step 3759 | loss:1.2566856145858765 lr:1.6364839243815116e-05 tokens_per_second_per_gpu:610.3273667709501
Step 3760 | loss:1.2533714771270752 lr:1.6347755055328243e-05 tokens_per_second_per_gpu:1261.6861164574648
Step 3761 | loss:1.4753916263580322 lr:1.633067707147429e-05 tokens_per_second_per_gpu:795.5416970432237
Step 3762 | loss:1.312696099281311 lr:1.6313605297934216e-05 tokens_per_second_per_gpu:904.1093533135274
Step 3763 | loss:1.3205251693725586 lr:1.6296539740386917e-05 tokens_per_second_per_gpu:1071.3508712932664
Step 3764 | loss:1.431373119354248 lr:1.6279480404509208e-05 tokens_per_second_per_gpu:743.3437150596432
Step 3765 | loss:1.104227066040039 lr:1.6262427295975856e-05 tokens_per_second_per_gpu:967.9235650943316
Step 3766 | loss:1.4743120670318604 lr:1.6245380420459536e-05 tokens_per_second_per_gpu:813.3774471851876
Step 3767 | loss:1.520071268081665 lr:1.6228339783630846e-05 tokens_per_second_per_gpu:732.4925447780564
Step 3768 | loss:1.1608580350875854 lr:1.621130539115836e-05 tokens_per_second_per_gpu:961.4836661685204
Step 3769 | loss:1.4117180109024048 lr:1.619427724870849e-05 tokens_per_second_per_gpu:692.4125070487526
Step 3770 | loss:1.3392682075500488 lr:1.6177255361945644e-05 tokens_per_second_per_gpu:982.9704715555857
Step 3771 | loss:1.3082221746444702 lr:1.616023973653211e-05 tokens_per_second_per_gpu:929.2839715673051
Step 3772 | loss:1.5097808837890625 lr:1.61432303781281e-05 tokens_per_second_per_gpu:719.3293913733412
Step 3773 | loss:1.327384114265442 lr:1.612622729239175e-05 tokens_per_second_per_gpu:950.552318884172
Step 3774 | loss:1.3969515562057495 lr:1.61092304849791e-05 tokens_per_second_per_gpu:879.7862145994986
Step 3775 | loss:1.307953119277954 lr:1.6092239961544102e-05 tokens_per_second_per_gpu:860.0056997892259
Step 3776 | loss:1.4162105321884155 lr:1.6075255727738625e-05 tokens_per_second_per_gpu:675.7628420324174
Step 3777 | loss:1.3855407238006592 lr:1.605827778921244e-05 tokens_per_second_per_gpu:840.2994246683782
Step 3778 | loss:1.4194248914718628 lr:1.604130615161322e-05 tokens_per_second_per_gpu:901.9367266372595
Step 3779 | loss:1.4454941749572754 lr:1.6024340820586557e-05 tokens_per_second_per_gpu:675.4446370662647
Step 3780 | loss:1.341172456741333 lr:1.600738180177593e-05 tokens_per_second_per_gpu:874.3807994205555
Step 3781 | loss:1.459492564201355 lr:1.5990429100822723e-05 tokens_per_second_per_gpu:975.6496494492307
Step 3782 | loss:1.4969531297683716 lr:1.5973482723366208e-05 tokens_per_second_per_gpu:641.4563908370811
Step 3783 | loss:1.4967612028121948 lr:1.59565426750436e-05 tokens_per_second_per_gpu:819.4490383574235
Step 3784 | loss:1.329753041267395 lr:1.5939608961489922e-05 tokens_per_second_per_gpu:860.352945834948
Step 3785 | loss:1.5006746053695679 lr:1.59226815883382e-05 tokens_per_second_per_gpu:699.9371802520735
Step 3786 | loss:1.3604234457015991 lr:1.5905760561219226e-05 tokens_per_second_per_gpu:1258.5523177040523
Step 3787 | loss:1.2408385276794434 lr:1.588884588576181e-05 tokens_per_second_per_gpu:1039.2306341444778
Step 3788 | loss:1.27777898311615 lr:1.5871937567592527e-05 tokens_per_second_per_gpu:1097.9281536729816
Step 3789 | loss:1.4095039367675781 lr:1.585503561233594e-05 tokens_per_second_per_gpu:787.7898637859392
Step 3790 | loss:1.2082329988479614 lr:1.5838140025614442e-05 tokens_per_second_per_gpu:1316.1708496500285
Step 3791 | loss:1.2926177978515625 lr:1.5821250813048302e-05 tokens_per_second_per_gpu:873.5785894955524
Step 3792 | loss:1.3943276405334473 lr:1.58043679802557e-05 tokens_per_second_per_gpu:735.0397974820017
Step 3793 | loss:1.2134459018707275 lr:1.578749153285267e-05 tokens_per_second_per_gpu:859.4271970104843
Step 3794 | loss:1.3380376100540161 lr:1.5770621476453128e-05 tokens_per_second_per_gpu:817.7328710674576
Step 3795 | loss:1.2838001251220703 lr:1.575375781666887e-05 tokens_per_second_per_gpu:637.5313609939323
Step 3796 | loss:1.3406407833099365 lr:1.573690055910954e-05 tokens_per_second_per_gpu:1231.2199362835204
Step 3797 | loss:1.4816207885742188 lr:1.5720049709382717e-05 tokens_per_second_per_gpu:675.6431327788123
Step 3798 | loss:1.2028285264968872 lr:1.570320527309375e-05 tokens_per_second_per_gpu:905.3434916043617
Step 3799 | loss:1.3447291851043701 lr:1.5686367255845955e-05 tokens_per_second_per_gpu:759.0468465938933
Step 3800 | loss:1.3615899085998535 lr:1.566953566324042e-05 tokens_per_second_per_gpu:825.5231931419893
Step 3801 | loss:1.39530348777771 lr:1.565271050087618e-05 tokens_per_second_per_gpu:697.7224000560359
Step 3802 | loss:1.4174463748931885 lr:1.5635891774350076e-05 tokens_per_second_per_gpu:819.5041070567249
Step 3803 | loss:1.3705427646636963 lr:1.561907948925683e-05 tokens_per_second_per_gpu:746.1294849504799
Step 3804 | loss:1.3270148038864136 lr:1.5602273651189007e-05 tokens_per_second_per_gpu:1008.2383610723504
Step 3805 | loss:1.2117221355438232 lr:1.5585474265737042e-05 tokens_per_second_per_gpu:1280.0327286441573
Step 3806 | loss:1.311103343963623 lr:1.5568681338489216e-05 tokens_per_second_per_gpu:882.0277840851393
Step 3807 | loss:1.241563320159912 lr:1.5551894875031668e-05 tokens_per_second_per_gpu:996.6666111508133
Step 3808 | loss:1.4740259647369385 lr:1.5535114880948365e-05 tokens_per_second_per_gpu:783.7903473270807
Step 3809 | loss:1.4232674837112427 lr:1.551834136182118e-05 tokens_per_second_per_gpu:725.7271469176266
Step 3810 | loss:1.119523525238037 lr:1.5501574323229737e-05 tokens_per_second_per_gpu:1079.902604425223
Step 3811 | loss:1.3093526363372803 lr:1.548481377075161e-05 tokens_per_second_per_gpu:989.9622689861395
Step 3812 | loss:1.3134050369262695 lr:1.5468059709962118e-05 tokens_per_second_per_gpu:800.4063266081159
Step 3813 | loss:1.174948811531067 lr:1.5451312146434502e-05 tokens_per_second_per_gpu:944.0813995104028
Step 3814 | loss:1.44888174533844 lr:1.5434571085739792e-05 tokens_per_second_per_gpu:1322.0304177548337
Step 3815 | loss:1.5263868570327759 lr:1.5417836533446875e-05 tokens_per_second_per_gpu:817.4069985671605
Step 3816 | loss:1.2680916786193848 lr:1.540110849512246e-05 tokens_per_second_per_gpu:846.7804575853212
Step 3817 | loss:1.3085111379623413 lr:1.53843869763311e-05 tokens_per_second_per_gpu:933.8189395898945
Step 3818 | loss:1.322070837020874 lr:1.5367671982635173e-05 tokens_per_second_per_gpu:745.1504870415649
Step 3819 | loss:1.229616403579712 lr:1.5350963519594894e-05 tokens_per_second_per_gpu:780.5647934931633
Step 3820 | loss:1.4299015998840332 lr:1.5334261592768283e-05 tokens_per_second_per_gpu:938.110046323807
Step 3821 | loss:1.3840675354003906 lr:1.5317566207711243e-05 tokens_per_second_per_gpu:805.6984216257899
Step 3822 | loss:1.2660108804702759 lr:1.530087736997741e-05 tokens_per_second_per_gpu:772.1323495478712
Step 3823 | loss:1.1917989253997803 lr:1.528419508511835e-05 tokens_per_second_per_gpu:971.389381775696
Step 3824 | loss:1.4763894081115723 lr:1.5267519358683333e-05 tokens_per_second_per_gpu:808.086593717364
Step 3825 | loss:1.4064878225326538 lr:1.525085019621955e-05 tokens_per_second_per_gpu:750.6250767900494
Step 3826 | loss:1.4821370840072632 lr:1.523418760327195e-05 tokens_per_second_per_gpu:881.9656494317832
Step 3827 | loss:1.3206422328948975 lr:1.5217531585383312e-05 tokens_per_second_per_gpu:867.7782540746094
Step 3828 | loss:1.3780407905578613 lr:1.5200882148094237e-05 tokens_per_second_per_gpu:821.693510685557
Step 3829 | loss:1.4209010601043701 lr:1.5184239296943113e-05 tokens_per_second_per_gpu:837.1743122117085
Step 3830 | loss:1.274106740951538 lr:1.5167603037466163e-05 tokens_per_second_per_gpu:903.7442389417689
Step 3831 | loss:1.313642144203186 lr:1.5150973375197404e-05 tokens_per_second_per_gpu:822.2781735375469
Step 3832 | loss:1.3997427225112915 lr:1.5134350315668654e-05 tokens_per_second_per_gpu:733.6047942876164
Step 3833 | loss:1.2659488916397095 lr:1.511773386440955e-05 tokens_per_second_per_gpu:1055.776017234098
Step 3834 | loss:1.4150962829589844 lr:1.5101124026947519e-05 tokens_per_second_per_gpu:776.9524273305248
Step 3835 | loss:1.3389025926589966 lr:1.508452080880779e-05 tokens_per_second_per_gpu:766.2139562323639
Step 3836 | loss:1.3491040468215942 lr:1.5067924215513392e-05 tokens_per_second_per_gpu:1065.3730212762368
Step 3837 | loss:1.2121061086654663 lr:1.5051334252585151e-05 tokens_per_second_per_gpu:737.1929008178182
Step 3838 | loss:1.3908993005752563 lr:1.5034750925541682e-05 tokens_per_second_per_gpu:741.7585133879483
Step 3839 | loss:1.2708089351654053 lr:1.5018174239899385e-05 tokens_per_second_per_gpu:1078.8556159273926
Step 3840 | loss:1.3421818017959595 lr:1.5001604201172505e-05 tokens_per_second_per_gpu:890.6710372042261
Step 3841 | loss:1.0928623676300049 lr:1.4985040814872977e-05 tokens_per_second_per_gpu:973.6485573411082
Step 3842 | loss:1.319676160812378 lr:1.4968484086510621e-05 tokens_per_second_per_gpu:833.2398408009825
Step 3843 | loss:1.4065755605697632 lr:1.4951934021592984e-05 tokens_per_second_per_gpu:758.363876301444
Step 3844 | loss:1.2959966659545898 lr:1.4935390625625413e-05 tokens_per_second_per_gpu:857.9536727818477
Step 3845 | loss:1.2837331295013428 lr:1.4918853904111038e-05 tokens_per_second_per_gpu:969.0630023035775
Step 3846 | loss:1.4093515872955322 lr:1.4902323862550766e-05 tokens_per_second_per_gpu:1130.40470110823
Step 3847 | loss:1.3404948711395264 lr:1.4885800506443285e-05 tokens_per_second_per_gpu:871.0196542685729
Step 3848 | loss:1.249439001083374 lr:1.4869283841285056e-05 tokens_per_second_per_gpu:1022.824128827117
Step 3849 | loss:1.4459172487258911 lr:1.4852773872570317e-05 tokens_per_second_per_gpu:930.2643919595599
Step 3850 | loss:1.2685954570770264 lr:1.4836270605791078e-05 tokens_per_second_per_gpu:977.3543055581168
Step 3851 | loss:1.442295789718628 lr:1.4819774046437098e-05 tokens_per_second_per_gpu:571.0513075626659
Step 3852 | loss:1.2348321676254272 lr:1.4803284199995972e-05 tokens_per_second_per_gpu:1159.2861542295063
Step 3853 | loss:1.4138001203536987 lr:1.4786801071952962e-05 tokens_per_second_per_gpu:958.7803389222934
Step 3854 | loss:1.2856703996658325 lr:1.4770324667791196e-05 tokens_per_second_per_gpu:838.4786734397754
Step 3855 | loss:1.3168606758117676 lr:1.475385499299147e-05 tokens_per_second_per_gpu:890.6516904276473
Step 3856 | loss:1.3019888401031494 lr:1.4737392053032427e-05 tokens_per_second_per_gpu:856.5967814689894
Step 3857 | loss:1.2157061100006104 lr:1.472093585339042e-05 tokens_per_second_per_gpu:808.8232780101251
Step 3858 | loss:1.3001755475997925 lr:1.4704486399539571e-05 tokens_per_second_per_gpu:628.6746083929323
Step 3859 | loss:1.3864659070968628 lr:1.4688043696951755e-05 tokens_per_second_per_gpu:907.6132142468219
Step 3860 | loss:1.4662989377975464 lr:1.4671607751096611e-05 tokens_per_second_per_gpu:806.8117860740105
Step 3861 | loss:1.2906244993209839 lr:1.4655178567441523e-05 tokens_per_second_per_gpu:1018.0124108439998
Step 3862 | loss:1.3343656063079834 lr:1.4638756151451625e-05 tokens_per_second_per_gpu:1056.7709015386088
Step 3863 | loss:1.3624753952026367 lr:1.4622340508589788e-05 tokens_per_second_per_gpu:985.0059448976593
Step 3864 | loss:1.4682790040969849 lr:1.4605931644316687e-05 tokens_per_second_per_gpu:1134.3283849338957
Step 3865 | loss:1.4010639190673828 lr:1.4589529564090638e-05 tokens_per_second_per_gpu:982.7243645873352
Step 3866 | loss:1.4090814590454102 lr:1.4573134273367823e-05 tokens_per_second_per_gpu:714.2708992820155
Step 3867 | loss:1.3808975219726562 lr:1.4556745777602048e-05 tokens_per_second_per_gpu:1116.1029233415793
Step 3868 | loss:1.2477267980575562 lr:1.4540364082244962e-05 tokens_per_second_per_gpu:990.9186498045793
Step 3869 | loss:1.3063117265701294 lr:1.4523989192745857e-05 tokens_per_second_per_gpu:1021.3623113655054
Step 3870 | loss:1.4128328561782837 lr:1.4507621114551849e-05 tokens_per_second_per_gpu:828.2444327303677
Step 3871 | loss:1.354001760482788 lr:1.4491259853107726e-05 tokens_per_second_per_gpu:768.7896429995459
Step 3872 | loss:1.200812578201294 lr:1.4474905413856035e-05 tokens_per_second_per_gpu:1121.2269665321567
Step 3873 | loss:1.2883740663528442 lr:1.4458557802237047e-05 tokens_per_second_per_gpu:693.96869803435
Step 3874 | loss:1.306091070175171 lr:1.4442217023688769e-05 tokens_per_second_per_gpu:757.2450320478177
Step 3875 | loss:1.4011188745498657 lr:1.4425883083646906e-05 tokens_per_second_per_gpu:1037.9688471077325
Step 3876 | loss:1.424723505973816 lr:1.4409555987544956e-05 tokens_per_second_per_gpu:727.5115430061956
Step 3877 | loss:1.3954071998596191 lr:1.4393235740814045e-05 tokens_per_second_per_gpu:918.5712124867977
Step 3878 | loss:1.2980759143829346 lr:1.437692234888312e-05 tokens_per_second_per_gpu:1025.156592931022
Step 3879 | loss:1.402899980545044 lr:1.4360615817178753e-05 tokens_per_second_per_gpu:1043.9460964599482
Step 3880 | loss:1.4740229845046997 lr:1.434431615112532e-05 tokens_per_second_per_gpu:975.0034766813268
Step 3881 | loss:1.353021502494812 lr:1.4328023356144835e-05 tokens_per_second_per_gpu:663.8088749311885
Step 3882 | loss:1.2574435472488403 lr:1.431173743765709e-05 tokens_per_second_per_gpu:905.3149679887407
Step 3883 | loss:1.3731011152267456 lr:1.4295458401079563e-05 tokens_per_second_per_gpu:907.3357703551831
Step 3884 | loss:1.3681687116622925 lr:1.427918625182744e-05 tokens_per_second_per_gpu:836.3746622640111
Step 3885 | loss:1.2127095460891724 lr:1.4262920995313613e-05 tokens_per_second_per_gpu:970.9415980400006
Step 3886 | loss:1.456315517425537 lr:1.4246662636948701e-05 tokens_per_second_per_gpu:855.3138649070323
Step 3887 | loss:1.3030469417572021 lr:1.4230411182141003e-05 tokens_per_second_per_gpu:939.2645434641479
Step 3888 | loss:1.462092638015747 lr:1.4214166636296538e-05 tokens_per_second_per_gpu:850.5738203802425
Step 3889 | loss:1.285473108291626 lr:1.4197929004819024e-05 tokens_per_second_per_gpu:975.7817583680674
Step 3890 | loss:1.2842329740524292 lr:1.4181698293109876e-05 tokens_per_second_per_gpu:908.3201456903578
Step 3891 | loss:1.2623004913330078 lr:1.4165474506568209e-05 tokens_per_second_per_gpu:1117.0224079023342
Step 3892 | loss:1.3771700859069824 lr:1.4149257650590834e-05 tokens_per_second_per_gpu:1104.5991342997083
Step 3893 | loss:1.4652615785598755 lr:1.4133047730572245e-05 tokens_per_second_per_gpu:1041.9371183872843
Step 3894 | loss:1.2605152130126953 lr:1.4116844751904661e-05 tokens_per_second_per_gpu:850.1664026933353
Step 3895 | loss:1.2243508100509644 lr:1.4100648719977964e-05 tokens_per_second_per_gpu:944.9900174771914
Step 3896 | loss:1.3781189918518066 lr:1.408445964017973e-05 tokens_per_second_per_gpu:914.0403351689251
Step 3897 | loss:1.2381962537765503 lr:1.4068277517895228e-05 tokens_per_second_per_gpu:1302.997625658947
Step 3898 | loss:1.2858796119689941 lr:1.4052102358507407e-05 tokens_per_second_per_gpu:1051.8257398952235
Step 3899 | loss:1.2734642028808594 lr:1.4035934167396899e-05 tokens_per_second_per_gpu:707.5874769543908
Step 3900 | loss:1.4001203775405884 lr:1.4019772949942023e-05 tokens_per_second_per_gpu:1005.0470868786055
Step 3901 | loss:1.1810718774795532 lr:1.4003618711518782e-05 tokens_per_second_per_gpu:992.1318356073035
Step 3902 | loss:1.2603212594985962 lr:1.3987471457500845e-05 tokens_per_second_per_gpu:1357.8870350364493
Step 3903 | loss:1.1805946826934814 lr:1.3971331193259567e-05 tokens_per_second_per_gpu:1005.6306604454916
Step 3904 | loss:1.2194786071777344 lr:1.3955197924163977e-05 tokens_per_second_per_gpu:1162.8301973635369
Step 3905 | loss:1.239243745803833 lr:1.3939071655580773e-05 tokens_per_second_per_gpu:1092.9592376518162
Step 3906 | loss:1.2948601245880127 lr:1.3922952392874315e-05 tokens_per_second_per_gpu:869.4851123539967
Step 3907 | loss:1.2596060037612915 lr:1.3906840141406684e-05 tokens_per_second_per_gpu:1067.704748589816
Step 3908 | loss:1.3886876106262207 lr:1.3890734906537537e-05 tokens_per_second_per_gpu:801.9366011211691
Step 3909 | loss:1.3589684963226318 lr:1.38746366936243e-05 tokens_per_second_per_gpu:892.1397987215641
Step 3910 | loss:1.3318313360214233 lr:1.385854550802196e-05 tokens_per_second_per_gpu:869.51732071183
Step 3911 | loss:1.3157503604888916 lr:1.3842461355083269e-05 tokens_per_second_per_gpu:847.0588998031333
Step 3912 | loss:1.2358449697494507 lr:1.3826384240158545e-05 tokens_per_second_per_gpu:1155.9221060481289
Step 3913 | loss:1.506540060043335 lr:1.3810314168595837e-05 tokens_per_second_per_gpu:842.2949099716642
Step 3914 | loss:1.4217301607131958 lr:1.3794251145740818e-05 tokens_per_second_per_gpu:842.7755953028521
Step 3915 | loss:1.3913978338241577 lr:1.3778195176936815e-05 tokens_per_second_per_gpu:838.2823907313219
Step 3916 | loss:1.2486896514892578 lr:1.3762146267524822e-05 tokens_per_second_per_gpu:1009.1216313949635
Step 3917 | loss:1.1982635259628296 lr:1.374610442284347e-05 tokens_per_second_per_gpu:775.0271655016186
Step 3918 | loss:1.317783236503601 lr:1.3730069648229037e-05 tokens_per_second_per_gpu:1013.6267838480662
Step 3919 | loss:1.419813871383667 lr:1.3714041949015504e-05 tokens_per_second_per_gpu:988.7945023351549
Step 3920 | loss:1.346575379371643 lr:1.3698021330534393e-05 tokens_per_second_per_gpu:810.9312801957333
Step 3921 | loss:1.2005637884140015 lr:1.3682007798114988e-05 tokens_per_second_per_gpu:1123.9539380010513
Step 3922 | loss:1.3138612508773804 lr:1.3666001357084112e-05 tokens_per_second_per_gpu:991.8718450822762
Step 3923 | loss:1.5448029041290283 lr:1.3650002012766318e-05 tokens_per_second_per_gpu:705.365408499623
Step 3924 | loss:1.418648600578308 lr:1.3634009770483712e-05 tokens_per_second_per_gpu:839.9119270171946
Step 3925 | loss:1.275199055671692 lr:1.361802463555612e-05 tokens_per_second_per_gpu:889.001264944353
Step 3926 | loss:1.242070198059082 lr:1.3602046613300952e-05 tokens_per_second_per_gpu:843.9867785846128
Step 3927 | loss:1.4109387397766113 lr:1.3586075709033266e-05 tokens_per_second_per_gpu:980.7357920505381
Step 3928 | loss:1.4688986539840698 lr:1.3570111928065754e-05 tokens_per_second_per_gpu:958.2248448806968
Step 3929 | loss:1.359116792678833 lr:1.3554155275708733e-05 tokens_per_second_per_gpu:740.5357306333414
Step 3930 | loss:1.36367666721344 lr:1.3538205757270142e-05 tokens_per_second_per_gpu:1165.3306773180593
Step 3931 | loss:1.3865511417388916 lr:1.3522263378055597e-05 tokens_per_second_per_gpu:763.755796092253
Step 3932 | loss:1.341166615486145 lr:1.3506328143368246e-05 tokens_per_second_per_gpu:950.4681695638483
Step 3933 | loss:1.406293272972107 lr:1.3490400058508962e-05 tokens_per_second_per_gpu:843.1666433938755
Step 3934 | loss:1.3131232261657715 lr:1.3474479128776146e-05 tokens_per_second_per_gpu:835.6890403931781
Step 3935 | loss:1.3559712171554565 lr:1.3458565359465915e-05 tokens_per_second_per_gpu:919.2745110823611
Step 3936 | loss:1.2423635721206665 lr:1.3442658755871896e-05 tokens_per_second_per_gpu:766.732467317851
Step 3937 | loss:1.1907157897949219 lr:1.3426759323285436e-05 tokens_per_second_per_gpu:946.440417571175
Step 3938 | loss:1.3011305332183838 lr:1.3410867066995431e-05 tokens_per_second_per_gpu:699.0619040575735
Step 3939 | loss:1.322037935256958 lr:1.3394981992288411e-05 tokens_per_second_per_gpu:800.3304423330163
Step 3940 | loss:1.1553912162780762 lr:1.3379104104448522e-05 tokens_per_second_per_gpu:1013.3688614444418
Step 3941 | loss:1.433034896850586 lr:1.3363233408757498e-05 tokens_per_second_per_gpu:807.7786381332166
Step 3942 | loss:1.2070060968399048 lr:1.334736991049471e-05 tokens_per_second_per_gpu:850.5962292385732
Step 3943 | loss:1.5149210691452026 lr:1.3331513614937107e-05 tokens_per_second_per_gpu:728.7340826633475
Step 3944 | loss:1.212334156036377 lr:1.3315664527359267e-05 tokens_per_second_per_gpu:1013.7181319471384
Step 3945 | loss:1.360854148864746 lr:1.329982265303335e-05 tokens_per_second_per_gpu:699.447293085625
Step 3946 | loss:1.3871442079544067 lr:1.328398799722911e-05 tokens_per_second_per_gpu:704.9165044145084
Step 3947 | loss:1.0954580307006836 lr:1.3268160565213963e-05 tokens_per_second_per_gpu:1315.029116486448
Step 3948 | loss:1.2863637208938599 lr:1.3252340362252811e-05 tokens_per_second_per_gpu:783.2693013566122
Step 3949 | loss:1.3495421409606934 lr:1.3236527393608259e-05 tokens_per_second_per_gpu:796.4800513496825
Step 3950 | loss:1.361899971961975 lr:1.3220721664540444e-05 tokens_per_second_per_gpu:847.8816390639429
Step 3951 | loss:1.4123916625976562 lr:1.3204923180307111e-05 tokens_per_second_per_gpu:902.5267138039674
Step 3952 | loss:1.3335847854614258 lr:1.31891319461636e-05 tokens_per_second_per_gpu:1052.9457917368152
Step 3953 | loss:1.331661343574524 lr:1.3173347967362825e-05 tokens_per_second_per_gpu:855.0668421278368
Step 3954 | loss:1.2470821142196655 lr:1.3157571249155305e-05 tokens_per_second_per_gpu:1154.5969358268567
Step 3955 | loss:1.265960931777954 lr:1.3141801796789133e-05 tokens_per_second_per_gpu:1070.0803714225028
Step 3956 | loss:1.3225133419036865 lr:1.312603961550998e-05 tokens_per_second_per_gpu:884.1427697676914
Step 3957 | loss:1.4206852912902832 lr:1.3110284710561113e-05 tokens_per_second_per_gpu:828.4439805873028
Step 3958 | loss:1.2695460319519043 lr:1.3094537087183362e-05 tokens_per_second_per_gpu:1017.4276465115659
Step 3959 | loss:1.362959861755371 lr:1.3078796750615153e-05 tokens_per_second_per_gpu:817.8594702465318
Step 3960 | loss:1.3866674900054932 lr:1.306306370609247e-05 tokens_per_second_per_gpu:678.6414497088991
Step 3961 | loss:1.3123323917388916 lr:1.3047337958848871e-05 tokens_per_second_per_gpu:1079.6715295829429
Step 3962 | loss:1.2857697010040283 lr:1.3031619514115532e-05 tokens_per_second_per_gpu:1123.5648246902604
Step 3963 | loss:1.5254085063934326 lr:1.3015908377121113e-05 tokens_per_second_per_gpu:682.7660362387263
Step 3964 | loss:1.4208180904388428 lr:1.300020455309194e-05 tokens_per_second_per_gpu:742.7083505965776
Step 3965 | loss:1.4365030527114868 lr:1.298450804725182e-05 tokens_per_second_per_gpu:1045.3783548794258
Step 3966 | loss:1.3905290365219116 lr:1.29688188648222e-05 tokens_per_second_per_gpu:802.5185183669391
Step 3967 | loss:1.2122350931167603 lr:1.2953137011022015e-05 tokens_per_second_per_gpu:1037.3507291731212
Step 3968 | loss:1.3793115615844727 lr:1.2937462491067841e-05 tokens_per_second_per_gpu:912.2666465373906
Step 3969 | loss:1.428910493850708 lr:1.2921795310173764e-05 tokens_per_second_per_gpu:723.6191111434871
Step 3970 | loss:1.3240742683410645 lr:1.2906135473551436e-05 tokens_per_second_per_gpu:666.4357553238999
Step 3971 | loss:1.451879620552063 lr:1.2890482986410076e-05 tokens_per_second_per_gpu:579.9237462603933
Step 3972 | loss:1.4329416751861572 lr:1.287483785395645e-05 tokens_per_second_per_gpu:669.1460383495877
Step 3973 | loss:1.3219720125198364 lr:1.2859200081394871e-05 tokens_per_second_per_gpu:972.9510120743353
Step 3974 | loss:1.3941211700439453 lr:1.2843569673927248e-05 tokens_per_second_per_gpu:822.4189715016795
Step 3975 | loss:1.2782701253890991 lr:1.2827946636752963e-05 tokens_per_second_per_gpu:755.9993394425927
Step 3976 | loss:1.2981868982315063 lr:1.281233097506903e-05 tokens_per_second_per_gpu:1137.6576294380159
