Step 1 | loss:7.98765230178833 lr:1e-05 tokens_per_second_per_gpu:74.66597842979291 mfu:1.2321000595158886 
Step 2 | loss:10.039064407348633 lr:2e-05 tokens_per_second_per_gpu:99.04317273677559 mfu:1.6343601408554138 
Step 3 | loss:3.9081826210021973 lr:3e-05 tokens_per_second_per_gpu:234.32592875767585 mfu:3.8667274820475295 
Step 4 | loss:2.532195568084717 lr:4e-05 tokens_per_second_per_gpu:290.4704132240612 mfu:4.793195253678847 
Step 5 | loss:2.589853525161743 lr:5e-05 tokens_per_second_per_gpu:226.42852587837726 mfu:3.7364085501560247 
Step 6 | loss:2.0885202884674072 lr:6e-05 tokens_per_second_per_gpu:284.77461771422895 mfu:4.699206128588183 
Step 7 | loss:1.7515971660614014 lr:7e-05 tokens_per_second_per_gpu:323.7120094846691 mfu:5.341731194577409 
Step 8 | loss:1.5992693901062012 lr:8e-05 tokens_per_second_per_gpu:267.3100418001711 mfu:4.411014565634735 
Step 9 | loss:1.9307289123535156 lr:9e-05 tokens_per_second_per_gpu:243.7465000106559 mfu:4.0221809649531926 
Step 10 | loss:1.5226410627365112 lr:0.0001 tokens_per_second_per_gpu:238.51817134332802 mfu:3.9359057403106803 
Step 11 | loss:2.0836527347564697 lr:0.00011000000000000002 tokens_per_second_per_gpu:254.12245376160058 mfu:4.193399684682337 
Step 12 | loss:1.597152590751648 lr:0.00012 tokens_per_second_per_gpu:219.70911721677976 mfu:3.625528280641437 
Step 13 | loss:1.6884806156158447 lr:0.00013000000000000002 tokens_per_second_per_gpu:245.15303578929627 mfu:4.045390904111808 
Step 14 | loss:1.506104588508606 lr:0.00014 tokens_per_second_per_gpu:233.91828670343295 mfu:3.8600007798753198 
Step 15 | loss:1.5597869157791138 lr:0.00015000000000000001 tokens_per_second_per_gpu:169.28651675184514 mfu:2.793480133141334 
Step 16 | loss:1.5466811656951904 lr:0.00016 tokens_per_second_per_gpu:225.8265909609852 mfu:3.726475725821032 
Step 17 | loss:1.6803532838821411 lr:0.00017 tokens_per_second_per_gpu:250.38457114148238 mfu:4.131719043839446 
Step 18 | loss:1.4735820293426514 lr:0.00018 tokens_per_second_per_gpu:263.2299274397175 mfu:4.343686590403373 
Step 19 | loss:1.4316495656967163 lr:0.00019 tokens_per_second_per_gpu:329.9372480627042 mfu:5.4444569203202215 
Step 20 | loss:1.6428101062774658 lr:0.0002 tokens_per_second_per_gpu:287.98104205254197 mfu:4.752116914747416 
Step 21 | loss:1.6125845909118652 lr:0.00019999997112454847 tokens_per_second_per_gpu:197.42144299982408 mfu:3.2577483987370885 
Step 22 | loss:1.499793291091919 lr:0.00019999988449821053 tokens_per_second_per_gpu:512.7764346382419 mfu:8.46157632863789 
Step 23 | loss:1.6282153129577637 lr:0.0001999997401210362 tokens_per_second_per_gpu:206.11256854294336 mfu:3.4011649389623826 
Step 24 | loss:1.4875552654266357 lr:0.00019999953799310888 tokens_per_second_per_gpu:263.3086910460402 mfu:4.344986307437539 
Step 25 | loss:1.427045464515686 lr:0.0001999992781145453 tokens_per_second_per_gpu:326.23788468896066 mfu:5.38341190452034 
Step 26 | loss:1.4796165227890015 lr:0.0001999989604854955 tokens_per_second_per_gpu:225.55947614797776 mfu:3.722067932821796 
Step 27 | loss:1.527590274810791 lr:0.000199998585106143 tokens_per_second_per_gpu:180.99624915832212 mfu:2.9867081909307513 
Step 28 | loss:1.4546619653701782 lr:0.0001999981519767045 tokens_per_second_per_gpu:275.8704868063026 mfu:4.552274682000244 
Step 29 | loss:1.5416967868804932 lr:0.00019999766109743018 tokens_per_second_per_gpu:159.95923013384572 mfu:2.6395659859107488 
Step 30 | loss:1.4358744621276855 lr:0.0001999971124686035 tokens_per_second_per_gpu:231.53074634935737 mfu:3.8206028013820874 
Step 31 | loss:1.5036392211914062 lr:0.00019999650609054133 tokens_per_second_per_gpu:256.0305264240961 mfu:4.224885730810184 
Step 32 | loss:1.619471788406372 lr:0.00019999584196359386 tokens_per_second_per_gpu:399.41263468028075 mfu:6.590904469613292 
Step 33 | loss:1.6410393714904785 lr:0.00019999512008814457 tokens_per_second_per_gpu:209.82333593957168 mfu:3.4623981381567703 
Step 34 | loss:1.407210111618042 lr:0.00019999434046461044 tokens_per_second_per_gpu:222.54989521581078 mfu:3.6724053565906747 
Step 35 | loss:1.26964271068573 lr:0.00019999350309344162 tokens_per_second_per_gpu:219.52493236048258 mfu:3.6224889556747244 
Step 36 | loss:1.4455382823944092 lr:0.00019999260797512176 tokens_per_second_per_gpu:150.92527261910004 mfu:2.4904922065850257 
Step 37 | loss:1.390861988067627 lr:0.0001999916551101678 tokens_per_second_per_gpu:216.67241569300913 mfu:3.575418174179926 
Step 38 | loss:1.354355812072754 lr:0.00019999064449912997 tokens_per_second_per_gpu:240.43295243094946 mfu:3.967502485463315 
Step 39 | loss:1.6082862615585327 lr:0.00019998957614259197 tokens_per_second_per_gpu:300.1777547587622 mfu:4.953380874147109 
Step 40 | loss:1.7106165885925293 lr:0.00019998845004117076 tokens_per_second_per_gpu:139.01587948424063 mfu:2.293969448846631 
Step 41 | loss:1.3487714529037476 lr:0.00019998726619551666 tokens_per_second_per_gpu:237.61994820739835 mfu:3.921083718253096 
Step 42 | loss:1.1435306072235107 lr:0.00019998602460631338 tokens_per_second_per_gpu:281.96248046638283 mfu:4.652801667770785 
Step 43 | loss:1.435631513595581 lr:0.00019998472527427795 tokens_per_second_per_gpu:173.91980284198414 mfu:2.8699362673468496 
Step 44 | loss:1.3354684114456177 lr:0.0001999833682001607 tokens_per_second_per_gpu:248.90502328620718 mfu:4.107304296468858 
Step 45 | loss:1.346629023551941 lr:0.0001999819533847454 tokens_per_second_per_gpu:282.6778748455229 mfu:4.6646067425270825 
Step 46 | loss:1.3941729068756104 lr:0.00019998048082884911 tokens_per_second_per_gpu:244.57513583737887 mfu:4.035854692571753 
Step 47 | loss:1.253205418586731 lr:0.0001999789505333222 tokens_per_second_per_gpu:284.32030626681336 mfu:4.691709311789273 
Step 48 | loss:1.810444951057434 lr:0.0001999773624990485 tokens_per_second_per_gpu:238.63810824186766 mfu:3.937884878104579 
Step 49 | loss:1.4149515628814697 lr:0.00019997571672694507 tokens_per_second_per_gpu:237.98929452779072 mfu:3.927178483672467 
Step 50 | loss:1.351197600364685 lr:0.00019997401321796238 tokens_per_second_per_gpu:271.2661069972767 mfu:4.476295544566603 
Step 51 | loss:1.5581765174865723 lr:0.0001999722519730842 tokens_per_second_per_gpu:233.7945648772152 mfu:3.8579591851269215 
Step 52 | loss:1.3401252031326294 lr:0.00019997043299332766 tokens_per_second_per_gpu:286.28808192273084 mfu:4.724180546396472 
Step 53 | loss:1.1916007995605469 lr:0.0001999685562797433 tokens_per_second_per_gpu:280.9909983134687 mfu:4.636770762616979 
Step 54 | loss:1.5399084091186523 lr:0.00019996662183341485 tokens_per_second_per_gpu:279.00382221472205 mfu:4.603979391754056 
Step 55 | loss:1.314745306968689 lr:0.0001999646296554595 tokens_per_second_per_gpu:259.0552568887303 mfu:4.2747982969329135 
Step 56 | loss:1.2632848024368286 lr:0.00019996257974702782 tokens_per_second_per_gpu:267.6997608830403 mfu:4.417445512034897 
Step 57 | loss:1.4120118618011475 lr:0.00019996047210930353 tokens_per_second_per_gpu:263.862934784485 mfu:4.354132156155858 
Step 58 | loss:1.415257215499878 lr:0.00019995830674350394 tokens_per_second_per_gpu:234.87199763832368 mfu:3.8757384334138014 
Step 59 | loss:1.0908033847808838 lr:0.00019995608365087946 tokens_per_second_per_gpu:247.12225468379597 mfu:4.077885954309192 
Step 60 | loss:1.5475053787231445 lr:0.00019995380283271397 tokens_per_second_per_gpu:295.9388272038455 mfu:4.8834322442285 
Step 61 | loss:1.486674189567566 lr:0.00019995146429032472 tokens_per_second_per_gpu:237.91257013117342 mfu:3.925912416641318 
Step 62 | loss:1.247200608253479 lr:0.00019994906802506217 tokens_per_second_per_gpu:334.41974404298395 mfu:5.5184247927063765 
Step 63 | loss:1.3854315280914307 lr:0.00019994661403831024 tokens_per_second_per_gpu:195.3309939402787 mfu:3.2232528699186638 
Step 64 | loss:1.2932158708572388 lr:0.00019994410233148608 tokens_per_second_per_gpu:266.36144177093377 mfu:4.3953612496659495 
Step 65 | loss:1.6265852451324463 lr:0.00019994153290604026 tokens_per_second_per_gpu:305.0537326255529 mfu:5.033841784808312 
Step 66 | loss:1.1955429315567017 lr:0.00019993890576345665 tokens_per_second_per_gpu:289.8558197730373 mfu:4.78305354465006 
Step 67 | loss:1.4174888134002686 lr:0.0001999362209052524 tokens_per_second_per_gpu:223.32764194455217 mfu:3.6852393381566104 
Step 68 | loss:1.322306752204895 lr:0.00019993347833297808 tokens_per_second_per_gpu:268.9444485529232 mfu:4.437984715891757 
Step 69 | loss:1.4700732231140137 lr:0.00019993067804821755 tokens_per_second_per_gpu:342.53324069939293 mfu:5.652309594372013 
Step 70 | loss:1.3482054471969604 lr:0.00019992782005258798 tokens_per_second_per_gpu:174.1815866944626 mfu:2.874256091542582 
Step 71 | loss:1.4807623624801636 lr:0.00019992490434773993 tokens_per_second_per_gpu:225.77359327118333 mfu:3.725601184856964 
Step 72 | loss:1.2782326936721802 lr:0.0001999219309353572 tokens_per_second_per_gpu:266.66032957662105 mfu:4.400293344455576 
Step 73 | loss:1.397825002670288 lr:0.00019991889981715698 tokens_per_second_per_gpu:248.97181888519555 mfu:4.108406523523532 
Step 74 | loss:1.3820163011550903 lr:0.00019991581099488976 tokens_per_second_per_gpu:248.48084065286955 mfu:4.100304650059988 
Step 75 | loss:1.4016153812408447 lr:0.00019991266447033938 tokens_per_second_per_gpu:246.62734465982336 mfu:4.06971920041652 
Step 76 | loss:1.3135335445404053 lr:0.00019990946024532296 tokens_per_second_per_gpu:257.0265780898076 mfu:4.241322069587396 
Step 77 | loss:1.554060697555542 lr:0.00019990619832169099 tokens_per_second_per_gpu:187.71113312456805 mfu:3.097513796220358 
Step 78 | loss:1.5636584758758545 lr:0.0001999028787013273 tokens_per_second_per_gpu:207.8692891698564 mfu:3.4301534506579405 
Step 79 | loss:1.2943743467330933 lr:0.0001998995013861489 tokens_per_second_per_gpu:211.81713956944705 mfu:3.4952988731728163 
Step 80 | loss:1.3046461343765259 lr:0.0001998960663781063 tokens_per_second_per_gpu:198.24082124109324 mfu:3.271269362381636 
Step 81 | loss:1.229073166847229 lr:0.00019989257367918322 tokens_per_second_per_gpu:269.460619898263 mfu:4.446502313312804 
Step 82 | loss:1.2456419467926025 lr:0.00019988902329139672 tokens_per_second_per_gpu:284.6011163092982 mfu:4.696343096510699 
Step 83 | loss:1.4431893825531006 lr:0.0001998854152167972 tokens_per_second_per_gpu:213.90520652339802 mfu:3.5297550936943924 
Step 84 | loss:1.4022624492645264 lr:0.00019988174945746834 tokens_per_second_per_gpu:290.21065827825856 mfu:4.78890890947077 
Step 85 | loss:1.4284534454345703 lr:0.00019987802601552718 tokens_per_second_per_gpu:339.1682799339794 mfu:5.596782720600004 
Step 86 | loss:1.2277686595916748 lr:0.00019987424489312399 tokens_per_second_per_gpu:265.29956484982006 mfu:4.377838695951168 
Step 87 | loss:1.3090426921844482 lr:0.00019987040609244244 tokens_per_second_per_gpu:219.46156817681944 mfu:3.6214433520932228 
Step 88 | loss:1.3790500164031982 lr:0.00019986650961569945 tokens_per_second_per_gpu:260.53522683732393 mfu:4.299220009473097 
Step 89 | loss:1.344897985458374 lr:0.0001998625554651453 tokens_per_second_per_gpu:218.18222233740497 mfu:3.6003322367227044 
Step 90 | loss:1.6607102155685425 lr:0.0001998585436430635 tokens_per_second_per_gpu:225.03755434211087 mfu:3.713455444221302 
Step 91 | loss:1.3776532411575317 lr:0.00019985447415177097 tokens_per_second_per_gpu:279.67497170331933 mfu:4.615054359794852 
Step 92 | loss:1.327250361442566 lr:0.00019985034699361785 tokens_per_second_per_gpu:229.30140886396916 mfu:3.783815406290084 
Step 93 | loss:1.3923280239105225 lr:0.00019984616217098763 tokens_per_second_per_gpu:179.52706425932803 mfu:2.9624644478022457 
Step 94 | loss:1.4927678108215332 lr:0.000199841919686297 tokens_per_second_per_gpu:289.5969967563662 mfu:4.778782578663264 
Step 95 | loss:1.2154462337493896 lr:0.00019983761954199615 tokens_per_second_per_gpu:294.1156375721836 mfu:4.853346894770558 
Step 96 | loss:1.5193123817443848 lr:0.0001998332617405684 tokens_per_second_per_gpu:217.68589781057997 mfu:3.592142141422269 
Step 97 | loss:1.3495049476623535 lr:0.0001998288462845304 tokens_per_second_per_gpu:324.64989320010795 mfu:5.357207675377801 
Step 98 | loss:1.3741071224212646 lr:0.00019982437317643217 tokens_per_second_per_gpu:255.4972036157539 mfu:4.216085108656449 
Step 99 | loss:1.6045734882354736 lr:0.0001998198424188569 tokens_per_second_per_gpu:224.31312271547267 mfu:3.701501241396044 
Step 100 | loss:1.4328902959823608 lr:0.00019981525401442117 tokens_per_second_per_gpu:215.04332683332885 mfu:3.5485357770938677 
Step 101 | loss:1.5311975479125977 lr:0.00019981060796577486 tokens_per_second_per_gpu:197.64527533668124 mfu:3.2614419662944014 
Step 102 | loss:1.1840507984161377 lr:0.0001998059042756011 tokens_per_second_per_gpu:350.03185073790354 mfu:5.776047849317974 
Step 103 | loss:1.399176836013794 lr:0.00019980114294661623 tokens_per_second_per_gpu:170.71094978722007 mfu:2.8169854037420814 
Step 104 | loss:1.6709645986557007 lr:0.00019979632398157006 tokens_per_second_per_gpu:266.2809193156554 mfu:4.394032508999487 
Step 105 | loss:1.6128168106079102 lr:0.00019979144738324555 tokens_per_second_per_gpu:248.9575594356663 mfu:4.1081712213285675 
Step 106 | loss:1.4446676969528198 lr:0.000199786513154459 tokens_per_second_per_gpu:257.5307416437067 mfu:4.24964152053183 
Step 107 | loss:1.3872096538543701 lr:0.00019978152129805993 tokens_per_second_per_gpu:281.935838864338 mfu:4.6523620415828555 
Step 108 | loss:1.3617744445800781 lr:0.00019977647181693118 tokens_per_second_per_gpu:229.1812151108612 mfu:3.781832030012533 
Step 109 | loss:1.1733373403549194 lr:0.00019977136471398892 tokens_per_second_per_gpu:317.8530506875239 mfu:5.245049631776333 
Step 110 | loss:1.37428879737854 lr:0.00019976619999218252 tokens_per_second_per_gpu:196.6036127836129 mfu:3.2442529798159376 
Step 111 | loss:1.4036973714828491 lr:0.00019976097765449463 tokens_per_second_per_gpu:227.981216762165 mfu:3.762030266639971 
Step 112 | loss:1.2086474895477295 lr:0.00019975569770394125 tokens_per_second_per_gpu:328.09803690282047 mfu:5.414107191739542 
Step 113 | loss:1.4422614574432373 lr:0.00019975036014357157 tokens_per_second_per_gpu:356.6457463105658 mfu:5.885186995420122 
Step 114 | loss:1.4818294048309326 lr:0.00019974496497646808 tokens_per_second_per_gpu:245.1493238241612 mfu:4.045329651148142 
Step 115 | loss:1.535966157913208 lr:0.0001997395122057465 tokens_per_second_per_gpu:238.83414034562907 mfu:3.9411197003327314 
Step 116 | loss:1.439671516418457 lr:0.00019973400183455597 tokens_per_second_per_gpu:242.55954406677665 mfu:4.002594420721786 
Step 117 | loss:1.4973511695861816 lr:0.00019972843386607865 tokens_per_second_per_gpu:233.9410845829572 mfu:3.8603769789061144 
Step 118 | loss:1.175944209098816 lr:0.00019972280830353017 tokens_per_second_per_gpu:261.7847175958044 mfu:4.319838471458912 
Step 119 | loss:1.4283499717712402 lr:0.00019971712515015928 tokens_per_second_per_gpu:243.1306298102604 mfu:4.012018187654628 
Step 120 | loss:1.621645212173462 lr:0.0001997113844092481 tokens_per_second_per_gpu:242.77020883430833 mfu:4.006070703736784 
Step 121 | loss:1.6090184450149536 lr:0.00019970558608411196 tokens_per_second_per_gpu:192.98969514744294 mfu:3.1846179461868354 
Step 122 | loss:1.6527099609375 lr:0.00019969973017809945 tokens_per_second_per_gpu:205.66426143587296 mfu:3.393767202738753 
Step 123 | loss:1.4500161409378052 lr:0.00019969381669459235 tokens_per_second_per_gpu:226.6966561887035 mfu:3.7408331003763315 
Step 124 | loss:1.3099397420883179 lr:0.00019968784563700586 tokens_per_second_per_gpu:231.2946927220189 mfu:3.816707564295412 
Step 125 | loss:1.309037685394287 lr:0.00019968181700878818 tokens_per_second_per_gpu:312.67888192676764 mfu:5.159668126408833 
Step 126 | loss:1.3262404203414917 lr:0.00019967573081342103 tokens_per_second_per_gpu:293.7174979690039 mfu:4.846776997220303 
Step 127 | loss:1.333999514579773 lr:0.00019966958705441913 tokens_per_second_per_gpu:246.2725330041207 mfu:4.0638642786529315 
Step 128 | loss:1.5692992210388184 lr:0.00019966338573533063 tokens_per_second_per_gpu:200.69745407847674 mfu:3.311807469948189 
Step 129 | loss:1.2893900871276855 lr:0.00019965712685973683 tokens_per_second_per_gpu:356.05998643587156 mfu:5.875521083425795 
Step 130 | loss:1.2965984344482422 lr:0.0001996508104312523 tokens_per_second_per_gpu:288.10559632191814 mfu:4.7541722460500875 
Step 131 | loss:1.3462436199188232 lr:0.00019964443645352478 tokens_per_second_per_gpu:240.2047637864095 mfu:3.9637370323288215 
Step 132 | loss:1.3413211107254028 lr:0.00019963800493023537 tokens_per_second_per_gpu:285.21667304142 mfu:4.706500701114994 
Step 133 | loss:1.3290538787841797 lr:0.0001996315158650983 tokens_per_second_per_gpu:415.7493374979895 mfu:6.860484443482097 
Step 134 | loss:1.3913893699645996 lr:0.00019962496926186106 tokens_per_second_per_gpu:276.7563189204169 mfu:4.566892233708183 
Step 135 | loss:1.1618374586105347 lr:0.0001996183651243044 tokens_per_second_per_gpu:259.3047429651596 mfu:4.278915189473283 
Step 136 | loss:1.3159260749816895 lr:0.00019961170345624221 tokens_per_second_per_gpu:247.61339780802282 mfu:4.085990548735149 
Step 137 | loss:1.4856376647949219 lr:0.0001996049842615217 tokens_per_second_per_gpu:272.87257897611704 mfu:4.50280472937024 
Step 138 | loss:1.4819691181182861 lr:0.00019959820754402328 tokens_per_second_per_gpu:222.2350578937249 mfu:3.6672100709808495 
Step 139 | loss:1.4080281257629395 lr:0.00019959137330766055 tokens_per_second_per_gpu:276.5623783681175 mfu:4.563691925200134 
Step 140 | loss:1.2526975870132446 lr:0.00019958448155638035 tokens_per_second_per_gpu:276.74602417979787 mfu:4.5667223551263145 
Step 141 | loss:1.514481544494629 lr:0.0001995775322941627 tokens_per_second_per_gpu:196.35633976233717 mfu:3.24017260598789 
Step 142 | loss:1.5777422189712524 lr:0.00019957052552502092 tokens_per_second_per_gpu:187.96073655159293 mfu:3.101632625220662 
Step 143 | loss:1.4849988222122192 lr:0.00019956346125300144 tokens_per_second_per_gpu:300.9639013610871 mfu:4.966353466161334 
Step 144 | loss:1.4054975509643555 lr:0.0001995563394821839 tokens_per_second_per_gpu:307.4380442697483 mfu:5.07318648477069 
Step 145 | loss:1.3743796348571777 lr:0.0001995491602166813 tokens_per_second_per_gpu:250.24941594840527 mfu:4.129488781477174 
Step 146 | loss:1.2076785564422607 lr:0.00019954192346063963 tokens_per_second_per_gpu:261.5249239301299 mfu:4.3155514883151715 
Step 147 | loss:1.4551595449447632 lr:0.0001995346292182382 tokens_per_second_per_gpu:326.0180684537217 mfu:5.379784608632492 
Step 148 | loss:1.3405187129974365 lr:0.00019952727749368956 tokens_per_second_per_gpu:208.0774889406991 mfu:3.4335890575493404 
Step 149 | loss:1.410255789756775 lr:0.0001995198682912393 tokens_per_second_per_gpu:227.6816084892139 mfu:3.7570862830654232 
Step 150 | loss:1.4831125736236572 lr:0.0001995124016151664 tokens_per_second_per_gpu:299.2507784879489 mfu:4.938084382458959 
Step 151 | loss:1.6914247274398804 lr:0.0001995048774697829 tokens_per_second_per_gpu:157.32318942871711 mfu:2.5960673808167414 
Step 152 | loss:1.3269202709197998 lr:0.00019949729585943404 tokens_per_second_per_gpu:307.72250522732077 mfu:5.077880515038901 
Step 153 | loss:1.4428324699401855 lr:0.0001994896567884983 tokens_per_second_per_gpu:231.27580261322984 mfu:3.816395849312863 
Step 154 | loss:1.2016680240631104 lr:0.00019948196026138725 tokens_per_second_per_gpu:304.0827908020175 mfu:5.017819795895527 
Step 155 | loss:1.483058214187622 lr:0.00019947420628254575 tokens_per_second_per_gpu:259.010616098045 mfu:4.274061657274305 
Step 156 | loss:1.26497220993042 lr:0.00019946639485645182 tokens_per_second_per_gpu:221.38634744362045 mfu:3.6532050821214486 
Step 157 | loss:1.404000163078308 lr:0.0001994585259876166 tokens_per_second_per_gpu:223.62455458884634 mfu:3.690138839835944 
Step 158 | loss:1.0665533542633057 lr:0.0001994505996805844 tokens_per_second_per_gpu:303.73354807409646 mfu:5.012056769750204 
Step 159 | loss:1.3749690055847168 lr:0.0001994426159399328 tokens_per_second_per_gpu:308.6414298517038 mfu:5.0930441425464075 
Step 160 | loss:1.7039718627929688 lr:0.00019943457477027238 tokens_per_second_per_gpu:223.75714725636064 mfu:3.692326816702669 
Step 161 | loss:1.4195430278778076 lr:0.0001994264761762471 tokens_per_second_per_gpu:251.78443933322004 mfu:4.154818957864896 
Step 162 | loss:1.4799168109893799 lr:0.00019941832016253397 tokens_per_second_per_gpu:235.05853374585698 mfu:3.8788165575344102 
Step 163 | loss:1.4886605739593506 lr:0.00019941010673384305 tokens_per_second_per_gpu:159.9105548280646 mfu:2.638762770732818 
Step 164 | loss:1.3572845458984375 lr:0.00019940183589491777 tokens_per_second_per_gpu:232.94042713541887 mfu:3.8438646378560843 
Step 165 | loss:1.3566029071807861 lr:0.00019939350765053459 tokens_per_second_per_gpu:224.20028397326578 mfu:3.699639233773395 
Step 166 | loss:1.3173123598098755 lr:0.00019938512200550312 tokens_per_second_per_gpu:272.63275181088466 mfu:4.498847223277499 
Step 167 | loss:1.4178483486175537 lr:0.0001993766789646662 tokens_per_second_per_gpu:201.57920054725292 mfu:3.326357602411511 
Step 168 | loss:1.315194845199585 lr:0.00019936817853289965 tokens_per_second_per_gpu:267.8490774668544 mfu:4.419909458475739 
Step 169 | loss:1.5896135568618774 lr:0.00019935962071511266 tokens_per_second_per_gpu:228.23153269913777 mfu:3.7661608531176123 
Step 170 | loss:1.620816707611084 lr:0.00019935100551624743 tokens_per_second_per_gpu:286.3657241668756 mfu:4.725461759281423 
Step 171 | loss:1.2426737546920776 lr:0.0001993423329412793 tokens_per_second_per_gpu:280.8646743650963 mfu:4.634686228970181 
Step 172 | loss:1.385208249092102 lr:0.00019933360299521672 tokens_per_second_per_gpu:271.6415870951565 mfu:4.4824915264672445 
Step 173 | loss:1.4046847820281982 lr:0.00019932481568310138 tokens_per_second_per_gpu:233.0267000001464 mfu:3.8452882688591297 
Step 174 | loss:1.4348398447036743 lr:0.00019931597101000798 tokens_per_second_per_gpu:256.0718309274867 mfu:4.225567316750074 
Step 175 | loss:1.377253532409668 lr:0.00019930706898104442 tokens_per_second_per_gpu:227.7815385656702 mfu:3.7587352784410744 
Step 176 | loss:1.6399831771850586 lr:0.00019929810960135172 tokens_per_second_per_gpu:243.18495900219537 mfu:4.0129147003907395 
Step 177 | loss:1.3342833518981934 lr:0.00019928909287610395 tokens_per_second_per_gpu:330.60236506609385 mfu:5.455432343353509 
Step 178 | loss:1.2638202905654907 lr:0.00019928001881050838 tokens_per_second_per_gpu:269.4388892103179 mfu:4.446143724535511 
Step 179 | loss:1.4437556266784668 lr:0.0001992708874098054 tokens_per_second_per_gpu:216.49514882623166 mfu:3.5724930063632065 
Step 180 | loss:1.7226250171661377 lr:0.00019926169867926844 tokens_per_second_per_gpu:216.39020812492726 mfu:3.5707613282007835 
Step 181 | loss:1.4288429021835327 lr:0.00019925245262420406 tokens_per_second_per_gpu:313.0809537103781 mfu:5.166302910803735 
Step 182 | loss:1.6099772453308105 lr:0.00019924314924995199 tokens_per_second_per_gpu:260.11407065795817 mfu:4.292270304070791 
Step 183 | loss:1.421165943145752 lr:0.00019923378856188495 tokens_per_second_per_gpu:236.02371924333266 mfu:3.89474355847771 
Step 184 | loss:1.3062824010849 lr:0.00019922437056540889 tokens_per_second_per_gpu:226.04018408998368 mfu:3.730000331169889 
Step 185 | loss:1.4320485591888428 lr:0.0001992148952659627 tokens_per_second_per_gpu:357.40884550976693 mfu:5.897779270891826 
Step 186 | loss:1.2415825128555298 lr:0.00019920536266901856 tokens_per_second_per_gpu:252.72706329935744 mfu:4.170373659875144 
Step 187 | loss:1.2620285749435425 lr:0.00019919577278008154 tokens_per_second_per_gpu:229.0175357493377 mfu:3.7791310763075705 
Step 188 | loss:1.3587137460708618 lr:0.0001991861256046899 tokens_per_second_per_gpu:213.25268558074987 mfu:3.518987524458986 
Step 189 | loss:1.280076026916504 lr:0.00019917642114841507 tokens_per_second_per_gpu:179.80070384920384 mfu:2.9669799093559823 
Step 190 | loss:1.315184473991394 lr:0.0001991666594168613 tokens_per_second_per_gpu:230.83021297056484 mfu:3.8090429553068805 
Step 191 | loss:1.2870604991912842 lr:0.0001991568404156662 tokens_per_second_per_gpu:257.50757703527086 mfu:4.249259269926766 
Step 192 | loss:1.4930377006530762 lr:0.0001991469641505003 tokens_per_second_per_gpu:264.62667467561266 mfu:4.366735004000381 
Step 193 | loss:1.4862335920333862 lr:0.0001991370306270672 tokens_per_second_per_gpu:262.9857483296499 mfu:4.3396572707269465 
Step 194 | loss:1.3666274547576904 lr:0.00019912703985110365 tokens_per_second_per_gpu:298.69544005150203 mfu:4.928920469590114 
Step 195 | loss:1.4681439399719238 lr:0.00019911699182837938 tokens_per_second_per_gpu:267.91485707039374 mfu:4.42099492008945 
Step 196 | loss:1.4168593883514404 lr:0.00019910688656469723 tokens_per_second_per_gpu:288.1949673820913 mfu:4.755647001901066 
Step 197 | loss:1.3587536811828613 lr:0.00019909672406589305 tokens_per_second_per_gpu:214.36371714609908 mfu:3.537321203151457 
Step 198 | loss:1.4292550086975098 lr:0.00019908650433783583 tokens_per_second_per_gpu:237.81367220077703 mfu:3.924280453215807 
Step 199 | loss:1.4508497714996338 lr:0.0001990762273864275 tokens_per_second_per_gpu:232.9061443595506 mfu:3.843298920898027 
Step 200 | loss:1.6364043951034546 lr:0.00019906589321760313 tokens_per_second_per_gpu:232.60409740065134 mfu:3.8383146953663636 
Step 201 | loss:1.3211288452148438 lr:0.0001990555018373308 tokens_per_second_per_gpu:240.43652314223291 mfu:3.9675614075276524 
Step 202 | loss:1.2690809965133667 lr:0.00019904505325161158 tokens_per_second_per_gpu:230.03831116784593 mfu:3.7959753938983316 
Step 203 | loss:1.259891152381897 lr:0.00019903454746647965 tokens_per_second_per_gpu:317.39219516536286 mfu:5.237444827979156 
Step 204 | loss:1.9193254709243774 lr:0.00019902398448800218 tokens_per_second_per_gpu:195.36528683363198 mfu:3.223818753830321 
Step 205 | loss:1.5848803520202637 lr:0.00019901336432227943 tokens_per_second_per_gpu:295.630608357707 mfu:4.8783461733477935 
Step 206 | loss:1.3404186964035034 lr:0.00019900268697544462 tokens_per_second_per_gpu:215.55824113173523 mfu:3.5570326313647675 
Step 207 | loss:1.676941156387329 lr:0.00019899195245366399 tokens_per_second_per_gpu:283.960680616748 mfu:4.685774951935333 
Step 208 | loss:1.39202880859375 lr:0.00019898116076313684 tokens_per_second_per_gpu:344.1497993468275 mfu:5.678985224258627 
Step 209 | loss:1.393122911453247 lr:0.00019897031191009546 tokens_per_second_per_gpu:210.04260611407383 mfu:3.466016423227637 
Step 210 | loss:1.4262278079986572 lr:0.0001989594059008052 tokens_per_second_per_gpu:281.64596181948474 mfu:4.64757863779271 
Step 211 | loss:1.3756111860275269 lr:0.0001989484427415643 tokens_per_second_per_gpu:201.84738600339406 mfu:3.330783062620052 
Step 212 | loss:1.4548088312149048 lr:0.00019893742243870418 tokens_per_second_per_gpu:207.07244096132217 mfu:3.4170042661724884 
Step 213 | loss:1.8892788887023926 lr:0.00019892634499858912 tokens_per_second_per_gpu:237.44430390407118 mfu:3.918185325154471 
Step 214 | loss:1.4922327995300293 lr:0.00019891521042761641 tokens_per_second_per_gpu:285.7205825793498 mfu:4.714815960416896 
Step 215 | loss:1.6011676788330078 lr:0.0001989040187322164 tokens_per_second_per_gpu:277.84447039194544 mfu:4.584848356711288 
Step 216 | loss:1.3668770790100098 lr:0.0001988927699188524 tokens_per_second_per_gpu:235.20681254197 mfu:3.8812633789296136 
Step 217 | loss:1.6222532987594604 lr:0.00019888146399402068 tokens_per_second_per_gpu:218.1175985105588 mfu:3.599265847149062 
Step 218 | loss:1.4461910724639893 lr:0.00019887010096425055 tokens_per_second_per_gpu:222.43053895107082 mfu:3.670435800120883 
Step 219 | loss:1.1547538042068481 lr:0.00019885868083610418 tokens_per_second_per_gpu:380.3479095640402 mfu:6.276308057105808 
Step 220 | loss:1.3047541379928589 lr:0.0001988472036161769 tokens_per_second_per_gpu:295.7775542393494 mfu:4.880770999665277 
Step 221 | loss:1.2281315326690674 lr:0.00019883566931109685 tokens_per_second_per_gpu:277.97887110766766 mfu:4.587066169071385 
Step 222 | loss:1.4962847232818604 lr:0.0001988240779275252 tokens_per_second_per_gpu:272.1188647855832 mfu:4.490367320545712 
Step 223 | loss:1.4854477643966675 lr:0.00019881242947215611 tokens_per_second_per_gpu:324.91302754885396 mfu:5.361549784777137 
Step 224 | loss:1.224272608757019 lr:0.00019880072395171662 tokens_per_second_per_gpu:239.97582664436388 mfu:3.9599592278685867 
Step 225 | loss:1.3131511211395264 lr:0.00019878896137296678 tokens_per_second_per_gpu:318.11400112765347 mfu:5.249355703424704 
Step 226 | loss:1.5066473484039307 lr:0.00019877714174269963 tokens_per_second_per_gpu:223.75761346424778 mfu:3.692334509828475 
Step 227 | loss:1.482935905456543 lr:0.00019876526506774108 tokens_per_second_per_gpu:226.90815978615285 mfu:3.74432322533666 
Step 228 | loss:1.6025071144104004 lr:0.00019875333135495002 tokens_per_second_per_gpu:314.2266640548296 mfu:5.185208841098534 
Step 229 | loss:1.5414317846298218 lr:0.0001987413406112183 tokens_per_second_per_gpu:186.20578022057575 mfu:3.0726732270400405 
Step 230 | loss:1.3400843143463135 lr:0.00019872929284347067 tokens_per_second_per_gpu:219.12712971610523 mfu:3.615924618447512 
Step 231 | loss:1.2900211811065674 lr:0.00019871718805866478 tokens_per_second_per_gpu:314.1465462464702 mfu:5.183886777710044 
Step 232 | loss:1.2928420305252075 lr:0.00019870502626379127 tokens_per_second_per_gpu:382.0387072353655 mfu:6.304208741664949 
Step 233 | loss:1.7336814403533936 lr:0.00019869280746587377 tokens_per_second_per_gpu:232.75390517442364 mfu:3.8407867471744623 
Step 234 | loss:1.5366945266723633 lr:0.00019868053167196865 tokens_per_second_per_gpu:223.78139205200537 mfu:3.6927268920085177 
Step 235 | loss:1.4677999019622803 lr:0.00019866819888916535 tokens_per_second_per_gpu:310.5844993561306 mfu:5.125107688787871 
Step 236 | loss:1.667989730834961 lr:0.0001986558091245861 tokens_per_second_per_gpu:165.03860934921875 mfu:2.7233833223359247 
Step 237 | loss:1.5924032926559448 lr:0.00019864336238538613 tokens_per_second_per_gpu:282.49225499967855 mfu:4.661543738091572 
Step 238 | loss:1.5775108337402344 lr:0.0001986308586787536 tokens_per_second_per_gpu:185.88713659444898 mfu:3.0674151317338323 
Step 239 | loss:1.5035364627838135 lr:0.00019861829801190946 tokens_per_second_per_gpu:258.0011683853641 mfu:4.257404263732724 
Step 240 | loss:1.5241212844848633 lr:0.00019860568039210762 tokens_per_second_per_gpu:285.7770263809 mfu:4.715747367367046 
Step 241 | loss:1.546550989151001 lr:0.0001985930058266348 tokens_per_second_per_gpu:248.65256404828722 mfu:4.103138342327388 
Step 242 | loss:1.558892846107483 lr:0.00019858027432281082 tokens_per_second_per_gpu:149.88648722560578 mfu:2.4733506975327875 
Step 243 | loss:1.464177131652832 lr:0.0001985674858879881 tokens_per_second_per_gpu:192.5378598653554 mfu:3.177161989810734 
Step 244 | loss:1.3557896614074707 lr:0.00019855464052955218 tokens_per_second_per_gpu:224.1943146652391 mfu:3.699540731283645 
Step 245 | loss:1.5698298215866089 lr:0.00019854173825492127 tokens_per_second_per_gpu:224.409609595909 mfu:3.7030934188994817 
Step 246 | loss:1.503772258758545 lr:0.00019852877907154668 tokens_per_second_per_gpu:325.6661805277039 mfu:5.3739779327714485 
Step 247 | loss:1.4738740921020508 lr:0.00019851576298691233 tokens_per_second_per_gpu:310.96150308850184 mfu:5.131328812931166 
Step 248 | loss:1.4135208129882812 lr:0.0001985026900085352 tokens_per_second_per_gpu:377.6943232950881 mfu:6.232519924027493 
Step 249 | loss:1.469713568687439 lr:0.00019848956014396503 tokens_per_second_per_gpu:238.3471485516995 mfu:3.9330836090512316 
Step 250 | loss:1.4901134967803955 lr:0.00019847637340078444 tokens_per_second_per_gpu:220.1323269394236 mfu:3.632511872572097 
Step 251 | loss:1.5635974407196045 lr:0.00019846312978660886 tokens_per_second_per_gpu:307.76621179071793 mfu:5.078601738553216 
Step 252 | loss:1.35623300075531 lr:0.00019844982930908666 tokens_per_second_per_gpu:385.57638474508883 mfu:6.362585699443338 
Step 253 | loss:1.4398834705352783 lr:0.00019843647197589895 tokens_per_second_per_gpu:227.28816929410206 mfu:3.7505939492621634 
Step 254 | loss:1.4739527702331543 lr:0.00019842305779475968 tokens_per_second_per_gpu:247.80237771959915 mfu:4.089108999269074 
Step 255 | loss:1.5723693370819092 lr:0.00019840958677341572 tokens_per_second_per_gpu:171.04179223712265 mfu:2.8224447978434877 
Step 256 | loss:1.2682311534881592 lr:0.0001983960589196467 tokens_per_second_per_gpu:220.56207011039604 mfu:3.6396032761492907 
Step 257 | loss:1.4722994565963745 lr:0.00019838247424126503 tokens_per_second_per_gpu:256.2869564075444 mfu:4.229117208177957 
Step 258 | loss:1.562349796295166 lr:0.000198368832746116 tokens_per_second_per_gpu:225.69399230797964 mfu:3.724287650184771 
Step 259 | loss:1.4033313989639282 lr:0.00019835513444207774 tokens_per_second_per_gpu:251.13224823341181 mfu:4.144056831528536 
Step 260 | loss:1.4846363067626953 lr:0.0001983413793370611 tokens_per_second_per_gpu:231.06810973609814 mfu:3.812968606924074 
Step 261 | loss:1.4124752283096313 lr:0.0001983275674390098 tokens_per_second_per_gpu:316.1994338126911 mfu:5.217762485839932 
Step 262 | loss:1.5341792106628418 lr:0.00019831369875590032 tokens_per_second_per_gpu:258.11382278993574 mfu:4.259263229509325 
Step 263 | loss:1.4132206439971924 lr:0.00019829977329574195 tokens_per_second_per_gpu:220.7610246314353 mfu:3.642886322623314 
Step 264 | loss:1.4542620182037354 lr:0.00019828579106657678 tokens_per_second_per_gpu:259.4722884259818 mfu:4.281679939585607 
Step 265 | loss:1.4588290452957153 lr:0.00019827175207647965 tokens_per_second_per_gpu:253.15595103018845 mfu:4.177450947413529 
Step 266 | loss:1.448444128036499 lr:0.00019825765633355827 tokens_per_second_per_gpu:297.97950749466503 mfu:4.917106514098756 
Step 267 | loss:1.4924795627593994 lr:0.00019824350384595296 tokens_per_second_per_gpu:293.5260017790335 mfu:4.843617024338123 
Step 268 | loss:1.5226399898529053 lr:0.00019822929462183698 tokens_per_second_per_gpu:294.4095570250727 mfu:4.858197004325314 
Step 269 | loss:1.4010992050170898 lr:0.00019821502866941625 tokens_per_second_per_gpu:262.29630043213416 mfu:4.328280351634391 
Step 270 | loss:1.4625554084777832 lr:0.00019820070599692956 tokens_per_second_per_gpu:255.27329628194045 mfu:4.212390303537448 
Step 271 | loss:1.252984642982483 lr:0.0001981863266126483 tokens_per_second_per_gpu:246.6160854602422 mfu:4.069533406822627 
Step 272 | loss:1.4746450185775757 lr:0.00019817189052487668 tokens_per_second_per_gpu:318.24357965572057 mfu:5.251493942492897 
Step 273 | loss:1.5841116905212402 lr:0.00019815739774195175 tokens_per_second_per_gpu:277.58493949309985 mfu:4.580565709612321 
Step 274 | loss:1.494964361190796 lr:0.00019814284827224317 tokens_per_second_per_gpu:252.18290328206498 mfu:4.161394207602613 
Step 275 | loss:1.558307409286499 lr:0.0001981282421241534 tokens_per_second_per_gpu:214.38107344199355 mfu:3.537607607932513 
Step 276 | loss:1.6919187307357788 lr:0.0001981135793061176 tokens_per_second_per_gpu:182.2574097041167 mfu:3.007519221820726 
Step 277 | loss:1.5277605056762695 lr:0.00019809885982660376 tokens_per_second_per_gpu:265.7493831185428 mfu:4.385261368596995 
Step 278 | loss:1.4134764671325684 lr:0.00019808408369411241 tokens_per_second_per_gpu:246.04955816729694 mfu:4.060184861125719 
Step 279 | loss:1.622375726699829 lr:0.00019806925091717697 tokens_per_second_per_gpu:254.92893206239157 mfu:4.206707780059901 
Step 280 | loss:1.5420305728912354 lr:0.00019805436150436352 tokens_per_second_per_gpu:275.0084144071528 mfu:4.538049201043101 
Step 281 | loss:1.3736693859100342 lr:0.00019803941546427074 tokens_per_second_per_gpu:245.40805476169106 mfu:4.04959909769171 
Step 282 | loss:1.4429142475128174 lr:0.00019802441280553017 tokens_per_second_per_gpu:194.4878156481532 mfu:3.2093391699209177 
Step 283 | loss:1.4631565809249878 lr:0.00019800935353680594 tokens_per_second_per_gpu:249.90226525841803 mfu:4.123760277079466 
Step 284 | loss:1.429780125617981 lr:0.00019799423766679496 tokens_per_second_per_gpu:274.407159378469 mfu:4.528127595886314 
Step 285 | loss:1.4440139532089233 lr:0.00019797906520422677 tokens_per_second_per_gpu:282.46874735522874 mfu:4.661155826880405 
Step 286 | loss:1.4858794212341309 lr:0.0001979638361578636 tokens_per_second_per_gpu:233.72298790766902 mfu:3.8567780583233566 
Step 287 | loss:1.3759315013885498 lr:0.00019794855053650035 tokens_per_second_per_gpu:375.10553308493127 mfu:6.18980102260698 
Step 288 | loss:1.5139356851577759 lr:0.0001979332083489646 tokens_per_second_per_gpu:218.37814680091654 mfu:3.6035652827261155 
Step 289 | loss:1.3955137729644775 lr:0.0001979178096041166 tokens_per_second_per_gpu:211.63811793424716 mfu:3.4923447490586885 
Step 290 | loss:1.5261577367782593 lr:0.0001979023543108493 tokens_per_second_per_gpu:272.84501168840677 mfu:4.502349827987538 
Step 291 | loss:1.6401437520980835 lr:0.00019788684247808825 tokens_per_second_per_gpu:259.4036616083334 mfu:4.280547494690527 
Step 292 | loss:1.516852617263794 lr:0.00019787127411479167 tokens_per_second_per_gpu:245.6207038071922 mfu:4.053108124254112 
Step 293 | loss:1.6657558679580688 lr:0.0001978556492299504 tokens_per_second_per_gpu:250.92330792992192 mfu:4.140609004743446 
Step 294 | loss:1.380565881729126 lr:0.000197839967832588 tokens_per_second_per_gpu:220.22372514571762 mfu:3.6340200793589457 
Step 295 | loss:1.2732964754104614 lr:0.00019782422993176062 tokens_per_second_per_gpu:348.99663997651453 mfu:5.758965327029484 
Step 296 | loss:1.3650063276290894 lr:0.00019780843553655704 tokens_per_second_per_gpu:214.5991862218937 mfu:3.5412067942654004 
Step 297 | loss:1.4464308023452759 lr:0.00019779258465609862 tokens_per_second_per_gpu:316.5931795547877 mfu:5.2242598781258645 
Step 298 | loss:1.2688182592391968 lr:0.00019777667729953938 tokens_per_second_per_gpu:263.0393433485359 mfu:4.340541668512229 
Step 299 | loss:1.4778549671173096 lr:0.00019776071347606607 tokens_per_second_per_gpu:236.47675304203307 mfu:3.902219292166331 
Step 300 | loss:1.4377936124801636 lr:0.0001977446931948978 tokens_per_second_per_gpu:249.33196427248353 mfu:4.1143494598171895 
Step 301 | loss:1.3207803964614868 lr:0.00019772861646528655 tokens_per_second_per_gpu:270.3934997977791 mfu:4.461896223683853 
Step 302 | loss:1.3404226303100586 lr:0.0001977124832965167 tokens_per_second_per_gpu:199.96969449306275 mfu:3.299798350837201 
Step 303 | loss:1.6794631481170654 lr:0.00019769629369790535 tokens_per_second_per_gpu:194.61791451549973 mfu:3.211485995363664 
Step 304 | loss:1.3846616744995117 lr:0.00019768004767880206 tokens_per_second_per_gpu:227.79268813618657 mfu:3.7589192629918124 
Step 305 | loss:1.5110670328140259 lr:0.00019766374524858915 tokens_per_second_per_gpu:279.1034233040156 mfu:4.605622958350613 
Step 306 | loss:1.3636748790740967 lr:0.00019764738641668138 tokens_per_second_per_gpu:291.09710522964036 mfu:4.803536606911073 
Step 307 | loss:1.5347626209259033 lr:0.00019763097119252608 tokens_per_second_per_gpu:223.15344164663557 mfu:3.682364773301982 
Step 308 | loss:1.5769678354263306 lr:0.00019761449958560326 tokens_per_second_per_gpu:209.28096537118003 mfu:3.45344821446129 
Step 309 | loss:1.3974425792694092 lr:0.00019759797160542539 tokens_per_second_per_gpu:277.7426623339568 mfu:4.583168371838058 
Step 310 | loss:1.3745685815811157 lr:0.0001975813872615375 tokens_per_second_per_gpu:299.7460644157901 mfu:4.94625733932638 
Step 311 | loss:1.4216623306274414 lr:0.00019756474656351726 tokens_per_second_per_gpu:159.77379420774196 mfu:2.636506016425401 
Step 312 | loss:1.4379456043243408 lr:0.00019754804952097478 tokens_per_second_per_gpu:243.20224263857725 mfu:4.013199906181416 
Step 313 | loss:1.4855265617370605 lr:0.00019753129614355277 tokens_per_second_per_gpu:277.01626045322627 mfu:4.571181656880293 
Step 314 | loss:1.4781057834625244 lr:0.00019751448644092645 tokens_per_second_per_gpu:292.7278259832832 mfu:4.830445932682601 
Step 315 | loss:1.3257367610931396 lr:0.00019749762042280358 tokens_per_second_per_gpu:189.05446647586598 mfu:3.119680801018134 
Step 316 | loss:1.6004585027694702 lr:0.0001974806980989244 tokens_per_second_per_gpu:267.7535184379296 mfu:4.418332591906766 
Step 317 | loss:1.2573952674865723 lr:0.00019746371947906177 tokens_per_second_per_gpu:255.19741414932727 mfu:4.21113813511918 
Step 318 | loss:1.6161330938339233 lr:0.00019744668457302096 tokens_per_second_per_gpu:289.05074629306375 mfu:4.769768630912235 
Step 319 | loss:1.312716007232666 lr:0.0001974295933906398 tokens_per_second_per_gpu:343.3800078281946 mfu:5.666282515530122 
Step 320 | loss:1.2320467233657837 lr:0.00019741244594178857 tokens_per_second_per_gpu:275.3904095543115 mfu:4.544352690978501 
Step 321 | loss:1.387447714805603 lr:0.0001973952422363701 tokens_per_second_per_gpu:361.11887393314805 mfu:5.959000275924951 
Step 322 | loss:1.4397876262664795 lr:0.00019737798228431968 tokens_per_second_per_gpu:251.37976578388052 mfu:4.14814124045315 
Step 323 | loss:1.3119271993637085 lr:0.00019736066609560507 tokens_per_second_per_gpu:187.84275122228794 mfu:3.0996856912312363 
Step 324 | loss:1.6850306987762451 lr:0.0001973432936802266 tokens_per_second_per_gpu:223.53466224085778 mfu:3.6886554819581545 
Step 325 | loss:1.427215576171875 lr:0.00019732586504821688 tokens_per_second_per_gpu:261.22718381487556 mfu:4.310638332130256 
Step 326 | loss:1.4284138679504395 lr:0.00019730838020964118 tokens_per_second_per_gpu:260.6173119680295 mfu:4.300574536615908 
Step 327 | loss:1.4608408212661743 lr:0.00019729083917459717 tokens_per_second_per_gpu:226.1384550051066 mfu:3.7316219479077644 
Step 328 | loss:1.5208466053009033 lr:0.00019727324195321488 tokens_per_second_per_gpu:210.52448395490737 mfu:3.4739681266520908 
Step 329 | loss:1.3326324224472046 lr:0.00019725558855565692 tokens_per_second_per_gpu:198.81174888121464 mfu:3.2806905203730796 
Step 330 | loss:1.5730340480804443 lr:0.00019723787899211828 tokens_per_second_per_gpu:268.58869336646126 mfu:4.432114224462719 
Step 331 | loss:1.5707595348358154 lr:0.00019722011327282638 tokens_per_second_per_gpu:215.94603882580094 mfu:3.5634318719826044 
Step 332 | loss:1.4043693542480469 lr:0.0001972022914080411 tokens_per_second_per_gpu:264.36214926548837 mfu:4.362369940012582 
Step 333 | loss:1.2923657894134521 lr:0.00019718441340805468 tokens_per_second_per_gpu:341.4545774416137 mfu:5.634510041053938 
Step 334 | loss:1.5173192024230957 lr:0.00019716647928319189 tokens_per_second_per_gpu:277.5466328654444 mfu:4.579933593095446 
Step 335 | loss:1.4447932243347168 lr:0.00019714848904380983 tokens_per_second_per_gpu:242.1270895677974 mfu:3.9954582761866777 
Step 336 | loss:1.7033625841140747 lr:0.000197130442700298 tokens_per_second_per_gpu:249.95938040269888 mfu:4.12470276218644 
Step 337 | loss:1.6673882007598877 lr:0.00019711234026307837 tokens_per_second_per_gpu:204.26209538377643 mfu:3.370629370588549 
Step 338 | loss:1.3856526613235474 lr:0.0001970941817426052 tokens_per_second_per_gpu:258.36540367928586 mfu:4.263414689588735 
Step 339 | loss:1.381129503250122 lr:0.00019707596714936527 tokens_per_second_per_gpu:358.84071957099025 mfu:5.921407329522457 
Step 340 | loss:1.4337139129638672 lr:0.00019705769649387762 tokens_per_second_per_gpu:265.693263873683 mfu:4.384335317316534 
Step 341 | loss:1.3773448467254639 lr:0.00019703936978669373 tokens_per_second_per_gpu:293.3505046911793 mfu:4.840721060514475 
Step 342 | loss:1.3951469659805298 lr:0.00019702098703839745 tokens_per_second_per_gpu:255.1441713205934 mfu:4.210259548996941 
Step 343 | loss:1.4953559637069702 lr:0.00019700254825960497 tokens_per_second_per_gpu:245.57417688856205 mfu:4.052340360669962 
Step 344 | loss:1.3956454992294312 lr:0.00019698405346096486 tokens_per_second_per_gpu:227.53022245637538 mfu:3.754588187627678 
Step 345 | loss:1.523754358291626 lr:0.00019696550265315806 tokens_per_second_per_gpu:279.44861250641446 mfu:4.611319095276212 
Step 346 | loss:1.33551025390625 lr:0.00019694689584689776 tokens_per_second_per_gpu:203.59266783521764 mfu:3.3595828171278397 
Step 347 | loss:1.6064910888671875 lr:0.00019692823305292962 tokens_per_second_per_gpu:276.8578901491311 mfu:4.5685683105449915 
Step 348 | loss:1.4483227729797363 lr:0.00019690951428203156 tokens_per_second_per_gpu:375.3993590678616 mfu:6.194649589767943 
Step 349 | loss:1.4090313911437988 lr:0.00019689073954501382 tokens_per_second_per_gpu:332.78343764589397 mfu:5.49142329548316 
Step 350 | loss:1.3747203350067139 lr:0.000196871908852719 tokens_per_second_per_gpu:261.5669874446149 mfu:4.316245599070703 
Step 351 | loss:1.5882797241210938 lr:0.00019685302221602194 tokens_per_second_per_gpu:276.14337596855216 mfu:4.556777760378371 
Step 352 | loss:1.6012171506881714 lr:0.00019683407964582995 tokens_per_second_per_gpu:241.17742613975048 mfu:3.979787412550747 
Step 353 | loss:1.4991052150726318 lr:0.00019681508115308244 tokens_per_second_per_gpu:237.34387628686014 mfu:3.916528119613943 
Step 354 | loss:1.42231023311615 lr:0.00019679602674875128 tokens_per_second_per_gpu:249.99617275028487 mfu:4.125309890822583 
Step 355 | loss:1.5731515884399414 lr:0.00019677691644384048 tokens_per_second_per_gpu:239.8510443886607 mfu:3.957900134451322 
Step 356 | loss:1.480539083480835 lr:0.0001967577502493865 tokens_per_second_per_gpu:209.5917258203622 mfu:3.4585762255847574 
Step 357 | loss:1.644794225692749 lr:0.00019673852817645796 tokens_per_second_per_gpu:244.56731377788626 mfu:4.035725616918168 
Step 358 | loss:1.310672402381897 lr:0.00019671925023615573 tokens_per_second_per_gpu:244.38556694818624 mfu:4.032726523028295 
Step 359 | loss:1.514763355255127 lr:0.00019669991643961305 tokens_per_second_per_gpu:349.26777013692475 mfu:5.763439379252507 
Step 360 | loss:1.4251571893692017 lr:0.00019668052679799533 tokens_per_second_per_gpu:174.76079308321772 mfu:2.8838138612399034 
Step 361 | loss:1.3001604080200195 lr:0.00019666108132250032 tokens_per_second_per_gpu:242.02822809197957 mfu:3.9938269143161107 
Step 362 | loss:1.411096215248108 lr:0.0001966415800243579 tokens_per_second_per_gpu:281.8740899185319 mfu:4.651343091836228 
Step 363 | loss:1.5633989572525024 lr:0.00019662202291483025 tokens_per_second_per_gpu:243.9302729998765 mfu:4.025213493498559 
Step 364 | loss:1.487993597984314 lr:0.00019660241000521181 tokens_per_second_per_gpu:168.99361292377282 mfu:2.7886467829115547 
Step 365 | loss:1.4403668642044067 lr:0.00019658274130682918 tokens_per_second_per_gpu:231.9535631312692 mfu:3.82757990920433 
Step 366 | loss:1.4915382862091064 lr:0.00019656301683104125 tokens_per_second_per_gpu:271.15920266021755 mfu:4.474531463484119 
Step 367 | loss:1.4257676601409912 lr:0.000196543236589239 tokens_per_second_per_gpu:195.99974080068037 mfu:3.234288191009068 
Step 368 | loss:1.488342046737671 lr:0.00019652340059284583 tokens_per_second_per_gpu:237.84830208615625 mfu:3.924851897998747 
Step 369 | loss:1.3047592639923096 lr:0.0001965035088533171 tokens_per_second_per_gpu:262.5428156405194 mfu:4.3323482204189485 
Step 370 | loss:1.5032296180725098 lr:0.0001964835613821405 tokens_per_second_per_gpu:271.8077221675241 mfu:4.485233003065509 
Step 371 | loss:1.5033286809921265 lr:0.00019646355819083589 tokens_per_second_per_gpu:248.2322214740775 mfu:4.096202062624205 
Step 372 | loss:1.5001106262207031 lr:0.00019644349929095526 tokens_per_second_per_gpu:249.4985433948902 mfu:4.117098263903703 
Step 373 | loss:1.2854604721069336 lr:0.00019642338469408284 tokens_per_second_per_gpu:196.11850179596115 mfu:3.2362479246445313 
Step 374 | loss:1.4677900075912476 lr:0.000196403214411835 tokens_per_second_per_gpu:219.65684439322393 mfu:3.6246657010520624 
Step 375 | loss:1.3421710729599 lr:0.00019638298845586018 tokens_per_second_per_gpu:262.94980013007347 mfu:4.339064071792585 
Step 376 | loss:1.2404005527496338 lr:0.00019636270683783916 tokens_per_second_per_gpu:215.00134052582854 mfu:3.5478429403687906 
Step 377 | loss:1.392333745956421 lr:0.00019634236956948467 tokens_per_second_per_gpu:290.9131738904554 mfu:4.800501465355007 
Step 378 | loss:1.4893834590911865 lr:0.00019632197666254175 tokens_per_second_per_gpu:216.1385158157461 mfu:3.5666080295279032 
Step 379 | loss:1.4834928512573242 lr:0.0001963015281287874 tokens_per_second_per_gpu:268.60419688775096 mfu:4.432370055698114 
Step 380 | loss:1.4157992601394653 lr:0.00019628102398003093 tokens_per_second_per_gpu:268.41510585808794 mfu:4.42924977154995 
Step 381 | loss:1.558275818824768 lr:0.00019626046422811357 tokens_per_second_per_gpu:314.71336824711204 mfu:5.193240186523703 
Step 382 | loss:1.424757957458496 lr:0.00019623984888490883 tokens_per_second_per_gpu:315.49817659588274 mfu:5.206190695357364 
Step 383 | loss:1.3444571495056152 lr:0.0001962191779623222 tokens_per_second_per_gpu:280.3965779768906 mfu:4.6269619400785595 
Step 384 | loss:1.4610562324523926 lr:0.00019619845147229138 tokens_per_second_per_gpu:190.24360627283852 mfu:3.1393033820842913 
Step 385 | loss:1.3542020320892334 lr:0.0001961776694267861 tokens_per_second_per_gpu:268.02007265529727 mfu:4.4227311342414355 
Step 386 | loss:1.5116124153137207 lr:0.00019615683183780815 tokens_per_second_per_gpu:205.6982182052265 mfu:3.3943275401028554 
Step 387 | loss:1.6735172271728516 lr:0.00019613593871739148 tokens_per_second_per_gpu:233.7856533944496 mfu:3.8578121323637116 
Step 388 | loss:1.4958975315093994 lr:0.00019611499007760193 tokens_per_second_per_gpu:246.22133709187608 mfu:4.063019469707143 
Step 389 | loss:1.4048364162445068 lr:0.0001960939859305377 tokens_per_second_per_gpu:252.10287713740288 mfu:4.160073656801906 
Step 390 | loss:1.6021814346313477 lr:0.00019607292628832874 tokens_per_second_per_gpu:230.65616523856653 mfu:3.80617090801756 