Step 3977 | loss:1.5248501300811768 lr:1.2796722694069923e-05 tokens_per_second_per_gpu:717.548444220899
Step 3978 | loss:1.4427670240402222 lr:1.2781121798947755e-05 tokens_per_second_per_gpu:915.8241503839099
Step 3979 | loss:1.2583729028701782 lr:1.2765528294892081e-05 tokens_per_second_per_gpu:1080.4228047549793
Step 3980 | loss:1.257925271987915 lr:1.2749942187090096e-05 tokens_per_second_per_gpu:1093.141959668083
Step 3981 | loss:1.338570475578308 lr:1.2734363480726463e-05 tokens_per_second_per_gpu:716.9635640372301
Step 3982 | loss:1.3925056457519531 lr:1.2718792180983418e-05 tokens_per_second_per_gpu:749.1837476051076
Step 3983 | loss:1.253901720046997 lr:1.270322829304072e-05 tokens_per_second_per_gpu:1311.7483245471624
Step 3984 | loss:1.468824863433838 lr:1.2687671822075666e-05 tokens_per_second_per_gpu:904.8521416905184
Step 3985 | loss:1.264162540435791 lr:1.2672122773263086e-05 tokens_per_second_per_gpu:829.2550840944411
Step 3986 | loss:1.4413988590240479 lr:1.2656581151775343e-05 tokens_per_second_per_gpu:895.7405586527118
Step 3987 | loss:1.2632906436920166 lr:1.2641046962782314e-05 tokens_per_second_per_gpu:813.3453823769809
Step 3988 | loss:1.3176398277282715 lr:1.262552021145145e-05 tokens_per_second_per_gpu:814.6684066679576
Step 3989 | loss:1.326337218284607 lr:1.2610000902947648e-05 tokens_per_second_per_gpu:611.4036180678374
Step 3990 | loss:1.4292563199996948 lr:1.2594489042433424e-05 tokens_per_second_per_gpu:790.2237111534499
Step 3991 | loss:1.3995281457901 lr:1.257898463506872e-05 tokens_per_second_per_gpu:923.320289279232
Step 3992 | loss:1.6321786642074585 lr:1.2563487686011083e-05 tokens_per_second_per_gpu:560.5229627733464
Step 3993 | loss:1.2585718631744385 lr:1.2547998200415533e-05 tokens_per_second_per_gpu:915.5351233463107
Step 3994 | loss:1.4995810985565186 lr:1.2532516183434613e-05 tokens_per_second_per_gpu:855.2431879999062
Step 3995 | loss:1.2955697774887085 lr:1.2517041640218389e-05 tokens_per_second_per_gpu:738.5762575057973
Step 3996 | loss:1.2661404609680176 lr:1.2501574575914436e-05 tokens_per_second_per_gpu:928.6692912057824
Step 3997 | loss:1.2680729627609253 lr:1.2486114995667841e-05 tokens_per_second_per_gpu:1083.6027646614068
Step 3998 | loss:1.3355046510696411 lr:1.2470662904621208e-05 tokens_per_second_per_gpu:1097.963702912194
Step 3999 | loss:1.3517518043518066 lr:1.2455218307914633e-05 tokens_per_second_per_gpu:742.3638900393853
Step 4000 | loss:1.1675281524658203 lr:1.2439781210685761e-05 tokens_per_second_per_gpu:824.9259900917104
Step 4001 | loss:1.2890615463256836 lr:1.242435161806967e-05 tokens_per_second_per_gpu:1087.131334260176
Step 4002 | loss:1.3206348419189453 lr:1.240892953519903e-05 tokens_per_second_per_gpu:862.6060285971258
Step 4003 | loss:1.1138192415237427 lr:1.2393514967203916e-05 tokens_per_second_per_gpu:1265.3373401972256
Step 4004 | loss:1.3074817657470703 lr:1.2378107919211996e-05 tokens_per_second_per_gpu:932.339442921342
Step 4005 | loss:1.2513877153396606 lr:1.2362708396348378e-05 tokens_per_second_per_gpu:925.5062167499063
Step 4006 | loss:1.3051151037216187 lr:1.2347316403735683e-05 tokens_per_second_per_gpu:833.8592525171488
Step 4007 | loss:1.4377610683441162 lr:1.2331931946494027e-05 tokens_per_second_per_gpu:714.8542138000047
Step 4008 | loss:1.3239617347717285 lr:1.2316555029741023e-05 tokens_per_second_per_gpu:740.3575887141587
Step 4009 | loss:1.213789701461792 lr:1.2301185658591773e-05 tokens_per_second_per_gpu:1111.4031369440816
Step 4010 | loss:1.3467212915420532 lr:1.2285823838158866e-05 tokens_per_second_per_gpu:1164.1216957034333
Step 4011 | loss:1.3764007091522217 lr:1.2270469573552377e-05 tokens_per_second_per_gpu:1034.7005745370832
Step 4012 | loss:1.176357626914978 lr:1.2255122869879883e-05 tokens_per_second_per_gpu:1056.3971422496113
Step 4013 | loss:1.4464613199234009 lr:1.2239783732246423e-05 tokens_per_second_per_gpu:1152.5795512838074
Step 4014 | loss:1.3483245372772217 lr:1.2224452165754542e-05 tokens_per_second_per_gpu:899.6541102013201
Step 4015 | loss:1.4016903638839722 lr:1.2209128175504249e-05 tokens_per_second_per_gpu:696.5838897144672
Step 4016 | loss:1.2440725564956665 lr:1.219381176659304e-05 tokens_per_second_per_gpu:1028.3961350802817
Step 4017 | loss:1.2939002513885498 lr:1.2178502944115894e-05 tokens_per_second_per_gpu:1137.0119989586826
Step 4018 | loss:1.2928608655929565 lr:1.2163201713165241e-05 tokens_per_second_per_gpu:1090.7585653223332
Step 4019 | loss:1.3792760372161865 lr:1.2147908078831047e-05 tokens_per_second_per_gpu:1012.4822248627185
Step 4020 | loss:1.2133805751800537 lr:1.2132622046200661e-05 tokens_per_second_per_gpu:966.5611434059234
Step 4021 | loss:1.4055567979812622 lr:1.2117343620358986e-05 tokens_per_second_per_gpu:854.8156237474517
Step 4022 | loss:1.3164854049682617 lr:1.2102072806388353e-05 tokens_per_second_per_gpu:911.8122541320658
Step 4023 | loss:1.3238199949264526 lr:1.2086809609368562e-05 tokens_per_second_per_gpu:688.7999449586207
Step 4024 | loss:1.3010060787200928 lr:1.2071554034376889e-05 tokens_per_second_per_gpu:867.913502391455
Step 4025 | loss:1.3609310388565063 lr:1.2056306086488071e-05 tokens_per_second_per_gpu:1298.9770891842375
Step 4026 | loss:1.3868016004562378 lr:1.204106577077431e-05 tokens_per_second_per_gpu:1032.9324434749756
Step 4027 | loss:1.306784749031067 lr:1.2025833092305266e-05 tokens_per_second_per_gpu:713.331408115696
Step 4028 | loss:1.1415777206420898 lr:1.2010608056148056e-05 tokens_per_second_per_gpu:1039.9770791069816
Step 4029 | loss:1.420053243637085 lr:1.1995390667367266e-05 tokens_per_second_per_gpu:873.229730970935
Step 4030 | loss:1.3035500049591064 lr:1.1980180931024913e-05 tokens_per_second_per_gpu:1131.777700331157
Step 4031 | loss:1.2730408906936646 lr:1.1964978852180525e-05 tokens_per_second_per_gpu:1044.8386552827092
Step 4032 | loss:1.421372890472412 lr:1.1949784435890996e-05 tokens_per_second_per_gpu:750.120318620593
Step 4033 | loss:1.4927902221679688 lr:1.1934597687210765e-05 tokens_per_second_per_gpu:1050.6582786108647
Step 4034 | loss:1.2398422956466675 lr:1.1919418611191623e-05 tokens_per_second_per_gpu:889.1696781820824
Step 4035 | loss:1.2880247831344604 lr:1.1904247212882906e-05 tokens_per_second_per_gpu:1060.3893354236698
Step 4036 | loss:1.429685354232788 lr:1.1889083497331329e-05 tokens_per_second_per_gpu:753.9299566966392
Step 4037 | loss:1.2730469703674316 lr:1.1873927469581077e-05 tokens_per_second_per_gpu:823.6247352515059
Step 4038 | loss:1.3361343145370483 lr:1.1858779134673773e-05 tokens_per_second_per_gpu:860.1539623007546
Step 4039 | loss:1.446541666984558 lr:1.1843638497648477e-05 tokens_per_second_per_gpu:844.9663309314633
Step 4040 | loss:1.378641128540039 lr:1.1828505563541698e-05 tokens_per_second_per_gpu:815.5988631365269
Step 4041 | loss:1.2847471237182617 lr:1.1813380337387371e-05 tokens_per_second_per_gpu:1081.8556790055031
Step 4042 | loss:1.2741540670394897 lr:1.1798262824216866e-05 tokens_per_second_per_gpu:936.9679183619694
Step 4043 | loss:1.2982844114303589 lr:1.178315302905903e-05 tokens_per_second_per_gpu:900.738224681642
Step 4044 | loss:1.3502867221832275 lr:1.1768050956940056e-05 tokens_per_second_per_gpu:931.979179849214
Step 4045 | loss:1.4891449213027954 lr:1.175295661288367e-05 tokens_per_second_per_gpu:783.2463698052528
Step 4046 | loss:1.4355192184448242 lr:1.1737870001910926e-05 tokens_per_second_per_gpu:776.6772437152824
Step 4047 | loss:1.3699512481689453 lr:1.1722791129040404e-05 tokens_per_second_per_gpu:708.22534510099
Step 4048 | loss:1.3467777967453003 lr:1.1707719999288012e-05 tokens_per_second_per_gpu:694.5739858337005
Step 4049 | loss:1.3365046977996826 lr:1.169265661766717e-05 tokens_per_second_per_gpu:1128.2383266289507
Step 4050 | loss:1.435866117477417 lr:1.1677600989188674e-05 tokens_per_second_per_gpu:1107.9991407675802
Step 4051 | loss:1.4119104146957397 lr:1.166255311886074e-05 tokens_per_second_per_gpu:721.2742893922349
Step 4052 | loss:1.2060538530349731 lr:1.1647513011689025e-05 tokens_per_second_per_gpu:965.5752678765576
Step 4053 | loss:1.4002376794815063 lr:1.1632480672676581e-05 tokens_per_second_per_gpu:872.7375085658729
Step 4054 | loss:1.326725721359253 lr:1.1617456106823877e-05 tokens_per_second_per_gpu:1101.1439007334625
Step 4055 | loss:1.348625659942627 lr:1.1602439319128847e-05 tokens_per_second_per_gpu:759.4354492325783
Step 4056 | loss:1.3992881774902344 lr:1.158743031458674e-05 tokens_per_second_per_gpu:868.8204133094665
Step 4057 | loss:1.3361790180206299 lr:1.1572429098190326e-05 tokens_per_second_per_gpu:1156.3364280040828
Step 4058 | loss:1.3615459203720093 lr:1.1557435674929679e-05 tokens_per_second_per_gpu:726.5289404034527
Step 4059 | loss:1.1950961351394653 lr:1.1542450049792381e-05 tokens_per_second_per_gpu:767.2606102464324
Step 4060 | loss:1.4343746900558472 lr:1.1527472227763327e-05 tokens_per_second_per_gpu:515.8756802162399
Step 4061 | loss:1.3409162759780884 lr:1.1512502213824888e-05 tokens_per_second_per_gpu:842.2470430301952
Step 4062 | loss:1.3487164974212646 lr:1.1497540012956806e-05 tokens_per_second_per_gpu:870.7210518594927
Step 4063 | loss:1.4137544631958008 lr:1.1482585630136222e-05 tokens_per_second_per_gpu:807.7963413268186
Step 4064 | loss:1.4292614459991455 lr:1.1467639070337687e-05 tokens_per_second_per_gpu:806.8817124794633
Step 4065 | loss:1.3685733079910278 lr:1.1452700338533143e-05 tokens_per_second_per_gpu:753.4264447482046
Step 4066 | loss:1.3128293752670288 lr:1.1437769439691927e-05 tokens_per_second_per_gpu:913.1058914474213
Step 4067 | loss:1.1871720552444458 lr:1.1422846378780778e-05 tokens_per_second_per_gpu:1005.8437438732983
Step 4068 | loss:1.2521580457687378 lr:1.1407931160763822e-05 tokens_per_second_per_gpu:1138.8553722833349
Step 4069 | loss:1.3267555236816406 lr:1.1393023790602578e-05 tokens_per_second_per_gpu:813.8171220390518
Step 4070 | loss:1.3490582704544067 lr:1.1378124273255949e-05 tokens_per_second_per_gpu:1021.2021355687435
Step 4071 | loss:1.1630730628967285 lr:1.1363232613680233e-05 tokens_per_second_per_gpu:808.5400916635485
Step 4072 | loss:1.4446611404418945 lr:1.1348348816829103e-05 tokens_per_second_per_gpu:975.3442418772169
Step 4073 | loss:1.3187919855117798 lr:1.1333472887653645e-05 tokens_per_second_per_gpu:1086.6091937719752
Step 4074 | loss:1.320263385772705 lr:1.1318604831102298e-05 tokens_per_second_per_gpu:1100.538743848857
Step 4075 | loss:1.3631765842437744 lr:1.130374465212089e-05 tokens_per_second_per_gpu:696.5378824310789
Step 4076 | loss:1.501695990562439 lr:1.1288892355652632e-05 tokens_per_second_per_gpu:632.0332245640321
Step 4077 | loss:1.2684099674224854 lr:1.127404794663811e-05 tokens_per_second_per_gpu:894.3359550541771
Step 4078 | loss:1.314850926399231 lr:1.1259211430015287e-05 tokens_per_second_per_gpu:1223.725348999036
Step 4079 | loss:1.2860746383666992 lr:1.1244382810719506e-05 tokens_per_second_per_gpu:780.6028810606722
Step 4080 | loss:1.4479103088378906 lr:1.1229562093683476e-05 tokens_per_second_per_gpu:836.0021738901495
Step 4081 | loss:1.3323887586593628 lr:1.1214749283837277e-05 tokens_per_second_per_gpu:940.4755838220419
Step 4082 | loss:1.3136932849884033 lr:1.1199944386108364e-05 tokens_per_second_per_gpu:755.34520314761
Step 4083 | loss:1.4135053157806396 lr:1.1185147405421559e-05 tokens_per_second_per_gpu:917.3167535176332
Step 4084 | loss:1.5212403535842896 lr:1.1170358346699041e-05 tokens_per_second_per_gpu:937.507858991842
Step 4085 | loss:1.432148814201355 lr:1.1155577214860359e-05 tokens_per_second_per_gpu:868.0729356797497
Step 4086 | loss:1.3000493049621582 lr:1.1140804014822461e-05 tokens_per_second_per_gpu:859.7437018247625
Step 4087 | loss:1.2958064079284668 lr:1.1126038751499571e-05 tokens_per_second_per_gpu:1029.4256540906736
Step 4088 | loss:1.3657846450805664 lr:1.1111281429803377e-05 tokens_per_second_per_gpu:912.6233769056952
Step 4089 | loss:1.3455206155776978 lr:1.1096532054642824e-05 tokens_per_second_per_gpu:847.9744752836472
Step 4090 | loss:1.497389793395996 lr:1.108179063092431e-05 tokens_per_second_per_gpu:864.5490904504845
Step 4091 | loss:1.4086546897888184 lr:1.10670571635515e-05 tokens_per_second_per_gpu:814.3874143772675
Step 4092 | loss:1.2311848402023315 lr:1.1052331657425477e-05 tokens_per_second_per_gpu:925.4727273061322
Step 4093 | loss:1.3721063137054443 lr:1.1037614117444648e-05 tokens_per_second_per_gpu:614.2222471052912
Step 4094 | loss:1.514156699180603 lr:1.1022904548504774e-05 tokens_per_second_per_gpu:735.0266780290544
Step 4095 | loss:1.1844338178634644 lr:1.1008202955498958e-05 tokens_per_second_per_gpu:1156.8606235857205
Step 4096 | loss:1.3787174224853516 lr:1.0993509343317663e-05 tokens_per_second_per_gpu:728.0627221810684
Step 4097 | loss:1.2599836587905884 lr:1.097882371684868e-05 tokens_per_second_per_gpu:979.4787918742264
Step 4098 | loss:1.2997103929519653 lr:1.0964146080977181e-05 tokens_per_second_per_gpu:897.5366049657821
Step 4099 | loss:1.3704785108566284 lr:1.0949476440585612e-05 tokens_per_second_per_gpu:756.5749313377681
Step 4100 | loss:1.4045237302780151 lr:1.0934814800553846e-05 tokens_per_second_per_gpu:711.1576026541935
Step 4101 | loss:1.432620882987976 lr:1.0920161165759004e-05 tokens_per_second_per_gpu:799.2298667356523
Step 4102 | loss:1.3962481021881104 lr:1.0905515541075631e-05 tokens_per_second_per_gpu:900.2826218081506
Step 4103 | loss:1.3184759616851807 lr:1.0890877931375526e-05 tokens_per_second_per_gpu:870.2040050498941
Step 4104 | loss:1.2427247762680054 lr:1.0876248341527891e-05 tokens_per_second_per_gpu:707.8933246842213
Step 4105 | loss:1.3354740142822266 lr:1.086162677639922e-05 tokens_per_second_per_gpu:734.0037638123342
Step 4106 | loss:1.31027090549469 lr:1.0847013240853344e-05 tokens_per_second_per_gpu:822.5551291722034
Step 4107 | loss:1.4030792713165283 lr:1.0832407739751436e-05 tokens_per_second_per_gpu:1155.1389720815741
Step 4108 | loss:1.2372004985809326 lr:1.0817810277951979e-05 tokens_per_second_per_gpu:830.9082100065863
Step 4109 | loss:1.2742867469787598 lr:1.0803220860310783e-05 tokens_per_second_per_gpu:904.0104368693584
Step 4110 | loss:1.411840796470642 lr:1.0788639491681025e-05 tokens_per_second_per_gpu:919.8928337120976
Step 4111 | loss:1.3414011001586914 lr:1.077406617691312e-05 tokens_per_second_per_gpu:731.353031897654
Step 4112 | loss:1.1588990688323975 lr:1.0759500920854899e-05 tokens_per_second_per_gpu:1133.4136227840916
Step 4113 | loss:1.2822868824005127 lr:1.0744943728351424e-05 tokens_per_second_per_gpu:993.0549160929323
Step 4114 | loss:1.0624576807022095 lr:1.0730394604245156e-05 tokens_per_second_per_gpu:1333.0544485434525
Step 4115 | loss:1.3071110248565674 lr:1.0715853553375791e-05 tokens_per_second_per_gpu:906.2372616561278
Step 4116 | loss:1.3048304319381714 lr:1.070132058058042e-05 tokens_per_second_per_gpu:703.6036836015338
Step 4117 | loss:1.2750701904296875 lr:1.0686795690693386e-05 tokens_per_second_per_gpu:982.1443717358366
Step 4118 | loss:1.3209588527679443 lr:1.067227888854637e-05 tokens_per_second_per_gpu:967.1578113388088
Step 4119 | loss:1.1236830949783325 lr:1.0657770178968361e-05 tokens_per_second_per_gpu:722.6454853207156
Step 4120 | loss:1.3120999336242676 lr:1.0643269566785651e-05 tokens_per_second_per_gpu:988.0512665758602
Step 4121 | loss:1.3423821926116943 lr:1.0628777056821841e-05 tokens_per_second_per_gpu:1028.811663520865
Step 4122 | loss:1.4274121522903442 lr:1.0614292653897833e-05 tokens_per_second_per_gpu:813.9943230135394
Step 4123 | loss:1.4449752569198608 lr:1.059981636283183e-05 tokens_per_second_per_gpu:899.5126220577106
Step 4124 | loss:1.4858304262161255 lr:1.0585348188439372e-05 tokens_per_second_per_gpu:1021.0159861342587
Step 4125 | loss:1.2965606451034546 lr:1.0570888135533221e-05 tokens_per_second_per_gpu:997.3779406645089
Step 4126 | loss:1.2912683486938477 lr:1.0556436208923537e-05 tokens_per_second_per_gpu:1044.9419955669466
Step 4127 | loss:1.2529029846191406 lr:1.0541992413417674e-05 tokens_per_second_per_gpu:878.4851165544554
Step 4128 | loss:1.448736310005188 lr:1.0527556753820372e-05 tokens_per_second_per_gpu:860.3658758173218
Step 4129 | loss:1.4390037059783936 lr:1.051312923493361e-05 tokens_per_second_per_gpu:757.9075491346825
Step 4130 | loss:1.5620274543762207 lr:1.0498709861556675e-05 tokens_per_second_per_gpu:773.9216780748885
Step 4131 | loss:1.2764641046524048 lr:1.0484298638486143e-05 tokens_per_second_per_gpu:980.6088838319353
Step 4132 | loss:1.3355867862701416 lr:1.0469895570515878e-05 tokens_per_second_per_gpu:1117.8085803521635
Step 4133 | loss:1.439608097076416 lr:1.0455500662437036e-05 tokens_per_second_per_gpu:896.9594873030005
Step 4134 | loss:1.387883186340332 lr:1.0441113919038054e-05 tokens_per_second_per_gpu:829.5886949190362
Step 4135 | loss:1.2668023109436035 lr:1.042673534510465e-05 tokens_per_second_per_gpu:1162.651025212973
Step 4136 | loss:1.4050476551055908 lr:1.0412364945419836e-05 tokens_per_second_per_gpu:918.8150798704114
Step 4137 | loss:1.2821884155273438 lr:1.039800272476389e-05 tokens_per_second_per_gpu:984.9535607318239
Step 4138 | loss:1.2916569709777832 lr:1.0383648687914382e-05 tokens_per_second_per_gpu:847.676293375906
Step 4139 | loss:1.3740259408950806 lr:1.0369302839646154e-05 tokens_per_second_per_gpu:1047.124293135574
Step 4140 | loss:1.2498645782470703 lr:1.0354965184731312e-05 tokens_per_second_per_gpu:892.0457913821349
Step 4141 | loss:1.2640024423599243 lr:1.034063572793928e-05 tokens_per_second_per_gpu:969.2972749615639
Step 4142 | loss:1.405890703201294 lr:1.032631447403668e-05 tokens_per_second_per_gpu:966.9372075673101
Step 4143 | loss:1.3815613985061646 lr:1.0312001427787497e-05 tokens_per_second_per_gpu:726.749577396764
Step 4144 | loss:1.4989309310913086 lr:1.0297696593952893e-05 tokens_per_second_per_gpu:608.3522099847349
Step 4145 | loss:1.5534417629241943 lr:1.0283399977291383e-05 tokens_per_second_per_gpu:645.6221610687217
Step 4146 | loss:1.1998330354690552 lr:1.0269111582558668e-05 tokens_per_second_per_gpu:921.0782393616792
Step 4147 | loss:1.389521837234497 lr:1.025483141450779e-05 tokens_per_second_per_gpu:663.6280183128576
Step 4148 | loss:1.2869497537612915 lr:1.0240559477889004e-05 tokens_per_second_per_gpu:964.2528971992898
Step 4149 | loss:1.4111055135726929 lr:1.0226295777449845e-05 tokens_per_second_per_gpu:946.1834999386947
Step 4150 | loss:1.1848595142364502 lr:1.0212040317935102e-05 tokens_per_second_per_gpu:1000.1663552889854
Step 4151 | loss:1.4148826599121094 lr:1.0197793104086824e-05 tokens_per_second_per_gpu:954.6937911313252
Step 4152 | loss:1.2875421047210693 lr:1.0183554140644316e-05 tokens_per_second_per_gpu:773.2334140194965
Step 4153 | loss:1.293969750404358 lr:1.0169323432344167e-05 tokens_per_second_per_gpu:881.791988032177
Step 4154 | loss:1.4783458709716797 lr:1.0155100983920155e-05 tokens_per_second_per_gpu:882.8764967287708
Step 4155 | loss:1.2756006717681885 lr:1.0140886800103392e-05 tokens_per_second_per_gpu:880.1366019543476
Step 4156 | loss:1.2577488422393799 lr:1.0126680885622148e-05 tokens_per_second_per_gpu:746.1211607381878
Step 4157 | loss:1.2158093452453613 lr:1.011248324520205e-05 tokens_per_second_per_gpu:1205.1618046959466
Step 4158 | loss:1.3267018795013428 lr:1.009829388356586e-05 tokens_per_second_per_gpu:881.7427174956131
Step 4159 | loss:1.3866488933563232 lr:1.0084112805433685e-05 tokens_per_second_per_gpu:759.3702007784833
Step 4160 | loss:1.1762564182281494 lr:1.006994001552281e-05 tokens_per_second_per_gpu:1295.6652809367665
Step 4161 | loss:1.350836992263794 lr:1.0055775518547793e-05 tokens_per_second_per_gpu:783.3041693881299
Step 4162 | loss:1.3144738674163818 lr:1.0041619319220427e-05 tokens_per_second_per_gpu:876.2570843542161
Step 4163 | loss:1.2173027992248535 lr:1.002747142224974e-05 tokens_per_second_per_gpu:1137.1202770469467
Step 4164 | loss:1.3969974517822266 lr:1.0013331832342007e-05 tokens_per_second_per_gpu:885.0080112808255
Step 4165 | loss:1.0730974674224854 lr:9.999200554200732e-06 tokens_per_second_per_gpu:1314.4721764597518
Step 4166 | loss:1.2226207256317139 lr:9.985077592526646e-06 tokens_per_second_per_gpu:1013.6257310055885
Step 4167 | loss:1.4182639122009277 lr:9.970962952017756e-06 tokens_per_second_per_gpu:811.4727771927652
Step 4168 | loss:1.3091320991516113 lr:9.956856637369232e-06 tokens_per_second_per_gpu:1066.5895031266114
Step 4169 | loss:1.5066890716552734 lr:9.942758653273552e-06 tokens_per_second_per_gpu:977.5554225114187
Step 4170 | loss:1.3690098524093628 lr:9.928669004420335e-06 tokens_per_second_per_gpu:770.8100324927735
Step 4171 | loss:1.319320559501648 lr:9.914587695496518e-06 tokens_per_second_per_gpu:736.897090757182
Step 4172 | loss:1.3622984886169434 lr:9.9005147311862e-06 tokens_per_second_per_gpu:888.475607403254
Step 4173 | loss:1.3519176244735718 lr:9.886450116170729e-06 tokens_per_second_per_gpu:1126.493456569009
Step 4174 | loss:1.486987829208374 lr:9.872393855128676e-06 tokens_per_second_per_gpu:835.7926902241397
Step 4175 | loss:1.5131937265396118 lr:9.858345952735823e-06 tokens_per_second_per_gpu:779.048671244223
Step 4176 | loss:1.3729321956634521 lr:9.844306413665177e-06 tokens_per_second_per_gpu:757.8020504759103
Step 4177 | loss:1.228795051574707 lr:9.83027524258697e-06 tokens_per_second_per_gpu:1048.9821336195755
Step 4178 | loss:1.256548285484314 lr:9.816252444168624e-06 tokens_per_second_per_gpu:916.9239192999883
Step 4179 | loss:1.3117897510528564 lr:9.802238023074837e-06 tokens_per_second_per_gpu:760.8297237628155
Step 4180 | loss:1.2884716987609863 lr:9.78823198396743e-06 tokens_per_second_per_gpu:739.9862790324141
Step 4181 | loss:1.3063615560531616 lr:9.77423433150553e-06 tokens_per_second_per_gpu:846.7341482377822
Step 4182 | loss:1.2838423252105713 lr:9.760245070345378e-06 tokens_per_second_per_gpu:1149.8558272967466
Step 4183 | loss:1.3452802896499634 lr:9.746264205140523e-06 tokens_per_second_per_gpu:892.2091203240221
Step 4184 | loss:1.2889621257781982 lr:9.732291740541645e-06 tokens_per_second_per_gpu:904.0484905399882
Step 4185 | loss:1.3413128852844238 lr:9.718327681196665e-06 tokens_per_second_per_gpu:731.3542736383047
Step 4186 | loss:1.3507699966430664 lr:9.704372031750703e-06 tokens_per_second_per_gpu:1006.0836801979896
Step 4187 | loss:1.2181320190429688 lr:9.690424796846074e-06 tokens_per_second_per_gpu:1433.3807152363754
Step 4188 | loss:1.2668039798736572 lr:9.676485981122298e-06 tokens_per_second_per_gpu:974.1255428878243
Step 4189 | loss:1.436967134475708 lr:9.662555589216096e-06 tokens_per_second_per_gpu:700.3466652696527
Step 4190 | loss:1.2673612833023071 lr:9.648633625761387e-06 tokens_per_second_per_gpu:1024.9897181724525
Step 4191 | loss:1.2643511295318604 lr:9.634720095389285e-06 tokens_per_second_per_gpu:1210.9267567738193
Step 4192 | loss:1.509564995765686 lr:9.620815002728097e-06 tokens_per_second_per_gpu:791.2703517850426
Step 4193 | loss:1.3492716550827026 lr:9.606918352403327e-06 tokens_per_second_per_gpu:800.6729107681361
Step 4194 | loss:1.1739519834518433 lr:9.593030149037668e-06 tokens_per_second_per_gpu:1078.5384203109531