Step 391 | loss:1.3164232969284058 lr:0.00019605181116313724 tokens_per_second_per_gpu:386.92223308021755 mfu:6.384794205227142 
Step 392 | loss:1.4700394868850708 lr:0.00019603064056715737 tokens_per_second_per_gpu:260.20504993637127 mfu:4.293771597922486 
Step 393 | loss:1.563895583152771 lr:0.00019600941451261534 tokens_per_second_per_gpu:338.52005149824913 mfu:5.586085984133956 
Step 394 | loss:1.2965394258499146 lr:0.0001959881330117694 tokens_per_second_per_gpu:246.3632729675992 mfu:4.065361623451105 
Step 395 | loss:1.392026424407959 lr:0.00019596679607690977 tokens_per_second_per_gpu:175.3843621329515 mfu:2.894103681040654 
Step 396 | loss:1.7640581130981445 lr:0.00019594540372035876 tokens_per_second_per_gpu:210.6742765307235 mfu:3.476439927671234 
Step 397 | loss:1.7049129009246826 lr:0.00019592395595447064 tokens_per_second_per_gpu:232.79588788148175 mfu:3.84147952448687 
Step 398 | loss:1.4221810102462769 lr:0.00019590245279163169 tokens_per_second_per_gpu:252.2452444131163 mfu:4.162422929289436 
Step 399 | loss:1.5492554903030396 lr:0.00019588089424426016 tokens_per_second_per_gpu:283.8705147861665 mfu:4.684287081186672 
Step 400 | loss:1.4373410940170288 lr:0.0001958592803248063 tokens_per_second_per_gpu:285.43618574602164 mfu:4.710122988294401 
Step 401 | loss:1.4377000331878662 lr:0.00019583761104575244 tokens_per_second_per_gpu:263.64185142072006 mfu:4.3504839507565425 
Step 402 | loss:1.6172852516174316 lr:0.00019581588641961266 tokens_per_second_per_gpu:227.3018385549075 mfu:3.7508195124625145 
Step 403 | loss:1.4543306827545166 lr:0.00019579410645893317 tokens_per_second_per_gpu:243.0126956766474 mfu:4.0100720984705145 
Step 404 | loss:1.526158332824707 lr:0.00019577227117629212 tokens_per_second_per_gpu:255.1179926336567 mfu:4.2098275615990515 
Step 405 | loss:1.4206191301345825 lr:0.00019575038058429955 tokens_per_second_per_gpu:269.2105843613936 mfu:4.442376353855277 
Step 406 | loss:1.3606603145599365 lr:0.00019572843469559752 tokens_per_second_per_gpu:260.9919027455295 mfu:4.306755843403253 
Step 407 | loss:1.4752445220947266 lr:0.00019570643352285992 tokens_per_second_per_gpu:207.5316742204311 mfu:3.42458230020859 
Step 408 | loss:1.6404602527618408 lr:0.00019568437707879265 tokens_per_second_per_gpu:251.34793408886642 mfu:4.147615969986652 
Step 409 | loss:1.2405524253845215 lr:0.00019566226537613354 tokens_per_second_per_gpu:255.89459906810333 mfu:4.222642726607595 
Step 410 | loss:1.366924524307251 lr:0.00019564009842765225 tokens_per_second_per_gpu:222.59943379967152 mfu:3.673222817145089 
Step 411 | loss:1.5161458253860474 lr:0.00019561787624615043 tokens_per_second_per_gpu:256.54905775047354 mfu:4.23344227143988 
Step 412 | loss:1.3420145511627197 lr:0.00019559559884446155 tokens_per_second_per_gpu:179.40428546308706 mfu:2.9604384144556386 
Step 413 | loss:1.4726375341415405 lr:0.00019557326623545102 tokens_per_second_per_gpu:283.95943415665164 mfu:4.685754383483794 
Step 414 | loss:1.4097306728363037 lr:0.00019555087843201613 tokens_per_second_per_gpu:236.85623605619477 mfu:3.908481328158715 
Step 415 | loss:1.4280649423599243 lr:0.00019552843544708607 tokens_per_second_per_gpu:290.46887854396374 mfu:4.793169929167213 
Step 416 | loss:1.5033880472183228 lr:0.00019550593729362185 tokens_per_second_per_gpu:260.04409377968653 mfu:4.291115581160888 
Step 417 | loss:1.3067684173583984 lr:0.00019548338398461633 tokens_per_second_per_gpu:261.231889246234 mfu:4.310715978769043 
Step 418 | loss:1.3412443399429321 lr:0.00019546077553309426 tokens_per_second_per_gpu:215.3327292331346 mfu:3.553311348532471 
Step 419 | loss:1.4335887432098389 lr:0.00019543811195211225 tokens_per_second_per_gpu:221.05224695461965 mfu:3.647691925513326 
Step 420 | loss:1.6104865074157715 lr:0.00019541539325475867 tokens_per_second_per_gpu:182.10695373601337 mfu:3.00503647383894 
Step 421 | loss:1.4033160209655762 lr:0.00019539261945415387 tokens_per_second_per_gpu:256.89628427582016 mfu:4.239172027234178 
Step 422 | loss:1.4044990539550781 lr:0.0001953697905634498 tokens_per_second_per_gpu:267.9476319895123 mfu:4.421535755161136 
Step 423 | loss:1.467797040939331 lr:0.00019534690659583044 tokens_per_second_per_gpu:254.777733367446 mfu:4.2042127759769325 
Step 424 | loss:1.446829080581665 lr:0.00019532396756451146 tokens_per_second_per_gpu:245.74925035423541 mfu:4.055229334095506 
Step 425 | loss:1.5729963779449463 lr:0.00019530097348274036 tokens_per_second_per_gpu:211.69158471032068 mfu:3.493227030646202 
Step 426 | loss:1.4548497200012207 lr:0.0001952779243637964 tokens_per_second_per_gpu:271.71899110528744 mfu:4.483768808135477 
Step 427 | loss:1.4811944961547852 lr:0.00019525482022099072 tokens_per_second_per_gpu:255.39961280786795 mfu:4.2144747147028285 
Step 428 | loss:1.3655109405517578 lr:0.00019523166106766616 tokens_per_second_per_gpu:217.7998594741775 mfu:3.5940226789234693 
Step 429 | loss:1.2976648807525635 lr:0.00019520844691719725 tokens_per_second_per_gpu:281.4185301603511 mfu:4.6438256760469825 
Step 430 | loss:1.4447888135910034 lr:0.00019518517778299046 tokens_per_second_per_gpu:254.3731757797936 mfu:4.197536972106059 
Step 431 | loss:1.3480716943740845 lr:0.00019516185367848393 tokens_per_second_per_gpu:293.19430255471366 mfu:4.838143492180366 
Step 432 | loss:1.5025641918182373 lr:0.00019513847461714748 tokens_per_second_per_gpu:260.3854384612187 mfu:4.2967482777554515 
Step 433 | loss:1.3563716411590576 lr:0.00019511504061248277 tokens_per_second_per_gpu:302.0435208563963 mfu:4.984168798825538 
Step 434 | loss:1.2843632698059082 lr:0.00019509155167802314 tokens_per_second_per_gpu:412.47025333271785 mfu:6.806374661756172 
Step 435 | loss:1.647051215171814 lr:0.00019506800782733365 tokens_per_second_per_gpu:209.5084389605025 mfu:3.4572018681177017 
Step 436 | loss:1.7552591562271118 lr:0.0001950444090740111 tokens_per_second_per_gpu:235.60374992699386 mfu:3.887813438086367 
Step 437 | loss:1.4570558071136475 lr:0.00019502075543168402 tokens_per_second_per_gpu:229.78610147795285 mfu:3.791813557671677 
Step 438 | loss:1.4571272134780884 lr:0.00019499704691401253 tokens_per_second_per_gpu:263.7815724787483 mfu:4.3527895567036206 
Step 439 | loss:1.5519468784332275 lr:0.00019497328353468854 tokens_per_second_per_gpu:233.95853090128352 mfu:3.8606648691916274 
Step 440 | loss:1.4013489484786987 lr:0.00019494946530743566 tokens_per_second_per_gpu:377.777950157494 mfu:6.233899892043907 
Step 441 | loss:1.4140836000442505 lr:0.00019492559224600905 tokens_per_second_per_gpu:315.6892943450547 mfu:5.2093444234016655 
Step 442 | loss:1.5702942609786987 lr:0.0001949016643641957 tokens_per_second_per_gpu:245.95703762977573 mfu:4.058658134198896 
Step 443 | loss:1.4476016759872437 lr:0.00019487768167581411 tokens_per_second_per_gpu:169.08408300392966 mfu:2.790139674232204 
Step 444 | loss:1.3510215282440186 lr:0.00019485364419471454 tokens_per_second_per_gpu:218.23383756110397 mfu:3.6011839649331807 
Step 445 | loss:1.6142531633377075 lr:0.00019482955193477887 tokens_per_second_per_gpu:225.35771053753595 mfu:3.7187384991779657 
Step 446 | loss:1.4211475849151611 lr:0.00019480540490992055 tokens_per_second_per_gpu:217.20538284950908 mfu:3.5842129275475667 
Step 447 | loss:1.5560054779052734 lr:0.0001947812031340847 tokens_per_second_per_gpu:270.72388831357136 mfu:4.467348127195086 
Step 448 | loss:1.2774600982666016 lr:0.00019475694662124813 tokens_per_second_per_gpu:183.2901485990827 mfu:3.024560954624756 
Step 449 | loss:1.358637809753418 lr:0.00019473263538541914 tokens_per_second_per_gpu:245.8174198462511 mfu:4.056354232435232 
Step 450 | loss:1.503928542137146 lr:0.00019470826944063772 tokens_per_second_per_gpu:217.21896378786144 mfu:3.584437033295648 
Step 451 | loss:1.3215651512145996 lr:0.00019468384880097535 tokens_per_second_per_gpu:258.9448805001383 mfu:4.272976921819197 
Step 452 | loss:1.4675062894821167 lr:0.00019465937348053528 tokens_per_second_per_gpu:209.64609126600593 mfu:3.4594733365611603 
Step 453 | loss:1.3626524209976196 lr:0.00019463484349345218 tokens_per_second_per_gpu:343.87393458772726 mfu:5.674433044092324 
Step 454 | loss:1.3487080335617065 lr:0.00019461025885389227 tokens_per_second_per_gpu:218.3976922203878 mfu:3.6038878113127653 
Step 455 | loss:1.3497577905654907 lr:0.00019458561957605354 tokens_per_second_per_gpu:231.25942675735146 mfu:3.816125623255069 
Step 456 | loss:1.351599097251892 lr:0.00019456092567416526 tokens_per_second_per_gpu:217.06861838187393 mfu:3.581956109753752 
Step 457 | loss:1.2383512258529663 lr:0.0001945361771624885 tokens_per_second_per_gpu:290.28872572130473 mfu:4.7901971387720685 
Step 458 | loss:1.5449084043502808 lr:0.00019451137405531563 tokens_per_second_per_gpu:273.2055755586419 mfu:4.508299669874277 
Step 459 | loss:1.4134702682495117 lr:0.00019448651636697078 tokens_per_second_per_gpu:182.00356790982738 mfu:3.003330453436132 
Step 460 | loss:1.4338808059692383 lr:0.0001944616041118094 tokens_per_second_per_gpu:208.9790889462474 mfu:3.448466802994545 
Step 461 | loss:1.5540558099746704 lr:0.00019443663730421863 tokens_per_second_per_gpu:271.43051363825293 mfu:4.47900849946777 
Step 462 | loss:1.2881697416305542 lr:0.0001944116159586169 tokens_per_second_per_gpu:258.7589959574993 mfu:4.269909549491598 
Step 463 | loss:1.2614043951034546 lr:0.0001943865400894544 tokens_per_second_per_gpu:287.39219267422413 mfu:4.7424000213331885 
Step 464 | loss:1.495157241821289 lr:0.0001943614097112126 tokens_per_second_per_gpu:263.87280474891514 mfu:4.354295025296764 
Step 465 | loss:1.3996104001998901 lr:0.00019433622483840452 tokens_per_second_per_gpu:212.18392056802134 mfu:3.5013513069542554 
Step 466 | loss:1.4476211071014404 lr:0.00019431098548557468 tokens_per_second_per_gpu:298.41355613219855 mfu:4.924268964298759 
Step 467 | loss:1.4541497230529785 lr:0.000194285691667299 tokens_per_second_per_gpu:217.70079781558624 mfu:3.59238801373843 
Step 468 | loss:1.3681833744049072 lr:0.00019426034339818494 tokens_per_second_per_gpu:247.52450092423584 mfu:4.084523617502101 
Step 469 | loss:1.2186453342437744 lr:0.00019423494069287128 tokens_per_second_per_gpu:367.0614372870537 mfu:6.0570614386660075 
Step 470 | loss:1.6071962118148804 lr:0.00019420948356602838 tokens_per_second_per_gpu:208.34995074582477 mfu:3.438085083897228 
Step 471 | loss:1.655518651008606 lr:0.0001941839720323579 tokens_per_second_per_gpu:261.9079186632364 mfu:4.321871472910277 
Step 472 | loss:1.4372344017028809 lr:0.00019415840610659304 tokens_per_second_per_gpu:265.0518174537922 mfu:4.373750494231855 
Step 473 | loss:1.5084853172302246 lr:0.00019413278580349835 tokens_per_second_per_gpu:279.52161719740326 mfu:4.612523781614003 
Step 474 | loss:1.3546192646026611 lr:0.0001941071111378697 tokens_per_second_per_gpu:239.50856830853974 mfu:3.9522487680917884 
Step 475 | loss:1.4856305122375488 lr:0.00019408138212453454 tokens_per_second_per_gpu:285.26494244463987 mfu:4.707297218294983 
Step 476 | loss:1.4248852729797363 lr:0.00019405559877835158 tokens_per_second_per_gpu:274.39860359956197 mfu:4.527986412767547 
Step 477 | loss:1.4790254831314087 lr:0.0001940297611142109 tokens_per_second_per_gpu:238.61851976561312 mfu:3.9375616390167565 
Step 478 | loss:1.3152990341186523 lr:0.00019400386914703407 tokens_per_second_per_gpu:234.03770369417146 mfu:3.861971338414701 
Step 479 | loss:1.226909875869751 lr:0.00019397792289177384 tokens_per_second_per_gpu:520.9839962904464 mfu:8.597013343096492 
Step 480 | loss:1.3226699829101562 lr:0.00019395192236341445 tokens_per_second_per_gpu:290.06108947272423 mfu:4.786440800995183 
Step 481 | loss:1.4620630741119385 lr:0.00019392586757697143 tokens_per_second_per_gpu:282.31189159120544 mfu:4.658567472716262 
Step 482 | loss:1.5861213207244873 lr:0.00019389975854749162 tokens_per_second_per_gpu:271.39666588383204 mfu:4.4784499610127275 
Step 483 | loss:1.4146252870559692 lr:0.0001938735952900533 tokens_per_second_per_gpu:267.73625376141706 mfu:4.4180476989822255 
Step 484 | loss:1.3704735040664673 lr:0.00019384737781976593 tokens_per_second_per_gpu:232.8519464653652 mfu:3.8424045747707036 
Step 485 | loss:1.3353731632232666 lr:0.00019382110615177037 tokens_per_second_per_gpu:198.78096643547303 mfu:3.2801825640852513 
Step 486 | loss:1.6430206298828125 lr:0.00019379478030123872 tokens_per_second_per_gpu:241.2788740647465 mfu:3.981461454692214 
Step 487 | loss:1.362246036529541 lr:0.0001937684002833744 tokens_per_second_per_gpu:238.66999640427298 mfu:3.9384110803672923 
Step 488 | loss:1.462471842765808 lr:0.0001937419661134121 tokens_per_second_per_gpu:195.64388720609625 mfu:3.228416075699171 
Step 489 | loss:1.5940293073654175 lr:0.00019371547780661782 tokens_per_second_per_gpu:251.19119851614266 mfu:4.1450295991583 
Step 490 | loss:1.3565804958343506 lr:0.0001936889353782888 tokens_per_second_per_gpu:161.3354973158208 mfu:2.662276448058053 
Step 491 | loss:1.267594337463379 lr:0.00019366233884375347 tokens_per_second_per_gpu:249.8443612239757 mfu:4.122804774107657 
Step 492 | loss:1.5490715503692627 lr:0.0001936356882183716 tokens_per_second_per_gpu:227.33990141594248 mfu:3.751447606466407 
Step 493 | loss:1.3963927030563354 lr:0.0001936089835175342 tokens_per_second_per_gpu:220.3364148017748 mfu:3.63587962683766 
Step 494 | loss:1.2773312330245972 lr:0.00019358222475666348 tokens_per_second_per_gpu:234.11916354487516 mfu:3.8633155475044485 
Step 495 | loss:1.4690877199172974 lr:0.00019355541195121282 tokens_per_second_per_gpu:262.2532782613652 mfu:4.327570421619682 
Step 496 | loss:1.4393340349197388 lr:0.0001935285451166669 tokens_per_second_per_gpu:282.0981581818805 mfu:4.655040552532696 
Step 497 | loss:1.5905356407165527 lr:0.0001935016242685415 tokens_per_second_per_gpu:202.27087151833732 mfu:3.337771205535186 
Step 498 | loss:1.7382197380065918 lr:0.0001934746494223837 tokens_per_second_per_gpu:240.047315762454 mfu:3.961138904992036 
Step 499 | loss:1.4774279594421387 lr:0.0001934476205937717 tokens_per_second_per_gpu:273.8040445525612 mfu:4.518175301300172 
Step 500 | loss:1.4275606870651245 lr:0.00019342053779831492 tokens_per_second_per_gpu:321.17873050908236 mfu:5.299928311360313 
Step 501 | loss:1.5056462287902832 lr:0.0001933934010516539 tokens_per_second_per_gpu:259.13243454558005 mfu:4.276071843434247 
Step 502 | loss:1.5090826749801636 lr:0.00019336621036946031 tokens_per_second_per_gpu:304.07429601388617 mfu:5.017679619215567 
Step 503 | loss:1.4755032062530518 lr:0.00019333896576743712 tokens_per_second_per_gpu:253.77650197724515 mfu:4.187690964016542 
Step 504 | loss:1.2879717350006104 lr:0.00019331166726131824 tokens_per_second_per_gpu:263.2724895329001 mfu:4.344388928451387 
Step 505 | loss:1.1979225873947144 lr:0.00019328431486686885 tokens_per_second_per_gpu:237.01115528125197 mfu:3.911037726540243 
Step 506 | loss:1.6587231159210205 lr:0.00019325690859988516 tokens_per_second_per_gpu:198.5917482664875 mfu:3.2770601819485496 
Step 507 | loss:1.4318394660949707 lr:0.0001932294484761946 tokens_per_second_per_gpu:264.9826138947441 mfu:4.372608532243075 
Step 508 | loss:1.3669357299804688 lr:0.00019320193451165564 tokens_per_second_per_gpu:205.40281964517422 mfu:3.3894530230728055 
Step 509 | loss:1.6728177070617676 lr:0.00019317436672215774 tokens_per_second_per_gpu:223.6919026835572 mfu:3.6912501838944647 
Step 510 | loss:1.5242958068847656 lr:0.00019314674512362165 tokens_per_second_per_gpu:269.0010304940449 mfu:4.438918402350967 
Step 511 | loss:1.4835196733474731 lr:0.00019311906973199907 tokens_per_second_per_gpu:253.68972865755953 mfu:4.186259074759916 
Step 512 | loss:1.3810994625091553 lr:0.00019309134056327276 tokens_per_second_per_gpu:177.06191747475256 mfu:2.9217858474026435 
Step 513 | loss:1.6162447929382324 lr:0.0001930635576334566 tokens_per_second_per_gpu:197.78626671219575 mfu:3.263768534375552 
Step 514 | loss:1.6156015396118164 lr:0.00019303572095859546 tokens_per_second_per_gpu:233.68487223145334 mfu:3.8561490927901723 
Step 515 | loss:1.645227313041687 lr:0.00019300783055476527 tokens_per_second_per_gpu:203.73723681626126 mfu:3.361968421038669 
Step 516 | loss:1.3398206233978271 lr:0.000192979886438073 tokens_per_second_per_gpu:329.23040762473556 mfu:5.432792998357311 
Step 517 | loss:1.276424765586853 lr:0.00019295188862465668 tokens_per_second_per_gpu:236.08775580492525 mfu:3.89580025729836 
Step 518 | loss:1.2767120599746704 lr:0.00019292383713068518 tokens_per_second_per_gpu:351.88291065730056 mfu:5.806593100111159 
Step 519 | loss:1.4379724264144897 lr:0.0001928957319723586 tokens_per_second_per_gpu:263.6130814698193 mfu:4.350009203636602 
Step 520 | loss:1.5025278329849243 lr:0.00019286757316590788 tokens_per_second_per_gpu:307.1037015872941 mfu:5.067669331609189 
Step 521 | loss:1.438103199005127 lr:0.00019283936072759497 tokens_per_second_per_gpu:286.1824377353572 mfu:4.722437259664177 
Step 522 | loss:1.7407827377319336 lr:0.0001928110946737128 tokens_per_second_per_gpu:232.49180966962 mfu:3.836461780250322 
Step 523 | loss:1.5321745872497559 lr:0.00019278277502058535 tokens_per_second_per_gpu:203.61083470673395 mfu:3.3598825976161852 
Step 524 | loss:1.5310993194580078 lr:0.0001927544017845674 tokens_per_second_per_gpu:268.5627936689276 mfu:4.431686840806283 
Step 525 | loss:1.4606800079345703 lr:0.0001927259749820448 tokens_per_second_per_gpu:185.190205518114 mfu:3.055914729024475 
Step 526 | loss:1.3951632976531982 lr:0.0001926974946294342 tokens_per_second_per_gpu:250.48926062626134 mfu:4.133446576554338 
Step 527 | loss:1.273565411567688 lr:0.00019266896074318334 tokens_per_second_per_gpu:315.5595322004377 mfu:5.207203154386409 
Step 528 | loss:1.2840754985809326 lr:0.0001926403733397708 tokens_per_second_per_gpu:194.02975819534157 mfu:3.201780538443242 
Step 529 | loss:1.4903149604797363 lr:0.00019261173243570603 tokens_per_second_per_gpu:244.62498916588694 mfu:4.036677346882507 
Step 530 | loss:1.3139203786849976 lr:0.0001925830380475294 tokens_per_second_per_gpu:207.18467315215935 mfu:3.4188562647924505 
Step 531 | loss:1.6197905540466309 lr:0.0001925542901918122 tokens_per_second_per_gpu:332.52994313937864 mfu:5.487240257865055 
Step 532 | loss:1.4155652523040771 lr:0.0001925254888851566 tokens_per_second_per_gpu:191.9114018527053 mfu:3.1668244978109987 
Step 533 | loss:1.4560658931732178 lr:0.00019249663414419558 tokens_per_second_per_gpu:344.23211780268474 mfu:5.680343601614605 
Step 534 | loss:1.2208166122436523 lr:0.00019246772598559302 tokens_per_second_per_gpu:359.4799795993273 mfu:5.931956073883998 
Step 535 | loss:1.5236271619796753 lr:0.00019243876442604364 tokens_per_second_per_gpu:218.1564889630002 mfu:3.5999075976460806 
Step 536 | loss:1.4095265865325928 lr:0.000192409749482273 tokens_per_second_per_gpu:273.59194367232345 mfu:4.514675320282578 
Step 537 | loss:1.590224027633667 lr:0.00019238068117103751 tokens_per_second_per_gpu:251.09431086087469 mfu:4.14343080827211 
Step 538 | loss:1.58504319190979 lr:0.00019235155950912436 tokens_per_second_per_gpu:219.3141746153419 mfu:3.619011138390438 
Step 539 | loss:1.2802681922912598 lr:0.0001923223845133516 tokens_per_second_per_gpu:323.5555095764644 mfu:5.339148712565275 
Step 540 | loss:1.4234371185302734 lr:0.00019229315620056803 tokens_per_second_per_gpu:254.1562033597449 mfu:4.1939566034123485 
Step 541 | loss:1.6069190502166748 lr:0.00019226387458765327 tokens_per_second_per_gpu:193.3736548649168 mfu:3.1909538544639373 
Step 542 | loss:1.2754948139190674 lr:0.00019223453969151772 tokens_per_second_per_gpu:327.0684333681653 mfu:5.397117197059177 
Step 543 | loss:1.5675938129425049 lr:0.00019220515152910256 tokens_per_second_per_gpu:245.66005983760442 mfu:4.053757557482378 
Step 544 | loss:1.3483326435089111 lr:0.0001921757101173797 tokens_per_second_per_gpu:262.3549990649621 mfu:4.329248966665248 
Step 545 | loss:1.4670966863632202 lr:0.0001921462154733518 tokens_per_second_per_gpu:299.04666837875953 mfu:4.934716261087369 
Step 546 | loss:1.3019812107086182 lr:0.00019211666761405233 tokens_per_second_per_gpu:288.962808954915 mfu:4.768317533614038 
Step 547 | loss:1.2591958045959473 lr:0.00019208706655654542 tokens_per_second_per_gpu:332.9768787048969 mfu:5.49461536160648 
Step 548 | loss:1.3096723556518555 lr:0.00019205741231792596 tokens_per_second_per_gpu:222.11992698669616 mfu:3.665310239218307 
Step 549 | loss:1.3844577074050903 lr:0.00019202770491531955 tokens_per_second_per_gpu:231.22434967927538 mfu:3.8155467991253373 
Step 550 | loss:1.5304229259490967 lr:0.00019199794436588243 tokens_per_second_per_gpu:288.38359974502936 mfu:4.758759717363853 
Step 551 | loss:1.5043872594833374 lr:0.00019196813068680165 tokens_per_second_per_gpu:249.04486016044027 mfu:4.109611813556136 
Step 552 | loss:1.3132271766662598 lr:0.00019193826389529484 tokens_per_second_per_gpu:302.04493385917965 mfu:4.984192115479924 
Step 553 | loss:1.601104497909546 lr:0.00019190834400861033 tokens_per_second_per_gpu:230.34099177349958 mfu:3.8009700755469598 
Step 554 | loss:1.4359478950500488 lr:0.0001918783710440272 tokens_per_second_per_gpu:256.82312798760347 mfu:4.237964839315915 
Step 555 | loss:1.399501085281372 lr:0.00019184834501885504 tokens_per_second_per_gpu:241.44516582362408 mfu:3.9842055168516985 
Step 556 | loss:1.1897376775741577 lr:0.00019181826595043413 tokens_per_second_per_gpu:333.2411133463723 mfu:5.498975627477692 
Step 557 | loss:1.5436019897460938 lr:0.0001917881338561355 tokens_per_second_per_gpu:195.05329426785894 mfu:3.218670410944559 
Step 558 | loss:1.4120593070983887 lr:0.0001917579487533606 tokens_per_second_per_gpu:294.3632718830085 mfu:4.857433230415279 
Step 559 | loss:1.4468989372253418 lr:0.00019172771065954165 tokens_per_second_per_gpu:296.63393712033985 mfu:4.894902595082979 
Step 560 | loss:1.3870059251785278 lr:0.00019169741959214142 tokens_per_second_per_gpu:237.49458963137616 mfu:3.919015114690591 
Step 561 | loss:1.4172890186309814 lr:0.0001916670755686533 tokens_per_second_per_gpu:258.04386368169685 mfu:4.258108799831478 
Step 562 | loss:1.2997150421142578 lr:0.0001916366786066012 tokens_per_second_per_gpu:217.46626470921618 mfu:3.588517867516631 
Step 563 | loss:1.265599250793457 lr:0.00019160622872353963 tokens_per_second_per_gpu:252.73602068196206 mfu:4.170521470054189 
Step 564 | loss:1.389436960220337 lr:0.00019157572593705372 tokens_per_second_per_gpu:261.4553979701081 mfu:4.314404206229244 
Step 565 | loss:1.4039711952209473 lr:0.00019154517026475905 tokens_per_second_per_gpu:293.2653874948444 mfu:4.839316499764378 
Step 566 | loss:1.464211344718933 lr:0.00019151456172430183 tokens_per_second_per_gpu:347.7093201058331 mfu:5.7377226282443345 
Step 567 | loss:1.3491936922073364 lr:0.00019148390033335878 tokens_per_second_per_gpu:273.80575466950796 mfu:4.518203520781603 
Step 568 | loss:1.5436327457427979 lr:0.00019145318610963713 tokens_per_second_per_gpu:231.06949859203445 mfu:3.8129915251194517 
Step 569 | loss:1.1025220155715942 lr:0.00019142241907087458 tokens_per_second_per_gpu:274.2454787665378 mfu:4.525459624532128 
Step 570 | loss:1.5181338787078857 lr:0.0001913915992348394 tokens_per_second_per_gpu:242.04690870137878 mfu:3.9941351722461156 
Step 571 | loss:1.4374812841415405 lr:0.00019136072661933034 tokens_per_second_per_gpu:268.63928098677127 mfu:4.432948995683902 
Step 572 | loss:1.3304322957992554 lr:0.0001913298012421766 tokens_per_second_per_gpu:315.23730234840417 mfu:5.201885881001429 
Step 573 | loss:1.4582431316375732 lr:0.00019129882312123785 tokens_per_second_per_gpu:285.33211700985544 mfu:4.7084056988578915 
Step 574 | loss:1.4778962135314941 lr:0.00019126779227440421 tokens_per_second_per_gpu:247.45433257430113 mfu:4.083365735024047 
Step 575 | loss:1.3676804304122925 lr:0.00019123670871959637 tokens_per_second_per_gpu:299.89863400610636 mfu:4.948774965228594 
Step 576 | loss:1.344504952430725 lr:0.00019120557247476527 tokens_per_second_per_gpu:325.5491952485725 mfu:5.372047501102148 
Step 577 | loss:1.500990629196167 lr:0.00019117438355789238 tokens_per_second_per_gpu:189.1073927220048 mfu:3.120554163055154 
Step 578 | loss:1.2937440872192383 lr:0.00019114314198698967 tokens_per_second_per_gpu:236.1080768616513 mfu:3.8961355850571073 
Step 579 | loss:1.4595668315887451 lr:0.00019111184778009932 tokens_per_second_per_gpu:234.183908236506 mfu:3.86438393152739 
Step 580 | loss:1.4162205457687378 lr:0.00019108050095529406 tokens_per_second_per_gpu:339.7575035819667 mfu:5.606505790022257 
Step 581 | loss:1.2421003580093384 lr:0.00019104910153067698 tokens_per_second_per_gpu:327.50130072492715 mfu:5.404260154363758 
Step 582 | loss:1.4178807735443115 lr:0.00019101764952438152 tokens_per_second_per_gpu:199.7213038104952 mfu:3.2956995339300814 
Step 583 | loss:1.5256198644638062 lr:0.00019098614495457152 tokens_per_second_per_gpu:257.5745080121504 mfu:4.250363730918652 
Step 584 | loss:1.517717719078064 lr:0.00019095458783944112 tokens_per_second_per_gpu:266.571741210214 mfu:4.398831504219661 
Step 585 | loss:1.650996208190918 lr:0.00019092297819721482 tokens_per_second_per_gpu:287.94581724444106 mfu:4.751535652851834 
Step 586 | loss:1.3573899269104004 lr:0.00019089131604614753 tokens_per_second_per_gpu:282.1284967958689 mfu:4.655541184934317 
Step 587 | loss:1.7595982551574707 lr:0.0001908596014045244 tokens_per_second_per_gpu:173.30037512961485 mfu:2.859714785792254 
Step 588 | loss:1.4241456985473633 lr:0.0001908278342906609 tokens_per_second_per_gpu:293.455212569399 mfu:4.842448896748584 
Step 589 | loss:1.3569397926330566 lr:0.00019079601472290288 tokens_per_second_per_gpu:251.38420538766624 mfu:4.148214500540323 
Step 590 | loss:1.5528277158737183 lr:0.00019076414271962638 tokens_per_second_per_gpu:243.02487823180905 mfu:4.0102731288093025 
Step 591 | loss:1.3001298904418945 lr:0.00019073221829923778 tokens_per_second_per_gpu:253.29784491492106 mfu:4.17979240824349 
Step 592 | loss:1.4514051675796509 lr:0.00019070024148017375 tokens_per_second_per_gpu:219.41452834779525 mfu:3.620667124722214 
Step 593 | loss:1.3686679601669312 lr:0.00019066821228090112 tokens_per_second_per_gpu:237.85086881505902 mfu:3.9248942528556756 
Step 594 | loss:1.4673629999160767 lr:0.00019063613071991715 tokens_per_second_per_gpu:235.81993253623608 mfu:3.8913807737232267 
Step 595 | loss:1.5195246934890747 lr:0.00019060399681574913 tokens_per_second_per_gpu:220.12396925249215 mfu:3.632373958266516 
Step 596 | loss:1.4648789167404175 lr:0.0001905718105869547 tokens_per_second_per_gpu:293.8320963398438 mfu:4.848668041341087 
Step 597 | loss:1.492934226989746 lr:0.00019053957205212178 tokens_per_second_per_gpu:267.5858823458443 mfu:4.415566346243361 
Step 598 | loss:1.4586148262023926 lr:0.00019050728122986836 tokens_per_second_per_gpu:268.7720628376511 mfu:4.435140094358455 
Step 599 | loss:1.2851998805999756 lr:0.00019047493813884262 tokens_per_second_per_gpu:277.3170015938563 mfu:4.576144334461991 
Step 600 | loss:1.5954594612121582 lr:0.0001904425427977231 tokens_per_second_per_gpu:245.9461981304413 mfu:4.058479266285344 
Step 601 | loss:1.3097976446151733 lr:0.00019041009522521832 tokens_per_second_per_gpu:343.56424148530886 mfu:5.669322645783137 
Step 602 | loss:1.463561773300171 lr:0.00019037759544006703 tokens_per_second_per_gpu:254.38556014263904 mfu:4.1977413325727655 
Step 603 | loss:1.4927726984024048 lr:0.00019034504346103823 tokens_per_second_per_gpu:226.6968734052654 mfu:3.74083668477373 
Step 604 | loss:1.5006582736968994 lr:0.00019031243930693094 tokens_per_second_per_gpu:267.87470002558 mfu:4.4203322689282984 
Step 605 | loss:1.5173988342285156 lr:0.00019027978299657436 tokens_per_second_per_gpu:210.96931172590564 mfu:3.481308448638719 
Step 606 | loss:1.2956445217132568 lr:0.0001902470745488278 tokens_per_second_per_gpu:212.32991371907326 mfu:3.503760411795346 
Step 607 | loss:1.1973192691802979 lr:0.00019021431398258068 tokens_per_second_per_gpu:258.2551306444591 mfu:4.261595019966367 
Step 608 | loss:1.406006097793579 lr:0.00019018150131675253 tokens_per_second_per_gpu:227.29849885430593 mfu:3.7507644024191387 
Step 609 | loss:1.313204050064087 lr:0.00019014863657029296 tokens_per_second_per_gpu:275.59129695718326 mfu:4.547667632886977 
Step 610 | loss:1.384185791015625 lr:0.00019011571976218164 tokens_per_second_per_gpu:255.15802067805006 mfu:4.210488084060774 
Step 611 | loss:1.5497634410858154 lr:0.00019008275091142833 tokens_per_second_per_gpu:306.7095339784276 mfu:5.06116497789205 
Step 612 | loss:1.362521767616272 lr:0.0001900497300370729 tokens_per_second_per_gpu:276.99451738560856 mfu:4.57082286381993 
Step 613 | loss:1.3045164346694946 lr:0.00019001665715818512 tokens_per_second_per_gpu:295.16933041348034 mfu:4.870734398956202 
Step 614 | loss:1.5047831535339355 lr:0.00018998353229386487 tokens_per_second_per_gpu:203.02965086454086 mfu:3.3502921969864112 
Step 615 | loss:1.2918062210083008 lr:0.00018995035546324216 tokens_per_second_per_gpu:292.64738695958505 mfu:4.829118568761706 
Step 616 | loss:1.5053908824920654 lr:0.0001899171266854768 tokens_per_second_per_gpu:184.2494413231522 mfu:3.0403907160137473 
Step 617 | loss:1.4344425201416016 lr:0.00018988384597975878 tokens_per_second_per_gpu:238.67044329443272 mfu:3.938418454721771 
Step 618 | loss:1.3961071968078613 lr:0.00018985051336530798 tokens_per_second_per_gpu:236.05275971101346 mfu:3.895222769528182 
Step 619 | loss:1.4594340324401855 lr:0.0001898171288613743 tokens_per_second_per_gpu:285.86554675054697 mfu:4.7172080855549545 
Step 620 | loss:1.522579550743103 lr:0.00018978369248723756 tokens_per_second_per_gpu:242.39883390178943 mfu:3.999942463190261 
Step 621 | loss:1.2496559619903564 lr:0.0001897502042622076 tokens_per_second_per_gpu:312.46279620256763 mfu:5.15610238951974 
Step 622 | loss:1.5813673734664917 lr:0.00018971666420562416 tokens_per_second_per_gpu:205.31072429165587 mfu:3.3879333123164836 
Step 623 | loss:1.2932112216949463 lr:0.00018968307233685692 tokens_per_second_per_gpu:275.9057998136212 mfu:4.552857399314527 
Step 624 | loss:1.470604658126831 lr:0.0001896494286753055 tokens_per_second_per_gpu:346.65024364975335 mfu:5.720246286381424 
Step 625 | loss:1.4576904773712158 lr:0.00018961573324039943 tokens_per_second_per_gpu:270.6810746756452 mfu:4.466641638283453 
Step 626 | loss:1.3081767559051514 lr:0.00018958198605159807 tokens_per_second_per_gpu:198.41158189103726 mfu:3.2740871679121266 
Step 627 | loss:1.4798998832702637 lr:0.0001895481871283908 tokens_per_second_per_gpu:242.5714032635174 mfu:4.002790115164119 
Step 628 | loss:1.5788424015045166 lr:0.00018951433649029676 tokens_per_second_per_gpu:202.84825385545446 mfu:3.3472988756586592 
Step 629 | loss:1.5531108379364014 lr:0.000189480434156865 tokens_per_second_per_gpu:213.12875138715347 mfu:3.516942425331948 
Step 630 | loss:1.5668747425079346 lr:0.00018944648014767448 tokens_per_second_per_gpu:226.95011845314042 mfu:3.745015605952032 
Step 631 | loss:1.436845302581787 lr:0.00018941247448233384 tokens_per_second_per_gpu:188.19195316047475 mfu:3.1054480442850787 
Step 632 | loss:1.422072172164917 lr:0.00018937841718048176 tokens_per_second_per_gpu:266.25065810794223 mfu:4.393533153916912 
Step 633 | loss:1.4561439752578735 lr:0.0001893443082617866 tokens_per_second_per_gpu:233.96798070379828 mfu:3.8608208050339705 
Step 634 | loss:1.1876630783081055 lr:0.00018931014774594654 tokens_per_second_per_gpu:268.5320428458815 mfu:4.431179406340117 
Step 635 | loss:1.541954517364502 lr:0.00018927593565268964 tokens_per_second_per_gpu:236.58329928683926 mfu:3.9039774641923004 
Step 636 | loss:1.3729252815246582 lr:0.00018924167200177366 tokens_per_second_per_gpu:207.8496324836267 mfu:3.429829086003746 
Step 637 | loss:1.3668040037155151 lr:0.00018920735681298616 tokens_per_second_per_gpu:200.9171168049116 mfu:3.3154322327117045 
Step 638 | loss:1.573453664779663 lr:0.0001891729901061445 tokens_per_second_per_gpu:196.14044550866438 mfu:3.236610028648205 
Step 639 | loss:1.7147983312606812 lr:0.00018913857190109575 tokens_per_second_per_gpu:231.39623126573804 mfu:3.8183831017810306 
Step 640 | loss:1.5724989175796509 lr:0.00018910410221771674 tokens_per_second_per_gpu:297.8761817264474 mfu:4.915401484742043 
Step 641 | loss:1.2835074663162231 lr:0.000189069581075914 tokens_per_second_per_gpu:299.10885901257427 mfu:4.93574249934522 
Step 642 | loss:1.4778826236724854 lr:0.00018903500849562382 tokens_per_second_per_gpu:180.72415814624495 mfu:2.982218283221456 
Step 643 | loss:1.458020806312561 lr:0.00018900038449681217 tokens_per_second_per_gpu:180.6319984095918 mfu:2.980697510047338 
Step 644 | loss:1.3946491479873657 lr:0.00018896570909947475 tokens_per_second_per_gpu:207.71390954590666 mfu:3.4275894550076855 
Step 645 | loss:1.411093831062317 lr:0.00018893098232363687 tokens_per_second_per_gpu:221.03762908791805 mfu:3.6474507089001937 
Step 646 | loss:1.5224831104278564 lr:0.00018889620418935358 tokens_per_second_per_gpu:211.05210845319533 mfu:3.4826747181870013 
Step 647 | loss:1.9243111610412598 lr:0.00018886137471670956 tokens_per_second_per_gpu:227.0248604885063 mfu:3.746248961064485 
Step 648 | loss:1.4780913591384888 lr:0.0001888264939258192 tokens_per_second_per_gpu:243.3425225026809 mfu:4.015514733262583 
Step 649 | loss:1.5469921827316284 lr:0.0001887915618368264 tokens_per_second_per_gpu:298.96925328356303 mfu:4.933438796499013 
Step 650 | loss:1.2852275371551514 lr:0.00018875657846990476 tokens_per_second_per_gpu:278.7191185921415 mfu:4.599281357151112 
Step 651 | loss:1.5111991167068481 lr:0.00018872154384525752 tokens_per_second_per_gpu:223.30879651769524 mfu:3.6849283604926155 
Step 652 | loss:1.467010259628296 lr:0.00018868645798311747 tokens_per_second_per_gpu:228.6265462090106 mfu:3.7726791654635963 
Step 653 | loss:1.423898458480835 lr:0.00018865132090374704 tokens_per_second_per_gpu:275.7564314327166 mfu:4.550392598144401 
Step 654 | loss:1.3693138360977173 lr:0.00018861613262743818 tokens_per_second_per_gpu:197.57813698318597 mfu:3.260334083278911 
Step 655 | loss:1.3107119798660278 lr:0.00018858089317451247 tokens_per_second_per_gpu:242.47662697533272 mfu:4.001226164985352 
Step 656 | loss:1.4018080234527588 lr:0.000188545602565321 tokens_per_second_per_gpu:255.05496334791258 mfu:4.208787484332943 
Step 657 | loss:1.5825293064117432 lr:0.00018851026082024439 tokens_per_second_per_gpu:253.00494382783077 mfu:4.174959103244004 
Step 658 | loss:1.4641222953796387 lr:0.00018847486795969286 tokens_per_second_per_gpu:224.45497457517936 mfu:3.703842008750367 
Step 659 | loss:1.408402919769287 lr:0.0001884394240041061 tokens_per_second_per_gpu:298.2879861184043 mfu:4.922196871697511 
Step 660 | loss:1.2896029949188232 lr:0.00018840392897395326 tokens_per_second_per_gpu:240.13693019209745 mfu:3.9626176768024264 
Step 661 | loss:1.400585412979126 lr:0.00018836838288973306 tokens_per_second_per_gpu:255.20775624708858 mfu:4.21130879516456 
Step 662 | loss:1.3580958843231201 lr:0.00018833278577197373 tokens_per_second_per_gpu:207.05214863236102 mfu:3.4166694124647283 
Step 663 | loss:1.616822361946106 lr:0.0001882971376412329 tokens_per_second_per_gpu:130.87239730028875 mfu:2.1595898412325947 
Step 664 | loss:1.4447829723358154 lr:0.00018826143851809768 tokens_per_second_per_gpu:242.59675504709202 mfu:4.003208457422642 
Step 665 | loss:1.4126019477844238 lr:0.00018822568842318465 tokens_per_second_per_gpu:234.912985975472 mfu:3.8764148021389144 
Step 666 | loss:1.4929239749908447 lr:0.0001881898873771398 tokens_per_second_per_gpu:198.84134045652888 mfu:3.281178825521858 
Step 667 | loss:1.3795289993286133 lr:0.00018815403540063859 tokens_per_second_per_gpu:225.38211659863225 mfu:3.719141235604404 
Step 668 | loss:1.4486510753631592 lr:0.0001881181325143858 tokens_per_second_per_gpu:217.18560121696783 mfu:3.5838865010927883 
Step 669 | loss:1.5162705183029175 lr:0.00018808217873911575 tokens_per_second_per_gpu:184.93290456421838 mfu:3.0516688793446725 
Step 670 | loss:1.4426016807556152 lr:0.00018804617409559198 tokens_per_second_per_gpu:280.37881481462654 mfu:4.626668821395284 
Step 671 | loss:1.2833434343338013 lr:0.00018801011860460756 tokens_per_second_per_gpu:239.09803550311565 mfu:3.9454743642115546 
Step 672 | loss:1.1971838474273682 lr:0.00018797401228698487 tokens_per_second_per_gpu:221.69576311342468 mfu:3.658310902378521 
Step 673 | loss:1.4540177583694458 lr:0.00018793785516357553 tokens_per_second_per_gpu:197.4331682080966 mfu:3.2579418821697606 
Step 674 | loss:1.375138521194458 lr:0.00018790164725526076 tokens_per_second_per_gpu:231.47584088735405 mfu:3.8196967793299472 
Step 675 | loss:1.5134282112121582 lr:0.00018786538858295084 tokens_per_second_per_gpu:274.99487873835193 mfu:4.53782584231017 
Step 676 | loss:1.5268666744232178 lr:0.00018782907916758555 tokens_per_second_per_gpu:242.6049462902887 mfu:4.003343625158234 
Step 677 | loss:1.3566927909851074 lr:0.00018779271903013385 tokens_per_second_per_gpu:203.5961133556763 mfu:3.3596396733567606 
Step 678 | loss:1.4393469095230103 lr:0.00018775630819159407 tokens_per_second_per_gpu:243.80768835520402 mfu:4.023190663942542 
Step 679 | loss:1.454614520072937 lr:0.00018771984667299377 tokens_per_second_per_gpu:288.95773054088056 mfu:4.768233732204538 
Step 680 | loss:1.441847324371338 lr:0.0001876833344953899 tokens_per_second_per_gpu:218.2545191736471 mfu:3.601525242400926 
Step 681 | loss:1.4036211967468262 lr:0.00018764677167986847 tokens_per_second_per_gpu:285.3316765027655 mfu:4.70839842983359 
Step 682 | loss:1.3183664083480835 lr:0.00018761015824754487 tokens_per_second_per_gpu:257.14177932657753 mfu:4.243223061895613 
Step 683 | loss:1.2748831510543823 lr:0.0001875734942195637 tokens_per_second_per_gpu:211.95396055890657 mfu:3.4975566236610742 
Step 684 | loss:1.5237146615982056 lr:0.00018753677961709874 tokens_per_second_per_gpu:233.80466712756746 mfu:3.8581258873321564 
Step 685 | loss:1.4226614236831665 lr:0.00018750001446135304 tokens_per_second_per_gpu:226.68070456488164 mfu:3.7405698747805034 
Step 686 | loss:1.5123904943466187 lr:0.0001874631987735588 tokens_per_second_per_gpu:286.76229891686506 mfu:4.73200583441899 
Step 687 | loss:1.5500609874725342 lr:0.00018742633257497738 tokens_per_second_per_gpu:211.19013614439677 mfu:3.484952381054623 
Step 688 | loss:1.3849081993103027 lr:0.0001873894158868994 tokens_per_second_per_gpu:293.74530008107905 mfu:4.847235773555427 
Step 689 | loss:1.5442029237747192 lr:0.00018735244873064453 tokens_per_second_per_gpu:250.99702498479036 mfu:4.141825446148231 
Step 690 | loss:1.3670012950897217 lr:0.00018731543112756167 tokens_per_second_per_gpu:299.6214745656852 mfu:4.944201420888592 
Step 691 | loss:1.3050016164779663 lr:0.0001872783630990288 tokens_per_second_per_gpu:309.0189902238595 mfu:5.099274452076755 
Step 692 | loss:1.208554744720459 lr:0.00018724124466645302 tokens_per_second_per_gpu:337.8902787083962 mfu:5.575693793364114 
Step 693 | loss:1.5469661951065063 lr:0.0001872040758512706 tokens_per_second_per_gpu:276.5273915605004 mfu:4.563114590667675 
Step 694 | loss:1.463992953300476 lr:0.00018716685667494689 tokens_per_second_per_gpu:219.7130861542677 mfu:3.625593774032375 
Step 695 | loss:1.4895974397659302 lr:0.00018712958715897621 tokens_per_second_per_gpu:246.40674404547013 mfu:4.066078961102849 
Step 696 | loss:1.3681674003601074 lr:0.00018709226732488215 tokens_per_second_per_gpu:241.28291718065478 mfu:3.9815281721377755 
Step 697 | loss:1.3212294578552246 lr:0.00018705489719421717 tokens_per_second_per_gpu:351.6838530158244 mfu:5.803308351996052 
Step 698 | loss:1.4100905656814575 lr:0.00018701747678856286 tokens_per_second_per_gpu:217.21099030442087 mfu:3.5843054589209693 
Step 699 | loss:1.2066335678100586 lr:0.00018698000612952988 tokens_per_second_per_gpu:258.19676687515 mfu:4.260631930683248 
Step 700 | loss:1.4656522274017334 lr:0.00018694248523875787 tokens_per_second_per_gpu:261.48665261386765 mfu:4.314919954488976 
Step 701 | loss:1.3035168647766113 lr:0.00018690491413791545 tokens_per_second_per_gpu:286.4415205627297 mfu:4.726712512915231 
Step 702 | loss:1.3345365524291992 lr:0.00018686729284870033 tokens_per_second_per_gpu:234.02382772606612 mfu:3.8617423642354574 
Step 703 | loss:1.458793044090271 lr:0.00018682962139283908 tokens_per_second_per_gpu:236.87780954776937 mfu:3.9088373229613276 
Step 704 | loss:1.5632169246673584 lr:0.00018679189979208736 tokens_per_second_per_gpu:285.8387895736028 mfu:4.716766552208728 
Step 705 | loss:1.2856218814849854 lr:0.00018675412806822968 tokens_per_second_per_gpu:233.51013149122787 mfu:3.8532656098310074 
Step 706 | loss:1.461705207824707 lr:0.00018671630624307958 tokens_per_second_per_gpu:306.22147141201935 mfu:5.053111217266861 
Step 707 | loss:1.3738152980804443 lr:0.00018667843433847953 tokens_per_second_per_gpu:318.3970987207295 mfu:5.2540272361443305 
Step 708 | loss:1.336956262588501 lr:0.00018664051237630088 tokens_per_second_per_gpu:277.78239310371515 mfu:4.583823988824714 
Step 709 | loss:1.5622484683990479 lr:0.00018660254037844388 tokens_per_second_per_gpu:217.16595857813894 mfu:3.5835623682416684 
Step 710 | loss:1.3419339656829834 lr:0.00018656451836683772 tokens_per_second_per_gpu:248.11687771925907 mfu:4.094298718555525 
Step 711 | loss:1.2978461980819702 lr:0.00018652644636344047 tokens_per_second_per_gpu:334.79367357385587 mfu:5.524595187937657 
Step 712 | loss:1.3614895343780518 lr:0.00018648832439023902 tokens_per_second_per_gpu:252.94517846552498 mfu:4.173972885585004 
Step 713 | loss:1.325931429862976 lr:0.0001864501524692492 tokens_per_second_per_gpu:196.93699007064978 mfu:3.2497542025125052 
Step 714 | loss:1.4356296062469482 lr:0.0001864119306225156 tokens_per_second_per_gpu:229.73766932459898 mfu:3.7910143548716233 
Step 715 | loss:1.2870922088623047 lr:0.00018637365887211167 tokens_per_second_per_gpu:415.05684327071236 mfu:6.849057255402792 
Step 716 | loss:1.3882265090942383 lr:0.00018633533724013974 tokens_per_second_per_gpu:156.97915036655218 mfu:2.590390222921224 
Step 717 | loss:1.3919520378112793 lr:0.00018629696574873087 tokens_per_second_per_gpu:262.0630204329026 mfu:4.324430883550243 
Step 718 | loss:1.3412926197052002 lr:0.000186258544420045 tokens_per_second_per_gpu:220.06618118832205 mfu:3.631420368977249 
Step 719 | loss:1.2824351787567139 lr:0.00018622007327627067 tokens_per_second_per_gpu:233.71339609628512 mfu:3.8566197791227683 
Step 720 | loss:1.498885989189148 lr:0.00018618155233962545 tokens_per_second_per_gpu:255.79439766574396 mfu:4.220989253949674 
Step 721 | loss:1.9549752473831177 lr:0.0001861429816323554 tokens_per_second_per_gpu:182.77974485791123 mfu:3.0161385312788163 
Step 722 | loss:1.2777889966964722 lr:0.00018610436117673555 tokens_per_second_per_gpu:196.61374874782246 mfu:3.244420238350125 
Step 723 | loss:1.450248122215271 lr:0.00018606569099506953 tokens_per_second_per_gpu:311.42940860134416 mfu:5.139049952094472 
Step 724 | loss:1.316967487335205 lr:0.00018602697110968973 tokens_per_second_per_gpu:240.45768151551866 mfu:3.9679105522590663 
Step 725 | loss:1.5535136461257935 lr:0.0001859882015429572 tokens_per_second_per_gpu:226.58553078906604 mfu:3.738999365462702 
Step 726 | loss:1.3314251899719238 lr:0.00018594938231726173 tokens_per_second_per_gpu:262.78578083313863 mfu:4.336357508646088 
Step 727 | loss:1.4526498317718506 lr:0.00018591051345502181 tokens_per_second_per_gpu:235.69713781586256 mfu:3.8893544776046713 
Step 728 | loss:1.5621837377548218 lr:0.00018587159497868448 tokens_per_second_per_gpu:250.45398156751796 mfu:4.132864419442203 
Step 729 | loss:1.476550817489624 lr:0.0001858326269107256 tokens_per_second_per_gpu:292.0016782238229 mfu:4.81846341110499 
Step 730 | loss:1.430310606956482 lr:0.00018579360927364956 tokens_per_second_per_gpu:235.9090407629199 mfu:3.892851192429435 
Step 731 | loss:1.4215949773788452 lr:0.00018575454208998932 tokens_per_second_per_gpu:280.64178666224683 mfu:4.631008249283564 
Step 732 | loss:1.4519308805465698 lr:0.00018571542538230662 tokens_per_second_per_gpu:276.73387377590376 mfu:4.566521855331416 
Step 733 | loss:1.379009485244751 lr:0.00018567625917319169 tokens_per_second_per_gpu:185.07959280972247 mfu:3.054089454281433 
Step 734 | loss:1.416244387626648 lr:0.00018563704348526338 tokens_per_second_per_gpu:245.21689187652947 mfu:4.0464446248362265 
Step 735 | loss:1.514824628829956 lr:0.00018559777834116904 tokens_per_second_per_gpu:324.15347902902846 mfu:5.3490161008134 
Step 736 | loss:1.3527439832687378 lr:0.00018555846376358472 tokens_per_second_per_gpu:268.4896324556275 mfu:4.430479571616794 
Step 737 | loss:1.5385665893554688 lr:0.0001855190997752149 tokens_per_second_per_gpu:191.61888898822082 mfu:3.1619975990638087 
Step 738 | loss:1.3301715850830078 lr:0.00018547968639879265 tokens_per_second_per_gpu:254.100296515875 mfu:4.193034057065162 
Step 739 | loss:1.4758968353271484 lr:0.00018544022365707955 tokens_per_second_per_gpu:295.51663578633895 mfu:4.876465455852103 
Step 740 | loss:1.495792269706726 lr:0.00018540071157286571 tokens_per_second_per_gpu:242.87699288554813 mfu:4.007832799923759 
Step 741 | loss:1.254568099975586 lr:0.0001853611501689697 tokens_per_second_per_gpu:231.7567272198044 mfu:3.8243318229496417 
Step 742 | loss:1.1502652168273926 lr:0.0001853215394682386 tokens_per_second_per_gpu:330.00233535944943 mfu:5.44553095783878 
Step 743 | loss:1.4549710750579834 lr:0.0001852818794935479 tokens_per_second_per_gpu:196.37708651123953 mfu:3.2405149583027586 
Step 744 | loss:1.4503231048583984 lr:0.00018524217026780163 tokens_per_second_per_gpu:256.3758747639036 mfu:4.230584493740488 
Step 745 | loss:1.577131748199463 lr:0.00018520241181393225 tokens_per_second_per_gpu:215.50066990560194 mfu:3.5560826202266704 
Step 746 | loss:1.2314234972000122 lr:0.00018516260415490061 tokens_per_second_per_gpu:240.9536352387369 mfu:3.9760945287466827 
Step 747 | loss:1.7868177890777588 lr:0.00018512274731369597 tokens_per_second_per_gpu:154.08739187278968 mfu:2.5426718927366068 
Step 748 | loss:1.5647625923156738 lr:0.00018508284131333602 tokens_per_second_per_gpu:239.6803412978303 mfu:3.9550832787320944 
Step 749 | loss:1.3257566690444946 lr:0.00018504288617686684 tokens_per_second_per_gpu:287.356958735888 mfu:4.741818608775101 
Step 750 | loss:1.3269259929656982 lr:0.0001850028819273629 tokens_per_second_per_gpu:329.121202246882 mfu:5.4309909466681425 
Step 751 | loss:1.486316204071045 lr:0.000184962828587927 tokens_per_second_per_gpu:274.71551846947244 mfu:4.533215981016562 
Step 752 | loss:1.4551301002502441 lr:0.0001849227261816903 tokens_per_second_per_gpu:209.01552857903926 mfu:3.44906811131027 
Step 753 | loss:1.3056399822235107 lr:0.0001848825747318123 tokens_per_second_per_gpu:295.73268201037575 mfu:4.880030540929562 
Step 754 | loss:1.472383975982666 lr:0.00018484237426148086 tokens_per_second_per_gpu:311.2731096175671 mfu:5.136470785635211 
Step 755 | loss:1.2624242305755615 lr:0.00018480212479391207 tokens_per_second_per_gpu:263.25533181917905 mfu:4.344105800572513 
Step 756 | loss:1.511137843132019 lr:0.0001847618263523504 tokens_per_second_per_gpu:240.079875564582 mfu:3.961676190312384 
Step 757 | loss:1.4071310758590698 lr:0.00018472147896006851 tokens_per_second_per_gpu:245.9267915375595 mfu:4.0581590285445746 
Step 758 | loss:1.3733835220336914 lr:0.00018468108264036747 tokens_per_second_per_gpu:260.3676955634633 mfu:4.296455493466808 
Step 759 | loss:1.550061583518982 lr:0.0001846406374165764 tokens_per_second_per_gpu:247.00368629727356 mfu:4.07592939900565 
Step 760 | loss:1.4972120523452759 lr:0.0001846001433120529 tokens_per_second_per_gpu:248.1395230356069 mfu:4.094672400066257 
Step 761 | loss:1.4842685461044312 lr:0.0001845596003501826 tokens_per_second_per_gpu:280.72102494424377 mfu:4.632315799174659 
Step 762 | loss:1.4828052520751953 lr:0.0001845190085543795 tokens_per_second_per_gpu:267.2878752939088 mfu:4.410648785204888 
Step 763 | loss:1.4458355903625488 lr:0.00018447836794808565 tokens_per_second_per_gpu:274.9158853445691 mfu:4.536522333440026 
Step 764 | loss:1.533052682876587 lr:0.00018443767855477142 tokens_per_second_per_gpu:306.80675095631096 mfu:5.062769203092803 
Step 765 | loss:1.4403116703033447 lr:0.00018439694039793525 tokens_per_second_per_gpu:273.96656511349255 mfu:4.52085713306622 
Step 766 | loss:1.4911292791366577 lr:0.00018435615350110386 tokens_per_second_per_gpu:258.4510753017815 mfu:4.264828399197789 
Step 767 | loss:1.2318906784057617 lr:0.000184315317887832 tokens_per_second_per_gpu:234.69140227399222 mfu:3.872758340420708 
Step 768 | loss:1.2219479084014893 lr:0.0001842744335817026 tokens_per_second_per_gpu:219.73023278329634 mfu:3.625876718997284 
Step 769 | loss:1.7805235385894775 lr:0.0001842335006063268 tokens_per_second_per_gpu:189.3164818278388 mfu:3.1240044453009626 
Step 770 | loss:1.4666019678115845 lr:0.00018419251898534367 tokens_per_second_per_gpu:197.22394090054576 mfu:3.2544893193894024 
Step 771 | loss:1.5624127388000488 lr:0.0001841514887424205 tokens_per_second_per_gpu:256.40509888476015 mfu:4.231066735342405 
Step 772 | loss:1.4723198413848877 lr:0.00018411040990125264 tokens_per_second_per_gpu:239.72847950469733 mfu:3.955877630976493 
Step 773 | loss:1.3827263116836548 lr:0.00018406928248556348 tokens_per_second_per_gpu:320.206073990482 mfu:5.2838780274203145 
Step 774 | loss:1.279882550239563 lr:0.00018402810651910442 tokens_per_second_per_gpu:280.5371206656064 mfu:4.629281104158006 
Step 775 | loss:1.42269766330719 lr:0.00018398688202565507 tokens_per_second_per_gpu:247.20014977222115 mfu:4.07917133950206 
Step 776 | loss:1.3546901941299438 lr:0.00018394560902902285 tokens_per_second_per_gpu:275.6036371955272 mfu:4.5478712652335656 
Step 777 | loss:1.5683149099349976 lr:0.0001839042875530433 tokens_per_second_per_gpu:263.22235649377114 mfu:4.343561658498009 