Step 4195 | loss:1.3577438592910767 lr:9.579150397251e-06 tokens_per_second_per_gpu:733.5345279979199
Step 4196 | loss:1.3479735851287842 lr:9.5652791016604e-06 tokens_per_second_per_gpu:1053.0473654328025
Step 4197 | loss:1.225921869277954 lr:9.551416266880117e-06 tokens_per_second_per_gpu:772.5965983802624
Step 4198 | loss:1.28986394405365 lr:9.537561897521615e-06 tokens_per_second_per_gpu:792.275046875976
Step 4199 | loss:1.3779751062393188 lr:9.523715998193511e-06 tokens_per_second_per_gpu:1119.2816090660208
Step 4200 | loss:1.2167913913726807 lr:9.509878573501619e-06 tokens_per_second_per_gpu:863.2237048626524
Step 4201 | loss:1.2474243640899658 lr:9.496049628048932e-06 tokens_per_second_per_gpu:978.0950469559227
Step 4202 | loss:1.358822226524353 lr:9.482229166435623e-06 tokens_per_second_per_gpu:828.9300536626773
Step 4203 | loss:1.4605846405029297 lr:9.468417193259034e-06 tokens_per_second_per_gpu:774.8497245574439
Step 4204 | loss:1.283151388168335 lr:9.4546137131137e-06 tokens_per_second_per_gpu:1125.6365249702262
Step 4205 | loss:1.234148621559143 lr:9.440818730591315e-06 tokens_per_second_per_gpu:1150.8089818274443
Step 4206 | loss:1.312801718711853 lr:9.427032250280757e-06 tokens_per_second_per_gpu:847.4876185296623
Step 4207 | loss:1.2261416912078857 lr:9.413254276768074e-06 tokens_per_second_per_gpu:989.4875932957818
Step 4208 | loss:1.4079128503799438 lr:9.399484814636475e-06 tokens_per_second_per_gpu:999.5272148721859
Step 4209 | loss:1.0855432748794556 lr:9.385723868466337e-06 tokens_per_second_per_gpu:1338.0095781504356
Step 4210 | loss:1.258955955505371 lr:9.371971442835245e-06 tokens_per_second_per_gpu:749.5565732513732
Step 4211 | loss:1.429654836654663 lr:9.358227542317876e-06 tokens_per_second_per_gpu:870.9346518356152
Step 4212 | loss:1.4607622623443604 lr:9.344492171486153e-06 tokens_per_second_per_gpu:690.7515951054498
Step 4213 | loss:1.2858126163482666 lr:9.330765334909072e-06 tokens_per_second_per_gpu:903.3120130566991
Step 4214 | loss:1.1702042818069458 lr:9.317047037152879e-06 tokens_per_second_per_gpu:903.1138574576672
Step 4215 | loss:1.1853032112121582 lr:9.303337282780922e-06 tokens_per_second_per_gpu:1272.9079902936264
Step 4216 | loss:1.267581820487976 lr:9.289636076353729e-06 tokens_per_second_per_gpu:786.6556872379339
Step 4217 | loss:1.2289867401123047 lr:9.275943422428974e-06 tokens_per_second_per_gpu:1007.1947821916117
Step 4218 | loss:1.3469562530517578 lr:9.2622593255615e-06 tokens_per_second_per_gpu:749.8718071570959
Step 4219 | loss:1.3284006118774414 lr:9.248583790303283e-06 tokens_per_second_per_gpu:883.6698513670262
Step 4220 | loss:1.3213834762573242 lr:9.234916821203474e-06 tokens_per_second_per_gpu:775.0147636697925
Step 4221 | loss:1.4945316314697266 lr:9.221258422808348e-06 tokens_per_second_per_gpu:793.7844073021897
Step 4222 | loss:1.4861537218093872 lr:9.20760859966138e-06 tokens_per_second_per_gpu:749.9071610513248
Step 4223 | loss:1.412964105606079 lr:9.193967356303112e-06 tokens_per_second_per_gpu:1055.8430521536905
Step 4224 | loss:1.3786273002624512 lr:9.180334697271316e-06 tokens_per_second_per_gpu:950.413207456572
Step 4225 | loss:1.3151859045028687 lr:9.166710627100835e-06 tokens_per_second_per_gpu:973.806235040755
Step 4226 | loss:1.2153213024139404 lr:9.153095150323713e-06 tokens_per_second_per_gpu:1113.448711586522
Step 4227 | loss:1.2622078657150269 lr:9.139488271469106e-06 tokens_per_second_per_gpu:895.3068364443226
Step 4228 | loss:1.1792575120925903 lr:9.125889995063314e-06 tokens_per_second_per_gpu:1039.676423732543
Step 4229 | loss:1.34795081615448 lr:9.11230032562978e-06 tokens_per_second_per_gpu:960.9587015501893
Step 4230 | loss:1.2257325649261475 lr:9.098719267689076e-06 tokens_per_second_per_gpu:736.1862735726777
Step 4231 | loss:1.3515757322311401 lr:9.08514682575892e-06 tokens_per_second_per_gpu:726.607027605618
Step 4232 | loss:1.3260060548782349 lr:9.071583004354154e-06 tokens_per_second_per_gpu:837.1682895976111
Step 4233 | loss:1.2534722089767456 lr:9.058027807986749e-06 tokens_per_second_per_gpu:984.8780906383664
Step 4234 | loss:1.321331262588501 lr:9.044481241165844e-06 tokens_per_second_per_gpu:897.3603123757448
Step 4235 | loss:1.5524530410766602 lr:9.030943308397638e-06 tokens_per_second_per_gpu:878.819749882552
Step 4236 | loss:1.171140193939209 lr:9.017414014185543e-06 tokens_per_second_per_gpu:1011.0268813473417
Step 4237 | loss:1.335838794708252 lr:9.003893363030001e-06 tokens_per_second_per_gpu:911.1501869943007
Step 4238 | loss:1.478089451789856 lr:8.99038135942868e-06 tokens_per_second_per_gpu:929.8618991260313
Step 4239 | loss:1.3514058589935303 lr:8.976878007876278e-06 tokens_per_second_per_gpu:895.3854871232328
Step 4240 | loss:1.5095255374908447 lr:8.963383312864687e-06 tokens_per_second_per_gpu:811.8586149794672
Step 4241 | loss:1.3947594165802002 lr:8.949897278882883e-06 tokens_per_second_per_gpu:902.9255595465801
Step 4242 | loss:1.4215291738510132 lr:8.93641991041697e-06 tokens_per_second_per_gpu:793.1163637430558
Step 4243 | loss:1.38786780834198 lr:8.922951211950168e-06 tokens_per_second_per_gpu:754.3427393318732
Step 4244 | loss:1.3803595304489136 lr:8.90949118796281e-06 tokens_per_second_per_gpu:686.083010032702
Step 4245 | loss:1.2183704376220703 lr:8.896039842932353e-06 tokens_per_second_per_gpu:1129.8426866739653
Step 4246 | loss:1.4276373386383057 lr:8.882597181333354e-06 tokens_per_second_per_gpu:1030.1557533391351
Step 4247 | loss:1.2402310371398926 lr:8.869163207637491e-06 tokens_per_second_per_gpu:959.531061420641
Step 4248 | loss:1.3914146423339844 lr:8.855737926313549e-06 tokens_per_second_per_gpu:931.2336209841791
Step 4249 | loss:1.3734062910079956 lr:8.842321341827426e-06 tokens_per_second_per_gpu:809.4551348948154
Step 4250 | loss:1.1425540447235107 lr:8.828913458642115e-06 tokens_per_second_per_gpu:839.5924660138758
Step 4251 | loss:1.2783904075622559 lr:8.815514281217716e-06 tokens_per_second_per_gpu:719.533165283197
Step 4252 | loss:1.3719582557678223 lr:8.802123814011457e-06 tokens_per_second_per_gpu:719.674544234803
Step 4253 | loss:1.1253725290298462 lr:8.788742061477646e-06 tokens_per_second_per_gpu:818.2501081403386
Step 4254 | loss:1.1677252054214478 lr:8.775369028067695e-06 tokens_per_second_per_gpu:1181.1258212313514
Step 4255 | loss:1.3306092023849487 lr:8.762004718230115e-06 tokens_per_second_per_gpu:1025.120676663999
Step 4256 | loss:1.2155662775039673 lr:8.748649136410518e-06 tokens_per_second_per_gpu:1057.5354954079307
Step 4257 | loss:1.319038987159729 lr:8.735302287051613e-06 tokens_per_second_per_gpu:883.401316555935
Step 4258 | loss:1.288398265838623 lr:8.721964174593203e-06 tokens_per_second_per_gpu:874.9319512268295
Step 4259 | loss:1.38979971408844 lr:8.708634803472185e-06 tokens_per_second_per_gpu:787.5252131021914
Step 4260 | loss:1.2673183679580688 lr:8.695314178122551e-06 tokens_per_second_per_gpu:1016.4276993373612
Step 4261 | loss:1.4570488929748535 lr:8.682002302975379e-06 tokens_per_second_per_gpu:1006.5846571679944
Step 4262 | loss:1.3722859621047974 lr:8.668699182458838e-06 tokens_per_second_per_gpu:1019.336967827345
Step 4263 | loss:1.2628793716430664 lr:8.655404820998188e-06 tokens_per_second_per_gpu:1036.9422167550497
Step 4264 | loss:1.317782998085022 lr:8.642119223015759e-06 tokens_per_second_per_gpu:775.651565764627
Step 4265 | loss:1.2664058208465576 lr:8.628842392931006e-06 tokens_per_second_per_gpu:814.1812601429948
Step 4266 | loss:1.1695117950439453 lr:8.615574335160407e-06 tokens_per_second_per_gpu:948.7546645304404
Step 4267 | loss:1.2254139184951782 lr:8.602315054117596e-06 tokens_per_second_per_gpu:852.9771109167992
Step 4268 | loss:1.371242642402649 lr:8.5890645542132e-06 tokens_per_second_per_gpu:1035.2850428702754
Step 4269 | loss:1.4294730424880981 lr:8.57582283985502e-06 tokens_per_second_per_gpu:893.6621341117902
Step 4270 | loss:1.2793867588043213 lr:8.562589915447839e-06 tokens_per_second_per_gpu:815.7984359544736
Step 4271 | loss:1.2666889429092407 lr:8.5493657853936e-06 tokens_per_second_per_gpu:1050.153400984504
Step 4272 | loss:1.3464975357055664 lr:8.536150454091271e-06 tokens_per_second_per_gpu:916.696603517947
Step 4273 | loss:1.4530037641525269 lr:8.522943925936906e-06 tokens_per_second_per_gpu:745.2042330409962
Step 4274 | loss:1.2405827045440674 lr:8.50974620532363e-06 tokens_per_second_per_gpu:1136.9186232087056
Step 4275 | loss:1.264128565788269 lr:8.496557296641646e-06 tokens_per_second_per_gpu:1067.5743087067203
Step 4276 | loss:1.3352912664413452 lr:8.483377204278197e-06 tokens_per_second_per_gpu:758.2333820358144
Step 4277 | loss:1.3097434043884277 lr:8.470205932617654e-06 tokens_per_second_per_gpu:753.1181772999936
Step 4278 | loss:1.297126054763794 lr:8.457043486041374e-06 tokens_per_second_per_gpu:877.2319121277751
Step 4279 | loss:1.3331671953201294 lr:8.443889868927855e-06 tokens_per_second_per_gpu:917.7084930610418
Step 4280 | loss:1.470304012298584 lr:8.430745085652583e-06 tokens_per_second_per_gpu:815.1550605795085
Step 4281 | loss:1.4307785034179688 lr:8.41760914058819e-06 tokens_per_second_per_gpu:791.1218555481834
Step 4282 | loss:1.3347384929656982 lr:8.404482038104273e-06 tokens_per_second_per_gpu:907.7460098400472
Step 4283 | loss:1.3847410678863525 lr:8.391363782567578e-06 tokens_per_second_per_gpu:812.6167937803078
Step 4284 | loss:1.4265824556350708 lr:8.37825437834185e-06 tokens_per_second_per_gpu:794.0464862969109
Step 4285 | loss:1.3920847177505493 lr:8.365153829787904e-06 tokens_per_second_per_gpu:934.6656249053656
Step 4286 | loss:1.321381688117981 lr:8.352062141263622e-06 tokens_per_second_per_gpu:750.5863329102272
Step 4287 | loss:1.3304989337921143 lr:8.338979317123918e-06 tokens_per_second_per_gpu:765.0932078698992
Step 4288 | loss:1.3572379350662231 lr:8.32590536172077e-06 tokens_per_second_per_gpu:842.1247013888047
Step 4289 | loss:1.2717046737670898 lr:8.312840279403219e-06 tokens_per_second_per_gpu:883.1321950594806
Step 4290 | loss:1.3011071681976318 lr:8.29978407451731e-06 tokens_per_second_per_gpu:881.8351149034381
Step 4291 | loss:1.3828386068344116 lr:8.286736751406204e-06 tokens_per_second_per_gpu:861.5400932459983
Step 4292 | loss:1.3302193880081177 lr:8.273698314410022e-06 tokens_per_second_per_gpu:838.5907061990564
Step 4293 | loss:1.33783757686615 lr:8.260668767866014e-06 tokens_per_second_per_gpu:961.7588225088443
Step 4294 | loss:1.3561222553253174 lr:8.247648116108402e-06 tokens_per_second_per_gpu:769.6366461106695
Step 4295 | loss:1.4583512544631958 lr:8.2346363634685e-06 tokens_per_second_per_gpu:757.1052240986767
Step 4296 | loss:1.3315600156784058 lr:8.221633514274639e-06 tokens_per_second_per_gpu:1179.1432600061294
Step 4297 | loss:1.3531553745269775 lr:8.208639572852192e-06 tokens_per_second_per_gpu:886.1140315752215
Step 4298 | loss:1.365348219871521 lr:8.195654543523562e-06 tokens_per_second_per_gpu:915.1710982657819
Step 4299 | loss:1.3440454006195068 lr:8.182678430608201e-06 tokens_per_second_per_gpu:910.3549368680227
Step 4300 | loss:1.306838035583496 lr:8.169711238422582e-06 tokens_per_second_per_gpu:611.4539271867925
Step 4301 | loss:1.50166654586792 lr:8.15675297128022e-06 tokens_per_second_per_gpu:706.0166824507105
Step 4302 | loss:1.4547327756881714 lr:8.143803633491645e-06 tokens_per_second_per_gpu:861.6967754589481
Step 4303 | loss:1.4330145120620728 lr:8.13086322936446e-06 tokens_per_second_per_gpu:871.3913874870351
Step 4304 | loss:1.3962905406951904 lr:8.117931763203223e-06 tokens_per_second_per_gpu:842.0644350684131
Step 4305 | loss:1.3475474119186401 lr:8.105009239309602e-06 tokens_per_second_per_gpu:1062.9944030711574
Step 4306 | loss:1.4041683673858643 lr:8.092095661982213e-06 tokens_per_second_per_gpu:808.2761889970013
Step 4307 | loss:1.3609592914581299 lr:8.07919103551676e-06 tokens_per_second_per_gpu:764.9850108048281
Step 4308 | loss:1.347846269607544 lr:8.066295364205928e-06 tokens_per_second_per_gpu:980.7078185597903
Step 4309 | loss:1.339039921760559 lr:8.053408652339443e-06 tokens_per_second_per_gpu:1082.106266813151
Step 4310 | loss:1.2770018577575684 lr:8.040530904204043e-06 tokens_per_second_per_gpu:793.3253009273272
Step 4311 | loss:1.3087347745895386 lr:8.027662124083483e-06 tokens_per_second_per_gpu:781.9882414137601
Step 4312 | loss:1.411321997642517 lr:8.014802316258538e-06 tokens_per_second_per_gpu:830.1891165889502
Step 4313 | loss:1.285179615020752 lr:8.001951485007e-06 tokens_per_second_per_gpu:1037.0751107459002
Step 4314 | loss:1.1310808658599854 lr:7.989109634603675e-06 tokens_per_second_per_gpu:1126.7722795945688
Step 4315 | loss:1.2128957509994507 lr:7.976276769320374e-06 tokens_per_second_per_gpu:853.3753717000925
Step 4316 | loss:1.302397608757019 lr:7.963452893425927e-06 tokens_per_second_per_gpu:1120.9755063411703
Step 4317 | loss:1.3085442781448364 lr:7.950638011186175e-06 tokens_per_second_per_gpu:976.4495833679158
Step 4318 | loss:1.2032616138458252 lr:7.937832126863958e-06 tokens_per_second_per_gpu:884.3150562976941
Step 4319 | loss:1.4946415424346924 lr:7.925035244719122e-06 tokens_per_second_per_gpu:678.2355645673775
Step 4320 | loss:1.2271244525909424 lr:7.91224736900855e-06 tokens_per_second_per_gpu:906.4586098466245
Step 4321 | loss:1.5854568481445312 lr:7.899468503986073e-06 tokens_per_second_per_gpu:638.6422456063284
Step 4322 | loss:1.4969799518585205 lr:7.886698653902588e-06 tokens_per_second_per_gpu:873.8156340462047
Step 4323 | loss:1.3430994749069214 lr:7.873937823005921e-06 tokens_per_second_per_gpu:815.8233367032088
Step 4324 | loss:1.3815393447875977 lr:7.861186015540981e-06 tokens_per_second_per_gpu:861.0192615577797
Step 4325 | loss:1.2970892190933228 lr:7.84844323574959e-06 tokens_per_second_per_gpu:829.8188647183421
Step 4326 | loss:1.4014109373092651 lr:7.83570948787064e-06 tokens_per_second_per_gpu:818.3565747977585
Step 4327 | loss:1.3756730556488037 lr:7.822984776139977e-06 tokens_per_second_per_gpu:958.298260840943
Step 4328 | loss:1.4152406454086304 lr:7.810269104790448e-06 tokens_per_second_per_gpu:726.6956576668166
Step 4329 | loss:1.455361008644104 lr:7.797562478051903e-06 tokens_per_second_per_gpu:691.2505321658256
Step 4330 | loss:1.3511462211608887 lr:7.784864900151173e-06 tokens_per_second_per_gpu:894.3606859200466
Step 4331 | loss:1.3136096000671387 lr:7.772176375312068e-06 tokens_per_second_per_gpu:954.2642594885646
Step 4332 | loss:1.2845100164413452 lr:7.75949690775544e-06 tokens_per_second_per_gpu:792.5670751734408
Step 4333 | loss:1.3470547199249268 lr:7.746826501699044e-06 tokens_per_second_per_gpu:865.9004304276107
Step 4334 | loss:1.472172737121582 lr:7.73416516135771e-06 tokens_per_second_per_gpu:815.8218411414563
Step 4335 | loss:1.3042852878570557 lr:7.72151289094316e-06 tokens_per_second_per_gpu:927.0985097067892
Step 4336 | loss:1.3313835859298706 lr:7.708869694664194e-06 tokens_per_second_per_gpu:643.2670761914799
Step 4337 | loss:1.3596965074539185 lr:7.696235576726504e-06 tokens_per_second_per_gpu:659.0311718855338
Step 4338 | loss:1.2871633768081665 lr:7.683610541332834e-06 tokens_per_second_per_gpu:1026.1378516815519
Step 4339 | loss:1.3505959510803223 lr:7.670994592682872e-06 tokens_per_second_per_gpu:884.3849769559371
Step 4340 | loss:1.4822463989257812 lr:7.65838773497328e-06 tokens_per_second_per_gpu:1020.1148353754638
Step 4341 | loss:1.385462760925293 lr:7.645789972397713e-06 tokens_per_second_per_gpu:873.4836764793112
Step 4342 | loss:1.152483582496643 lr:7.633201309146793e-06 tokens_per_second_per_gpu:1013.1244130173408
Step 4343 | loss:1.3093849420547485 lr:7.620621749408104e-06 tokens_per_second_per_gpu:893.8783572277495
Step 4344 | loss:1.3044307231903076 lr:7.608051297366225e-06 tokens_per_second_per_gpu:1195.5399958587072
Step 4345 | loss:1.2694826126098633 lr:7.59548995720267e-06 tokens_per_second_per_gpu:856.8086874756118
Step 4346 | loss:1.3900892734527588 lr:7.582937733095984e-06 tokens_per_second_per_gpu:811.4213302830751
Step 4347 | loss:1.2984422445297241 lr:7.570394629221593e-06 tokens_per_second_per_gpu:1132.0625930959723
Step 4348 | loss:1.2618602514266968 lr:7.557860649751981e-06 tokens_per_second_per_gpu:778.0856503713475
Step 4349 | loss:1.4704078435897827 lr:7.545335798856511e-06 tokens_per_second_per_gpu:836.9471825147374
Step 4350 | loss:1.3209325075149536 lr:7.532820080701579e-06 tokens_per_second_per_gpu:1044.5371564947357
Step 4351 | loss:1.222596287727356 lr:7.520313499450502e-06 tokens_per_second_per_gpu:1053.9774233303617
Step 4352 | loss:1.2260372638702393 lr:7.5078160592635715e-06 tokens_per_second_per_gpu:943.690439127214
Step 4353 | loss:1.3063715696334839 lr:7.495327764298042e-06 tokens_per_second_per_gpu:653.8981869248469
Step 4354 | loss:1.2137203216552734 lr:7.482848618708115e-06 tokens_per_second_per_gpu:891.1065947055803
Step 4355 | loss:1.3450320959091187 lr:7.47037862664495e-06 tokens_per_second_per_gpu:850.3603254722565
Step 4356 | loss:1.404649257659912 lr:7.457917792256678e-06 tokens_per_second_per_gpu:1143.7695925252042
Step 4357 | loss:1.3210976123809814 lr:7.445466119688349e-06 tokens_per_second_per_gpu:863.5576623211083
Step 4358 | loss:1.2664955854415894 lr:7.433023613082022e-06 tokens_per_second_per_gpu:1255.5734523191798
Step 4359 | loss:1.3252499103546143 lr:7.420590276576633e-06 tokens_per_second_per_gpu:615.814495885405
Step 4360 | loss:1.2276328802108765 lr:7.408166114308149e-06 tokens_per_second_per_gpu:698.628049131188
Step 4361 | loss:1.3445621728897095 lr:7.395751130409401e-06 tokens_per_second_per_gpu:830.5297940833527
Step 4362 | loss:1.268787145614624 lr:7.383345329010238e-06 tokens_per_second_per_gpu:704.1327082887756
Step 4363 | loss:1.372314691543579 lr:7.370948714237418e-06 tokens_per_second_per_gpu:772.1636297864859
Step 4364 | loss:1.3637744188308716 lr:7.358561290214652e-06 tokens_per_second_per_gpu:949.0380059264337
Step 4365 | loss:1.2358226776123047 lr:7.3461830610625885e-06 tokens_per_second_per_gpu:1065.2934453755493
Step 4366 | loss:1.3927054405212402 lr:7.333814030898822e-06 tokens_per_second_per_gpu:805.6279321380212
Step 4367 | loss:1.1534876823425293 lr:7.321454203837889e-06 tokens_per_second_per_gpu:1072.001584996916
Step 4368 | loss:1.255659818649292 lr:7.309103583991261e-06 tokens_per_second_per_gpu:825.8391203122607
Step 4369 | loss:1.420681118965149 lr:7.296762175467345e-06 tokens_per_second_per_gpu:662.8565431922719
Step 4370 | loss:1.2606858015060425 lr:7.28442998237149e-06 tokens_per_second_per_gpu:1156.1002095617846
Step 4371 | loss:1.355952501296997 lr:7.272107008805974e-06 tokens_per_second_per_gpu:694.4771337027881
Step 4372 | loss:1.2663066387176514 lr:7.25979325887001e-06 tokens_per_second_per_gpu:1092.6504796183845
Step 4373 | loss:1.5242639780044556 lr:7.247488736659746e-06 tokens_per_second_per_gpu:880.6929182695633
Step 4374 | loss:1.2726328372955322 lr:7.235193446268242e-06 tokens_per_second_per_gpu:1120.7272394932438
Step 4375 | loss:1.282295823097229 lr:7.222907391785534e-06 tokens_per_second_per_gpu:1093.102941999973
Step 4376 | loss:1.3861443996429443 lr:7.21063057729852e-06 tokens_per_second_per_gpu:1000.1276118567625
Step 4377 | loss:1.3072943687438965 lr:7.1983630068910815e-06 tokens_per_second_per_gpu:698.3849606919587
Step 4378 | loss:1.3819200992584229 lr:7.186104684643994e-06 tokens_per_second_per_gpu:782.2806877321501
Step 4379 | loss:1.245591163635254 lr:7.173855614634963e-06 tokens_per_second_per_gpu:1144.991613071394
Step 4380 | loss:1.390683650970459 lr:7.16161580093862e-06 tokens_per_second_per_gpu:809.8707425103506
Step 4381 | loss:1.2837625741958618 lr:7.149385247626517e-06 tokens_per_second_per_gpu:815.563369022207
Step 4382 | loss:1.341772437095642 lr:7.137163958767118e-06 tokens_per_second_per_gpu:867.9780231234554
Step 4383 | loss:1.3844430446624756 lr:7.124951938425819e-06 tokens_per_second_per_gpu:756.1024117239958
Step 4384 | loss:1.3217051029205322 lr:7.112749190664916e-06 tokens_per_second_per_gpu:780.4976999255639
Step 4385 | loss:1.1787960529327393 lr:7.100555719543633e-06 tokens_per_second_per_gpu:955.2252931010979
Step 4386 | loss:1.301728367805481 lr:7.0883715291181045e-06 tokens_per_second_per_gpu:880.5864007331346
Step 4387 | loss:1.281928300857544 lr:7.07619662344138e-06 tokens_per_second_per_gpu:948.3526228444864
Step 4388 | loss:1.1823588609695435 lr:7.064031006563406e-06 tokens_per_second_per_gpu:1015.4209736229865
Step 4389 | loss:1.448460340499878 lr:7.05187468253108e-06 tokens_per_second_per_gpu:777.1717658667891
Step 4390 | loss:1.433149814605713 lr:7.039727655388138e-06 tokens_per_second_per_gpu:998.6960914141848
Step 4391 | loss:1.2957295179367065 lr:7.027589929175312e-06 tokens_per_second_per_gpu:821.2380687344828
Step 4392 | loss:1.3349645137786865 lr:7.015461507930144e-06 tokens_per_second_per_gpu:764.3290135319679
Step 4393 | loss:1.4847729206085205 lr:7.0033423956871674e-06 tokens_per_second_per_gpu:727.563508241518
Step 4394 | loss:1.3115942478179932 lr:6.991232596477769e-06 tokens_per_second_per_gpu:766.6510602525141
Step 4395 | loss:1.3027197122573853 lr:6.979132114330246e-06 tokens_per_second_per_gpu:951.6267976297045
Step 4396 | loss:1.4694560766220093 lr:6.967040953269805e-06 tokens_per_second_per_gpu:621.9104102705361
Step 4397 | loss:1.425667405128479 lr:6.9549591173185455e-06 tokens_per_second_per_gpu:695.164007425832
Step 4398 | loss:1.40591561794281 lr:6.9428866104954655e-06 tokens_per_second_per_gpu:868.9337226773875
Step 4399 | loss:1.3644275665283203 lr:6.9308234368164615e-06 tokens_per_second_per_gpu:796.2817889302999
Step 4400 | loss:1.3378185033798218 lr:6.9187696002943156e-06 tokens_per_second_per_gpu:806.7641786648257
Step 4401 | loss:1.4628677368164062 lr:6.906725104938742e-06 tokens_per_second_per_gpu:1093.904895444811
Step 4402 | loss:1.1723301410675049 lr:6.894689954756281e-06 tokens_per_second_per_gpu:1018.0664882478821
Step 4403 | loss:1.454993724822998 lr:6.882664153750435e-06 tokens_per_second_per_gpu:1234.5278219755107
Step 4404 | loss:1.228727102279663 lr:6.870647705921533e-06 tokens_per_second_per_gpu:827.1754218583029
Step 4405 | loss:1.3751991987228394 lr:6.85864061526685e-06 tokens_per_second_per_gpu:961.4547158826776
Step 4406 | loss:1.3536205291748047 lr:6.8466428857805055e-06 tokens_per_second_per_gpu:937.7817622833292
Step 4407 | loss:1.4015295505523682 lr:6.834654521453526e-06 tokens_per_second_per_gpu:999.8364354704845
Step 4408 | loss:1.2508728504180908 lr:6.8226755262738155e-06 tokens_per_second_per_gpu:872.8606100777916
Step 4409 | loss:1.3132858276367188 lr:6.810705904226162e-06 tokens_per_second_per_gpu:971.0987071151443
Step 4410 | loss:1.2427058219909668 lr:6.798745659292243e-06 tokens_per_second_per_gpu:1054.4131346278125
Step 4411 | loss:1.4870113134384155 lr:6.786794795450604e-06 tokens_per_second_per_gpu:649.0956898679017
Step 4412 | loss:1.341597080230713 lr:6.774853316676671e-06 tokens_per_second_per_gpu:836.6218975973522
Step 4413 | loss:1.2941718101501465 lr:6.7629212269427805e-06 tokens_per_second_per_gpu:817.0652349917087
Step 4414 | loss:1.4254006147384644 lr:6.750998530218085e-06 tokens_per_second_per_gpu:1014.7455878126597