Step 778 | loss:1.38548743724823 lr:0.00018386291762157998 tokens_per_second_per_gpu:257.5593157990301 mfu:4.250113036732581 
Step 779 | loss:1.776878833770752 lr:0.00018382149925852442 tokens_per_second_per_gpu:239.78185986234422 mfu:3.9567584865310144 
Step 780 | loss:1.4233739376068115 lr:0.00018378003248779601 tokens_per_second_per_gpu:257.7954537818433 mfu:4.254009665810464 
Step 781 | loss:1.313942790031433 lr:0.00018373851733334226 tokens_per_second_per_gpu:287.78966312080297 mfu:4.748958876801025 
Step 782 | loss:1.3794100284576416 lr:0.0001836969538191385 tokens_per_second_per_gpu:224.49250906805307 mfu:3.7044613838911764 
Step 783 | loss:1.3905110359191895 lr:0.00018365534196918812 tokens_per_second_per_gpu:194.87423647477152 mfu:3.2157156901713324 
Step 784 | loss:1.631638526916504 lr:0.00018361368180752223 tokens_per_second_per_gpu:337.6204021383866 mfu:5.57124042725329 
Step 785 | loss:1.5252268314361572 lr:0.00018357197335820002 tokens_per_second_per_gpu:301.343881619985 mfu:4.972623707433846 
Step 786 | loss:1.2320916652679443 lr:0.00018353021664530846 tokens_per_second_per_gpu:228.30641347787815 mfu:3.7673964977027747 
Step 787 | loss:1.448542833328247 lr:0.00018348841169296245 tokens_per_second_per_gpu:238.35444200778326 mfu:3.9332039619597965 
Step 788 | loss:1.294222116470337 lr:0.00018344655852530468 tokens_per_second_per_gpu:252.7326721613936 mfu:4.170466214468199 
Step 789 | loss:1.421802282333374 lr:0.0001834046571665058 tokens_per_second_per_gpu:298.2009124145782 mfu:4.92076002565434 
Step 790 | loss:1.371847152709961 lr:0.0001833627076407642 tokens_per_second_per_gpu:268.71447276045865 mfu:4.434189772149752 
Step 791 | loss:1.3616794347763062 lr:0.0001833207099723061 tokens_per_second_per_gpu:249.02952056894773 mfu:4.109358687407007 
Step 792 | loss:1.4877076148986816 lr:0.00018327866418538555 tokens_per_second_per_gpu:255.10793143265326 mfu:4.2096615367693255 
Step 793 | loss:1.2369232177734375 lr:0.00018323657030428433 tokens_per_second_per_gpu:279.1391594702644 mfu:4.606212658418675 
Step 794 | loss:1.6123087406158447 lr:0.0001831944283533121 tokens_per_second_per_gpu:246.27616947646516 mfu:4.063924285872904 
Step 795 | loss:1.4762482643127441 lr:0.00018315223835680617 tokens_per_second_per_gpu:336.9653295147638 mfu:5.560430751474223 
Step 796 | loss:1.381195306777954 lr:0.00018311000033913164 tokens_per_second_per_gpu:328.5605415007534 mfu:5.421739207747681 
Step 797 | loss:1.2614326477050781 lr:0.00018306771432468138 tokens_per_second_per_gpu:320.8019414717439 mfu:5.293710730005424 
Step 798 | loss:1.6077897548675537 lr:0.00018302538033787596 tokens_per_second_per_gpu:230.6100524643694 mfu:3.805409978434535 
Step 799 | loss:1.4775770902633667 lr:0.00018298299840316355 tokens_per_second_per_gpu:276.5713390977439 mfu:4.563839790610032 
Step 800 | loss:1.4352821111679077 lr:0.0001829405685450202 tokens_per_second_per_gpu:247.16064450521196 mfu:4.078519443647257 
Step 801 | loss:1.6788668632507324 lr:0.00018289809078794947 tokens_per_second_per_gpu:205.827436502721 mfu:3.39645983482907 
Step 802 | loss:1.6275298595428467 lr:0.00018285556515648267 tokens_per_second_per_gpu:318.56773053697185 mfu:5.256842915726501 
Step 803 | loss:1.423478603363037 lr:0.00018281299167517877 tokens_per_second_per_gpu:267.79224089254416 mfu:4.418971570188957 
Step 804 | loss:1.4378809928894043 lr:0.00018277037036862427 tokens_per_second_per_gpu:220.42134664393012 mfu:3.6372811289672113 
Step 805 | loss:1.4646639823913574 lr:0.00018272770126143343 tokens_per_second_per_gpu:254.53193687468183 mfu:4.200156767072579 
Step 806 | loss:1.3274223804473877 lr:0.000182684984378248 tokens_per_second_per_gpu:293.3635386817854 mfu:4.840936140808595 
Step 807 | loss:1.273532748222351 lr:0.0001826422197437374 tokens_per_second_per_gpu:313.4935450434955 mfu:5.173111283462612 
Step 808 | loss:1.4529626369476318 lr:0.00018259940738259855 tokens_per_second_per_gpu:269.7904226233392 mfu:4.451944550403113 
Step 809 | loss:1.6009752750396729 lr:0.000182556547319556 tokens_per_second_per_gpu:265.8061975046716 mfu:4.386198890745672 
Step 810 | loss:1.4522348642349243 lr:0.0001825136395793618 tokens_per_second_per_gpu:274.8910951669447 mfu:4.536113258517702 
Step 811 | loss:1.3126085996627808 lr:0.00018247068418679563 tokens_per_second_per_gpu:304.9639440715251 mfu:5.032360139685754 
Step 812 | loss:1.3504713773727417 lr:0.00018242768116666453 tokens_per_second_per_gpu:327.007164382386 mfu:5.396106167369181 
Step 813 | loss:1.4648864269256592 lr:0.00018238463054380316 tokens_per_second_per_gpu:157.5790965867023 mfu:2.600290230784221 
Step 814 | loss:1.4230940341949463 lr:0.00018234153234307368 tokens_per_second_per_gpu:210.73868156567892 mfu:3.4775027068522006 
Step 815 | loss:1.5149608850479126 lr:0.00018229838658936564 tokens_per_second_per_gpu:303.41320409645533 mfu:5.00677061610677 
Step 816 | loss:1.5231425762176514 lr:0.00018225519330759612 tokens_per_second_per_gpu:240.23099153598787 mfu:3.964169829333509 
Step 817 | loss:1.4866139888763428 lr:0.00018221195252270965 tokens_per_second_per_gpu:197.71877013888968 mfu:3.262654740198654 
Step 818 | loss:1.5161466598510742 lr:0.00018216866425967818 tokens_per_second_per_gpu:224.92349966365168 mfu:3.711573371836089 
Step 819 | loss:1.4604406356811523 lr:0.000182125328543501 tokens_per_second_per_gpu:238.11093356729108 mfu:3.9291857093321267 
Step 820 | loss:1.5035706758499146 lr:0.00018208194539920495 tokens_per_second_per_gpu:145.43555725120058 mfu:2.39990371134587 
Step 821 | loss:1.5404479503631592 lr:0.0001820385148518442 tokens_per_second_per_gpu:305.3790129611745 mfu:5.039209395724382 
Step 822 | loss:1.3754096031188965 lr:0.0001819950369265002 tokens_per_second_per_gpu:302.6880734819894 mfu:4.994804878939336 
Step 823 | loss:1.308070182800293 lr:0.0001819515116482819 tokens_per_second_per_gpu:334.1644633273453 mfu:5.514212279972382 
Step 824 | loss:1.503173589706421 lr:0.00018190793904232554 tokens_per_second_per_gpu:292.87612651922836 mfu:4.832893112817474 
Step 825 | loss:1.426316499710083 lr:0.00018186431913379473 tokens_per_second_per_gpu:262.34054630918826 mfu:4.3290104746288005 
Step 826 | loss:1.3741616010665894 lr:0.00018182065194788025 tokens_per_second_per_gpu:212.05468869629118 mfu:3.4992187882328976 
Step 827 | loss:1.5191805362701416 lr:0.0001817769375098004 tokens_per_second_per_gpu:231.4309796337067 mfu:3.8189565017034934 
Step 828 | loss:1.5197359323501587 lr:0.0001817331758448006 tokens_per_second_per_gpu:302.6742752529079 mfu:4.994577187569985 
Step 829 | loss:1.4493663311004639 lr:0.0001816893669781537 tokens_per_second_per_gpu:256.59066443925343 mfu:4.234128843889609 
Step 830 | loss:1.3689359426498413 lr:0.00018164551093515958 tokens_per_second_per_gpu:340.6759916522731 mfu:5.621662213736081 
Step 831 | loss:1.2868046760559082 lr:0.0001816016077411456 tokens_per_second_per_gpu:288.1850596248033 mfu:4.75548350912161 
Step 832 | loss:1.404953122138977 lr:0.0001815576574214662 tokens_per_second_per_gpu:251.0995160647826 mfu:4.143516701903716 
Step 833 | loss:1.667436957359314 lr:0.00018151366000150314 tokens_per_second_per_gpu:216.61151436307975 mfu:3.5744132113600635 
Step 834 | loss:1.380780577659607 lr:0.00018146961550666527 tokens_per_second_per_gpu:258.10271701 mfu:4.259079967568511 
Step 835 | loss:1.8151549100875854 lr:0.00018142552396238873 tokens_per_second_per_gpu:237.27765781916196 mfu:3.915435416086744 
Step 836 | loss:1.5303919315338135 lr:0.0001813813853941367 tokens_per_second_per_gpu:208.4668805153271 mfu:3.4400145995748193 
Step 837 | loss:1.6268943548202515 lr:0.00018133719982739975 tokens_per_second_per_gpu:220.94555949172394 mfu:3.645931423178156 
Step 838 | loss:1.5867449045181274 lr:0.0001812929672876953 tokens_per_second_per_gpu:300.15513192983826 mfu:4.953007563712426 
Step 839 | loss:1.3407450914382935 lr:0.00018124868780056814 tokens_per_second_per_gpu:284.18199568639824 mfu:4.689426980827503 
Step 840 | loss:1.398423433303833 lr:0.00018120436139159002 tokens_per_second_per_gpu:283.68370820158276 mfu:4.681204493791129 
Step 841 | loss:1.4384732246398926 lr:0.00018115998808635982 tokens_per_second_per_gpu:150.2793476334622 mfu:2.479833480482675 
Step 842 | loss:1.312941312789917 lr:0.00018111556791050362 tokens_per_second_per_gpu:256.3599514958733 mfu:4.230321736057532 
Step 843 | loss:1.5833511352539062 lr:0.00018107110088967437 tokens_per_second_per_gpu:234.93875729534037 mfu:3.87684006737231 
Step 844 | loss:1.4364266395568848 lr:0.00018102658704955226 tokens_per_second_per_gpu:232.71700177522112 mfu:3.840177786020936 
Step 845 | loss:1.7948737144470215 lr:0.00018098202641584433 tokens_per_second_per_gpu:178.2215147943942 mfu:2.9409209335100113 
Step 846 | loss:1.4479910135269165 lr:0.00018093741901428488 tokens_per_second_per_gpu:294.40926772085953 mfu:4.858192230374102 
Step 847 | loss:1.370712399482727 lr:0.00018089276487063497 tokens_per_second_per_gpu:244.09181776844136 mfu:4.027879223234498 
Step 848 | loss:1.4861996173858643 lr:0.00018084806401068285 tokens_per_second_per_gpu:232.94151514817827 mfu:3.84388259169013 
Step 849 | loss:1.3478511571884155 lr:0.0001808033164602436 tokens_per_second_per_gpu:311.87555020548876 mfu:5.146411954288496 
Step 850 | loss:1.5966296195983887 lr:0.00018075852224515944 tokens_per_second_per_gpu:218.5263592815155 mfu:3.606011009816382 
Step 851 | loss:1.5713616609573364 lr:0.00018071368139129933 tokens_per_second_per_gpu:241.89780335799708 mfu:3.991674711587618 
Step 852 | loss:1.652692198753357 lr:0.0001806687939245593 tokens_per_second_per_gpu:173.90294882898334 mfu:2.8696581509830374 
Step 853 | loss:1.3877644538879395 lr:0.00018062385987086227 tokens_per_second_per_gpu:380.40026380009317 mfu:6.277171980122867 
Step 854 | loss:1.293452262878418 lr:0.0001805788792561581 tokens_per_second_per_gpu:366.753447450641 mfu:6.0519791467875015 
Step 855 | loss:1.4531991481781006 lr:0.00018053385210642343 tokens_per_second_per_gpu:179.96775250402004 mfu:2.9697364614278827 
Step 856 | loss:1.4568002223968506 lr:0.00018048877844766193 tokens_per_second_per_gpu:202.72065578479993 mfu:3.3451933170929817 
Step 857 | loss:1.383447527885437 lr:0.00018044365830590395 tokens_per_second_per_gpu:272.64370089742187 mfu:4.499027899543422 
Step 858 | loss:1.422858476638794 lr:0.00018039849170720684 tokens_per_second_per_gpu:279.8685177501273 mfu:4.618248158373618 
Step 859 | loss:1.415083408355713 lr:0.00018035327867765472 tokens_per_second_per_gpu:242.54833089348813 mfu:4.002409386630401 
Step 860 | loss:1.3965789079666138 lr:0.0001803080192433585 tokens_per_second_per_gpu:251.86936891301823 mfu:4.156220422662179 
Step 861 | loss:1.3536958694458008 lr:0.00018026271343045592 tokens_per_second_per_gpu:228.9936658955659 mfu:3.7787371881021072 
Step 862 | loss:1.5795063972473145 lr:0.0001802173612651115 tokens_per_second_per_gpu:210.77841844086032 mfu:3.478158424587448 
Step 863 | loss:1.381502628326416 lr:0.0001801719627735165 tokens_per_second_per_gpu:223.606425872607 mfu:3.6898396889666034 
Step 864 | loss:1.4024882316589355 lr:0.000180126517981889 tokens_per_second_per_gpu:291.78897609509914 mfu:4.814953508590204 
Step 865 | loss:1.4354768991470337 lr:0.00018008102691647378 tokens_per_second_per_gpu:275.6847414351271 mfu:4.5492096062094625 
Step 866 | loss:1.3665674924850464 lr:0.00018003548960354227 tokens_per_second_per_gpu:290.04418749962855 mfu:4.78616189321824 
Step 867 | loss:1.4117850065231323 lr:0.00017998990606939277 tokens_per_second_per_gpu:331.4667337717512 mfu:5.469695716794541 
Step 868 | loss:1.2471845149993896 lr:0.00017994427634035015 tokens_per_second_per_gpu:197.6267471583161 mfu:3.2611362237039137 
Step 869 | loss:1.3214094638824463 lr:0.00017989860044276593 tokens_per_second_per_gpu:267.98659031678915 mfu:4.4221786256942215 
Step 870 | loss:1.6268082857131958 lr:0.00017985287840301847 tokens_per_second_per_gpu:208.86533106368782 mfu:3.446589628184549 
Step 871 | loss:1.5369527339935303 lr:0.00017980711024751254 tokens_per_second_per_gpu:242.20419482831502 mfu:3.9967306280405026 
Step 872 | loss:1.4478117227554321 lr:0.0001797612960026797 tokens_per_second_per_gpu:238.86261350834482 mfu:3.9415895500047573 
Step 873 | loss:1.5736243724822998 lr:0.00017971543569497817 tokens_per_second_per_gpu:267.346056986646 mfu:4.411608869952878 
Step 874 | loss:1.2971750497817993 lr:0.00017966952935089263 tokens_per_second_per_gpu:202.66334781179893 mfu:3.3442476500243896 
Step 875 | loss:1.3277826309204102 lr:0.00017962357699693437 tokens_per_second_per_gpu:207.99551058903987 mfu:3.4322362924201277 
Step 876 | loss:1.5298243761062622 lr:0.00017957757865964135 tokens_per_second_per_gpu:291.1399284686239 mfu:4.804243254254479 
Step 877 | loss:1.3369605541229248 lr:0.00017953153436557802 tokens_per_second_per_gpu:267.1878359790146 mfu:4.4089979872320075 
Step 878 | loss:1.4778214693069458 lr:0.00017948544414133534 tokens_per_second_per_gpu:254.2205341595903 mfu:4.1950181576032275 
Step 879 | loss:1.4596290588378906 lr:0.00017943930801353085 tokens_per_second_per_gpu:238.22189165753946 mfu:3.93101668339118 
Step 880 | loss:1.3980411291122437 lr:0.0001793931260088086 tokens_per_second_per_gpu:250.26518078097655 mfu:4.129748924738641 
Step 881 | loss:1.3629746437072754 lr:0.00017934689815383908 tokens_per_second_per_gpu:197.3743606198417 mfu:3.2569714692117766 
Step 882 | loss:1.3794353008270264 lr:0.0001793006244753193 tokens_per_second_per_gpu:265.0159032827861 mfu:4.373157856819681 
Step 883 | loss:1.4490594863891602 lr:0.00017925430499997274 tokens_per_second_per_gpu:186.4902470170009 mfu:3.0773673536580333 
Step 884 | loss:1.6313849687576294 lr:0.00017920793975454932 tokens_per_second_per_gpu:151.1288880385137 mfu:2.4938521648371474 
Step 885 | loss:1.6164557933807373 lr:0.0001791615287658254 tokens_per_second_per_gpu:186.39067614590428 mfu:3.0757242857068166 
Step 886 | loss:1.4023338556289673 lr:0.00017911507206060367 tokens_per_second_per_gpu:231.07097398667142 mfu:3.813015871332523 
Step 887 | loss:1.6536285877227783 lr:0.00017906856966571342 tokens_per_second_per_gpu:291.53706067697357 mfu:4.81079652828682 
Step 888 | loss:1.3011749982833862 lr:0.00017902202160801007 tokens_per_second_per_gpu:363.7916066057931 mfu:6.0031043532341695 
Step 889 | loss:1.3788120746612549 lr:0.00017897542791437565 tokens_per_second_per_gpu:240.46849702157544 mfu:3.968089024247735 
Step 890 | loss:1.5520837306976318 lr:0.0001789287886117184 tokens_per_second_per_gpu:277.8011747448012 mfu:4.5841339139283095 
Step 891 | loss:1.351435661315918 lr:0.00017888210372697292 tokens_per_second_per_gpu:217.29090677967247 mfu:3.5856242000127554 
Step 892 | loss:1.3312852382659912 lr:0.00017883537328710017 tokens_per_second_per_gpu:290.9985823820004 mfu:4.801910832910735 
Step 893 | loss:1.4385521411895752 lr:0.0001787885973190874 tokens_per_second_per_gpu:241.30220442944162 mfu:3.981846440522895 
Step 894 | loss:1.4389281272888184 lr:0.00017874177584994815 tokens_per_second_per_gpu:280.5861062394895 mfu:4.630089439222598 
Step 895 | loss:1.4532434940338135 lr:0.00017869490890672226 tokens_per_second_per_gpu:240.55306429219704 mfu:3.969484510402971 
Step 896 | loss:1.2893333435058594 lr:0.0001786479965164758 tokens_per_second_per_gpu:223.9856727654238 mfu:3.69609782860446 
Step 897 | loss:1.4030265808105469 lr:0.00017860103870630107 tokens_per_second_per_gpu:213.2756229650783 mfu:3.519366025527217 
Step 898 | loss:1.4269380569458008 lr:0.00017855403550331666 tokens_per_second_per_gpu:174.80393681508733 mfu:2.884525797194165 
Step 899 | loss:1.5864646434783936 lr:0.0001785069869346674 tokens_per_second_per_gpu:193.17262015118322 mfu:3.187636481706426 
Step 900 | loss:1.315281629562378 lr:0.00017845989302752412 tokens_per_second_per_gpu:275.29930395807446 mfu:4.542849312694221 
Step 901 | loss:1.5433263778686523 lr:0.0001784127538090841 tokens_per_second_per_gpu:246.62901821335413 mfu:4.0697468165470285 
Step 902 | loss:1.6688493490219116 lr:0.00017836556930657063 tokens_per_second_per_gpu:231.15504679073717 mfu:3.814403198051753 
Step 903 | loss:1.2942118644714355 lr:0.00017831833954723317 tokens_per_second_per_gpu:210.3171140414652 mfu:3.4705462136461005 
Step 904 | loss:1.4111460447311401 lr:0.00017827106455834733 tokens_per_second_per_gpu:329.050383781519 mfu:5.429822336315428 
Step 905 | loss:1.342307209968567 lr:0.00017822374436721487 tokens_per_second_per_gpu:269.3830990561755 mfu:4.445223103742952 
Step 906 | loss:1.569006085395813 lr:0.00017817637900116362 tokens_per_second_per_gpu:311.94525651302695 mfu:5.147562212377555 
Step 907 | loss:1.353316068649292 lr:0.0001781289684875475 tokens_per_second_per_gpu:239.0139168787093 mfu:3.9440862813883326 
Step 908 | loss:1.4278335571289062 lr:0.00017808151285374652 tokens_per_second_per_gpu:243.8712430695603 mfu:4.024239411564788 
Step 909 | loss:1.4036223888397217 lr:0.00017803401212716674 tokens_per_second_per_gpu:217.73778010433136 mfu:3.592998276687127 
Step 910 | loss:1.235028862953186 lr:0.00017798646633524019 tokens_per_second_per_gpu:247.9276441934415 mfu:4.091176083008179 
Step 911 | loss:1.4078518152236938 lr:0.00017793887550542506 tokens_per_second_per_gpu:202.61843346853922 mfu:3.343506496340112 
Step 912 | loss:1.4656245708465576 lr:0.00017789123966520552 tokens_per_second_per_gpu:304.76570079332055 mfu:5.02908882977981 
Step 913 | loss:1.278946876525879 lr:0.00017784355884209162 tokens_per_second_per_gpu:213.31840128297338 mfu:3.5200719316056337 
Step 914 | loss:1.6777490377426147 lr:0.00017779583306361954 tokens_per_second_per_gpu:189.126105958325 mfu:3.1208629593780413 
Step 915 | loss:1.6428099870681763 lr:0.00017774806235735128 tokens_per_second_per_gpu:219.3509152037395 mfu:3.6196174129227394 
Step 916 | loss:1.2129647731781006 lr:0.00017770024675087484 tokens_per_second_per_gpu:301.5809424787165 mfu:4.976535565341482 
Step 917 | loss:1.3385124206542969 lr:0.00017765238627180424 tokens_per_second_per_gpu:211.6687201795515 mfu:3.4928497317704097 
Step 918 | loss:1.4457945823669434 lr:0.0001776044809477793 tokens_per_second_per_gpu:258.77394742411343 mfu:4.27015627100108 
Step 919 | loss:1.4926581382751465 lr:0.0001775565308064658 tokens_per_second_per_gpu:250.62310413168848 mfu:4.135655194113105 
Step 920 | loss:1.5019947290420532 lr:0.00017750853587555535 tokens_per_second_per_gpu:201.10194771974042 mfu:3.3184822186082283 
Step 921 | loss:1.8250285387039185 lr:0.00017746049618276545 tokens_per_second_per_gpu:223.1916993492765 mfu:3.682996082483113 
Step 922 | loss:1.5551879405975342 lr:0.00017741241175583952 tokens_per_second_per_gpu:235.32002949977982 mfu:3.8831316276740786 
Step 923 | loss:1.4131224155426025 lr:0.00017736428262254665 tokens_per_second_per_gpu:230.41622352228256 mfu:3.802211511661538 
Step 924 | loss:1.5922869443893433 lr:0.00017731610881068194 tokens_per_second_per_gpu:426.2465802697524 mfu:7.033704613040354 
Step 925 | loss:1.3995437622070312 lr:0.00017726789034806616 tokens_per_second_per_gpu:271.4714508993002 mfu:4.479684025361001 
Step 926 | loss:1.2541207075119019 lr:0.00017721962726254589 tokens_per_second_per_gpu:212.10866296112988 mfu:3.500109444142303 
Step 927 | loss:1.4629753828048706 lr:0.00017717131958199355 tokens_per_second_per_gpu:260.15489383385227 mfu:4.292943947388758 
Step 928 | loss:1.2202908992767334 lr:0.0001771229673343072 tokens_per_second_per_gpu:276.3378971151393 mfu:4.559987649558521 
Step 929 | loss:1.6130770444869995 lr:0.00017707457054741074 tokens_per_second_per_gpu:265.911356672683 mfu:4.387934173934752 
Step 930 | loss:1.4628326892852783 lr:0.00017702612924925376 tokens_per_second_per_gpu:235.59055786557883 mfu:3.8875957493880273 
Step 931 | loss:1.3445823192596436 lr:0.00017697764346781151 tokens_per_second_per_gpu:226.45405626004646 mfu:3.736829839549609 
Step 932 | loss:1.2122938632965088 lr:0.00017692911323108503 tokens_per_second_per_gpu:263.309224834157 mfu:4.344995115737977 
Step 933 | loss:1.5190116167068481 lr:0.00017688053856710088 tokens_per_second_per_gpu:290.81048752057825 mfu:4.798806987025012 
Step 934 | loss:1.4797782897949219 lr:0.00017683191950391142 tokens_per_second_per_gpu:239.01755756773707 mfu:3.944146358189871 
Step 935 | loss:1.448354959487915 lr:0.0001767832560695946 tokens_per_second_per_gpu:279.7254980790497 mfu:4.615888120389085 
Step 936 | loss:1.2843434810638428 lr:0.000176734548292254 tokens_per_second_per_gpu:245.69791983223305 mfu:4.054382303887851 
Step 937 | loss:1.396041989326477 lr:0.00017668579620001878 tokens_per_second_per_gpu:323.74370707129737 mfu:5.342254252055426 
Step 938 | loss:1.2515445947647095 lr:0.00017663699982104373 tokens_per_second_per_gpu:389.1901496670679 mfu:6.422218213060413 
Step 939 | loss:1.4487102031707764 lr:0.00017658815918350916 tokens_per_second_per_gpu:213.0293879612283 mfu:3.515302780535608 
Step 940 | loss:1.4491634368896484 lr:0.00017653927431562102 tokens_per_second_per_gpu:324.1618217879259 mfu:5.349153768784144 
Step 941 | loss:1.43107008934021 lr:0.00017649034524561073 tokens_per_second_per_gpu:157.15507101738984 mfu:2.593293176166134 
Step 942 | loss:1.4053572416305542 lr:0.00017644137200173535 tokens_per_second_per_gpu:229.45324114956895 mfu:3.786320865564281 
Step 943 | loss:1.627436876296997 lr:0.00017639235461227725 tokens_per_second_per_gpu:322.0987361108332 mfu:5.315109776607408 
Step 944 | loss:1.581833004951477 lr:0.0001763432931055445 tokens_per_second_per_gpu:225.64728510533203 mfu:3.7235169116453157 
Step 945 | loss:1.4679070711135864 lr:0.00017629418750987055 tokens_per_second_per_gpu:303.99127210910694 mfu:5.016309600899717 
Step 946 | loss:1.5040103197097778 lr:0.00017624503785361432 tokens_per_second_per_gpu:238.2029133667128 mfu:3.930703513273427 
Step 947 | loss:1.3855583667755127 lr:0.00017619584416516014 tokens_per_second_per_gpu:211.84154108465694 mfu:3.4957015345853453 
Step 948 | loss:1.3121525049209595 lr:0.0001761466064729179 tokens_per_second_per_gpu:250.20137350621346 mfu:4.128696009492817 
Step 949 | loss:1.498081922531128 lr:0.00017609732480532267 tokens_per_second_per_gpu:188.8671748662769 mfu:3.1165902099862555 
Step 950 | loss:1.565269947052002 lr:0.00017604799919083522 tokens_per_second_per_gpu:255.02193490245114 mfu:4.208242465698291 
Step 951 | loss:1.5910981893539429 lr:0.00017599862965794145 tokens_per_second_per_gpu:226.8934539362492 mfu:3.744080556869407 
Step 952 | loss:1.597245693206787 lr:0.00017594921623515273 tokens_per_second_per_gpu:244.067917647834 mfu:4.027484835581084 
Step 953 | loss:1.4662599563598633 lr:0.00017589975895100572 tokens_per_second_per_gpu:295.89603887003767 mfu:4.882726172872577 
Step 954 | loss:1.366265892982483 lr:0.00017585025783406247 tokens_per_second_per_gpu:277.2424956754856 mfu:4.57491487563229 
Step 955 | loss:1.5245275497436523 lr:0.0001758007129129104 tokens_per_second_per_gpu:241.92316178489216 mfu:3.9920931634708414 
Step 956 | loss:1.572113037109375 lr:0.00017575112421616202 tokens_per_second_per_gpu:266.2561373899685 mfu:4.3936235702464455 
Step 957 | loss:1.3606882095336914 lr:0.0001757014917724553 tokens_per_second_per_gpu:296.76377391238685 mfu:4.897045095892219 
Step 958 | loss:1.4805597066879272 lr:0.0001756518156104535 tokens_per_second_per_gpu:196.2915519394891 mfu:3.239103510235504 
Step 959 | loss:1.5397365093231201 lr:0.00017560209575884494 tokens_per_second_per_gpu:259.15173084931894 mfu:4.276390261239586 
Step 960 | loss:1.5115742683410645 lr:0.00017555233224634335 tokens_per_second_per_gpu:196.4082506870759 mfu:3.2410292137067622 
Step 961 | loss:1.6663312911987305 lr:0.00017550252510168757 tokens_per_second_per_gpu:217.89177837668413 mfu:3.5955394779748007 
Step 962 | loss:1.4559916257858276 lr:0.00017545267435364173 tokens_per_second_per_gpu:230.66076775772373 mfu:3.8062468564514624 
Step 963 | loss:1.4602595567703247 lr:0.00017540278003099502 tokens_per_second_per_gpu:270.9537804078717 mfu:4.471141689792488 
Step 964 | loss:1.418715476989746 lr:0.00017535284216256192 tokens_per_second_per_gpu:163.91298650621962 mfu:2.7048088657893503 
Step 965 | loss:1.6013704538345337 lr:0.00017530286077718194 tokens_per_second_per_gpu:200.70847137794303 mfu:3.3119892718292276 
Step 966 | loss:1.491919755935669 lr:0.00017525283590371984 tokens_per_second_per_gpu:227.39341823674528 mfu:3.75233071386663 
Step 967 | loss:1.3653993606567383 lr:0.0001752027675710654 tokens_per_second_per_gpu:293.1865351504915 mfu:4.838015318420299 
Step 968 | loss:1.3210197687149048 lr:0.00017515265580813355 tokens_per_second_per_gpu:264.4883592201257 mfu:4.3644525925926505 
Step 969 | loss:1.500325083732605 lr:0.0001751025006438643 tokens_per_second_per_gpu:164.4205052757291 mfu:2.7131836827979567 
Step 970 | loss:1.3953447341918945 lr:0.00017505230210722265 tokens_per_second_per_gpu:274.1323852402422 mfu:4.52359341259183 
Step 971 | loss:1.3648356199264526 lr:0.00017500206022719877 tokens_per_second_per_gpu:246.22572867302864 mfu:4.06309193734921 
Step 972 | loss:1.3764228820800781 lr:0.0001749517750328078 tokens_per_second_per_gpu:266.06708055751716 mfu:4.390503850403301 
Step 973 | loss:1.4073264598846436 lr:0.00017490144655308987 tokens_per_second_per_gpu:257.14624739231925 mfu:4.243296791647531 
Step 974 | loss:1.2610692977905273 lr:0.00017485107481711012 tokens_per_second_per_gpu:261.98630688244214 mfu:4.323164995496867 
Step 975 | loss:1.3179584741592407 lr:0.0001748006598539587 tokens_per_second_per_gpu:292.66320142737897 mfu:4.829379531078412 
Step 976 | loss:1.4346086978912354 lr:0.00017475020169275068 tokens_per_second_per_gpu:257.21622382465995 mfu:4.2444515071989075 
Step 977 | loss:1.372435212135315 lr:0.00017469970036262619 tokens_per_second_per_gpu:239.1376870881593 mfu:3.9461286745322606 
Step 978 | loss:1.33132004737854 lr:0.0001746491558927501 tokens_per_second_per_gpu:281.7298121597136 mfu:4.648962293526675 
Step 979 | loss:1.4761178493499756 lr:0.00017459856831231234 tokens_per_second_per_gpu:269.22674609545237 mfu:4.442643046583537 
Step 980 | loss:1.3581647872924805 lr:0.0001745479376505277 tokens_per_second_per_gpu:256.6413805082249 mfu:4.234965734705376 
Step 981 | loss:1.4504348039627075 lr:0.00017449726393663583 tokens_per_second_per_gpu:268.95266765430296 mfu:4.438120343328939 
Step 982 | loss:1.309264063835144 lr:0.00017444654719990128 tokens_per_second_per_gpu:270.7013338262215 mfu:4.466975944498355 
Step 983 | loss:1.4355124235153198 lr:0.0001743957874696134 tokens_per_second_per_gpu:236.1337855877532 mfu:3.8965598173999543 
Step 984 | loss:1.4674338102340698 lr:0.0001743449847750864 tokens_per_second_per_gpu:246.27644032533658 mfu:4.063928755283439 
Step 985 | loss:1.425932765007019 lr:0.00017429413914565932 tokens_per_second_per_gpu:194.37253303605104 mfu:3.207436834798292 
Step 986 | loss:1.566841721534729 lr:0.0001742432506106959 tokens_per_second_per_gpu:246.45332423885472 mfu:4.066847603799943 
Step 987 | loss:1.729727029800415 lr:0.00017419231919958483 tokens_per_second_per_gpu:208.40868288983012 mfu:3.4390542519125176 
Step 988 | loss:1.4722973108291626 lr:0.00017414134494173937 tokens_per_second_per_gpu:304.0615391900383 mfu:5.017469112586541 
Step 989 | loss:1.3832653760910034 lr:0.00017409032786659768 tokens_per_second_per_gpu:289.60815656361007 mfu:4.778966732135281 
Step 990 | loss:1.514974594116211 lr:0.00017403926800362251 tokens_per_second_per_gpu:280.9533492571667 mfu:4.6361494970086525 
Step 991 | loss:1.5684009790420532 lr:0.00017398816538230147 tokens_per_second_per_gpu:268.88163344631187 mfu:4.436948172900934 
Step 992 | loss:1.4294898509979248 lr:0.00017393702003214674 tokens_per_second_per_gpu:274.059387790419 mfu:4.522388845744076 
Step 993 | loss:1.4955081939697266 lr:0.0001738858319826952 tokens_per_second_per_gpu:230.8207315321737 mfu:3.80888649742537 
Step 994 | loss:1.2116644382476807 lr:0.0001738346012635085 tokens_per_second_per_gpu:288.1941617674 mfu:4.755633708056533 
Step 995 | loss:1.4337689876556396 lr:0.00017378332790417273 tokens_per_second_per_gpu:254.48388606146716 mfu:4.199363856953853 
Step 996 | loss:1.514521598815918 lr:0.0001737320119342988 tokens_per_second_per_gpu:233.23621294783356 mfu:3.8487455451279646 
Step 997 | loss:1.322291612625122 lr:0.0001736806533835221 tokens_per_second_per_gpu:224.26900261753792 mfu:3.7007731939447894 
Step 998 | loss:1.471392273902893 lr:0.0001736292522815027 tokens_per_second_per_gpu:207.45984448053338 mfu:3.4233970023170444 
Step 999 | loss:1.3460506200790405 lr:0.00017357780865792516 tokens_per_second_per_gpu:300.6753043442488 mfu:4.961591184743473 
Step 1000 | loss:1.467512607574463 lr:0.00017352632254249864 tokens_per_second_per_gpu:266.580303868075 mfu:4.398972800851435 
Step 1001 | loss:1.3615901470184326 lr:0.0001734747939649569 tokens_per_second_per_gpu:262.892898658838 mfu:4.3381251126097 
Step 1002 | loss:1.2951984405517578 lr:0.00017342322295505803 tokens_per_second_per_gpu:269.6354959152889 mfu:4.449388028541033 
Step 1003 | loss:1.3016432523727417 lr:0.0001733716095425849 tokens_per_second_per_gpu:319.72676352381035 mfu:5.275968689500528 
Step 1004 | loss:1.5559043884277344 lr:0.00017331995375734463 tokens_per_second_per_gpu:193.62614423478374 mfu:3.195120305827495 
Step 1005 | loss:1.5113773345947266 lr:0.00017326825562916892 tokens_per_second_per_gpu:274.75866863990456 mfu:4.533928023216713 
Step 1006 | loss:1.5895183086395264 lr:0.00017321651518791394 tokens_per_second_per_gpu:263.49340998366256 mfu:4.348034445543065 
Step 1007 | loss:1.6278986930847168 lr:0.0001731647324634602 tokens_per_second_per_gpu:263.05522256990554 mfu:4.340803699359557 
Step 1008 | loss:1.4874565601348877 lr:0.00017311290748571275 tokens_per_second_per_gpu:181.00741768872263 mfu:2.986892488347869 
Step 1009 | loss:1.4736452102661133 lr:0.00017306104028460095 tokens_per_second_per_gpu:289.91539005342065 mfu:4.784036543166242 
Step 1010 | loss:1.385927677154541 lr:0.00017300913089007857 tokens_per_second_per_gpu:249.75397566979274 mfu:4.121313277591706 
Step 1011 | loss:1.3552641868591309 lr:0.0001729571793321238 tokens_per_second_per_gpu:175.55958707133854 mfu:2.8969951539919974 
Step 1012 | loss:1.5475302934646606 lr:0.00017290518564073908 tokens_per_second_per_gpu:210.73564342721872 mfu:3.477452573034144 
Step 1013 | loss:1.4933454990386963 lr:0.00017285314984595126 tokens_per_second_per_gpu:284.9016665656828 mfu:4.701302624217512 
Step 1014 | loss:1.3395237922668457 lr:0.0001728010719778115 tokens_per_second_per_gpu:282.7274370386906 mfu:4.665424592670291 
Step 1015 | loss:1.4562910795211792 lr:0.0001727489520663952 tokens_per_second_per_gpu:257.2733390163575 mfu:4.245393993088328 
Step 1016 | loss:1.2466589212417603 lr:0.0001726967901418021 tokens_per_second_per_gpu:230.71173973045325 mfu:3.807087970061093 
Step 1017 | loss:1.2559854984283447 lr:0.0001726445862341562 tokens_per_second_per_gpu:231.14404213637047 mfu:3.814221604833727 
Step 1018 | loss:1.4453500509262085 lr:0.0001725923403736057 tokens_per_second_per_gpu:427.8453185972273 mfu:7.060086181056425 
Step 1019 | loss:1.3688960075378418 lr:0.0001725400525903231 tokens_per_second_per_gpu:245.20900051290712 mfu:4.046314405561087 
Step 1020 | loss:1.4644343852996826 lr:0.00017248772291450498 tokens_per_second_per_gpu:308.0681836546128 mfu:5.083584724905251 
Step 1021 | loss:1.4661431312561035 lr:0.00017243535137637225 tokens_per_second_per_gpu:255.66241397554663 mfu:4.218811326117385 
Step 1022 | loss:1.2147912979125977 lr:0.00017238293800617 tokens_per_second_per_gpu:263.2811308674016 mfu:4.344531523365128 
Step 1023 | loss:1.4409003257751465 lr:0.00017233048283416734 tokens_per_second_per_gpu:268.11036313717557 mfu:4.424221061922495 
Step 1024 | loss:1.5524017810821533 lr:0.00017227798589065766 tokens_per_second_per_gpu:362.60073824210633 mfu:5.983453248237886 
Step 1025 | loss:1.387155294418335 lr:0.00017222544720595838 tokens_per_second_per_gpu:282.7454966754213 mfu:4.665722603624659 
Step 1026 | loss:1.3408695459365845 lr:0.0001721728668104111 tokens_per_second_per_gpu:318.38940171365215 mfu:5.253900224042199 
Step 1027 | loss:1.3153537511825562 lr:0.00017212024473438147 tokens_per_second_per_gpu:230.47351805732302 mfu:3.8031569569837282 
Step 1028 | loss:1.3819061517715454 lr:0.00017206758100825917 tokens_per_second_per_gpu:225.33630016714636 mfu:3.718385196118312 
Step 1029 | loss:1.645973563194275 lr:0.00017201487566245805 tokens_per_second_per_gpu:252.696205050385 mfu:4.169864452720895 
Step 1030 | loss:1.3649866580963135 lr:0.00017196212872741583 tokens_per_second_per_gpu:231.01621005319132 mfu:3.812112184712203 
Step 1031 | loss:1.3108924627304077 lr:0.00017190934023359443 tokens_per_second_per_gpu:203.315702988223 mfu:3.3550124838697446 
Step 1032 | loss:1.5490386486053467 lr:0.00017185651021147964 tokens_per_second_per_gpu:217.87275061253217 mfu:3.5952254914733563 
Step 1033 | loss:1.1356234550476074 lr:0.00017180363869158128 tokens_per_second_per_gpu:244.8981489509496 mfu:4.041184890940869 
Step 1034 | loss:1.3559613227844238 lr:0.00017175072570443312 tokens_per_second_per_gpu:322.33576526808235 mfu:5.319021111393281 
Step 1035 | loss:1.454237461090088 lr:0.0001716977712805929 tokens_per_second_per_gpu:235.8959309501975 mfu:3.892634860957255 
Step 1036 | loss:1.1757967472076416 lr:0.00017164477545064227 tokens_per_second_per_gpu:230.77303373541355 mfu:3.8080994126049093 
Step 1037 | loss:1.472583532333374 lr:0.00017159173824518684 tokens_per_second_per_gpu:203.07854730380961 mfu:3.35109906119686 
Step 1038 | loss:1.3854992389678955 lr:0.00017153865969485603 tokens_per_second_per_gpu:269.9599480096268 mfu:4.454741972240033 
Step 1039 | loss:1.4232088327407837 lr:0.00017148553983030318 tokens_per_second_per_gpu:293.18744590834547 mfu:4.838030347283909 
Step 1040 | loss:1.5361194610595703 lr:0.00017143237868220553 tokens_per_second_per_gpu:253.15772932808105 mfu:4.177480291982306 
Step 1041 | loss:1.4575527906417847 lr:0.00017137917628126407 tokens_per_second_per_gpu:263.20809830464265 mfu:4.343326377101539 
Step 1042 | loss:1.413753628730774 lr:0.0001713259326582037 tokens_per_second_per_gpu:264.39365278437543 mfu:4.362889795083285 
Step 1043 | loss:1.1991665363311768 lr:0.0001712726478437731 tokens_per_second_per_gpu:263.6475685623223 mfu:4.350578292124011 
Step 1044 | loss:1.4761178493499756 lr:0.00017121932186874473 tokens_per_second_per_gpu:205.72157229411744 mfu:3.394712917418168 
Step 1045 | loss:1.3924400806427002 lr:0.0001711659547639148 tokens_per_second_per_gpu:251.77031322591628 mfu:4.154585856015625 
Step 1046 | loss:1.3411145210266113 lr:0.00017111254656010329 tokens_per_second_per_gpu:268.5517654784332 mfu:4.4315048592070285 
Step 1047 | loss:1.5790671110153198 lr:0.00017105909728815398 tokens_per_second_per_gpu:188.9671912099985 mfu:3.1182406289005113 
Step 1048 | loss:1.3531198501586914 lr:0.00017100560697893422 tokens_per_second_per_gpu:269.1724509966679 mfu:4.441747096435284 
Step 1049 | loss:1.295555591583252 lr:0.00017095207566333523 tokens_per_second_per_gpu:201.59020804504488 mfu:3.326539242550297 
Step 1050 | loss:1.4220526218414307 lr:0.00017089850337227176 tokens_per_second_per_gpu:221.5633587912215 mfu:3.656126033490476 
Step 1051 | loss:1.5392282009124756 lr:0.00017084489013668232 tokens_per_second_per_gpu:244.75287886912238 mfu:4.038787717820939 
Step 1052 | loss:1.4193497896194458 lr:0.00017079123598752908 tokens_per_second_per_gpu:212.1741467141831 mfu:3.5011900237815303 
Step 1053 | loss:1.6080242395401 lr:0.00017073754095579772 tokens_per_second_per_gpu:199.73457650605903 mfu:3.295918553212197 
Step 1054 | loss:1.508202314376831 lr:0.00017068380507249766 tokens_per_second_per_gpu:240.32251541022626 mfu:3.965680109828959 
Step 1055 | loss:1.470618486404419 lr:0.0001706300283686618 tokens_per_second_per_gpu:262.87192451467445 mfu:4.3377790079337055 
Step 1056 | loss:1.3887512683868408 lr:0.00017057621087534675 tokens_per_second_per_gpu:264.9860411649954 mfu:4.372665087316342 
Step 1057 | loss:1.3931286334991455 lr:0.00017052235262363254 tokens_per_second_per_gpu:268.00521507862976 mfu:4.422485962056174 
Step 1058 | loss:1.3409709930419922 lr:0.00017046845364462285 tokens_per_second_per_gpu:396.67016658275196 mfu:6.545649653735365 
Step 1059 | loss:1.4015982151031494 lr:0.00017041451396944477 tokens_per_second_per_gpu:238.21707495611386 mfu:3.93093720063025 
Step 1060 | loss:1.4602038860321045 lr:0.00017036053362924896 tokens_per_second_per_gpu:237.99131371819192 mfu:3.927211803327092 
Step 1061 | loss:1.2891395092010498 lr:0.00017030651265520955 tokens_per_second_per_gpu:270.82740341174593 mfu:4.469056280778603 
Step 1062 | loss:1.3259354829788208 lr:0.00017025245107852422 tokens_per_second_per_gpu:272.834940121997 mfu:4.50218363211314 
Step 1063 | loss:1.3229718208312988 lr:0.0001701983489304139 tokens_per_second_per_gpu:355.9070979602274 mfu:5.872998195439835 
Step 1064 | loss:1.6061869859695435 lr:0.00017014420624212315 tokens_per_second_per_gpu:296.200914644512 mfu:4.887757078082344 
Step 1065 | loss:1.519477367401123 lr:0.00017009002304491983 tokens_per_second_per_gpu:273.61422460950183 mfu:4.515042988993294 
Step 1066 | loss:1.5205645561218262 lr:0.0001700357993700952 tokens_per_second_per_gpu:249.79255285346213 mfu:4.121949858686531 
Step 1067 | loss:1.4469904899597168 lr:0.00016998153524896403 tokens_per_second_per_gpu:361.1967623908824 mfu:5.960285551701526 
Step 1068 | loss:1.3731658458709717 lr:0.00016992723071286423 tokens_per_second_per_gpu:253.7247497383188 mfu:4.186836974850362 
Step 1069 | loss:1.3525203466415405 lr:0.00016987288579315717 tokens_per_second_per_gpu:274.39526815372335 mfu:4.527931372934109 
Step 1070 | loss:1.2686209678649902 lr:0.00016981850052122757 tokens_per_second_per_gpu:245.69021288476037 mfu:4.054255127754363 
Step 1071 | loss:1.2476181983947754 lr:0.0001697640749284834 tokens_per_second_per_gpu:281.54405407908405 mfu:4.6458970080109365 
Step 1072 | loss:1.4428741931915283 lr:0.00016970960904635595 tokens_per_second_per_gpu:394.5516840249797 mfu:6.510691530365041 
Step 1073 | loss:1.2486038208007812 lr:0.00016965510290629972 tokens_per_second_per_gpu:178.53727237382188 mfu:2.94613140473917 
Step 1074 | loss:1.4518619775772095 lr:0.00016960055653979253 tokens_per_second_per_gpu:205.14672934694818 mfu:3.3852271510180727 
Step 1075 | loss:1.562462329864502 lr:0.00016954596997833537 tokens_per_second_per_gpu:278.9047224222777 mfu:4.602344097303538 
Step 1076 | loss:1.2813408374786377 lr:0.00016949134325345254 tokens_per_second_per_gpu:227.0451442224359 mfu:3.746583672941399 
Step 1077 | loss:1.3423454761505127 lr:0.00016943667639669134 tokens_per_second_per_gpu:237.01072514392638 mfu:3.9110306286325263 
Step 1078 | loss:1.3144598007202148 lr:0.00016938196943962251 tokens_per_second_per_gpu:333.1043435624189 mfu:5.496718721956693 
Step 1079 | loss:1.43900728225708 lr:0.00016932722241383975 tokens_per_second_per_gpu:237.42251570671382 mfu:3.917825787386062 
Step 1080 | loss:1.45426344871521 lr:0.00016927243535095997 tokens_per_second_per_gpu:315.21450269724926 mfu:5.201509652736084 
Step 1081 | loss:1.4128038883209229 lr:0.00016921760828262315 tokens_per_second_per_gpu:218.81097727107127 mfu:3.610707631346637 
Step 1082 | loss:1.430519938468933 lr:0.0001691627412404925 tokens_per_second_per_gpu:221.41492910604248 mfu:3.6536767222005295 
Step 1083 | loss:1.2673273086547852 lr:0.00016910783425625416 tokens_per_second_per_gpu:288.33922362150406 mfu:4.7580274451083175 
Step 1084 | loss:1.391936182975769 lr:0.00016905288736161745 tokens_per_second_per_gpu:290.37216710456755 mfu:4.791574046105854 
Step 1085 | loss:1.5137660503387451 lr:0.00016899790058831467 tokens_per_second_per_gpu:234.9667285129973 mfu:3.8773016342018694 
Step 1086 | loss:1.378644347190857 lr:0.0001689428739681012 tokens_per_second_per_gpu:230.0583442810875 mfu:3.7963059701599207 
Step 1087 | loss:1.5670888423919678 lr:0.00016888780753275542 tokens_per_second_per_gpu:394.0345560035518 mfu:6.502158146361003 
Step 1088 | loss:1.5862245559692383 lr:0.00016883270131407864 tokens_per_second_per_gpu:327.9571355575866 mfu:5.411782109292363 
Step 1089 | loss:1.2992298603057861 lr:0.00016877755534389527 tokens_per_second_per_gpu:260.71039065920473 mfu:4.302110473910891 
Step 1090 | loss:1.2947723865509033 lr:0.00016872236965405257 tokens_per_second_per_gpu:410.9512686552554 mfu:6.781309147972474 
Step 1091 | loss:1.3276686668395996 lr:0.00016866714427642076 tokens_per_second_per_gpu:353.4404899597761 mfu:5.8322954827978775 
Step 1092 | loss:1.3910095691680908 lr:0.000168611879242893 tokens_per_second_per_gpu:277.0177856374852 mfu:4.5712068246964215 
Step 1093 | loss:1.362156629562378 lr:0.00016855657458538542 tokens_per_second_per_gpu:206.74445157446226 mfu:3.411591951868583 
Step 1094 | loss:1.4832897186279297 lr:0.00016850123033583685 tokens_per_second_per_gpu:307.8458330980612 mfu:5.079915608934069 
Step 1095 | loss:1.3936138153076172 lr:0.00016844584652620913 tokens_per_second_per_gpu:247.9808478393969 mfu:4.092054022556105 
Step 1096 | loss:1.195754885673523 lr:0.00016839042318848692 tokens_per_second_per_gpu:302.13558320839894 mfu:4.985687965007607 
Step 1097 | loss:1.5189300775527954 lr:0.00016833496035467772 tokens_per_second_per_gpu:250.7461632557173 mfu:4.137685853286513 
Step 1098 | loss:1.340651273727417 lr:0.0001682794580568118 tokens_per_second_per_gpu:393.29709647057473 mfu:6.489988963641112 
Step 1099 | loss:1.2761446237564087 lr:0.0001682239163269422 tokens_per_second_per_gpu:243.92898136634412 mfu:4.025192179617919 
Step 1100 | loss:1.3339054584503174 lr:0.00016816833519714481 tokens_per_second_per_gpu:245.2473426360736 mfu:4.04694710780686 
Step 1101 | loss:1.2119320631027222 lr:0.00016811271469951826 tokens_per_second_per_gpu:267.37597426457637 mfu:4.412102549680831 
Step 1102 | loss:1.3704699277877808 lr:0.00016805705486618386 tokens_per_second_per_gpu:260.3635743359763 mfu:4.296387487063639 
Step 1103 | loss:1.2746027708053589 lr:0.0001680013557292856 tokens_per_second_per_gpu:287.7525834221223 mfu:4.748347006443038 
Step 1104 | loss:1.3529149293899536 lr:0.00016794561732099038 tokens_per_second_per_gpu:261.99804837746075 mfu:4.323358747685152 
Step 1105 | loss:1.3647876977920532 lr:0.0001678898396734875 tokens_per_second_per_gpu:277.76402961607187 mfu:4.583520963876886 
Step 1106 | loss:1.3063664436340332 lr:0.00016783402281898914 tokens_per_second_per_gpu:233.8969277228577 mfu:3.859648324824286 
Step 1107 | loss:1.2980130910873413 lr:0.00016777816678972997 tokens_per_second_per_gpu:297.1785878794806 mfu:4.903890145328285 
Step 1108 | loss:1.3929418325424194 lr:0.00016772227161796743 tokens_per_second_per_gpu:185.24130331974 mfu:3.056757918998658 
Step 1109 | loss:1.412407398223877 lr:0.00016766633733598143 tokens_per_second_per_gpu:340.20905334055135 mfu:5.613957034834506 
Step 1110 | loss:1.419091820716858 lr:0.0001676103639760745 tokens_per_second_per_gpu:281.5433937385104 mfu:4.645886111406122 
Step 1111 | loss:1.306636095046997 lr:0.00016755435157057185 tokens_per_second_per_gpu:261.41973732047404 mfu:4.313815752298009 
Step 1112 | loss:1.3374600410461426 lr:0.00016749830015182107 tokens_per_second_per_gpu:207.55679022587987 mfu:3.4249967517762117 
Step 1113 | loss:1.4062492847442627 lr:0.00016744220975219238 tokens_per_second_per_gpu:169.0837055447686 mfu:2.790133445592808 
Step 1114 | loss:1.4990261793136597 lr:0.0001673860804040785 tokens_per_second_per_gpu:282.9523798593893 mfu:4.669136484868036 
Step 1115 | loss:1.6682000160217285 lr:0.00016732991213989467 tokens_per_second_per_gpu:152.32046599598138 mfu:2.5135149791896603 
Step 1116 | loss:1.4152501821517944 lr:0.0001672737049920785 tokens_per_second_per_gpu:265.8649651356311 mfu:4.387168644348659 
Step 1117 | loss:1.3914257287979126 lr:0.0001672174589930902 tokens_per_second_per_gpu:221.0854034813244 mfu:3.6482390576796138 
Step 1118 | loss:1.30116868019104 lr:0.00016716117417541227 tokens_per_second_per_gpu:179.9272635096019 mfu:2.9690683326029284 
Step 1119 | loss:1.267817497253418 lr:0.00016710485057154975 tokens_per_second_per_gpu:282.122834106871 mfu:4.655447742116075 
Step 1120 | loss:1.282429575920105 lr:0.00016704848821403 tokens_per_second_per_gpu:247.47791119944657 mfu:4.083754817522608 
Step 1121 | loss:1.5041674375534058 lr:0.0001669920871354028 tokens_per_second_per_gpu:256.12780219253744 mfu:4.226490926142872 
Step 1122 | loss:1.3347851037979126 lr:0.0001669356473682403 tokens_per_second_per_gpu:288.0564158891939 mfu:4.753360695523852 
Step 1123 | loss:1.4342014789581299 lr:0.00016687916894513695 tokens_per_second_per_gpu:233.49196216407202 mfu:3.8529657888209456 
Step 1124 | loss:1.2481666803359985 lr:0.00016682265189870958 tokens_per_second_per_gpu:307.7562075860449 mfu:5.07843665424799 
Step 1125 | loss:1.5216307640075684 lr:0.0001667660962615973 tokens_per_second_per_gpu:198.92686107466156 mfu:3.282590043333598 
Step 1126 | loss:1.4130953550338745 lr:0.00016670950206646142 tokens_per_second_per_gpu:265.8623620741047 mfu:4.387125689949224 
Step 1127 | loss:1.5037786960601807 lr:0.00016665286934598568 tokens_per_second_per_gpu:261.69026481956803 mfu:4.3182798597100325 
Step 1128 | loss:1.4668766260147095 lr:0.00016659619813287597 tokens_per_second_per_gpu:292.32238709293193 mfu:4.82375558600213 
Step 1129 | loss:1.2988735437393188 lr:0.00016653948845986042 tokens_per_second_per_gpu:255.85658145856263 mfu:4.22201537932088 
Step 1130 | loss:1.4701833724975586 lr:0.00016648274035968935 tokens_per_second_per_gpu:240.10560538767444 mfu:3.9621007707870555 
Step 1131 | loss:1.412070393562317 lr:0.00016642595386513536 tokens_per_second_per_gpu:243.66180581833865 mfu:4.020783384400587 
Step 1132 | loss:1.3658028841018677 lr:0.00016636912900899314 tokens_per_second_per_gpu:313.6986702259107 mfu:5.176496155057104 
Step 1133 | loss:1.4008409976959229 lr:0.00016631226582407952 tokens_per_second_per_gpu:267.63300801024496 mfu:4.4163439900261645 
Step 1134 | loss:1.518680453300476 lr:0.00016625536434323356 tokens_per_second_per_gpu:219.9603407920872 mfu:3.6296738445059638 
Step 1135 | loss:1.4593156576156616 lr:0.00016619842459931634 tokens_per_second_per_gpu:256.81483344518836 mfu:4.2378279669890775 
Step 1136 | loss:1.6563692092895508 lr:0.0001661414466252111 tokens_per_second_per_gpu:234.40969998721118 mfu:3.8681098323370025 
Step 1137 | loss:1.6196491718292236 lr:0.0001660844304538231 tokens_per_second_per_gpu:227.31365257884082 mfu:3.7510144614861187 
Step 1138 | loss:1.5736281871795654 lr:0.00016602737611807976 tokens_per_second_per_gpu:259.3991323961018 mfu:4.280472755930285 
Step 1139 | loss:1.3702514171600342 lr:0.0001659702836509304 tokens_per_second_per_gpu:263.80349859782336 mfu:4.353151370386178 
Step 1140 | loss:1.388120412826538 lr:0.00016591315308534646 tokens_per_second_per_gpu:226.9227819300512 mfu:3.7445645125299216 
Step 1141 | loss:1.4663991928100586 lr:0.00016585598445432136 tokens_per_second_per_gpu:189.84727524575126 mfu:3.13276332873829 
Step 1142 | loss:1.4606748819351196 lr:0.00016579877779087054 tokens_per_second_per_gpu:215.25972482247934 mfu:3.552106666820601 
Step 1143 | loss:1.5536367893218994 lr:0.0001657415331280313 tokens_per_second_per_gpu:261.1423217329063 mfu:4.309237981147869 
Step 1144 | loss:1.3503477573394775 lr:0.00016568425049886298 tokens_per_second_per_gpu:248.48149599365027 mfu:4.100315464160759 
Step 1145 | loss:1.334963083267212 lr:0.00016562692993644685 tokens_per_second_per_gpu:310.8899231256462 mfu:5.130147636733528 
Step 1146 | loss:1.4034934043884277 lr:0.00016556957147388597 tokens_per_second_per_gpu:287.71172949650287 mfu:4.747672855708718 
Step 1147 | loss:1.4623326063156128 lr:0.00016551217514430543 tokens_per_second_per_gpu:155.56962680184893 mfu:2.567130980834242 
Step 1148 | loss:1.5093963146209717 lr:0.0001654547409808521 tokens_per_second_per_gpu:212.59414060666882 mfu:3.5081205497159695 
Step 1149 | loss:1.3441283702850342 lr:0.00016539726901669476 tokens_per_second_per_gpu:230.523669423639 mfu:3.8039845293630394 
Step 1150 | loss:1.2796902656555176 lr:0.000165339759285024 tokens_per_second_per_gpu:282.78953045257015 mfu:4.66644922665414 
Step 1151 | loss:1.3883662223815918 lr:0.00016528221181905217 tokens_per_second_per_gpu:151.74217546614287 mfu:2.503972322531093 
Step 1152 | loss:1.3986421823501587 lr:0.00016522462665201346 tokens_per_second_per_gpu:257.41504564681145 mfu:4.247732363943272 
Step 1153 | loss:1.3605178594589233 lr:0.00016516700381716382 tokens_per_second_per_gpu:251.9465920336316 mfu:4.157494719383453 
Step 1154 | loss:1.3598082065582275 lr:0.00016510934334778096 tokens_per_second_per_gpu:254.9185075858071 mfu:4.206535760641014 
Step 1155 | loss:1.4668376445770264 lr:0.00016505164527716435 tokens_per_second_per_gpu:244.30023415766226 mfu:4.031318404652373 
Step 1156 | loss:1.3387798070907593 lr:0.0001649939096386351 tokens_per_second_per_gpu:168.41922096870715 mfu:2.7791684585541327 
Step 1157 | loss:1.4347184896469116 lr:0.0001649361364655361 tokens_per_second_per_gpu:306.6552014373872 mfu:5.060268409890701 
Step 1158 | loss:1.399531364440918 lr:0.00016487832579123186 tokens_per_second_per_gpu:175.01889511114675 mfu:2.888072929836608 
Step 1159 | loss:1.404834270477295 lr:0.00016482047764910856 tokens_per_second_per_gpu:245.73700051984642 mfu:4.055027193549072 
Step 1160 | loss:1.5629565715789795 lr:0.00016476259207257407 tokens_per_second_per_gpu:218.93095707640705 mfu:3.612687477166697 
Step 1161 | loss:1.3983651399612427 lr:0.00016470466909505776 tokens_per_second_per_gpu:191.3667473336356 mfu:3.1578368855212546 
Step 1162 | loss:1.3487191200256348 lr:0.00016464670875001073 tokens_per_second_per_gpu:385.2030265880499 mfu:6.356424732732897 
Step 1163 | loss:1.3440016508102417 lr:0.0001645887110709056 tokens_per_second_per_gpu:250.14275916781023 mfu:4.127728785445749 