Step 4415 | loss:1.373429775238037 lr:6.739085230468674e-06 tokens_per_second_per_gpu:650.8406012841675
Step 4416 | loss:1.2446072101593018 lr:6.727181331657457e-06 tokens_per_second_per_gpu:799.1537095851642
Step 4417 | loss:1.413320541381836 lr:6.715286837744276e-06 tokens_per_second_per_gpu:877.6433897546257
Step 4418 | loss:1.388871431350708 lr:6.703401752685771e-06 tokens_per_second_per_gpu:824.0787343146599
Step 4419 | loss:1.365634799003601 lr:6.691526080435524e-06 tokens_per_second_per_gpu:614.8382089470248
Step 4420 | loss:1.3429454565048218 lr:6.679659824943943e-06 tokens_per_second_per_gpu:783.5885887061303
Step 4421 | loss:1.4525835514068604 lr:6.6678029901583155e-06 tokens_per_second_per_gpu:578.865960943621
Step 4422 | loss:1.2135149240493774 lr:6.655955580022797e-06 tokens_per_second_per_gpu:929.9123836858819
Step 4423 | loss:1.334330677986145 lr:6.644117598478399e-06 tokens_per_second_per_gpu:886.4165630137695
Step 4424 | loss:1.4240578413009644 lr:6.632289049463008e-06 tokens_per_second_per_gpu:895.0956653125135
Step 4425 | loss:1.3956278562545776 lr:6.620469936911369e-06 tokens_per_second_per_gpu:1063.8257375699322
Step 4426 | loss:1.2398759126663208 lr:6.6086602647550805e-06 tokens_per_second_per_gpu:1041.212086726889
Step 4427 | loss:1.164849042892456 lr:6.596860036922615e-06 tokens_per_second_per_gpu:1274.42288106547
Step 4428 | loss:1.43374502658844 lr:6.585069257339277e-06 tokens_per_second_per_gpu:796.3813106159633
Step 4429 | loss:1.3418161869049072 lr:6.573287929927282e-06 tokens_per_second_per_gpu:845.3919787135259
Step 4430 | loss:1.33992600440979 lr:6.561516058605627e-06 tokens_per_second_per_gpu:999.9076262716351
Step 4431 | loss:1.3987982273101807 lr:6.549753647290224e-06 tokens_per_second_per_gpu:958.735430962496
Step 4432 | loss:1.1904152631759644 lr:6.5380006998938154e-06 tokens_per_second_per_gpu:1108.8921243147465
Step 4433 | loss:1.2795230150222778 lr:6.5262572203259865e-06 tokens_per_second_per_gpu:1039.8817313030415
Step 4434 | loss:1.2421419620513916 lr:6.514523212493195e-06 tokens_per_second_per_gpu:976.1674079674311
Step 4435 | loss:1.2480119466781616 lr:6.502798680298722e-06 tokens_per_second_per_gpu:1086.7995013461025
Step 4436 | loss:1.2985937595367432 lr:6.491083627642723e-06 tokens_per_second_per_gpu:760.762638899666
Step 4437 | loss:1.3685510158538818 lr:6.47937805842218e-06 tokens_per_second_per_gpu:861.7951300808013
Step 4438 | loss:1.2757130861282349 lr:6.467681976530929e-06 tokens_per_second_per_gpu:1020.106923048073
Step 4439 | loss:1.3564692735671997 lr:6.4559953858596505e-06 tokens_per_second_per_gpu:736.0136915821629
Step 4440 | loss:1.3366891145706177 lr:6.444318290295866e-06 tokens_per_second_per_gpu:800.2058274768827
Step 4441 | loss:1.2292360067367554 lr:6.432650693723939e-06 tokens_per_second_per_gpu:726.9038872510413
Step 4442 | loss:1.232303500175476 lr:6.420992600025067e-06 tokens_per_second_per_gpu:1086.2583474581581
Step 4443 | loss:1.1984785795211792 lr:6.409344013077291e-06 tokens_per_second_per_gpu:954.3271125604997
Step 4444 | loss:1.276950716972351 lr:6.397704936755511e-06 tokens_per_second_per_gpu:859.3815945407417
Step 4445 | loss:1.4123036861419678 lr:6.386075374931414e-06 tokens_per_second_per_gpu:801.6427269096762
Step 4446 | loss:1.3343151807785034 lr:6.3744553314735825e-06 tokens_per_second_per_gpu:935.3065381378132
Step 4447 | loss:1.4075406789779663 lr:6.362844810247365e-06 tokens_per_second_per_gpu:844.9113678725489
Step 4448 | loss:1.2739577293395996 lr:6.351243815115006e-06 tokens_per_second_per_gpu:932.6157782926591
Step 4449 | loss:1.2542158365249634 lr:6.339652349935549e-06 tokens_per_second_per_gpu:990.9985853921232
Step 4450 | loss:1.309065580368042 lr:6.328070418564868e-06 tokens_per_second_per_gpu:758.0777109612407
Step 4451 | loss:1.521304726600647 lr:6.316498024855669e-06 tokens_per_second_per_gpu:844.4787041287964
Step 4452 | loss:1.2336204051971436 lr:6.30493517265749e-06 tokens_per_second_per_gpu:1098.281887380261
Step 4453 | loss:1.2132225036621094 lr:6.29338186581669e-06 tokens_per_second_per_gpu:974.2539228478643
Step 4454 | loss:1.2675988674163818 lr:6.281838108176453e-06 tokens_per_second_per_gpu:1179.9581729890724
Step 4455 | loss:1.372340440750122 lr:6.270303903576783e-06 tokens_per_second_per_gpu:933.644727431489
Step 4456 | loss:1.2986387014389038 lr:6.258779255854528e-06 tokens_per_second_per_gpu:849.4122524705489
Step 4457 | loss:1.4794405698776245 lr:6.247264168843313e-06 tokens_per_second_per_gpu:825.5333319503485
Step 4458 | loss:1.2025279998779297 lr:6.235758646373637e-06 tokens_per_second_per_gpu:1043.859429563461
Step 4459 | loss:1.349876880645752 lr:6.224262692272762e-06 tokens_per_second_per_gpu:1001.4152980850802
Step 4460 | loss:1.3320802450180054 lr:6.212776310364828e-06 tokens_per_second_per_gpu:860.4525466261367
Step 4461 | loss:1.247423529624939 lr:6.201299504470718e-06 tokens_per_second_per_gpu:887.4005683246404
Step 4462 | loss:1.3897759914398193 lr:6.189832278408199e-06 tokens_per_second_per_gpu:1053.7756227174307
Step 4463 | loss:1.3344199657440186 lr:6.178374635991811e-06 tokens_per_second_per_gpu:889.1996086741283
Step 4464 | loss:1.3082133531570435 lr:6.166926581032918e-06 tokens_per_second_per_gpu:1235.0965617458842
Step 4465 | loss:1.3754680156707764 lr:6.1554881173396955e-06 tokens_per_second_per_gpu:783.3005105909184
Step 4466 | loss:1.3745064735412598 lr:6.144059248717117e-06 tokens_per_second_per_gpu:769.8569488082674
Step 4467 | loss:1.4383699893951416 lr:6.132639978966978e-06 tokens_per_second_per_gpu:905.5590951509662
Step 4468 | loss:1.321699857711792 lr:6.121230311887888e-06 tokens_per_second_per_gpu:757.0832198341823
Step 4469 | loss:1.2755101919174194 lr:6.10983025127523e-06 tokens_per_second_per_gpu:953.0665260234991
Step 4470 | loss:1.3177121877670288 lr:6.098439800921237e-06 tokens_per_second_per_gpu:902.2829647472429
Step 4471 | loss:1.2563585042953491 lr:6.087058964614888e-06 tokens_per_second_per_gpu:1170.3470516238228
Step 4472 | loss:1.3785146474838257 lr:6.0756877461420274e-06 tokens_per_second_per_gpu:862.9112834254229
Step 4473 | loss:1.3791449069976807 lr:6.064326149285244e-06 tokens_per_second_per_gpu:899.6339480746207
Step 4474 | loss:1.2318439483642578 lr:6.052974177823966e-06 tokens_per_second_per_gpu:972.1106564727907
Step 4475 | loss:1.3049558401107788 lr:6.041631835534399e-06 tokens_per_second_per_gpu:855.3284506280046
Step 4476 | loss:1.2661997079849243 lr:6.030299126189556e-06 tokens_per_second_per_gpu:1063.479675085945
Step 4477 | loss:1.4585708379745483 lr:6.018976053559237e-06 tokens_per_second_per_gpu:540.4633772656917
Step 4478 | loss:1.5960218906402588 lr:6.007662621410038e-06 tokens_per_second_per_gpu:657.1724559377939
Step 4479 | loss:1.2976946830749512 lr:5.996358833505352e-06 tokens_per_second_per_gpu:1050.6903891780814
Step 4480 | loss:1.104184865951538 lr:5.985064693605363e-06 tokens_per_second_per_gpu:929.1229589629079
Step 4481 | loss:1.3271808624267578 lr:5.9737802054670366e-06 tokens_per_second_per_gpu:775.1303484642186
Step 4482 | loss:1.3036677837371826 lr:5.962505372844161e-06 tokens_per_second_per_gpu:1078.7089799388987
Step 4483 | loss:1.310037612915039 lr:5.951240199487249e-06 tokens_per_second_per_gpu:703.6044734489141
Step 4484 | loss:1.2469823360443115 lr:5.939984689143677e-06 tokens_per_second_per_gpu:754.6277003305033
Step 4485 | loss:1.292216420173645 lr:5.928738845557534e-06 tokens_per_second_per_gpu:738.6607148170264
Step 4486 | loss:1.3119961023330688 lr:5.917502672469754e-06 tokens_per_second_per_gpu:1004.5461880772771
Step 4487 | loss:1.381258487701416 lr:5.906276173618017e-06 tokens_per_second_per_gpu:740.8052787097519
Step 4488 | loss:1.5320967435836792 lr:5.895059352736797e-06 tokens_per_second_per_gpu:1107.9632182409473
Step 4489 | loss:1.2710570096969604 lr:5.88385221355735e-06 tokens_per_second_per_gpu:848.5471435247924
Step 4490 | loss:1.287756323814392 lr:5.872654759807705e-06 tokens_per_second_per_gpu:952.1804765498473
Step 4491 | loss:1.2575995922088623 lr:5.861466995212678e-06 tokens_per_second_per_gpu:845.1379974353443
Step 4492 | loss:1.437883973121643 lr:5.850288923493852e-06 tokens_per_second_per_gpu:678.3868870971688
Step 4493 | loss:1.3587543964385986 lr:5.839120548369593e-06 tokens_per_second_per_gpu:954.5711362280297
Step 4494 | loss:1.3116185665130615 lr:5.827961873555041e-06 tokens_per_second_per_gpu:794.9712014791903
Step 4495 | loss:1.2078132629394531 lr:5.816812902762104e-06 tokens_per_second_per_gpu:1087.4993208858111
Step 4496 | loss:1.5011439323425293 lr:5.8056736396994704e-06 tokens_per_second_per_gpu:642.3659626996678
Step 4497 | loss:1.2496079206466675 lr:5.794544088072588e-06 tokens_per_second_per_gpu:875.889352654303
Step 4498 | loss:1.2799465656280518 lr:5.7834242515836755e-06 tokens_per_second_per_gpu:776.3959885513829
Step 4499 | loss:1.219736933708191 lr:5.772314133931752e-06 tokens_per_second_per_gpu:798.0146477884304
Step 4500 | loss:1.258521318435669 lr:5.7612137388125355e-06 tokens_per_second_per_gpu:1052.0593450720082
Step 4501 | loss:1.4002101421356201 lr:5.7501230699185945e-06 tokens_per_second_per_gpu:832.6430454353671
Step 4502 | loss:1.3327674865722656 lr:5.7390421309391755e-06 tokens_per_second_per_gpu:872.7852097933242
Step 4503 | loss:1.3865487575531006 lr:5.727970925560364e-06 tokens_per_second_per_gpu:935.8013143450636
Step 4504 | loss:1.2794580459594727 lr:5.716909457464959e-06 tokens_per_second_per_gpu:983.9003053474885
Step 4505 | loss:1.2407563924789429 lr:5.705857730332547e-06 tokens_per_second_per_gpu:948.9802568180215
Step 4506 | loss:1.336391568183899 lr:5.6948157478394526e-06 tokens_per_second_per_gpu:933.2105537239565
Step 4507 | loss:1.169939398765564 lr:5.683783513658776e-06 tokens_per_second_per_gpu:905.5264003134007
Step 4508 | loss:1.27689790725708 lr:5.672761031460364e-06 tokens_per_second_per_gpu:946.6101935582807
Step 4509 | loss:1.5488085746765137 lr:5.661748304910826e-06 tokens_per_second_per_gpu:910.626097511065
Step 4510 | loss:1.3028993606567383 lr:5.650745337673519e-06 tokens_per_second_per_gpu:1312.17096514978
Step 4511 | loss:1.3534232378005981 lr:5.6397521334085796e-06 tokens_per_second_per_gpu:945.7544626848984
Step 4512 | loss:1.321205973625183 lr:5.628768695772843e-06 tokens_per_second_per_gpu:898.1299709828932
Step 4513 | loss:1.4609442949295044 lr:5.617795028419961e-06 tokens_per_second_per_gpu:735.7917797255926
Step 4514 | loss:1.3168766498565674 lr:5.606831135000275e-06 tokens_per_second_per_gpu:899.4456661115596
Step 4515 | loss:1.4773781299591064 lr:5.595877019160927e-06 tokens_per_second_per_gpu:872.6092247528076
Step 4516 | loss:1.378287672996521 lr:5.5849326845457536e-06 tokens_per_second_per_gpu:869.8277455837093
Step 4517 | loss:1.1443617343902588 lr:5.573998134795391e-06 tokens_per_second_per_gpu:810.4069664772594
Step 4518 | loss:1.4530255794525146 lr:5.563073373547192e-06 tokens_per_second_per_gpu:692.8862899226569
Step 4519 | loss:1.4896234273910522 lr:5.552158404435248e-06 tokens_per_second_per_gpu:658.5338985444128
Step 4520 | loss:1.2696317434310913 lr:5.54125323109041e-06 tokens_per_second_per_gpu:907.8724027301089
Step 4521 | loss:1.328342318534851 lr:5.530357857140259e-06 tokens_per_second_per_gpu:742.4879316263156
Step 4522 | loss:1.2574810981750488 lr:5.5194722862091205e-06 tokens_per_second_per_gpu:1008.3223977941764
Step 4523 | loss:1.4633244276046753 lr:5.508596521918058e-06 tokens_per_second_per_gpu:851.6183324475381
Step 4524 | loss:1.3055107593536377 lr:5.4977305678848635e-06 tokens_per_second_per_gpu:853.5274347469376
Step 4525 | loss:1.2787590026855469 lr:5.486874427724107e-06 tokens_per_second_per_gpu:976.8813204599899
Step 4526 | loss:1.4031429290771484 lr:5.4760281050470226e-06 tokens_per_second_per_gpu:889.3750816236384
Step 4527 | loss:1.284785509109497 lr:5.465191603461655e-06 tokens_per_second_per_gpu:678.9412711470621
Step 4528 | loss:1.3798238039016724 lr:5.45436492657271e-06 tokens_per_second_per_gpu:690.895360556866
Step 4529 | loss:1.4061063528060913 lr:5.443548077981685e-06 tokens_per_second_per_gpu:862.5167808547558
Step 4530 | loss:1.303944706916809 lr:5.432741061286774e-06 tokens_per_second_per_gpu:904.8845672925456
Step 4531 | loss:1.1823822259902954 lr:5.421943880082919e-06 tokens_per_second_per_gpu:1136.5212678042874
Step 4532 | loss:1.3175722360610962 lr:5.41115653796177e-06 tokens_per_second_per_gpu:969.998985089577
Step 4533 | loss:1.283199429512024 lr:5.400379038511719e-06 tokens_per_second_per_gpu:896.0615399488037
Step 4534 | loss:1.1743217706680298 lr:5.389611385317888e-06 tokens_per_second_per_gpu:883.3723171654314
Step 4535 | loss:1.2820453643798828 lr:5.378853581962102e-06 tokens_per_second_per_gpu:652.324875297136
Step 4536 | loss:1.3786394596099854 lr:5.368105632022927e-06 tokens_per_second_per_gpu:740.5035728543187
Step 4537 | loss:1.3253682851791382 lr:5.357367539075664e-06 tokens_per_second_per_gpu:1015.326471902221
Step 4538 | loss:1.3113917112350464 lr:5.346639306692292e-06 tokens_per_second_per_gpu:1022.9015187625348
Step 4539 | loss:1.250792145729065 lr:5.335920938441567e-06 tokens_per_second_per_gpu:706.5179483756299
Step 4540 | loss:1.3472504615783691 lr:5.325212437888898e-06 tokens_per_second_per_gpu:857.3741851688904
Step 4541 | loss:1.3302503824234009 lr:5.3145138085964745e-06 tokens_per_second_per_gpu:888.9165230772995
Step 4542 | loss:1.3640799522399902 lr:5.303825054123165e-06 tokens_per_second_per_gpu:1028.348120972415
Step 4543 | loss:1.4809492826461792 lr:5.293146178024565e-06 tokens_per_second_per_gpu:740.1652758104799
Step 4544 | loss:1.205816388130188 lr:5.28247718385298e-06 tokens_per_second_per_gpu:757.1093691403463
Step 4545 | loss:1.21466064453125 lr:5.27181807515743e-06 tokens_per_second_per_gpu:763.1571419107075
Step 4546 | loss:1.430662751197815 lr:5.261168855483647e-06 tokens_per_second_per_gpu:866.0610089871577
Step 4547 | loss:1.2740812301635742 lr:5.250529528374072e-06 tokens_per_second_per_gpu:862.7286134159943
Step 4548 | loss:1.3013124465942383 lr:5.2399000973678624e-06 tokens_per_second_per_gpu:837.1426419376745
Step 4549 | loss:1.4943439960479736 lr:5.229280566000868e-06 tokens_per_second_per_gpu:768.5489598891296
Step 4550 | loss:1.394280195236206 lr:5.218670937805664e-06 tokens_per_second_per_gpu:1007.0542976258994
Step 4551 | loss:1.52054762840271 lr:5.208071216311515e-06 tokens_per_second_per_gpu:879.8577372325241
Step 4552 | loss:1.4341357946395874 lr:5.197481405044404e-06 tokens_per_second_per_gpu:829.7912302762348
Step 4553 | loss:1.333019733428955 lr:5.186901507526998e-06 tokens_per_second_per_gpu:739.9674242091187
Step 4554 | loss:1.0964943170547485 lr:5.176331527278712e-06 tokens_per_second_per_gpu:1155.163187722019
Step 4555 | loss:1.333471417427063 lr:5.165771467815585e-06 tokens_per_second_per_gpu:707.2779218122125
Step 4556 | loss:1.3409342765808105 lr:5.1552213326504325e-06 tokens_per_second_per_gpu:832.9339467338527
Step 4557 | loss:1.3183650970458984 lr:5.144681125292725e-06 tokens_per_second_per_gpu:1009.9060123923076
Step 4558 | loss:1.3396096229553223 lr:5.134150849248646e-06 tokens_per_second_per_gpu:835.7924383940488
Step 4559 | loss:1.3136030435562134 lr:5.123630508021066e-06 tokens_per_second_per_gpu:869.925106501223
Step 4560 | loss:1.360412836074829 lr:5.113120105109558e-06 tokens_per_second_per_gpu:654.6754593881792
Step 4561 | loss:1.2699127197265625 lr:5.102619644010393e-06 tokens_per_second_per_gpu:930.3276223221166
Step 4562 | loss:1.2857887744903564 lr:5.092129128216517e-06 tokens_per_second_per_gpu:862.3798691311225
Step 4563 | loss:1.3980834484100342 lr:5.0816485612175876e-06 tokens_per_second_per_gpu:1050.6657203298741
Step 4564 | loss:1.4167399406433105 lr:5.071177946499946e-06 tokens_per_second_per_gpu:670.1839256381543
Step 4565 | loss:1.4253276586532593 lr:5.060717287546616e-06 tokens_per_second_per_gpu:642.0919245228034
Step 4566 | loss:1.2230967283248901 lr:5.0502665878373215e-06 tokens_per_second_per_gpu:957.7317809205265
Step 4567 | loss:1.283427119255066 lr:5.039825850848457e-06 tokens_per_second_per_gpu:1307.990432662513
Step 4568 | loss:1.4542346000671387 lr:5.029395080053132e-06 tokens_per_second_per_gpu:1034.9996103879544
Step 4569 | loss:1.4042555093765259 lr:5.018974278921098e-06 tokens_per_second_per_gpu:684.4442252621184
Step 4570 | loss:1.371070146560669 lr:5.008563450918847e-06 tokens_per_second_per_gpu:820.8216789984772
Step 4571 | loss:1.5466388463974 lr:4.9981625995094795e-06 tokens_per_second_per_gpu:695.883007945806
Step 4572 | loss:1.2201833724975586 lr:4.987771728152849e-06 tokens_per_second_per_gpu:1095.3191610110875
Step 4573 | loss:1.300836443901062 lr:4.977390840305449e-06 tokens_per_second_per_gpu:943.1284699212775
Step 4574 | loss:1.268420696258545 lr:4.967019939420462e-06 tokens_per_second_per_gpu:865.7549829343102
Step 4575 | loss:1.2714954614639282 lr:4.956659028947749e-06 tokens_per_second_per_gpu:742.4449442742903
Step 4576 | loss:1.455794334411621 lr:4.946308112333841e-06 tokens_per_second_per_gpu:843.2770283904338
Step 4577 | loss:1.2850441932678223 lr:4.935967193021962e-06 tokens_per_second_per_gpu:945.5846371703127
Step 4578 | loss:1.4030182361602783 lr:4.925636274451985e-06 tokens_per_second_per_gpu:914.4149079215662
Step 4579 | loss:1.2194677591323853 lr:4.915315360060472e-06 tokens_per_second_per_gpu:1111.0231547860349
Step 4580 | loss:1.2853083610534668 lr:4.905004453280674e-06 tokens_per_second_per_gpu:1152.8646518113057
Step 4581 | loss:1.3967807292938232 lr:4.894703557542467e-06 tokens_per_second_per_gpu:1271.2040248627477
Step 4582 | loss:1.259562373161316 lr:4.8844126762724465e-06 tokens_per_second_per_gpu:1093.0133372875873
Step 4583 | loss:1.2794522047042847 lr:4.874131812893833e-06 tokens_per_second_per_gpu:916.0218240137375
Step 4584 | loss:1.4219616651535034 lr:4.8638609708265515e-06 tokens_per_second_per_gpu:819.6854050361385
Step 4585 | loss:1.4351555109024048 lr:4.853600153487172e-06 tokens_per_second_per_gpu:927.7426383755964
Step 4586 | loss:1.508892297744751 lr:4.843349364288937e-06 tokens_per_second_per_gpu:725.78646475863
Step 4587 | loss:1.4104251861572266 lr:4.833108606641755e-06 tokens_per_second_per_gpu:909.1403432941779
Step 4588 | loss:1.2270147800445557 lr:4.822877883952184e-06 tokens_per_second_per_gpu:873.250255136432
Step 4589 | loss:1.3215938806533813 lr:4.812657199623461e-06 tokens_per_second_per_gpu:1108.5605887546342
Step 4590 | loss:1.3877555131912231 lr:4.8024465570554775e-06 tokens_per_second_per_gpu:990.7201651153248
Step 4591 | loss:1.3821889162063599 lr:4.79224595964477e-06 tokens_per_second_per_gpu:872.3166282368184
Step 4592 | loss:1.2663124799728394 lr:4.782055410784578e-06 tokens_per_second_per_gpu:917.0263466724087
Step 4593 | loss:1.3572041988372803 lr:4.771874913864731e-06 tokens_per_second_per_gpu:1031.5867876300417
Step 4594 | loss:1.4258856773376465 lr:4.761704472271785e-06 tokens_per_second_per_gpu:656.4178363891838
Step 4595 | loss:1.20527184009552 lr:4.751544089388887e-06 tokens_per_second_per_gpu:1076.8960423949666
Step 4596 | loss:1.3166733980178833 lr:4.7413937685959e-06 tokens_per_second_per_gpu:710.2154316944022
Step 4597 | loss:1.4038856029510498 lr:4.731253513269276e-06 tokens_per_second_per_gpu:869.2565076695623
Step 4598 | loss:1.2407128810882568 lr:4.721123326782172e-06 tokens_per_second_per_gpu:787.8045355205121
Step 4599 | loss:1.3051825761795044 lr:4.711003212504371e-06 tokens_per_second_per_gpu:835.2977931200156
Step 4600 | loss:1.2922775745391846 lr:4.7008931738023095e-06 tokens_per_second_per_gpu:943.6937219502421
Step 4601 | loss:1.2586824893951416 lr:4.6907932140390705e-06 tokens_per_second_per_gpu:731.9139942365748
Step 4602 | loss:1.3233535289764404 lr:4.6807033365743825e-06 tokens_per_second_per_gpu:915.125300102824
Step 4603 | loss:1.499295949935913 lr:4.67062354476463e-06 tokens_per_second_per_gpu:830.6186733654024
Step 4604 | loss:1.2949466705322266 lr:4.660553841962835e-06 tokens_per_second_per_gpu:634.7309597196347
Step 4605 | loss:1.444004774093628 lr:4.650494231518659e-06 tokens_per_second_per_gpu:793.5114753305072
Step 4606 | loss:1.1658333539962769 lr:4.640444716778418e-06 tokens_per_second_per_gpu:958.6942959036671
Step 4607 | loss:1.526513695716858 lr:4.630405301085056e-06 tokens_per_second_per_gpu:871.6788218406256
Step 4608 | loss:1.1887351274490356 lr:4.6203759877781786e-06 tokens_per_second_per_gpu:1055.6119907004663
Step 4609 | loss:1.2267600297927856 lr:4.610356780193998e-06 tokens_per_second_per_gpu:958.2487802854231
Step 4610 | loss:1.3689285516738892 lr:4.600347681665403e-06 tokens_per_second_per_gpu:867.8943442921537
Step 4611 | loss:1.4601562023162842 lr:4.590348695521892e-06 tokens_per_second_per_gpu:937.6094594516525
Step 4612 | loss:1.205062985420227 lr:4.580359825089609e-06 tokens_per_second_per_gpu:947.413179245649
Step 4613 | loss:1.4465382099151611 lr:4.570381073691331e-06 tokens_per_second_per_gpu:741.7202319863336
Step 4614 | loss:1.4322155714035034 lr:4.560412444646471e-06 tokens_per_second_per_gpu:920.8755203721834
Step 4615 | loss:1.3921619653701782 lr:4.5504539412710755e-06 tokens_per_second_per_gpu:915.608051432004
Step 4616 | loss:1.34157395362854 lr:4.54050556687782e-06 tokens_per_second_per_gpu:812.6479565024183
Step 4617 | loss:1.2173224687576294 lr:4.53056732477601e-06 tokens_per_second_per_gpu:961.1582921398829
Step 4618 | loss:1.2865705490112305 lr:4.520639218271589e-06 tokens_per_second_per_gpu:833.7589271399852
Step 4619 | loss:1.3868407011032104 lr:4.510721250667115e-06 tokens_per_second_per_gpu:906.4229452938986
Step 4620 | loss:1.2940138578414917 lr:4.500813425261781e-06 tokens_per_second_per_gpu:755.3680058729474
Step 4621 | loss:1.2992414236068726 lr:4.490915745351409e-06 tokens_per_second_per_gpu:1041.7032002588512
Step 4622 | loss:1.4686813354492188 lr:4.481028214228437e-06 tokens_per_second_per_gpu:839.4482168665666
Step 4623 | loss:1.2263424396514893 lr:4.47115083518195e-06 tokens_per_second_per_gpu:827.9914274236231
Step 4624 | loss:1.3232638835906982 lr:4.461283611497614e-06 tokens_per_second_per_gpu:818.4980139152751
Step 4625 | loss:1.439801812171936 lr:4.451426546457769e-06 tokens_per_second_per_gpu:968.892350428459
Step 4626 | loss:1.287452220916748 lr:4.441579643341318e-06 tokens_per_second_per_gpu:1161.4132563489231
Step 4627 | loss:1.4937609434127808 lr:4.431742905423837e-06 tokens_per_second_per_gpu:640.83263595702
Step 4628 | loss:1.3005198240280151 lr:4.421916335977493e-06 tokens_per_second_per_gpu:748.8496916059099
Step 4629 | loss:1.3232687711715698 lr:4.41209993827107e-06 tokens_per_second_per_gpu:689.8330331169634
Step 4630 | loss:1.272610068321228 lr:4.40229371556998e-06 tokens_per_second_per_gpu:1044.8937247960152
Step 4631 | loss:1.439500331878662 lr:4.392497671136238e-06 tokens_per_second_per_gpu:961.2598896048182
Step 4632 | loss:1.462960958480835 lr:4.382711808228484e-06 tokens_per_second_per_gpu:902.389691433684
Step 4633 | loss:1.3598337173461914 lr:4.372936130101963e-06 tokens_per_second_per_gpu:885.5405112114086
Step 4634 | loss:1.3034729957580566 lr:4.3631706400085265e-06 tokens_per_second_per_gpu:839.0365916558765