Step 1164 | loss:1.5242042541503906 lr:0.00016453067609123654 tokens_per_second_per_gpu:253.0543121697481 mfu:4.17577375455232 
Step 1165 | loss:1.2910754680633545 lr:0.00016447260384451923 tokens_per_second_per_gpu:194.32456587338731 mfu:3.2066453050384784 
Step 1166 | loss:1.2195223569869995 lr:0.000164414494364291 tokens_per_second_per_gpu:428.6839105630953 mfu:7.073924199827278 
Step 1167 | loss:1.349074125289917 lr:0.00016435634768411056 tokens_per_second_per_gpu:292.8991406701202 mfu:4.8332728806485505 
Step 1168 | loss:1.504604458808899 lr:0.0001642981638375581 tokens_per_second_per_gpu:269.50341148961456 mfu:4.447208438423059 
Step 1169 | loss:1.6013376712799072 lr:0.00016423994285823539 tokens_per_second_per_gpu:208.5494424191749 mfu:3.441376994185911 
Step 1170 | loss:1.311617136001587 lr:0.00016418168477976553 tokens_per_second_per_gpu:217.17131797169333 mfu:3.58365080623252 
Step 1171 | loss:1.336463212966919 lr:0.00016412338963579313 tokens_per_second_per_gpu:248.17895332343446 mfu:4.0953230586526805 
Step 1172 | loss:1.5875277519226074 lr:0.0001640650574599841 tokens_per_second_per_gpu:246.56101735818848 mfu:4.068624700966965 
Step 1173 | loss:1.4698305130004883 lr:0.00016400668828602585 tokens_per_second_per_gpu:265.80630834860057 mfu:4.386200719835899 
Step 1174 | loss:1.3532066345214844 lr:0.00016394828214762706 tokens_per_second_per_gpu:319.8129416153654 mfu:5.277390756604809 
Step 1175 | loss:1.3884445428848267 lr:0.00016388983907851784 tokens_per_second_per_gpu:213.7904312273777 mfu:3.527861130044126 
Step 1176 | loss:1.4950716495513916 lr:0.00016383135911244955 tokens_per_second_per_gpu:194.3616231899612 mfu:3.207256806058305 
Step 1177 | loss:1.422478437423706 lr:0.00016377284228319495 tokens_per_second_per_gpu:228.25462620949435 mfu:3.7665419304982772 
Step 1178 | loss:1.2502501010894775 lr:0.000163714288624548 tokens_per_second_per_gpu:223.20873969763602 mfu:3.68327727365839 
Step 1179 | loss:1.3416495323181152 lr:0.00016365569817032398 tokens_per_second_per_gpu:268.3326033019334 mfu:4.427888356264354 
Step 1180 | loss:1.3064053058624268 lr:0.0001635970709543594 tokens_per_second_per_gpu:242.1698648409147 mfu:3.996164132021718 
Step 1181 | loss:1.3849859237670898 lr:0.000163538407010512 tokens_per_second_per_gpu:208.51955347124223 mfu:3.4408837819451934 
Step 1182 | loss:1.1659513711929321 lr:0.00016347970637266076 tokens_per_second_per_gpu:280.589889384619 mfu:4.630151866762386 
Step 1183 | loss:1.0516704320907593 lr:0.00016342096907470582 tokens_per_second_per_gpu:285.63594050969164 mfu:4.713419239965941 
Step 1184 | loss:1.3422898054122925 lr:0.0001633621951505685 tokens_per_second_per_gpu:192.12142979402537 mfu:3.170290272243243 
Step 1185 | loss:1.392751693725586 lr:0.00016330338463419128 tokens_per_second_per_gpu:214.3392987105101 mfu:3.5369182625274247 
Step 1186 | loss:1.3826053142547607 lr:0.00016324453755953773 tokens_per_second_per_gpu:314.2366595309853 mfu:5.1853737813702 
Step 1187 | loss:1.367964744567871 lr:0.0001631856539605926 tokens_per_second_per_gpu:273.462997701441 mfu:4.512547519351823 
Step 1188 | loss:1.2349108457565308 lr:0.0001631267338713617 tokens_per_second_per_gpu:200.4578398299144 mfu:3.3078534772982153 
Step 1189 | loss:1.372558355331421 lr:0.00016306777732587189 tokens_per_second_per_gpu:243.23447125022815 mfu:4.013731726364695 
Step 1190 | loss:1.112696886062622 lr:0.00016300878435817113 tokens_per_second_per_gpu:294.5454735877886 mfu:4.860439830422731 
Step 1191 | loss:1.3623796701431274 lr:0.00016294975500232836 tokens_per_second_per_gpu:224.01715972864497 mfu:3.6966174104819713 
Step 1192 | loss:1.4797872304916382 lr:0.0001628906892924336 tokens_per_second_per_gpu:303.09021237983757 mfu:5.001440770819307 
Step 1193 | loss:1.3377634286880493 lr:0.00016283158726259784 tokens_per_second_per_gpu:248.38704165659112 mfu:4.098756826655975 
Step 1194 | loss:1.4230589866638184 lr:0.000162772448946953 tokens_per_second_per_gpu:241.84581994455573 mfu:3.9908169076969857 
Step 1195 | loss:1.3749432563781738 lr:0.00016271327437965201 tokens_per_second_per_gpu:244.22467508098322 mfu:4.0300715671390765 
Step 1196 | loss:1.4495022296905518 lr:0.0001626540635948687 tokens_per_second_per_gpu:205.47514815190758 mfu:3.390646551361391 
Step 1197 | loss:1.3441640138626099 lr:0.00016259481662679788 tokens_per_second_per_gpu:203.2247030252094 mfu:3.3535108486912755 
Step 1198 | loss:1.5906126499176025 lr:0.00016253553350965516 tokens_per_second_per_gpu:240.43790518324272 mfu:3.9675842132665746 
Step 1199 | loss:1.2419469356536865 lr:0.00016247621427767708 tokens_per_second_per_gpu:284.1924736988838 mfu:4.689599883668644 
Step 1200 | loss:1.3221311569213867 lr:0.00016241685896512103 tokens_per_second_per_gpu:259.25124625955834 mfu:4.278032414003901 
Step 1201 | loss:1.3742989301681519 lr:0.00016235746760626528 tokens_per_second_per_gpu:266.10375755970847 mfu:4.391109075668316 
Step 1202 | loss:1.2020034790039062 lr:0.00016229804023540887 tokens_per_second_per_gpu:262.44238438059773 mfu:4.330690954768261 
Step 1203 | loss:1.4143868684768677 lr:0.0001622385768868716 tokens_per_second_per_gpu:270.01976439934776 mfu:4.4557290319275245 
Step 1204 | loss:1.288175106048584 lr:0.00016217907759499408 tokens_per_second_per_gpu:203.70949312181045 mfu:3.3615106086815167 
Step 1205 | loss:1.4127211570739746 lr:0.00016211954239413778 tokens_per_second_per_gpu:260.6862746534535 mfu:4.301712523830463 
Step 1206 | loss:1.1290796995162964 lr:0.00016205997131868473 tokens_per_second_per_gpu:258.53867901757826 mfu:4.266273991229354 
Step 1207 | loss:1.5132458209991455 lr:0.00016200036440303778 tokens_per_second_per_gpu:247.41159889110767 mfu:4.082660565484809 
Step 1208 | loss:1.3232958316802979 lr:0.00016194072168162048 tokens_per_second_per_gpu:286.6089703831639 mfu:4.729475684818442 
Step 1209 | loss:1.3673336505889893 lr:0.00016188104318887704 tokens_per_second_per_gpu:232.0072675410043 mfu:3.8284661121018533 
Step 1210 | loss:1.3050472736358643 lr:0.00016182132895927232 tokens_per_second_per_gpu:299.2791370684365 mfu:4.938552341353241 
Step 1211 | loss:1.2579295635223389 lr:0.00016176157902729186 tokens_per_second_per_gpu:249.19461742782337 mfu:4.112083031933448 
Step 1212 | loss:1.4207332134246826 lr:0.0001617017934274417 tokens_per_second_per_gpu:195.52695541280215 mfu:3.2264865266259957 
Step 1213 | loss:1.3244065046310425 lr:0.00016164197219424863 tokens_per_second_per_gpu:327.5640518124738 mfu:5.405295640944486 
Step 1214 | loss:1.5731085538864136 lr:0.00016158211536225996 tokens_per_second_per_gpu:215.68015234160552 mfu:3.559044348241659 
Step 1215 | loss:1.2907824516296387 lr:0.00016152222296604354 tokens_per_second_per_gpu:252.65275692554806 mfu:4.169147493828461 
Step 1216 | loss:1.4382089376449585 lr:0.00016146229504018775 tokens_per_second_per_gpu:256.2678790783232 mfu:4.22880240377891 
Step 1217 | loss:1.6121290922164917 lr:0.00016140233161930152 tokens_per_second_per_gpu:188.71529650594263 mfu:3.1140839904101876 
Step 1218 | loss:1.450840711593628 lr:0.00016134233273801428 tokens_per_second_per_gpu:204.662180171391 mfu:3.377231366584554 
Step 1219 | loss:1.339296817779541 lr:0.0001612822984309759 tokens_per_second_per_gpu:248.80421857442983 mfu:4.105640868305292 
Step 1220 | loss:1.5162897109985352 lr:0.00016122222873285672 tokens_per_second_per_gpu:250.37414499569402 mfu:4.131546996876204 
Step 1221 | loss:1.322876214981079 lr:0.0001611621236783476 tokens_per_second_per_gpu:240.88628365698713 mfu:3.974983127146818 
Step 1222 | loss:1.4569050073623657 lr:0.0001611019833021597 tokens_per_second_per_gpu:360.2313581193553 mfu:5.944354940659928 
Step 1223 | loss:1.3764694929122925 lr:0.00016104180763902465 tokens_per_second_per_gpu:290.4139805680734 mfu:4.792264030647107 
Step 1224 | loss:1.4941667318344116 lr:0.00016098159672369442 tokens_per_second_per_gpu:218.14519188331423 mfu:3.599721178973933 
Step 1225 | loss:1.4480239152908325 lr:0.00016092135059094138 tokens_per_second_per_gpu:229.64482681928274 mfu:3.7894823149957477 
Step 1226 | loss:1.283759593963623 lr:0.0001608610692755582 tokens_per_second_per_gpu:294.67386712153524 mfu:4.862558515316406 
Step 1227 | loss:1.5254566669464111 lr:0.0001608007528123579 tokens_per_second_per_gpu:238.68503151711928 mfu:3.938659182164421 
Step 1228 | loss:1.541223406791687 lr:0.00016074040123617374 tokens_per_second_per_gpu:217.10098498863454 mfu:3.582490207062255 
Step 1229 | loss:1.3899445533752441 lr:0.00016068001458185936 tokens_per_second_per_gpu:275.0430038120029 mfu:4.538619977836905 
Step 1230 | loss:1.6232774257659912 lr:0.00016061959288428854 tokens_per_second_per_gpu:207.71972748539665 mfu:3.4276854596907103 
Step 1231 | loss:1.3406221866607666 lr:0.0001605591361783554 tokens_per_second_per_gpu:268.88803268390177 mfu:4.437053769870011 
Step 1232 | loss:1.410765528678894 lr:0.00016049864449897423 tokens_per_second_per_gpu:178.539022171933 mfu:2.946160279019025 
Step 1233 | loss:1.3112226724624634 lr:0.00016043811788107952 tokens_per_second_per_gpu:294.109018150234 mfu:4.853237664430991 
Step 1234 | loss:1.3938446044921875 lr:0.0001603775563596259 tokens_per_second_per_gpu:275.70927894832835 mfu:4.549614511791783 
Step 1235 | loss:1.3825939893722534 lr:0.00016031695996958822 tokens_per_second_per_gpu:210.09964734566108 mfu:3.4669576886648747 
Step 1236 | loss:1.4282280206680298 lr:0.00016025632874596148 tokens_per_second_per_gpu:274.08975860991177 mfu:4.522890009584576 
Step 1237 | loss:1.5186293125152588 lr:0.0001601956627237607 tokens_per_second_per_gpu:269.44336857072153 mfu:4.4462176406662035 
Step 1238 | loss:1.219001054763794 lr:0.0001601349619380211 tokens_per_second_per_gpu:275.5522115614213 mfu:4.5470226655342785 
Step 1239 | loss:1.3465635776519775 lr:0.0001600742264237979 tokens_per_second_per_gpu:221.90856773179866 mfu:3.6618224961254695 
Step 1240 | loss:1.2637642621994019 lr:0.0001600134562161664 tokens_per_second_per_gpu:209.10460954322306 mfu:3.450538080144547 
Step 1241 | loss:1.386626124382019 lr:0.00015995265135022204 tokens_per_second_per_gpu:206.97564658564028 mfu:3.4154070145386592 
Step 1242 | loss:1.3390475511550903 lr:0.00015989181186108002 tokens_per_second_per_gpu:272.9915631890129 mfu:4.5047681464294325 
Step 1243 | loss:1.4306886196136475 lr:0.0001598309377838758 tokens_per_second_per_gpu:322.2114209294041 mfu:5.31696924426038 
Step 1244 | loss:1.4001073837280273 lr:0.00015977002915376474 tokens_per_second_per_gpu:268.3378932282864 mfu:4.427975647942726 
Step 1245 | loss:1.3014267683029175 lr:0.00015970908600592201 tokens_per_second_per_gpu:158.77906112523746 mfu:2.6200914362386745 
Step 1246 | loss:1.2975324392318726 lr:0.00015964810837554292 tokens_per_second_per_gpu:323.0670153884078 mfu:5.33108782953883 
Step 1247 | loss:1.4639081954956055 lr:0.00015958709629784257 tokens_per_second_per_gpu:258.86982019992263 mfu:4.271738314861813 
Step 1248 | loss:1.3497226238250732 lr:0.00015952604980805599 tokens_per_second_per_gpu:266.2018140141261 mfu:4.3927271534845405 
Step 1249 | loss:1.1633803844451904 lr:0.00015946496894143807 tokens_per_second_per_gpu:342.85634289623994 mfu:5.657641262748116 
Step 1250 | loss:1.3719574213027954 lr:0.00015940385373326357 tokens_per_second_per_gpu:333.33925131271985 mfu:5.50059505036239 
Step 1251 | loss:1.3619049787521362 lr:0.00015934270421882709 tokens_per_second_per_gpu:361.38754018161205 mfu:5.96343366992425 
Step 1252 | loss:1.1836585998535156 lr:0.00015928152043344297 tokens_per_second_per_gpu:262.27211597041475 mfu:4.327881271928339 
Step 1253 | loss:1.578178882598877 lr:0.00015922030241244546 tokens_per_second_per_gpu:230.55917985169245 mfu:3.804570504414036 
Step 1254 | loss:1.5430982112884521 lr:0.00015915905019118852 tokens_per_second_per_gpu:248.78064501359708 mfu:4.105251869375446 
Step 1255 | loss:1.415256142616272 lr:0.00015909776380504585 tokens_per_second_per_gpu:265.41395720839733 mfu:4.379726340562211 
Step 1256 | loss:1.2504160404205322 lr:0.00015903644328941086 tokens_per_second_per_gpu:249.47939109693536 mfu:4.116782222408683 
Step 1257 | loss:1.3528417348861694 lr:0.0001589750886796967 tokens_per_second_per_gpu:299.65048049209634 mfu:4.944680061956572 
Step 1258 | loss:1.3292146921157837 lr:0.00015891370001133628 tokens_per_second_per_gpu:353.94134900644355 mfu:5.840560404442054 
Step 1259 | loss:1.581383466720581 lr:0.00015885227731978204 tokens_per_second_per_gpu:193.2987497433636 mfu:3.18971780818604 
Step 1260 | loss:1.2837495803833008 lr:0.00015879082064050617 tokens_per_second_per_gpu:236.6644104294301 mfu:3.9053159190778484 
Step 1261 | loss:1.3569793701171875 lr:0.00015872933000900044 tokens_per_second_per_gpu:261.9534225018026 mfu:4.3226223541467474 
Step 1262 | loss:1.463329553604126 lr:0.00015866780546077626 tokens_per_second_per_gpu:170.4768680442869 mfu:2.8131227056905086 
Step 1263 | loss:1.4185020923614502 lr:0.00015860624703136465 tokens_per_second_per_gpu:314.0539347654766 mfu:5.182358550080222 
Step 1264 | loss:1.2401232719421387 lr:0.00015854465475631605 tokens_per_second_per_gpu:228.12725796941274 mfu:3.7644401644800025 
Step 1265 | loss:1.4807381629943848 lr:0.00015848302867120065 tokens_per_second_per_gpu:288.6419352425072 mfu:4.763022638556492 
Step 1266 | loss:1.4583642482757568 lr:0.00015842136881160805 tokens_per_second_per_gpu:225.3951442129291 mfu:3.719356210679907 
Step 1267 | loss:1.4095892906188965 lr:0.00015835967521314736 tokens_per_second_per_gpu:294.83859677219664 mfu:4.86527680035937 
Step 1268 | loss:1.24833345413208 lr:0.0001582979479114472 tokens_per_second_per_gpu:303.50275478586724 mfu:5.0082483361082275 
Step 1269 | loss:1.331405520439148 lr:0.00015823618694215568 tokens_per_second_per_gpu:218.27535580019145 mfu:3.6018690778310014 
Step 1270 | loss:1.4626030921936035 lr:0.00015817439234094022 tokens_per_second_per_gpu:181.74676236063317 mfu:2.9990927786731376 
Step 1271 | loss:1.3725546598434448 lr:0.00015811256414348789 tokens_per_second_per_gpu:349.7423924612482 mfu:5.771271355827974 
Step 1272 | loss:1.350989818572998 lr:0.0001580507023855049 tokens_per_second_per_gpu:364.69009383728394 mfu:6.017930733262592 
Step 1273 | loss:1.3281657695770264 lr:0.0001579888071027171 tokens_per_second_per_gpu:202.51417730080004 mfu:3.3417861140029665 
Step 1274 | loss:1.4182186126708984 lr:0.00015792687833086943 tokens_per_second_per_gpu:222.67735569937946 mfu:3.6745086447641304 
Step 1275 | loss:1.4017189741134644 lr:0.00015786491610572645 tokens_per_second_per_gpu:206.75247376790514 mfu:3.411724330030984 
Step 1276 | loss:1.2094441652297974 lr:0.00015780292046307186 tokens_per_second_per_gpu:173.77559600641007 mfu:2.867556639376656 
Step 1277 | loss:1.3979023694992065 lr:0.00015774089143870868 tokens_per_second_per_gpu:301.5547262197726 mfu:4.97610295794941 
Step 1278 | loss:1.5493556261062622 lr:0.00015767882906845925 tokens_per_second_per_gpu:226.9799147314503 mfu:3.745507289005693 
Step 1279 | loss:1.3493733406066895 lr:0.00015761673338816513 tokens_per_second_per_gpu:214.82933846805417 mfu:3.545004649756689 
Step 1280 | loss:1.5371047258377075 lr:0.0001575546044336872 tokens_per_second_per_gpu:262.04500328425286 mfu:4.324133573712611 
Step 1281 | loss:1.254266381263733 lr:0.00015749244224090537 tokens_per_second_per_gpu:254.7817330012752 mfu:4.2042787759033065 
Step 1282 | loss:1.5117162466049194 lr:0.000157430246845719 tokens_per_second_per_gpu:294.3011283185614 mfu:4.85640776887223 
Step 1283 | loss:1.2469103336334229 lr:0.0001573680182840464 tokens_per_second_per_gpu:234.26286855386138 mfu:3.865686894587125 
Step 1284 | loss:1.3817100524902344 lr:0.00015730575659182521 tokens_per_second_per_gpu:256.4333018264791 mfu:4.231532125964764 
Step 1285 | loss:1.2789474725723267 lr:0.00015724346180501204 tokens_per_second_per_gpu:264.29872211451675 mfu:4.361323297376531 
Step 1286 | loss:1.300360918045044 lr:0.00015718113395958274 tokens_per_second_per_gpu:247.038317218261 mfu:4.07650086087767 
Step 1287 | loss:1.3473070859909058 lr:0.00015711877309153218 tokens_per_second_per_gpu:223.88531243397725 mfu:3.6944417333794495 
Step 1288 | loss:1.2483099699020386 lr:0.0001570563792368743 tokens_per_second_per_gpu:238.79365947978235 mfu:3.940451705641336 
Step 1289 | loss:1.3015481233596802 lr:0.00015699395243164217 tokens_per_second_per_gpu:289.94429307956614 mfu:4.7845134862262935 
Step 1290 | loss:1.3365648984909058 lr:0.0001569314927118878 tokens_per_second_per_gpu:279.82848951707706 mfu:4.617587632798775 
Step 1291 | loss:1.3637675046920776 lr:0.00015686900011368228 tokens_per_second_per_gpu:401.59852076990165 mfu:6.626974851837631 
Step 1292 | loss:1.250847339630127 lr:0.00015680647467311557 tokens_per_second_per_gpu:237.24365341345398 mfu:3.9148742926517115 
Step 1293 | loss:1.2448382377624512 lr:0.0001567439164262968 tokens_per_second_per_gpu:192.83331496479093 mfu:3.1820374398249744 
Step 1294 | loss:1.4387638568878174 lr:0.0001566813254093538 tokens_per_second_per_gpu:220.01242700939264 mfu:3.6305333448137556 
Step 1295 | loss:1.339601755142212 lr:0.0001566187016584335 tokens_per_second_per_gpu:277.8823089171431 mfu:4.585472748839115 
Step 1296 | loss:1.4266490936279297 lr:0.00015655604520970167 tokens_per_second_per_gpu:297.4210251720096 mfu:4.907890722416211 
Step 1297 | loss:1.3060169219970703 lr:0.00015649335609934303 tokens_per_second_per_gpu:245.34973357048074 mfu:4.048636711010754 
Step 1298 | loss:1.4043757915496826 lr:0.00015643063436356102 tokens_per_second_per_gpu:298.56478722538816 mfu:4.926764503001098 
Step 1299 | loss:1.5326021909713745 lr:0.00015636788003857806 tokens_per_second_per_gpu:205.84504747762278 mfu:3.3967504421937753 
Step 1300 | loss:1.2848286628723145 lr:0.00015630509316063532 tokens_per_second_per_gpu:178.17958345826878 mfu:2.9402290038946473 
Step 1301 | loss:1.3223999738693237 lr:0.00015624227376599283 tokens_per_second_per_gpu:193.00532857618902 mfu:3.1848759210891076 
Step 1302 | loss:1.3342958688735962 lr:0.0001561794218909293 tokens_per_second_per_gpu:222.6225644640807 mfu:3.6736045076230623 
Step 1303 | loss:1.3144086599349976 lr:0.00015611653757174228 tokens_per_second_per_gpu:253.27495792820162 mfu:4.179414738811009 
Step 1304 | loss:1.3454563617706299 lr:0.00015605362084474805 tokens_per_second_per_gpu:266.3357807917436 mfu:4.394937805218394 
Step 1305 | loss:1.2704155445098877 lr:0.0001559906717462816 tokens_per_second_per_gpu:331.6624868863982 mfu:5.4729259352860025 
Step 1306 | loss:1.5206241607666016 lr:0.00015592769031269653 tokens_per_second_per_gpu:248.06043834982864 mfu:4.093367384741964 
Step 1307 | loss:1.385568618774414 lr:0.00015586467658036524 tokens_per_second_per_gpu:262.07320506784623 mfu:4.32459894522417 
Step 1308 | loss:1.5113122463226318 lr:0.00015580163058567873 tokens_per_second_per_gpu:219.33646439841468 mfu:3.6193789530716107 
Step 1309 | loss:1.3410978317260742 lr:0.00015573855236504665 tokens_per_second_per_gpu:259.5496878822686 mfu:4.282957146108618 
Step 1310 | loss:1.4635729789733887 lr:0.0001556754419548972 tokens_per_second_per_gpu:252.949119243057 mfu:4.17403791429465 
Step 1311 | loss:1.355727195739746 lr:0.00015561229939167718 tokens_per_second_per_gpu:218.59458226953137 mfu:3.6071367909199368 
Step 1312 | loss:1.3400601148605347 lr:0.0001555491247118521 tokens_per_second_per_gpu:256.8237406974506 mfu:4.237974949942669 
Step 1313 | loss:1.3371981382369995 lr:0.00015548591795190578 tokens_per_second_per_gpu:306.9513078040852 mfu:5.065154606786583 
Step 1314 | loss:1.2960513830184937 lr:0.0001554226791483408 tokens_per_second_per_gpu:272.8944194812811 mfu:4.503165130295512 
Step 1315 | loss:1.3175363540649414 lr:0.00015535940833767814 tokens_per_second_per_gpu:230.36594910633198 mfu:3.8013819087796428 
Step 1316 | loss:1.1813509464263916 lr:0.00015529610555645716 tokens_per_second_per_gpu:286.2611847406481 mfu:4.723736702756546 
Step 1317 | loss:1.2591197490692139 lr:0.00015523277084123586 tokens_per_second_per_gpu:215.98305826925284 mfu:3.5640427480394052 
Step 1318 | loss:1.30470609664917 lr:0.00015516940422859063 tokens_per_second_per_gpu:191.32669898027075 mfu:3.157176027931198 
Step 1319 | loss:1.3286917209625244 lr:0.00015510600575511623 tokens_per_second_per_gpu:235.73037923084945 mfu:3.8899030105542827 
Step 1320 | loss:1.355210781097412 lr:0.00015504257545742584 tokens_per_second_per_gpu:216.74779861108925 mfu:3.5766621048134786 
Step 1321 | loss:1.4305797815322876 lr:0.00015497911337215104 tokens_per_second_per_gpu:264.34246336316266 mfu:4.362045093249208 
Step 1322 | loss:1.4617257118225098 lr:0.00015491561953594177 tokens_per_second_per_gpu:236.8660158252882 mfu:3.9086427089419775 
Step 1323 | loss:1.333406686782837 lr:0.0001548520939854663 tokens_per_second_per_gpu:305.598582948375 mfu:5.042832628152147 
Step 1324 | loss:1.3140294551849365 lr:0.0001547885367574112 tokens_per_second_per_gpu:243.4725450592692 mfu:4.017660299463948 
Step 1325 | loss:1.3472986221313477 lr:0.00015472494788848132 tokens_per_second_per_gpu:280.0183320711674 mfu:4.620720318221404 
Step 1326 | loss:1.4330445528030396 lr:0.0001546613274153998 tokens_per_second_per_gpu:216.5837658241174 mfu:3.573955319061242 
Step 1327 | loss:1.401680588722229 lr:0.0001545976753749081 tokens_per_second_per_gpu:257.64945246813426 mfu:4.25160042627335 
Step 1328 | loss:1.4485697746276855 lr:0.0001545339918037658 tokens_per_second_per_gpu:175.19747326789476 mfu:2.891019735894528 
Step 1329 | loss:1.3438570499420166 lr:0.00015447027673875073 tokens_per_second_per_gpu:225.75152756536824 mfu:3.7252370677849087 
Step 1330 | loss:1.2958205938339233 lr:0.00015440653021665893 tokens_per_second_per_gpu:198.83621463718384 mfu:3.2810942418539963 
Step 1331 | loss:1.504374623298645 lr:0.0001543427522743046 tokens_per_second_per_gpu:249.6018786453041 mfu:4.1188034497308035 
Step 1332 | loss:1.2264126539230347 lr:0.00015427894294852012 tokens_per_second_per_gpu:306.3493363644176 mfu:5.055221179779546 
Step 1333 | loss:1.3630595207214355 lr:0.0001542151022761559 tokens_per_second_per_gpu:209.04936595523247 mfu:3.44962647850907 
Step 1334 | loss:1.587570309638977 lr:0.00015415123029408046 tokens_per_second_per_gpu:234.8250563438248 mfu:3.874963832009492 
Step 1335 | loss:1.4446226358413696 lr:0.0001540873270391805 tokens_per_second_per_gpu:213.67343998569618 mfu:3.52593059998385 
Step 1336 | loss:1.3499445915222168 lr:0.00015402339254836075 tokens_per_second_per_gpu:354.84958297115924 mfu:5.855547620112613 
Step 1337 | loss:1.514020323753357 lr:0.0001539594268585439 tokens_per_second_per_gpu:228.72042655904133 mfu:3.7742283313259173 
Step 1338 | loss:1.5255401134490967 lr:0.00015389543000667074 tokens_per_second_per_gpu:362.403398939279 mfu:5.9801968552745635 
Step 1339 | loss:1.3671842813491821 lr:0.00015383140202970006 tokens_per_second_per_gpu:225.10141212581473 mfu:3.7145091929400182 
Step 1340 | loss:1.1408339738845825 lr:0.00015376734296460856 tokens_per_second_per_gpu:307.31144372073385 mfu:5.07109738680056 
Step 1341 | loss:1.317305088043213 lr:0.00015370325284839092 tokens_per_second_per_gpu:295.0048245631639 mfu:4.868019806952882 
Step 1342 | loss:1.5550094842910767 lr:0.00015363913171805978 tokens_per_second_per_gpu:178.95284989047633 mfu:2.9529890538823453 
Step 1343 | loss:1.502967357635498 lr:0.00015357497961064568 tokens_per_second_per_gpu:226.9745788898481 mfu:3.7454192396571964 
Step 1344 | loss:1.4972202777862549 lr:0.00015351079656319703 tokens_per_second_per_gpu:243.74473000145866 mfu:4.022151757160257 
Step 1345 | loss:1.3984193801879883 lr:0.0001534465826127801 tokens_per_second_per_gpu:278.78917590194015 mfu:4.6004374073012295 
Step 1346 | loss:1.3719435930252075 lr:0.0001533823377964791 tokens_per_second_per_gpu:319.7148531391888 mfu:5.27577215038178 
Step 1347 | loss:1.2139418125152588 lr:0.00015331806215139587 tokens_per_second_per_gpu:279.56195343469614 mfu:4.613189389718449 
Step 1348 | loss:1.4058111906051636 lr:0.00015325375571465026 tokens_per_second_per_gpu:206.30017616558007 mfu:3.4042607446810966 
Step 1349 | loss:1.3503916263580322 lr:0.0001531894185233798 tokens_per_second_per_gpu:248.42846620903995 mfu:4.09944039358446 
Step 1350 | loss:1.2175102233886719 lr:0.00015312505061473982 tokens_per_second_per_gpu:222.70027915581667 mfu:3.6748869160013733 
Step 1351 | loss:1.4157133102416992 lr:0.00015306065202590335 tokens_per_second_per_gpu:256.6945746035074 mfu:4.235843516652949 
Step 1352 | loss:1.4094655513763428 lr:0.0001529962227940611 tokens_per_second_per_gpu:242.87704868882852 mfu:4.007833720761154 
Step 1353 | loss:1.540911078453064 lr:0.00015293176295642168 tokens_per_second_per_gpu:267.0679916524866 mfu:4.407020377014435 
Step 1354 | loss:1.208902359008789 lr:0.00015286727255021108 tokens_per_second_per_gpu:237.01950566206125 mfu:3.9111755202839054 
Step 1355 | loss:1.378527045249939 lr:0.00015280275161267315 tokens_per_second_per_gpu:261.5706131928067 mfu:4.316305429326154 
Step 1356 | loss:1.2441608905792236 lr:0.0001527382001810693 tokens_per_second_per_gpu:229.18142853266465 mfu:3.781835551790755 
Step 1357 | loss:1.3593764305114746 lr:0.0001526736182926786 tokens_per_second_per_gpu:240.48746296894902 mfu:3.9684019906800936 
Step 1358 | loss:1.3479677438735962 lr:0.00015260900598479765 tokens_per_second_per_gpu:223.47689516178633 mfu:3.6877022389543286 
Step 1359 | loss:1.4702355861663818 lr:0.00015254436329474063 tokens_per_second_per_gpu:215.76768538707395 mfu:3.5604887741073523 
Step 1360 | loss:1.30838143825531 lr:0.0001524796902598393 tokens_per_second_per_gpu:370.6068070656789 mfu:6.115565330359562 
Step 1361 | loss:1.4210296869277954 lr:0.0001524149869174429 tokens_per_second_per_gpu:343.3392899906326 mfu:5.665610610451819 
Step 1362 | loss:1.3295423984527588 lr:0.00015235025330491818 tokens_per_second_per_gpu:263.58654313219614 mfu:4.34957128146572 
Step 1363 | loss:1.3112785816192627 lr:0.00015228548945964948 tokens_per_second_per_gpu:184.2511081300279 mfu:3.0404182208143795 
Step 1364 | loss:1.1716804504394531 lr:0.00015222069541903838 tokens_per_second_per_gpu:226.43349003722872 mfu:3.7364904661845153 
Step 1365 | loss:1.2224915027618408 lr:0.0001521558712205041 tokens_per_second_per_gpu:251.0632429616492 mfu:4.142918141575848 
Step 1366 | loss:1.4923701286315918 lr:0.00015209101690148317 tokens_per_second_per_gpu:218.31475171837772 mfu:3.602519169267058 
Step 1367 | loss:1.393873929977417 lr:0.0001520261324994296 tokens_per_second_per_gpu:269.56642762497165 mfu:4.448248298688159 
Step 1368 | loss:1.2891967296600342 lr:0.0001519612180518146 tokens_per_second_per_gpu:247.6625410727912 mfu:4.08680148593465 
Step 1369 | loss:1.6626875400543213 lr:0.00015189627359612698 tokens_per_second_per_gpu:256.4912770747002 mfu:4.232488804070185 
Step 1370 | loss:1.5137594938278198 lr:0.00015183129916987266 tokens_per_second_per_gpu:330.80885385591966 mfu:5.4588397165050315 
Step 1371 | loss:1.5001826286315918 lr:0.000151766294810575 tokens_per_second_per_gpu:283.62505457745874 mfu:4.680236621471047 
Step 1372 | loss:1.2160968780517578 lr:0.00015170126055577462 tokens_per_second_per_gpu:313.3734076422882 mfu:5.17112883707551 
Step 1373 | loss:1.4733883142471313 lr:0.00015163619644302932 tokens_per_second_per_gpu:244.826264393266 mfu:4.039998688474059 
Step 1374 | loss:1.4004840850830078 lr:0.0001515711025099143 tokens_per_second_per_gpu:231.05751206217766 mfu:3.8127937294906995 
Step 1375 | loss:1.354882836341858 lr:0.00015150597879402185 tokens_per_second_per_gpu:271.45611665259827 mfu:4.479430987408892 
Step 1376 | loss:1.365305781364441 lr:0.00015144082533296148 tokens_per_second_per_gpu:224.36633986310943 mfu:3.7023794037418596 
Step 1377 | loss:1.3824822902679443 lr:0.00015137564216435994 tokens_per_second_per_gpu:281.29754210190583 mfu:4.641829192546116 
Step 1378 | loss:1.1945979595184326 lr:0.00015131042932586106 tokens_per_second_per_gpu:247.97221415003855 mfu:4.091911553798634 
Step 1379 | loss:1.5253362655639648 lr:0.0001512451868551259 tokens_per_second_per_gpu:223.17384537717837 mfu:3.6827014653020713 
Step 1380 | loss:1.371312141418457 lr:0.00015117991478983255 tokens_per_second_per_gpu:206.07959165683778 mfu:3.4006207711340384 
Step 1381 | loss:1.4984639883041382 lr:0.0001511146131676762 tokens_per_second_per_gpu:190.17132357473875 mfu:3.138110609706515 
Step 1382 | loss:1.4425525665283203 lr:0.00015104928202636913 tokens_per_second_per_gpu:201.08098319551476 mfu:3.3181362726755643 
Step 1383 | loss:1.3763123750686646 lr:0.0001509839214036407 tokens_per_second_per_gpu:257.5961900766286 mfu:4.250721517336186 
Step 1384 | loss:1.9425735473632812 lr:0.00015091853133723722 tokens_per_second_per_gpu:223.88929386697265 mfu:3.6945074329649064 
Step 1385 | loss:1.3097518682479858 lr:0.00015085311186492206 tokens_per_second_per_gpu:200.17478157677516 mfu:3.303182593746247 
Step 1386 | loss:1.5590054988861084 lr:0.00015078766302447556 tokens_per_second_per_gpu:269.5833390275402 mfu:4.448527362065474 
Step 1387 | loss:1.4055814743041992 lr:0.000150722184853695 tokens_per_second_per_gpu:273.5785311031836 mfu:4.514453992877741 
Step 1388 | loss:1.2164983749389648 lr:0.0001506566773903946 tokens_per_second_per_gpu:323.99770924753545 mfu:5.346445666981494 
Step 1389 | loss:1.252084493637085 lr:0.00015059114067240558 tokens_per_second_per_gpu:268.85285637948647 mfu:4.436473308357619 
Step 1390 | loss:1.5095723867416382 lr:0.0001505255747375759 tokens_per_second_per_gpu:263.77111109115515 mfu:4.352616928198013 
Step 1391 | loss:1.3576030731201172 lr:0.0001504599796237706 tokens_per_second_per_gpu:364.21210600786316 mfu:6.010043220831064 
Step 1392 | loss:1.3288490772247314 lr:0.00015039435536887128 tokens_per_second_per_gpu:305.3625769605682 mfu:5.03893817718883 
Step 1393 | loss:1.1794285774230957 lr:0.0001503287020107767 tokens_per_second_per_gpu:236.08343509882187 mfu:3.8957289592003623 
Step 1394 | loss:1.2904927730560303 lr:0.00015026301958740216 tokens_per_second_per_gpu:243.08150853439898 mfu:4.011207613304903 
Step 1395 | loss:1.2038062810897827 lr:0.0001501973081366799 tokens_per_second_per_gpu:229.95376912808248 mfu:3.7945803240899036 
Step 1396 | loss:1.2537295818328857 lr:0.00015013156769655886 tokens_per_second_per_gpu:274.40590262374207 mfu:4.52810685755801 
Step 1397 | loss:1.377245306968689 lr:0.00015006579830500476 tokens_per_second_per_gpu:270.0940645426728 mfu:4.456955095161918 
Step 1398 | loss:1.173761010169983 lr:0.00015000000000000001 tokens_per_second_per_gpu:296.7181845557109 mfu:4.896292803479328 
Step 1399 | loss:1.3945562839508057 lr:0.00014993417281954373 tokens_per_second_per_gpu:225.06305950808715 mfu:3.7138763175183276 
Step 1400 | loss:1.394254446029663 lr:0.00014986831680165167 tokens_per_second_per_gpu:191.3154455340012 mfu:3.1569903292755312 
Step 1401 | loss:1.367868185043335 lr:0.0001498024319843563 tokens_per_second_per_gpu:218.8971404226137 mfu:3.612129451918416 
Step 1402 | loss:1.3155995607376099 lr:0.00014973651840570674 tokens_per_second_per_gpu:221.987514043178 mfu:3.6631252280656996 
Step 1403 | loss:1.3382314443588257 lr:0.00014967057610376864 tokens_per_second_per_gpu:206.67882590223675 mfu:3.4105090303512435 
Step 1404 | loss:1.071484923362732 lr:0.00014960460511662427 tokens_per_second_per_gpu:380.31771268928816 mfu:6.275809763613088 
Step 1405 | loss:1.957952618598938 lr:0.00014953860548237241 tokens_per_second_per_gpu:264.82562759315914 mfu:4.37001802401438 
Step 1406 | loss:1.4045273065567017 lr:0.0001494725772391286 tokens_per_second_per_gpu:234.55439106530517 mfu:3.8704974510313543 
Step 1407 | loss:1.235317587852478 lr:0.00014940652042502462 tokens_per_second_per_gpu:277.9108771623448 mfu:4.585944167514039 
Step 1408 | loss:1.3336819410324097 lr:0.00014934043507820892 tokens_per_second_per_gpu:258.20581581581393 mfu:4.260781251706893 
Step 1409 | loss:1.3162128925323486 lr:0.00014927432123684634 tokens_per_second_per_gpu:236.87161210132626 mfu:3.908735055847282 
Step 1410 | loss:1.4441722631454468 lr:0.00014920817893911828 tokens_per_second_per_gpu:233.85473078044086 mfu:3.8589520123087797 
Step 1411 | loss:1.2318185567855835 lr:0.00014914200822322256 tokens_per_second_per_gpu:209.87603155450523 mfu:3.46326769443476 
Step 1412 | loss:1.461285948753357 lr:0.00014907580912737323 tokens_per_second_per_gpu:291.5934391934476 mfu:4.811726857935796 
Step 1413 | loss:1.443859338760376 lr:0.00014900958168980092 tokens_per_second_per_gpu:334.961040766859 mfu:5.527356996364959 
Step 1414 | loss:1.4421429634094238 lr:0.00014894332594875262 tokens_per_second_per_gpu:204.03970542761573 mfu:3.366959604465026 
Step 1415 | loss:1.2982847690582275 lr:0.0001488770419424916 tokens_per_second_per_gpu:288.6969535014649 mfu:4.763930521926695 
Step 1416 | loss:1.286630630493164 lr:0.00014881072970929747 tokens_per_second_per_gpu:219.95271631855027 mfu:3.6295480293154823 
Step 1417 | loss:1.3983711004257202 lr:0.00014874438928746608 tokens_per_second_per_gpu:229.0045876817731 mfu:3.7789174138718478 
Step 1418 | loss:1.337887167930603 lr:0.0001486780207153097 tokens_per_second_per_gpu:313.42337364700563 mfu:5.171953350711851 
Step 1419 | loss:1.5511081218719482 lr:0.00014861162403115674 tokens_per_second_per_gpu:191.45228862733066 mfu:3.159248444510626 
Step 1420 | loss:1.4018408060073853 lr:0.00014854519927335192 tokens_per_second_per_gpu:260.9661739180231 mfu:4.306331279357238 
Step 1421 | loss:1.3212206363677979 lr:0.0001484787464802561 tokens_per_second_per_gpu:240.58441859562984 mfu:3.9700019031960223 
Step 1422 | loss:1.4727007150650024 lr:0.00014841226569024642 tokens_per_second_per_gpu:220.3207838281 mfu:3.6356216924477276 
Step 1423 | loss:1.1760302782058716 lr:0.00014834575694171607 tokens_per_second_per_gpu:332.59203031384953 mfu:5.488264788889351 
Step 1424 | loss:1.2513556480407715 lr:0.00014827922027307451 tokens_per_second_per_gpu:277.81071408269014 mfu:4.58429132723793 
Step 1425 | loss:1.4504799842834473 lr:0.0001482126557227472 tokens_per_second_per_gpu:286.35673866448116 mfu:4.725313485083886 
Step 1426 | loss:1.181964635848999 lr:0.00014814606332917585 tokens_per_second_per_gpu:225.20093126875878 mfu:3.7161514072995296 
Step 1427 | loss:1.3419679403305054 lr:0.0001480794431308181 tokens_per_second_per_gpu:194.27122884807332 mfu:3.2057651645321084 
Step 1428 | loss:1.3709014654159546 lr:0.00014801279516614782 tokens_per_second_per_gpu:301.0896223907807 mfu:4.968428050750265 
Step 1429 | loss:1.3957387208938599 lr:0.00014794611947365464 tokens_per_second_per_gpu:223.14752840202803 mfu:3.6822671959423054 
Step 1430 | loss:1.5119304656982422 lr:0.0001478794160918445 tokens_per_second_per_gpu:223.38738315725757 mfu:3.6862251573111684 
Step 1431 | loss:1.2268904447555542 lr:0.0001478126850592392 tokens_per_second_per_gpu:243.26887297436576 mfu:4.014299406146689 
Step 1432 | loss:1.4310033321380615 lr:0.0001477459264143765 tokens_per_second_per_gpu:195.28450778948206 mfu:3.2224857790646007 
Step 1433 | loss:1.1871278285980225 lr:0.00014767914019581007 tokens_per_second_per_gpu:237.76441784302168 mfu:3.9234676828162494 
Step 1434 | loss:1.4467973709106445 lr:0.00014761232644210963 tokens_per_second_per_gpu:268.0578203762574 mfu:4.423354027963846 
Step 1435 | loss:1.3800270557403564 lr:0.00014754548519186066 tokens_per_second_per_gpu:243.91923692675593 mfu:4.025031381824212 
Step 1436 | loss:1.4342221021652222 lr:0.00014747861648366467 tokens_per_second_per_gpu:236.78816429094525 mfu:3.907358042456457 
Step 1437 | loss:1.1620553731918335 lr:0.00014741172035613885 tokens_per_second_per_gpu:217.55832327198485 mfu:3.5900369711706857 
Step 1438 | loss:1.2562023401260376 lr:0.00014734479684791636 tokens_per_second_per_gpu:244.2957452732165 mfu:4.0312443313607735 
Step 1439 | loss:1.3366451263427734 lr:0.00014727784599764614 tokens_per_second_per_gpu:219.063839002582 mfu:3.6148802272329497 
Step 1440 | loss:1.3876696825027466 lr:0.00014721086784399287 tokens_per_second_per_gpu:234.9570739720912 mfu:3.8771423198705617 
Step 1441 | loss:1.3301886320114136 lr:0.0001471438624256371 tokens_per_second_per_gpu:368.2493564847317 mfu:6.076663878022446 
Step 1442 | loss:1.4173102378845215 lr:0.00014707682978127502 tokens_per_second_per_gpu:292.9848474339132 mfu:4.834687170141449 
Step 1443 | loss:1.502784252166748 lr:0.0001470097699496186 tokens_per_second_per_gpu:262.6803523409738 mfu:4.334617781206594 
Step 1444 | loss:1.2112970352172852 lr:0.0001469426829693955 tokens_per_second_per_gpu:336.8286616755477 mfu:5.558175528193511 
Step 1445 | loss:1.2805639505386353 lr:0.00014687556887934907 tokens_per_second_per_gpu:262.91568251498217 mfu:4.338501080233798 
Step 1446 | loss:1.493173599243164 lr:0.00014680842771823825 tokens_per_second_per_gpu:196.79788949571366 mfu:3.247458835462321 
Step 1447 | loss:1.3249115943908691 lr:0.00014674125952483775 tokens_per_second_per_gpu:204.94394413718476 mfu:3.3818808924640065 
Step 1448 | loss:1.2825490236282349 lr:0.00014667406433793774 tokens_per_second_per_gpu:255.86419905469677 mfu:4.2221410810239535 
Step 1449 | loss:1.4833966493606567 lr:0.00014660684219634408 tokens_per_second_per_gpu:151.2823634855171 mfu:2.4963847387264044 
Step 1450 | loss:1.3199806213378906 lr:0.00014653959313887813 tokens_per_second_per_gpu:252.28568151853128 mfu:4.1630902018684095 
Step 1451 | loss:1.5167372226715088 lr:0.00014647231720437686 tokens_per_second_per_gpu:264.77539770049714 mfu:4.369189155833183 
Step 1452 | loss:1.3587076663970947 lr:0.00014640501443169274 tokens_per_second_per_gpu:269.85766955740127 mfu:4.4530542251599785 
Step 1453 | loss:1.3737961053848267 lr:0.00014633768485969371 tokens_per_second_per_gpu:225.12472391748412 mfu:3.71489387228806 
Step 1454 | loss:1.4049452543258667 lr:0.0001462703285272632 tokens_per_second_per_gpu:223.65768930366175 mfu:3.6906856120735103 
Step 1455 | loss:1.369521975517273 lr:0.00014620294547330008 tokens_per_second_per_gpu:204.92207766013516 mfu:3.3815200629638675 
Step 1456 | loss:1.4758975505828857 lr:0.00014613553573671875 tokens_per_second_per_gpu:256.51100427801066 mfu:4.2328143323614364 
Step 1457 | loss:1.3039885759353638 lr:0.00014606809935644886 tokens_per_second_per_gpu:281.17983597304266 mfu:4.639886865780599 
Step 1458 | loss:1.354610800743103 lr:0.00014600063637143553 tokens_per_second_per_gpu:244.33458987460634 mfu:4.031885325247021 
Step 1459 | loss:1.253498911857605 lr:0.00014593314682063933 tokens_per_second_per_gpu:322.80891278673744 mfu:5.326828751474537 
Step 1460 | loss:1.192499041557312 lr:0.00014586563074303602 tokens_per_second_per_gpu:284.9110199494782 mfu:4.701456969007112 
Step 1461 | loss:1.3513085842132568 lr:0.00014579808817761673 tokens_per_second_per_gpu:228.0818327624137 mfu:3.7636905807817227 
Step 1462 | loss:1.489362359046936 lr:0.0001457305191633879 tokens_per_second_per_gpu:246.6445235737029 mfu:4.070002678129644 
Step 1463 | loss:1.467900037765503 lr:0.0001456629237393713 tokens_per_second_per_gpu:206.04987101947864 mfu:3.400130336268935 
Step 1464 | loss:1.3755043745040894 lr:0.0001455953019446039 tokens_per_second_per_gpu:253.9734665024393 mfu:4.19094117258968 
Step 1465 | loss:1.3375437259674072 lr:0.00014552765381813782 tokens_per_second_per_gpu:284.9834136287745 mfu:4.702651572740235 
Step 1466 | loss:1.323163628578186 lr:0.0001454599793990405 tokens_per_second_per_gpu:276.36052668465265 mfu:4.560361071222987 
Step 1467 | loss:1.0712831020355225 lr:0.00014539227872639458 tokens_per_second_per_gpu:288.4427732895829 mfu:4.759736169146839 
Step 1468 | loss:1.4680137634277344 lr:0.00014532455183929773 tokens_per_second_per_gpu:281.0842320980631 mfu:4.638309259184806 
Step 1469 | loss:1.4023913145065308 lr:0.00014525679877686292 tokens_per_second_per_gpu:242.55070527876094 mfu:4.002448567530423 
Step 1470 | loss:1.4296983480453491 lr:0.00014518901957821806 tokens_per_second_per_gpu:248.3687386457232 mfu:4.098454799665182 
Step 1471 | loss:1.3030893802642822 lr:0.00014512121428250633 tokens_per_second_per_gpu:270.7151776566608 mfu:4.467204388358153 
Step 1472 | loss:1.2301325798034668 lr:0.00014505338292888586 tokens_per_second_per_gpu:272.03862829611967 mfu:4.489043298741908 
Step 1473 | loss:1.6707653999328613 lr:0.00014498552555652986 tokens_per_second_per_gpu:179.31524705422876 mfu:2.958969147847733 
Step 1474 | loss:1.2947934865951538 lr:0.00014491764220462663 tokens_per_second_per_gpu:206.39465898667726 mfu:3.405819852215012 
Step 1475 | loss:1.567277193069458 lr:0.00014484973291237934 tokens_per_second_per_gpu:246.79667843131963 mfu:4.072513460323457 
Step 1476 | loss:1.3889145851135254 lr:0.00014478179771900632 tokens_per_second_per_gpu:233.9695240835885 mfu:3.8608462731035167 
Step 1477 | loss:1.238279938697815 lr:0.0001447138366637407 tokens_per_second_per_gpu:258.9233626771735 mfu:4.272621845631713 
Step 1478 | loss:1.4666993618011475 lr:0.00014464584978583057 tokens_per_second_per_gpu:234.55736062936924 mfu:3.870546453269549 
Step 1479 | loss:1.2065571546554565 lr:0.000144577837124539 tokens_per_second_per_gpu:327.6672909408093 mfu:5.40699924061386 
Step 1480 | loss:1.1936731338500977 lr:0.00014450979871914393 tokens_per_second_per_gpu:321.94211025971003 mfu:5.31252521634919 
Step 1481 | loss:1.2081429958343506 lr:0.00014444173460893814 tokens_per_second_per_gpu:230.4088940395397 mfu:3.802090564259338 
Step 1482 | loss:1.4381940364837646 lr:0.00014437364483322926 tokens_per_second_per_gpu:225.96584856912136 mfu:3.7287736841533397 
Step 1483 | loss:1.3293383121490479 lr:0.00014430552943133976 tokens_per_second_per_gpu:245.85257837528798 mfu:4.056934400627355 
Step 1484 | loss:1.297939419746399 lr:0.0001442373884426069 tokens_per_second_per_gpu:427.5842809874633 mfu:7.055778670979014 
Step 1485 | loss:1.1819924116134644 lr:0.00014416922190638274 tokens_per_second_per_gpu:301.930914338972 mfu:4.982310623258324 
Step 1486 | loss:1.4510457515716553 lr:0.000144101029862034 tokens_per_second_per_gpu:286.65360442981387 mfu:4.730212213190404 
Step 1487 | loss:1.2352252006530762 lr:0.00014403281234894228 tokens_per_second_per_gpu:194.40667602805698 mfu:3.2080002451140373 
Step 1488 | loss:1.4631348848342896 lr:0.00014396456940650378 tokens_per_second_per_gpu:233.08268581542805 mfu:3.8462121183524496 
Step 1489 | loss:1.4179612398147583 lr:0.0001438963010741294 tokens_per_second_per_gpu:265.8897974602619 mfu:4.387578414759479 
Step 1490 | loss:1.2690012454986572 lr:0.00014382800739124474 tokens_per_second_per_gpu:233.5722710459122 mfu:3.8542910052069863 
Step 1491 | loss:1.3487863540649414 lr:0.00014375968839729 tokens_per_second_per_gpu:288.56679288256333 mfu:4.761782677491145 
Step 1492 | loss:1.440582275390625 lr:0.00014369134413172002 tokens_per_second_per_gpu:265.36252164989287 mfu:4.378877577095538 
Step 1493 | loss:1.50017249584198 lr:0.00014362297463400421 tokens_per_second_per_gpu:267.8854798228582 mfu:4.420510151668837 
Step 1494 | loss:1.4137200117111206 lr:0.00014355457994362665 tokens_per_second_per_gpu:260.1326823223924 mfu:4.292577424305994 
Step 1495 | loss:1.5254207849502563 lr:0.00014348616010008582 tokens_per_second_per_gpu:224.861724008093 mfu:3.7105539813386885 
Step 1496 | loss:1.4433305263519287 lr:0.0001434177151428948 tokens_per_second_per_gpu:238.69482555020605 mfu:3.9388207983248575 
Step 1497 | loss:1.1894117593765259 lr:0.00014334924511158123 tokens_per_second_per_gpu:266.66916086121984 mfu:4.400439073829363 
Step 1498 | loss:1.3376036882400513 lr:0.0001432807500456871 tokens_per_second_per_gpu:345.2009969925841 mfu:5.696331553994566 
Step 1499 | loss:1.2620583772659302 lr:0.00014321222998476895 tokens_per_second_per_gpu:189.20135317122313 mfu:3.122104650673594 
Step 1500 | loss:1.3360600471496582 lr:0.00014314368496839777 tokens_per_second_per_gpu:213.13519053880637 mfu:3.517048680942624 
Step 1501 | loss:1.4347126483917236 lr:0.0001430751150361589 tokens_per_second_per_gpu:213.9107795041611 mfu:3.529847056192899 
Step 1502 | loss:1.2314696311950684 lr:0.00014300652022765207 tokens_per_second_per_gpu:301.7075951222686 mfu:4.978625522949218 
Step 1503 | loss:1.3798130750656128 lr:0.0001429379005824914 tokens_per_second_per_gpu:236.62314462150871 mfu:3.904634971670942 
Step 1504 | loss:1.6604101657867432 lr:0.00014286925614030542 tokens_per_second_per_gpu:284.05250949204583 mfu:4.687290265403381 
Step 1505 | loss:1.2002192735671997 lr:0.00014280058694073687 tokens_per_second_per_gpu:265.4377861593527 mfu:4.380119553810168 
Step 1506 | loss:1.4782030582427979 lr:0.00014273189302344282 tokens_per_second_per_gpu:215.62489965252936 mfu:3.5581325964246897 
Step 1507 | loss:1.3463082313537598 lr:0.00014266317442809468 tokens_per_second_per_gpu:234.99758176379646 mfu:3.877810758878802 
Step 1508 | loss:1.5354152917861938 lr:0.000142594431194378 tokens_per_second_per_gpu:273.9276196812035 mfu:4.520214475319675 
Step 1509 | loss:1.3798097372055054 lr:0.00014252566336199265 tokens_per_second_per_gpu:237.87981950451433 mfu:3.9253719824314617 
Step 1510 | loss:1.3284759521484375 lr:0.00014245687097065268 tokens_per_second_per_gpu:211.46490578936684 mfu:3.4894864902036655 
Step 1511 | loss:1.2626501321792603 lr:0.0001423880540600863 tokens_per_second_per_gpu:293.5237685402958 mfu:4.843580172566546 
Step 1512 | loss:1.3594744205474854 lr:0.00014231921267003587 tokens_per_second_per_gpu:302.76000616802554 mfu:4.995991875595779 
Step 1513 | loss:1.4196285009384155 lr:0.00014225034684025797 tokens_per_second_per_gpu:177.16353220154235 mfu:2.923462642022607 
Step 1514 | loss:1.4378201961517334 lr:0.0001421814566105232 tokens_per_second_per_gpu:238.62764851463655 mfu:3.937712276997422 
Step 1515 | loss:1.260145664215088 lr:0.00014211254202061633 tokens_per_second_per_gpu:236.76798926668513 mfu:3.907025124451304 
Step 1516 | loss:1.2980877161026 lr:0.00014204360311033612 tokens_per_second_per_gpu:206.03435406127454 mfu:3.399874283304401 
Step 1517 | loss:1.3695876598358154 lr:0.0001419746399194954 tokens_per_second_per_gpu:262.2926708136033 mfu:4.328220457512571 
Step 1518 | loss:1.5622949600219727 lr:0.00014190565248792112 tokens_per_second_per_gpu:200.01585387973344 mfu:3.3005600495955942 
Step 1519 | loss:1.1170456409454346 lr:0.00014183664085545402 tokens_per_second_per_gpu:247.37317320271504 mfu:4.08202648428811 
Step 1520 | loss:1.3952867984771729 lr:0.00014176760506194906 tokens_per_second_per_gpu:292.56077371080073 mfu:4.827689320913809 
Step 1521 | loss:1.2597273588180542 lr:0.00014169854514727498 tokens_per_second_per_gpu:313.1259045401513 mfu:5.16704466656993 
Step 1522 | loss:1.3406049013137817 lr:0.00014162946115131448 tokens_per_second_per_gpu:300.51664304119834 mfu:4.9589730364911855 
Step 1523 | loss:1.2878837585449219 lr:0.0001415603531139642 tokens_per_second_per_gpu:184.48529104555524 mfu:3.0442825883647244 
Step 1524 | loss:1.4779654741287231 lr:0.00014149122107513472 tokens_per_second_per_gpu:246.98209767697335 mfu:4.07557315455649 
Step 1525 | loss:1.239243745803833 lr:0.00014142206507475035 tokens_per_second_per_gpu:259.19619980850894 mfu:4.277124065422118 
Step 1526 | loss:1.450533151626587 lr:0.00014135288515274933 tokens_per_second_per_gpu:372.57820520540395 mfu:6.148096341355 
Step 1527 | loss:1.3439942598342896 lr:0.00014128368134908365 tokens_per_second_per_gpu:261.19232630599845 mfu:4.310063131219945 
Step 1528 | loss:1.23048734664917 lr:0.00014121445370371923 tokens_per_second_per_gpu:319.96108269633635 mfu:5.279835305494671 
Step 1529 | loss:1.3889977931976318 lr:0.00014114520225663556 tokens_per_second_per_gpu:191.01935826953252 mfu:3.152104447594937 
Step 1530 | loss:1.291283130645752 lr:0.00014107592704782598 tokens_per_second_per_gpu:197.68638449086984 mfu:3.2621203286809606 
Step 1531 | loss:1.4041105508804321 lr:0.00014100662811729762 tokens_per_second_per_gpu:270.29659765237716 mfu:4.460297193688831 
Step 1532 | loss:1.2575886249542236 lr:0.00014093730550507122 tokens_per_second_per_gpu:263.9462685797627 mfu:4.355507288127348 
Step 1533 | loss:1.3656327724456787 lr:0.00014086795925118115 tokens_per_second_per_gpu:243.08127089955542 mfu:4.011203691975389 
Step 1534 | loss:1.3262466192245483 lr:0.00014079858939567555 tokens_per_second_per_gpu:181.17054179569277 mfu:2.989584279524159 
Step 1535 | loss:1.3889122009277344 lr:0.00014072919597861615 tokens_per_second_per_gpu:216.18892883408205 mfu:3.5674399195559765 
Step 1536 | loss:1.3300678730010986 lr:0.00014065977904007823 tokens_per_second_per_gpu:203.8905455488326 mfu:3.364498243891028 
Step 1537 | loss:1.4348423480987549 lr:0.00014059033862015075 tokens_per_second_per_gpu:282.0816417102877 mfu:4.65476800610579 
Step 1538 | loss:1.447544813156128 lr:0.00014052087475893615 tokens_per_second_per_gpu:187.39384721791276 mfu:3.0922781053113972 
Step 1539 | loss:1.4351246356964111 lr:0.00014045138749655043 tokens_per_second_per_gpu:217.00885613900869 mfu:3.5809699435701763 
Step 1540 | loss:1.235182762145996 lr:0.0001403818768731231 tokens_per_second_per_gpu:281.6296033059087 mfu:4.647308697908784 
Step 1541 | loss:1.20602285861969 lr:0.00014031234292879725 tokens_per_second_per_gpu:266.2557272537614 mfu:4.393616802387029 
Step 1542 | loss:1.3014426231384277 lr:0.00014024278570372927 tokens_per_second_per_gpu:262.36384753070803 mfu:4.329394979553601 
Step 1543 | loss:1.2882509231567383 lr:0.0001401732052380891 tokens_per_second_per_gpu:282.7736505364382 mfu:4.666187184342197 
Step 1544 | loss:1.3234384059906006 lr:0.00014010360157206013 tokens_per_second_per_gpu:220.71149156560531 mfu:3.64206895312464 
Step 1545 | loss:1.4027369022369385 lr:0.0001400339747458391 tokens_per_second_per_gpu:212.588364002528 mfu:3.5080252271278867 
Step 1546 | loss:1.2915408611297607 lr:0.0001399643247996361 tokens_per_second_per_gpu:231.43904771651455 mfu:3.819089637108892 
Step 1547 | loss:1.2966392040252686 lr:0.00013989465177367464 tokens_per_second_per_gpu:328.38567027528836 mfu:5.418853571587356 