Step 4635 | loss:1.267828106880188 lr:4.353415341196672e-06 tokens_per_second_per_gpu:883.9551990267896
Step 4636 | loss:1.3098596334457397 lr:4.343670236911444e-06 tokens_per_second_per_gpu:887.5540846506027
Step 4637 | loss:1.2304856777191162 lr:4.3339353303945735e-06 tokens_per_second_per_gpu:844.202763741953
Step 4638 | loss:1.3612935543060303 lr:4.32421062488432e-06 tokens_per_second_per_gpu:756.7396654611133
Step 4639 | loss:1.4429770708084106 lr:4.31449612361562e-06 tokens_per_second_per_gpu:821.597414300768
Step 4640 | loss:1.2940691709518433 lr:4.3047918298199505e-06 tokens_per_second_per_gpu:880.4159824174728
Step 4641 | loss:1.3994957208633423 lr:4.295097746725456e-06 tokens_per_second_per_gpu:677.5790305446778
Step 4642 | loss:1.4944179058074951 lr:4.2854138775568385e-06 tokens_per_second_per_gpu:728.2936904679083
Step 4643 | loss:1.2556017637252808 lr:4.27574022553542e-06 tokens_per_second_per_gpu:1116.0005775976247
Step 4644 | loss:1.442574143409729 lr:4.2660767938791276e-06 tokens_per_second_per_gpu:936.0030280944507
Step 4645 | loss:1.384005069732666 lr:4.256423585802476e-06 tokens_per_second_per_gpu:859.488427992448
Step 4646 | loss:1.4944684505462646 lr:4.2467806045165835e-06 tokens_per_second_per_gpu:882.986039740944
Step 4647 | loss:1.528760313987732 lr:4.2371478532291905e-06 tokens_per_second_per_gpu:961.6098910304249
Step 4648 | loss:1.33395516872406 lr:4.227525335144579e-06 tokens_per_second_per_gpu:1212.074565033496
Step 4649 | loss:1.2090957164764404 lr:4.217913053463695e-06 tokens_per_second_per_gpu:798.6826837598766
Step 4650 | loss:1.3163992166519165 lr:4.208311011384016e-06 tokens_per_second_per_gpu:844.3910349684792
Step 4651 | loss:1.447986125946045 lr:4.1987192120996695e-06 tokens_per_second_per_gpu:860.3039504701677
Step 4652 | loss:1.2312942743301392 lr:4.189137658801319e-06 tokens_per_second_per_gpu:1178.071073940944
Step 4653 | loss:1.3776905536651611 lr:4.179566354676277e-06 tokens_per_second_per_gpu:997.5542671105025
Step 4654 | loss:1.4009226560592651 lr:4.170005302908405e-06 tokens_per_second_per_gpu:772.0212107844256
Step 4655 | loss:1.224316120147705 lr:4.160454506678171e-06 tokens_per_second_per_gpu:1047.2224598531443
Step 4656 | loss:1.2642009258270264 lr:4.1509139691626275e-06 tokens_per_second_per_gpu:802.7441767534877
Step 4657 | loss:1.2388800382614136 lr:4.1413836935354204e-06 tokens_per_second_per_gpu:1067.742489449961
Step 4658 | loss:1.4184306859970093 lr:4.131863682966764e-06 tokens_per_second_per_gpu:635.5240063678656
Step 4659 | loss:1.3464051485061646 lr:4.122353940623495e-06 tokens_per_second_per_gpu:811.7649269246924
Step 4660 | loss:1.5103176832199097 lr:4.112854469668985e-06 tokens_per_second_per_gpu:760.7305531511076
Step 4661 | loss:1.4210143089294434 lr:4.10336527326324e-06 tokens_per_second_per_gpu:929.2650498105198
Step 4662 | loss:1.3250718116760254 lr:4.093886354562793e-06 tokens_per_second_per_gpu:725.750288979725
Step 4663 | loss:1.354579210281372 lr:4.084417716720822e-06 tokens_per_second_per_gpu:722.8178120756891
Step 4664 | loss:1.4047619104385376 lr:4.074959362887013e-06 tokens_per_second_per_gpu:709.6875721701136
Step 4665 | loss:1.3582875728607178 lr:4.065511296207701e-06 tokens_per_second_per_gpu:1000.4866580417652
Step 4666 | loss:1.1884065866470337 lr:4.056073519825752e-06 tokens_per_second_per_gpu:1091.496831655615
Step 4667 | loss:1.4076964855194092 lr:4.046646036880626e-06 tokens_per_second_per_gpu:815.6679822145052
Step 4668 | loss:1.1648939847946167 lr:4.037228850508361e-06 tokens_per_second_per_gpu:1326.249772500124
Step 4669 | loss:1.453359842300415 lr:4.0278219638415585e-06 tokens_per_second_per_gpu:830.2733584918202
Step 4670 | loss:1.352917194366455 lr:4.018425380009405e-06 tokens_per_second_per_gpu:846.9985317648042
Step 4671 | loss:1.3657304048538208 lr:4.009039102137657e-06 tokens_per_second_per_gpu:888.7682684676557
Step 4672 | loss:1.259004831314087 lr:3.999663133348639e-06 tokens_per_second_per_gpu:937.4400649856707
Step 4673 | loss:1.432522177696228 lr:3.990297476761247e-06 tokens_per_second_per_gpu:952.4590483491395
Step 4674 | loss:1.35518217086792 lr:3.980942135490955e-06 tokens_per_second_per_gpu:1020.4635173697629
Step 4675 | loss:1.243735432624817 lr:3.971597112649796e-06 tokens_per_second_per_gpu:1073.9838087911705
Step 4676 | loss:1.2100605964660645 lr:3.962262411346367e-06 tokens_per_second_per_gpu:894.0607811721296
Step 4677 | loss:1.3591244220733643 lr:3.952938034685842e-06 tokens_per_second_per_gpu:867.0224922175903
Step 4678 | loss:1.3351088762283325 lr:3.9436239857699715e-06 tokens_per_second_per_gpu:745.3514087655067
Step 4679 | loss:1.4068230390548706 lr:3.934320267697028e-06 tokens_per_second_per_gpu:837.6741343840581
Step 4680 | loss:1.2453252077102661 lr:3.925026883561905e-06 tokens_per_second_per_gpu:974.1418505643761
Step 4681 | loss:1.2971391677856445 lr:3.915743836455998e-06 tokens_per_second_per_gpu:818.549888700347
Step 4682 | loss:1.2774006128311157 lr:3.906471129467321e-06 tokens_per_second_per_gpu:842.0902389422947
Step 4683 | loss:1.3748074769973755 lr:3.897208765680409e-06 tokens_per_second_per_gpu:876.687783937346
Step 4684 | loss:1.245181679725647 lr:3.887956748176371e-06 tokens_per_second_per_gpu:1158.8913874436946
Step 4685 | loss:1.4401034116744995 lr:3.8787150800328745e-06 tokens_per_second_per_gpu:675.9977755726675
Step 4686 | loss:1.4591833353042603 lr:3.8694837643241374e-06 tokens_per_second_per_gpu:752.2958361903711
Step 4687 | loss:1.382610559463501 lr:3.8602628041209464e-06 tokens_per_second_per_gpu:992.9776801618253
Step 4688 | loss:1.3013803958892822 lr:3.851052202490631e-06 tokens_per_second_per_gpu:822.2941857236693
Step 4689 | loss:1.4544174671173096 lr:3.841851962497071e-06 tokens_per_second_per_gpu:1016.2151462308882
Step 4690 | loss:1.3689707517623901 lr:3.832662087200733e-06 tokens_per_second_per_gpu:967.5324056362277
Step 4691 | loss:1.387812852859497 lr:3.823482579658583e-06 tokens_per_second_per_gpu:599.6489210317997
Step 4692 | loss:1.2257689237594604 lr:3.814313442924193e-06 tokens_per_second_per_gpu:864.5212786051547
Step 4693 | loss:1.3700942993164062 lr:3.8051546800476333e-06 tokens_per_second_per_gpu:733.4968010081639
Step 4694 | loss:1.5553481578826904 lr:3.7960062940755705e-06 tokens_per_second_per_gpu:809.7885159380472
Step 4695 | loss:1.325278401374817 lr:3.786868288051176e-06 tokens_per_second_per_gpu:886.2234428122824
Step 4696 | loss:1.3807545900344849 lr:3.7777406650142067e-06 tokens_per_second_per_gpu:786.8552851670345
Step 4697 | loss:1.2450141906738281 lr:3.768623428000942e-06 tokens_per_second_per_gpu:1041.2113922634328
Step 4698 | loss:1.24735426902771 lr:3.759516580044214e-06 tokens_per_second_per_gpu:1114.7516180469138
Step 4699 | loss:1.465383529663086 lr:3.750420124173397e-06 tokens_per_second_per_gpu:1028.7362147347546
Step 4700 | loss:1.1526681184768677 lr:3.7413340634144097e-06 tokens_per_second_per_gpu:983.842828903126
Step 4701 | loss:1.2407808303833008 lr:3.732258400789706e-06 tokens_per_second_per_gpu:969.8640486833054
Step 4702 | loss:1.4529273509979248 lr:3.7231931393183086e-06 tokens_per_second_per_gpu:863.586412028052
Step 4703 | loss:1.327038049697876 lr:3.71413828201573e-06 tokens_per_second_per_gpu:830.7313920205524
Step 4704 | loss:1.3216581344604492 lr:3.70509383189408e-06 tokens_per_second_per_gpu:1110.8526728218606
Step 4705 | loss:1.3993176221847534 lr:3.6960597919619482e-06 tokens_per_second_per_gpu:826.1584592484634
Step 4706 | loss:1.3971070051193237 lr:3.687036165224519e-06 tokens_per_second_per_gpu:772.8528939602961
Step 4707 | loss:1.2971398830413818 lr:3.678022954683453e-06 tokens_per_second_per_gpu:656.4085275909154
Step 4708 | loss:1.242027997970581 lr:3.6690201633370064e-06 tokens_per_second_per_gpu:902.6923259968554
Step 4709 | loss:1.3419904708862305 lr:3.6600277941799237e-06 tokens_per_second_per_gpu:981.7251164781671
Step 4710 | loss:1.393924355506897 lr:3.651045850203506e-06 tokens_per_second_per_gpu:889.5172590743596
Step 4711 | loss:1.3722293376922607 lr:3.6420743343955725e-06 tokens_per_second_per_gpu:983.6025776700002
Step 4712 | loss:1.2161767482757568 lr:3.6331132497404886e-06 tokens_per_second_per_gpu:934.707715085718
Step 4713 | loss:1.2625313997268677 lr:3.624162599219137e-06 tokens_per_second_per_gpu:768.3965847440707
Step 4714 | loss:1.4758740663528442 lr:3.615222385808935e-06 tokens_per_second_per_gpu:549.2142237857088
Step 4715 | loss:1.3775306940078735 lr:3.606292612483819e-06 tokens_per_second_per_gpu:1055.2797086582646
Step 4716 | loss:1.316325068473816 lr:3.5973732822142844e-06 tokens_per_second_per_gpu:886.5519561436822
Step 4717 | loss:1.1127110719680786 lr:3.5884643979672963e-06 tokens_per_second_per_gpu:1280.711748782773
Step 4718 | loss:1.1979033946990967 lr:3.579565962706411e-06 tokens_per_second_per_gpu:1122.418465400558
Step 4719 | loss:1.2959792613983154 lr:3.5706779793916416e-06 tokens_per_second_per_gpu:839.7373168114432
Step 4720 | loss:1.1798902750015259 lr:3.5618004509795895e-06 tokens_per_second_per_gpu:846.5973967407957
Step 4721 | loss:1.3317817449569702 lr:3.552933380423331e-06 tokens_per_second_per_gpu:1002.1451464410961
Step 4722 | loss:1.388283371925354 lr:3.5440767706724797e-06 tokens_per_second_per_gpu:1130.4489604206017
Step 4723 | loss:1.3595479726791382 lr:3.5352306246731737e-06 tokens_per_second_per_gpu:900.1211114286643
Step 4724 | loss:1.3232786655426025 lr:3.526394945368067e-06 tokens_per_second_per_gpu:826.9403034153174
Step 4725 | loss:1.2379844188690186 lr:3.51756973569633e-06 tokens_per_second_per_gpu:765.2130418586177
Step 4726 | loss:1.5070934295654297 lr:3.5087549985936496e-06 tokens_per_second_per_gpu:649.8834199458286
Step 4727 | loss:1.3440991640090942 lr:3.4999507369922288e-06 tokens_per_second_per_gpu:1016.9689574265349
Step 4728 | loss:1.4854401350021362 lr:3.491156953820795e-06 tokens_per_second_per_gpu:883.9160984401292
Step 4729 | loss:1.2790336608886719 lr:3.4823736520045804e-06 tokens_per_second_per_gpu:794.5502500406466
Step 4730 | loss:1.1937789916992188 lr:3.4736008344653298e-06 tokens_per_second_per_gpu:1473.8286567826917
Step 4731 | loss:1.368129014968872 lr:3.4648385041213038e-06 tokens_per_second_per_gpu:929.1611378787709
Step 4732 | loss:1.2724332809448242 lr:3.456086663887273e-06 tokens_per_second_per_gpu:975.734855519997
Step 4733 | loss:1.2257860898971558 lr:3.44734531667453e-06 tokens_per_second_per_gpu:910.1048245142176
Step 4734 | loss:1.2520064115524292 lr:3.438614465390863e-06 tokens_per_second_per_gpu:932.9460007181341
Step 4735 | loss:1.3680293560028076 lr:3.4298941129405668e-06 tokens_per_second_per_gpu:939.2368380471156
Step 4736 | loss:1.3293131589889526 lr:3.4211842622244534e-06 tokens_per_second_per_gpu:992.6194520687536
Step 4737 | loss:1.441721796989441 lr:3.4124849161398395e-06 tokens_per_second_per_gpu:965.432873709256
Step 4738 | loss:1.46104097366333 lr:3.403796077580543e-06 tokens_per_second_per_gpu:949.758272708675
Step 4739 | loss:1.3551466464996338 lr:3.3951177494368892e-06 tokens_per_second_per_gpu:846.8463180176036
Step 4740 | loss:1.3201576471328735 lr:3.38644993459571e-06 tokens_per_second_per_gpu:1047.7795700610184
Step 4741 | loss:1.4147891998291016 lr:3.377792635940333e-06 tokens_per_second_per_gpu:800.1185442260622
Step 4742 | loss:1.250678300857544 lr:3.3691458563505945e-06 tokens_per_second_per_gpu:756.9646778131294
Step 4743 | loss:1.201696753501892 lr:3.360509598702824e-06 tokens_per_second_per_gpu:835.253418938562
Step 4744 | loss:1.3225386142730713 lr:3.351883865869864e-06 tokens_per_second_per_gpu:776.5378966993459
Step 4745 | loss:1.252016544342041 lr:3.343268660721042e-06 tokens_per_second_per_gpu:736.9240335095453
Step 4746 | loss:1.3977141380310059 lr:3.334663986122182e-06 tokens_per_second_per_gpu:772.5621985580188
Step 4747 | loss:1.4261980056762695 lr:3.326069844935636e-06 tokens_per_second_per_gpu:923.1243300677676
Step 4748 | loss:1.1443240642547607 lr:3.3174862400202e-06 tokens_per_second_per_gpu:821.6311101545124
Step 4749 | loss:1.2576615810394287 lr:3.3089131742312158e-06 tokens_per_second_per_gpu:912.3772175134129
Step 4750 | loss:1.416785478591919 lr:3.300350650420481e-06 tokens_per_second_per_gpu:1290.5923912758706
Step 4751 | loss:1.3131569623947144 lr:3.291798671436311e-06 tokens_per_second_per_gpu:711.7272895554472
Step 4752 | loss:1.2908034324645996 lr:3.283257240123502e-06 tokens_per_second_per_gpu:850.788591425706
Step 4753 | loss:1.2469085454940796 lr:3.2747263593233482e-06 tokens_per_second_per_gpu:915.24027553291
Step 4754 | loss:1.3487107753753662 lr:3.2662060318736274e-06 tokens_per_second_per_gpu:885.9335765472288
Step 4755 | loss:1.4164986610412598 lr:3.257696260608612e-06 tokens_per_second_per_gpu:974.4685857801455
Step 4756 | loss:1.3308277130126953 lr:3.249197048359059e-06 tokens_per_second_per_gpu:764.8392802787902
Step 4757 | loss:1.2499215602874756 lr:3.240708397952211e-06 tokens_per_second_per_gpu:1026.8061863802302
Step 4758 | loss:1.2922836542129517 lr:3.2322303122118036e-06 tokens_per_second_per_gpu:782.0707645448898
Step 4759 | loss:1.3079395294189453 lr:3.223762793958066e-06 tokens_per_second_per_gpu:776.3501254883754
Step 4760 | loss:1.4054245948791504 lr:3.215305846007679e-06 tokens_per_second_per_gpu:883.5136818684939
Step 4761 | loss:1.2921833992004395 lr:3.20685947117386e-06 tokens_per_second_per_gpu:978.6630467797565
Step 4762 | loss:1.3918133974075317 lr:3.1984236722662488e-06 tokens_per_second_per_gpu:836.0115440125237
Step 4763 | loss:1.2823028564453125 lr:3.1899984520910165e-06 tokens_per_second_per_gpu:647.6552799527927
Step 4764 | loss:1.5272538661956787 lr:3.1815838134507903e-06 tokens_per_second_per_gpu:635.6218280043378
Step 4765 | loss:1.4424724578857422 lr:3.1731797591446846e-06 tokens_per_second_per_gpu:900.153474659682
Step 4766 | loss:1.2470427751541138 lr:3.1647862919682888e-06 tokens_per_second_per_gpu:1069.6155024498648
Step 4767 | loss:1.434568166732788 lr:3.15640341471368e-06 tokens_per_second_per_gpu:660.5245240673529
Step 4768 | loss:1.4856376647949219 lr:3.1480311301693962e-06 tokens_per_second_per_gpu:716.7956186687821
Step 4769 | loss:1.3143247365951538 lr:3.1396694411204724e-06 tokens_per_second_per_gpu:812.0002315977738
Step 4770 | loss:1.3346461057662964 lr:3.13131835034839e-06 tokens_per_second_per_gpu:1091.1780104246534
Step 4771 | loss:1.3189265727996826 lr:3.122977860631152e-06 tokens_per_second_per_gpu:942.7907078909536
Step 4772 | loss:1.3461532592773438 lr:3.1146479747431774e-06 tokens_per_second_per_gpu:1074.3863622495246
Step 4773 | loss:1.2177006006240845 lr:3.1063286954554134e-06 tokens_per_second_per_gpu:1003.7488727915928
Step 4774 | loss:1.4094126224517822 lr:3.0980200255352193e-06 tokens_per_second_per_gpu:700.8913232839517
Step 4775 | loss:1.2837190628051758 lr:3.089721967746485e-06 tokens_per_second_per_gpu:775.0991490871547
Step 4776 | loss:1.202677607536316 lr:3.081434524849537e-06 tokens_per_second_per_gpu:1172.6447930671093
Step 4777 | loss:1.2662675380706787 lr:3.073157699601173e-06 tokens_per_second_per_gpu:843.4038739827565
Step 4778 | loss:1.2418410778045654 lr:3.064891494754663e-06 tokens_per_second_per_gpu:1393.674252102816
Step 4779 | loss:1.3789881467819214 lr:3.0566359130597453e-06 tokens_per_second_per_gpu:835.8618339771945
Step 4780 | loss:1.3585255146026611 lr:3.0483909572626243e-06 tokens_per_second_per_gpu:810.8690270284839
Step 4781 | loss:1.2973518371582031 lr:3.0401566301059623e-06 tokens_per_second_per_gpu:931.4009556959868
Step 4782 | loss:1.4593435525894165 lr:3.0319329343289e-06 tokens_per_second_per_gpu:622.9535879164806
Step 4783 | loss:1.3415513038635254 lr:3.0237198726670313e-06 tokens_per_second_per_gpu:827.0407248104736
Step 4784 | loss:1.344678521156311 lr:3.0155174478524176e-06 tokens_per_second_per_gpu:927.2627028472742
Step 4785 | loss:1.3164948225021362 lr:3.0073256626135717e-06 tokens_per_second_per_gpu:1095.955992412007
Step 4786 | loss:1.1850264072418213 lr:2.9991445196754754e-06 tokens_per_second_per_gpu:693.1194829466019
Step 4787 | loss:1.2034106254577637 lr:2.9909740217595856e-06 tokens_per_second_per_gpu:1382.8215445165488
Step 4788 | loss:1.3045475482940674 lr:2.9828141715837805e-06 tokens_per_second_per_gpu:1063.0472136369171
Step 4789 | loss:1.189574956893921 lr:2.9746649718624335e-06 tokens_per_second_per_gpu:1097.2922880225806
Step 4790 | loss:1.2553000450134277 lr:2.9665264253063535e-06 tokens_per_second_per_gpu:803.1815097763288
Step 4791 | loss:1.3133796453475952 lr:2.9583985346228194e-06 tokens_per_second_per_gpu:827.8487060299053
Step 4792 | loss:1.32562255859375 lr:2.9502813025155492e-06 tokens_per_second_per_gpu:747.1021297754181
Step 4793 | loss:1.4024090766906738 lr:2.942174731684729e-06 tokens_per_second_per_gpu:975.5181132218197
Step 4794 | loss:1.2786216735839844 lr:2.9340788248269933e-06 tokens_per_second_per_gpu:734.8596491899547
Step 4795 | loss:1.128461480140686 lr:2.925993584635429e-06 tokens_per_second_per_gpu:968.1378563634134
Step 4796 | loss:1.3582634925842285 lr:2.917919013799579e-06 tokens_per_second_per_gpu:1035.9245067670095
Step 4797 | loss:1.3218621015548706 lr:2.909855115005427e-06 tokens_per_second_per_gpu:950.8308989402451
Step 4798 | loss:1.3005399703979492 lr:2.9018018909354172e-06 tokens_per_second_per_gpu:797.740252326897
Step 4799 | loss:1.4411762952804565 lr:2.8937593442684375e-06 tokens_per_second_per_gpu:769.4671476572171
Step 4800 | loss:1.1766884326934814 lr:2.8857274776798246e-06 tokens_per_second_per_gpu:1403.9679881006593
Step 4801 | loss:1.4201695919036865 lr:2.877706293841363e-06 tokens_per_second_per_gpu:734.075746239187
Step 4802 | loss:1.3200892210006714 lr:2.8696957954212946e-06 tokens_per_second_per_gpu:1057.2750845439996
Step 4803 | loss:1.3951960802078247 lr:2.8616959850842775e-06 tokens_per_second_per_gpu:697.2924580038756
Step 4804 | loss:1.3818339109420776 lr:2.8537068654914537e-06 tokens_per_second_per_gpu:1095.681057158773
Step 4805 | loss:1.3112411499023438 lr:2.8457284393003664e-06 tokens_per_second_per_gpu:1030.8759290902665
Step 4806 | loss:1.365051031112671 lr:2.8377607091650357e-06 tokens_per_second_per_gpu:935.3798276367611
Step 4807 | loss:1.3027757406234741 lr:2.8298036777359167e-06 tokens_per_second_per_gpu:1141.4148916001993
Step 4808 | loss:1.3420604467391968 lr:2.821857347659891e-06 tokens_per_second_per_gpu:746.8009598416313
Step 4809 | loss:1.2193480730056763 lr:2.813921721580292e-06 tokens_per_second_per_gpu:1198.3702856586976
Step 4810 | loss:1.341788649559021 lr:2.805996802136889e-06 tokens_per_second_per_gpu:822.8094405261091
Step 4811 | loss:1.4111449718475342 lr:2.798082591965897e-06 tokens_per_second_per_gpu:746.9362645713925
Step 4812 | loss:1.34065842628479 lr:2.790179093699956e-06 tokens_per_second_per_gpu:1012.6912925475689
Step 4813 | loss:1.4626823663711548 lr:2.782286309968146e-06 tokens_per_second_per_gpu:923.5558785569922
Step 4814 | loss:1.3268967866897583 lr:2.774404243396004e-06 tokens_per_second_per_gpu:1014.5257375568857
Step 4815 | loss:1.2766581773757935 lr:2.7665328966054596e-06 tokens_per_second_per_gpu:863.3933247211824
Step 4816 | loss:1.1824030876159668 lr:2.7586722722149267e-06 tokens_per_second_per_gpu:934.7607491243976
Step 4817 | loss:1.28495454788208 lr:2.750822372839202e-06 tokens_per_second_per_gpu:855.5496566254429
Step 4818 | loss:1.3350087404251099 lr:2.742983201089561e-06 tokens_per_second_per_gpu:834.7578909268697
Step 4819 | loss:1.4893596172332764 lr:2.7351547595736687e-06 tokens_per_second_per_gpu:715.8878700088173
Step 4820 | loss:1.3677408695220947 lr:2.7273370508956523e-06 tokens_per_second_per_gpu:842.4447534047927
Step 4821 | loss:1.2237943410873413 lr:2.7195300776560614e-06 tokens_per_second_per_gpu:958.0694192834119
Step 4822 | loss:1.4017173051834106 lr:2.7117338424518607e-06 tokens_per_second_per_gpu:759.9587930625313
Step 4823 | loss:1.301605224609375 lr:2.7039483478764557e-06 tokens_per_second_per_gpu:1086.5701110582847
Step 4824 | loss:1.4008619785308838 lr:2.6961735965196798e-06 tokens_per_second_per_gpu:625.4444719498558
Step 4825 | loss:1.2471987009048462 lr:2.68840959096778e-06 tokens_per_second_per_gpu:1016.4158290131835
Step 4826 | loss:1.2834175825119019 lr:2.6806563338034564e-06 tokens_per_second_per_gpu:813.1849755135495
Step 4827 | loss:1.3005483150482178 lr:2.672913827605787e-06 tokens_per_second_per_gpu:785.2783675688348
Step 4828 | loss:1.3159701824188232 lr:2.6651820749503294e-06 tokens_per_second_per_gpu:867.92381591668
Step 4829 | loss:1.4255090951919556 lr:2.6574610784090115e-06 tokens_per_second_per_gpu:1015.3699458658235
Step 4830 | loss:1.391532063484192 lr:2.649750840550234e-06 tokens_per_second_per_gpu:735.1093836689064
Step 4831 | loss:1.418577790260315 lr:2.6420513639387623e-06 tokens_per_second_per_gpu:598.3477608068579
Step 4832 | loss:1.2343460321426392 lr:2.6343626511358364e-06 tokens_per_second_per_gpu:1022.8960569312596
Step 4833 | loss:1.3333938121795654 lr:2.6266847046990836e-06 tokens_per_second_per_gpu:1049.9355765765815
Step 4834 | loss:1.3804799318313599 lr:2.619017527182558e-06 tokens_per_second_per_gpu:789.1596863962067
Step 4835 | loss:1.3795896768569946 lr:2.6113611211367268e-06 tokens_per_second_per_gpu:842.3108852416049
Step 4836 | loss:1.3904051780700684 lr:2.603715489108486e-06 tokens_per_second_per_gpu:797.8605756880976
Step 4837 | loss:1.47179114818573 lr:2.5960806336411294e-06 tokens_per_second_per_gpu:639.3466324403522
Step 4838 | loss:1.3326537609100342 lr:2.588456557274395e-06 tokens_per_second_per_gpu:860.6714728987164
Step 4839 | loss:1.1371469497680664 lr:2.580843262544393e-06 tokens_per_second_per_gpu:917.2430934729838
Step 4840 | loss:1.3858814239501953 lr:2.5732407519836995e-06 tokens_per_second_per_gpu:762.7258927923092
Step 4841 | loss:1.3898977041244507 lr:2.5656490281212464e-06 tokens_per_second_per_gpu:833.7958163581887
Step 4842 | loss:1.407186508178711 lr:2.5580680934824267e-06 tokens_per_second_per_gpu:742.5668792497507
Step 4843 | loss:1.3353806734085083 lr:2.550497950589006e-06 tokens_per_second_per_gpu:925.0858600644926
Step 4844 | loss:1.314766526222229 lr:2.542938601959196e-06 tokens_per_second_per_gpu:829.7051185861658
Step 4845 | loss:1.369314432144165 lr:2.5353900501075868e-06 tokens_per_second_per_gpu:826.5408921959838
Step 4846 | loss:1.466792106628418 lr:2.5278522975451966e-06 tokens_per_second_per_gpu:930.4154191014018
Step 4847 | loss:1.48838472366333 lr:2.5203253467794377e-06 tokens_per_second_per_gpu:577.079919874431
Step 4848 | loss:1.396216869354248 lr:2.51280920031414e-06 tokens_per_second_per_gpu:1047.3608813334226
Step 4849 | loss:1.2966923713684082 lr:2.5053038606495324e-06 tokens_per_second_per_gpu:872.3954818339292
Step 4850 | loss:1.3758851289749146 lr:2.497809330282251e-06 tokens_per_second_per_gpu:906.8067477381909
Step 4851 | loss:1.2558239698410034 lr:2.4903256117053395e-06 tokens_per_second_per_gpu:940.3652370290589
Step 4852 | loss:1.1897591352462769 lr:2.482852707408242e-06 tokens_per_second_per_gpu:1151.5310935890288
Step 4853 | loss:1.3156116008758545 lr:2.4753906198768057e-06 tokens_per_second_per_gpu:1011.0406528111976