Step 1548 | loss:1.3677129745483398 lr:0.00013982495570819144 tokens_per_second_per_gpu:278.18891570109776 mfu:4.590532218288293 
Step 1549 | loss:1.416274070739746 lr:0.00013975523664343673 tokens_per_second_per_gpu:253.34728754722713 mfu:4.180608285454075 
Step 1550 | loss:1.5296614170074463 lr:0.00013968549461967382 tokens_per_second_per_gpu:173.4591161790388 mfu:2.8623342499787006 
Step 1551 | loss:1.4710811376571655 lr:0.00013961572967717935 tokens_per_second_per_gpu:199.73041195752475 mfu:3.295849831947106 
Step 1552 | loss:1.3302687406539917 lr:0.00013954594185624326 tokens_per_second_per_gpu:234.84357341569637 mfu:3.875269391326263 
Step 1553 | loss:1.3416619300842285 lr:0.0001394761311971686 tokens_per_second_per_gpu:232.0919294987024 mfu:3.8298631607351425 
Step 1554 | loss:1.1890419721603394 lr:0.0001394062977402717 tokens_per_second_per_gpu:279.77825681498257 mfu:4.616758718257751 
Step 1555 | loss:1.6049505472183228 lr:0.00013933644152588193 tokens_per_second_per_gpu:251.89425327482863 mfu:4.156631051764113 
Step 1556 | loss:1.4616451263427734 lr:0.000139266562594342 tokens_per_second_per_gpu:292.6800309491215 mfu:4.829657243299917 
Step 1557 | loss:1.246201515197754 lr:0.00013919666098600753 tokens_per_second_per_gpu:301.56951217507486 mfu:4.976346948275272 
Step 1558 | loss:1.2907028198242188 lr:0.00013912673674124735 tokens_per_second_per_gpu:244.9713781298781 mfu:4.042393281664643 
Step 1559 | loss:1.1700327396392822 lr:0.00013905678990044337 tokens_per_second_per_gpu:197.6960374678913 mfu:3.2622796172058384 
Step 1560 | loss:1.4203754663467407 lr:0.0001389868205039905 tokens_per_second_per_gpu:242.45078253002197 mfu:4.000799693073041 
Step 1561 | loss:1.1316934823989868 lr:0.00013891682859229674 tokens_per_second_per_gpu:272.6047164871062 mfu:4.498384598601276 
Step 1562 | loss:1.5814696550369263 lr:0.000138846814205783 tokens_per_second_per_gpu:217.4194822280621 mfu:3.58774588676949 
Step 1563 | loss:1.3851033449172974 lr:0.0001387767773848832 tokens_per_second_per_gpu:223.42339883500685 mfu:3.686819469736071 
Step 1564 | loss:1.5146706104278564 lr:0.00013870671817004432 tokens_per_second_per_gpu:266.22563784687475 mfu:4.39312028227445 
Step 1565 | loss:1.325286626815796 lr:0.00013863663660172612 tokens_per_second_per_gpu:259.9397036023245 mfu:4.289392987464997 
Step 1566 | loss:1.2641124725341797 lr:0.0001385665327204014 tokens_per_second_per_gpu:330.50555218738276 mfu:5.453834786392089 
Step 1567 | loss:1.368986964225769 lr:0.00013849640656655573 tokens_per_second_per_gpu:285.03591517955664 mfu:4.7035179266701475 
Step 1568 | loss:1.439394474029541 lr:0.00013842625818068758 tokens_per_second_per_gpu:207.2137330488934 mfu:3.419335796451293 
Step 1569 | loss:1.2704806327819824 lr:0.00013835608760330833 tokens_per_second_per_gpu:273.91727687278126 mfu:4.5200438035473285 
Step 1570 | loss:1.204740047454834 lr:0.00013828589487494211 tokens_per_second_per_gpu:233.3887602327899 mfu:3.851262802958457 
Step 1571 | loss:1.4968117475509644 lr:0.00013821568003612587 tokens_per_second_per_gpu:217.84721683187396 mfu:3.5948041459913815 
Step 1572 | loss:1.1968586444854736 lr:0.00013814544312740925 tokens_per_second_per_gpu:211.41653191709634 mfu:3.4886882491284545 
Step 1573 | loss:1.3499104976654053 lr:0.00013807518418935475 tokens_per_second_per_gpu:291.9664255370136 mfu:4.817881689169119 
Step 1574 | loss:1.4429566860198975 lr:0.00013800490326253755 tokens_per_second_per_gpu:258.80546292075246 mfu:4.270676323722563 
Step 1575 | loss:1.335371732711792 lr:0.00013793460038754546 tokens_per_second_per_gpu:306.81562191839055 mfu:5.06291558720423 
Step 1576 | loss:1.338255524635315 lr:0.0001378642756049791 tokens_per_second_per_gpu:265.86517715013656 mfu:4.387172142904363 
Step 1577 | loss:1.3870923519134521 lr:0.00013779392895545164 tokens_per_second_per_gpu:278.4628158451871 mfu:4.595051979375348 
Step 1578 | loss:1.2498316764831543 lr:0.00013772356047958887 tokens_per_second_per_gpu:326.24604089354216 mfu:5.383546494066497 
Step 1579 | loss:1.3655500411987305 lr:0.0001376531702180293 tokens_per_second_per_gpu:206.3375331894963 mfu:3.404877191319291 
Step 1580 | loss:1.358737826347351 lr:0.00013758275821142382 tokens_per_second_per_gpu:253.12864004673204 mfu:4.177000275433469 
Step 1581 | loss:1.2158774137496948 lr:0.0001375123245004361 tokens_per_second_per_gpu:238.74508914689244 mfu:3.939650222672749 
Step 1582 | loss:1.2634146213531494 lr:0.00013744186912574224 tokens_per_second_per_gpu:306.6771241719043 mfu:5.060630167723001 
Step 1583 | loss:1.1897112131118774 lr:0.0001373713921280308 tokens_per_second_per_gpu:212.72274005068792 mfu:3.5102426324363964 
Step 1584 | loss:1.5659325122833252 lr:0.0001373008935480029 tokens_per_second_per_gpu:328.3594004599741 mfu:5.418420080435256 
Step 1585 | loss:1.3417304754257202 lr:0.00013723037342637217 tokens_per_second_per_gpu:258.5860817716039 mfu:4.267056207404437 
Step 1586 | loss:1.4866492748260498 lr:0.00013715983180386454 tokens_per_second_per_gpu:231.77813351637806 mfu:3.824685058785254 
Step 1587 | loss:1.420197606086731 lr:0.00013708926872121844 tokens_per_second_per_gpu:182.82323989509572 mfu:3.0168562642949857 
Step 1588 | loss:1.4790992736816406 lr:0.0001370186842191847 tokens_per_second_per_gpu:258.3061002607901 mfu:4.262436094691906 
Step 1589 | loss:1.3687293529510498 lr:0.00013694807833852657 tokens_per_second_per_gpu:227.25623238024934 mfu:3.750066942527822 
Step 1590 | loss:1.5373516082763672 lr:0.00013687745112001947 tokens_per_second_per_gpu:216.0413282904368 mfu:3.5650042903385697 
Step 1591 | loss:1.2927736043930054 lr:0.00013680680260445136 tokens_per_second_per_gpu:202.99908158987714 mfu:3.3497877583394584 
Step 1592 | loss:1.256111979484558 lr:0.00013673613283262233 tokens_per_second_per_gpu:242.12022041109856 mfu:3.995344924851097 
Step 1593 | loss:1.3597298860549927 lr:0.00013666544184534482 tokens_per_second_per_gpu:200.71768704872235 mfu:3.3121413441485683 
Step 1594 | loss:1.6103572845458984 lr:0.00013659472968344355 tokens_per_second_per_gpu:232.87267222684903 mfu:3.8427465807618493 
Step 1595 | loss:1.3971771001815796 lr:0.00013652399638775542 tokens_per_second_per_gpu:198.32883094394535 mfu:3.27272165380542 
Step 1596 | loss:1.21047043800354 lr:0.00013645324199912948 tokens_per_second_per_gpu:283.84829010745204 mfu:4.68392034082456 
Step 1597 | loss:1.4592771530151367 lr:0.00013638246655842712 tokens_per_second_per_gpu:265.75727266074745 mfu:4.385391557816024 
Step 1598 | loss:1.3473831415176392 lr:0.00013631167010652178 tokens_per_second_per_gpu:276.10459240047874 mfu:4.556137773632916 
Step 1599 | loss:1.315722107887268 lr:0.000136240852684299 tokens_per_second_per_gpu:196.76366036210186 mfu:3.2468940036815397 
Step 1600 | loss:1.4809390306472778 lr:0.00013617001433265647 tokens_per_second_per_gpu:379.61288247140186 mfu:6.264179013281156 
Step 1601 | loss:1.4258241653442383 lr:0.0001360991550925041 tokens_per_second_per_gpu:258.4288836107638 mfu:4.264462203181898 
Step 1602 | loss:1.3007819652557373 lr:0.00013602827500476362 tokens_per_second_per_gpu:247.85737396012414 mfu:4.0900165193022815 
Step 1603 | loss:1.305074691772461 lr:0.00013595737411036899 tokens_per_second_per_gpu:297.46634937543985 mfu:4.908638639404891 
Step 1604 | loss:1.444246530532837 lr:0.00013588645245026602 tokens_per_second_per_gpu:245.01866531347758 mfu:4.043173590755242 
Step 1605 | loss:1.4211022853851318 lr:0.00013581551006541274 tokens_per_second_per_gpu:263.1317604332347 mfu:4.3420666883131105 
Step 1606 | loss:1.1934081315994263 lr:0.00013574454699677893 tokens_per_second_per_gpu:257.35031889370214 mfu:4.2466642759327025 
Step 1607 | loss:1.2976067066192627 lr:0.00013567356328534643 tokens_per_second_per_gpu:241.92644503215544 mfu:3.9921473419498965 
Step 1608 | loss:1.5362942218780518 lr:0.00013560255897210896 tokens_per_second_per_gpu:284.6876597603685 mfu:4.697771192592164 
Step 1609 | loss:1.4335525035858154 lr:0.00013553153409807218 tokens_per_second_per_gpu:281.5394281834704 mfu:4.645820673830622 
Step 1610 | loss:1.223623275756836 lr:0.00013546048870425356 tokens_per_second_per_gpu:222.81289973229124 mfu:3.676745323563895 
Step 1611 | loss:1.2186020612716675 lr:0.0001353894228316825 tokens_per_second_per_gpu:291.62787499058754 mfu:4.8122950999731735 
Step 1612 | loss:1.277510166168213 lr:0.00013531833652140012 tokens_per_second_per_gpu:159.91908901860847 mfu:2.63890359761138 
Step 1613 | loss:1.1365457773208618 lr:0.0001352472298144595 tokens_per_second_per_gpu:154.30153807875666 mfu:2.5462056246807365 
Step 1614 | loss:1.2439311742782593 lr:0.00013517610275192533 tokens_per_second_per_gpu:254.3329884943807 mfu:4.1968738219298976 
Step 1615 | loss:1.5983924865722656 lr:0.00013510495537487417 tokens_per_second_per_gpu:281.75623862857935 mfu:4.649398369696129 
Step 1616 | loss:1.4363508224487305 lr:0.0001350337877243942 tokens_per_second_per_gpu:306.0691857663611 mfu:5.050598276875202 
Step 1617 | loss:1.4044032096862793 lr:0.00013496259984158547 tokens_per_second_per_gpu:277.14243798533687 mfu:4.57326377444029 
Step 1618 | loss:1.2714178562164307 lr:0.0001348913917675596 tokens_per_second_per_gpu:192.12975513171185 mfu:3.1704276527380104 
Step 1619 | loss:1.3248891830444336 lr:0.0001348201635434399 tokens_per_second_per_gpu:282.0948580862515 mfu:4.654986096030465 
Step 1620 | loss:1.3346894979476929 lr:0.00013474891521036126 tokens_per_second_per_gpu:228.42851127741343 mfu:3.7694112935875648 
Step 1621 | loss:1.4270182847976685 lr:0.00013467764680947028 tokens_per_second_per_gpu:183.42966337640766 mfu:3.026863156632422 
Step 1622 | loss:1.1316184997558594 lr:0.00013460635838192513 tokens_per_second_per_gpu:242.347185740855 mfu:3.9990901914662516 
Step 1623 | loss:1.2453964948654175 lr:0.00013453504996889548 tokens_per_second_per_gpu:200.15867961919403 mfu:3.302916887419065 
Step 1624 | loss:1.5838642120361328 lr:0.00013446372161156258 tokens_per_second_per_gpu:256.6120006145014 mfu:4.234480922618714 
Step 1625 | loss:1.3462480306625366 lr:0.00013439237335111922 tokens_per_second_per_gpu:209.4538028431588 mfu:3.4563002906543567 
Step 1626 | loss:1.4068108797073364 lr:0.00013432100522876966 tokens_per_second_per_gpu:282.17762461424826 mfu:4.656351867245352 
Step 1627 | loss:1.4252617359161377 lr:0.00013424961728572963 tokens_per_second_per_gpu:196.18342909301083 mfu:3.237319321929365 
Step 1628 | loss:1.267439842224121 lr:0.00013417820956322633 tokens_per_second_per_gpu:291.74038547553414 mfu:4.814151690861206 
Step 1629 | loss:1.3975938558578491 lr:0.00013410678210249834 tokens_per_second_per_gpu:174.10934601371264 mfu:2.8730640125137747 
Step 1630 | loss:1.3242223262786865 lr:0.00013403533494479568 tokens_per_second_per_gpu:227.0897194441301 mfu:3.7473192306138134 
Step 1631 | loss:1.4042012691497803 lr:0.0001339638681313797 tokens_per_second_per_gpu:276.567718370649 mfu:4.563780043210173 
Step 1632 | loss:1.1359927654266357 lr:0.00013389238170352318 tokens_per_second_per_gpu:273.6803750268486 mfu:4.51613456958815 
Step 1633 | loss:1.2882882356643677 lr:0.00013382087570251014 tokens_per_second_per_gpu:258.5514620863065 mfu:4.266484930938068 
Step 1634 | loss:1.252455711364746 lr:0.00013374935016963595 tokens_per_second_per_gpu:279.526192651645 mfu:4.612599283436414 
Step 1635 | loss:1.2869900465011597 lr:0.00013367780514620726 tokens_per_second_per_gpu:187.4883164731213 mfu:3.093836988987907 
Step 1636 | loss:1.2698545455932617 lr:0.00013360624067354198 tokens_per_second_per_gpu:285.13194319877283 mfu:4.705102532278747 
Step 1637 | loss:1.3787610530853271 lr:0.00013353465679296917 tokens_per_second_per_gpu:188.55618512136738 mfu:3.1114584151411355 
Step 1638 | loss:1.2912815809249878 lr:0.00013346305354582924 tokens_per_second_per_gpu:326.16070961707214 mfu:5.382138400674724 
Step 1639 | loss:1.1848454475402832 lr:0.00013339143097347372 tokens_per_second_per_gpu:251.3461770297754 mfu:4.147586975889793 
Step 1640 | loss:1.3960399627685547 lr:0.00013331978911726523 tokens_per_second_per_gpu:196.46524581873183 mfu:3.241969718426344 
Step 1641 | loss:1.2588779926300049 lr:0.0001332481280185776 tokens_per_second_per_gpu:304.54103264072046 mfu:5.025381470015548 
Step 1642 | loss:1.367897868156433 lr:0.0001331764477187958 tokens_per_second_per_gpu:126.39524783667615 mfu:2.085710194349436 
Step 1643 | loss:1.2740955352783203 lr:0.00013310474825931585 tokens_per_second_per_gpu:325.98618161324333 mfu:5.3792584281835465 
Step 1644 | loss:1.2212529182434082 lr:0.0001330330296815448 tokens_per_second_per_gpu:223.63474291157695 mfu:3.690306962363858 
Step 1645 | loss:1.3897837400436401 lr:0.0001329612920269008 tokens_per_second_per_gpu:217.22447275056865 mfu:3.584527939400706 
Step 1646 | loss:1.2423979043960571 lr:0.00013288953533681299 tokens_per_second_per_gpu:212.0017568152569 mfu:3.498345333211693 
Step 1647 | loss:1.508221983909607 lr:0.0001328177596527215 tokens_per_second_per_gpu:217.76440723655315 mfu:3.593437664101384 
Step 1648 | loss:1.4534169435501099 lr:0.00013274596501607744 tokens_per_second_per_gpu:223.94773097482147 mfu:3.6954717324433655 
Step 1649 | loss:1.4599448442459106 lr:0.00013267415146834286 tokens_per_second_per_gpu:238.1634102477806 mfu:3.9300516528650995 
Step 1650 | loss:1.259408712387085 lr:0.00013260231905099073 tokens_per_second_per_gpu:308.6738241100877 mfu:5.093578696147956 
Step 1651 | loss:1.3227224349975586 lr:0.00013253046780550493 tokens_per_second_per_gpu:270.0293816511717 mfu:4.455887730933335 
Step 1652 | loss:1.4776897430419922 lr:0.00013245859777338018 tokens_per_second_per_gpu:256.69575490440525 mfu:4.23586299337899 
Step 1653 | loss:1.460713267326355 lr:0.0001323867089961221 tokens_per_second_per_gpu:225.78168631190627 mfu:3.7257347321052037 
Step 1654 | loss:1.4988995790481567 lr:0.0001323148015152471 tokens_per_second_per_gpu:265.44020386963217 mfu:4.38015944963745 
Step 1655 | loss:1.4983967542648315 lr:0.00013224287537228242 tokens_per_second_per_gpu:153.81934569997088 mfu:2.5382487309107216 
Step 1656 | loss:1.3006829023361206 lr:0.000132170930608766 tokens_per_second_per_gpu:208.39554091543695 mfu:3.4388373897247786 
Step 1657 | loss:1.3489476442337036 lr:0.00013209896726624663 tokens_per_second_per_gpu:321.6546974089021 mfu:5.307782475437825 
Step 1658 | loss:1.34109628200531 lr:0.00013202698538628376 tokens_per_second_per_gpu:188.12216507591597 mfu:3.1042964367531525 
Step 1659 | loss:1.2376775741577148 lr:0.00013195498501044766 tokens_per_second_per_gpu:307.96302423154987 mfu:5.081849437507438 
Step 1660 | loss:1.3477720022201538 lr:0.0001318829661803191 tokens_per_second_per_gpu:296.67965923323436 mfu:4.895657078171572 
Step 1661 | loss:1.4350566864013672 lr:0.00013181092893748962 tokens_per_second_per_gpu:177.57556426655347 mfu:2.930261785923199 
Step 1662 | loss:1.378929853439331 lr:0.00013173887332356142 tokens_per_second_per_gpu:258.53180938552964 mfu:4.266160632049791 
Step 1663 | loss:1.4232195615768433 lr:0.00013166679938014726 tokens_per_second_per_gpu:308.70270608136684 mfu:5.094055291771295 
Step 1664 | loss:1.3035268783569336 lr:0.00013159470714887048 tokens_per_second_per_gpu:184.81342813357733 mfu:3.0496973399582035 
Step 1665 | loss:1.3823310136795044 lr:0.000131522596671365 tokens_per_second_per_gpu:268.71999080447137 mfu:4.434280828109903 
Step 1666 | loss:1.3544224500656128 lr:0.00013145046798927523 tokens_per_second_per_gpu:237.4072755968868 mfu:3.917574302832858 
Step 1667 | loss:1.3412294387817383 lr:0.0001313783211442562 tokens_per_second_per_gpu:258.32749861000025 mfu:4.262789199384161 
Step 1668 | loss:1.4149527549743652 lr:0.00013130615617797337 tokens_per_second_per_gpu:191.9315117237703 mfu:3.167156340691212 
Step 1669 | loss:1.2580397129058838 lr:0.00013123397313210256 tokens_per_second_per_gpu:250.81374151135114 mfu:4.138800995343704 
Step 1670 | loss:1.2758485078811646 lr:0.00013116177204833024 tokens_per_second_per_gpu:240.25023872661842 mfu:3.964487436699274 
Step 1671 | loss:1.4430547952651978 lr:0.00013108955296835313 tokens_per_second_per_gpu:243.01275563025257 mfu:4.010073087794461 
Step 1672 | loss:1.4180147647857666 lr:0.00013101731593387846 tokens_per_second_per_gpu:169.7873583121861 mfu:2.8017447662350308 
Step 1673 | loss:1.086277723312378 lr:0.0001309450609866237 tokens_per_second_per_gpu:225.0678610373486 mfu:3.7139555499159096 
Step 1674 | loss:1.0721125602722168 lr:0.00013087278816831672 tokens_per_second_per_gpu:323.063536364021 mfu:5.3310304204451 
Step 1675 | loss:1.3281488418579102 lr:0.00013080049752069582 tokens_per_second_per_gpu:202.23101921416955 mfu:3.3371135830494225 
Step 1676 | loss:1.3057258129119873 lr:0.00013072818908550944 tokens_per_second_per_gpu:222.38568536059535 mfu:3.6696956489482004 
Step 1677 | loss:1.2587183713912964 lr:0.00013065586290451634 tokens_per_second_per_gpu:291.0321896413072 mfu:4.802465402837533 
Step 1678 | loss:1.383934736251831 lr:0.00013058351901948555 tokens_per_second_per_gpu:260.59132030178694 mfu:4.300145635338541 
Step 1679 | loss:1.4205340147018433 lr:0.00013051115747219637 tokens_per_second_per_gpu:247.2230787486956 mfu:4.079549701828154 
Step 1680 | loss:1.5157628059387207 lr:0.0001304387783044382 tokens_per_second_per_gpu:275.59912311899114 mfu:4.547796776234885 
Step 1681 | loss:1.3051011562347412 lr:0.0001303663815580107 tokens_per_second_per_gpu:222.67920446399745 mfu:3.6745391521390247 
Step 1682 | loss:1.2230186462402344 lr:0.00013029396727472356 tokens_per_second_per_gpu:273.3706547960468 mfu:4.5110237236201565 
Step 1683 | loss:1.446264386177063 lr:0.00013022153549639676 tokens_per_second_per_gpu:238.25003564459473 mfu:3.931481101173617 
Step 1684 | loss:1.271868109703064 lr:0.0001301490862648603 tokens_per_second_per_gpu:283.51273689169136 mfu:4.678383212057162 
Step 1685 | loss:1.3058011531829834 lr:0.00013007661962195427 tokens_per_second_per_gpu:331.1786951387195 mfu:5.464942649542701 
Step 1686 | loss:1.3919472694396973 lr:0.00013000413560952876 tokens_per_second_per_gpu:254.6093343023298 mfu:4.201433940120021 
Step 1687 | loss:1.3576686382293701 lr:0.00012993163426944397 tokens_per_second_per_gpu:221.23386846385839 mfu:3.650688951428587 
Step 1688 | loss:1.2576204538345337 lr:0.0001298591156435701 tokens_per_second_per_gpu:256.46833055487554 mfu:4.232110152252634 
Step 1689 | loss:1.3919916152954102 lr:0.0001297865797737873 tokens_per_second_per_gpu:174.0859893190092 mfu:2.8726785921986675 
Step 1690 | loss:1.2825405597686768 lr:0.00012971402670198566 tokens_per_second_per_gpu:223.50465031348114 mfu:3.6881602403731035 
Step 1691 | loss:1.2299480438232422 lr:0.00012964145647006528 tokens_per_second_per_gpu:313.16935509445017 mfu:5.16776166555211 
Step 1692 | loss:1.1927449703216553 lr:0.00012956886911993608 tokens_per_second_per_gpu:338.7841146788776 mfu:5.59044342064534 
Step 1693 | loss:1.4364995956420898 lr:0.00012949626469351794 tokens_per_second_per_gpu:295.12070012671484 mfu:4.869931926659205 
Step 1694 | loss:1.4769837856292725 lr:0.0001294236432327406 tokens_per_second_per_gpu:249.6828155615491 mfu:4.120139029621667 
Step 1695 | loss:1.1900280714035034 lr:0.0001293510047795435 tokens_per_second_per_gpu:217.46735950816165 mfu:3.588535933332874 
Step 1696 | loss:1.3764495849609375 lr:0.00012927834937587616 tokens_per_second_per_gpu:242.4711409704673 mfu:4.001135637718941 
Step 1697 | loss:1.1555712223052979 lr:0.00012920567706369758 tokens_per_second_per_gpu:254.13636394449077 mfu:4.193629223456586 
Step 1698 | loss:1.4447855949401855 lr:0.0001291329878849768 tokens_per_second_per_gpu:259.51168565645673 mfu:4.282330052676385 
Step 1699 | loss:1.2147715091705322 lr:0.0001290602818816924 tokens_per_second_per_gpu:245.57552286638844 mfu:4.052362571312545 
Step 1700 | loss:1.3191134929656982 lr:0.00012898755909583276 tokens_per_second_per_gpu:235.31939790996802 mfu:3.8831212054997346 
Step 1701 | loss:1.3634748458862305 lr:0.00012891481956939598 tokens_per_second_per_gpu:321.1904735408481 mfu:5.3001220889072185 
Step 1702 | loss:1.3494014739990234 lr:0.00012884206334438976 tokens_per_second_per_gpu:291.4166839774694 mfu:4.808810133120743 
Step 1703 | loss:1.2269766330718994 lr:0.00012876929046283148 tokens_per_second_per_gpu:248.86147697966075 mfu:4.106585717431713 
Step 1704 | loss:1.4164988994598389 lr:0.00012869650096674818 tokens_per_second_per_gpu:314.0245329496416 mfu:5.181873376246007 
Step 1705 | loss:1.3071413040161133 lr:0.0001286236948981764 tokens_per_second_per_gpu:327.3769137065345 mfu:5.402207582951884 
Step 1706 | loss:1.517743468284607 lr:0.00012855087229916233 tokens_per_second_per_gpu:187.17088152629043 mfu:3.0885988386936534 
Step 1707 | loss:1.4623554944992065 lr:0.00012847803321176167 tokens_per_second_per_gpu:289.6690718049248 mfu:4.779971924513759 
Step 1708 | loss:1.2088596820831299 lr:0.00012840517767803963 tokens_per_second_per_gpu:297.6573578072204 mfu:4.911790563549113 
Step 1709 | loss:1.3016091585159302 lr:0.00012833230574007097 tokens_per_second_per_gpu:237.57377664916808 mfu:3.9203218186458075 
Step 1710 | loss:1.3952960968017578 lr:0.0001282594174399399 tokens_per_second_per_gpu:303.2445609813552 mfu:5.003987753060957 
Step 1711 | loss:1.396275520324707 lr:0.00012818651281974004 tokens_per_second_per_gpu:252.7968998560994 mfu:4.171526067270422 
Step 1712 | loss:1.3895516395568848 lr:0.00012811359192157448 tokens_per_second_per_gpu:248.56930659927494 mfu:4.101764470183201 
Step 1713 | loss:1.3827905654907227 lr:0.0001280406547875557 tokens_per_second_per_gpu:245.4893525234257 mfu:4.0509406320716 
Step 1714 | loss:1.5599660873413086 lr:0.00012796770145980554 tokens_per_second_per_gpu:181.3432598876775 mfu:2.992434385769187 
Step 1715 | loss:1.0304523706436157 lr:0.00012789473198045523 tokens_per_second_per_gpu:265.70619682456874 mfu:4.384548730304498 
Step 1716 | loss:1.1939010620117188 lr:0.0001278217463916453 tokens_per_second_per_gpu:313.4857656118051 mfu:5.172982911231372 
Step 1717 | loss:1.5630050897598267 lr:0.00012774874473552554 tokens_per_second_per_gpu:214.0176577211007 mfu:3.5316107062544337 
Step 1718 | loss:1.3089025020599365 lr:0.00012767572705425513 tokens_per_second_per_gpu:152.9999311894424 mfu:2.524727168769276 
Step 1719 | loss:1.2218444347381592 lr:0.00012760269339000236 tokens_per_second_per_gpu:515.879066921019 mfu:8.512774391003871 
Step 1720 | loss:1.2515251636505127 lr:0.00012752964378494495 tokens_per_second_per_gpu:179.70486987187277 mfu:2.965398505728033 
Step 1721 | loss:1.3866934776306152 lr:0.00012745657828126962 tokens_per_second_per_gpu:210.36991916076974 mfu:3.4714175769096123 
Step 1722 | loss:1.533915400505066 lr:0.00012738349692117238 tokens_per_second_per_gpu:213.51540513026623 mfu:3.5233227890520755 
Step 1723 | loss:1.2713581323623657 lr:0.00012731039974685834 tokens_per_second_per_gpu:284.21477637217174 mfu:4.689967911057601 
Step 1724 | loss:1.4547430276870728 lr:0.00012723728680054185 tokens_per_second_per_gpu:296.8879169080186 mfu:4.899093640564411 
Step 1725 | loss:1.53607177734375 lr:0.00012716415812444624 tokens_per_second_per_gpu:203.22591033076844 mfu:3.3535307710345226 
Step 1726 | loss:1.230954647064209 lr:0.000127091013760804 tokens_per_second_per_gpu:207.33606435328213 mfu:3.421354445514597 
Step 1727 | loss:1.4061055183410645 lr:0.00012701785375185664 tokens_per_second_per_gpu:211.4439357996163 mfu:3.4891404540816855 
Step 1728 | loss:1.3572381734848022 lr:0.0001269446781398548 tokens_per_second_per_gpu:254.5786456821185 mfu:4.200927532093447 
Step 1729 | loss:1.1866047382354736 lr:0.00012687148696705799 tokens_per_second_per_gpu:340.03811051456563 mfu:5.611136223127487 
Step 1730 | loss:1.3181666135787964 lr:0.00012679828027573474 tokens_per_second_per_gpu:247.95204238141523 mfu:4.091578689516346 
Step 1731 | loss:1.5477261543273926 lr:0.00012672505810816263 tokens_per_second_per_gpu:302.02945425483614 mfu:4.983936678909829 
Step 1732 | loss:1.138273000717163 lr:0.0001266518205066281 tokens_per_second_per_gpu:202.2223141007912 mfu:3.336969935689044 
Step 1733 | loss:1.383409023284912 lr:0.0001265785675134266 tokens_per_second_per_gpu:243.17363769972584 mfu:4.012727882006519 
Step 1734 | loss:1.307630181312561 lr:0.0001265052991708623 tokens_per_second_per_gpu:254.8932318178349 mfu:4.20611867275336 
Step 1735 | loss:1.4245927333831787 lr:0.00012643201552124837 tokens_per_second_per_gpu:329.6353615035117 mfu:5.439475341623066 
Step 1736 | loss:1.468850016593933 lr:0.00012635871660690676 tokens_per_second_per_gpu:213.33969478692848 mfu:3.5204233061947314 
Step 1737 | loss:1.254989504814148 lr:0.00012628540247016832 tokens_per_second_per_gpu:169.85115442269426 mfu:2.8027974972539904 
Step 1738 | loss:1.4533048868179321 lr:0.00012621207315337252 tokens_per_second_per_gpu:257.00403672522174 mfu:4.240950103435852 
Step 1739 | loss:1.3007774353027344 lr:0.00012613872869886777 tokens_per_second_per_gpu:241.000043232575 mfu:3.976860329894306 
Step 1740 | loss:1.422749400138855 lr:0.00012606536914901116 tokens_per_second_per_gpu:233.03994905649736 mfu:3.845506898058958 
Step 1741 | loss:1.3207225799560547 lr:0.00012599199454616842 tokens_per_second_per_gpu:204.1322132035484 mfu:3.3684861208065953 
Step 1742 | loss:1.2877357006072998 lr:0.00012591860493271417 tokens_per_second_per_gpu:290.2102538984979 mfu:4.78890223660131 
Step 1743 | loss:1.2148387432098389 lr:0.00012584520035103147 tokens_per_second_per_gpu:263.74395248754485 mfu:4.352168770712792 
Step 1744 | loss:1.2990145683288574 lr:0.0001257717808435122 tokens_per_second_per_gpu:294.2575945460369 mfu:4.85568939666515 
Step 1745 | loss:1.4811581373214722 lr:0.00012569834645255668 tokens_per_second_per_gpu:221.79407769652414 mfu:3.6599332397031707 
Step 1746 | loss:1.6815320253372192 lr:0.00012562489722057408 tokens_per_second_per_gpu:226.4545116873308 mfu:3.7368373547793823 
Step 1747 | loss:1.4951303005218506 lr:0.00012555143318998188 tokens_per_second_per_gpu:278.00375772537524 mfu:4.587476835398988 
Step 1748 | loss:1.2867943048477173 lr:0.00012547795440320626 tokens_per_second_per_gpu:250.79932016741074 mfu:4.13856302164938 
Step 1749 | loss:1.1658626794815063 lr:0.00012540446090268193 tokens_per_second_per_gpu:207.45096090351066 mfu:3.423250410040233 
Step 1750 | loss:1.3412959575653076 lr:0.00012533095273085197 tokens_per_second_per_gpu:333.79897866052016 mfu:5.508181237599171 
Step 1751 | loss:1.342594027519226 lr:0.00012525742993016806 tokens_per_second_per_gpu:274.04290311298274 mfu:4.5221168239681955 
Step 1752 | loss:1.3988393545150757 lr:0.00012518389254309026 tokens_per_second_per_gpu:229.16701213682097 mfu:3.78159765974741 
Step 1753 | loss:1.4437021017074585 lr:0.0001251103406120871 tokens_per_second_per_gpu:207.85694997241595 mfu:3.429949835487813 
Step 1754 | loss:1.2499791383743286 lr:0.00012503677417963547 tokens_per_second_per_gpu:276.50797240570466 mfu:4.562794145636582 
Step 1755 | loss:1.4235899448394775 lr:0.00012496319328822062 tokens_per_second_per_gpu:263.75943427168505 mfu:4.352424243252786 
Step 1756 | loss:1.2852637767791748 lr:0.00012488959798033624 tokens_per_second_per_gpu:224.83968605243285 mfu:3.7101903221855976 
Step 1757 | loss:1.4055438041687012 lr:0.00012481598829848425 tokens_per_second_per_gpu:257.4059448809309 mfu:4.247582187726221 
Step 1758 | loss:1.4542824029922485 lr:0.0001247423642851749 tokens_per_second_per_gpu:229.5257744898793 mfu:3.787517773912536 
Step 1759 | loss:1.3195101022720337 lr:0.00012466872598292675 tokens_per_second_per_gpu:303.35559915934914 mfu:5.005820048687317 
Step 1760 | loss:1.3259234428405762 lr:0.00012459507343426653 tokens_per_second_per_gpu:223.2183647717954 mfu:3.683436101744408 
Step 1761 | loss:1.4780421257019043 lr:0.0001245214066817293 tokens_per_second_per_gpu:295.42017414943075 mfu:4.874873694904547 
Step 1762 | loss:1.4621796607971191 lr:0.00012444772576785827 tokens_per_second_per_gpu:212.83708587488783 mfu:3.512129509160775 
Step 1763 | loss:1.3454722166061401 lr:0.00012437403073520484 tokens_per_second_per_gpu:229.67948493226416 mfu:3.7900542255762444 
Step 1764 | loss:1.4518011808395386 lr:0.00012430032162632853 tokens_per_second_per_gpu:327.03638911579014 mfu:5.396588419079047 
Step 1765 | loss:1.2780845165252686 lr:0.00012422659848379704 tokens_per_second_per_gpu:247.5893306382701 mfu:4.0855934045215685 
Step 1766 | loss:1.1618573665618896 lr:0.00012415286135018612 tokens_per_second_per_gpu:266.9232158771795 mfu:4.404631360689682 
Step 1767 | loss:1.269155502319336 lr:0.00012407911026807966 tokens_per_second_per_gpu:259.58723531692215 mfu:4.283576734808106 
Step 1768 | loss:1.3306400775909424 lr:0.00012400534528006957 tokens_per_second_per_gpu:189.83799998263706 mfu:3.1326102730565006 
Step 1769 | loss:1.3727669715881348 lr:0.0001239315664287558 tokens_per_second_per_gpu:320.0312882671932 mfu:5.280993802173482 
Step 1770 | loss:1.4790873527526855 lr:0.0001238577737567463 tokens_per_second_per_gpu:212.9602690294749 mfu:3.5141622150234695 
Step 1771 | loss:1.2241907119750977 lr:0.00012378396730665695 tokens_per_second_per_gpu:161.1716820724683 mfu:2.659573252100151 
Step 1772 | loss:1.3885130882263184 lr:0.00012371014712111173 tokens_per_second_per_gpu:212.62393097329056 mfu:3.5086121352179553 
Step 1773 | loss:1.246289849281311 lr:0.00012363631324274242 tokens_per_second_per_gpu:263.04928536790345 mfu:4.340705726667121 
Step 1774 | loss:1.4081721305847168 lr:0.00012356246571418878 tokens_per_second_per_gpu:161.11211624013401 mfu:2.6585903269834166 
Step 1775 | loss:1.2617064714431763 lr:0.00012348860457809838 tokens_per_second_per_gpu:321.7004088161127 mfu:5.308536781866658 
Step 1776 | loss:1.4543298482894897 lr:0.00012341472987712672 tokens_per_second_per_gpu:253.9651718579337 mfu:4.190804298578196 
Step 1777 | loss:1.1421650648117065 lr:0.0001233408416539371 tokens_per_second_per_gpu:253.526385024784 mfu:4.183563661080264 
Step 1778 | loss:1.3101327419281006 lr:0.00012326693995120064 tokens_per_second_per_gpu:297.0941426791381 mfu:4.902496673514805 
Step 1779 | loss:1.314551830291748 lr:0.00012319302481159626 tokens_per_second_per_gpu:276.12429052261695 mfu:4.556462822041431 
Step 1780 | loss:1.1645737886428833 lr:0.00012311909627781052 tokens_per_second_per_gpu:327.3270197729889 mfu:5.401384258597422 
Step 1781 | loss:1.4562811851501465 lr:0.000123045154392538 tokens_per_second_per_gpu:218.74918647285241 mfu:3.6096879909727475 
Step 1782 | loss:1.2616171836853027 lr:0.00012297119919848064 tokens_per_second_per_gpu:207.20314225749377 mfu:3.419161032589783 
Step 1783 | loss:1.0782865285873413 lr:0.0001228972307383483 tokens_per_second_per_gpu:373.71474855387845 mfu:6.166851002537329 
Step 1784 | loss:1.3389103412628174 lr:0.00012282324905485843 tokens_per_second_per_gpu:155.69625359560712 mfu:2.569220511881806 
Step 1785 | loss:1.2357423305511475 lr:0.00012274925419073615 tokens_per_second_per_gpu:268.8083790383514 mfu:4.435739365860486 
Step 1786 | loss:1.5156089067459106 lr:0.00012267524618871412 tokens_per_second_per_gpu:189.81840139817024 mfu:3.132286867168092 
Step 1787 | loss:1.1841593980789185 lr:0.0001226012250915326 tokens_per_second_per_gpu:182.7218701713745 mfu:3.015183512591243 
Step 1788 | loss:1.3913655281066895 lr:0.0001225271909419395 tokens_per_second_per_gpu:208.98609418605983 mfu:3.448582399904561 
Step 1789 | loss:1.1347209215164185 lr:0.00012245314378269022 tokens_per_second_per_gpu:287.66472282015366 mfu:4.746897175406317 
Step 1790 | loss:1.1833581924438477 lr:0.00012237908365654763 tokens_per_second_per_gpu:268.8768640253064 mfu:4.436869470337487 
Step 1791 | loss:1.405600666999817 lr:0.0001223050106062821 tokens_per_second_per_gpu:222.43865044905536 mfu:3.6705696519414808 
Step 1792 | loss:1.2033718824386597 lr:0.00012223092467467152 tokens_per_second_per_gpu:317.0358757931427 mfu:5.231565026643238 
Step 1793 | loss:1.3142808675765991 lr:0.00012215682590450118 tokens_per_second_per_gpu:336.59038295544843 mfu:5.554243573756032 
Step 1794 | loss:1.315812110900879 lr:0.0001220827143385638 tokens_per_second_per_gpu:260.6462858169467 mfu:4.301052648357374 
Step 1795 | loss:1.37599515914917 lr:0.00012200859001965947 tokens_per_second_per_gpu:217.4471079623075 mfu:3.5882017526072354 
Step 1796 | loss:1.2463382482528687 lr:0.00012193445299059561 tokens_per_second_per_gpu:173.00055990729768 mfu:2.8547673872443586 
Step 1797 | loss:1.1370489597320557 lr:0.00012186030329418708 tokens_per_second_per_gpu:291.607378334445 mfu:4.811956874562026 
Step 1798 | loss:1.6145445108413696 lr:0.00012178614097325601 tokens_per_second_per_gpu:269.06233399881336 mfu:4.439930001655793 
Step 1799 | loss:1.333057165145874 lr:0.00012171196607063175 tokens_per_second_per_gpu:216.39038245146617 mfu:3.570764204848803 
Step 1800 | loss:1.1657769680023193 lr:0.000121637778629151 tokens_per_second_per_gpu:236.39180302149316 mfu:3.9008174900663084 
Step 1801 | loss:1.3935575485229492 lr:0.0001215635786916577 tokens_per_second_per_gpu:418.29257557470856 mfu:6.902451666728693 
Step 1802 | loss:1.2351688146591187 lr:0.000121489366301003 tokens_per_second_per_gpu:289.0610249128572 mfu:4.769938243476426 
Step 1803 | loss:1.394148588180542 lr:0.00012141514150004516 tokens_per_second_per_gpu:300.6611887333574 mfu:4.961358256100668 
Step 1804 | loss:1.428544521331787 lr:0.00012134090433164969 tokens_per_second_per_gpu:152.3810436351325 mfu:2.5145146006286745 
Step 1805 | loss:1.3549349308013916 lr:0.00012126665483868927 tokens_per_second_per_gpu:208.0812486378986 mfu:3.4336510981632946 
Step 1806 | loss:1.173217535018921 lr:0.00012119239306404362 tokens_per_second_per_gpu:240.14386304268643 mfu:3.962732079182237 
Step 1807 | loss:1.1396148204803467 lr:0.00012111811905059962 tokens_per_second_per_gpu:203.62025629269908 mfu:3.3600380678433552 
Step 1808 | loss:1.358829379081726 lr:0.0001210438328412511 tokens_per_second_per_gpu:227.51605773814043 mfu:3.754354448640427 
Step 1809 | loss:1.358951210975647 lr:0.0001209695344788991 tokens_per_second_per_gpu:228.98967025814727 mfu:3.778671254122471 
Step 1810 | loss:1.3145616054534912 lr:0.00012089522400645154 tokens_per_second_per_gpu:234.80843877535818 mfu:3.8746896173333134 
Step 1811 | loss:1.282753586769104 lr:0.00012082090146682348 tokens_per_second_per_gpu:258.96879594136476 mfu:4.2733715622856865 
Step 1812 | loss:1.3423023223876953 lr:0.00012074656690293673 tokens_per_second_per_gpu:252.44319574344374 mfu:4.165689421619769 
Step 1813 | loss:1.2099483013153076 lr:0.00012067222035772026 tokens_per_second_per_gpu:307.7664256662564 mfu:5.078605267818742 
Step 1814 | loss:1.1437127590179443 lr:0.00012059786187410984 tokens_per_second_per_gpu:229.23100324990767 mfu:3.782653608599895 
Step 1815 | loss:1.278672218322754 lr:0.00012052349149504818 tokens_per_second_per_gpu:267.7528137475296 mfu:4.418320963463638 
Step 1816 | loss:1.3639583587646484 lr:0.00012044910926348483 tokens_per_second_per_gpu:341.0759730380912 mfu:5.62826250344815 
Step 1817 | loss:1.5144853591918945 lr:0.00012037471522237622 tokens_per_second_per_gpu:234.88320665347575 mfu:3.875923398889731 
Step 1818 | loss:1.2359366416931152 lr:0.00012030030941468555 tokens_per_second_per_gpu:233.6931383948429 mfu:3.856285496820741 
Step 1819 | loss:1.3448705673217773 lr:0.00012022589188338288 tokens_per_second_per_gpu:282.304922121272 mfu:4.658452466062625 
Step 1820 | loss:1.4983899593353271 lr:0.00012015146267144499 tokens_per_second_per_gpu:233.65800617045403 mfu:3.85570576269456 
Step 1821 | loss:1.338073968887329 lr:0.00012007702182185543 tokens_per_second_per_gpu:250.41592556904052 mfu:4.13223643868075 
Step 1822 | loss:1.311609148979187 lr:0.00012000256937760445 tokens_per_second_per_gpu:226.01147883089348 mfu:3.729526651561354 
Step 1823 | loss:1.4402103424072266 lr:0.00011992810538168902 tokens_per_second_per_gpu:321.0572474593441 mfu:5.2979236597644945 
Step 1824 | loss:1.3002854585647583 lr:0.00011985362987711275 tokens_per_second_per_gpu:289.3281901992174 mfu:4.774346869361299 
Step 1825 | loss:1.3211756944656372 lr:0.00011977914290688594 tokens_per_second_per_gpu:188.8434298183336 mfu:3.1161983812631955 
Step 1826 | loss:1.5034663677215576 lr:0.00011970464451402547 tokens_per_second_per_gpu:207.5285101297905 mfu:3.4245300879916125 
Step 1827 | loss:1.2250727415084839 lr:0.00011963013474155487 tokens_per_second_per_gpu:257.62732647369194 mfu:4.251235314348984 
Step 1828 | loss:1.4020007848739624 lr:0.00011955561363250416 tokens_per_second_per_gpu:350.4833724798788 mfu:5.783498631814363 
Step 1829 | loss:1.2297756671905518 lr:0.00011948108122990997 tokens_per_second_per_gpu:262.503374851239 mfu:4.331697388542883 
Step 1830 | loss:1.4381532669067383 lr:0.00011940653757681546 tokens_per_second_per_gpu:206.56880739860932 mfu:3.4086935608734725 
Step 1831 | loss:1.120428442955017 lr:0.00011933198271627024 tokens_per_second_per_gpu:212.16147317354546 mfu:3.5009808914497467 
Step 1832 | loss:1.2141568660736084 lr:0.00011925741669133042 tokens_per_second_per_gpu:257.2926537023646 mfu:4.245712714228522 
Step 1833 | loss:1.3000390529632568 lr:0.00011918283954505854 tokens_per_second_per_gpu:212.2141687677276 mfu:3.501850447385307 
Step 1834 | loss:1.593186616897583 lr:0.00011910825132052357 tokens_per_second_per_gpu:203.59977944792368 mfu:3.3597001693493285 
Step 1835 | loss:1.4533295631408691 lr:0.0001190336520608009 tokens_per_second_per_gpu:232.12496736295333 mfu:3.830408334793876 
Step 1836 | loss:1.2759110927581787 lr:0.00011895904180897231 tokens_per_second_per_gpu:281.89640253232494 mfu:4.6517112832583525 
Step 1837 | loss:1.4018936157226562 lr:0.00011888442060812584 tokens_per_second_per_gpu:316.6619724633514 mfu:5.225395063768885 
Step 1838 | loss:1.2729392051696777 lr:0.00011880978850135593 tokens_per_second_per_gpu:225.9930740909383 mfu:3.7292229458888237 
Step 1839 | loss:1.40853750705719 lr:0.00011873514553176328 tokens_per_second_per_gpu:210.97943563051953 mfu:3.4814755081715827 
Step 1840 | loss:1.1508369445800781 lr:0.00011866049174245491 tokens_per_second_per_gpu:285.091561621976 mfu:4.704436176004831 
Step 1841 | loss:1.1944777965545654 lr:0.00011858582717654401 tokens_per_second_per_gpu:206.44722483539425 mfu:3.4066872671567934 
Step 1842 | loss:1.3080620765686035 lr:0.00011851115187715012 tokens_per_second_per_gpu:314.4244114956265 mfu:5.188471968947372 
Step 1843 | loss:1.1851507425308228 lr:0.00011843646588739883 tokens_per_second_per_gpu:286.5216805483799 mfu:4.728035272291956 
Step 1844 | loss:1.1646836996078491 lr:0.00011836176925042197 tokens_per_second_per_gpu:291.04994130963337 mfu:4.802758331853681 
Step 1845 | loss:1.29593026638031 lr:0.00011828706200935756 tokens_per_second_per_gpu:220.87096612911702 mfu:3.644700521388074 
Step 1846 | loss:1.403935432434082 lr:0.00011821234420734973 tokens_per_second_per_gpu:184.7951975465093 mfu:3.0493965080681793 
Step 1847 | loss:1.402017593383789 lr:0.00011813761588754859 tokens_per_second_per_gpu:258.84489118598134 mfu:4.2713269489330905 
Step 1848 | loss:1.2394251823425293 lr:0.0001180628770931105 tokens_per_second_per_gpu:230.27504035103837 mfu:3.7998817786646524 
Step 1849 | loss:1.1394922733306885 lr:0.00011798812786719776 tokens_per_second_per_gpu:245.8627928872335 mfu:4.057102955316394 
Step 1850 | loss:1.3209450244903564 lr:0.00011791336825297876 tokens_per_second_per_gpu:247.5163958086514 mfu:4.084389871000629 
Step 1851 | loss:1.3119614124298096 lr:0.0001178385982936278 tokens_per_second_per_gpu:235.2907589724468 mfu:3.882648620296053 
Step 1852 | loss:1.373766303062439 lr:0.00011776381803232523 tokens_per_second_per_gpu:270.5754914577108 mfu:4.464899357637882 
Step 1853 | loss:1.381651520729065 lr:0.0001176890275122573 tokens_per_second_per_gpu:233.3583851009759 mfu:3.850761567958221 
Step 1854 | loss:1.3447272777557373 lr:0.00011761422677661625 tokens_per_second_per_gpu:214.57148375583088 mfu:3.5407496622381704 
Step 1855 | loss:1.2882275581359863 lr:0.0001175394158686002 tokens_per_second_per_gpu:229.0677927781984 mfu:3.7799603922765375 
Step 1856 | loss:1.310623288154602 lr:0.00011746459483141306 tokens_per_second_per_gpu:238.8911819068238 mfu:3.942060971208985 
Step 1857 | loss:1.2822693586349487 lr:0.00011738976370826466 tokens_per_second_per_gpu:277.59394961162553 mfu:4.580714390012756 
Step 1858 | loss:1.4094668626785278 lr:0.00011731492254237071 tokens_per_second_per_gpu:273.0039748070185 mfu:4.504972956646951 
Step 1859 | loss:1.3091816902160645 lr:0.00011724007137695266 tokens_per_second_per_gpu:272.43528607845997 mfu:4.495588744037163 
Step 1860 | loss:1.3176074028015137 lr:0.00011716521025523764 tokens_per_second_per_gpu:320.8371607571006 mfu:5.294291900767486 
Step 1861 | loss:1.3985775709152222 lr:0.0001170903392204587 tokens_per_second_per_gpu:219.79309526139042 mfu:3.626914043688259 
Step 1862 | loss:1.2929790019989014 lr:0.0001170154583158545 tokens_per_second_per_gpu:282.6941937979553 mfu:4.664876029593106 
Step 1863 | loss:1.1530753374099731 lr:0.00011694056758466949 tokens_per_second_per_gpu:312.16303071986744 mfu:5.151155811749744 
Step 1864 | loss:1.4369072914123535 lr:0.00011686566707015371 tokens_per_second_per_gpu:256.54446584354537 mfu:4.233366498123592 
Step 1865 | loss:1.3695919513702393 lr:0.00011679075681556287 tokens_per_second_per_gpu:306.81052402141046 mfu:5.062831464297055 
Step 1866 | loss:1.2350499629974365 lr:0.00011671583686415832 tokens_per_second_per_gpu:303.87494052306795 mfu:5.01438995614187 
Step 1867 | loss:1.259024739265442 lr:0.00011664090725920706 tokens_per_second_per_gpu:260.676392511762 mfu:4.301549453746573 
Step 1868 | loss:1.2992219924926758 lr:0.00011656596804398158 tokens_per_second_per_gpu:270.30334742861714 mfu:4.460408575068703 
Step 1869 | loss:1.2755813598632812 lr:0.00011649101926175992 tokens_per_second_per_gpu:238.32899378305987 mfu:3.932784028278411 
Step 1870 | loss:1.231795310974121 lr:0.0001164160609558257 tokens_per_second_per_gpu:292.3919987375404 mfu:4.824904282011595 
Step 1871 | loss:1.4635884761810303 lr:0.00011634109316946809 tokens_per_second_per_gpu:268.6727815224098 mfu:4.4335018045109225 
Step 1872 | loss:1.2369017601013184 lr:0.00011626611594598156 tokens_per_second_per_gpu:233.84597183914866 mfu:3.8588074767075007 
Step 1873 | loss:1.2161991596221924 lr:0.00011619112932866616 tokens_per_second_per_gpu:331.8688059231459 mfu:5.476330507258432 
Step 1874 | loss:1.3351497650146484 lr:0.00011611613336082738 tokens_per_second_per_gpu:275.39452953824417 mfu:4.544420676861167 
Step 1875 | loss:1.247967004776001 lr:0.00011604112808577603 tokens_per_second_per_gpu:289.7703060165974 mfu:4.78164244006649 
Step 1876 | loss:1.2684228420257568 lr:0.00011596611354682836 tokens_per_second_per_gpu:212.31059607418632 mfu:3.503441641829219 
Step 1877 | loss:1.3464072942733765 lr:0.00011589108978730592 tokens_per_second_per_gpu:272.2824008634225 mfu:4.493065909856079 
Step 1878 | loss:1.3742165565490723 lr:0.00011581605685053561 tokens_per_second_per_gpu:210.10876166565362 mfu:3.4671080885449994 
Step 1879 | loss:1.4037797451019287 lr:0.00011574101477984964 tokens_per_second_per_gpu:200.1821761957259 mfu:3.303304615993071 
Step 1880 | loss:1.1980030536651611 lr:0.00011566596361858548 tokens_per_second_per_gpu:214.90904067202155 mfu:3.546319855052553 
Step 1881 | loss:1.2348860502243042 lr:0.00011559090341008587 tokens_per_second_per_gpu:266.69973917404417 mfu:4.4009436616194515 
Step 1882 | loss:1.4667115211486816 lr:0.00011551583419769873 tokens_per_second_per_gpu:239.78629498336718 mfu:3.9568316726459125 
Step 1883 | loss:1.1538116931915283 lr:0.00011544075602477723 tokens_per_second_per_gpu:386.7379003084016 mfu:6.381752439433653 
Step 1884 | loss:1.4317017793655396 lr:0.00011536566893467967 tokens_per_second_per_gpu:244.51731027576494 mfu:4.03490048451871 
Step 1885 | loss:1.2593406438827515 lr:0.00011529057297076953 tokens_per_second_per_gpu:238.23087464873558 mfu:3.931164916150198 
Step 1886 | loss:1.2474497556686401 lr:0.00011521546817641544 tokens_per_second_per_gpu:303.5374124905533 mfu:5.008820239951242 
Step 1887 | loss:1.249927282333374 lr:0.00011514035459499104 tokens_per_second_per_gpu:213.12571041268825 mfu:3.516892244715577 
Step 1888 | loss:1.2644093036651611 lr:0.00011506523226987515 tokens_per_second_per_gpu:247.85745729747057 mfu:4.090017894492852 
Step 1889 | loss:1.3838486671447754 lr:0.00011499010124445158 tokens_per_second_per_gpu:175.8720476610879 mfu:2.9021512199717465 
Step 1890 | loss:1.3117918968200684 lr:0.00011491496156210914 tokens_per_second_per_gpu:236.06875685846376 mfu:3.8954867463318092 
Step 1891 | loss:1.4076330661773682 lr:0.00011483981326624173 tokens_per_second_per_gpu:222.06962854239237 mfu:3.664480239832729 
Step 1892 | loss:1.1935083866119385 lr:0.00011476465640024814 tokens_per_second_per_gpu:236.04933338986575 mfu:3.895166230116541 
Step 1893 | loss:1.3676297664642334 lr:0.00011468949100753212 tokens_per_second_per_gpu:200.23057552515314 mfu:3.304103277149355 
Step 1894 | loss:1.1608545780181885 lr:0.00011461431713150241 tokens_per_second_per_gpu:237.69104692955543 mfu:3.9222569532611073 
Step 1895 | loss:1.3381491899490356 lr:0.00011453913481557257 tokens_per_second_per_gpu:244.85460831426187 mfu:4.040466405464853 
Step 1896 | loss:1.3856878280639648 lr:0.00011446394410316108 tokens_per_second_per_gpu:276.09035833817603 mfu:4.555902890365073 
Step 1897 | loss:1.2670793533325195 lr:0.00011438874503769124 tokens_per_second_per_gpu:197.391343565816 mfu:3.257251713162043 
Step 1898 | loss:1.2630773782730103 lr:0.00011431353766259121 tokens_per_second_per_gpu:260.4059009166571 mfu:4.297085938803946 
Step 1899 | loss:1.2481690645217896 lr:0.0001142383220212939 tokens_per_second_per_gpu:260.4181477134739 mfu:4.297288029225904 
Step 1900 | loss:1.1986624002456665 lr:0.00011416309815723704 tokens_per_second_per_gpu:193.64496152508178 mfu:3.195430819196284 
Step 1901 | loss:1.4374830722808838 lr:0.0001140878661138631 tokens_per_second_per_gpu:300.762264048853 mfu:4.963026149629377 
Step 1902 | loss:1.3438531160354614 lr:0.00011401262593461923 tokens_per_second_per_gpu:298.0776645606383 mfu:4.918726252155779 
Step 1903 | loss:1.2068809270858765 lr:0.00011393737766295738 tokens_per_second_per_gpu:237.43524032563718 mfu:3.9180357625857773 
Step 1904 | loss:1.3032069206237793 lr:0.00011386212134233405 tokens_per_second_per_gpu:276.7926023853782 mfu:4.567490965021672 
Step 1905 | loss:1.309822678565979 lr:0.00011378685701621045 tokens_per_second_per_gpu:248.0167350041295 mfu:4.092646214324468 
Step 1906 | loss:1.244523286819458 lr:0.00011371158472805239 tokens_per_second_per_gpu:212.7252600417183 mfu:3.5102842160486896 
Step 1907 | loss:1.25601065158844 lr:0.00011363630452133039 tokens_per_second_per_gpu:180.50701473829554 mfu:2.978635092972238 
Step 1908 | loss:1.226244330406189 lr:0.00011356101643951933 tokens_per_second_per_gpu:253.0031853772017 mfu:4.174930086184691 
Step 1909 | loss:1.3507421016693115 lr:0.00011348572052609883 tokens_per_second_per_gpu:307.13932266638665 mfu:5.068257132567442 
Step 1910 | loss:1.3061507940292358 lr:0.00011341041682455291 tokens_per_second_per_gpu:320.7859241013876 mfu:5.293446419493671 
Step 1911 | loss:1.1994777917861938 lr:0.0001133351053783702 tokens_per_second_per_gpu:233.15185112161575 mfu:3.847353449111952 
Step 1912 | loss:1.1308462619781494 lr:0.0001132597862310437 tokens_per_second_per_gpu:301.1335894707539 mfu:4.969153573176824 
Step 1913 | loss:1.3652148246765137 lr:0.0001131844594260709 tokens_per_second_per_gpu:264.83240974395386 mfu:4.370129939622714 
Step 1914 | loss:1.1703875064849854 lr:0.0001131091250069537 tokens_per_second_per_gpu:243.03253076909454 mfu:4.010399407093511 
Step 1915 | loss:1.1967511177062988 lr:0.00011303378301719844 tokens_per_second_per_gpu:251.84473246866867 mfu:4.155813884568288 
Step 1916 | loss:1.3653157949447632 lr:0.0001129584335003158 tokens_per_second_per_gpu:269.34045934141676 mfu:4.444519484823107 
Step 1917 | loss:1.478203296661377 lr:0.00011288307649982077 tokens_per_second_per_gpu:286.4685631469934 mfu:4.7271587559081105 
Step 1918 | loss:1.2245408296585083 lr:0.00011280771205923268 tokens_per_second_per_gpu:313.5539295971118 mfu:5.1741077187021824 
Step 1919 | loss:1.2648828029632568 lr:0.00011273234022207526 tokens_per_second_per_gpu:301.87412611003447 mfu:4.9813735327423325 
Step 1920 | loss:1.4536300897598267 lr:0.0001126569610318764 tokens_per_second_per_gpu:213.40811926434532 mfu:3.5215524121740622 
Step 1921 | loss:1.600292444229126 lr:0.0001125815745321682 tokens_per_second_per_gpu:160.36144605130596 mfu:2.646203148729247 
Step 1922 | loss:1.3675565719604492 lr:0.00011250618076648706 tokens_per_second_per_gpu:172.51799839080766 mfu:2.846804402151402 
Step 1923 | loss:1.1946285963058472 lr:0.00011243077977837362 tokens_per_second_per_gpu:228.51544659774362 mfu:3.7708458560965608 
Step 1924 | loss:1.3973568677902222 lr:0.00011235537161137262 tokens_per_second_per_gpu:214.85500483144315 mfu:3.54542818305156 
Step 1925 | loss:1.2642444372177124 lr:0.00011227995630903291 tokens_per_second_per_gpu:217.27241367945342 mfu:3.5853190362640213 
Step 1926 | loss:1.3846522569656372 lr:0.00011220453391490752 tokens_per_second_per_gpu:296.917129268776 mfu:4.899575688107143 
Step 1927 | loss:1.0062637329101562 lr:0.0001121291044725536 tokens_per_second_per_gpu:259.58479268547717 mfu:4.283536427744406 
Step 1928 | loss:1.1950998306274414 lr:0.0001120536680255323 tokens_per_second_per_gpu:227.14278042982602 mfu:3.7481948160545824 
Step 1929 | loss:1.2311160564422607 lr:0.0001119782246174089 tokens_per_second_per_gpu:287.27336625862756 mfu:4.740439208164895 
Step 1930 | loss:1.206031084060669 lr:0.00011190277429175255 tokens_per_second_per_gpu:235.63647398524537 mfu:3.8883534338778527 
Step 1931 | loss:1.2464931011199951 lr:0.00011182731709213659 tokens_per_second_per_gpu:269.9915688948957 mfu:4.455263764031168 
Step 1932 | loss:1.2589619159698486 lr:0.00011175185306213818 tokens_per_second_per_gpu:228.95362086197946 mfu:3.778076385293348 
Step 1933 | loss:1.2366225719451904 lr:0.00011167638224533854 tokens_per_second_per_gpu:218.97590007361433 mfu:3.6134291036838664 
Step 1934 | loss:1.2139708995819092 lr:0.00011160090468532264 tokens_per_second_per_gpu:215.0429769758552 mfu:3.5485300039235006 
Step 1935 | loss:1.2332737445831299 lr:0.00011152542042567957 tokens_per_second_per_gpu:272.1572809528279 mfu:4.491001244629262 
Step 1936 | loss:1.2023881673812866 lr:0.0001114499295100021 tokens_per_second_per_gpu:240.49096663823292 mfu:3.9684598064513996 
Step 1937 | loss:1.292346715927124 lr:0.00011137443198188696 tokens_per_second_per_gpu:357.49324223595994 mfu:5.899171942809507 
Step 1938 | loss:1.2804312705993652 lr:0.0001112989278849346 tokens_per_second_per_gpu:264.96179519881264 mfu:4.372264992694869 
Step 1939 | loss:1.2338522672653198 lr:0.00011122341726274934 tokens_per_second_per_gpu:281.61054119084764 mfu:4.646994144566081 
Step 1940 | loss:1.3616454601287842 lr:0.00011114790015893927 tokens_per_second_per_gpu:221.12912113512567 mfu:3.648960464202145 
Step 1941 | loss:1.2549313306808472 lr:0.0001110723766171162 tokens_per_second_per_gpu:272.1996169180794 mfu:4.491699851228989 
Step 1942 | loss:1.2305558919906616 lr:0.00011099684668089563 tokens_per_second_per_gpu:297.309390604744 mfu:4.906048585476946 
Step 1943 | loss:1.2816969156265259 lr:0.00011092131039389677 tokens_per_second_per_gpu:288.6792305541092 mfu:4.763638066849416 
Step 1944 | loss:1.2308037281036377 lr:0.00011084576779974257 tokens_per_second_per_gpu:238.2564552660474 mfu:3.931587034506846 
Step 1945 | loss:1.156424641609192 lr:0.00011077021894205948 tokens_per_second_per_gpu:290.61125048622637 mfu:4.795519278659769 
Step 1946 | loss:1.2829350233078003 lr:0.00011069466386447771 tokens_per_second_per_gpu:190.5065369872834 mfu:3.1436421312137983 
Step 1947 | loss:1.2266242504119873 lr:0.00011061910261063098 tokens_per_second_per_gpu:270.1798657408894 mfu:4.45837094296372 
Step 1948 | loss:1.2433216571807861 lr:0.00011054353522415657 tokens_per_second_per_gpu:267.3830452016439 mfu:4.412219230693589 
Step 1949 | loss:1.4316415786743164 lr:0.00011046796174869536 tokens_per_second_per_gpu:212.51217053919672 mfu:3.506767921288206 
Step 1950 | loss:1.4264938831329346 lr:0.00011039238222789175 tokens_per_second_per_gpu:205.61115447480478 mfu:3.3928908586357376 
Step 1951 | loss:1.2766910791397095 lr:0.00011031679670539348 tokens_per_second_per_gpu:344.9635060082106 mfu:5.692412598372009 
Step 1952 | loss:1.2893351316452026 lr:0.000110241205224852 tokens_per_second_per_gpu:270.2931148784683 mfu:4.4602397227223936 
Step 1953 | loss:1.3639435768127441 lr:0.00011016560782992197 tokens_per_second_per_gpu:249.04921941440904 mfu:4.109683747751433 
Step 1954 | loss:1.0085161924362183 lr:0.00011009000456426165 tokens_per_second_per_gpu:232.53435258612802 mfu:3.8371638018545897 
Step 1955 | loss:1.3358453512191772 lr:0.00011001439547153256 tokens_per_second_per_gpu:311.49812408152906 mfu:5.140183860053705 
Step 1956 | loss:1.3581273555755615 lr:0.00010993878059539964 tokens_per_second_per_gpu:322.9722767062665 mfu:5.329524499915894 
Step 1957 | loss:1.1614501476287842 lr:0.00010986315997953118 tokens_per_second_per_gpu:241.4540031017767 mfu:3.984351345128067 
Step 1958 | loss:1.4388325214385986 lr:0.00010978753366759877 tokens_per_second_per_gpu:243.1762335327009 mfu:4.01277071712407 
Step 1959 | loss:1.550004005432129 lr:0.00010971190170327725 tokens_per_second_per_gpu:237.28925241385477 mfu:3.915626744200452 
Step 1960 | loss:1.2720615863800049 lr:0.00010963626413024481 tokens_per_second_per_gpu:264.21532341643257 mfu:4.359947094411889 
Step 1961 | loss:1.2348440885543823 lr:0.00010956062099218282 tokens_per_second_per_gpu:228.45743149644107 mfu:3.7698885203558268 
Step 1962 | loss:1.25778329372406 lr:0.00010948497233277586 tokens_per_second_per_gpu:209.34779736058226 mfu:3.4545510420120933 
Step 1963 | loss:1.1426892280578613 lr:0.00010940931819571172 tokens_per_second_per_gpu:312.0424242017442 mfu:5.149165624233521 
Step 1964 | loss:1.2442681789398193 lr:0.00010933365862468133 tokens_per_second_per_gpu:303.91353557606095 mfu:5.0150268321072 
Step 1965 | loss:1.0583341121673584 lr:0.00010925799366337881 tokens_per_second_per_gpu:218.14017444693843 mfu:3.5996383837867914 
Step 1966 | loss:1.1456209421157837 lr:0.00010918232335550134 tokens_per_second_per_gpu:367.1903502858705 mfu:6.059188695508477 
Step 1967 | loss:1.2689974308013916 lr:0.00010910664774474922 tokens_per_second_per_gpu:232.91291273722098 mfu:3.8434106092292573 
Step 1968 | loss:1.23177170753479 lr:0.00010903096687482577 tokens_per_second_per_gpu:366.13122439458533 mfu:6.041711537890912 
Step 1969 | loss:1.3457880020141602 lr:0.0001089552807894374 tokens_per_second_per_gpu:188.96212207964425 mfu:3.1181569806855878 
Step 1970 | loss:1.0946317911148071 lr:0.00010887958953229349 tokens_per_second_per_gpu:229.252183986198 mfu:3.783003122354254 
Step 1971 | loss:1.438963532447815 lr:0.00010880389314710644 tokens_per_second_per_gpu:241.3797204624721 mfu:3.9831255707361297 
Step 1972 | loss:1.1337933540344238 lr:0.00010872819167759161 tokens_per_second_per_gpu:254.08572303121596 mfu:4.192793572821959 
Step 1973 | loss:1.2419604063034058 lr:0.00010865248516746724 tokens_per_second_per_gpu:179.11465956511654 mfu:2.955659154963816 
Step 1974 | loss:1.2930498123168945 lr:0.00010857677366045456 tokens_per_second_per_gpu:233.4967530758564 mfu:3.8530448460143125 
Step 1975 | loss:1.110629677772522 lr:0.00010850105720027763 tokens_per_second_per_gpu:234.625170081101 mfu:3.871665410407344 
Step 1976 | loss:1.3114140033721924 lr:0.00010842533583066339 tokens_per_second_per_gpu:246.98117492915614 mfu:4.075557927840595 
Step 1977 | loss:1.6774479150772095 lr:0.00010834960959534164 tokens_per_second_per_gpu:241.81671598121144 mfu:3.9903366488733187 
Step 1978 | loss:1.4519424438476562 lr:0.00010827387853804494 tokens_per_second_per_gpu:225.98939769187788 mfu:3.729162279818461 
Step 1979 | loss:1.352117657661438 lr:0.00010819814270250865 tokens_per_second_per_gpu:285.87778105512973 mfu:4.717409969836411 
Step 1980 | loss:1.1730796098709106 lr:0.0001081224021324709 tokens_per_second_per_gpu:257.1608253319152 mfu:4.243537349403841 
Step 1981 | loss:1.392869234085083 lr:0.00010804665687167262 tokens_per_second_per_gpu:273.46074446845824 mfu:4.512510337645368 
Step 1982 | loss:1.303765058517456 lr:0.00010797090696385727 tokens_per_second_per_gpu:197.28688659919953 mfu:3.255528017343793 
Step 1983 | loss:1.2427425384521484 lr:0.0001078951524527712 tokens_per_second_per_gpu:248.3289257355068 mfu:4.0977978272383995 
Step 1984 | loss:1.323710322380066 lr:0.00010781939338216328 tokens_per_second_per_gpu:300.72142998971276 mfu:4.962352326721607 
Step 1985 | loss:1.1925064325332642 lr:0.00010774362979578508 tokens_per_second_per_gpu:271.59531778576576 mfu:4.481728013819946 
Step 1986 | loss:1.3039631843566895 lr:0.00010766786173739071 tokens_per_second_per_gpu:326.24342696283117 mfu:5.383503360309299 
Step 1987 | loss:1.4613512754440308 lr:0.00010759208925073696 tokens_per_second_per_gpu:213.91738905294815 mfu:3.5299561236105523 
Step 1988 | loss:1.1477818489074707 lr:0.00010751631237958309 tokens_per_second_per_gpu:246.42937220534503 mfu:4.066452359506177 
Step 1989 | loss:1.3896597623825073 lr:0.00010744053116769096 tokens_per_second_per_gpu:273.88773920679466 mfu:4.519556387982899 
Step 1990 | loss:1.1085288524627686 lr:0.00010736474565882488 tokens_per_second_per_gpu:260.2861888539181 mfu:4.2951105111362535 
Step 1991 | loss:1.3093986511230469 lr:0.0001072889558967517 tokens_per_second_per_gpu:228.24727871000445 mfu:3.766420685792868 
Step 1992 | loss:1.3634819984436035 lr:0.0001072131619252406 tokens_per_second_per_gpu:278.3969521172629 mfu:4.593965129583757 
Step 1993 | loss:1.3669501543045044 lr:0.00010713736378806338 tokens_per_second_per_gpu:276.08541987594936 mfu:4.555821398369235 
Step 1994 | loss:1.2963935136795044 lr:0.00010706156152899416 tokens_per_second_per_gpu:373.6919875330313 mfu:6.166475411729706 
Step 1995 | loss:1.2198693752288818 lr:0.00010698575519180934 tokens_per_second_per_gpu:304.12341307473486 mfu:5.018490124011294 
Step 1996 | loss:1.2529003620147705 lr:0.0001069099448202878 tokens_per_second_per_gpu:285.12041774501637 mfu:4.704912345093661 
Step 1997 | loss:1.3986574411392212 lr:0.00010683413045821074 tokens_per_second_per_gpu:305.4864107120494 mfu:5.040981618871089 
Step 1998 | loss:1.107487440109253 lr:0.00010675831214936165 tokens_per_second_per_gpu:279.192975171713 mfu:4.6071006977955395 
Step 1999 | loss:1.4139102697372437 lr:0.00010668248993752624 tokens_per_second_per_gpu:194.9246924149386 mfu:3.216548288473667 
Step 2000 | loss:1.338929533958435 lr:0.0001066066638664925 tokens_per_second_per_gpu:258.20343415265546 mfu:4.260741950710897 
Step 2001 | loss:1.1335489749908447 lr:0.00010653083398005075 tokens_per_second_per_gpu:201.55667235236635 mfu:3.325985853579657 
Step 2002 | loss:1.5316658020019531 lr:0.0001064550003219934 tokens_per_second_per_gpu:245.1987295505744 mfu:4.046144919356425 
Step 2003 | loss:1.258751630783081 lr:0.0001063791629361151 tokens_per_second_per_gpu:262.34775346917746 mfu:4.329129403523035 
Step 2004 | loss:1.3250479698181152 lr:0.00010630332186621254 tokens_per_second_per_gpu:203.69326616546797 mfu:3.361242839688251 
Step 2005 | loss:1.1509294509887695 lr:0.0001062274771560847 tokens_per_second_per_gpu:239.69123366402818 mfu:3.955263019027781 
Step 2006 | loss:1.1551401615142822 lr:0.00010615162884953255 tokens_per_second_per_gpu:256.9903610103547 mfu:4.240724433733855 
Step 2007 | loss:1.3020474910736084 lr:0.00010607577699035925 tokens_per_second_per_gpu:236.05493223665766 mfu:3.895258619443121 
Step 2008 | loss:1.3748762607574463 lr:0.00010599992162236978 tokens_per_second_per_gpu:250.12282983252433 mfu:4.127399921675283 
Step 2009 | loss:1.184790015220642 lr:0.00010592406278937144 tokens_per_second_per_gpu:311.3955923044791 mfu:5.1384919327360405 
Step 2010 | loss:1.3981530666351318 lr:0.00010584820053517333 tokens_per_second_per_gpu:287.56190196422176 mfu:4.745200477855741 
Step 2011 | loss:1.4428640604019165 lr:0.00010577233490358662 tokens_per_second_per_gpu:171.93946914148984 mfu:2.837257806265213 
Step 2012 | loss:1.2150719165802002 lr:0.00010569646593842433 tokens_per_second_per_gpu:299.5227588344575 mfu:4.9425724640212385 
Step 2013 | loss:1.2449040412902832 lr:0.00010562059368350152 tokens_per_second_per_gpu:366.545622515894 mfu:6.048549725251006 
Step 2014 | loss:1.2431893348693848 lr:0.00010554471818263511 tokens_per_second_per_gpu:271.02029420306235 mfu:4.472239266663995 
Step 2015 | loss:1.2349693775177002 lr:0.0001054688394796439 tokens_per_second_per_gpu:218.91528670367927 mfu:3.6124288926335995 
Step 2016 | loss:1.2834601402282715 lr:0.00010539295761834849 tokens_per_second_per_gpu:233.88735145324043 mfu:3.8594903020860385 
Step 2017 | loss:1.252864956855774 lr:0.00010531707264257133 tokens_per_second_per_gpu:225.1927941157021 mfu:3.71601713213196 
Step 2018 | loss:1.2555184364318848 lr:0.00010524118459613672 tokens_per_second_per_gpu:256.8257472971437 mfu:4.238008061831823 
Step 2019 | loss:1.35415780544281 lr:0.00010516529352287068 tokens_per_second_per_gpu:269.1895506823562 mfu:4.442029266765028 
Step 2020 | loss:1.2731107473373413 lr:0.00010508939946660097 tokens_per_second_per_gpu:272.1356251041123 mfu:4.490643890810932 
Step 2021 | loss:1.2588435411453247 lr:0.00010501350247115711 tokens_per_second_per_gpu:283.7289761584194 mfu:4.681951482627083 
Step 2022 | loss:1.3016127347946167 lr:0.00010493760258037031 tokens_per_second_per_gpu:203.90108350599368 mfu:3.3646721359087635 
Step 2023 | loss:1.3257781267166138 lr:0.00010486169983807341 tokens_per_second_per_gpu:272.8664994582065 mfu:4.502704408252952 
Step 2024 | loss:1.2492969036102295 lr:0.00010478579428810096 tokens_per_second_per_gpu:267.9056910534672 mfu:4.420843667132773 
Step 2025 | loss:1.3914093971252441 lr:0.00010470988597428911 tokens_per_second_per_gpu:229.6658851448784 mfu:3.7898298087909854 
Step 2026 | loss:1.2863714694976807 lr:0.00010463397494047553 tokens_per_second_per_gpu:215.16717689783647 mfu:3.5505794879654045 
Step 2027 | loss:1.356590986251831 lr:0.0001045580612304996 tokens_per_second_per_gpu:357.1451384184025 mfu:5.893427710384648 
Step 2028 | loss:1.0353349447250366 lr:0.00010448214488820214 tokens_per_second_per_gpu:256.12159228961775 mfu:4.226388453478375 
Step 2029 | loss:1.4679700136184692 lr:0.00010440622595742553 tokens_per_second_per_gpu:286.2279517876066 mfu:4.72318830944166 
Step 2030 | loss:1.3435642719268799 lr:0.00010433030448201364 tokens_per_second_per_gpu:202.8256139525242 mfu:3.3469252834773955 
Step 2031 | loss:1.3095483779907227 lr:0.00010425438050581182 tokens_per_second_per_gpu:190.57166937470348 mfu:3.1447169127957766 
Step 2032 | loss:1.3294941186904907 lr:0.00010417845407266681 tokens_per_second_per_gpu:252.39970238195633 mfu:4.164971716255102 
Step 2033 | loss:1.3166780471801758 lr:0.00010410252522642684 tokens_per_second_per_gpu:235.65928542176195 mfu:3.8887298566192507 
Step 2034 | loss:1.3360551595687866 lr:0.00010402659401094152 tokens_per_second_per_gpu:274.34444463290646 mfu:4.527092709002554 
Step 2035 | loss:1.222608208656311 lr:0.00010395066047006179 tokens_per_second_per_gpu:264.62191640386214 mfu:4.366656485416277 
Step 2036 | loss:1.1610866785049438 lr:0.00010387472464763996 tokens_per_second_per_gpu:219.25509857059726 mfu:3.618036295499786 
Step 2037 | loss:1.2129765748977661 lr:0.00010379878658752966 tokens_per_second_per_gpu:297.0899946169667 mfu:4.902428224299303 
Step 2038 | loss:1.345346450805664 lr:0.0001037228463335858 tokens_per_second_per_gpu:309.7828406819779 mfu:5.111879124441612 
Step 2039 | loss:1.2888721227645874 lr:0.00010364690392966454 tokens_per_second_per_gpu:285.5651542090969 mfu:4.712251160379899 
Step 2040 | loss:1.2718849182128906 lr:0.00010357095941962336 tokens_per_second_per_gpu:246.7118836616543 mfu:4.071114220094528 
Step 2041 | loss:1.2740410566329956 lr:0.00010349501284732082 tokens_per_second_per_gpu:233.51284469687525 mfu:3.8533103817727934 
Step 2042 | loss:1.420990228652954 lr:0.00010341906425661685 tokens_per_second_per_gpu:252.9425861554755 mfu:4.173930108600983 
Step 2043 | loss:1.1914284229278564 lr:0.00010334311369137237 tokens_per_second_per_gpu:291.58557711049394 mfu:4.811597121835383 
Step 2044 | loss:1.0625537633895874 lr:0.00010326716119544955 tokens_per_second_per_gpu:273.3407314737041 mfu:4.510529944150381 
Step 2045 | loss:1.4726663827896118 lr:0.00010319120681271159 tokens_per_second_per_gpu:237.27776845957243 mfu:3.915437241818613 
Step 2046 | loss:1.2356553077697754 lr:0.00010311525058702294 tokens_per_second_per_gpu:252.99629926450763 mfu:4.174816455049887 
Step 2047 | loss:1.3312146663665771 lr:0.00010303929256224891 tokens_per_second_per_gpu:204.77917388416427 mfu:3.379161937421532 
Step 2048 | loss:1.367530345916748 lr:0.00010296333278225599 tokens_per_second_per_gpu:298.67827554590485 mfu:4.928637229635149 
Step 2049 | loss:1.3580414056777954 lr:0.0001028873712909116 tokens_per_second_per_gpu:260.61467463686074 mfu:4.3005310167162385 
Step 2050 | loss:1.369394063949585 lr:0.00010281140813208423 tokens_per_second_per_gpu:289.08714440977275 mfu:4.770369254150644 
Step 2051 | loss:1.3741575479507446 lr:0.00010273544334964332 tokens_per_second_per_gpu:220.8225421137755 mfu:3.6439014528773686 
Step 2052 | loss:1.3631620407104492 lr:0.00010265947698745913 tokens_per_second_per_gpu:203.10788185260478 mfu:3.3515831250245425 
Step 2053 | loss:1.2765190601348877 lr:0.00010258350908940293 tokens_per_second_per_gpu:283.5049189122542 mfu:4.678254203730581 
Step 2054 | loss:1.1256170272827148 lr:0.00010250753969934694 tokens_per_second_per_gpu:350.17724498847116 mfu:5.778447071407403 
Step 2055 | loss:1.4183251857757568 lr:0.00010243156886116414 tokens_per_second_per_gpu:248.3554625960143 mfu:4.098235725034669 
Step 2056 | loss:1.3516576290130615 lr:0.00010235559661872836 tokens_per_second_per_gpu:197.25814565408197 mfu:3.255053748862557 
Step 2057 | loss:1.242513656616211 lr:0.00010227962301591422 tokens_per_second_per_gpu:311.12932746934507 mfu:5.134098165640038 
Step 2058 | loss:1.2903332710266113 lr:0.00010220364809659723 tokens_per_second_per_gpu:306.4004623824343 mfu:5.056064835366279 
Step 2059 | loss:1.3446067571640015 lr:0.00010212767190465357 tokens_per_second_per_gpu:200.84923587102128 mfu:3.3143120960116295 
Step 2060 | loss:1.2083276510238647 lr:0.00010205169448396017 tokens_per_second_per_gpu:254.49629481022188 mfu:4.19956861982445 
Step 2061 | loss:1.4666301012039185 lr:0.00010197571587839465 tokens_per_second_per_gpu:224.89225728732535 mfu:3.7110578260073117 
Step 2062 | loss:1.3664973974227905 lr:0.00010189973613183539 tokens_per_second_per_gpu:261.81609116316037 mfu:4.3203561821354395 
Step 2063 | loss:1.1927193403244019 lr:0.00010182375528816135 tokens_per_second_per_gpu:341.07112540074564 mfu:5.6281825101983785 
Step 2064 | loss:1.3103457689285278 lr:0.00010174777339125219 tokens_per_second_per_gpu:230.41572304724937 mfu:3.8022032530766885 
Step 2065 | loss:1.3392239809036255 lr:0.00010167179048498808 tokens_per_second_per_gpu:262.16075245342626 mfu:4.3260436077231015 
Step 2066 | loss:1.5494831800460815 lr:0.00010159580661324987 tokens_per_second_per_gpu:221.33025299445933 mfu:3.6522794400070167 
Step 2067 | loss:1.0792211294174194 lr:0.00010151982181991892 tokens_per_second_per_gpu:216.57641801683886 mfu:3.573834069276861 
Step 2068 | loss:1.2611854076385498 lr:0.0001014438361488772 tokens_per_second_per_gpu:244.25797327819757 mfu:4.030621037080171 
Step 2069 | loss:1.1598864793777466 lr:0.00010136784964400701 tokens_per_second_per_gpu:228.23995415474698 mfu:3.766299819701531 
Step 2070 | loss:1.3321702480316162 lr:0.0001012918623491913 tokens_per_second_per_gpu:148.6121012343591 mfu:2.4523214270580467 
Step 2071 | loss:1.2615193128585815 lr:0.00010121587430831342 tokens_per_second_per_gpu:249.73847722810433 mfu:4.1210575301773105 
Step 2072 | loss:1.1622540950775146 lr:0.00010113988556525717 tokens_per_second_per_gpu:265.7338147705786 mfu:4.385004467624735 
Step 2073 | loss:1.4402544498443604 lr:0.0001010638961639067 tokens_per_second_per_gpu:273.2076096203789 mfu:4.508333234928133 
Step 2074 | loss:1.2731202840805054 lr:0.00010098790614814658 tokens_per_second_per_gpu:232.42971805929866 mfu:3.8354371760278743 
Step 2075 | loss:1.2686421871185303 lr:0.00010091191556186174 tokens_per_second_per_gpu:299.8116447269299 mfu:4.947339512318118 
Step 2076 | loss:1.3115100860595703 lr:0.00010083592444893744 tokens_per_second_per_gpu:331.2605593770872 mfu:5.466293531632324 
Step 2077 | loss:1.2520720958709717 lr:0.0001007599328532592 tokens_per_second_per_gpu:364.8169573201286 mfu:6.020024170033267 
Step 2078 | loss:1.294667363166809 lr:0.00010068394081871289 tokens_per_second_per_gpu:275.87249900747395 mfu:4.552307886322146 
Step 2079 | loss:1.2419947385787964 lr:0.00010060794838918458 tokens_per_second_per_gpu:218.26145167473922 mfu:3.6016396390135177 
Step 2080 | loss:1.2083710432052612 lr:0.00010053195560856057 tokens_per_second_per_gpu:226.4762457563102 mfu:3.737195999348786 
Step 2081 | loss:1.3234275579452515 lr:0.00010045596252072741 tokens_per_second_per_gpu:282.1929389405667 mfu:4.656604576481408 
Step 2082 | loss:1.3216304779052734 lr:0.00010037996916957178 tokens_per_second_per_gpu:184.71322220089976 mfu:3.0480437925432726 
Step 2083 | loss:1.280066728591919 lr:0.0001003039755989805 tokens_per_second_per_gpu:140.1865281610143 mfu:2.313286898837342 
Step 2084 | loss:1.2281582355499268 lr:0.0001002279818528406 tokens_per_second_per_gpu:226.29021352078996 mfu:3.734126189868262 
Step 2085 | loss:1.5288766622543335 lr:0.00010015198797503908 tokens_per_second_per_gpu:195.15231389844715 mfu:3.2203043826048336 
Step 2086 | loss:1.1748651266098022 lr:0.00010007599400946317 tokens_per_second_per_gpu:234.00812844123737 mfu:3.8614833026095514 
Step 2087 | loss:1.3227496147155762 lr:0.0001 tokens_per_second_per_gpu:242.9142572563229 mfu:4.008447717646864 
Step 2088 | loss:1.4020330905914307 lr:9.992400599053688e-05 tokens_per_second_per_gpu:270.3053020615791 mfu:4.460440829429248 
Step 2089 | loss:1.3038264513015747 lr:9.984801202496094e-05 tokens_per_second_per_gpu:201.9512391435159 mfu:3.3324967944001203 
Step 2090 | loss:1.2559528350830078 lr:9.977201814715943e-05 tokens_per_second_per_gpu:264.86294587334737 mfu:4.370633831323249 
Step 2091 | loss:1.2540154457092285 lr:9.96960244010195e-05 tokens_per_second_per_gpu:222.90987659242447 mfu:3.6783455864634718 
Step 2092 | loss:1.3861836194992065 lr:9.962003083042824e-05 tokens_per_second_per_gpu:311.8777903380399 mfu:5.1464489198182815 
Step 2093 | loss:1.2540504932403564 lr:9.954403747927261e-05 tokens_per_second_per_gpu:267.24384832866434 mfu:4.4099222745819935 
Step 2094 | loss:1.2207010984420776 lr:9.946804439143942e-05 tokens_per_second_per_gpu:256.31874109272735 mfu:4.229641702912095 
Step 2095 | loss:1.2726049423217773 lr:9.939205161081545e-05 tokens_per_second_per_gpu:189.54016130148932 mfu:3.127695490387265 
Step 2096 | loss:1.1827868223190308 lr:9.931605918128716e-05 tokens_per_second_per_gpu:277.8739886589283 mfu:4.585335452163209 
Step 2097 | loss:1.1822733879089355 lr:9.924006714674082e-05 tokens_per_second_per_gpu:267.83539780619566 mfu:4.41968372366229 
Step 2098 | loss:1.1455588340759277 lr:9.91640755510626e-05 tokens_per_second_per_gpu:310.06701007659063 mfu:5.11656834348592 
Step 2099 | loss:1.3209514617919922 lr:9.908808443813827e-05 tokens_per_second_per_gpu:209.96807523673894 mfu:3.464786552537783 
Step 2100 | loss:1.1574862003326416 lr:9.901209385185345e-05 tokens_per_second_per_gpu:198.9138151969531 mfu:3.2823747668845504 
Step 2101 | loss:1.2501639127731323 lr:9.893610383609333e-05 tokens_per_second_per_gpu:206.32088312908735 mfu:3.404602440477579 
Step 2102 | loss:1.3376505374908447 lr:9.886011443474284e-05 tokens_per_second_per_gpu:213.38176288080854 mfu:3.5211174925171154 
Step 2103 | loss:1.395768642425537 lr:9.878412569168659e-05 tokens_per_second_per_gpu:275.8488350057327 mfu:4.5519173949823575 
Step 2104 | loss:1.3583321571350098 lr:9.87081376508087e-05 tokens_per_second_per_gpu:211.79907624709443 mfu:3.4950008014001868 
Step 2105 | loss:1.3949604034423828 lr:9.863215035599302e-05 tokens_per_second_per_gpu:279.2982950756355 mfu:4.608838633367001 
Step 2106 | loss:1.2972477674484253 lr:9.855616385112285e-05 tokens_per_second_per_gpu:284.0428590897552 mfu:4.687131019365404 
Step 2107 | loss:1.1510355472564697 lr:9.848017818008106e-05 tokens_per_second_per_gpu:267.2292364969812 mfu:4.409681157555672 
Step 2108 | loss:1.408177137374878 lr:9.840419338675015e-05 tokens_per_second_per_gpu:218.7285698358781 mfu:3.609347785698843 
Step 2109 | loss:1.2100082635879517 lr:9.832820951501195e-05 tokens_per_second_per_gpu:344.551444262547 mfu:5.685612964696363 
Step 2110 | loss:1.237677812576294 lr:9.825222660874783e-05 tokens_per_second_per_gpu:234.11045667287462 mfu:3.8631718711241794 
Step 2111 | loss:1.463412880897522 lr:9.817624471183866e-05 tokens_per_second_per_gpu:279.7907964358724 mfu:4.616965640713862 
Step 2112 | loss:2.0711958408355713 lr:9.810026386816461e-05 tokens_per_second_per_gpu:205.9728511891299 mfu:3.3988593941403744 
Step 2113 | loss:1.0340664386749268 lr:9.802428412160537e-05 tokens_per_second_per_gpu:235.47622211197358 mfu:3.8857090388434887 
Step 2114 | loss:1.4246459007263184 lr:9.794830551603987e-05 tokens_per_second_per_gpu:210.8145631469855 mfu:3.478754866173088 
Step 2115 | loss:1.3146450519561768 lr:9.787232809534644e-05 tokens_per_second_per_gpu:171.57851722046595 mfu:2.831301560961415 
Step 2116 | loss:1.2891333103179932 lr:9.779635190340279e-05 tokens_per_second_per_gpu:229.52002020355206 mfu:3.7874228196016797 
Step 2117 | loss:1.2097834348678589 lr:9.772037698408579e-05 tokens_per_second_per_gpu:255.80414632892632 mfu:4.221150121438988 
Step 2118 | loss:1.4379504919052124 lr:9.764440338127167e-05 tokens_per_second_per_gpu:275.0866915615354 mfu:4.53934089089438 
Step 2119 | loss:1.3081293106079102 lr:9.75684311388359e-05 tokens_per_second_per_gpu:265.67562218525137 mfu:4.3840442031327544 
Step 2120 | loss:1.3421742916107178 lr:9.749246030065306e-05 tokens_per_second_per_gpu:301.94837577334715 mfu:4.982598762981197 
Step 2121 | loss:1.176666021347046 lr:9.741649091059708e-05 tokens_per_second_per_gpu:268.83295780193976 mfu:4.436144952135746 
Step 2122 | loss:1.2913477420806885 lr:9.734052301254092e-05 tokens_per_second_per_gpu:317.56313041709507 mfu:5.240265514699691 
Step 2123 | loss:1.247291088104248 lr:9.72645566503567e-05 tokens_per_second_per_gpu:258.0971542755465 mfu:4.258988174149401 
Step 2124 | loss:1.0382968187332153 lr:9.718859186791578e-05 tokens_per_second_per_gpu:287.32030979179234 mfu:4.741213846510533 
Step 2125 | loss:1.2657884359359741 lr:9.71126287090884e-05 tokens_per_second_per_gpu:323.3103432565824 mfu:5.335103102453813 
Step 2126 | loss:1.2555005550384521 lr:9.703666721774402e-05 tokens_per_second_per_gpu:217.77942377607386 mfu:3.5936854594109247 
Step 2127 | loss:1.3631346225738525 lr:9.696070743775113e-05 tokens_per_second_per_gpu:186.77983395372246 mfu:3.0821459702311107 
Step 2128 | loss:1.28299081325531 lr:9.688474941297708e-05 tokens_per_second_per_gpu:365.46041003953866 mfu:6.0306421000537815 
Step 2129 | loss:1.1468009948730469 lr:9.680879318728843e-05 tokens_per_second_per_gpu:302.29615784808465 mfu:4.9883376861694275 
Step 2130 | loss:1.1391390562057495 lr:9.673283880455048e-05 tokens_per_second_per_gpu:212.4090393060942 mfu:3.5050661020511753 
Step 2131 | loss:1.2798590660095215 lr:9.665688630862766e-05 tokens_per_second_per_gpu:224.50152715211007 mfu:3.704610195734763 
Step 2132 | loss:1.2564702033996582 lr:9.65809357433832e-05 tokens_per_second_per_gpu:149.25100664671228 mfu:2.4628643197267017 
Step 2133 | loss:1.4581894874572754 lr:9.650498715267919e-05 tokens_per_second_per_gpu:287.00099667183633 mfu:4.735944703557133 
Step 2134 | loss:1.2585710287094116 lr:9.642904058037667e-05 tokens_per_second_per_gpu:291.6958703141214 mfu:4.813417124273057 
Step 2135 | loss:1.3047773838043213 lr:9.635309607033549e-05 tokens_per_second_per_gpu:263.03134885837216 mfu:4.340409747495271 
Step 2136 | loss:1.0881178379058838 lr:9.627715366641423e-05 tokens_per_second_per_gpu:284.07496884870017 mfu:4.687660878301684 
Step 2137 | loss:1.328218698501587 lr:9.620121341247038e-05 tokens_per_second_per_gpu:280.4642149869676 mfu:4.628078051671735 
Step 2138 | loss:1.283375859260559 lr:9.612527535236006e-05 tokens_per_second_per_gpu:179.45410834434975 mfu:2.96126056634141 
Step 2139 | loss:1.4401606321334839 lr:9.604933952993822e-05 tokens_per_second_per_gpu:235.27656666929101 mfu:3.8824144261164464 
Step 2140 | loss:1.4307188987731934 lr:9.597340598905852e-05 tokens_per_second_per_gpu:215.41158729548965 mfu:3.5546126242321168 
Step 2141 | loss:1.3484301567077637 lr:9.589747477357316e-05 tokens_per_second_per_gpu:258.2841368167938 mfu:4.262073665092453 
Step 2142 | loss:1.3328288793563843 lr:9.582154592733321e-05 tokens_per_second_per_gpu:277.4077145662267 mfu:4.577641233866605 
Step 2143 | loss:1.1786413192749023 lr:9.574561949418819e-05 tokens_per_second_per_gpu:204.8789514437255 mfu:3.380808416040831 
Step 2144 | loss:1.3342247009277344 lr:9.566969551798638e-05 tokens_per_second_per_gpu:157.19782367832275 mfu:2.5939986588663904 
Step 2145 | loss:1.141178011894226 lr:9.559377404257451e-05 tokens_per_second_per_gpu:231.10690762758313 mfu:3.813608830027192 
Step 2146 | loss:1.3702282905578613 lr:9.551785511179787e-05 tokens_per_second_per_gpu:232.3712988703162 mfu:3.8344731722374488 
Step 2147 | loss:1.19382905960083 lr:9.544193876950042e-05 tokens_per_second_per_gpu:220.93047452874373 mfu:3.6456824987794327 
Step 2148 | loss:1.1877838373184204 lr:9.53660250595245e-05 tokens_per_second_per_gpu:258.66761125310023 mfu:4.2684015655061645 
Step 2149 | loss:1.3373684883117676 lr:9.529011402571093e-05 tokens_per_second_per_gpu:235.63738237408725 mfu:3.8883684236492275 
Step 2150 | loss:1.268530011177063 lr:9.521420571189905e-05 tokens_per_second_per_gpu:184.04089679167225 mfu:3.036949420057386 
Step 2151 | loss:1.4153666496276855 lr:9.513830016192657e-05 tokens_per_second_per_gpu:281.37159908276146 mfu:4.643051243236921 
Step 2152 | loss:1.3080689907073975 lr:9.506239741962971e-05 tokens_per_second_per_gpu:194.28758848018833 mfu:3.206035122873598 
Step 2153 | loss:1.4416968822479248 lr:9.498649752884293e-05 tokens_per_second_per_gpu:179.00957872881716 mfu:2.9539251643648687 
Step 2154 | loss:1.3016750812530518 lr:9.491060053339903e-05 tokens_per_second_per_gpu:309.99036679986403 mfu:5.115303615054013 
Step 2155 | loss:1.3692741394042969 lr:9.483470647712934e-05 tokens_per_second_per_gpu:318.1461796959203 mfu:5.2498866978174705 
Step 2156 | loss:1.128963589668274 lr:9.475881540386328e-05 tokens_per_second_per_gpu:243.73381768390243 mfu:4.021971687637387 
Step 2157 | loss:1.3033185005187988 lr:9.468292735742868e-05 tokens_per_second_per_gpu:277.20206762381014 mfu:4.574247752453528 
Step 2158 | loss:1.2048053741455078 lr:9.460704238165154e-05 tokens_per_second_per_gpu:225.0629914783605 mfu:3.7138751949263247 
Step 2159 | loss:1.183946132659912 lr:9.45311605203561e-05 tokens_per_second_per_gpu:252.27690447030514 mfu:4.162945367475702 
Step 2160 | loss:1.2693121433258057 lr:9.44552818173649e-05 tokens_per_second_per_gpu:280.34845082780606 mfu:4.626167770304072 
Step 2161 | loss:1.3315201997756958 lr:9.437940631649853e-05 tokens_per_second_per_gpu:260.51140546247774 mfu:4.298826921242246 
Step 2162 | loss:1.1738975048065186 lr:9.43035340615757e-05 tokens_per_second_per_gpu:199.5789170015474 mfu:3.2933499391150374 
Step 2163 | loss:1.190467357635498 lr:9.422766509641343e-05 tokens_per_second_per_gpu:246.2322997800927 mfu:4.063200370421072 
Step 2164 | loss:1.358029842376709 lr:9.415179946482667e-05 tokens_per_second_per_gpu:233.00520822403357 mfu:3.8449336224835706 
Step 2165 | loss:1.4421417713165283 lr:9.407593721062859e-05 tokens_per_second_per_gpu:221.95316834360395 mfu:3.6625584727726035 
Step 2166 | loss:1.2260565757751465 lr:9.400007837763024e-05 tokens_per_second_per_gpu:247.9433008575795 mfu:4.091434441329089 
Step 2167 | loss:1.2340823411941528 lr:9.392422300964079e-05 tokens_per_second_per_gpu:298.40778682277096 mfu:4.924173762084329 
Step 2168 | loss:1.155442476272583 lr:9.384837115046746e-05 tokens_per_second_per_gpu:264.2752816118093 mfu:4.360936494104301 
Step 2169 | loss:1.224194049835205 lr:9.37725228439153e-05 tokens_per_second_per_gpu:365.6554858258007 mfu:6.0338611416161925 
Step 2170 | loss:1.3476372957229614 lr:9.369667813378749e-05 tokens_per_second_per_gpu:237.2627152033235 mfu:3.9151888406282684 
Step 2171 | loss:1.2564599514007568 lr:9.362083706388495e-05 tokens_per_second_per_gpu:232.95406182647687 mfu:3.8440896306040178 
Step 2172 | loss:1.4179530143737793 lr:9.354499967800659e-05 tokens_per_second_per_gpu:273.66152179517104 mfu:4.515823463132968 
Step 2173 | loss:1.1128463745117188 lr:9.346916601994926e-05 tokens_per_second_per_gpu:253.0378653360605 mfu:4.175502357254762 
Step 2174 | loss:1.3328146934509277 lr:9.33933361335075e-05 tokens_per_second_per_gpu:252.5684668997862 mfu:4.167756582627112 
Step 2175 | loss:1.3101365566253662 lr:9.331751006247379e-05 tokens_per_second_per_gpu:229.75905148795417 mfu:3.7913671924731194 
Step 2176 | loss:1.324180006980896 lr:9.324168785063841e-05 tokens_per_second_per_gpu:242.24280343786913 mfu:3.9973677277093183 
Step 2177 | loss:1.2996537685394287 lr:9.316586954178926e-05 tokens_per_second_per_gpu:269.9921354533696 mfu:4.455273113091397 
Step 2178 | loss:1.097211241722107 lr:9.309005517971222e-05 tokens_per_second_per_gpu:358.77039842824786 mfu:5.920246925735079 
Step 2179 | loss:1.3057324886322021 lr:9.30142448081907e-05 tokens_per_second_per_gpu:266.77187490774395 mfu:4.40213400886533 
Step 2180 | loss:1.360308051109314 lr:9.293843847100588e-05 tokens_per_second_per_gpu:195.57474491857306 mfu:3.227275124781981 
Step 2181 | loss:1.1990225315093994 lr:9.286263621193663e-05 tokens_per_second_per_gpu:342.5497299819353 mfu:5.652581692139015 
Step 2182 | loss:1.257178783416748 lr:9.27868380747594e-05 tokens_per_second_per_gpu:253.357621899681 mfu:4.180778817690325 
Step 2183 | loss:1.3835049867630005 lr:9.271104410324833e-05 tokens_per_second_per_gpu:251.79900340977935 mfu:4.155059286860417 
Step 2184 | loss:1.1233469247817993 lr:9.263525434117515e-05 tokens_per_second_per_gpu:260.6049946097113 mfu:4.300371281823885 
Step 2185 | loss:1.2905224561691284 lr:9.255946883230905e-05 tokens_per_second_per_gpu:240.2095988000384 mfu:3.963816817268431 
Step 2186 | loss:1.2381032705307007 lr:9.248368762041693e-05 tokens_per_second_per_gpu:374.20280226392055 mfu:6.174904617019261 
Step 2187 | loss:1.3676493167877197 lr:9.240791074926306e-05 tokens_per_second_per_gpu:245.0805188968574 mfu:4.044194267177975 
Step 2188 | loss:1.2215795516967773 lr:9.23321382626093e-05 tokens_per_second_per_gpu:308.28027376953395 mfu:5.087084528279055 
Step 2189 | loss:1.3718681335449219 lr:9.225637020421497e-05 tokens_per_second_per_gpu:250.23836029635294 mfu:4.129306346721236 
Step 2190 | loss:1.3446667194366455 lr:9.218060661783673e-05 tokens_per_second_per_gpu:197.1844316370502 mfu:3.2538373575866104 
Step 2191 | loss:1.3376591205596924 lr:9.210484754722881e-05 tokens_per_second_per_gpu:233.84830799652104 mfu:3.8588460267901232 
Step 2192 | loss:1.2412713766098022 lr:9.202909303614275e-05 tokens_per_second_per_gpu:316.9974147439962 mfu:5.2309303619413345 
Step 2193 | loss:1.1859557628631592 lr:9.195334312832742e-05 tokens_per_second_per_gpu:235.89483249744606 mfu:3.892616734847761 
Step 2194 | loss:1.3254886865615845 lr:9.187759786752911e-05 tokens_per_second_per_gpu:276.40268948216305 mfu:4.561056820296587 
Step 2195 | loss:1.233102560043335 lr:9.180185729749138e-05 tokens_per_second_per_gpu:221.5110145534549 mfu:3.655262275460061 
Step 2196 | loss:1.3481864929199219 lr:9.17261214619551e-05 tokens_per_second_per_gpu:248.81079959115428 mfu:4.105749464901337 
Step 2197 | loss:1.3391170501708984 lr:9.165039040465841e-05 tokens_per_second_per_gpu:299.6430409001017 mfu:4.944557297587417 
Step 2198 | loss:1.1843641996383667 lr:9.157466416933662e-05 tokens_per_second_per_gpu:308.7709078835811 mfu:5.095180723277511 
Step 2199 | loss:1.2895066738128662 lr:9.149894279972239e-05 tokens_per_second_per_gpu:297.8933642951136 mfu:4.915685022764601 
Step 2200 | loss:1.4427332878112793 lr:9.142322633954544e-05 tokens_per_second_per_gpu:197.75741258747513 mfu:3.2632923982619806 
Step 2201 | loss:1.121802568435669 lr:9.134751483253277e-05 tokens_per_second_per_gpu:189.1271693500936 mfu:3.1208805069289998 
Step 2202 | loss:1.2075860500335693 lr:9.127180832240844e-05 tokens_per_second_per_gpu:290.69468729133933 mfu:4.796896110447249 
Step 2203 | loss:1.3496816158294678 lr:9.119610685289357e-05 tokens_per_second_per_gpu:223.07436308063703 mfu:3.6810598589631867 
Step 2204 | loss:1.4832834005355835 lr:9.112041046770653e-05 tokens_per_second_per_gpu:197.92612558232963 mfu:3.2660764144280154 
Step 2205 | loss:1.4612832069396973 lr:9.104471921056265e-05 tokens_per_second_per_gpu:229.7953154564181 mfu:3.7919656020653103 
Step 2206 | loss:1.069189429283142 lr:9.096903312517425e-05 tokens_per_second_per_gpu:244.6586594508493 mfu:4.037232956826666 
Step 2207 | loss:1.4028794765472412 lr:9.08933522552508e-05 tokens_per_second_per_gpu:234.43699279281245 mfu:3.8685602043553278 
Step 2208 | loss:1.474606990814209 lr:9.081767664449866e-05 tokens_per_second_per_gpu:220.02426495557285 mfu:3.6307286885901298 
Step 2209 | loss:1.1919491291046143 lr:9.074200633662122e-05 tokens_per_second_per_gpu:188.3974722852814 mfu:3.1088394165168647 
Step 2210 | loss:1.2138668298721313 lr:9.066634137531871e-05 tokens_per_second_per_gpu:262.9298407946532 mfu:4.338734712975137 
Step 2211 | loss:1.4286928176879883 lr:9.059068180428832e-05 tokens_per_second_per_gpu:292.4228639411529 mfu:4.825413603927783 
Step 2212 | loss:1.275814414024353 lr:9.051502766722417e-05 tokens_per_second_per_gpu:253.40865649250887 mfu:4.18162096462502 
Step 2213 | loss:1.3153166770935059 lr:9.043937900781719e-05 tokens_per_second_per_gpu:250.6060290958659 mfu:4.135373430542927 
Step 2214 | loss:1.1400972604751587 lr:9.03637358697552e-05 tokens_per_second_per_gpu:268.2657671863232 mfu:4.426785460624963 
Step 2215 | loss:1.2126491069793701 lr:9.028809829672276e-05 tokens_per_second_per_gpu:190.01143980722543 mfu:3.1354722889664473 
Step 2216 | loss:1.2526602745056152 lr:9.021246633240124e-05 tokens_per_second_per_gpu:255.85303045833248 mfu:4.221956782518336 
Step 2217 | loss:1.3110108375549316 lr:9.013684002046884e-05 tokens_per_second_per_gpu:224.76926358777246 mfu:3.7090282464353823 
Step 2218 | loss:1.2916921377182007 lr:9.00612194046004e-05 tokens_per_second_per_gpu:281.62082773325176 mfu:4.647163887865169 
Step 2219 | loss:1.25163996219635 lr:8.998560452846746e-05 tokens_per_second_per_gpu:348.27809841118767 mfu:5.747108319004922 
Step 2220 | loss:1.126542568206787 lr:8.990999543573836e-05 tokens_per_second_per_gpu:232.87731374002973 mfu:3.8428231726553252 
Step 2221 | loss:1.199107050895691 lr:8.983439217007802e-05 tokens_per_second_per_gpu:208.29838313492755 mfu:3.437234141369028 
Step 2222 | loss:1.2291228771209717 lr:8.975879477514804e-05 tokens_per_second_per_gpu:307.8176259016518 mfu:5.0794501481029695 
Step 2223 | loss:1.2793275117874146 lr:8.968320329460653e-05 tokens_per_second_per_gpu:198.13691612692006 mfu:3.2695547729521657 
Step 2224 | loss:1.1536940336227417 lr:8.960761777210827e-05 tokens_per_second_per_gpu:277.8831974143546 mfu:4.5854874103689065 
Step 2225 | loss:1.3215136528015137 lr:8.953203825130465e-05 tokens_per_second_per_gpu:263.82251149392573 mfu:4.353465111542618 
Step 2226 | loss:1.6360883712768555 lr:8.945646477584343e-05 tokens_per_second_per_gpu:177.14330734036324 mfu:2.923128901633925 
Step 2227 | loss:1.3000493049621582 lr:8.938089738936906e-05 tokens_per_second_per_gpu:210.137849158323 mfu:3.4675880755779533 
Step 2228 | loss:1.1365556716918945 lr:8.930533613552232e-05 tokens_per_second_per_gpu:305.72930668738644 mfu:5.044989764909787 
Step 2229 | loss:1.1373870372772217 lr:8.922978105794051e-05 tokens_per_second_per_gpu:291.28989905278473 mfu:4.806717992676932 
Step 2230 | loss:1.2578670978546143 lr:8.915423220025747e-05 tokens_per_second_per_gpu:326.33958850805044 mfu:5.385090169296195 
Step 2231 | loss:1.2658355236053467 lr:8.907868960610324e-05 tokens_per_second_per_gpu:267.4490080133762 mfu:4.413307715515865 
Step 2232 | loss:1.4037964344024658 lr:8.90031533191044e-05 tokens_per_second_per_gpu:279.9780594422643 mfu:4.620055759750305 
Step 2233 | loss:1.22919762134552 lr:8.892762338288383e-05 tokens_per_second_per_gpu:233.7434283201543 mfu:3.8571153556302322 
Step 2234 | loss:1.3063650131225586 lr:8.885209984106072e-05 tokens_per_second_per_gpu:278.86800161881433 mfu:4.601738149252175 
Step 2235 | loss:1.1529844999313354 lr:8.877658273725068e-05 tokens_per_second_per_gpu:249.57723103105488 mfu:4.118396727316901 
Step 2236 | loss:1.0910887718200684 lr:8.870107211506544e-05 tokens_per_second_per_gpu:277.434532954279 mfu:4.578083777287454 
Step 2237 | loss:1.1149059534072876 lr:8.862556801811305e-05 tokens_per_second_per_gpu:242.29749612313265 mfu:3.99827023862775 
Step 2238 | loss:1.236206293106079 lr:8.855007048999792e-05 tokens_per_second_per_gpu:218.46208577897158 mfu:3.6049504011164752 
Step 2239 | loss:1.376728892326355 lr:8.847457957432044e-05 tokens_per_second_per_gpu:223.91613000077655 mfu:3.694950269217137 
Step 2240 | loss:1.2922298908233643 lr:8.839909531467737e-05 tokens_per_second_per_gpu:206.1136303877512 mfu:3.4011824609861803 
Step 2241 | loss:1.3863532543182373 lr:8.832361775466151e-05 tokens_per_second_per_gpu:194.96355343588468 mfu:3.217189553307095 
Step 2242 | loss:1.4370479583740234 lr:8.824814693786182e-05 tokens_per_second_per_gpu:252.94418972777177 mfu:4.173956569936697 
Step 2243 | loss:1.2629743814468384 lr:8.817268290786343e-05 tokens_per_second_per_gpu:204.8312007681045 mfu:3.3800204586402613 
Step 2244 | loss:1.1880182027816772 lr:8.809722570824748e-05 tokens_per_second_per_gpu:290.0640328536754 mfu:4.786489371172945 
Step 2245 | loss:1.293419361114502 lr:8.802177538259113e-05 tokens_per_second_per_gpu:186.13836471703493 mfu:3.07156077063524 
Step 2246 | loss:1.1450891494750977 lr:8.79463319744677e-05 tokens_per_second_per_gpu:339.0495275789175 mfu:5.594823129541045 
Step 2247 | loss:1.3833626508712769 lr:8.78708955274464e-05 tokens_per_second_per_gpu:332.5256118620261 mfu:5.4871687853256725 
Step 2248 | loss:0.9809339046478271 lr:8.779546608509249e-05 tokens_per_second_per_gpu:278.76602093236346 mfu:4.6000553157517245 
Step 2249 | loss:1.2977161407470703 lr:8.772004369096712e-05 tokens_per_second_per_gpu:227.48666178947914 mfu:3.7538693716233333 
Step 2250 | loss:1.096678376197815 lr:8.764462838862739e-05 tokens_per_second_per_gpu:310.53034785232495 mfu:5.124214108171037 
Step 2251 | loss:1.0892444849014282 lr:8.756922022162639e-05 tokens_per_second_per_gpu:394.5999984210424 mfu:6.5114887899940745 
Step 2252 | loss:1.1311213970184326 lr:8.749381923351293e-05 tokens_per_second_per_gpu:298.54379644258165 mfu:4.926418123762668 
Step 2253 | loss:1.1426681280136108 lr:8.741842546783183e-05 tokens_per_second_per_gpu:237.06087545728224 mfu:3.911858183636424 
Step 2254 | loss:1.2940881252288818 lr:8.734303896812366e-05 tokens_per_second_per_gpu:275.061549594147 mfu:4.538926010916014 
Step 2255 | loss:1.4112820625305176 lr:8.726765977792473e-05 tokens_per_second_per_gpu:184.74812380367706 mfu:3.0486197210687322 
Step 2256 | loss:1.180140495300293 lr:8.719228794076733e-05 tokens_per_second_per_gpu:191.1969089427883 mfu:3.1550342986420405 
Step 2257 | loss:1.1449040174484253 lr:8.711692350017928e-05 tokens_per_second_per_gpu:235.54674969644958 mfu:3.8868728492275193 
Step 2258 | loss:1.146066427230835 lr:8.704156649968422e-05 tokens_per_second_per_gpu:251.4671305214286 mfu:4.149582888987011 
Step 2259 | loss:1.2360811233520508 lr:8.696621698280158e-05 tokens_per_second_per_gpu:208.23317758109062 mfu:3.4361581524319944 
Step 2260 | loss:1.389553427696228 lr:8.68908749930463e-05 tokens_per_second_per_gpu:362.1451331693011 mfu:5.975935084689721 
Step 2261 | loss:1.1811671257019043 lr:8.681554057392913e-05 tokens_per_second_per_gpu:262.31723599072717 mfu:4.328625819590894 
Step 2262 | loss:1.187085747718811 lr:8.674021376895634e-05 tokens_per_second_per_gpu:238.05719598170145 mfu:3.928298958983499 
Step 2263 | loss:1.0914725065231323 lr:8.666489462162981e-05 tokens_per_second_per_gpu:204.6787113483137 mfu:3.3775041556713465 
Step 2264 | loss:1.262447476387024 lr:8.658958317544712e-05 tokens_per_second_per_gpu:255.04528395870273 mfu:4.208627759967545 
Step 2265 | loss:1.0859020948410034 lr:8.65142794739012e-05 tokens_per_second_per_gpu:290.2860955235202 mfu:4.790153736583884 
Step 2266 | loss:1.0861773490905762 lr:8.643898356048069e-05 tokens_per_second_per_gpu:221.03239340827034 mfu:3.6473643123734063 
Step 2267 | loss:1.201948642730713 lr:8.636369547866968e-05 tokens_per_second_per_gpu:276.81890990728783 mfu:4.5679250783888605 
Step 2268 | loss:1.1946449279785156 lr:8.628841527194759e-05 tokens_per_second_per_gpu:259.72998624655736 mfu:4.285932338157828 
Step 2269 | loss:1.3336457014083862 lr:8.621314298378957e-05 tokens_per_second_per_gpu:268.13450846398314 mfu:4.424619495844106 
Step 2270 | loss:1.153153419494629 lr:8.6137878657666e-05 tokens_per_second_per_gpu:246.74364782515147 mfu:4.0716383761902275 
Step 2271 | loss:1.1607310771942139 lr:8.606262233704265e-05 tokens_per_second_per_gpu:202.65217098357357 mfu:3.34406321568078 
Step 2272 | loss:1.4831657409667969 lr:8.598737406538079e-05 tokens_per_second_per_gpu:263.5355298511485 mfu:4.348729486207202 
Step 2273 | loss:1.2509615421295166 lr:8.591213388613692e-05 tokens_per_second_per_gpu:259.6865003718745 mfu:4.285214756336607 
Step 2274 | loss:1.113965630531311 lr:8.583690184276297e-05 tokens_per_second_per_gpu:272.5482769002224 mfu:4.49745326119941 
Step 2275 | loss:1.298256516456604 lr:8.576167797870614e-05 tokens_per_second_per_gpu:219.44487808742406 mfu:3.621167940713504 
Step 2276 | loss:1.2088617086410522 lr:8.568646233740883e-05 tokens_per_second_per_gpu:211.92246958120563 mfu:3.497036975538656 
Step 2277 | loss:1.464851975440979 lr:8.561125496230878e-05 tokens_per_second_per_gpu:284.6198957939846 mfu:4.696652986030482 
Step 2278 | loss:1.2338392734527588 lr:8.553605589683893e-05 tokens_per_second_per_gpu:243.1623058976854 mfu:4.01254089036371 
Step 2279 | loss:1.1443250179290771 lr:8.546086518442745e-05 tokens_per_second_per_gpu:297.69076777901955 mfu:4.912341877937644 
Step 2280 | loss:1.2178915739059448 lr:8.538568286849762e-05 tokens_per_second_per_gpu:216.8938453031824 mfu:3.5790720931616424 
Step 2281 | loss:1.2987396717071533 lr:8.531050899246789e-05 tokens_per_second_per_gpu:276.85334566362206 mfu:4.568493319752881 
Step 2282 | loss:1.2365071773529053 lr:8.523534359975189e-05 tokens_per_second_per_gpu:195.7387005132829 mfu:3.229980636746709 
Step 2283 | loss:1.2301301956176758 lr:8.516018673375832e-05 tokens_per_second_per_gpu:221.81502065846553 mfu:3.6602788298259687 
Step 2284 | loss:1.4038718938827515 lr:8.508503843789088e-05 tokens_per_second_per_gpu:237.13737663564618 mfu:3.9131205672333103 
Step 2285 | loss:1.165964961051941 lr:8.500989875554846e-05 tokens_per_second_per_gpu:229.21761629783109 mfu:3.7824327039148278 
Step 2286 | loss:1.352651596069336 lr:8.493476773012486e-05 tokens_per_second_per_gpu:237.11516761571372 mfu:3.912754085264467 
Step 2287 | loss:1.157546043395996 lr:8.485964540500899e-05 tokens_per_second_per_gpu:250.13014394827212 mfu:4.127520615499134 
Step 2288 | loss:1.1606824398040771 lr:8.478453182358461e-05 tokens_per_second_per_gpu:293.3823400288718 mfu:4.841246391090601 
Step 2289 | loss:1.2428443431854248 lr:8.470942702923048e-05 tokens_per_second_per_gpu:231.05076570248798 mfu:3.8126824044890055 
Step 2290 | loss:1.1443662643432617 lr:8.463433106532036e-05 tokens_per_second_per_gpu:254.29293122831265 mfu:4.1962128172669395 
Step 2291 | loss:1.1272765398025513 lr:8.455924397522278e-05 tokens_per_second_per_gpu:251.942732567897 mfu:4.1574310324397965 
Step 2292 | loss:0.9465252161026001 lr:8.448416580230129e-05 tokens_per_second_per_gpu:251.6404045364874 mfu:4.152442168792301 
Step 2293 | loss:1.2040133476257324 lr:8.440909658991417e-05 tokens_per_second_per_gpu:170.6471322787799 mfu:2.8159323196253143 
Step 2294 | loss:1.1219264268875122 lr:8.433403638141452e-05 tokens_per_second_per_gpu:253.73024650179389 mfu:4.186927679649887 
Step 2295 | loss:1.2931158542633057 lr:8.425898522015038e-05 tokens_per_second_per_gpu:228.0828906743971 mfu:3.763708037908049 
Step 2296 | loss:1.0847187042236328 lr:8.418394314946444e-05 tokens_per_second_per_gpu:243.97981836014236 mfu:4.02603106587377 
Step 2297 | loss:1.0897608995437622 lr:8.410891021269412e-05 tokens_per_second_per_gpu:235.67691491376257 mfu:3.889020769543718 
Step 2298 | loss:1.1717419624328613 lr:8.403388645317168e-05 tokens_per_second_per_gpu:257.10482820908004 mfu:4.242613313319016 
Step 2299 | loss:1.1977112293243408 lr:8.395887191422397e-05 tokens_per_second_per_gpu:255.1274025495147 mfu:4.20998283925204 
Step 2300 | loss:1.1687018871307373 lr:8.388386663917265e-05 tokens_per_second_per_gpu:158.75455557052234 mfu:2.619687058019063 
Step 2301 | loss:1.418629765510559 lr:8.380887067133387e-05 tokens_per_second_per_gpu:200.16229407461668 mfu:3.3029765313269737 
Step 2302 | loss:1.2012531757354736 lr:8.373388405401845e-05 tokens_per_second_per_gpu:258.32595879491447 mfu:4.262763790137557 
Step 2303 | loss:1.1175453662872314 lr:8.365890683053195e-05 tokens_per_second_per_gpu:279.6199847915857 mfu:4.614146993700624 
Step 2304 | loss:1.1552716493606567 lr:8.358393904417428e-05 tokens_per_second_per_gpu:169.6615705273347 mfu:2.7996690800863853 
Step 2305 | loss:1.2045800685882568 lr:8.35089807382401e-05 tokens_per_second_per_gpu:301.7448927508987 mfu:4.979240989476563 
Step 2306 | loss:1.289434552192688 lr:8.343403195601845e-05 tokens_per_second_per_gpu:292.0804076553153 mfu:4.819762564203461 
Step 2307 | loss:1.1633820533752441 lr:8.335909274079295e-05 tokens_per_second_per_gpu:260.1679271853711 mfu:4.293159017136986 
Step 2308 | loss:1.1581852436065674 lr:8.328416313584169e-05 tokens_per_second_per_gpu:269.579656676953 mfu:4.448466597786038 
Step 2309 | loss:1.1466588973999023 lr:8.320924318443716e-05 tokens_per_second_per_gpu:275.08500193786193 mfu:4.5393130095825365 
Step 2310 | loss:1.2806270122528076 lr:8.313433292984631e-05 tokens_per_second_per_gpu:312.0673761572389 mfu:5.149577368732108 
Step 2311 | loss:1.27462899684906 lr:8.305943241533054e-05 tokens_per_second_per_gpu:211.07741567441317 mfu:3.483092325100142 
Step 2312 | loss:1.0025469064712524 lr:8.29845416841455e-05 tokens_per_second_per_gpu:258.32448080689255 mfu:4.262739401129765 
Step 2313 | loss:1.4449195861816406 lr:8.290966077954134e-05 tokens_per_second_per_gpu:318.2073407115409 mfu:5.250895945838737 
Step 2314 | loss:1.326608419418335 lr:8.28347897447624e-05 tokens_per_second_per_gpu:222.47371531384198 mfu:3.6711482745337114 
Step 2315 | loss:1.3477764129638672 lr:8.275992862304738e-05 tokens_per_second_per_gpu:208.05612843472355 mfu:3.4332365773269253 
Step 2316 | loss:1.2776432037353516 lr:8.26850774576293e-05 tokens_per_second_per_gpu:350.9326368556241 mfu:5.79091216439955 