Step 4854 | loss:1.3911352157592773 lr:2.467939351593275e-06 tokens_per_second_per_gpu:776.474605057117
Step 4855 | loss:1.3869588375091553 lr:2.4604989050363074e-06 tokens_per_second_per_gpu:913.7692253293451
Step 4856 | loss:1.304664969444275 lr:2.453069282680939e-06 tokens_per_second_per_gpu:927.6913493143591
Step 4857 | loss:1.3078222274780273 lr:2.4456504869986433e-06 tokens_per_second_per_gpu:684.3659649582133
Step 4858 | loss:1.3830151557922363 lr:2.4382425204572405e-06 tokens_per_second_per_gpu:672.4241705662422
Step 4859 | loss:1.2925440073013306 lr:2.430845385521003e-06 tokens_per_second_per_gpu:873.1932492569052
Step 4860 | loss:1.3615895509719849 lr:2.4234590846505437e-06 tokens_per_second_per_gpu:875.267033848695
Step 4861 | loss:1.4893240928649902 lr:2.4160836203029264e-06 tokens_per_second_per_gpu:640.8623013074538
Step 4862 | loss:1.2701056003570557 lr:2.4087189949315753e-06 tokens_per_second_per_gpu:936.5272666245291
Step 4863 | loss:1.3014235496520996 lr:2.4013652109863235e-06 tokens_per_second_per_gpu:1205.1960246678755
Step 4864 | loss:1.4235057830810547 lr:2.3940222709133823e-06 tokens_per_second_per_gpu:610.0417315102069
Step 4865 | loss:1.3951305150985718 lr:2.3866901771553765e-06 tokens_per_second_per_gpu:660.1245084748817
Step 4866 | loss:1.2841744422912598 lr:2.379368932151306e-06 tokens_per_second_per_gpu:1013.5892544609721
Step 4867 | loss:1.2362926006317139 lr:2.372058538336576e-06 tokens_per_second_per_gpu:959.1116214833448
Step 4868 | loss:1.2347030639648438 lr:2.364758998142962e-06 tokens_per_second_per_gpu:882.7291315097996
Step 4869 | loss:1.2519588470458984 lr:2.3574703139986617e-06 tokens_per_second_per_gpu:943.4551629625134
Step 4870 | loss:1.478872537612915 lr:2.350192488328219e-06 tokens_per_second_per_gpu:632.7018402178261
Step 4871 | loss:1.2213444709777832 lr:2.342925523552612e-06 tokens_per_second_per_gpu:1013.5094457272439
Step 4872 | loss:1.208709478378296 lr:2.3356694220891563e-06 tokens_per_second_per_gpu:909.7075128135798
Step 4873 | loss:1.425706386566162 lr:2.3284241863516066e-06 tokens_per_second_per_gpu:944.11272933439
Step 4874 | loss:1.3785191774368286 lr:2.321189818750056e-06 tokens_per_second_per_gpu:720.6648317466351
Step 4875 | loss:1.3468588590621948 lr:2.313966321691011e-06 tokens_per_second_per_gpu:1064.599284321972
Step 4876 | loss:1.4068423509597778 lr:2.3067536975773526e-06 tokens_per_second_per_gpu:869.0511053999317
Step 4877 | loss:1.4564380645751953 lr:2.2995519488083487e-06 tokens_per_second_per_gpu:836.3081633504161
Step 4878 | loss:1.392979383468628 lr:2.2923610777796447e-06 tokens_per_second_per_gpu:780.8094251095799
Step 4879 | loss:1.230446696281433 lr:2.285181086883273e-06 tokens_per_second_per_gpu:965.4973642919192
Step 4880 | loss:1.2994582653045654 lr:2.278011978507629e-06 tokens_per_second_per_gpu:786.6412747954813
Step 4881 | loss:1.2790453433990479 lr:2.2708537550375284e-06 tokens_per_second_per_gpu:956.9493452135239
Step 4882 | loss:1.2509336471557617 lr:2.2637064188541152e-06 tokens_per_second_per_gpu:1301.6143688656493
Step 4883 | loss:1.353484034538269 lr:2.2565699723349596e-06 tokens_per_second_per_gpu:742.432401950004
Step 4884 | loss:1.2921056747436523 lr:2.2494444178539656e-06 tokens_per_second_per_gpu:866.2528656832937
Step 4885 | loss:1.2367064952850342 lr:2.242329757781452e-06 tokens_per_second_per_gpu:1178.88765500564
Step 4886 | loss:1.2924606800079346 lr:2.2352259944840766e-06 tokens_per_second_per_gpu:797.0084353293751
Step 4887 | loss:1.2630280256271362 lr:2.228133130324915e-06 tokens_per_second_per_gpu:983.0656049448254
Step 4888 | loss:1.4617189168930054 lr:2.221051167663382e-06 tokens_per_second_per_gpu:797.0984810322993
Step 4889 | loss:1.364759922027588 lr:2.213980108855278e-06 tokens_per_second_per_gpu:984.5282460700556
Step 4890 | loss:1.4359476566314697 lr:2.206919956252784e-06 tokens_per_second_per_gpu:1017.7023206698175
Step 4891 | loss:1.3918087482452393 lr:2.199870712204441e-06 tokens_per_second_per_gpu:727.4032722770847
Step 4892 | loss:1.3287856578826904 lr:2.192832379055167e-06 tokens_per_second_per_gpu:1075.6046950628765
Step 4893 | loss:1.3778973817825317 lr:2.1858049591462493e-06 tokens_per_second_per_gpu:1014.6326129126519
Step 4894 | loss:1.4020709991455078 lr:2.1787884548153387e-06 tokens_per_second_per_gpu:830.4776143524925
Step 4895 | loss:1.3508890867233276 lr:2.171782868396484e-06 tokens_per_second_per_gpu:784.9268936300624
Step 4896 | loss:1.2054502964019775 lr:2.164788202220053e-06 tokens_per_second_per_gpu:970.0397236513822
Step 4897 | loss:1.3080127239227295 lr:2.1578044586128285e-06 tokens_per_second_per_gpu:986.0303483041215
Step 4898 | loss:1.2278271913528442 lr:2.1508316398979205e-06 tokens_per_second_per_gpu:976.0979641175527
Step 4899 | loss:1.1737213134765625 lr:2.1438697483948405e-06 tokens_per_second_per_gpu:1390.026340259451
Step 4900 | loss:1.2851207256317139 lr:2.1369187864194397e-06 tokens_per_second_per_gpu:996.7735530280555
Step 4901 | loss:1.3704477548599243 lr:2.129978756283945e-06 tokens_per_second_per_gpu:720.1814757249847
Step 4902 | loss:1.41056227684021 lr:2.1230496602969405e-06 tokens_per_second_per_gpu:918.4597637531675
Step 4903 | loss:1.2311558723449707 lr:2.116131500763378e-06 tokens_per_second_per_gpu:1029.827558998002
Step 4904 | loss:1.3301498889923096 lr:2.109224279984573e-06 tokens_per_second_per_gpu:839.5934165083974
Step 4905 | loss:1.2698888778686523 lr:2.102328000258191e-06 tokens_per_second_per_gpu:948.4115131393704
Step 4906 | loss:1.21847665309906 lr:2.0954426638782763e-06 tokens_per_second_per_gpu:972.3420502679592
Step 4907 | loss:1.102419137954712 lr:2.0885682731352167e-06 tokens_per_second_per_gpu:1015.2347538228476
Step 4908 | loss:1.3683397769927979 lr:2.081704830315763e-06 tokens_per_second_per_gpu:1097.4052500295568
Step 4909 | loss:1.4746782779693604 lr:2.074852337703033e-06 tokens_per_second_per_gpu:699.7118088331063
Step 4910 | loss:1.418513298034668 lr:2.0680107975764877e-06 tokens_per_second_per_gpu:989.988140305388
Step 4911 | loss:1.2562085390090942 lr:2.061180212211951e-06 tokens_per_second_per_gpu:1149.4323001819068
Step 4912 | loss:1.429162621498108 lr:2.0543605838816097e-06 tokens_per_second_per_gpu:933.3517899176928
Step 4913 | loss:1.4322670698165894 lr:2.047551914854002e-06 tokens_per_second_per_gpu:780.9362465317578
Step 4914 | loss:1.2563756704330444 lr:2.0407542073940135e-06 tokens_per_second_per_gpu:1092.600632418077
Step 4915 | loss:1.2161521911621094 lr:2.033967463762889e-06 tokens_per_second_per_gpu:1259.3347454905625
Step 4916 | loss:1.4352984428405762 lr:2.0271916862182274e-06 tokens_per_second_per_gpu:568.1519447841247
Step 4917 | loss:1.3135546445846558 lr:2.0204268770139766e-06 tokens_per_second_per_gpu:1022.288104178466
Step 4918 | loss:1.217408299446106 lr:2.013673038400434e-06 tokens_per_second_per_gpu:1035.0911508273343
Step 4919 | loss:1.4552390575408936 lr:2.0069301726242578e-06 tokens_per_second_per_gpu:726.4692268624295
Step 4920 | loss:1.5903987884521484 lr:2.000198281928444e-06 tokens_per_second_per_gpu:848.6560293085756
Step 4921 | loss:1.4303628206253052 lr:1.9934773685523414e-06 tokens_per_second_per_gpu:979.3545632283084
Step 4922 | loss:1.4453237056732178 lr:1.986767434731653e-06 tokens_per_second_per_gpu:657.4192528620644
Step 4923 | loss:1.3986701965332031 lr:1.980068482698418e-06 tokens_per_second_per_gpu:628.7907593327725
Step 4924 | loss:1.439198613166809 lr:1.973380514681046e-06 tokens_per_second_per_gpu:860.9079705576823
Step 4925 | loss:1.2740681171417236 lr:1.9667035329042554e-06 tokens_per_second_per_gpu:1015.0636907552455
Step 4926 | loss:1.5936133861541748 lr:1.960037539589154e-06 tokens_per_second_per_gpu:653.5617973466366
Step 4927 | loss:1.2887157201766968 lr:1.953382536953147e-06 tokens_per_second_per_gpu:988.7588703658687
Step 4928 | loss:1.4015636444091797 lr:1.94673852721003e-06 tokens_per_second_per_gpu:938.9404068901847
Step 4929 | loss:1.3133200407028198 lr:1.9401055125699028e-06 tokens_per_second_per_gpu:812.7955080858435
Step 4930 | loss:1.5496386289596558 lr:1.933483495239232e-06 tokens_per_second_per_gpu:909.3166676710613
Step 4931 | loss:1.350677490234375 lr:1.926872477420824e-06 tokens_per_second_per_gpu:817.967444947217
Step 4932 | loss:1.5046042203903198 lr:1.9202724613138126e-06 tokens_per_second_per_gpu:612.1580458467807
Step 4933 | loss:1.3616667985916138 lr:1.9136834491136837e-06 tokens_per_second_per_gpu:844.8633226216482
Step 4934 | loss:1.3862876892089844 lr:1.9071054430122624e-06 tokens_per_second_per_gpu:928.1644278651672
Step 4935 | loss:1.132616400718689 lr:1.9005384451977012e-06 tokens_per_second_per_gpu:1182.3802842761327
Step 4936 | loss:1.4042712450027466 lr:1.8939824578545088e-06 tokens_per_second_per_gpu:620.5256405049577
Step 4937 | loss:1.4053853750228882 lr:1.8874374831635092e-06 tokens_per_second_per_gpu:809.7081299091603
Step 4938 | loss:1.442352056503296 lr:1.8809035233018976e-06 tokens_per_second_per_gpu:654.059733082655
Step 4939 | loss:1.2744903564453125 lr:1.8743805804431544e-06 tokens_per_second_per_gpu:835.7940287726886
Step 4940 | loss:1.3180736303329468 lr:1.86786865675715e-06 tokens_per_second_per_gpu:1140.640508587599
Step 4941 | loss:1.348451018333435 lr:1.8613677544100398e-06 tokens_per_second_per_gpu:817.2384746893396
Step 4942 | loss:1.2497498989105225 lr:1.854877875564354e-06 tokens_per_second_per_gpu:939.3076293888361
Step 4943 | loss:1.268397331237793 lr:1.8483990223789352e-06 tokens_per_second_per_gpu:874.4778295932698
Step 4944 | loss:1.3120744228363037 lr:1.841931197008954e-06 tokens_per_second_per_gpu:883.9087931078793
Step 4945 | loss:1.2885161638259888 lr:1.8354744016059242e-06 tokens_per_second_per_gpu:856.330501018078
Step 4946 | loss:1.153973937034607 lr:1.8290286383176879e-06 tokens_per_second_per_gpu:959.6977561172323
Step 4947 | loss:1.3359841108322144 lr:1.8225939092884107e-06 tokens_per_second_per_gpu:874.4596449769306
Step 4948 | loss:1.336487054824829 lr:1.8161702166585984e-06 tokens_per_second_per_gpu:624.1194005459987
Step 4949 | loss:1.399992823600769 lr:1.8097575625650729e-06 tokens_per_second_per_gpu:691.0134035751698
Step 4950 | loss:1.341680884361267 lr:1.8033559491410032e-06 tokens_per_second_per_gpu:1112.392318053756
Step 4951 | loss:1.3209394216537476 lr:1.7969653785158554e-06 tokens_per_second_per_gpu:1040.3702556376504
Step 4952 | loss:1.2524701356887817 lr:1.7905858528154625e-06 tokens_per_second_per_gpu:669.499474748645
Step 4953 | loss:1.4073442220687866 lr:1.7842173741619386e-06 tokens_per_second_per_gpu:1052.9259170095352
Step 4954 | loss:1.3318692445755005 lr:1.7778599446737606e-06 tokens_per_second_per_gpu:764.9526908464022
Step 4955 | loss:1.4021964073181152 lr:1.7715135664657144e-06 tokens_per_second_per_gpu:879.1751234819645
Step 4956 | loss:1.2161773443222046 lr:1.7651782416489052e-06 tokens_per_second_per_gpu:947.1434971043109
Step 4957 | loss:1.2296440601348877 lr:1.7588539723307671e-06 tokens_per_second_per_gpu:1173.6270198820632
Step 4958 | loss:1.3995683193206787 lr:1.7525407606150577e-06 tokens_per_second_per_gpu:1137.7529490367954
Step 4959 | loss:1.4652849435806274 lr:1.746238608601851e-06 tokens_per_second_per_gpu:711.2850922357609
Step 4960 | loss:1.3971164226531982 lr:1.7399475183875528e-06 tokens_per_second_per_gpu:821.828439634766
Step 4961 | loss:1.3398418426513672 lr:1.7336674920648735e-06 tokens_per_second_per_gpu:734.4778236624802
Step 4962 | loss:1.3665105104446411 lr:1.7273985317228594e-06 tokens_per_second_per_gpu:814.270646507851
Step 4963 | loss:1.2905018329620361 lr:1.7211406394468574e-06 tokens_per_second_per_gpu:699.1018918858903
Step 4964 | loss:1.3991836309432983 lr:1.7148938173185617e-06 tokens_per_second_per_gpu:834.6274384262614
Step 4965 | loss:1.1877866983413696 lr:1.7086580674159439e-06 tokens_per_second_per_gpu:993.8867443400483
Step 4966 | loss:1.4555681943893433 lr:1.7024333918133309e-06 tokens_per_second_per_gpu:618.6290899366348
Step 4967 | loss:1.3292876482009888 lr:1.6962197925813348e-06 tokens_per_second_per_gpu:974.081646634206
Step 4968 | loss:1.2782690525054932 lr:1.690017271786911e-06 tokens_per_second_per_gpu:892.0072713187087
Step 4969 | loss:1.3380085229873657 lr:1.6838258314933078e-06 tokens_per_second_per_gpu:1275.3686967321676
Step 4970 | loss:1.3171377182006836 lr:1.6776454737600943e-06 tokens_per_second_per_gpu:1013.5738989399496
Step 4971 | loss:1.2707525491714478 lr:1.6714762006431626e-06 tokens_per_second_per_gpu:1168.4089289569702
Step 4972 | loss:1.3504635095596313 lr:1.6653180141947025e-06 tokens_per_second_per_gpu:978.6792313103147
Step 4973 | loss:1.4482944011688232 lr:1.6591709164632238e-06 tokens_per_second_per_gpu:771.6914072616554
Step 4974 | loss:1.3349201679229736 lr:1.6530349094935485e-06 tokens_per_second_per_gpu:968.1580132894732
Step 4975 | loss:1.2965271472930908 lr:1.6469099953268033e-06 tokens_per_second_per_gpu:1046.791261726212
Step 4976 | loss:1.438942551612854 lr:1.640796176000435e-06 tokens_per_second_per_gpu:854.3302790823393
Step 4977 | loss:1.1711068153381348 lr:1.6346934535481875e-06 tokens_per_second_per_gpu:974.0057409204961
Step 4978 | loss:1.4287837743759155 lr:1.6286018300001248e-06 tokens_per_second_per_gpu:755.1369723932403
Step 4979 | loss:1.370418667793274 lr:1.622521307382611e-06 tokens_per_second_per_gpu:886.2761960912353
Step 4980 | loss:1.2277565002441406 lr:1.6164518877183159e-06 tokens_per_second_per_gpu:1164.3000127059759
Step 4981 | loss:1.2740482091903687 lr:1.6103935730262364e-06 tokens_per_second_per_gpu:723.1550137586692
Step 4982 | loss:1.1868877410888672 lr:1.6043463653216353e-06 tokens_per_second_per_gpu:1091.7217925328475
Step 4983 | loss:1.2650558948516846 lr:1.5983102666161273e-06 tokens_per_second_per_gpu:1169.872279229663
Step 4984 | loss:1.2330026626586914 lr:1.5922852789175882e-06 tokens_per_second_per_gpu:928.5449120194731
Step 4985 | loss:1.4052213430404663 lr:1.58627140423023e-06 tokens_per_second_per_gpu:669.4702499093418
Step 4986 | loss:1.4102920293807983 lr:1.580268644554557e-06 tokens_per_second_per_gpu:885.1706235382097
Step 4987 | loss:1.2535547018051147 lr:1.5742770018873752e-06 tokens_per_second_per_gpu:888.9895477142783
Step 4988 | loss:1.2249414920806885 lr:1.5682964782217867e-06 tokens_per_second_per_gpu:1050.450959674587
Step 4989 | loss:1.3933964967727661 lr:1.56232707554721e-06 tokens_per_second_per_gpu:1029.0358987857335
Step 4990 | loss:1.1558724641799927 lr:1.5563687958493454e-06 tokens_per_second_per_gpu:1012.0725899082171
Step 4991 | loss:1.2470296621322632 lr:1.5504216411102128e-06 tokens_per_second_per_gpu:901.7585018957368
Step 4992 | loss:1.2540338039398193 lr:1.5444856133081095e-06 tokens_per_second_per_gpu:1072.6953120367748
Step 4993 | loss:1.415771484375 lr:1.5385607144176615e-06 tokens_per_second_per_gpu:810.4620698189391
Step 4994 | loss:1.2252830266952515 lr:1.5326469464097518e-06 tokens_per_second_per_gpu:842.8416205255863
Step 4995 | loss:1.261963963508606 lr:1.5267443112516076e-06 tokens_per_second_per_gpu:995.4686482252871
Step 4996 | loss:1.504572868347168 lr:1.5208528109067096e-06 tokens_per_second_per_gpu:702.6597136851802
Step 4997 | loss:1.3057026863098145 lr:1.5149724473348673e-06 tokens_per_second_per_gpu:846.8623412154367
Step 4998 | loss:1.3847322463989258 lr:1.5091032224921667e-06 tokens_per_second_per_gpu:1232.9289325755594
Step 4999 | loss:1.4021025896072388 lr:1.5032451383309912e-06 tokens_per_second_per_gpu:688.9762559268315
Step 5000 | loss:1.2978622913360596 lr:1.4973981968000286e-06 tokens_per_second_per_gpu:800.8531096853872
Step 5001 | loss:1.2755595445632935 lr:1.4915623998442444e-06 tokens_per_second_per_gpu:748.6206803998931
Step 5002 | loss:1.2763781547546387 lr:1.4857377494049083e-06 tokens_per_second_per_gpu:1103.049480139603
Step 5003 | loss:1.3499996662139893 lr:1.4799242474195833e-06 tokens_per_second_per_gpu:855.2509453745312
Step 5004 | loss:1.347316026687622 lr:1.4741218958221057e-06 tokens_per_second_per_gpu:785.0873408976669
Step 5005 | loss:1.3316823244094849 lr:1.46833069654264e-06 tokens_per_second_per_gpu:862.371957457465
Step 5006 | loss:1.1964085102081299 lr:1.462550651507593e-06 tokens_per_second_per_gpu:946.5022429990422
Step 5007 | loss:1.517928123474121 lr:1.4567817626397071e-06 tokens_per_second_per_gpu:669.4461285230018
Step 5008 | loss:1.3893029689788818 lr:1.4510240318579675e-06 tokens_per_second_per_gpu:853.9366534137665
Step 5009 | loss:1.2934670448303223 lr:1.4452774610776986e-06 tokens_per_second_per_gpu:1435.217430875056
Step 5010 | loss:1.3334870338439941 lr:1.4395420522104634e-06 tokens_per_second_per_gpu:985.2886888166695
Step 5011 | loss:1.1589624881744385 lr:1.4338178071641455e-06 tokens_per_second_per_gpu:1247.238480894747
Step 5012 | loss:1.2991323471069336 lr:1.4281047278429054e-06 tokens_per_second_per_gpu:1010.5128916650068
Step 5013 | loss:1.4186924695968628 lr:1.422402816147185e-06 tokens_per_second_per_gpu:682.8494380313218
Step 5014 | loss:1.3439369201660156 lr:1.416712073973712e-06 tokens_per_second_per_gpu:600.5779044147059
Step 5015 | loss:1.286257266998291 lr:1.4110325032155023e-06 tokens_per_second_per_gpu:739.3745928933118
Step 5016 | loss:1.2924338579177856 lr:1.4053641057618499e-06 tokens_per_second_per_gpu:813.583368299302
Step 5017 | loss:1.358778715133667 lr:1.3997068834983527e-06 tokens_per_second_per_gpu:975.6033905912742
Step 5018 | loss:1.2592381238937378 lr:1.394060838306848e-06 tokens_per_second_per_gpu:876.8298387566709
Step 5019 | loss:1.232225775718689 lr:1.3884259720655084e-06 tokens_per_second_per_gpu:893.6857669931355
Step 5020 | loss:1.258628487586975 lr:1.382802286648741e-06 tokens_per_second_per_gpu:808.0257418992724
Step 5021 | loss:1.2816437482833862 lr:1.3771897839272694e-06 tokens_per_second_per_gpu:1052.929319774964
Step 5022 | loss:1.4621131420135498 lr:1.3715884657680676e-06 tokens_per_second_per_gpu:825.5755330454446
Step 5023 | loss:1.371660590171814 lr:1.3659983340344099e-06 tokens_per_second_per_gpu:946.3144677000575
Step 5024 | loss:1.2576338052749634 lr:1.3604193905858484e-06 tokens_per_second_per_gpu:855.6071577572129
Step 5025 | loss:1.3606510162353516 lr:1.3548516372781971e-06 tokens_per_second_per_gpu:794.8342968227334
Step 5026 | loss:1.4804980754852295 lr:1.3492950759635624e-06 tokens_per_second_per_gpu:998.6990280598901
Step 5027 | loss:1.3564839363098145 lr:1.3437497084903288e-06 tokens_per_second_per_gpu:1009.2368565490339
Step 5028 | loss:1.3117544651031494 lr:1.3382155367031421e-06 tokens_per_second_per_gpu:1041.0281567330376
Step 5029 | loss:1.3802587985992432 lr:1.3326925624429418e-06 tokens_per_second_per_gpu:712.7561474205434
Step 5030 | loss:1.4242138862609863 lr:1.3271807875469326e-06 tokens_per_second_per_gpu:736.4525056965325
Step 5031 | loss:1.2058130502700806 lr:1.3216802138485926e-06 tokens_per_second_per_gpu:1068.2617401735604
Step 5032 | loss:1.2503881454467773 lr:1.3161908431776818e-06 tokens_per_second_per_gpu:867.0750159064825
Step 5033 | loss:1.3943257331848145 lr:1.3107126773602255e-06 tokens_per_second_per_gpu:923.0437775197657
Step 5034 | loss:1.435349464416504 lr:1.3052457182185227e-06 tokens_per_second_per_gpu:944.1182885075301
Step 5035 | loss:1.3363651037216187 lr:1.299789967571146e-06 tokens_per_second_per_gpu:656.480185431038
Step 5036 | loss:1.3245840072631836 lr:1.2943454272329567e-06 tokens_per_second_per_gpu:1025.8361621868273
Step 5037 | loss:1.4196667671203613 lr:1.2889120990150437e-06 tokens_per_second_per_gpu:642.53160225076
Step 5038 | loss:1.0965471267700195 lr:1.2834899847248116e-06 tokens_per_second_per_gpu:984.8791384494854
Step 5039 | loss:1.341726303100586 lr:1.2780790861659152e-06 tokens_per_second_per_gpu:949.4382438115636
Step 5040 | loss:1.3335787057876587 lr:1.2726794051382716e-06 tokens_per_second_per_gpu:925.6966026973756
Step 5041 | loss:1.461897373199463 lr:1.267290943438079e-06 tokens_per_second_per_gpu:996.9294335517488
Step 5042 | loss:1.2906800508499146 lr:1.2619137028577976e-06 tokens_per_second_per_gpu:1054.0679914501063
Step 5043 | loss:1.426146149635315 lr:1.2565476851861567e-06 tokens_per_second_per_gpu:811.0418822213287
Step 5044 | loss:1.301121473312378 lr:1.251192892208152e-06 tokens_per_second_per_gpu:1064.118481288349
Step 5045 | loss:1.3119182586669922 lr:1.2458493257050451e-06 tokens_per_second_per_gpu:782.1276794302296
Step 5046 | loss:1.4125288724899292 lr:1.2405169874543586e-06 tokens_per_second_per_gpu:714.2403939114176
Step 5047 | loss:1.3517084121704102 lr:1.2351958792298854e-06 tokens_per_second_per_gpu:724.4695675790416
Step 5048 | loss:1.3766390085220337 lr:1.2298860028016922e-06 tokens_per_second_per_gpu:1138.847214023666
Step 5049 | loss:1.4898033142089844 lr:1.2245873599360795e-06 tokens_per_second_per_gpu:857.4255827437513
Step 5050 | loss:1.4740605354309082 lr:1.219299952395653e-06 tokens_per_second_per_gpu:661.1023881081038
Step 5051 | loss:1.2268279790878296 lr:1.2140237819392417e-06 tokens_per_second_per_gpu:1097.4214708464376
Step 5052 | loss:1.2988795042037964 lr:1.2087588503219631e-06 tokens_per_second_per_gpu:1191.5022292171632
Step 5053 | loss:1.2085556983947754 lr:1.2035051592951772e-06 tokens_per_second_per_gpu:1305.5385004948923
Step 5054 | loss:1.3162842988967896 lr:1.1982627106065218e-06 tokens_per_second_per_gpu:856.5733913785685
Step 5055 | loss:1.3239729404449463 lr:1.1930315059998886e-06 tokens_per_second_per_gpu:770.2783742183586
Step 5056 | loss:1.3274468183517456 lr:1.1878115472154193e-06 tokens_per_second_per_gpu:945.3328512348494
Step 5057 | loss:1.392435073852539 lr:1.1826028359895294e-06 tokens_per_second_per_gpu:911.3718043695332
Step 5058 | loss:1.1557605266571045 lr:1.177405374054885e-06 tokens_per_second_per_gpu:826.4659952624155
Step 5059 | loss:1.2607123851776123 lr:1.1722191631404054e-06 tokens_per_second_per_gpu:849.5934235514065
Step 5060 | loss:1.1926603317260742 lr:1.1670442049712919e-06 tokens_per_second_per_gpu:882.0504261710439
Step 5061 | loss:1.284584403038025 lr:1.1618805012689608e-06 tokens_per_second_per_gpu:925.3694396481163
Step 5062 | loss:1.1773042678833008 lr:1.1567280537511254e-06 tokens_per_second_per_gpu:1024.1144054896238
Step 5063 | loss:1.325999140739441 lr:1.1515868641317256e-06 tokens_per_second_per_gpu:860.6179351584027
Step 5064 | loss:1.2557563781738281 lr:1.1464569341209828e-06 tokens_per_second_per_gpu:906.7016153355974
Step 5065 | loss:1.2621992826461792 lr:1.1413382654253378e-06 tokens_per_second_per_gpu:1311.9305580044888
Step 5066 | loss:1.2400946617126465 lr:1.136230859747524e-06 tokens_per_second_per_gpu:934.3889045241018
Step 5067 | loss:1.3342716693878174 lr:1.1311347187865016e-06 tokens_per_second_per_gpu:769.3134335901877
Step 5068 | loss:1.3019691705703735 lr:1.1260498442374933e-06 tokens_per_second_per_gpu:950.031957282071
Step 5069 | loss:1.2808438539505005 lr:1.1209762377919712e-06 tokens_per_second_per_gpu:1061.8623575326706
Step 5070 | loss:1.2823196649551392 lr:1.115913901137666e-06 tokens_per_second_per_gpu:733.0548286720858
Step 5071 | loss:1.3434734344482422 lr:1.110862835958547e-06 tokens_per_second_per_gpu:686.5854711379396