Step 2317 | loss:1.440262794494629 lr:8.261023629173533e-05 tokens_per_second_per_gpu:213.14714877368638 mfu:3.5172460096620384 
Step 2318 | loss:1.391322374343872 lr:8.253540516858695e-05 tokens_per_second_per_gpu:219.60310138469967 mfu:3.6237788612169215 
Step 2319 | loss:1.2237917184829712 lr:8.246058413139985e-05 tokens_per_second_per_gpu:199.77527033467533 mfu:3.2965900621070707 
Step 2320 | loss:1.2551274299621582 lr:8.238577322338375e-05 tokens_per_second_per_gpu:248.33839884751853 mfu:4.097954147722225 
Step 2321 | loss:1.2628587484359741 lr:8.231097248774274e-05 tokens_per_second_per_gpu:331.61487329076357 mfu:5.4721402399097565 
Step 2322 | loss:1.2018738985061646 lr:8.223618196767482e-05 tokens_per_second_per_gpu:307.4432647871457 mfu:5.073272631097724 
Step 2323 | loss:1.168289303779602 lr:8.216140170637223e-05 tokens_per_second_per_gpu:187.13629833083414 mfu:3.0880281643641125 
Step 2324 | loss:1.2054972648620605 lr:8.208663174702129e-05 tokens_per_second_per_gpu:262.00487969205466 mfu:4.3234714745695335 
Step 2325 | loss:1.180980920791626 lr:8.201187213280225e-05 tokens_per_second_per_gpu:303.5908804587522 mfu:5.009702541210603 
Step 2326 | loss:1.3394298553466797 lr:8.193712290688951e-05 tokens_per_second_per_gpu:271.99736021528463 mfu:4.488362313828535 
Step 2327 | loss:1.4322675466537476 lr:8.186238411245145e-05 tokens_per_second_per_gpu:224.78049103196057 mfu:3.7092135160179054 
Step 2328 | loss:1.0241878032684326 lr:8.178765579265031e-05 tokens_per_second_per_gpu:280.26914030604496 mfu:4.624859028349074 
Step 2329 | loss:1.3491050004959106 lr:8.171293799064247e-05 tokens_per_second_per_gpu:252.09777205056022 mfu:4.15998941525127 
Step 2330 | loss:1.0569835901260376 lr:8.163823074957803e-05 tokens_per_second_per_gpu:264.08926098352435 mfu:4.35786687616048 
Step 2331 | loss:1.3629472255706787 lr:8.15635341126012e-05 tokens_per_second_per_gpu:289.92457675420104 mfu:4.784188137437372 
Step 2332 | loss:1.2368053197860718 lr:8.148884812284992e-05 tokens_per_second_per_gpu:218.9881416782423 mfu:3.6136311084269614 
Step 2333 | loss:1.1406474113464355 lr:8.141417282345598e-05 tokens_per_second_per_gpu:293.63374089082413 mfu:4.845394880449313 
Step 2334 | loss:1.1936814785003662 lr:8.13395082575451e-05 tokens_per_second_per_gpu:296.58194099704644 mfu:4.894044581460823 
Step 2335 | loss:1.340213418006897 lr:8.126485446823671e-05 tokens_per_second_per_gpu:257.9060564404986 mfu:4.255834774717862 
Step 2336 | loss:1.3249850273132324 lr:8.119021149864409e-05 tokens_per_second_per_gpu:215.06684298657072 mfu:3.548923828712801 
Step 2337 | loss:1.2788279056549072 lr:8.111557939187421e-05 tokens_per_second_per_gpu:254.3105075423842 mfu:4.1965028526762245 
Step 2338 | loss:1.0748367309570312 lr:8.104095819102771e-05 tokens_per_second_per_gpu:335.6827485253047 mfu:5.5392662513005275 
Step 2339 | loss:1.372754693031311 lr:8.096634793919911e-05 tokens_per_second_per_gpu:234.2477363258347 mfu:3.8654371902446067 
Step 2340 | loss:1.2447373867034912 lr:8.089174867947647e-05 tokens_per_second_per_gpu:309.3710494705628 mfu:5.105083954984751 
Step 2341 | loss:1.2962977886199951 lr:8.08171604549415e-05 tokens_per_second_per_gpu:278.9404334756719 mfu:4.602933382972028 
Step 2342 | loss:1.320252776145935 lr:8.074258330866962e-05 tokens_per_second_per_gpu:271.4623753804738 mfu:4.479534265758017 
Step 2343 | loss:1.4347351789474487 lr:8.066801728372977e-05 tokens_per_second_per_gpu:250.8237048770707 mfu:4.138965405745258 
Step 2344 | loss:1.260573148727417 lr:8.059346242318456e-05 tokens_per_second_per_gpu:269.83699916688437 mfu:4.45271313287241 
Step 2345 | loss:1.068256139755249 lr:8.051891877009005e-05 tokens_per_second_per_gpu:241.8969157253479 mfu:3.9916600643243942 
Step 2346 | loss:1.2666218280792236 lr:8.044438636749586e-05 tokens_per_second_per_gpu:287.47318398129505 mfu:4.74373649875384 
Step 2347 | loss:1.23176908493042 lr:8.036986525844515e-05 tokens_per_second_per_gpu:353.121387049614 mfu:5.827029808619749 
Step 2348 | loss:1.2819404602050781 lr:8.029535548597451e-05 tokens_per_second_per_gpu:231.62048316162844 mfu:3.8220835926884513 
Step 2349 | loss:1.2721302509307861 lr:8.022085709311408e-05 tokens_per_second_per_gpu:260.08469544929875 mfu:4.291785569294675 
Step 2350 | loss:1.3036811351776123 lr:8.014637012288727e-05 tokens_per_second_per_gpu:247.81243462479412 mfu:4.089274953211551 
Step 2351 | loss:1.2536978721618652 lr:8.007189461831098e-05 tokens_per_second_per_gpu:223.24292581653668 mfu:3.6838413956322524 
Step 2352 | loss:1.102429986000061 lr:7.999743062239557e-05 tokens_per_second_per_gpu:274.147808632139 mfu:4.523847921572676 
Step 2353 | loss:1.2098537683486938 lr:7.992297817814462e-05 tokens_per_second_per_gpu:253.87210064602846 mfu:4.189268484702328 
Step 2354 | loss:1.1605931520462036 lr:7.984853732855502e-05 tokens_per_second_per_gpu:267.29828643199335 mfu:4.410820584518623 
Step 2355 | loss:1.2803990840911865 lr:7.977410811661713e-05 tokens_per_second_per_gpu:270.5259807042852 mfu:4.464082356327174 
Step 2356 | loss:1.262737512588501 lr:7.969969058531444e-05 tokens_per_second_per_gpu:196.76376759691593 mfu:3.2468957732159858 
Step 2357 | loss:1.4664976596832275 lr:7.96252847776238e-05 tokens_per_second_per_gpu:288.11221247372623 mfu:4.75428142242744 
Step 2358 | loss:1.1829384565353394 lr:7.955089073651518e-05 tokens_per_second_per_gpu:208.8197173572513 mfu:3.445836933964276 
Step 2359 | loss:1.380052924156189 lr:7.947650850495182e-05 tokens_per_second_per_gpu:179.7036649931258 mfu:2.965378623430807 
Step 2360 | loss:1.32435941696167 lr:7.940213812589018e-05 tokens_per_second_per_gpu:299.2028634083233 mfu:4.9372937121469915 
Step 2361 | loss:1.071696400642395 lr:7.932777964227974e-05 tokens_per_second_per_gpu:254.16583341193044 mfu:4.194115513643226 
Step 2362 | loss:1.2976131439208984 lr:7.92534330970633e-05 tokens_per_second_per_gpu:322.1329744873805 mfu:5.315674760910417 
Step 2363 | loss:1.2495142221450806 lr:7.917909853317657e-05 tokens_per_second_per_gpu:291.65688127690515 mfu:4.812773746980147 
Step 2364 | loss:1.1875228881835938 lr:7.910477599354844e-05 tokens_per_second_per_gpu:269.69862711731207 mfu:4.450429787577824 
Step 2365 | loss:1.2192198038101196 lr:7.903046552110092e-05 tokens_per_second_per_gpu:337.98869712241674 mfu:5.577317844053896 
Step 2366 | loss:1.1704655885696411 lr:7.895616715874893e-05 tokens_per_second_per_gpu:255.656175816098 mfu:4.218708387177998 
Step 2367 | loss:1.322129249572754 lr:7.888188094940042e-05 tokens_per_second_per_gpu:211.3565527458185 mfu:3.4876985033023735 
Step 2368 | loss:1.1367621421813965 lr:7.880760693595641e-05 tokens_per_second_per_gpu:115.4655942616132 mfu:1.9053546012999811 
Step 2369 | loss:1.270950436592102 lr:7.873334516131074e-05 tokens_per_second_per_gpu:259.7913030671547 mfu:4.2869441571937 
Step 2370 | loss:1.4398101568222046 lr:7.865909566835034e-05 tokens_per_second_per_gpu:184.34693011559 mfu:3.041999426560247 
Step 2371 | loss:1.4266011714935303 lr:7.858485849995489e-05 tokens_per_second_per_gpu:289.843181548778 mfu:4.782844995091218 
Step 2372 | loss:1.2292834520339966 lr:7.851063369899702e-05 tokens_per_second_per_gpu:233.32516523845692 mfu:3.8502133906564904 
Step 2373 | loss:1.2451372146606445 lr:7.843642130834232e-05 tokens_per_second_per_gpu:216.48327284962565 mfu:3.5722970350280576 
Step 2374 | loss:1.3017055988311768 lr:7.8362221370849e-05 tokens_per_second_per_gpu:192.38944963971196 mfu:3.174712999632162 
Step 2375 | loss:1.1594904661178589 lr:7.828803392936826e-05 tokens_per_second_per_gpu:264.82032051582297 mfu:4.3699304493191935 
Step 2376 | loss:1.3123571872711182 lr:7.821385902674403e-05 tokens_per_second_per_gpu:203.92417155216685 mfu:3.3650531231222485 
Step 2377 | loss:1.3394999504089355 lr:7.813969670581292e-05 tokens_per_second_per_gpu:255.91727114273283 mfu:4.223016849669902 
Step 2378 | loss:1.1647285223007202 lr:7.806554700940441e-05 tokens_per_second_per_gpu:298.366148733053 mfu:4.923486671472266 
Step 2379 | loss:1.1728042364120483 lr:7.799140998034058e-05 tokens_per_second_per_gpu:288.30165031105633 mfu:4.757407429419613 
Step 2380 | loss:1.2000854015350342 lr:7.791728566143622e-05 tokens_per_second_per_gpu:286.5927552118094 mfu:4.729208110295063 
Step 2381 | loss:1.1899573802947998 lr:7.784317409549883e-05 tokens_per_second_per_gpu:240.98207052133174 mfu:3.976563753340189 
Step 2382 | loss:1.2188161611557007 lr:7.776907532532849e-05 tokens_per_second_per_gpu:230.18317976385265 mfu:3.798365941903133 
Step 2383 | loss:1.321541666984558 lr:7.76949893937179e-05 tokens_per_second_per_gpu:315.82824733623426 mfu:5.211637355099644 
Step 2384 | loss:1.1648434400558472 lr:7.762091634345242e-05 tokens_per_second_per_gpu:171.34613695449673 mfu:2.827466939818665 
Step 2385 | loss:1.264206051826477 lr:7.75468562173098e-05 tokens_per_second_per_gpu:213.69195842837038 mfu:3.5262361819209094 
Step 2386 | loss:1.2448413372039795 lr:7.747280905806052e-05 tokens_per_second_per_gpu:277.5156174222923 mfu:4.579421792002669 
Step 2387 | loss:1.2777812480926514 lr:7.739877490846741e-05 tokens_per_second_per_gpu:226.94019474162639 mfu:3.744851849904041 
Step 2388 | loss:1.046465516090393 lr:7.732475381128593e-05 tokens_per_second_per_gpu:242.6216181702737 mfu:4.003618736055509 
Step 2389 | loss:1.2293665409088135 lr:7.72507458092639e-05 tokens_per_second_per_gpu:257.51631152727055 mfu:4.249403402078236 
Step 2390 | loss:1.2440623044967651 lr:7.717675094514157e-05 tokens_per_second_per_gpu:225.90606152022403 mfu:3.7277871086332186 
Step 2391 | loss:1.1689693927764893 lr:7.710276926165171e-05 tokens_per_second_per_gpu:273.8840118913544 mfu:4.519494881716292 
Step 2392 | loss:1.152030110359192 lr:7.70288008015194e-05 tokens_per_second_per_gpu:318.0451120877645 mfu:5.248218931471369 
Step 2393 | loss:1.0595577955245972 lr:7.695484560746203e-05 tokens_per_second_per_gpu:286.676238348112 mfu:4.730585706616307 
Step 2394 | loss:1.2676801681518555 lr:7.688090372218949e-05 tokens_per_second_per_gpu:254.31149090493724 mfu:4.196519079625708 
Step 2395 | loss:1.2296652793884277 lr:7.680697518840378e-05 tokens_per_second_per_gpu:230.8942192593582 mfu:3.8100991545811707 
Step 2396 | loss:1.3555960655212402 lr:7.673306004879937e-05 tokens_per_second_per_gpu:209.78868654361335 mfu:3.4618263714201625 
Step 2397 | loss:1.367188811302185 lr:7.665915834606295e-05 tokens_per_second_per_gpu:265.24731346815315 mfu:4.376976470184956 
Step 2398 | loss:1.171135663986206 lr:7.65852701228733e-05 tokens_per_second_per_gpu:219.8063833691523 mfu:3.6271333172946396 
Step 2399 | loss:1.2804396152496338 lr:7.651139542190164e-05 tokens_per_second_per_gpu:312.6483296499109 mfu:5.159163968251059 
Step 2400 | loss:1.1252466440200806 lr:7.643753428581122e-05 tokens_per_second_per_gpu:235.5456745005558 mfu:3.8868551068908808 
Step 2401 | loss:1.1651127338409424 lr:7.636368675725758e-05 tokens_per_second_per_gpu:214.48426309127007 mfu:3.539310391123583 
Step 2402 | loss:1.128470540046692 lr:7.62898528788883e-05 tokens_per_second_per_gpu:296.11564227383616 mfu:4.8863499567240725 
Step 2403 | loss:1.3107212781906128 lr:7.621603269334306e-05 tokens_per_second_per_gpu:295.5590944373778 mfu:4.87716608695039 
Step 2404 | loss:1.2479091882705688 lr:7.614222624325375e-05 tokens_per_second_per_gpu:226.92966371451277 mfu:3.74467807224243 
Step 2405 | loss:1.6041483879089355 lr:7.606843357124426e-05 tokens_per_second_per_gpu:178.96116120263025 mfu:2.953126202934897 
Step 2406 | loss:1.1320531368255615 lr:7.599465471993046e-05 tokens_per_second_per_gpu:345.4877802701187 mfu:5.701063906007482 
Step 2407 | loss:1.2523993253707886 lr:7.592088973192036e-05 tokens_per_second_per_gpu:323.7921778094803 mfu:5.343054091562734 
Step 2408 | loss:1.200537919998169 lr:7.584713864981387e-05 tokens_per_second_per_gpu:266.79575923074447 mfu:4.4025281358346575 
Step 2409 | loss:1.0809688568115234 lr:7.577340151620298e-05 tokens_per_second_per_gpu:383.49104135459726 mfu:6.328174421782903 
Step 2410 | loss:1.2987196445465088 lr:7.569967837367151e-05 tokens_per_second_per_gpu:247.38554328577175 mfu:4.082230609116993 
Step 2411 | loss:1.2826893329620361 lr:7.562596926479518e-05 tokens_per_second_per_gpu:193.9765067512046 mfu:3.200901810153996 
Step 2412 | loss:1.1193574666976929 lr:7.555227423214174e-05 tokens_per_second_per_gpu:255.55327344556648 mfu:4.217010344514893 
Step 2413 | loss:1.3992825746536255 lr:7.547859331827069e-05 tokens_per_second_per_gpu:297.3154328116735 mfu:4.90614829090737 
Step 2414 | loss:1.0886447429656982 lr:7.54049265657335e-05 tokens_per_second_per_gpu:299.1571902672793 mfu:4.936540037167007 
Step 2415 | loss:1.1173546314239502 lr:7.533127401707329e-05 tokens_per_second_per_gpu:190.2424847187194 mfu:3.13928487476776 
Step 2416 | loss:1.0793081521987915 lr:7.52576357148251e-05 tokens_per_second_per_gpu:248.166313809988 mfu:4.095114487820326 
Step 2417 | loss:1.241355061531067 lr:7.518401170151578e-05 tokens_per_second_per_gpu:225.82732816517225 mfu:3.7264878907901635 
Step 2418 | loss:1.105475902557373 lr:7.51104020196638e-05 tokens_per_second_per_gpu:292.7732288695358 mfu:4.831195148055256 
Step 2419 | loss:1.2468558549880981 lr:7.50368067117794e-05 tokens_per_second_per_gpu:321.0291916914886 mfu:5.297460697730494 
Step 2420 | loss:1.200316309928894 lr:7.496322582036457e-05 tokens_per_second_per_gpu:261.16686771440544 mfu:4.309643026469741 
Step 2421 | loss:0.9707479476928711 lr:7.48896593879129e-05 tokens_per_second_per_gpu:256.99004705064397 mfu:4.240719252930141 
Step 2422 | loss:1.0918769836425781 lr:7.481610745690975e-05 tokens_per_second_per_gpu:281.18655710182713 mfu:4.6399977744347085 
Step 2423 | loss:1.478735089302063 lr:7.474257006983197e-05 tokens_per_second_per_gpu:203.8025666972834 mfu:3.3630464615597777 
Step 2424 | loss:1.4869983196258545 lr:7.466904726914803e-05 tokens_per_second_per_gpu:238.56733496537532 mfu:3.9367170134356617 
Step 2425 | loss:1.1151556968688965 lr:7.45955390973181e-05 tokens_per_second_per_gpu:216.01024791727738 mfu:3.5644914178037843 
Step 2426 | loss:1.1514354944229126 lr:7.452204559679372e-05 tokens_per_second_per_gpu:203.2657703269371 mfu:3.354188520449778 
Step 2427 | loss:1.1882944107055664 lr:7.444856681001814e-05 tokens_per_second_per_gpu:321.71868090782897 mfu:5.30883829864531 
Step 2428 | loss:1.205422282218933 lr:7.437510277942595e-05 tokens_per_second_per_gpu:201.247399243562 mfu:3.3208823857918106 
Step 2429 | loss:1.0332520008087158 lr:7.43016535474433e-05 tokens_per_second_per_gpu:226.52095977771313 mfu:3.7379338474235086 
Step 2430 | loss:1.2493311166763306 lr:7.422821915648786e-05 tokens_per_second_per_gpu:256.5134500173152 mfu:4.2328546907094555 
Step 2431 | loss:1.3921953439712524 lr:7.415479964896855e-05 tokens_per_second_per_gpu:235.7742369744573 mfu:3.890626728767663 
Step 2432 | loss:1.2093936204910278 lr:7.408139506728584e-05 tokens_per_second_per_gpu:232.91833108252152 mfu:3.843500020011888 
Step 2433 | loss:1.100531816482544 lr:7.400800545383159e-05 tokens_per_second_per_gpu:257.577099313423 mfu:4.25040649125635 
Step 2434 | loss:1.071419358253479 lr:7.393463085098887e-05 tokens_per_second_per_gpu:237.51966001223855 mfu:3.9194288133844575 
Step 2435 | loss:1.1734727621078491 lr:7.386127130113227e-05 tokens_per_second_per_gpu:174.73121008599662 mfu:2.883325697642462 
Step 2436 | loss:1.095379114151001 lr:7.378792684662751e-05 tokens_per_second_per_gpu:326.70302957619634 mfu:5.391087489241772 
Step 2437 | loss:1.3145699501037598 lr:7.371459752983172e-05 tokens_per_second_per_gpu:192.65954915911465 mfu:3.179170044740654 
Step 2438 | loss:1.1681952476501465 lr:7.364128339309326e-05 tokens_per_second_per_gpu:269.8514018476618 mfu:4.452950798596697 
Step 2439 | loss:1.1763484477996826 lr:7.356798447875164e-05 tokens_per_second_per_gpu:276.1113189396209 mfu:4.556248771566 
Step 2440 | loss:1.255323052406311 lr:7.34947008291377e-05 tokens_per_second_per_gpu:268.848830931307 mfu:4.4364068824559455 
Step 2441 | loss:1.02000093460083 lr:7.342143248657342e-05 tokens_per_second_per_gpu:269.7363003213996 mfu:4.451051451660644 
Step 2442 | loss:1.4540268182754517 lr:7.334817949337187e-05 tokens_per_second_per_gpu:311.31649245859876 mfu:5.137186667247441 
Step 2443 | loss:1.1766853332519531 lr:7.32749418918374e-05 tokens_per_second_per_gpu:225.38454200638776 mfu:3.719181258451526 
Step 2444 | loss:1.2015204429626465 lr:7.32017197242653e-05 tokens_per_second_per_gpu:290.52014641368606 mfu:4.794015925518758 
Step 2445 | loss:1.091508388519287 lr:7.312851303294207e-05 tokens_per_second_per_gpu:172.37536140205722 mfu:2.8444506789962998 
Step 2446 | loss:1.3159146308898926 lr:7.305532186014525e-05 tokens_per_second_per_gpu:226.5224616618515 mfu:3.7379586307528805 
Step 2447 | loss:1.3809131383895874 lr:7.298214624814334e-05 tokens_per_second_per_gpu:234.7871765539018 mfu:3.8743387589521228 
Step 2448 | loss:1.3153761625289917 lr:7.290898623919602e-05 tokens_per_second_per_gpu:253.5011576610469 mfu:4.183147371934718 
Step 2449 | loss:1.1772419214248657 lr:7.283584187555378e-05 tokens_per_second_per_gpu:211.53385735066485 mfu:3.4906242938535414 
Step 2450 | loss:1.2133502960205078 lr:7.276271319945818e-05 tokens_per_second_per_gpu:279.2777328066577 mfu:4.608499325246166 
Step 2451 | loss:1.287851333618164 lr:7.268960025314169e-05 tokens_per_second_per_gpu:285.2136037064509 mfu:4.706450052507988 
Step 2452 | loss:1.0958309173583984 lr:7.261650307882766e-05 tokens_per_second_per_gpu:413.41127834705946 mfu:6.821902978675857 
Step 2453 | loss:1.092279314994812 lr:7.254342171873041e-05 tokens_per_second_per_gpu:229.45700206621555 mfu:3.786382926300932 
Step 2454 | loss:1.1349798440933228 lr:7.24703562150551e-05 tokens_per_second_per_gpu:248.64207808557546 mfu:4.102965308295651 
Step 2455 | loss:1.119961142539978 lr:7.239730660999762e-05 tokens_per_second_per_gpu:250.71694861135987 mfu:4.137203768060972 
Step 2456 | loss:1.2705373764038086 lr:7.232427294574491e-05 tokens_per_second_per_gpu:174.1326484573995 mfu:2.8734485376061563 
Step 2457 | loss:1.1976395845413208 lr:7.22512552644745e-05 tokens_per_second_per_gpu:202.02757474720462 mfu:3.3337564457677975 
Step 2458 | loss:1.2719250917434692 lr:7.217825360835473e-05 tokens_per_second_per_gpu:258.13285929801356 mfu:4.259577360298594 
Step 2459 | loss:1.2252167463302612 lr:7.210526801954482e-05 tokens_per_second_per_gpu:248.0381729213645 mfu:4.092999971948175 
Step 2460 | loss:1.2733315229415894 lr:7.203229854019448e-05 tokens_per_second_per_gpu:223.88087498418318 mfu:3.6943685088363525 
Step 2461 | loss:1.2534328699111938 lr:7.195934521244432e-05 tokens_per_second_per_gpu:239.84689779959174 mfu:3.9578317095442084 
Step 2462 | loss:1.2972230911254883 lr:7.188640807842557e-05 tokens_per_second_per_gpu:288.2726887540983 mfu:4.756929520513816 
Step 2463 | loss:1.2872828245162964 lr:7.181348718025997e-05 tokens_per_second_per_gpu:267.28110434862003 mfu:4.410537054504123 
Step 2464 | loss:1.4668259620666504 lr:7.174058256006012e-05 tokens_per_second_per_gpu:196.57067586252543 mfu:3.243709471470028 
Step 2465 | loss:1.3953957557678223 lr:7.166769425992902e-05 tokens_per_second_per_gpu:236.80619754035405 mfu:3.907655617980639 
Step 2466 | loss:1.295400619506836 lr:7.159482232196038e-05 tokens_per_second_per_gpu:260.56736607218585 mfu:4.29975035480599 
Step 2467 | loss:1.1601628065109253 lr:7.152196678823838e-05 tokens_per_second_per_gpu:282.47850810663243 mfu:4.661316893843408 
Step 2468 | loss:1.2129096984863281 lr:7.14491277008377e-05 tokens_per_second_per_gpu:268.00532324223224 mfu:4.422487746917016 
Step 2469 | loss:1.3198457956314087 lr:7.137630510182362e-05 tokens_per_second_per_gpu:257.46912688561974 mfu:4.248624785082801 
Step 2470 | loss:1.4173431396484375 lr:7.130349903325186e-05 tokens_per_second_per_gpu:191.48769012915363 mfu:3.1598326221162814 
Step 2471 | loss:1.2453067302703857 lr:7.123070953716853e-05 tokens_per_second_per_gpu:300.14525035649154 mfu:4.952844503007073 
Step 2472 | loss:1.0898137092590332 lr:7.115793665561027e-05 tokens_per_second_per_gpu:206.41811840932456 mfu:3.4062069676944824 
Step 2473 | loss:1.2275099754333496 lr:7.108518043060404e-05 tokens_per_second_per_gpu:262.78854931240994 mfu:4.336403192685148 
Step 2474 | loss:1.0645201206207275 lr:7.101244090416728e-05 tokens_per_second_per_gpu:210.97361033893245 mfu:3.4813793821679853 
Step 2475 | loss:1.1504496335983276 lr:7.093971811830766e-05 tokens_per_second_per_gpu:271.9500337215169 mfu:4.487581356061502 
Step 2476 | loss:1.2157526016235352 lr:7.086701211502323e-05 tokens_per_second_per_gpu:236.29274387613225 mfu:3.8991828663533212 
Step 2477 | loss:1.040320873260498 lr:7.079432293630244e-05 tokens_per_second_per_gpu:317.4805597254333 mfu:5.238902975076555 
Step 2478 | loss:1.3231852054595947 lr:7.072165062412386e-05 tokens_per_second_per_gpu:218.78571664736546 mfu:3.6102907933619774 
Step 2479 | loss:1.2031184434890747 lr:7.064899522045649e-05 tokens_per_second_per_gpu:342.188048776247 mfu:5.646613412550028 
Step 2480 | loss:1.0961873531341553 lr:7.057635676725945e-05 tokens_per_second_per_gpu:252.29739309592784 mfu:4.1632834603712885 
Step 2481 | loss:1.2119264602661133 lr:7.050373530648204e-05 tokens_per_second_per_gpu:225.93598001130857 mfu:3.7282808083800263 
Step 2482 | loss:1.1656771898269653 lr:7.043113088006394e-05 tokens_per_second_per_gpu:250.6792213765776 mfu:4.136581212391065 
Step 2483 | loss:1.124389410018921 lr:7.035854352993477e-05 tokens_per_second_per_gpu:226.1745836288049 mfu:3.732218124109363 
Step 2484 | loss:1.2785301208496094 lr:7.028597329801436e-05 tokens_per_second_per_gpu:255.6439333345572 mfu:4.218506367964532 
Step 2485 | loss:1.184933066368103 lr:7.021342022621273e-05 tokens_per_second_per_gpu:240.1747425349193 mfu:3.963241636881983 
Step 2486 | loss:1.0436408519744873 lr:7.01408843564299e-05 tokens_per_second_per_gpu:207.8350717250432 mfu:3.4295888117597784 
Step 2487 | loss:1.1288855075836182 lr:7.006836573055604e-05 tokens_per_second_per_gpu:362.03101534836594 mfu:5.974051970359433 
Step 2488 | loss:1.1816792488098145 lr:6.999586439047128e-05 tokens_per_second_per_gpu:227.38514593567544 mfu:3.752194208555177 
Step 2489 | loss:1.167258858680725 lr:6.992338037804575e-05 tokens_per_second_per_gpu:243.7365708631741 mfu:4.022017119203622 
Step 2490 | loss:1.1344351768493652 lr:6.985091373513972e-05 tokens_per_second_per_gpu:329.3715092612733 mfu:5.435121385909875 
Step 2491 | loss:1.2786846160888672 lr:6.977846450360323e-05 tokens_per_second_per_gpu:207.9355475917265 mfu:3.4312468134885954 
Step 2492 | loss:1.1513612270355225 lr:6.970603272527645e-05 tokens_per_second_per_gpu:229.92844948425036 mfu:3.7941625121850904 
Step 2493 | loss:1.3770098686218262 lr:6.963361844198934e-05 tokens_per_second_per_gpu:273.04177488343277 mfu:4.505596714312479 
Step 2494 | loss:1.1896591186523438 lr:6.95612216955618e-05 tokens_per_second_per_gpu:242.27109385529263 mfu:3.997834561811332 
Step 2495 | loss:1.208528757095337 lr:6.948884252780365e-05 tokens_per_second_per_gpu:305.53002006219356 mfu:5.041701238221668 
Step 2496 | loss:1.301265001296997 lr:6.941648098051444e-05 tokens_per_second_per_gpu:227.47753430044426 mfu:3.753718754434359 
Step 2497 | loss:1.1467552185058594 lr:6.934413709548368e-05 tokens_per_second_per_gpu:280.7916206194337 mfu:4.633480733157073 
Step 2498 | loss:1.2334282398223877 lr:6.927181091449061e-05 tokens_per_second_per_gpu:193.17186674969594 mfu:3.1876240494576717 
Step 2499 | loss:1.1546416282653809 lr:6.91995024793042e-05 tokens_per_second_per_gpu:283.48811428208705 mfu:4.677976902257212 
Step 2500 | loss:1.2404533624649048 lr:6.91272118316833e-05 tokens_per_second_per_gpu:255.24528571782437 mfu:4.211928087432599 
Step 2501 | loss:1.3314743041992188 lr:6.905493901337637e-05 tokens_per_second_per_gpu:283.57578036474354 mfu:4.679423523435024 
Step 2502 | loss:1.2527073621749878 lr:6.898268406612156e-05 tokens_per_second_per_gpu:363.68615387169183 mfu:6.001364225766551 
Step 2503 | loss:1.2659823894500732 lr:6.891044703164689e-05 tokens_per_second_per_gpu:293.99511501074636 mfu:4.851358092664932 
Step 2504 | loss:1.0861411094665527 lr:6.883822795166977e-05 tokens_per_second_per_gpu:230.03338762434157 mfu:3.795894148083674 
Step 2505 | loss:1.309096336364746 lr:6.876602686789743e-05 tokens_per_second_per_gpu:269.88456112255835 mfu:4.45349797611225 
Step 2506 | loss:1.1331309080123901 lr:6.869384382202669e-05 tokens_per_second_per_gpu:254.32220767973402 mfu:4.196695922401262 
Step 2507 | loss:1.1768226623535156 lr:6.86216788557438e-05 tokens_per_second_per_gpu:246.24221966953283 mfu:4.063364063399141 
Step 2508 | loss:1.2871428728103638 lr:6.854953201072479e-05 tokens_per_second_per_gpu:284.51134219959636 mfu:4.694861689741073 
Step 2509 | loss:1.173840045928955 lr:6.847740332863503e-05 tokens_per_second_per_gpu:265.167204526015 mfu:4.375654553102345 
Step 2510 | loss:1.4094737768173218 lr:6.840529285112953e-05 tokens_per_second_per_gpu:222.55904677472356 mfu:3.6725563709685507 
Step 2511 | loss:1.1838879585266113 lr:6.833320061985277e-05 tokens_per_second_per_gpu:300.7946735452732 mfu:4.963560954681262 
Step 2512 | loss:1.1501084566116333 lr:6.826112667643857e-05 tokens_per_second_per_gpu:228.40994508231378 mfu:3.76910492366423 
Step 2513 | loss:1.122528076171875 lr:6.818907106251039e-05 tokens_per_second_per_gpu:154.25000010626516 mfu:2.5453551712304567 
Step 2514 | loss:1.1022504568099976 lr:6.811703381968095e-05 tokens_per_second_per_gpu:240.7007272014973 mfu:3.9719211687467477 
Step 2515 | loss:1.3902565240859985 lr:6.804501498955238e-05 tokens_per_second_per_gpu:250.7562244106362 mfu:4.137851877355775 
Step 2516 | loss:1.3093113899230957 lr:6.797301461371625e-05 tokens_per_second_per_gpu:202.6518137343841 mfu:3.3440573205360717 
Step 2517 | loss:1.2923088073730469 lr:6.790103273375338e-05 tokens_per_second_per_gpu:242.26988364260524 mfu:3.997814591496129 
Step 2518 | loss:1.2471590042114258 lr:6.782906939123403e-05 tokens_per_second_per_gpu:248.60576935827964 mfu:4.102366160115946 
Step 2519 | loss:1.2442471981048584 lr:6.775712462771763e-05 tokens_per_second_per_gpu:221.858442677356 mfu:3.66099535793133 
Step 2520 | loss:1.5145962238311768 lr:6.768519848475291e-05 tokens_per_second_per_gpu:261.51881919482133 mfu:4.315450751073188 
Step 2521 | loss:1.6646300554275513 lr:6.76132910038779e-05 tokens_per_second_per_gpu:224.04645144305434 mfu:3.697100767478372 
Step 2522 | loss:1.2592670917510986 lr:6.754140222661982e-05 tokens_per_second_per_gpu:247.8395518960707 mfu:4.08972242865159 
Step 2523 | loss:1.178292155265808 lr:6.746953219449508e-05 tokens_per_second_per_gpu:325.88802915057767 mfu:5.377638766087968 
Step 2524 | loss:1.1445761919021606 lr:6.739768094900932e-05 tokens_per_second_per_gpu:276.2691349359716 mfu:4.558852970996388 
Step 2525 | loss:1.1679422855377197 lr:6.732584853165715e-05 tokens_per_second_per_gpu:242.00824662674253 mfu:3.9934971903236645 
Step 2526 | loss:1.1605091094970703 lr:6.725403498392258e-05 tokens_per_second_per_gpu:234.9724242555645 mfu:3.877395622453328 
Step 2527 | loss:1.1698932647705078 lr:6.718224034727853e-05 tokens_per_second_per_gpu:253.47655711361227 mfu:4.182741426193488 
Step 2528 | loss:1.1722466945648193 lr:6.711046466318702e-05 tokens_per_second_per_gpu:214.19812023610245 mfu:3.534588607035351 
Step 2529 | loss:1.1904993057250977 lr:6.703870797309922e-05 tokens_per_second_per_gpu:308.7990219699392 mfu:5.095644647653826 
Step 2530 | loss:1.2249349355697632 lr:6.696697031845522e-05 tokens_per_second_per_gpu:289.7951126455776 mfu:4.782051786460734 
Step 2531 | loss:1.0954091548919678 lr:6.689525174068417e-05 tokens_per_second_per_gpu:247.86328560423732 mfu:4.090114070251413 
Step 2532 | loss:1.1677993535995483 lr:6.682355228120423e-05 tokens_per_second_per_gpu:265.23245005962 mfu:4.37673120176521 
Step 2533 | loss:1.626420497894287 lr:6.675187198142241e-05 tokens_per_second_per_gpu:368.152427761353 mfu:6.075064409451147 
Step 2534 | loss:1.209691047668457 lr:6.668021088273481e-05 tokens_per_second_per_gpu:327.9601657571029 mfu:5.411832112106 
Step 2535 | loss:1.2866861820220947 lr:6.660856902652631e-05 tokens_per_second_per_gpu:208.48757262479143 mfu:3.4403560502574284 
Step 2536 | loss:1.148809790611267 lr:6.653694645417076e-05 tokens_per_second_per_gpu:215.93156317486586 mfu:3.563193002141832 
Step 2537 | loss:1.45709228515625 lr:6.646534320703084e-05 tokens_per_second_per_gpu:238.13731649362418 mfu:3.9296210669848195 
Step 2538 | loss:1.064414381980896 lr:6.639375932645806e-05 tokens_per_second_per_gpu:264.49419358535596 mfu:4.3645488683249 
Step 2539 | loss:1.2113150358200073 lr:6.632219485379276e-05 tokens_per_second_per_gpu:256.1708551414035 mfu:4.227201364042109 
Step 2540 | loss:1.1334333419799805 lr:6.625064983036409e-05 tokens_per_second_per_gpu:291.3488649854833 mfu:4.807691018554516 
Step 2541 | loss:1.0905593633651733 lr:6.617912429748988e-05 tokens_per_second_per_gpu:255.78308490747088 mfu:4.2208025765574435 
Step 2542 | loss:1.0940468311309814 lr:6.610761829647685e-05 tokens_per_second_per_gpu:290.2965575167654 mfu:4.790326375083654 
Step 2543 | loss:1.271986484527588 lr:6.603613186862029e-05 tokens_per_second_per_gpu:229.01397090776783 mfu:3.779072251102266 
Step 2544 | loss:1.2215696573257446 lr:6.596466505520436e-05 tokens_per_second_per_gpu:235.4183733839133 mfu:3.8847544485095122 
Step 2545 | loss:1.1456366777420044 lr:6.589321789750168e-05 tokens_per_second_per_gpu:245.15169975962888 mfu:4.045368857628693 
Step 2546 | loss:1.3126546144485474 lr:6.58217904367737e-05 tokens_per_second_per_gpu:202.18618235487614 mfu:3.3363737079662097 
Step 2547 | loss:1.1004254817962646 lr:6.575038271427039e-05 tokens_per_second_per_gpu:321.15344599770737 mfu:5.299511079193467 
Step 2548 | loss:1.3428303003311157 lr:6.567899477123035e-05 tokens_per_second_per_gpu:248.5476213555328 mfu:4.101406631303069 
Step 2549 | loss:1.116229772567749 lr:6.56076266488808e-05 tokens_per_second_per_gpu:265.78108950494374 mfu:4.385784571284391 
Step 2550 | loss:1.2241458892822266 lr:6.553627838843743e-05 tokens_per_second_per_gpu:280.47814020369634 mfu:4.628307838526753 
Step 2551 | loss:1.1425156593322754 lr:6.546495003110453e-05 tokens_per_second_per_gpu:208.3507192599203 mfu:3.4380977655265688 
Step 2552 | loss:1.0147738456726074 lr:6.539364161807489e-05 tokens_per_second_per_gpu:283.31603123908343 mfu:4.675137275267983 
Step 2553 | loss:1.2641574144363403 lr:6.532235319052976e-05 tokens_per_second_per_gpu:291.1614611464091 mfu:4.804598575568666 
Step 2554 | loss:1.337725281715393 lr:6.525108478963876e-05 tokens_per_second_per_gpu:258.99554546763244 mfu:4.273812969384335 
Step 2555 | loss:1.1951018571853638 lr:6.517983645656014e-05 tokens_per_second_per_gpu:237.06086991282606 mfu:3.9118580921446235 
Step 2556 | loss:1.3488274812698364 lr:6.51086082324404e-05 tokens_per_second_per_gpu:234.9669586716851 mfu:3.877305432163658 
Step 2557 | loss:1.0958583354949951 lr:6.503740015841454e-05 tokens_per_second_per_gpu:209.46904706093932 mfu:3.4565518429949225 
Step 2558 | loss:1.1533026695251465 lr:6.496621227560581e-05 tokens_per_second_per_gpu:300.0131917020921 mfu:4.95066533815359 
Step 2559 | loss:1.240685224533081 lr:6.489504462512585e-05 tokens_per_second_per_gpu:248.65063760317523 mfu:4.103106553108428 
Step 2560 | loss:1.4146977663040161 lr:6.482389724807469e-05 tokens_per_second_per_gpu:246.68632532605497 mfu:4.0706924694193845 
Step 2561 | loss:1.2120530605316162 lr:6.475277018554049e-05 tokens_per_second_per_gpu:219.62145491699644 mfu:3.624081721886677 
Step 2562 | loss:1.1908496618270874 lr:6.468166347859987e-05 tokens_per_second_per_gpu:219.65753635078622 mfu:3.6246771193843688 
Step 2563 | loss:1.220528244972229 lr:6.461057716831753e-05 tokens_per_second_per_gpu:263.3976567871883 mfu:4.346454374919793 
Step 2564 | loss:1.1527172327041626 lr:6.453951129574644e-05 tokens_per_second_per_gpu:335.50114306607105 mfu:5.536269490234299 
Step 2565 | loss:1.1258575916290283 lr:6.446846590192786e-05 tokens_per_second_per_gpu:242.78987850562194 mfu:4.00639528266424 
Step 2566 | loss:1.3047468662261963 lr:6.439744102789107e-05 tokens_per_second_per_gpu:337.8066496764527 mfu:5.574313789547092 
Step 2567 | loss:1.217836856842041 lr:6.432643671465358e-05 tokens_per_second_per_gpu:229.6615129774154 mfu:3.7897576615037654 
Step 2568 | loss:1.3539164066314697 lr:6.425545300322112e-05 tokens_per_second_per_gpu:235.22939104577264 mfu:3.881635957933653 
Step 2569 | loss:1.1840474605560303 lr:6.418448993458728e-05 tokens_per_second_per_gpu:233.8333336761761 mfu:3.8585989281599815 
Step 2570 | loss:1.1471058130264282 lr:6.4113547549734e-05 tokens_per_second_per_gpu:247.40903240259385 mfu:4.082618214594657 
Step 2571 | loss:1.1486358642578125 lr:6.404262588963105e-05 tokens_per_second_per_gpu:351.33965476523383 mfu:5.797628567253973 
Step 2572 | loss:1.4042391777038574 lr:6.397172499523639e-05 tokens_per_second_per_gpu:230.0800767144954 mfu:3.7966645877399534 
Step 2573 | loss:1.2352969646453857 lr:6.390084490749593e-05 tokens_per_second_per_gpu:275.8807728552635 mfu:4.552444417156783 
Step 2574 | loss:1.1628572940826416 lr:6.382998566734351e-05 tokens_per_second_per_gpu:236.11120294993395 mfu:3.896187170178472 
Step 2575 | loss:1.1817456483840942 lr:6.375914731570103e-05 tokens_per_second_per_gpu:225.77059640117002 mfu:3.7255517320298615 
Step 2576 | loss:1.3074684143066406 lr:6.368832989347828e-05 tokens_per_second_per_gpu:281.06170724110694 mfu:4.637937565433783 
Step 2577 | loss:1.0920255184173584 lr:6.361753344157288e-05 tokens_per_second_per_gpu:249.4169355523866 mfu:4.115751612728427 
Step 2578 | loss:1.2534756660461426 lr:6.354675800087054e-05 tokens_per_second_per_gpu:282.01228589174565 mfu:4.653623531608161 
Step 2579 | loss:1.2671021223068237 lr:6.347600361224465e-05 tokens_per_second_per_gpu:265.96157843756515 mfu:4.388762907995453 
Step 2580 | loss:1.3428637981414795 lr:6.340527031655646e-05 tokens_per_second_per_gpu:270.91363212765935 mfu:4.4704791832603386 
Step 2581 | loss:1.2385711669921875 lr:6.33345581546552e-05 tokens_per_second_per_gpu:239.13687981504526 mfu:3.946115353321278 
Step 2582 | loss:1.2892098426818848 lr:6.32638671673777e-05 tokens_per_second_per_gpu:205.1104266050334 mfu:3.384628101606086 
Step 2583 | loss:1.2235137224197388 lr:6.319319739554865e-05 tokens_per_second_per_gpu:221.99663329373854 mfu:3.6632757093075536 
Step 2584 | loss:1.130149483680725 lr:6.312254887998055e-05 tokens_per_second_per_gpu:236.47606883354845 mfu:3.9022080017053695 
Step 2585 | loss:1.1561415195465088 lr:6.305192166147346e-05 tokens_per_second_per_gpu:209.60747978084115 mfu:3.4588361894404778 
Step 2586 | loss:1.1235952377319336 lr:6.298131578081531e-05 tokens_per_second_per_gpu:186.9681934894863 mfu:3.0852541836384155 
Step 2587 | loss:1.3051445484161377 lr:6.291073127878158e-05 tokens_per_second_per_gpu:208.0458998072656 mfu:3.433067789710869 
Step 2588 | loss:1.213310956954956 lr:6.28401681961355e-05 tokens_per_second_per_gpu:172.0566137497349 mfu:2.8391908671026385 
Step 2589 | loss:1.277137041091919 lr:6.276962657362788e-05 tokens_per_second_per_gpu:233.03878720492676 mfu:3.845487725774347 
Step 2590 | loss:1.2691736221313477 lr:6.26991064519971e-05 tokens_per_second_per_gpu:252.1226987519902 mfu:4.160400743020106 
Step 2591 | loss:1.3003036975860596 lr:6.262860787196923e-05 tokens_per_second_per_gpu:237.50762941749966 mfu:3.9192302906193976 
Step 2592 | loss:1.139605164527893 lr:6.255813087425781e-05 tokens_per_second_per_gpu:160.73247936376504 mfu:2.6523257520350225 
Step 2593 | loss:1.2000560760498047 lr:6.248767549956392e-05 tokens_per_second_per_gpu:289.26498082711583 mfu:4.773303820401571 
Step 2594 | loss:1.1065565347671509 lr:6.24172417885762e-05 tokens_per_second_per_gpu:279.2650762855599 mfu:4.608290473762187 
Step 2595 | loss:1.2195249795913696 lr:6.234682978197074e-05 tokens_per_second_per_gpu:176.15084823444414 mfu:2.906751845454051 
Step 2596 | loss:1.3122801780700684 lr:6.227643952041114e-05 tokens_per_second_per_gpu:265.97443459102584 mfu:4.388975053711309 
Step 2597 | loss:1.0829050540924072 lr:6.220607104454841e-05 tokens_per_second_per_gpu:312.3250227418893 mfu:5.1538289218351085 
Step 2598 | loss:1.2162504196166992 lr:6.213572439502091e-05 tokens_per_second_per_gpu:292.70025014530927 mfu:4.829990890207789 
Step 2599 | loss:1.242630958557129 lr:6.206539961245455e-05 tokens_per_second_per_gpu:293.188946663017 mfu:4.838055111975391 
Step 2600 | loss:1.1522740125656128 lr:6.199509673746246e-05 tokens_per_second_per_gpu:175.97217189770188 mfu:2.903803419279723 
Step 2601 | loss:1.2040764093399048 lr:6.192481581064526e-05 tokens_per_second_per_gpu:297.69911850785263 mfu:4.912479677424219 
Step 2602 | loss:1.328460454940796 lr:6.185455687259079e-05 tokens_per_second_per_gpu:227.3808153408728 mfu:3.7521227472788863 
Step 2603 | loss:1.4370803833007812 lr:6.178431996387417e-05 tokens_per_second_per_gpu:194.80144560567484 mfu:3.2145145322138227 
Step 2604 | loss:1.2797937393188477 lr:6.171410512505791e-05 tokens_per_second_per_gpu:247.06585196452903 mfu:4.0769552252780175 
Step 2605 | loss:1.4044363498687744 lr:6.164391239669169e-05 tokens_per_second_per_gpu:219.73555571813446 mfu:3.6259645553649142 
Step 2606 | loss:1.1798157691955566 lr:6.157374181931244e-05 tokens_per_second_per_gpu:204.64433815228125 mfu:3.376936946645657 
Step 2607 | loss:1.157113790512085 lr:6.150359343344432e-05 tokens_per_second_per_gpu:329.9981679845678 mfu:5.44546218993474 
Step 2608 | loss:1.142669677734375 lr:6.143346727959861e-05 tokens_per_second_per_gpu:224.46548402553594 mfu:3.704015430363291 
Step 2609 | loss:1.1423060894012451 lr:6.136336339827389e-05 tokens_per_second_per_gpu:274.7975989765631 mfu:4.534570431862829 
Step 2610 | loss:1.2672773599624634 lr:6.129328182995572e-05 tokens_per_second_per_gpu:223.5320580109115 mfu:3.688612508278049 
Step 2611 | loss:1.0054843425750732 lr:6.12232226151168e-05 tokens_per_second_per_gpu:218.94207609352603 mfu:3.6128709575407867 
Step 2612 | loss:1.2865660190582275 lr:6.115318579421704e-05 tokens_per_second_per_gpu:251.1299881351027 mfu:4.144019536533952 
Step 2613 | loss:1.4348993301391602 lr:6.108317140770328e-05 tokens_per_second_per_gpu:249.94636502533328 mfu:4.124487989038561 
Step 2614 | loss:1.1992912292480469 lr:6.101317949600951e-05 tokens_per_second_per_gpu:238.00920818793912 mfu:3.927507088779773 
Step 2615 | loss:1.403814673423767 lr:6.0943210099556644e-05 tokens_per_second_per_gpu:241.33021277511065 mfu:3.982308620020056 
Step 2616 | loss:1.2748249769210815 lr:6.0873263258752645e-05 tokens_per_second_per_gpu:189.4275734785711 mfu:3.1258376233072975 
Step 2617 | loss:1.216747760772705 lr:6.080333901399251e-05 tokens_per_second_per_gpu:202.71216255257704 mfu:3.3450531660878333 
Step 2618 | loss:1.2545708417892456 lr:6.073343740565807e-05 tokens_per_second_per_gpu:237.12542896232432 mfu:3.9129234127953656 
Step 2619 | loss:1.1452068090438843 lr:6.0663558474118084e-05 tokens_per_second_per_gpu:179.3857575633384 mfu:2.9601326764627385 
Step 2620 | loss:1.2879270315170288 lr:6.0593702259728336e-05 tokens_per_second_per_gpu:209.72678258772882 mfu:3.460804863775937 
Step 2621 | loss:1.4173816442489624 lr:6.05238688028314e-05 tokens_per_second_per_gpu:244.09687088288086 mfu:4.027962607162929 
Step 2622 | loss:1.2417138814926147 lr:6.0454058143756764e-05 tokens_per_second_per_gpu:273.77493053526246 mfu:4.5176948765712535 
Step 2623 | loss:1.3191145658493042 lr:6.0384270322820657e-05 tokens_per_second_per_gpu:270.20225404743127 mfu:4.458740383429148 
Step 2624 | loss:1.0999114513397217 lr:6.031450538032619e-05 tokens_per_second_per_gpu:214.6809020853374 mfu:3.5425552279473758 
Step 2625 | loss:1.3247096538543701 lr:6.024476335656329e-05 tokens_per_second_per_gpu:229.1897448014373 mfu:3.7819727826349125 
Step 2626 | loss:1.1791162490844727 lr:6.0175044291808535e-05 tokens_per_second_per_gpu:195.90374552156638 mfu:3.2327041256610087 
Step 2627 | loss:1.214744210243225 lr:6.010534822632541e-05 tokens_per_second_per_gpu:196.7368218501721 mfu:3.2464511281866844 
Step 2628 | loss:1.2784535884857178 lr:6.0035675200363926e-05 tokens_per_second_per_gpu:262.930105711324 mfu:4.3387390844955105 
Step 2629 | loss:1.2138824462890625 lr:5.9966025254160906e-05 tokens_per_second_per_gpu:318.12345282782377 mfu:5.249511670581195 
Step 2630 | loss:1.4926267862319946 lr:5.989639842793988e-05 tokens_per_second_per_gpu:258.51777409287575 mfu:4.265929028777755 
Step 2631 | loss:1.1265969276428223 lr:5.982679476191092e-05 tokens_per_second_per_gpu:160.45581791565363 mfu:2.6477604253112275 
Step 2632 | loss:1.216382622718811 lr:5.975721429627075e-05 tokens_per_second_per_gpu:241.37151094465193 mfu:3.9829901014419806 
Step 2633 | loss:1.1165714263916016 lr:5.96876570712028e-05 tokens_per_second_per_gpu:338.25354240073636 mfu:5.58168818634422 
Step 2634 | loss:1.1951161623001099 lr:5.961812312687689e-05 tokens_per_second_per_gpu:324.26400356831533 mfu:5.350839920634651 
Step 2635 | loss:1.1633963584899902 lr:5.9548612503449605e-05 tokens_per_second_per_gpu:191.59795413423282 mfu:3.1616521427343396 
Step 2636 | loss:1.1042320728302002 lr:5.9479125241063896e-05 tokens_per_second_per_gpu:244.77739147589983 mfu:4.039192212410102 
Step 2637 | loss:1.1256213188171387 lr:5.940966137984927e-05 tokens_per_second_per_gpu:294.05889001095164 mfu:4.852410475332394 
Step 2638 | loss:1.1479514837265015 lr:5.934022095992179e-05 tokens_per_second_per_gpu:325.77346861144514 mfu:5.375748346246807 
Step 2639 | loss:1.224137544631958 lr:5.927080402138386e-05 tokens_per_second_per_gpu:209.32467358492272 mfu:3.4541694652087687 
Step 2640 | loss:1.1967747211456299 lr:5.9201410604324444e-05 tokens_per_second_per_gpu:179.4697163124945 mfu:2.9615181211057684 
Step 2641 | loss:1.1712685823440552 lr:5.9132040748818886e-05 tokens_per_second_per_gpu:240.52215030586729 mfu:3.9689743834991553 
Step 2642 | loss:1.2655115127563477 lr:5.906269449492881e-05 tokens_per_second_per_gpu:293.7689643333227 mfu:4.84762626902888 
Step 2643 | loss:1.2260503768920898 lr:5.8993371882702396e-05 tokens_per_second_per_gpu:217.9144653789702 mfu:3.595913847365716 
Step 2644 | loss:1.3437224626541138 lr:5.892407295217401e-05 tokens_per_second_per_gpu:284.0419330897941 mfu:4.687115738984284 
Step 2645 | loss:1.2028934955596924 lr:5.8854797743364466e-05 tokens_per_second_per_gpu:250.39360405762247 mfu:4.131868100434536 
Step 2646 | loss:1.1042444705963135 lr:5.8785546296280816e-05 tokens_per_second_per_gpu:261.74560563105877 mfu:4.319193065678337 
Step 2647 | loss:1.335113763809204 lr:5.871631865091635e-05 tokens_per_second_per_gpu:287.24599408259525 mfu:4.739987526416022 
Step 2648 | loss:1.2743984460830688 lr:5.86471148472507e-05 tokens_per_second_per_gpu:293.68269044229936 mfu:4.8462026210904225 
Step 2649 | loss:1.150569200515747 lr:5.857793492524969e-05 tokens_per_second_per_gpu:208.43058116045148 mfu:3.439415606054033 
Step 2650 | loss:1.2451744079589844 lr:5.8508778924865305e-05 tokens_per_second_per_gpu:220.99132536079995 mfu:3.6466866283090362 
Step 2651 | loss:1.1912317276000977 lr:5.8439646886035814e-05 tokens_per_second_per_gpu:329.93838865512873 mfu:5.4444757417972 
Step 2652 | loss:0.941226065158844 lr:5.837053884868553e-05 tokens_per_second_per_gpu:386.0112000003608 mfu:6.36976079997996 
Step 2653 | loss:1.1735634803771973 lr:5.830145485272507e-05 tokens_per_second_per_gpu:322.00783591259005 mfu:5.313609787696517 
Step 2654 | loss:1.186784267425537 lr:5.823239493805097e-05 tokens_per_second_per_gpu:236.05580069350427 mfu:3.895272950276987 
Step 2655 | loss:1.1602530479431152 lr:5.8163359144545956e-05 tokens_per_second_per_gpu:345.95715009545 mfu:5.70880920851188 
Step 2656 | loss:1.282701015472412 lr:5.809434751207894e-05 tokens_per_second_per_gpu:186.89454462991512 mfu:3.084038867557796 
Step 2657 | loss:1.1292953491210938 lr:5.8025360080504585e-05 tokens_per_second_per_gpu:196.70171601725085 mfu:3.2458718295591 
Step 2658 | loss:1.2650378942489624 lr:5.795639688966388e-05 tokens_per_second_per_gpu:194.2994600472038 mfu:3.2062310214439225 
Step 2659 | loss:1.1154680252075195 lr:5.788745797938372e-05 tokens_per_second_per_gpu:307.0596742583738 mfu:5.066942814985101 
Step 2660 | loss:1.2928777933120728 lr:5.781854338947679e-05 tokens_per_second_per_gpu:259.7509465439718 mfu:4.286278214341799 
Step 2661 | loss:1.1384226083755493 lr:5.774965315974208e-05 tokens_per_second_per_gpu:355.49252602033846 mfu:5.866157139813796 
Step 2662 | loss:1.2463574409484863 lr:5.768078732996418e-05 tokens_per_second_per_gpu:279.9421182138971 mfu:4.6194626758513 
Step 2663 | loss:1.1891790628433228 lr:5.761194593991373e-05 tokens_per_second_per_gpu:273.02929333664457 mfu:4.505390750165702 
Step 2664 | loss:1.3039064407348633 lr:5.7543129029347375e-05 tokens_per_second_per_gpu:310.48891758597836 mfu:5.123530446954712 
Step 2665 | loss:1.1497102975845337 lr:5.7474336638007345e-05 tokens_per_second_per_gpu:293.68810949146916 mfu:4.846292043487946 
Step 2666 | loss:1.308733344078064 lr:5.7405568805622e-05 tokens_per_second_per_gpu:192.69664926291082 mfu:3.179782251813495 
Step 2667 | loss:1.3702383041381836 lr:5.733682557190536e-05 tokens_per_second_per_gpu:269.0470973378941 mfu:4.439678574014715 
Step 2668 | loss:1.2422183752059937 lr:5.726810697655716e-05 tokens_per_second_per_gpu:186.99902792477315 mfu:3.085762997831318 
Step 2669 | loss:1.0675466060638428 lr:5.719941305926317e-05 tokens_per_second_per_gpu:197.89560621820144 mfu:3.2655727993793744 
Step 2670 | loss:1.1446740627288818 lr:5.713074385969457e-05 tokens_per_second_per_gpu:253.85700485033445 mfu:4.189019381547664 
Step 2671 | loss:1.4233489036560059 lr:5.7062099417508585e-05 tokens_per_second_per_gpu:262.3781125929841 mfu:4.329630374367262 
Step 2672 | loss:1.1617074012756348 lr:5.699347977234799e-05 tokens_per_second_per_gpu:331.00831481522 mfu:5.462131119966061 
Step 2673 | loss:1.3159631490707397 lr:5.692488496384112e-05 tokens_per_second_per_gpu:239.44986021162066 mfu:3.9512799968893044 
Step 2674 | loss:1.1394153833389282 lr:5.685631503160224e-05 tokens_per_second_per_gpu:352.06774768687507 mfu:5.80964318691011 
Step 2675 | loss:1.1590100526809692 lr:5.678777001523108e-05 tokens_per_second_per_gpu:222.56114004957576 mfu:3.672590913127164 
Step 2676 | loss:1.3263012170791626 lr:5.67192499543129e-05 tokens_per_second_per_gpu:274.60250009395435 mfu:4.531351009176233 
Step 2677 | loss:1.170203447341919 lr:5.6650754888418825e-05 tokens_per_second_per_gpu:274.0726177758789 mfu:4.522607160245745 
Step 2678 | loss:1.072995662689209 lr:5.658228485710517e-05 tokens_per_second_per_gpu:260.06915860378876 mfu:4.291529188159919 
Step 2679 | loss:1.4010478258132935 lr:5.651383989991418e-05 tokens_per_second_per_gpu:350.7679569870558 mfu:5.788194700835407 
Step 2680 | loss:1.2315442562103271 lr:5.644542005637339e-05 tokens_per_second_per_gpu:326.4382247272235 mfu:5.3867178140959995 
Step 2681 | loss:1.1708672046661377 lr:5.637702536599576e-05 tokens_per_second_per_gpu:302.2108693284787 mfu:4.986930298329712 
Step 2682 | loss:1.2293033599853516 lr:5.630865586827998e-05 tokens_per_second_per_gpu:203.51383021174482 mfu:3.3582818787002497 
Step 2683 | loss:1.2247642278671265 lr:5.6240311602710015e-05 tokens_per_second_per_gpu:269.7938780461777 mfu:4.452001570036078 
Step 2684 | loss:1.0490487813949585 lr:5.6171992608755276e-05 tokens_per_second_per_gpu:210.36308186545892 mfu:3.471304751334477 
Step 2685 | loss:1.1868106126785278 lr:5.610369892587064e-05 tokens_per_second_per_gpu:276.7110233349167 mfu:4.566144788958054 
Step 2686 | loss:1.1114623546600342 lr:5.603543059349623e-05 tokens_per_second_per_gpu:233.98819702263646 mfu:3.8611544044612804 
Step 2687 | loss:1.3578675985336304 lr:5.596718765105772e-05 tokens_per_second_per_gpu:186.75347803342154 mfu:3.0817110582182465 
Step 2688 | loss:1.124312400817871 lr:5.5898970137966033e-05 tokens_per_second_per_gpu:259.22702734214687 mfu:4.277632765727515 
Step 2689 | loss:1.33159601688385 lr:5.5830778093617274e-05 tokens_per_second_per_gpu:176.0171157290441 mfu:2.904545059561363 
Step 2690 | loss:1.1976368427276611 lr:5.576261155739313e-05 tokens_per_second_per_gpu:250.7357471799772 mfu:4.137513972494093 
Step 2691 | loss:1.2779629230499268 lr:5.569447056866024e-05 tokens_per_second_per_gpu:241.89147207543053 mfu:3.991570235977828 
Step 2692 | loss:1.286238431930542 lr:5.562635516677075e-05 tokens_per_second_per_gpu:189.19686619391223 mfu:3.1220306088525653 
Step 2693 | loss:1.2457661628723145 lr:5.55582653910619e-05 tokens_per_second_per_gpu:207.76242490009454 mfu:3.428390030745651 
Step 2694 | loss:1.2478997707366943 lr:5.549020128085608e-05 tokens_per_second_per_gpu:199.840639558559 mfu:3.2976687518441015 
Step 2695 | loss:1.2424325942993164 lr:5.5422162875461e-05 tokens_per_second_per_gpu:182.25420839902145 mfu:3.007466395509716 
Step 2696 | loss:1.0762951374053955 lr:5.535415021416945e-05 tokens_per_second_per_gpu:239.37406449494034 mfu:3.9500292544628772 
Step 2697 | loss:1.4007210731506348 lr:5.528616333625933e-05 tokens_per_second_per_gpu:173.33708209007426 mfu:2.8603205054133958 
Step 2698 | loss:1.130561351776123 lr:5.5218202280993725e-05 tokens_per_second_per_gpu:290.6677752960179 mfu:4.796452022366781 
Step 2699 | loss:1.2493255138397217 lr:5.515026708762064e-05 tokens_per_second_per_gpu:309.63818393372884 mfu:5.109492072240927 
Step 2700 | loss:1.3156191110610962 lr:5.5082357795373386e-05 tokens_per_second_per_gpu:234.89343907773892 mfu:3.876092249158739 
Step 2701 | loss:1.1934502124786377 lr:5.501447444347019e-05 tokens_per_second_per_gpu:265.646807312021 mfu:4.383568714727343 
Step 2702 | loss:1.1222549676895142 lr:5.494661707111417e-05 tokens_per_second_per_gpu:211.84103915673634 mfu:3.4956932520256863 
Step 2703 | loss:1.3033075332641602 lr:5.48787857174937e-05 tokens_per_second_per_gpu:235.51357020196457 mfu:3.886325338058585 