Step 5072 | loss:1.4279038906097412 lr:1.1058230439348448e-06 tokens_per_second_per_gpu:755.4902435803864
Step 5073 | loss:1.2624616622924805 lr:1.100794526743033e-06 tokens_per_second_per_gpu:950.1312901589586
Step 5074 | loss:1.381669282913208 lr:1.0957772860558467e-06 tokens_per_second_per_gpu:984.4813514772301
Step 5075 | loss:1.290634036064148 lr:1.0907713235422483e-06 tokens_per_second_per_gpu:748.2831813187727
Step 5076 | loss:1.2740103006362915 lr:1.0857766408674774e-06 tokens_per_second_per_gpu:1091.7560373609556
Step 5077 | loss:1.3029545545578003 lr:1.0807932396929886e-06 tokens_per_second_per_gpu:741.5071663826872
Step 5078 | loss:1.4452800750732422 lr:1.0758211216765144e-06 tokens_per_second_per_gpu:698.5483522113158
Step 5079 | loss:1.3696256875991821 lr:1.0708602884720141e-06 tokens_per_second_per_gpu:787.6881421767944
Step 5080 | loss:1.2873390913009644 lr:1.065910741729697e-06 tokens_per_second_per_gpu:939.650702620892
Step 5081 | loss:1.3765233755111694 lr:1.0609724830960265e-06 tokens_per_second_per_gpu:897.3042007542821
Step 5082 | loss:1.3513696193695068 lr:1.056045514213697e-06 tokens_per_second_per_gpu:984.085153913517
Step 5083 | loss:1.296553611755371 lr:1.0511298367216609e-06 tokens_per_second_per_gpu:675.1273275118442
Step 5084 | loss:1.4996623992919922 lr:1.046225452255109e-06 tokens_per_second_per_gpu:724.883034060065
Step 5085 | loss:1.3973174095153809 lr:1.0413323624454707e-06 tokens_per_second_per_gpu:759.6984806647636
Step 5086 | loss:1.3727784156799316 lr:1.0364505689204256e-06 tokens_per_second_per_gpu:711.3544351618664
Step 5087 | loss:1.369646430015564 lr:1.031580073303896e-06 tokens_per_second_per_gpu:613.4988065660235
Step 5088 | loss:1.3781135082244873 lr:1.0267208772160346e-06 tokens_per_second_per_gpu:826.529177097304
Step 5089 | loss:1.2790651321411133 lr:1.0218729822732485e-06 tokens_per_second_per_gpu:1022.0371548342393
Step 5090 | loss:1.3316315412521362 lr:1.0170363900881796e-06 tokens_per_second_per_gpu:1012.7700950011476
Step 5091 | loss:1.4382593631744385 lr:1.0122111022697117e-06 tokens_per_second_per_gpu:623.0750439128248
Step 5092 | loss:1.4477490186691284 lr:1.0073971204229674e-06 tokens_per_second_per_gpu:960.8850501140772
Step 5093 | loss:1.413346529006958 lr:1.0025944461493085e-06 tokens_per_second_per_gpu:757.687381570205
Step 5094 | loss:1.3304928541183472 lr:9.978030810463383e-07 tokens_per_second_per_gpu:852.536522615014
Step 5095 | loss:1.4690468311309814 lr:9.930230267078876e-07 tokens_per_second_per_gpu:571.4019901704953
Step 5096 | loss:1.4728834629058838 lr:9.88254284724037e-07 tokens_per_second_per_gpu:825.885579890703
Step 5097 | loss:1.4103132486343384 lr:9.834968566810986e-07 tokens_per_second_per_gpu:743.1923328355015
Step 5098 | loss:1.3493660688400269 lr:9.78750744161622e-07 tokens_per_second_per_gpu:1042.1486522899772
Step 5099 | loss:1.1914784908294678 lr:9.740159487443888e-07 tokens_per_second_per_gpu:1016.9448490682356
Step 5100 | loss:1.21787428855896 lr:9.69292472004426e-07 tokens_per_second_per_gpu:1060.8138316754555
Step 5101 | loss:1.3321659564971924 lr:9.645803155129838e-07 tokens_per_second_per_gpu:882.8648254229513
Step 5102 | loss:1.322677493095398 lr:9.598794808375477e-07 tokens_per_second_per_gpu:1131.9657620409707
Step 5103 | loss:1.298085331916809 lr:9.551899695418564e-07 tokens_per_second_per_gpu:871.1674888574665
Step 5104 | loss:1.2784547805786133 lr:9.505117831858489e-07 tokens_per_second_per_gpu:757.9242841544511
Step 5105 | loss:1.5083822011947632 lr:9.458449233257298e-07 tokens_per_second_per_gpu:1089.419232760904
Step 5106 | loss:1.3452008962631226 lr:9.411893915139074e-07 tokens_per_second_per_gpu:1004.6520628681264
Step 5107 | loss:1.4375683069229126 lr:9.365451892990516e-07 tokens_per_second_per_gpu:710.7992554067357
Step 5108 | loss:1.449371099472046 lr:9.319123182260285e-07 tokens_per_second_per_gpu:837.7752132744558
Step 5109 | loss:1.3340933322906494 lr:9.272907798359657e-07 tokens_per_second_per_gpu:752.8923378119209
Step 5110 | loss:1.397213101387024 lr:9.226805756662026e-07 tokens_per_second_per_gpu:853.8037275831022
Step 5111 | loss:1.368552803993225 lr:9.180817072503244e-07 tokens_per_second_per_gpu:857.6527410751264
Step 5112 | loss:1.330353856086731 lr:9.134941761181241e-07 tokens_per_second_per_gpu:1175.1001385168415
Step 5113 | loss:1.2785544395446777 lr:9.089179837956411e-07 tokens_per_second_per_gpu:1119.9644093000766
Step 5114 | loss:1.3694789409637451 lr:9.043531318051378e-07 tokens_per_second_per_gpu:954.0274802469146
Step 5115 | loss:1.2683777809143066 lr:8.997996216650993e-07 tokens_per_second_per_gpu:740.2414699767535
Step 5116 | loss:1.2722551822662354 lr:8.95257454890242e-07 tokens_per_second_per_gpu:853.9381805084386
Step 5117 | loss:1.438058853149414 lr:8.907266329915203e-07 tokens_per_second_per_gpu:787.5821123341764
Step 5118 | loss:1.30056893825531 lr:8.862071574760809e-07 tokens_per_second_per_gpu:1086.0208789272153
Step 5119 | loss:1.4007978439331055 lr:8.816990298473442e-07 tokens_per_second_per_gpu:922.8351022373865
Step 5120 | loss:1.160455346107483 lr:8.772022516049065e-07 tokens_per_second_per_gpu:1110.213486394213
Step 5121 | loss:1.4722830057144165 lr:8.727168242446264e-07 tokens_per_second_per_gpu:1059.2971687411505
Step 5122 | loss:1.282611608505249 lr:8.682427492585736e-07 tokens_per_second_per_gpu:1027.1765460181307
Step 5123 | loss:1.3082928657531738 lr:8.637800281350332e-07 tokens_per_second_per_gpu:934.441840704738
Step 5124 | loss:1.3136498928070068 lr:8.593286623585211e-07 tokens_per_second_per_gpu:830.7122371243554
Step 5125 | loss:1.2987933158874512 lr:8.548886534097798e-07 tokens_per_second_per_gpu:789.3964011683339
Step 5126 | loss:1.4308712482452393 lr:8.504600027657677e-07 tokens_per_second_per_gpu:670.247984484112
Step 5127 | loss:1.0698412656784058 lr:8.460427118996693e-07 tokens_per_second_per_gpu:839.0893520150651
Step 5128 | loss:1.4848504066467285 lr:8.416367822808773e-07 tokens_per_second_per_gpu:591.4342244109151
Step 5129 | loss:1.1969780921936035 lr:8.372422153750341e-07 tokens_per_second_per_gpu:997.6785757153218
Step 5130 | loss:1.3391366004943848 lr:8.328590126439666e-07 tokens_per_second_per_gpu:1217.2776508050163
Step 5131 | loss:1.344081163406372 lr:8.284871755457517e-07 tokens_per_second_per_gpu:1051.915272326401
Step 5132 | loss:1.2971457242965698 lr:8.241267055346584e-07 tokens_per_second_per_gpu:1045.7821840831327
Step 5133 | loss:1.3705992698669434 lr:8.197776040611981e-07 tokens_per_second_per_gpu:736.1781625893794
Step 5134 | loss:1.3986599445343018 lr:8.154398725720934e-07 tokens_per_second_per_gpu:840.9630309095052
Step 5135 | loss:1.3764718770980835 lr:8.111135125102747e-07 tokens_per_second_per_gpu:838.9176113426205
Step 5136 | loss:1.4246947765350342 lr:8.067985253149028e-07 tokens_per_second_per_gpu:1181.2333225516131
Step 5137 | loss:1.3909724950790405 lr:8.024949124213465e-07 tokens_per_second_per_gpu:863.4451344143569
Step 5138 | loss:1.1846766471862793 lr:7.982026752611931e-07 tokens_per_second_per_gpu:1164.1571135859601
Step 5139 | loss:1.3278179168701172 lr:7.939218152622495e-07 tokens_per_second_per_gpu:721.8111186975004
Step 5140 | loss:1.348441243171692 lr:7.896523338485377e-07 tokens_per_second_per_gpu:811.1414553364453
Step 5141 | loss:1.2041395902633667 lr:7.853942324402873e-07 tokens_per_second_per_gpu:800.661533997076
Step 5142 | loss:1.3004019260406494 lr:7.811475124539507e-07 tokens_per_second_per_gpu:1142.9558847303044
Step 5143 | loss:1.332232117652893 lr:7.769121753021918e-07 tokens_per_second_per_gpu:1126.7051323839737
Step 5144 | loss:1.4476304054260254 lr:7.726882223938818e-07 tokens_per_second_per_gpu:916.8507300036272
Step 5145 | loss:1.216157078742981 lr:7.684756551341192e-07 tokens_per_second_per_gpu:1135.0991170983045
Step 5146 | loss:1.3448822498321533 lr:7.642744749241941e-07 tokens_per_second_per_gpu:920.3883154431172
Step 5147 | loss:1.1748847961425781 lr:7.600846831616314e-07 tokens_per_second_per_gpu:1097.608707753614
Step 5148 | loss:1.3880614042282104 lr:7.559062812401556e-07 tokens_per_second_per_gpu:1010.7474371614366
Step 5149 | loss:1.3073506355285645 lr:7.517392705497028e-07 tokens_per_second_per_gpu:926.0673803133344
Step 5150 | loss:1.2827057838439941 lr:7.475836524764201e-07 tokens_per_second_per_gpu:686.7525771514313
Step 5151 | loss:1.3716503381729126 lr:7.434394284026623e-07 tokens_per_second_per_gpu:762.6728104301684
Step 5152 | loss:1.2397403717041016 lr:7.393065997070075e-07 tokens_per_second_per_gpu:1061.4433471168559
Step 5153 | loss:1.4000731706619263 lr:7.351851677642212e-07 tokens_per_second_per_gpu:929.1221432195442
Step 5154 | loss:1.438239336013794 lr:7.310751339452964e-07 tokens_per_second_per_gpu:679.1125377712151
Step 5155 | loss:1.4055284261703491 lr:7.269764996174293e-07 tokens_per_second_per_gpu:731.5167188898847
Step 5156 | loss:1.3226869106292725 lr:7.228892661440161e-07 tokens_per_second_per_gpu:749.5544414771301
Step 5157 | loss:1.2869759798049927 lr:7.188134348846758e-07 tokens_per_second_per_gpu:849.7876155966817
Step 5158 | loss:1.6597038507461548 lr:7.147490071952156e-07 tokens_per_second_per_gpu:735.7346190861948
Step 5159 | loss:1.351581335067749 lr:7.106959844276655e-07 tokens_per_second_per_gpu:866.0118466924786
Step 5160 | loss:1.2660387754440308 lr:7.066543679302594e-07 tokens_per_second_per_gpu:932.2641776467576
Step 5161 | loss:1.2655537128448486 lr:7.02624159047423e-07 tokens_per_second_per_gpu:980.1026493711474
Step 5162 | loss:1.338921070098877 lr:6.986053591198087e-07 tokens_per_second_per_gpu:1038.15828089988
Step 5163 | loss:1.5416159629821777 lr:6.945979694842535e-07 tokens_per_second_per_gpu:615.5327641405944
Step 5164 | loss:1.150301218032837 lr:6.906019914738131e-07 tokens_per_second_per_gpu:1109.0151793136201
Step 5165 | loss:1.411991000175476 lr:6.866174264177354e-07 tokens_per_second_per_gpu:941.5657016827224
Step 5166 | loss:1.1923385858535767 lr:6.826442756414874e-07 tokens_per_second_per_gpu:940.3949674319687
Step 5167 | loss:1.3186721801757812 lr:6.78682540466724e-07 tokens_per_second_per_gpu:1119.8284522987667
Step 5168 | loss:1.3882856369018555 lr:6.747322222113077e-07 tokens_per_second_per_gpu:776.8240297868425
Step 5169 | loss:1.410152554512024 lr:6.707933221893086e-07 tokens_per_second_per_gpu:701.5480427478861
Step 5170 | loss:1.396662712097168 lr:6.668658417109924e-07 tokens_per_second_per_gpu:835.6580879984259
Step 5171 | loss:1.3063191175460815 lr:6.629497820828205e-07 tokens_per_second_per_gpu:903.5857276935042
Step 5172 | loss:1.3110274076461792 lr:6.59045144607478e-07 tokens_per_second_per_gpu:876.1853222246084
Step 5173 | loss:1.41591477394104 lr:6.551519305838216e-07 tokens_per_second_per_gpu:707.993979171983
Step 5174 | loss:1.3210046291351318 lr:6.512701413069315e-07 tokens_per_second_per_gpu:726.989765845087
Step 5175 | loss:1.30219304561615 lr:6.473997780680646e-07 tokens_per_second_per_gpu:896.6018724547232
Step 5176 | loss:1.2236926555633545 lr:6.435408421546962e-07 tokens_per_second_per_gpu:877.3437088203933
Step 5177 | loss:1.250600814819336 lr:6.396933348504979e-07 tokens_per_second_per_gpu:1097.7957513507226
Step 5178 | loss:1.3046910762786865 lr:6.358572574353332e-07 tokens_per_second_per_gpu:848.4351265624404
Step 5179 | loss:1.0550956726074219 lr:6.320326111852652e-07 tokens_per_second_per_gpu:862.4451536700036
Step 5180 | loss:1.304068684577942 lr:6.28219397372553e-07 tokens_per_second_per_gpu:727.9085091046467
Step 5181 | loss:1.3107267618179321 lr:6.244176172656551e-07 tokens_per_second_per_gpu:1081.3995446953763
Step 5182 | loss:1.379529595375061 lr:6.206272721292261e-07 tokens_per_second_per_gpu:839.492018874495
Step 5183 | loss:1.2313003540039062 lr:6.1684836322412e-07 tokens_per_second_per_gpu:1055.442960572553
Step 5184 | loss:1.2597700357437134 lr:6.130808918073832e-07 tokens_per_second_per_gpu:951.1072166529257
Step 5185 | loss:1.182671308517456 lr:6.093248591322536e-07 tokens_per_second_per_gpu:1087.737037102805
Step 5186 | loss:1.1841492652893066 lr:6.055802664481729e-07 tokens_per_second_per_gpu:924.1860989534626
Step 5187 | loss:1.4199894666671753 lr:6.01847115000767e-07 tokens_per_second_per_gpu:871.8387556387908
Step 5188 | loss:1.4267405271530151 lr:5.98125406031873e-07 tokens_per_second_per_gpu:807.8015386608707
Step 5189 | loss:1.3257486820220947 lr:5.944151407794928e-07 tokens_per_second_per_gpu:1014.0081602578475
Step 5190 | loss:1.4404191970825195 lr:5.907163204778514e-07 tokens_per_second_per_gpu:606.0210303886264
Step 5191 | loss:1.173831582069397 lr:5.870289463573502e-07 tokens_per_second_per_gpu:1092.920371334816
Step 5192 | loss:1.2353030443191528 lr:5.833530196445863e-07 tokens_per_second_per_gpu:935.7178920173827
Step 5193 | loss:1.372460961341858 lr:5.796885415623565e-07 tokens_per_second_per_gpu:772.8500061353428
Step 5194 | loss:1.381386637687683 lr:5.760355133296301e-07 tokens_per_second_per_gpu:1043.3422144970552
Step 5195 | loss:1.171877145767212 lr:5.723939361615881e-07 tokens_per_second_per_gpu:1090.2905326848063
Step 5196 | loss:1.3376061916351318 lr:5.687638112695952e-07 tokens_per_second_per_gpu:887.133718755475
Step 5197 | loss:1.2653982639312744 lr:5.651451398612006e-07 tokens_per_second_per_gpu:866.6335120421563
Step 5198 | loss:1.2633243799209595 lr:5.615379231401529e-07 tokens_per_second_per_gpu:1145.9751697086647
Step 5199 | loss:1.3617362976074219 lr:5.579421623063774e-07 tokens_per_second_per_gpu:731.4550893871811
Step 5200 | loss:1.384964942932129 lr:5.543578585560105e-07 tokens_per_second_per_gpu:976.1874845762898
Step 5201 | loss:1.492138147354126 lr:5.507850130813457e-07 tokens_per_second_per_gpu:732.1942984272898
Step 5202 | loss:1.4052751064300537 lr:5.472236270708996e-07 tokens_per_second_per_gpu:901.9825124985326
Step 5203 | loss:1.297083854675293 lr:5.436737017093534e-07 tokens_per_second_per_gpu:818.0201312126841
Step 5204 | loss:1.3073694705963135 lr:5.401352381775842e-07 tokens_per_second_per_gpu:797.4849127664683
Step 5205 | loss:1.512153148651123 lr:5.366082376526532e-07 tokens_per_second_per_gpu:699.4688541542679
Step 5206 | loss:1.2139232158660889 lr:5.330927013078096e-07 tokens_per_second_per_gpu:951.084586172415
Step 5207 | loss:1.321489930152893 lr:5.295886303124946e-07 tokens_per_second_per_gpu:740.9120734853421
Step 5208 | loss:1.3805550336837769 lr:5.26096025832326e-07 tokens_per_second_per_gpu:840.1570247038643
Step 5209 | loss:1.263280987739563 lr:5.226148890291132e-07 tokens_per_second_per_gpu:1032.4314068855876
Step 5210 | loss:1.2270164489746094 lr:5.191452210608499e-07 tokens_per_second_per_gpu:924.127495265589
Step 5211 | loss:1.564831256866455 lr:5.156870230817139e-07 tokens_per_second_per_gpu:808.1929252390128
Step 5212 | loss:1.2579500675201416 lr:5.122402962420713e-07 tokens_per_second_per_gpu:861.3655515457592
Step 5213 | loss:1.317080020904541 lr:5.088050416884604e-07 tokens_per_second_per_gpu:1132.0721328321226
Step 5214 | loss:1.316670298576355 lr:5.053812605636193e-07 tokens_per_second_per_gpu:854.0626379079334
Step 5215 | loss:1.3804521560668945 lr:5.019689540064625e-07 tokens_per_second_per_gpu:988.3215954216296
Step 5216 | loss:1.3096897602081299 lr:4.98568123152081e-07 tokens_per_second_per_gpu:1055.129960744699
Step 5217 | loss:1.45522141456604 lr:4.951787691317616e-07 tokens_per_second_per_gpu:743.5363389180737
Step 5218 | loss:1.2271947860717773 lr:4.918008930729634e-07 tokens_per_second_per_gpu:992.9708294036496
Step 5219 | loss:1.3178271055221558 lr:4.884344960993297e-07 tokens_per_second_per_gpu:702.5541053287502
Step 5220 | loss:1.2640918493270874 lr:4.850795793306883e-07 tokens_per_second_per_gpu:1215.5224740253661
Step 5221 | loss:1.3333406448364258 lr:4.817361438830392e-07 tokens_per_second_per_gpu:912.5880511780992
Step 5222 | loss:1.2619736194610596 lr:4.784041908685782e-07 tokens_per_second_per_gpu:934.7231801038183
Step 5223 | loss:1.3460358381271362 lr:4.7508372139566597e-07 tokens_per_second_per_gpu:1029.729025943456
Step 5224 | loss:1.231945276260376 lr:4.717747365688551e-07 tokens_per_second_per_gpu:805.0407032275946
Step 5225 | loss:1.2109071016311646 lr:4.684772374888707e-07 tokens_per_second_per_gpu:1002.3289224757997
Step 5226 | loss:1.3386472463607788 lr:4.65191225252618e-07 tokens_per_second_per_gpu:883.0733163628138
Step 5227 | loss:1.3779563903808594 lr:4.6191670095319046e-07 tokens_per_second_per_gpu:889.787925996297
Step 5228 | loss:1.3454312086105347 lr:4.586536656798384e-07 tokens_per_second_per_gpu:777.2889369871295
Step 5229 | loss:1.3522436618804932 lr:4.554021205180197e-07 tokens_per_second_per_gpu:780.8874116015047
Step 5230 | loss:1.1848362684249878 lr:4.521620665493375e-07 tokens_per_second_per_gpu:884.0882546765515
Step 5231 | loss:1.38054358959198 lr:4.489335048516063e-07 tokens_per_second_per_gpu:913.0966449890228
Step 5232 | loss:1.2613707780838013 lr:4.4571643649878974e-07 tokens_per_second_per_gpu:1214.6575768971522
Step 5233 | loss:1.1092422008514404 lr:4.425108625610435e-07 tokens_per_second_per_gpu:1048.8041248905924
Step 5234 | loss:1.3175262212753296 lr:4.3931678410469187e-07 tokens_per_second_per_gpu:1143.8965208286209
Step 5235 | loss:1.326693058013916 lr:4.36134202192247e-07 tokens_per_second_per_gpu:893.1905412578863
Step 5236 | loss:1.3248515129089355 lr:4.3296311788237837e-07 tokens_per_second_per_gpu:1195.5635586561634
Step 5237 | loss:1.444223165512085 lr:4.298035322299509e-07 tokens_per_second_per_gpu:755.9144546326123
Step 5238 | loss:1.361262321472168 lr:4.266554462859828e-07 tokens_per_second_per_gpu:873.1389124654647
Step 5239 | loss:1.2613089084625244 lr:4.2351886109769193e-07 tokens_per_second_per_gpu:1010.553808807643
Step 5240 | loss:1.3866167068481445 lr:4.203937777084454e-07 tokens_per_second_per_gpu:680.7091478622585
Step 5241 | loss:1.3897454738616943 lr:4.1728019715780993e-07 tokens_per_second_per_gpu:591.326330924351
Step 5242 | loss:1.3597941398620605 lr:4.141781204814937e-07 tokens_per_second_per_gpu:1149.4475229640273
Step 5243 | loss:1.231204867362976 lr:4.1108754871141234e-07 tokens_per_second_per_gpu:1042.507240150218
Step 5244 | loss:1.3186780214309692 lr:4.080084828756308e-07 tokens_per_second_per_gpu:1133.9256538839568
Step 5245 | loss:1.2799980640411377 lr:4.0494092399839804e-07 tokens_per_second_per_gpu:863.7265550351212
Step 5246 | loss:1.407078742980957 lr:4.0188487310012786e-07 tokens_per_second_per_gpu:821.1660431343269
Step 5247 | loss:1.3492646217346191 lr:3.988403311974103e-07 tokens_per_second_per_gpu:1128.7681650788065
Step 5248 | loss:1.49724543094635 lr:3.9580729930300813e-07 tokens_per_second_per_gpu:660.4127430973463
Step 5249 | loss:1.3098889589309692 lr:3.927857784258526e-07 tokens_per_second_per_gpu:683.6078710259447
Step 5250 | loss:1.3513070344924927 lr:3.8977576957104737e-07 tokens_per_second_per_gpu:810.0902006748664
Step 5251 | loss:1.3742148876190186 lr:3.8677727373986886e-07 tokens_per_second_per_gpu:850.534138741066
Step 5252 | loss:1.4184802770614624 lr:3.837902919297503e-07 tokens_per_second_per_gpu:758.5883563566206
Step 5253 | loss:1.3507496118545532 lr:3.808148251343207e-07 tokens_per_second_per_gpu:888.5284912164981
Step 5254 | loss:1.4544830322265625 lr:3.778508743433467e-07 tokens_per_second_per_gpu:894.9852006528716
Step 5255 | loss:1.2579162120819092 lr:3.748984405427985e-07 tokens_per_second_per_gpu:782.4007171534031
Step 5256 | loss:1.2381149530410767 lr:3.719575247147799e-07 tokens_per_second_per_gpu:754.0435236215926
Step 5257 | loss:1.3384984731674194 lr:3.690281278375906e-07 tokens_per_second_per_gpu:919.7420592166195
Step 5258 | loss:1.4841899871826172 lr:3.661102508856911e-07 tokens_per_second_per_gpu:1199.7412434008477
Step 5259 | loss:1.6191296577453613 lr:3.632038948297028e-07 tokens_per_second_per_gpu:822.5871779390715
Step 5260 | loss:1.4399797916412354 lr:3.6030906063641953e-07 tokens_per_second_per_gpu:943.6503950173607
Step 5261 | loss:1.2336971759796143 lr:3.5742574926879985e-07 tokens_per_second_per_gpu:1107.4737132240912
Step 5262 | loss:1.111446738243103 lr:3.545539616859788e-07 tokens_per_second_per_gpu:1020.8472791166287
Step 5263 | loss:1.2311686277389526 lr:3.516936988432445e-07 tokens_per_second_per_gpu:866.9350302604291
Step 5264 | loss:1.1689246892929077 lr:3.488449616920613e-07 tokens_per_second_per_gpu:985.3675090828708
Step 5265 | loss:1.2791334390640259 lr:3.4600775118005465e-07 tokens_per_second_per_gpu:816.5990795039532
Step 5266 | loss:1.2759435176849365 lr:3.4318206825101834e-07 tokens_per_second_per_gpu:1115.268580507623
Step 5267 | loss:1.4218336343765259 lr:3.4036791384491115e-07 tokens_per_second_per_gpu:885.7820464547243
Step 5268 | loss:1.4497941732406616 lr:3.375652888978486e-07 tokens_per_second_per_gpu:599.4889750964674
Step 5269 | loss:1.2885147333145142 lr:3.347741943421267e-07 tokens_per_second_per_gpu:910.4940923434481
Step 5270 | loss:1.190403938293457 lr:3.319946311061944e-07 tokens_per_second_per_gpu:1211.3947468563367
Step 5271 | loss:1.3564554452896118 lr:3.292266001146693e-07 tokens_per_second_per_gpu:1030.0682799640194
Step 5272 | loss:1.2549176216125488 lr:3.264701022883337e-07 tokens_per_second_per_gpu:962.1115114768064
Step 5273 | loss:1.2990549802780151 lr:3.2372513854412305e-07 tokens_per_second_per_gpu:1086.9146877407409
Step 5274 | loss:1.2973153591156006 lr:3.209917097951531e-07 tokens_per_second_per_gpu:1181.7295376852703
Step 5275 | loss:1.4235795736312866 lr:3.1826981695068863e-07 tokens_per_second_per_gpu:916.0288968121182
Step 5276 | loss:1.4168505668640137 lr:3.155594609161632e-07 tokens_per_second_per_gpu:972.81226030755
Step 5277 | loss:1.1510275602340698 lr:3.1286064259317125e-07 tokens_per_second_per_gpu:1187.4247585206504
Step 5278 | loss:1.3535690307617188 lr:3.101733628794717e-07 tokens_per_second_per_gpu:593.7744939020789
Step 5279 | loss:1.334519386291504 lr:3.074976226689807e-07 tokens_per_second_per_gpu:776.2842626381002
Step 5280 | loss:1.1653248071670532 lr:3.0483342285177515e-07 tokens_per_second_per_gpu:999.7872176687787
Step 5281 | loss:1.3735942840576172 lr:3.0218076431410056e-07 tokens_per_second_per_gpu:860.9469197239865
Step 5282 | loss:1.3071049451828003 lr:2.995396479383594e-07 tokens_per_second_per_gpu:1082.985167522649
Step 5283 | loss:1.4266117811203003 lr:2.9691007460310724e-07 tokens_per_second_per_gpu:590.4175003220643
Step 5284 | loss:1.3193604946136475 lr:2.9429204518307604e-07 tokens_per_second_per_gpu:879.9531569321289
Step 5285 | loss:1.3145289421081543 lr:2.9168556054913916e-07 tokens_per_second_per_gpu:785.3649538294763
Step 5286 | loss:1.468702793121338 lr:2.890906215683464e-07 tokens_per_second_per_gpu:884.754506444849
Step 5287 | loss:1.194576621055603 lr:2.865072291038889e-07 tokens_per_second_per_gpu:1168.875078352389
Step 5288 | loss:1.218704104423523 lr:2.8393538401513814e-07 tokens_per_second_per_gpu:1005.3484567870493
Step 5289 | loss:1.315003514289856 lr:2.81375087157607e-07 tokens_per_second_per_gpu:934.6684445261449
Step 5290 | loss:1.2007839679718018 lr:2.78826339382977e-07 tokens_per_second_per_gpu:1308.4406053592625
Step 5291 | loss:1.2000442743301392 lr:2.762891415390789e-07 tokens_per_second_per_gpu:895.6560593121816
Step 5292 | loss:1.4511972665786743 lr:2.7376349446991186e-07 tokens_per_second_per_gpu:674.8950821993432
Step 5293 | loss:1.2399216890335083 lr:2.7124939901562446e-07 tokens_per_second_per_gpu:815.4474179047724
Step 5294 | loss:1.3786449432373047 lr:2.687468560125261e-07 tokens_per_second_per_gpu:628.7359656101266
Step 5295 | loss:1.3214399814605713 lr:2.66255866293083e-07 tokens_per_second_per_gpu:1016.8705317000264
Step 5296 | loss:1.313459038734436 lr:2.637764306859225e-07 tokens_per_second_per_gpu:1063.2405684398648
Step 5297 | loss:1.5110663175582886 lr:2.6130855001581684e-07 tokens_per_second_per_gpu:746.62404652387
Step 5298 | loss:1.3602359294891357 lr:2.588522251037034e-07 tokens_per_second_per_gpu:828.817041798845
Step 5299 | loss:1.2187283039093018 lr:2.564074567666763e-07 tokens_per_second_per_gpu:926.2879618684185
Step 5300 | loss:1.311724305152893 lr:2.5397424581798277e-07 tokens_per_second_per_gpu:853.2624986530835
Step 5301 | loss:1.3971432447433472 lr:2.5155259306702316e-07 tokens_per_second_per_gpu:793.2476438271389
Step 5302 | loss:1.3562036752700806 lr:2.491424993193586e-07 tokens_per_second_per_gpu:1081.3866648727937
Step 5303 | loss:1.4286043643951416 lr:2.467439653766995e-07 tokens_per_second_per_gpu:1135.5010605169039
Step 5304 | loss:1.5162898302078247 lr:2.443569920369171e-07 tokens_per_second_per_gpu:693.0642406322744
Step 5305 | loss:1.415251612663269 lr:2.419815800940278e-07 tokens_per_second_per_gpu:1013.254324428353
Step 5306 | loss:1.3938138484954834 lr:2.3961773033821295e-07 tokens_per_second_per_gpu:893.1595048040293
Step 5307 | loss:1.2610368728637695 lr:2.3726544355579914e-07 tokens_per_second_per_gpu:761.8408171770831
Step 5308 | loss:1.4133689403533936 lr:2.3492472052927368e-07 tokens_per_second_per_gpu:883.9117157746009
Step 5309 | loss:1.4852240085601807 lr:2.3259556203726937e-07 tokens_per_second_per_gpu:815.1178614268259
Step 5310 | loss:1.2936816215515137 lr:2.3027796885457973e-07 tokens_per_second_per_gpu:927.7044350884443
Step 5311 | loss:1.5204074382781982 lr:2.2797194175214363e-07 tokens_per_second_per_gpu:729.1603111463195
Step 5312 | loss:1.3381584882736206 lr:2.256774814970569e-07 tokens_per_second_per_gpu:666.7913563336177
Step 5313 | loss:1.3596349954605103 lr:2.2339458885257234e-07 tokens_per_second_per_gpu:915.106703534205
Step 5314 | loss:1.2772623300552368 lr:2.2112326457808804e-07 tokens_per_second_per_gpu:1196.7582219857668
Step 5315 | loss:1.3127707242965698 lr:2.1886350942915132e-07 tokens_per_second_per_gpu:1008.3773676316396
Step 5316 | loss:1.437562108039856 lr:2.166153241574703e-07 tokens_per_second_per_gpu:876.8827241931016
Step 5317 | loss:1.2206376791000366 lr:2.1437870951089453e-07 tokens_per_second_per_gpu:755.964324123977
Step 5318 | loss:1.3115520477294922 lr:2.1215366623343443e-07 tokens_per_second_per_gpu:829.968538015055
Step 5319 | loss:1.2245903015136719 lr:2.0994019506524184e-07 tokens_per_second_per_gpu:830.7516797832534
Step 5320 | loss:1.3280138969421387 lr:2.0773829674262943e-07 tokens_per_second_per_gpu:1081.560280362328
Step 5321 | loss:1.383305311203003 lr:2.0554797199805128e-07 tokens_per_second_per_gpu:866.4296020793266
Step 5322 | loss:1.289115071296692 lr:2.033692215601107e-07 tokens_per_second_per_gpu:962.6351720653864
Step 5323 | loss:1.232380986213684 lr:2.0120204615356793e-07 tokens_per_second_per_gpu:1047.367918795293
Step 5324 | loss:1.395285964012146 lr:1.9904644649933243e-07 tokens_per_second_per_gpu:890.9795820185287
Step 5325 | loss:1.368679404258728 lr:1.9690242331445894e-07 tokens_per_second_per_gpu:914.6891112992201
Step 5326 | loss:1.283780574798584 lr:1.9476997731215137e-07 tokens_per_second_per_gpu:1051.6822060751854
Step 5327 | loss:1.4085137844085693 lr:1.926491092017629e-07 tokens_per_second_per_gpu:749.4244653946242
Step 5328 | loss:1.5066221952438354 lr:1.9053981968879583e-07 tokens_per_second_per_gpu:833.4799024716912
Step 5329 | loss:1.2082957029342651 lr:1.884421094749017e-07 tokens_per_second_per_gpu:1048.1376893484357
Step 5330 | loss:1.2129132747650146 lr:1.8635597925788115e-07 tokens_per_second_per_gpu:1347.8455702164838
Step 5331 | loss:1.308506965637207 lr:1.8428142973168413e-07 tokens_per_second_per_gpu:869.779149962013
Step 5332 | loss:1.2327340841293335 lr:1.8221846158639808e-07 tokens_per_second_per_gpu:967.6650095230727
Step 5333 | loss:1.1632943153381348 lr:1.8016707550827126e-07 tokens_per_second_per_gpu:1128.6769738238786
Step 5334 | loss:1.3099761009216309 lr:1.7812727217969335e-07 tokens_per_second_per_gpu:748.9400968787016
Step 5335 | loss:1.2543413639068604 lr:1.7609905227919553e-07 tokens_per_second_per_gpu:962.225051056837
Step 5336 | loss:1.2126336097717285 lr:1.7408241648146582e-07 tokens_per_second_per_gpu:887.3382951131216
Step 5337 | loss:1.1749464273452759 lr:1.7207736545732986e-07 tokens_per_second_per_gpu:738.8273509182176
Step 5338 | loss:1.1845341920852661 lr:1.7008389987377024e-07 tokens_per_second_per_gpu:1090.3788994946
Step 5339 | loss:1.2754714488983154 lr:1.6810202039390709e-07 tokens_per_second_per_gpu:978.2402621878134
Step 5340 | loss:1.4253160953521729 lr:1.6613172767700578e-07 tokens_per_second_per_gpu:830.1778493751655
Step 5341 | loss:1.4199904203414917 lr:1.6417302237848484e-07 tokens_per_second_per_gpu:727.218641161793
Step 5342 | loss:1.4183048009872437 lr:1.6222590514989642e-07 tokens_per_second_per_gpu:1053.1602807382965
Step 5343 | loss:1.3777382373809814 lr:1.602903766389535e-07 tokens_per_second_per_gpu:875.5334206671591
Step 5344 | loss:1.3415091037750244 lr:1.5836643748950272e-07 tokens_per_second_per_gpu:765.6259782334348
Step 5345 | loss:1.3553591966629028 lr:1.5645408834153994e-07 tokens_per_second_per_gpu:1128.206729260358
Step 5346 | loss:1.2207456827163696 lr:1.545533298312024e-07 tokens_per_second_per_gpu:1051.648460516029
Step 5347 | loss:1.2797693014144897 lr:1.5266416259077263e-07 tokens_per_second_per_gpu:797.4244163055532
Step 5348 | loss:1.3306846618652344 lr:1.5078658724867855e-07 tokens_per_second_per_gpu:839.86942698159
Step 5349 | loss:1.3715003728866577 lr:1.4892060442949717e-07 tokens_per_second_per_gpu:912.0201955394774
Step 5350 | loss:1.3799760341644287 lr:1.470662147539392e-07 tokens_per_second_per_gpu:1015.0155068911391
Step 5351 | loss:1.172870397567749 lr:1.4522341883886457e-07 tokens_per_second_per_gpu:1067.514636539994
Step 5352 | loss:1.2395349740982056 lr:1.4339221729727456e-07 tokens_per_second_per_gpu:903.0302762960915
Step 5353 | loss:1.38374662399292 lr:1.4157261073831972e-07 tokens_per_second_per_gpu:865.5071264887716
Step 5354 | loss:1.238250970840454 lr:1.3976459976728028e-07 tokens_per_second_per_gpu:864.540576797711
Step 5355 | loss:1.4257463216781616 lr:1.3796818498559736e-07 tokens_per_second_per_gpu:825.4839636238686
Step 5356 | loss:1.2466447353363037 lr:1.36183366990838e-07 tokens_per_second_per_gpu:753.6153188158876
Step 5357 | loss:1.301226258277893 lr:1.3441014637672222e-07 tokens_per_second_per_gpu:1072.9798478457556
Step 5358 | loss:1.5189850330352783 lr:1.3264852373310376e-07 tokens_per_second_per_gpu:617.2370105959042
Step 5359 | loss:1.278740406036377 lr:1.3089849964598554e-07 tokens_per_second_per_gpu:776.5504752611677
Step 5360 | loss:1.2445142269134521 lr:1.291600746975119e-07 tokens_per_second_per_gpu:788.0840789303531
Step 5361 | loss:1.3472340106964111 lr:1.2743324946596466e-07 tokens_per_second_per_gpu:1170.1134649521755
Step 5362 | loss:1.2212275266647339 lr:1.257180245257672e-07 tokens_per_second_per_gpu:1225.7708929917706
Step 5363 | loss:1.3488222360610962 lr:1.24014400447488e-07 tokens_per_second_per_gpu:866.6004956825096
Step 5364 | loss:1.32254958152771 lr:1.2232237779783327e-07 tokens_per_second_per_gpu:1011.2772540935661
Step 5365 | loss:1.4116380214691162 lr:1.206419571396544e-07 tokens_per_second_per_gpu:867.05469103818
Step 5366 | loss:1.2334057092666626 lr:1.1897313903193262e-07 tokens_per_second_per_gpu:912.5663834174202
Step 5367 | loss:1.439765453338623 lr:1.1731592402980217e-07 tokens_per_second_per_gpu:668.9438860256636
Step 5368 | loss:1.4322352409362793 lr:1.1567031268453486e-07 tokens_per_second_per_gpu:815.036791569796
Step 5369 | loss:1.4729223251342773 lr:1.1403630554353227e-07 tokens_per_second_per_gpu:1006.4357850218744
Step 5370 | loss:1.3879083395004272 lr:1.1241390315035292e-07 tokens_per_second_per_gpu:890.1793266284993
Step 5371 | loss:1.2294702529907227 lr:1.1080310604467735e-07 tokens_per_second_per_gpu:1136.2566434414662
Step 5372 | loss:1.274853229522705 lr:1.0920391476233914e-07 tokens_per_second_per_gpu:873.7490734461435
Step 5373 | loss:1.3444924354553223 lr:1.0761632983530554e-07 tokens_per_second_per_gpu:953.0563305829089
Step 5374 | loss:1.2289217710494995 lr:1.0604035179168136e-07 tokens_per_second_per_gpu:1073.5562813375432
Step 5375 | loss:1.3205275535583496 lr:1.0447598115571664e-07 tokens_per_second_per_gpu:709.715431906612
Step 5376 | loss:1.165972113609314 lr:1.0292321844779128e-07 tokens_per_second_per_gpu:1188.0695745233436
Step 5377 | loss:1.3165501356124878 lr:1.0138206418443429e-07 tokens_per_second_per_gpu:905.7963216727902
Step 5378 | loss:1.3550611734390259 lr:9.985251887830059e-08 tokens_per_second_per_gpu:908.1762225845381
Step 5379 | loss:1.2766759395599365 lr:9.833458303819819e-08 tokens_per_second_per_gpu:1031.5229308098915
Step 5380 | loss:1.305228590965271 lr:9.682825716905706e-08 tokens_per_second_per_gpu:887.2501310963613
Step 5381 | loss:1.188274621963501 lr:9.533354177196029e-08 tokens_per_second_per_gpu:787.2874375720735
Step 5382 | loss:1.1767090559005737 lr:9.385043734412456e-08 tokens_per_second_per_gpu:862.5734277588549
Step 5383 | loss:1.2862930297851562 lr:9.237894437889248e-08 tokens_per_second_per_gpu:1153.4834833685813
Step 5384 | loss:1.2370091676712036 lr:9.091906336575972e-08 tokens_per_second_per_gpu:842.6780606108614
Step 5385 | loss:1.3753859996795654 lr:8.94707947903478e-08 tokens_per_second_per_gpu:888.574020725292
Step 5386 | loss:1.3940001726150513 lr:8.803413913442747e-08 tokens_per_second_per_gpu:858.9602170809117
Step 5387 | loss:1.5029667615890503 lr:8.660909687589534e-08 tokens_per_second_per_gpu:688.2818230538918
Step 5388 | loss:1.4620393514633179 lr:8.519566848878945e-08 tokens_per_second_per_gpu:909.8936865299829
Step 5389 | loss:1.2977098226547241 lr:8.379385444328146e-08 tokens_per_second_per_gpu:815.65748181079
Step 5390 | loss:1.3058165311813354 lr:8.240365520568449e-08 tokens_per_second_per_gpu:839.8351906564717
Step 5391 | loss:1.2137093544006348 lr:8.102507123844915e-08 tokens_per_second_per_gpu:1474.3639899877483
Step 5392 | loss:1.3091585636138916 lr:7.965810300015196e-08 tokens_per_second_per_gpu:1054.0279666551567
Step 5393 | loss:1.4038342237472534 lr:7.830275094551474e-08 tokens_per_second_per_gpu:756.0467514094107
Step 5394 | loss:1.2963918447494507 lr:7.695901552539685e-08 tokens_per_second_per_gpu:801.6869693639641
Step 5395 | loss:1.3775196075439453 lr:7.56268971867835e-08 tokens_per_second_per_gpu:915.4779785726134
Step 5396 | loss:1.3109078407287598 lr:7.430639637280522e-08 tokens_per_second_per_gpu:800.5485977304797
Step 5397 | loss:1.3429388999938965 lr:7.299751352272232e-08 tokens_per_second_per_gpu:1352.9338155025312
Step 5398 | loss:1.4564776420593262 lr:7.170024907192873e-08 tokens_per_second_per_gpu:764.6215725241613
Step 5399 | loss:1.3774253129959106 lr:7.04146034519637e-08 tokens_per_second_per_gpu:750.905862606443
Step 5400 | loss:1.2292914390563965 lr:6.914057709048847e-08 tokens_per_second_per_gpu:855.8832381057946
Step 5401 | loss:1.3636574745178223 lr:6.78781704113135e-08 tokens_per_second_per_gpu:736.5527192601295
Step 5402 | loss:1.362583041191101 lr:6.662738383436728e-08 tokens_per_second_per_gpu:773.9131999085955
Step 5403 | loss:1.4225997924804688 lr:6.538821777572367e-08 tokens_per_second_per_gpu:937.0888985283605
Step 5404 | loss:1.379746675491333 lr:6.416067264759405e-08 tokens_per_second_per_gpu:729.8814538072666
Step 5405 | loss:1.3049973249435425 lr:6.29447488583118e-08 tokens_per_second_per_gpu:933.8293613451835
Step 5406 | loss:1.3773967027664185 lr:6.174044681235558e-08 tokens_per_second_per_gpu:1122.4093357406623
Step 5407 | loss:1.4296047687530518 lr:6.05477669103338e-08 tokens_per_second_per_gpu:739.2498517172309
Step 5408 | loss:1.3908603191375732 lr:5.936670954898859e-08 tokens_per_second_per_gpu:689.5713531777393
Step 5409 | loss:1.2581040859222412 lr:5.819727512119565e-08 tokens_per_second_per_gpu:797.6076687034132
Step 5410 | loss:1.4418067932128906 lr:5.703946401596826e-08 tokens_per_second_per_gpu:1019.3421762388595
Step 5411 | loss:1.4409838914871216 lr:5.589327661844556e-08 tokens_per_second_per_gpu:663.2082998745652
Step 5412 | loss:1.3876097202301025 lr:5.475871330990811e-08 tokens_per_second_per_gpu:876.118699649249
Step 5413 | loss:1.433173656463623 lr:5.363577446776235e-08 tokens_per_second_per_gpu:948.5120469774461
Step 5414 | loss:1.3156903982162476 lr:5.252446046555614e-08 tokens_per_second_per_gpu:1177.349673627339
Step 5415 | loss:1.2573113441467285 lr:5.142477167296322e-08 tokens_per_second_per_gpu:1191.3417857452644
Step 5416 | loss:1.342978835105896 lr:5.033670845579485e-08 tokens_per_second_per_gpu:773.8126045470851
Step 5417 | loss:1.4270702600479126 lr:4.9260271175992075e-08 tokens_per_second_per_gpu:760.4695799057602
Step 5418 | loss:1.1495927572250366 lr:4.819546019162957e-08 tokens_per_second_per_gpu:1298.8813092888756
Step 5419 | loss:1.2582720518112183 lr:4.714227585691177e-08 tokens_per_second_per_gpu:945.1822874405223
Step 5420 | loss:1.3048831224441528 lr:4.610071852218067e-08 tokens_per_second_per_gpu:1032.6314689439168
Step 5421 | loss:1.2257611751556396 lr:4.5070788533911885e-08 tokens_per_second_per_gpu:1116.4546807246388
Step 5422 | loss:1.2211408615112305 lr:4.405248623470692e-08 tokens_per_second_per_gpu:1128.0579874395537
Step 5423 | loss:1.4298908710479736 lr:4.304581196329704e-08 tokens_per_second_per_gpu:665.2903606377832
Step 5424 | loss:1.288585901260376 lr:4.205076605455882e-08 tokens_per_second_per_gpu:797.1566223813176
Step 5425 | loss:1.1518189907073975 lr:4.106734883948693e-08 tokens_per_second_per_gpu:1025.1396929896623
Step 5426 | loss:1.3395487070083618 lr:4.0095560645217464e-08 tokens_per_second_per_gpu:1135.6803353493701
Step 5427 | loss:1.3572421073913574 lr:3.913540179500851e-08 tokens_per_second_per_gpu:1119.5974838387585
Step 5428 | loss:1.470301866531372 lr:3.818687260825959e-08 tokens_per_second_per_gpu:868.8453320936399
Step 5429 | loss:1.3016254901885986 lr:3.7249973400492187e-08 tokens_per_second_per_gpu:891.0021588925276
Step 5430 | loss:1.3182692527770996 lr:3.632470448336922e-08 tokens_per_second_per_gpu:934.4373029228468
Step 5431 | loss:1.4133756160736084 lr:3.541106616467948e-08 tokens_per_second_per_gpu:850.6351144507371
Step 5432 | loss:1.20756995677948 lr:3.450905874833765e-08 tokens_per_second_per_gpu:1420.5071323885227
Step 5433 | loss:1.239502191543579 lr:3.361868253439981e-08 tokens_per_second_per_gpu:1082.188655337295
Step 5434 | loss:1.2247387170791626 lr:3.273993781904405e-08 tokens_per_second_per_gpu:918.6825054470834
Step 5435 | loss:1.3625776767730713 lr:3.187282489458598e-08 tokens_per_second_per_gpu:828.5566777206645
Step 5436 | loss:1.3454946279525757 lr:3.101734404947098e-08 tokens_per_second_per_gpu:658.3146514956904
Step 5437 | loss:1.3069238662719727 lr:3.017349556826643e-08 tokens_per_second_per_gpu:883.2404704819513
Step 5438 | loss:1.2711231708526611 lr:2.9341279731684987e-08 tokens_per_second_per_gpu:805.3959069205351
Step 5439 | loss:1.472461223602295 lr:2.8520696816553555e-08 tokens_per_second_per_gpu:784.4375739886574
Step 5440 | loss:1.3735342025756836 lr:2.7711747095840454e-08 tokens_per_second_per_gpu:913.3976716902106
Step 5441 | loss:1.327967643737793 lr:2.691443083864764e-08 tokens_per_second_per_gpu:1094.7351761516757
Step 5442 | loss:1.2215158939361572 lr:2.6128748310191295e-08 tokens_per_second_per_gpu:1138.789034670292
Step 5443 | loss:1.426263451576233 lr:2.5354699771829022e-08 tokens_per_second_per_gpu:730.6366308030231
Step 5444 | loss:1.4068843126296997 lr:2.4592285481052078e-08 tokens_per_second_per_gpu:965.1121497028623
Step 5445 | loss:1.2284823656082153 lr:2.3841505691469808e-08 tokens_per_second_per_gpu:847.9997038298753
Step 5446 | loss:1.252670407295227 lr:2.3102360652832995e-08 tokens_per_second_per_gpu:783.4599056635922
Step 5447 | loss:1.2457327842712402 lr:2.2374850611014405e-08 tokens_per_second_per_gpu:906.5313600890978
Step 5448 | loss:1.273289442062378 lr:2.1658975808016566e-08 tokens_per_second_per_gpu:965.1915039729503
Step 5449 | loss:1.3497179746627808 lr:2.0954736481979538e-08 tokens_per_second_per_gpu:839.6236366387502
Step 5450 | loss:1.2147791385650635 lr:2.026213286715761e-08 tokens_per_second_per_gpu:1097.8774333067488
Step 5451 | loss:1.3513119220733643 lr:1.958116519395425e-08 tokens_per_second_per_gpu:819.2595875957211
Step 5452 | loss:1.298092246055603 lr:1.891183368888716e-08 tokens_per_second_per_gpu:821.6079745806504
Step 5453 | loss:1.1754344701766968 lr:1.8254138574611554e-08 tokens_per_second_per_gpu:904.5164785100744
Step 5454 | loss:1.444778561592102 lr:1.7608080069900776e-08 tokens_per_second_per_gpu:1068.9193283115317
Step 5455 | loss:1.4324860572814941 lr:1.697365838967346e-08 tokens_per_second_per_gpu:878.1485606092726
Step 5456 | loss:1.3952903747558594 lr:1.6350873744962467e-08 tokens_per_second_per_gpu:824.9481770629029
Step 5457 | loss:1.4050861597061157 lr:1.5739726342938186e-08 tokens_per_second_per_gpu:950.4553722800558
Step 5458 | loss:1.3993010520935059 lr:1.5140216386900773e-08 tokens_per_second_per_gpu:834.1863743196751
Step 5459 | loss:1.3958100080490112 lr:1.4552344076272371e-08 tokens_per_second_per_gpu:664.5070405943667
Step 5460 | loss:1.3511145114898682 lr:1.3976109606608777e-08 tokens_per_second_per_gpu:1029.8777786927335
Step 5461 | loss:1.2847002744674683 lr:1.341151316959166e-08 tokens_per_second_per_gpu:1073.6030120616067
Step 5462 | loss:1.2270681858062744 lr:1.2858554953032452e-08 tokens_per_second_per_gpu:1037.9295852774337
Step 5463 | loss:1.3504842519760132 lr:1.2317235140876236e-08 tokens_per_second_per_gpu:1004.0970539408814
Step 5464 | loss:1.429997205734253 lr:1.1787553913190084e-08 tokens_per_second_per_gpu:844.5647578398689
Step 5465 | loss:1.4259333610534668 lr:1.1269511446166946e-08 tokens_per_second_per_gpu:826.3534285943883
Step 5466 | loss:1.5805494785308838 lr:1.0763107912137304e-08 tokens_per_second_per_gpu:616.7845152231284
Step 5467 | loss:1.3990038633346558 lr:1.026834347955363e-08 tokens_per_second_per_gpu:1103.0156923819054
Step 5468 | loss:1.2646836042404175 lr:9.785218313002053e-09 tokens_per_second_per_gpu:1044.5846690998162
Step 5469 | loss:1.2818243503570557 lr:9.313732573186794e-09 tokens_per_second_per_gpu:938.6921553605912
Step 5470 | loss:1.3409628868103027 lr:8.853886416949619e-09 tokens_per_second_per_gpu:853.1258846657444
Step 5471 | loss:1.2801792621612549 lr:8.405679997262049e-09 tokens_per_second_per_gpu:871.5058646681965
Step 5472 | loss:1.3127923011779785 lr:7.96911346320983e-09 tokens_per_second_per_gpu:816.8037710849843
Step 5473 | loss:1.2645409107208252 lr:7.544186960024012e-09 tokens_per_second_per_gpu:1080.065154915757
Step 5474 | loss:1.293416976928711 lr:7.130900629049863e-09 tokens_per_second_per_gpu:763.4698354779797
Step 5475 | loss:1.2880785465240479 lr:6.729254607770185e-09 tokens_per_second_per_gpu:901.0324874155921
Step 5476 | loss:1.5194073915481567 lr:6.339249029789772e-09 tokens_per_second_per_gpu:828.6036473544958
Step 5477 | loss:1.1871318817138672 lr:5.9608840248431825e-09 tokens_per_second_per_gpu:1060.620424551236
Step 5478 | loss:1.2712304592132568 lr:5.594159718794733e-09 tokens_per_second_per_gpu:858.967880820696
Step 5479 | loss:1.2357378005981445 lr:5.2390762336346205e-09 tokens_per_second_per_gpu:1137.9774979830906
Step 5480 | loss:1.2657116651535034 lr:4.895633687478917e-09 tokens_per_second_per_gpu:1029.778272139189
Step 5481 | loss:1.1666613817214966 lr:4.563832194569572e-09 tokens_per_second_per_gpu:1101.4972637432372
Step 5482 | loss:1.4019232988357544 lr:4.243671865289955e-09 tokens_per_second_per_gpu:961.2507540681555
Step 5483 | loss:1.2978211641311646 lr:3.935152806129882e-09 tokens_per_second_per_gpu:965.0718061237301
Step 5484 | loss:1.3448140621185303 lr:3.6382751197244762e-09 tokens_per_second_per_gpu:878.223621279206
Step 5485 | loss:1.3645744323730469 lr:3.35303890482308e-09 tokens_per_second_per_gpu:789.0849730273636
Step 5486 | loss:1.3437927961349487 lr:3.0794442563164545e-09 tokens_per_second_per_gpu:882.6784068051094
Step 5487 | loss:1.3258014917373657 lr:2.8174912652134673e-09 tokens_per_second_per_gpu:879.7501233319388
Step 5488 | loss:1.4707680940628052 lr:2.5671800186488624e-09 tokens_per_second_per_gpu:830.9898926051038
Step 5489 | loss:1.4303364753723145 lr:2.3285105998910314e-09 tokens_per_second_per_gpu:810.3203202599709
Step 5490 | loss:1.326790690422058 lr:2.101483088330358e-09 tokens_per_second_per_gpu:828.5975935868626
Step 5491 | loss:1.2218103408813477 lr:1.8860975594908735e-09 tokens_per_second_per_gpu:790.1267032626168
Step 5492 | loss:1.458016037940979 lr:1.6823540850186002e-09 tokens_per_second_per_gpu:1053.3589222809385
Step 5493 | loss:1.5493372678756714 lr:1.4902527326854374e-09 tokens_per_second_per_gpu:707.5683748841984
Step 5494 | loss:1.3454421758651733 lr:1.3097935663969328e-09 tokens_per_second_per_gpu:880.2808676202369
Step 5495 | loss:1.168249487876892 lr:1.1409766461806247e-09 tokens_per_second_per_gpu:1044.4160181228526
Step 5496 | loss:1.3047959804534912 lr:9.838020281938141e-10 tokens_per_second_per_gpu:778.1985200323516
Step 5497 | loss:1.2544037103652954 lr:8.382697647235647e-10 tokens_per_second_per_gpu:960.3067493916104
Step 5498 | loss:1.1786757707595825 lr:7.043799041750453e-10 tokens_per_second_per_gpu:935.6100160087577
Step 5499 | loss:1.2874048948287964 lr:5.821324910909586e-10 tokens_per_second_per_gpu:1218.0713851929368
Step 5500 | loss:1.2697529792785645 lr:4.715275661321127e-10 tokens_per_second_per_gpu:746.1663782863575
Step 5501 | loss:1.4192466735839844 lr:3.725651660968498e-10 tokens_per_second_per_gpu:676.8610740816439
Step 5502 | loss:1.3464140892028809 lr:2.8524532390161724e-10 tokens_per_second_per_gpu:763.7461085818395
Step 5503 | loss:1.3928749561309814 lr:2.0956806859262487e-10 tokens_per_second_per_gpu:837.9956663010163
Step 5504 | loss:1.4041361808776855 lr:1.4553342534195933e-10 tokens_per_second_per_gpu:896.0261257587475
Step 5505 | loss:1.2859240770339966 lr:9.314141545924137e-11 tokens_per_second_per_gpu:792.8856194899439
Step 5506 | loss:1.597116470336914 lr:5.239205636053956e-11 tokens_per_second_per_gpu:719.9193009514217
Step 5507 | loss:1.5208561420440674 lr:2.328536161111394e-11 tokens_per_second_per_gpu:784.2370097756669
Step 5508 | loss:1.3775694370269775 lr:5.821340886558168e-12 tokens_per_second_per_gpu:1028.9069611629152
Step 5509 | loss:1.266069769859314 lr:0.0 tokens_per_second_per_gpu:893.8833924150542