Step 2704 | loss:1.2702945470809937 lr:5.481098042178195e-05 tokens_per_second_per_gpu:156.7417534145622 mfu:2.5864728189733097 
Step 2705 | loss:1.3889461755752563 lr:5.474320122313712e-05 tokens_per_second_per_gpu:195.67986167308771 mfu:3.2290097080850764 
Step 2706 | loss:1.162056565284729 lr:5.4675448160702316e-05 tokens_per_second_per_gpu:301.8062621920171 mfu:4.980253676829551 
Step 2707 | loss:1.351730465888977 lr:5.460772127360544e-05 tokens_per_second_per_gpu:325.77224983680935 mfu:5.37572823464668 
Step 2708 | loss:1.1397230625152588 lr:5.45400206009595e-05 tokens_per_second_per_gpu:249.1155916393873 mfu:4.110778988503188 
Step 2709 | loss:1.2837610244750977 lr:5.44723461818622e-05 tokens_per_second_per_gpu:264.4041881726807 mfu:4.363063644711065 
Step 2710 | loss:1.0872583389282227 lr:5.440469805539613e-05 tokens_per_second_per_gpu:279.03593050540894 mfu:4.604509226461887 
Step 2711 | loss:1.082276701927185 lr:5.43370762606287e-05 tokens_per_second_per_gpu:231.59879950360545 mfu:3.8217257799750506 
Step 2712 | loss:1.4297168254852295 lr:5.4269480836612095e-05 tokens_per_second_per_gpu:216.03430522912612 mfu:3.564888399347239 
Step 2713 | loss:1.1055185794830322 lr:5.42019118223833e-05 tokens_per_second_per_gpu:192.04410902072632 mfu:3.1690143641069404 
Step 2714 | loss:1.215857982635498 lr:5.413436925696404e-05 tokens_per_second_per_gpu:265.66956252725936 mfu:4.383944209733759 
Step 2715 | loss:1.3045426607131958 lr:5.406685317936069e-05 tokens_per_second_per_gpu:271.248286467838 mfu:4.476001479239343 
Step 2716 | loss:1.318794846534729 lr:5.399936362856446e-05 tokens_per_second_per_gpu:274.5833923639391 mfu:4.531035703118721 
Step 2717 | loss:1.20625901222229 lr:5.393190064355117e-05 tokens_per_second_per_gpu:239.901874736024 mfu:3.9587389110310793 
Step 2718 | loss:1.1010539531707764 lr:5.3864464263281286e-05 tokens_per_second_per_gpu:275.45706786091677 mfu:4.545452652503988 
Step 2719 | loss:1.213428020477295 lr:5.379705452669993e-05 tokens_per_second_per_gpu:218.99680368004616 mfu:3.613774044382031 
Step 2720 | loss:1.1592729091644287 lr:5.372967147273683e-05 tokens_per_second_per_gpu:227.91808714272523 mfu:3.760988533718168 
Step 2721 | loss:1.165065884590149 lr:5.366231514030633e-05 tokens_per_second_per_gpu:287.1035122778335 mfu:4.737636364028297 
Step 2722 | loss:1.2320297956466675 lr:5.3594985568307286e-05 tokens_per_second_per_gpu:241.05065624851 mfu:3.977695520181197 
Step 2723 | loss:1.2307908535003662 lr:5.3527682795623146e-05 tokens_per_second_per_gpu:295.2714932000542 mfu:4.872420237380409 
Step 2724 | loss:1.1314467191696167 lr:5.3460406861121894e-05 tokens_per_second_per_gpu:229.9187233100339 mfu:3.794002015797272 
Step 2725 | loss:1.206990361213684 lr:5.3393157803655954e-05 tokens_per_second_per_gpu:269.23545197348665 mfu:4.442786706561881 
Step 2726 | loss:1.186293601989746 lr:5.332593566206229e-05 tokens_per_second_per_gpu:306.70727452764567 mfu:5.0611276935826295 
Step 2727 | loss:1.2425220012664795 lr:5.325874047516228e-05 tokens_per_second_per_gpu:305.7746901103508 mfu:5.045738659109144 
Step 2728 | loss:1.288543701171875 lr:5.319157228176176e-05 tokens_per_second_per_gpu:217.52314716506368 mfu:3.5894565129172404 
Step 2729 | loss:1.1495306491851807 lr:5.3124431120650953e-05 tokens_per_second_per_gpu:223.7651195176986 mfu:3.6924583709108307 
Step 2730 | loss:1.0732340812683105 lr:5.305731703060451e-05 tokens_per_second_per_gpu:301.90327965403833 mfu:4.981854609720866 
Step 2731 | loss:1.0973877906799316 lr:5.299023005038142e-05 tokens_per_second_per_gpu:353.77848209508653 mfu:5.837872857377164 
Step 2732 | loss:1.286942958831787 lr:5.2923170218724994e-05 tokens_per_second_per_gpu:293.0813056477955 mfu:4.836278874603971 
Step 2733 | loss:1.274891972541809 lr:5.2856137574362916e-05 tokens_per_second_per_gpu:216.32425966266968 mfu:3.5696730801662526 
Step 2734 | loss:1.369296669960022 lr:5.278913215600714e-05 tokens_per_second_per_gpu:222.62573768361105 mfu:3.6736568704803423 
Step 2735 | loss:1.1459782123565674 lr:5.272215400235389e-05 tokens_per_second_per_gpu:207.0573811638125 mfu:3.4167557570415807 
Step 2736 | loss:1.180095911026001 lr:5.265520315208367e-05 tokens_per_second_per_gpu:232.04419625715056 mfu:3.8290754910227283 
Step 2737 | loss:1.0850119590759277 lr:5.2588279643861194e-05 tokens_per_second_per_gpu:279.61797090817913 mfu:4.61411376161933 
Step 2738 | loss:1.2929320335388184 lr:5.2521383516335376e-05 tokens_per_second_per_gpu:186.43189085768384 mfu:3.076404389951138 
Step 2739 | loss:1.1472811698913574 lr:5.245451480813935e-05 tokens_per_second_per_gpu:236.09226241838067 mfu:3.895874623145073 
Step 2740 | loss:1.2059822082519531 lr:5.23876735578904e-05 tokens_per_second_per_gpu:227.63386063246918 mfu:3.7562983721805177 
Step 2741 | loss:1.1647194623947144 lr:5.232085980418995e-05 tokens_per_second_per_gpu:226.60754999944308 mfu:3.7393627152906497 
Step 2742 | loss:1.1730875968933105 lr:5.225407358562354e-05 tokens_per_second_per_gpu:231.72501979203972 mfu:3.8238086030781893 
Step 2743 | loss:1.5081408023834229 lr:5.218731494076082e-05 tokens_per_second_per_gpu:307.0795702401203 mfu:5.067271128372396 
Step 2744 | loss:1.2842085361480713 lr:5.2120583908155506e-05 tokens_per_second_per_gpu:293.2590366761558 mfu:4.839211701779422 
Step 2745 | loss:1.2192139625549316 lr:5.205388052634539e-05 tokens_per_second_per_gpu:224.1752032302186 mfu:3.6992253640880177 
Step 2746 | loss:1.3255316019058228 lr:5.198720483385224e-05 tokens_per_second_per_gpu:196.6718691008038 mfu:3.245379310900614 
Step 2747 | loss:1.2724429368972778 lr:5.1920556869181915e-05 tokens_per_second_per_gpu:263.8353759974321 mfu:4.353677395046687 
Step 2748 | loss:1.337280035018921 lr:5.185393667082417e-05 tokens_per_second_per_gpu:198.07502038363853 mfu:3.268533400828144 
Step 2749 | loss:1.228194236755371 lr:5.17873442772528e-05 tokens_per_second_per_gpu:239.2051251012224 mfu:3.947241502377767 
Step 2750 | loss:1.3236687183380127 lr:5.172077972692553e-05 tokens_per_second_per_gpu:214.95472451366027 mfu:3.5470737066083182 
Step 2751 | loss:1.2582250833511353 lr:5.1654243058283946e-05 tokens_per_second_per_gpu:243.53773703417937 mfu:4.018736064328428 
Step 2752 | loss:1.1656339168548584 lr:5.1587734309753613e-05 tokens_per_second_per_gpu:283.02492054161775 mfu:4.670333514368896 
Step 2753 | loss:1.2657763957977295 lr:5.1521253519743905e-05 tokens_per_second_per_gpu:229.34100616642436 mfu:3.78446882086708 
Step 2754 | loss:1.233065128326416 lr:5.14548007266481e-05 tokens_per_second_per_gpu:258.1208304972821 mfu:4.259378867137333 
Step 2755 | loss:1.1393320560455322 lr:5.1388375968843274e-05 tokens_per_second_per_gpu:225.5270610834489 mfu:3.7215330358878087 
Step 2756 | loss:1.1382694244384766 lr:5.132197928469034e-05 tokens_per_second_per_gpu:221.63861383436597 mfu:3.657367853996777 
Step 2757 | loss:1.0463746786117554 lr:5.125561071253395e-05 tokens_per_second_per_gpu:257.3984724474409 mfu:4.247458881423385 
Step 2758 | loss:1.1375820636749268 lr:5.1189270290702594e-05 tokens_per_second_per_gpu:224.96863316774716 mfu:3.7123181420011853 
Step 2759 | loss:1.4493144750595093 lr:5.112295805750843e-05 tokens_per_second_per_gpu:199.89322266340636 mfu:3.2985364515377826 
Step 2760 | loss:1.2130497694015503 lr:5.105667405124739e-05 tokens_per_second_per_gpu:261.61805960573685 mfu:4.317088365938308 
Step 2761 | loss:1.1780918836593628 lr:5.099041831019905e-05 tokens_per_second_per_gpu:227.3824218088056 mfu:3.752149256396924 
Step 2762 | loss:1.3106307983398438 lr:5.092419087262681e-05 tokens_per_second_per_gpu:235.6722490285548 mfu:3.8889437754754277 
Step 2763 | loss:1.1233642101287842 lr:5.08579917767775e-05 tokens_per_second_per_gpu:275.0637930886818 mfu:4.538963031923545 
Step 2764 | loss:1.168611764907837 lr:5.0791821060881714e-05 tokens_per_second_per_gpu:234.67583692528694 mfu:3.872501488940697 
Step 2765 | loss:1.2906941175460815 lr:5.0725678763153674e-05 tokens_per_second_per_gpu:271.73751524577676 mfu:4.484074484094989 
Step 2766 | loss:1.0817439556121826 lr:5.065956492179113e-05 tokens_per_second_per_gpu:255.09053174856524 mfu:4.209374416018331 
Step 2767 | loss:1.3461947441101074 lr:5.059347957497542e-05 tokens_per_second_per_gpu:219.83143534036947 mfu:3.6275467122018887 
Step 2768 | loss:1.0989524126052856 lr:5.0527422760871435e-05 tokens_per_second_per_gpu:324.1347066176599 mfu:5.348706328013915 
Step 2769 | loss:1.4972341060638428 lr:5.046139451762755e-05 tokens_per_second_per_gpu:224.95168734985518 mfu:3.7120385107196787 
Step 2770 | loss:1.1891460418701172 lr:5.039539488337579e-05 tokens_per_second_per_gpu:236.43275903601338 mfu:3.901493325419827 
Step 2771 | loss:1.182318925857544 lr:5.032942389623141e-05 tokens_per_second_per_gpu:277.2095389184473 mfu:4.574371039963593 
Step 2772 | loss:1.0985959768295288 lr:5.026348159429328e-05 tokens_per_second_per_gpu:242.82672172993418 mfu:4.007003250842284 
Step 2773 | loss:1.009604811668396 lr:5.019756801564372e-05 tokens_per_second_per_gpu:286.467678114406 mfu:4.727144151549786 
Step 2774 | loss:1.3554140329360962 lr:5.013168319834832e-05 tokens_per_second_per_gpu:216.44649666041795 mfu:3.5716901730292667 
Step 2775 | loss:1.3395065069198608 lr:5.0065827180456315e-05 tokens_per_second_per_gpu:233.36697393498923 mfu:3.8509032965355674 
Step 2776 | loss:1.1953788995742798 lr:5.000000000000002e-05 tokens_per_second_per_gpu:245.0668590374189 mfu:4.043968859114209 
Step 2777 | loss:1.220269799232483 lr:4.993420169499523e-05 tokens_per_second_per_gpu:260.642440907355 mfu:4.300989201611796 
Step 2778 | loss:1.0728496313095093 lr:4.986843230344117e-05 tokens_per_second_per_gpu:273.49975858170677 mfu:4.513154128730228 
Step 2779 | loss:1.051757574081421 lr:4.9802691863320136e-05 tokens_per_second_per_gpu:237.8381447408647 mfu:3.9246842866448013 
Step 2780 | loss:1.1441670656204224 lr:4.973698041259789e-05 tokens_per_second_per_gpu:263.8712458171833 mfu:4.354269300596975 
Step 2781 | loss:1.2086362838745117 lr:4.967129798922335e-05 tokens_per_second_per_gpu:220.58366512993592 mfu:3.639959626195455 
Step 2782 | loss:1.5352929830551147 lr:4.960564463112871e-05 tokens_per_second_per_gpu:197.92171923577393 mfu:3.266003703134764 
Step 2783 | loss:1.279843807220459 lr:4.954002037622947e-05 tokens_per_second_per_gpu:236.52867750229453 mfu:3.9030761232415254 
Step 2784 | loss:1.263898491859436 lr:4.947442526242412e-05 tokens_per_second_per_gpu:245.4629119146919 mfu:4.0505043225732225 
Step 2785 | loss:1.1998316049575806 lr:4.9408859327594426e-05 tokens_per_second_per_gpu:362.35149197271573 mfu:5.979340312871493 
Step 2786 | loss:1.2965524196624756 lr:4.9343322609605424e-05 tokens_per_second_per_gpu:239.80313346678508 mfu:3.9571095327484342 
Step 2787 | loss:1.102632999420166 lr:4.9277815146305005e-05 tokens_per_second_per_gpu:174.6312838705481 mfu:2.8816767659791998 
Step 2788 | loss:1.1501965522766113 lr:4.9212336975524486e-05 tokens_per_second_per_gpu:283.17501013779605 mfu:4.672810216667224 
Step 2789 | loss:1.2705507278442383 lr:4.914688813507797e-05 tokens_per_second_per_gpu:245.11307302972784 mfu:4.044731458947114 
Step 2790 | loss:1.0694137811660767 lr:4.908146866276277e-05 tokens_per_second_per_gpu:249.45517960933964 mfu:4.116382696735346 
Step 2791 | loss:1.1145612001419067 lr:4.901607859635934e-05 tokens_per_second_per_gpu:315.63203006581216 mfu:5.208399477345288 
Step 2792 | loss:1.0415358543395996 lr:4.895071797363089e-05 tokens_per_second_per_gpu:199.3460398856 mfu:3.289507119206255 
Step 2793 | loss:1.0525399446487427 lr:4.88853868323238e-05 tokens_per_second_per_gpu:220.21714613987828 mfu:3.6339115159455058 
Step 2794 | loss:1.2284244298934937 lr:4.8820085210167485e-05 tokens_per_second_per_gpu:261.4452509766976 mfu:4.314236765696783 
Step 2795 | loss:1.2003971338272095 lr:4.875481314487409e-05 tokens_per_second_per_gpu:296.353482529863 mfu:4.890274675850087 
Step 2796 | loss:1.2780911922454834 lr:4.868957067413896e-05 tokens_per_second_per_gpu:230.5024555631204 mfu:3.8036344690094865 
Step 2797 | loss:1.0540426969528198 lr:4.8624357835640114e-05 tokens_per_second_per_gpu:359.7731225846263 mfu:5.936793370564883 
Step 2798 | loss:1.0921872854232788 lr:4.855917466703853e-05 tokens_per_second_per_gpu:215.51075357056794 mfu:3.556249015745299 
Step 2799 | loss:1.207889199256897 lr:4.849402120597821e-05 tokens_per_second_per_gpu:379.8775672491639 mfu:6.268546707072784 
Step 2800 | loss:0.9857535362243652 lr:4.84288974900857e-05 tokens_per_second_per_gpu:284.88585201869324 mfu:4.701041660593962 
Step 2801 | loss:1.3838634490966797 lr:4.836380355697067e-05 tokens_per_second_per_gpu:251.81075794995016 mfu:4.155253254313179 
Step 2802 | loss:1.1152868270874023 lr:4.829873944422544e-05 tokens_per_second_per_gpu:340.18608308671213 mfu:5.613577991370301 
Step 2803 | loss:1.2255260944366455 lr:4.823370518942499e-05 tokens_per_second_per_gpu:225.1077227313925 mfu:3.71461332734864 
Step 2804 | loss:1.0173041820526123 lr:4.816870083012738e-05 tokens_per_second_per_gpu:293.6752314744642 mfu:4.8460795369909855 
Step 2805 | loss:1.0980780124664307 lr:4.810372640387304e-05 tokens_per_second_per_gpu:261.0025088191923 mfu:4.30693085944491 
Step 2806 | loss:1.0957014560699463 lr:4.80387819481854e-05 tokens_per_second_per_gpu:288.61964699406496 mfu:4.762654849199015 
Step 2807 | loss:0.9975846409797668 lr:4.7973867500570466e-05 tokens_per_second_per_gpu:238.63146466357082 mfu:3.937775249149236 
Step 2808 | loss:1.3408936262130737 lr:4.790898309851682e-05 tokens_per_second_per_gpu:289.00097830226247 mfu:4.768947384800985 
Step 2809 | loss:1.1385576725006104 lr:4.784412877949591e-05 tokens_per_second_per_gpu:237.30863944441128 mfu:3.9159466591336627 
Step 2810 | loss:1.244828224182129 lr:4.777930458096167e-05 tokens_per_second_per_gpu:368.6469065584468 mfu:6.083224047456848 
Step 2811 | loss:1.382637858390808 lr:4.7714510540350546e-05 tokens_per_second_per_gpu:361.73487412424373 mfu:5.9691651982640375 
Step 2812 | loss:1.125129222869873 lr:4.764974669508184e-05 tokens_per_second_per_gpu:304.1912140815675 mfu:5.019608941795651 
Step 2813 | loss:1.2830466032028198 lr:4.758501308255712e-05 tokens_per_second_per_gpu:256.05089896962716 mfu:4.225221908211045 
Step 2814 | loss:1.1500779390335083 lr:4.752030974016072e-05 tokens_per_second_per_gpu:254.56061890248523 mfu:4.200630063330215 
Step 2815 | loss:1.2102386951446533 lr:4.7455636705259424e-05 tokens_per_second_per_gpu:253.35336525703252 mfu:4.180708576734928 
Step 2816 | loss:1.0464963912963867 lr:4.7390994015202376e-05 tokens_per_second_per_gpu:325.00831556993097 mfu:5.363122179312227 
Step 2817 | loss:1.231006383895874 lr:4.732638170732141e-05 tokens_per_second_per_gpu:241.07077737037713 mfu:3.9780275487164336 
Step 2818 | loss:1.1198575496673584 lr:4.726179981893071e-05 tokens_per_second_per_gpu:197.70347074102696 mfu:3.2624022773043926 
Step 2819 | loss:1.1299360990524292 lr:4.719724838732686e-05 tokens_per_second_per_gpu:185.529363891454 mfu:3.061511348271492 
Step 2820 | loss:1.2136156558990479 lr:4.713272744978898e-05 tokens_per_second_per_gpu:209.9815901048068 mfu:3.4650095680275803 
Step 2821 | loss:1.3531526327133179 lr:4.7068237043578347e-05 tokens_per_second_per_gpu:250.82341374481246 mfu:4.138960601628574 
Step 2822 | loss:1.3304059505462646 lr:4.700377720593887e-05 tokens_per_second_per_gpu:228.92795272971225 mfu:3.777652822809347 
Step 2823 | loss:1.3072081804275513 lr:4.693934797409671e-05 tokens_per_second_per_gpu:225.18947475273762 mfu:3.715962357689943 
Step 2824 | loss:1.2901108264923096 lr:4.687494938526018e-05 tokens_per_second_per_gpu:196.55305721513622 mfu:3.243418737497831 
Step 2825 | loss:1.1495327949523926 lr:4.6810581476620184e-05 tokens_per_second_per_gpu:242.010871240138 mfu:3.993540500361097 
Step 2826 | loss:1.1164886951446533 lr:4.674624428534974e-05 tokens_per_second_per_gpu:347.8134531437415 mfu:5.73944097875554 
Step 2827 | loss:1.1301145553588867 lr:4.668193784860414e-05 tokens_per_second_per_gpu:281.1244979811324 mfu:4.63897370633958 
Step 2828 | loss:1.0407600402832031 lr:4.661766220352097e-05 tokens_per_second_per_gpu:321.6279823591529 mfu:5.3073416372531765 
Step 2829 | loss:1.1103630065917969 lr:4.6553417387219886e-05 tokens_per_second_per_gpu:262.7883413098631 mfu:4.336399760332746 
Step 2830 | loss:1.1361782550811768 lr:4.6489203436802975e-05 tokens_per_second_per_gpu:195.8299378191561 mfu:3.2314861884365214 
Step 2831 | loss:1.358534574508667 lr:4.6425020389354325e-05 tokens_per_second_per_gpu:218.7039932054954 mfu:3.6089422346246587 
Step 2832 | loss:1.3511943817138672 lr:4.636086828194022e-05 tokens_per_second_per_gpu:211.4959011776997 mfu:3.489997960361999 
Step 2833 | loss:1.2526562213897705 lr:4.6296747151609074e-05 tokens_per_second_per_gpu:240.66229356242602 mfu:3.9712869563519866 
Step 2834 | loss:1.2368584871292114 lr:4.623265703539146e-05 tokens_per_second_per_gpu:207.47488446574238 mfu:3.423645184515428 
Step 2835 | loss:1.0695278644561768 lr:4.6168597970299953e-05 tokens_per_second_per_gpu:320.3219196246725 mfu:5.28578965324753 
Step 2836 | loss:1.2883586883544922 lr:4.6104569993329294e-05 tokens_per_second_per_gpu:223.33991389235362 mfu:3.685441843607346 
Step 2837 | loss:1.1768184900283813 lr:4.604057314145611e-05 tokens_per_second_per_gpu:283.51339280713484 mfu:4.678394035640727 
Step 2838 | loss:1.120491623878479 lr:4.597660745163928e-05 tokens_per_second_per_gpu:275.24998265801867 mfu:4.542035437646815 
Step 2839 | loss:1.2871713638305664 lr:4.591267296081951e-05 tokens_per_second_per_gpu:254.90475546037 mfu:4.206308830050592 
Step 2840 | loss:1.306581974029541 lr:4.584876970591957e-05 tokens_per_second_per_gpu:294.5806120480249 mfu:4.861019667449699 
Step 2841 | loss:1.0676777362823486 lr:4.578489772384414e-05 tokens_per_second_per_gpu:323.4173161359415 mfu:5.336868314586522 
Step 2842 | loss:1.0864149332046509 lr:4.57210570514799e-05 tokens_per_second_per_gpu:234.9321322061 mfu:3.876730743513987 
Step 2843 | loss:1.1787339448928833 lr:4.5657247725695385e-05 tokens_per_second_per_gpu:225.159216238841 mfu:3.7154630470593597 
Step 2844 | loss:1.2480475902557373 lr:4.5593469783341055e-05 tokens_per_second_per_gpu:225.6851833271672 mfu:3.7241422888567404 
Step 2845 | loss:1.0541679859161377 lr:4.552972326124928e-05 tokens_per_second_per_gpu:292.929961876926 mfu:4.833781476551777 
Step 2846 | loss:1.0927976369857788 lr:4.546600819623422e-05 tokens_per_second_per_gpu:253.14673304544897 mfu:4.177298836910394 
Step 2847 | loss:1.2166787385940552 lr:4.540232462509192e-05 tokens_per_second_per_gpu:285.5730300729239 mfu:4.712381123885288 
Step 2848 | loss:1.2381209135055542 lr:4.533867258460021e-05 tokens_per_second_per_gpu:254.73933149777778 mfu:4.2035790878247274 
Step 2849 | loss:1.2043341398239136 lr:4.527505211151871e-05 tokens_per_second_per_gpu:267.51419072960044 mfu:4.414383327598211 
Step 2850 | loss:1.3272348642349243 lr:4.521146324258884e-05 tokens_per_second_per_gpu:211.64633066303875 mfu:3.4924802713386573 
Step 2851 | loss:1.1692649126052856 lr:4.5147906014533715e-05 tokens_per_second_per_gpu:219.36397793964613 mfu:3.6198329675572123 
Step 2852 | loss:1.1726032495498657 lr:4.508438046405823e-05 tokens_per_second_per_gpu:373.5306153444491 mfu:6.163812529821001 
Step 2853 | loss:1.387345790863037 lr:4.5020886627848965e-05 tokens_per_second_per_gpu:221.05428167121397 mfu:3.6477255013733054 
Step 2854 | loss:1.2096763849258423 lr:4.495742454257418e-05 tokens_per_second_per_gpu:302.50100034897537 mfu:4.991717893096952 
Step 2855 | loss:1.3408005237579346 lr:4.4893994244883796e-05 tokens_per_second_per_gpu:208.2238375458802 mfu:3.4360040279139654 
Step 2856 | loss:1.209010362625122 lr:4.483059577140939e-05 tokens_per_second_per_gpu:336.60040112415726 mfu:5.554408888488684 
Step 2857 | loss:1.114023208618164 lr:4.476722915876415e-05 tokens_per_second_per_gpu:281.2999471663595 mfu:4.641868879698403 
Step 2858 | loss:1.2136497497558594 lr:4.470389444354286e-05 tokens_per_second_per_gpu:244.43618757190646 mfu:4.033561838854994 
Step 2859 | loss:1.3362137079238892 lr:4.4640591662321905e-05 tokens_per_second_per_gpu:213.45986291661387 mfu:3.522406259647575 
Step 2860 | loss:1.4641544818878174 lr:4.4577320851659196e-05 tokens_per_second_per_gpu:262.6154616478292 mfu:4.333546987940815 
Step 2861 | loss:1.1949433088302612 lr:4.451408204809422e-05 tokens_per_second_per_gpu:259.4188470219675 mfu:4.280798076674931 
Step 2862 | loss:1.136224627494812 lr:4.4450875288147934e-05 tokens_per_second_per_gpu:180.80839664193738 mfu:2.983608344099768 
Step 2863 | loss:1.2801748514175415 lr:4.438770060832282e-05 tokens_per_second_per_gpu:219.02423008597933 mfu:3.61422662100519 
Step 2864 | loss:1.0667753219604492 lr:4.432455804510285e-05 tokens_per_second_per_gpu:279.2251834106312 mfu:4.607632181798328 
Step 2865 | loss:1.255608320236206 lr:4.426144763495338e-05 tokens_per_second_per_gpu:250.97555539542395 mfu:4.1414711658870935 
Step 2866 | loss:1.2935909032821655 lr:4.419836941432127e-05 tokens_per_second_per_gpu:208.7247035677415 mfu:3.4442690646592493 
Step 2867 | loss:1.1977201700210571 lr:4.4135323419634766e-05 tokens_per_second_per_gpu:210.84640558925224 mfu:3.4792803139852913 
Step 2868 | loss:1.0956294536590576 lr:4.407230968730348e-05 tokens_per_second_per_gpu:262.4648133923912 mfu:4.3310610669310785 
Step 2869 | loss:1.3526206016540527 lr:4.400932825371843e-05 tokens_per_second_per_gpu:206.4551316610151 mfu:3.4068177415779806 
Step 2870 | loss:1.18116295337677 lr:4.394637915525195e-05 tokens_per_second_per_gpu:286.0846955116926 mfu:4.7208243671242665 
Step 2871 | loss:1.09959077835083 lr:4.3883462428257714e-05 tokens_per_second_per_gpu:272.4374285348821 mfu:4.495624097765069 
Step 2872 | loss:1.0641796588897705 lr:4.382057810907071e-05 tokens_per_second_per_gpu:247.42430864542877 mfu:4.082870295396408 
Step 2873 | loss:1.3604300022125244 lr:4.375772623400719e-05 tokens_per_second_per_gpu:158.95509648549236 mfu:2.6229962823601367 
Step 2874 | loss:1.1373939514160156 lr:4.3694906839364694e-05 tokens_per_second_per_gpu:231.9156364119224 mfu:3.8269540617414406 
Step 2875 | loss:1.3243459463119507 lr:4.363211996142196e-05 tokens_per_second_per_gpu:233.98478939483715 mfu:3.861098173517782 
Step 2876 | loss:1.1286163330078125 lr:4.356936563643901e-05 tokens_per_second_per_gpu:254.17186429612678 mfu:4.194215032231659 
Step 2877 | loss:1.1354715824127197 lr:4.350664390065701e-05 tokens_per_second_per_gpu:254.77383110185053 mfu:4.204148382771707 
Step 2878 | loss:1.3086562156677246 lr:4.344395479029835e-05 tokens_per_second_per_gpu:234.0843375250257 mfu:3.862740866210081 
Step 2879 | loss:0.9758341312408447 lr:4.338129834156652e-05 tokens_per_second_per_gpu:252.21363412616392 mfu:4.161901312386338 
Step 2880 | loss:1.2260490655899048 lr:4.3318674590646237e-05 tokens_per_second_per_gpu:308.9708106637578 mfu:5.098479417442279 
Step 2881 | loss:1.2578375339508057 lr:4.325608357370324e-05 tokens_per_second_per_gpu:276.68388313022047 mfu:4.56569693508237 
Step 2882 | loss:1.3412357568740845 lr:4.3193525326884435e-05 tokens_per_second_per_gpu:286.9557241641369 mfu:4.735197639625153 
Step 2883 | loss:1.1500078439712524 lr:4.313099988631773e-05 tokens_per_second_per_gpu:316.4665243838981 mfu:5.222169878813289 
Step 2884 | loss:0.9469707608222961 lr:4.3068507288112214e-05 tokens_per_second_per_gpu:220.1830832752071 mfu:3.6333494278503484 
Step 2885 | loss:1.2731221914291382 lr:4.300604756835786e-05 tokens_per_second_per_gpu:248.4455585716933 mfu:4.099722443073201 
Step 2886 | loss:1.1050357818603516 lr:4.294362076312572e-05 tokens_per_second_per_gpu:313.50578380296344 mfu:5.173313241256321 
Step 2887 | loss:1.3060473203659058 lr:4.2881226908467864e-05 tokens_per_second_per_gpu:258.16545693706894 mfu:4.260115269984703 
Step 2888 | loss:1.1803293228149414 lr:4.281886604041729e-05 tokens_per_second_per_gpu:275.84132240663007 mfu:4.551793425886978 
Step 2889 | loss:1.2265349626541138 lr:4.275653819498798e-05 tokens_per_second_per_gpu:332.88476884184524 mfu:5.4930954114212085 
Step 2890 | loss:1.4000288248062134 lr:4.2694243408174816e-05 tokens_per_second_per_gpu:295.68534998989963 mfu:4.879249491963594 
Step 2891 | loss:1.542600154876709 lr:4.2631981715953564e-05 tokens_per_second_per_gpu:189.91885817842243 mfu:3.133944553942315 
Step 2892 | loss:1.1370396614074707 lr:4.2569753154281026e-05 tokens_per_second_per_gpu:238.84301581640548 mfu:3.941266158844384 
Step 2893 | loss:1.2263034582138062 lr:4.250755775909464e-05 tokens_per_second_per_gpu:221.20521867701274 mfu:3.650216187194863 
Step 2894 | loss:1.1227121353149414 lr:4.244539556631285e-05 tokens_per_second_per_gpu:283.2312024836237 mfu:4.673737474222734 
Step 2895 | loss:0.990052342414856 lr:4.238326661183488e-05 tokens_per_second_per_gpu:253.8316962142807 mfu:4.188601751287619 
Step 2896 | loss:1.070063591003418 lr:4.232117093154074e-05 tokens_per_second_per_gpu:252.42738539136303 mfu:4.165428527218473 
Step 2897 | loss:1.1803009510040283 lr:4.225910856129135e-05 tokens_per_second_per_gpu:303.13043834946006 mfu:5.0021045593426505 
Step 2898 | loss:1.1584038734436035 lr:4.2197079536928173e-05 tokens_per_second_per_gpu:254.450045206502 mfu:4.198805432350124 
Step 2899 | loss:1.2196998596191406 lr:4.213508389427353e-05 tokens_per_second_per_gpu:242.18260306362416 mfu:3.9963743317042044 
Step 2900 | loss:1.1357202529907227 lr:4.2073121669130576e-05 tokens_per_second_per_gpu:291.5209338123426 mfu:4.810530410956151 
Step 2901 | loss:1.1738921403884888 lr:4.201119289728296e-05 tokens_per_second_per_gpu:294.75506453804314 mfu:4.863898393850322 
Step 2902 | loss:1.4562232494354248 lr:4.194929761449512e-05 tokens_per_second_per_gpu:219.2072972053865 mfu:3.617247501645347 
Step 2903 | loss:1.2638468742370605 lr:4.188743585651216e-05 tokens_per_second_per_gpu:274.10571765990704 mfu:4.523153357723347 
Step 2904 | loss:1.000537395477295 lr:4.182560765905975e-05 tokens_per_second_per_gpu:258.7574225465771 mfu:4.269883585863563 
Step 2905 | loss:1.328070878982544 lr:4.176381305784436e-05 tokens_per_second_per_gpu:340.563192186919 mfu:5.619800854240111 
Step 2906 | loss:1.1635246276855469 lr:4.170205208855281e-05 tokens_per_second_per_gpu:338.53139130441843 mfu:5.586273107856833 
Step 2907 | loss:1.192124843597412 lr:4.1640324786852626e-05 tokens_per_second_per_gpu:318.21537499968315 mfu:5.251028523581725 
Step 2908 | loss:1.373339056968689 lr:4.157863118839198e-05 tokens_per_second_per_gpu:177.03114811249915 mfu:2.9212781070118936 
Step 2909 | loss:1.4527063369750977 lr:4.1516971328799335e-05 tokens_per_second_per_gpu:230.76332834801372 mfu:3.8079392592305825 
Step 2910 | loss:1.1428569555282593 lr:4.1455345243683985e-05 tokens_per_second_per_gpu:306.3756527780751 mfu:5.055655439873843 
Step 2911 | loss:1.3218159675598145 lr:4.1393752968635415e-05 tokens_per_second_per_gpu:320.1137144468064 mfu:5.282353957132177 
Step 2912 | loss:1.0557254552841187 lr:4.1332194539223736e-05 tokens_per_second_per_gpu:196.03293708702478 mfu:3.234835979268739 
Step 2913 | loss:0.9318742752075195 lr:4.1270669990999586e-05 tokens_per_second_per_gpu:206.26387085588715 mfu:3.403661652896939 
Step 2914 | loss:1.0985480546951294 lr:4.1209179359493876e-05 tokens_per_second_per_gpu:213.15440771029668 mfu:3.517365792947782 
Step 2915 | loss:1.1171867847442627 lr:4.114772268021796e-05 tokens_per_second_per_gpu:226.3562144697556 mfu:3.7352153040117955 
Step 2916 | loss:1.1305913925170898 lr:4.1086299988663765e-05 tokens_per_second_per_gpu:305.3595882097655 mfu:5.038888858340817 
Step 2917 | loss:1.1540377140045166 lr:4.1024911320303284e-05 tokens_per_second_per_gpu:175.01255093655843 mfu:2.887968241489221 
Step 2918 | loss:1.0433142185211182 lr:4.096355671058918e-05 tokens_per_second_per_gpu:208.31006649373342 mfu:3.437426934223053 
Step 2919 | loss:1.1911362409591675 lr:4.090223619495419e-05 tokens_per_second_per_gpu:249.1130666460075 mfu:4.110737322344664 
Step 2920 | loss:1.1281156539916992 lr:4.084094980881147e-05 tokens_per_second_per_gpu:264.02882917620514 mfu:4.3568696611643 
Step 2921 | loss:1.197084903717041 lr:4.077969758755455e-05 tokens_per_second_per_gpu:246.80384492169895 mfu:4.072631718108442 
Step 2922 | loss:1.2304216623306274 lr:4.071847956655701e-05 tokens_per_second_per_gpu:307.04050871221824 mfu:5.066626554875001 
Step 2923 | loss:1.0801903009414673 lr:4.0657295781172925e-05 tokens_per_second_per_gpu:271.42387361139373 mfu:4.478898929116448 
Step 2924 | loss:0.9767026901245117 lr:4.059614626673646e-05 tokens_per_second_per_gpu:396.1632813714019 mfu:6.537285291381774 
Step 2925 | loss:1.3498947620391846 lr:4.0535031058561936e-05 tokens_per_second_per_gpu:227.04384595476202 mfu:3.746562249587525 
Step 2926 | loss:1.1961125135421753 lr:4.0473950191944045e-05 tokens_per_second_per_gpu:227.848452250957 mfu:3.759839454095878 
Step 2927 | loss:1.041809320449829 lr:4.0412903702157464e-05 tokens_per_second_per_gpu:261.3196210178352 mfu:4.312163683912462 
Step 2928 | loss:0.9565403461456299 lr:4.0351891624457074e-05 tokens_per_second_per_gpu:232.71035766531688 mfu:3.8400681482932773 
Step 2929 | loss:1.362513780593872 lr:4.0290913994078016e-05 tokens_per_second_per_gpu:223.20952067435235 mfu:3.6832901609395714 
Step 2930 | loss:1.2607276439666748 lr:4.022997084623528e-05 tokens_per_second_per_gpu:249.04343063073463 mfu:4.109588224182871 
Step 2931 | loss:1.1900787353515625 lr:4.0169062216124174e-05 tokens_per_second_per_gpu:262.31080237550316 mfu:4.328519655339556 
Step 2932 | loss:1.0306448936462402 lr:4.010818813892e-05 tokens_per_second_per_gpu:257.9638946320112 mfu:4.2567891911830795 
Step 2933 | loss:1.2103288173675537 lr:4.0047348649777985e-05 tokens_per_second_per_gpu:267.3819394869286 mfu:4.412200984750856 
Step 2934 | loss:1.2671328783035278 lr:3.998654378383361e-05 tokens_per_second_per_gpu:290.4648787680978 mfu:4.793103926897021 
Step 2935 | loss:1.1294560432434082 lr:3.99257735762021e-05 tokens_per_second_per_gpu:238.58345325881314 mfu:3.936982989328855 
Step 2936 | loss:1.3857561349868774 lr:3.986503806197891e-05 tokens_per_second_per_gpu:263.3803861987455 mfu:4.346169384439581 
Step 2937 | loss:1.2056388854980469 lr:3.9804337276239334e-05 tokens_per_second_per_gpu:212.3889323584337 mfu:3.5047343074114994 
Step 2938 | loss:1.2023375034332275 lr:3.974367125403853e-05 tokens_per_second_per_gpu:240.0246580993743 mfu:3.9607650197418054 
Step 2939 | loss:1.1702296733856201 lr:3.9683040030411765e-05 tokens_per_second_per_gpu:251.71911640454405 mfu:4.153741032067874 
Step 2940 | loss:1.1244562864303589 lr:3.962244364037414e-05 tokens_per_second_per_gpu:265.44422686426265 mfu:4.380225835051903 
Step 2941 | loss:1.2882009744644165 lr:3.95618821189205e-05 tokens_per_second_per_gpu:245.64800728838534 mfu:4.053558672435634 
Step 2942 | loss:1.0836639404296875 lr:3.950135550102581e-05 tokens_per_second_per_gpu:222.98422321193772 mfu:3.679572416624323 
Step 2943 | loss:1.2010657787322998 lr:3.9440863821644594e-05 tokens_per_second_per_gpu:248.0324949258982 mfu:4.092906276550364 
Step 2944 | loss:1.261411190032959 lr:3.938040711571146e-05 tokens_per_second_per_gpu:278.1489543477611 mfu:4.589872796328522 
Step 2945 | loss:1.15804922580719 lr:3.931998541814069e-05 tokens_per_second_per_gpu:233.61257445377652 mfu:3.8549560715768725 
Step 2946 | loss:1.2551214694976807 lr:3.9259598763826265e-05 tokens_per_second_per_gpu:306.13159157198663 mfu:5.051628065789006 
Step 2947 | loss:1.1512736082077026 lr:3.919924718764213e-05 tokens_per_second_per_gpu:291.9038639589725 mfu:4.816849329778018 
Step 2948 | loss:1.315730094909668 lr:3.9138930724441816e-05 tokens_per_second_per_gpu:243.35197559221805 mfu:4.015670723345701 
Step 2949 | loss:1.250105619430542 lr:3.9078649409058634e-05 tokens_per_second_per_gpu:347.9386470837662 mfu:5.741506865578419 
Step 2950 | loss:1.1212308406829834 lr:3.9018403276305624e-05 tokens_per_second_per_gpu:186.1996218865154 mfu:3.0725716053386734 
Step 2951 | loss:1.3985886573791504 lr:3.895819236097536e-05 tokens_per_second_per_gpu:268.048563987736 mfu:4.423201283741002 
Step 2952 | loss:1.3893752098083496 lr:3.88980166978403e-05 tokens_per_second_per_gpu:212.48550279440076 mfu:3.5063278637058746 
Step 2953 | loss:1.2283995151519775 lr:3.8837876321652444e-05 tokens_per_second_per_gpu:332.8773655109467 mfu:5.4929732454142455 
Step 2954 | loss:1.115931749343872 lr:3.877777126714327e-05 tokens_per_second_per_gpu:286.4206218656344 mfu:4.726367653228444 
Step 2955 | loss:1.442158579826355 lr:3.871770156902412e-05 tokens_per_second_per_gpu:158.30548894759076 mfu:2.6122767886503864 
Step 2956 | loss:1.1303136348724365 lr:3.865766726198574e-05 tokens_per_second_per_gpu:288.6735916550265 mfu:4.763545016600273 
Step 2957 | loss:1.2768476009368896 lr:3.8597668380698495e-05 tokens_per_second_per_gpu:248.5906356823044 mfu:4.102116431880116 
Step 2958 | loss:1.108069896697998 lr:3.8537704959812294e-05 tokens_per_second_per_gpu:295.75729932003566 mfu:4.880436763272522 
Step 2959 | loss:1.4155840873718262 lr:3.847777703395646e-05 tokens_per_second_per_gpu:192.41018459889224 mfu:3.1750551573990236 
Step 2960 | loss:1.2123768329620361 lr:3.8417884637740044e-05 tokens_per_second_per_gpu:211.3837083728238 mfu:3.4881466116691695 
Step 2961 | loss:1.0778955221176147 lr:3.835802780575136e-05 tokens_per_second_per_gpu:264.4190841789607 mfu:4.363309451042277 
Step 2962 | loss:1.208883285522461 lr:3.8298206572558306e-05 tokens_per_second_per_gpu:292.12067457651773 mfu:4.820427028488981 
Step 2963 | loss:0.9483437538146973 lr:3.823842097270818e-05 tokens_per_second_per_gpu:334.104105442082 mfu:5.513216284800431 
Step 2964 | loss:1.1020236015319824 lr:3.817867104072769e-05 tokens_per_second_per_gpu:270.30774324522685 mfu:4.460481112602133 
Step 2965 | loss:1.12229323387146 lr:3.8118956811122964e-05 tokens_per_second_per_gpu:211.0848892219966 mfu:3.483215649787181 
Step 2966 | loss:1.5379538536071777 lr:3.805927831837953e-05 tokens_per_second_per_gpu:238.87974611460825 mfu:3.9418722635731154 
Step 2967 | loss:1.1012229919433594 lr:3.7999635596962235e-05 tokens_per_second_per_gpu:243.10486496695708 mfu:4.011593029294221 
Step 2968 | loss:1.1900880336761475 lr:3.79400286813153e-05 tokens_per_second_per_gpu:288.43489640161954 mfu:4.759606188741673 
Step 2969 | loss:1.0698461532592773 lr:3.7880457605862243e-05 tokens_per_second_per_gpu:198.78816419986728 mfu:3.28030133793815 
Step 2970 | loss:1.0905523300170898 lr:3.782092240500592e-05 tokens_per_second_per_gpu:279.829157136583 mfu:4.617598649516834 
Step 2971 | loss:1.2191002368927002 lr:3.776142311312842e-05 tokens_per_second_per_gpu:219.3801027360572 mfu:3.620099050759168 
Step 2972 | loss:1.3620322942733765 lr:3.7701959764591156e-05 tokens_per_second_per_gpu:300.8818299025598 mfu:4.964999164629866 
Step 2973 | loss:1.1608860492706299 lr:3.764253239373472e-05 tokens_per_second_per_gpu:251.79183294355508 mfu:4.154940963468057 
Step 2974 | loss:1.2686697244644165 lr:3.758314103487897e-05 tokens_per_second_per_gpu:177.70631576875823 mfu:2.9324193808149577 
Step 2975 | loss:1.239304542541504 lr:3.752378572232294e-05 tokens_per_second_per_gpu:255.95987496985174 mfu:4.223719876390139 
Step 2976 | loss:1.4139639139175415 lr:3.746446649034486e-05 tokens_per_second_per_gpu:266.30303874364836 mfu:4.394397512567641 
Step 2977 | loss:1.0892804861068726 lr:3.7405183373202146e-05 tokens_per_second_per_gpu:364.2394594876163 mfu:6.010494594063432 
Step 2978 | loss:1.1472681760787964 lr:3.73459364051313e-05 tokens_per_second_per_gpu:227.12549933288034 mfu:3.7479096521683917 
Step 2979 | loss:1.1767899990081787 lr:3.728672562034801e-05 tokens_per_second_per_gpu:211.59361806922507 mfu:3.49161043488381 
Step 2980 | loss:1.065197467803955 lr:3.722755105304702e-05 tokens_per_second_per_gpu:257.40533340510825 mfu:4.247572097462712 
Step 2981 | loss:1.1610143184661865 lr:3.716841273740218e-05 tokens_per_second_per_gpu:341.5245713657594 mfu:5.635665045246198 
Step 2982 | loss:1.1894845962524414 lr:3.7109310707566406e-05 tokens_per_second_per_gpu:348.52957405429146 mfu:5.75125804236422 
Step 2983 | loss:1.1725590229034424 lr:3.7050244997671645e-05 tokens_per_second_per_gpu:252.39797276476585 mfu:4.16494317499055 
Step 2984 | loss:1.0097047090530396 lr:3.69912156418289e-05 tokens_per_second_per_gpu:266.8379828335294 mfu:4.40322488828602 
Step 2985 | loss:1.1146701574325562 lr:3.693222267412814e-05 tokens_per_second_per_gpu:223.01112346692486 mfu:3.6800163109717574 
Step 2986 | loss:1.2455859184265137 lr:3.687326612863833e-05 tokens_per_second_per_gpu:283.04420534922536 mfu:4.670651742470914 
Step 2987 | loss:1.389087438583374 lr:3.681434603940741e-05 tokens_per_second_per_gpu:219.69194241812536 mfu:3.6252448708356693 
Step 2988 | loss:1.2232085466384888 lr:3.675546244046228e-05 tokens_per_second_per_gpu:214.59466034455085 mfu:3.541132110535799 
Step 2989 | loss:1.2312403917312622 lr:3.669661536580874e-05 tokens_per_second_per_gpu:174.47739008443554 mfu:2.879137288870403 
Step 2990 | loss:1.1163612604141235 lr:3.663780484943151e-05 tokens_per_second_per_gpu:279.67259815411165 mfu:4.6150151926911525 
Step 2991 | loss:1.24806809425354 lr:3.657903092529419e-05 tokens_per_second_per_gpu:237.61327703985728 mfu:3.920973634034055 
Step 2992 | loss:1.0091254711151123 lr:3.652029362733924e-05 tokens_per_second_per_gpu:258.0602024944979 mfu:4.258378414623221 
Step 2993 | loss:1.1522018909454346 lr:3.6461592989488014e-05 tokens_per_second_per_gpu:232.0756559867033 mfu:3.829594623504073 
Step 2994 | loss:1.1815850734710693 lr:3.640292904564062e-05 tokens_per_second_per_gpu:359.51736246517845 mfu:5.9325729469526784 
Step 2995 | loss:1.1758716106414795 lr:3.6344301829676056e-05 tokens_per_second_per_gpu:373.79676472887655 mfu:6.1682043918080725 
Step 2996 | loss:1.313485860824585 lr:3.628571137545202e-05 tokens_per_second_per_gpu:212.37849701934437 mfu:3.504562108745073 
Step 2997 | loss:1.2639567852020264 lr:3.622715771680508e-05 tokens_per_second_per_gpu:250.7726581705164 mfu:4.138123058916001 
Step 2998 | loss:1.292245864868164 lr:3.616864088755048e-05 tokens_per_second_per_gpu:231.25471895002585 mfu:3.816047937409279 
Step 2999 | loss:1.0978504419326782 lr:3.611016092148219e-05 tokens_per_second_per_gpu:200.6900768253753 mfu:3.3116857342637913 
Step 3000 | loss:1.1248652935028076 lr:3.605171785237297e-05 tokens_per_second_per_gpu:210.7614549086102 mfu:3.477878500992599 
Step 3001 | loss:1.2013401985168457 lr:3.5993311713974185e-05 tokens_per_second_per_gpu:170.2407737424938 mfu:2.809226797414637 
Step 3002 | loss:1.1331533193588257 lr:3.5934942540015924e-05 tokens_per_second_per_gpu:224.86597004068773 mfu:3.7106240472123653 
Step 3003 | loss:1.1238988637924194 lr:3.58766103642069e-05 tokens_per_second_per_gpu:244.2916355783287 mfu:4.031176515262701 
Step 3004 | loss:1.3459911346435547 lr:3.581831522023448e-05 tokens_per_second_per_gpu:270.15776549035627 mfu:4.45800625585227 
Step 3005 | loss:1.0486546754837036 lr:3.5760057141764624e-05 tokens_per_second_per_gpu:314.82968604704723 mfu:5.195159603790265 
Step 3006 | loss:1.1649998426437378 lr:3.5701836162441915e-05 tokens_per_second_per_gpu:226.28744728894802 mfu:3.734080542915142 
Step 3007 | loss:1.1457476615905762 lr:3.564365231588949e-05 tokens_per_second_per_gpu:233.77533552659378 mfu:3.8576418721479264 
Step 3008 | loss:1.1406453847885132 lr:3.558550563570903e-05 tokens_per_second_per_gpu:287.6057134944378 mfu:4.745923433479196 
Step 3009 | loss:1.1755810976028442 lr:3.552739615548078e-05 tokens_per_second_per_gpu:156.3934864638614 mfu:2.5807258946081606 
Step 3010 | loss:1.0658104419708252 lr:3.546932390876351e-05 tokens_per_second_per_gpu:287.02691149063685 mfu:4.736372336737036 
Step 3011 | loss:1.1547825336456299 lr:3.541128892909443e-05 tokens_per_second_per_gpu:297.83386570976734 mfu:4.914703207323513 
Step 3012 | loss:1.0308771133422852 lr:3.535329124998929e-05 tokens_per_second_per_gpu:244.08867525614374 mfu:4.027827367092379 
Step 3013 | loss:1.2177231311798096 lr:3.529533090494226e-05 tokens_per_second_per_gpu:292.824744369003 mfu:4.832045230667101 
Step 3014 | loss:1.1450111865997314 lr:3.523740792742596e-05 tokens_per_second_per_gpu:211.6841739944232 mfu:3.4931047427757376 
Step 3015 | loss:1.1402804851531982 lr:3.5179522350891446e-05 tokens_per_second_per_gpu:217.0406348925987 mfu:3.5814943404241784 
Step 3016 | loss:1.2366389036178589 lr:3.5121674208768165e-05 tokens_per_second_per_gpu:232.0568051092787 mfu:3.8292835558975784 
Step 3017 | loss:1.3200058937072754 lr:3.5063863534463926e-05 tokens_per_second_per_gpu:304.93690448794035 mfu:5.031913946208556 
Step 3018 | loss:1.2914983034133911 lr:3.5006090361364885e-05 tokens_per_second_per_gpu:205.0689556525272 mfu:3.3839437690074163 
Step 3019 | loss:1.1255303621292114 lr:3.494835472283568e-05 tokens_per_second_per_gpu:318.0882460701839 mfu:5.248930706545155 
Step 3020 | loss:1.2194527387619019 lr:3.4890656652219057e-05 tokens_per_second_per_gpu:199.29782470024898 mfu:3.2887114967020055 
Step 3021 | loss:1.1033834218978882 lr:3.483299618283621e-05 tokens_per_second_per_gpu:196.2776109134969 mfu:3.2388734625040483 
Step 3022 | loss:1.128774642944336 lr:3.477537334798657e-05 tokens_per_second_per_gpu:217.8085194509366 mfu:3.594165581462278 
Step 3023 | loss:1.2006144523620605 lr:3.471778818094785e-05 tokens_per_second_per_gpu:235.08856316625122 mfu:3.879312087780355 
Step 3024 | loss:1.2197672128677368 lr:3.4660240714976025e-05 tokens_per_second_per_gpu:191.10032240612423 mfu:3.1534404766621393 
Step 3025 | loss:1.3929628133773804 lr:3.460273098330524e-05 tokens_per_second_per_gpu:292.8261374223405 mfu:4.832068218125862 
Step 3026 | loss:1.171116828918457 lr:3.454525901914787e-05 tokens_per_second_per_gpu:215.9759688388004 mfu:3.5639257618582008 
Step 3027 | loss:1.1565382480621338 lr:3.448782485569461e-05 tokens_per_second_per_gpu:254.53849938543905 mfu:4.20026505829255 
Step 3028 | loss:1.3636598587036133 lr:3.443042852611407e-05 tokens_per_second_per_gpu:169.94372369245738 mfu:2.804325028335522 
Step 3029 | loss:1.1984295845031738 lr:3.437307006355322e-05 tokens_per_second_per_gpu:304.33668111170607 mfu:5.022009364856602 
Step 3030 | loss:1.2673372030258179 lr:3.431574950113705e-05 tokens_per_second_per_gpu:253.8704331373966 mfu:4.1892409683216725 
Step 3031 | loss:1.0423779487609863 lr:3.425846687196871e-05 tokens_per_second_per_gpu:349.5175544141795 mfu:5.767561192551465 
Step 3032 | loss:2.0241994857788086 lr:3.42012222091295e-05 tokens_per_second_per_gpu:209.71452469284935 mfu:3.4606025902193838 
Step 3033 | loss:1.128671646118164 lr:3.414401554567867e-05 tokens_per_second_per_gpu:241.66907155629625 mfu:3.9879002955494784 
Step 3034 | loss:1.130916953086853 lr:3.4086846914653545e-05 tokens_per_second_per_gpu:201.23030877702115 mfu:3.320600367591755 
Step 3035 | loss:1.261817455291748 lr:3.402971634906965e-05 tokens_per_second_per_gpu:243.03251223100236 mfu:4.010399101187328 
Step 3036 | loss:1.256089448928833 lr:3.397262388192029e-05 tokens_per_second_per_gpu:301.10694094066815 mfu:4.968713832665881 
Step 3037 | loss:1.3529698848724365 lr:3.391556954617692e-05 tokens_per_second_per_gpu:270.06607621851475 mfu:4.456493246049564 
Step 3038 | loss:1.147326946258545 lr:3.385855337478894e-05 tokens_per_second_per_gpu:317.722287070575 mfu:5.24289183697322 
Step 3039 | loss:1.2184958457946777 lr:3.380157540068366e-05 tokens_per_second_per_gpu:224.84982132786152 mfu:3.7103575693538726 
Step 3040 | loss:1.261577844619751 lr:3.374463565676647e-05 tokens_per_second_per_gpu:270.7282107975959 mfu:4.467419454631435 
Step 3041 | loss:1.0880283117294312 lr:3.36877341759205e-05 tokens_per_second_per_gpu:260.8227906896647 mfu:4.303965242135077 
Step 3042 | loss:1.1027714014053345 lr:3.3630870991006866e-05 tokens_per_second_per_gpu:321.710319948841 mfu:5.308700330345915 
Step 3043 | loss:1.2582043409347534 lr:3.357404613486467e-05 tokens_per_second_per_gpu:238.80066220572215 mfu:3.940567261068703 
Step 3044 | loss:1.1853797435760498 lr:3.351725964031064e-05 tokens_per_second_per_gpu:248.23590443105263 mfu:4.096262836909946 
Step 3045 | loss:1.0742288827896118 lr:3.3460511540139615e-05 tokens_per_second_per_gpu:193.74945812487945 mfu:3.1971551690211637 
Step 3046 | loss:1.22096848487854 lr:3.3403801867124064e-05 tokens_per_second_per_gpu:264.08166315247934 mfu:4.35774150061087 
Step 3047 | loss:1.0793005228042603 lr:3.334713065401431e-05 tokens_per_second_per_gpu:271.30638624318686 mfu:4.476960212228191 
Step 3048 | loss:1.282513976097107 lr:3.3290497933538614e-05 tokens_per_second_per_gpu:205.6452964113212 mfu:3.393454251534331 
Step 3049 | loss:1.3220665454864502 lr:3.323390373840276e-05 tokens_per_second_per_gpu:310.7536038263029 mfu:5.127898164880802 
Step 3050 | loss:1.2687565088272095 lr:3.3177348101290405e-05 tokens_per_second_per_gpu:240.15412323215523 mfu:3.9629013876185697 
Step 3051 | loss:1.0889233350753784 lr:3.3120831054863064e-05 tokens_per_second_per_gpu:232.80221636573236 mfu:3.8415839539202725 
Step 3052 | loss:0.9498918056488037 lr:3.30643526317597e-05 tokens_per_second_per_gpu:241.94711491735794 mfu:3.9924884258990225 
Step 3053 | loss:1.340539813041687 lr:3.3007912864597225e-05 tokens_per_second_per_gpu:240.30714288689194 mfu:3.9654264402552997 
Step 3054 | loss:1.1277461051940918 lr:3.295151178597004e-05 tokens_per_second_per_gpu:217.78096685586118 mfu:3.5937109225299757 
Step 3055 | loss:1.3709884881973267 lr:3.2895149428450254e-05 tokens_per_second_per_gpu:218.245592624166 mfu:3.6013779410144284 
Step 3056 | loss:1.2816622257232666 lr:3.283882582458777e-05 tokens_per_second_per_gpu:232.47656372316894 mfu:3.836210199384113 
Step 3057 | loss:1.173051118850708 lr:3.2782541006909816e-05 tokens_per_second_per_gpu:270.08141645464076 mfu:4.456746382836108 
Step 3058 | loss:1.103142499923706 lr:3.272629500792149e-05 tokens_per_second_per_gpu:250.47922365179713 mfu:4.1332809514986595 
Step 3059 | loss:1.3192343711853027 lr:3.267008786010537e-05 tokens_per_second_per_gpu:197.00410000687228 mfu:3.2508616166005906 
Step 3060 | loss:1.1501615047454834 lr:3.261391959592148e-05 tokens_per_second_per_gpu:262.23515860044716 mfu:4.327271420176655 
Step 3061 | loss:1.216174840927124 lr:3.255779024780765e-05 tokens_per_second_per_gpu:269.6754044722985 mfu:4.450046579282627 
Step 3062 | loss:1.1043660640716553 lr:3.250169984817897e-05 tokens_per_second_per_gpu:353.95156005518544 mfu:5.8407289019830655 
Step 3063 | loss:1.1687142848968506 lr:3.2445648429428165e-05 tokens_per_second_per_gpu:260.84990508231067 mfu:4.304412670073415 
Step 3064 | loss:1.2077836990356445 lr:3.238963602392553e-05 tokens_per_second_per_gpu:209.2020166962684 mfu:3.4521454435192505 
Step 3065 | loss:1.2280347347259521 lr:3.233366266401859e-05 tokens_per_second_per_gpu:270.7954855771062 mfu:4.468529588879746 
Step 3066 | loss:1.190773606300354 lr:3.227772838203258e-05 tokens_per_second_per_gpu:309.02165381568045 mfu:5.099318405316372 
Step 3067 | loss:1.043773889541626 lr:3.2221833210270055e-05 tokens_per_second_per_gpu:237.51054397539409 mfu:3.919278385173714 
Step 3068 | loss:1.0759902000427246 lr:3.2165977181010874e-05 tokens_per_second_per_gpu:349.2395327733716 mfu:5.76297342061852 
Step 3069 | loss:1.2175743579864502 lr:3.2110160326512526e-05 tokens_per_second_per_gpu:280.56828850070553 mfu:4.629795419945307 
Step 3070 | loss:1.1830694675445557 lr:3.205438267900963e-05 tokens_per_second_per_gpu:259.28855664348526 mfu:4.278648091012675 
Step 3071 | loss:1.1469271183013916 lr:3.199864427071438e-05 tokens_per_second_per_gpu:282.2031180280375 mfu:4.656772546613754 
Step 3072 | loss:1.0539952516555786 lr:3.1942945133816195e-05 tokens_per_second_per_gpu:255.7675884754868 mfu:4.220546862306169 
Step 3073 | loss:1.216781497001648 lr:3.188728530048174e-05 tokens_per_second_per_gpu:209.99925204713244 mfu:3.4653010164308324 
Step 3074 | loss:1.1907565593719482 lr:3.1831664802855175e-05 tokens_per_second_per_gpu:238.4823496071959 mfu:3.935314628211857 
Step 3075 | loss:1.1211681365966797 lr:3.177608367305783e-05 tokens_per_second_per_gpu:303.5868999085752 mfu:5.009636856192967 
Step 3076 | loss:1.1037607192993164 lr:3.172054194318822e-05 tokens_per_second_per_gpu:265.8054402264038 mfu:4.386186394524254 
Step 3077 | loss:1.2335357666015625 lr:3.166503964532231e-05 tokens_per_second_per_gpu:247.36122223004088 mfu:4.081829275405929 
Step 3078 | loss:1.0652724504470825 lr:3.160957681151307e-05 tokens_per_second_per_gpu:171.70814252477365 mfu:2.833440571907377 
Step 3079 | loss:1.2950893640518188 lr:3.155415347379087e-05 tokens_per_second_per_gpu:195.3116173437529 mfu:3.222933127162529 
Step 3080 | loss:1.1083084344863892 lr:3.1498769664163195e-05 tokens_per_second_per_gpu:219.30296539682422 mfu:3.618826169558673 
Step 3081 | loss:1.3258730173110962 lr:3.1443425414614604e-05 tokens_per_second_per_gpu:230.07101479998317 mfu:3.7965150526284526 
Step 3082 | loss:1.1457722187042236 lr:3.1388120757106976e-05 tokens_per_second_per_gpu:207.8825240917312 mfu:3.4303718466178217 
Step 3083 | loss:1.0990140438079834 lr:3.133285572357923e-05 tokens_per_second_per_gpu:286.55834770876646 mfu:4.728640335152508 
Step 3084 | loss:1.100354790687561 lr:3.127763034594744e-05 tokens_per_second_per_gpu:457.7158285264119 mfu:7.552994167203341 
Step 3085 | loss:1.1077697277069092 lr:3.122244465610476e-05 tokens_per_second_per_gpu:218.68245582519975 mfu:3.6085868357120328 
Step 3086 | loss:1.4606096744537354 lr:3.1167298685921355e-05 tokens_per_second_per_gpu:272.22445587401825 mfu:4.492109731066288 
Step 3087 | loss:1.2470512390136719 lr:3.111219246724459e-05 tokens_per_second_per_gpu:245.27496348311283 mfu:4.04740289299841 
Step 3088 | loss:1.253161907196045 lr:3.105712603189884e-05 tokens_per_second_per_gpu:230.6586895656506 mfu:3.80621256318121 
Step 3089 | loss:1.0375518798828125 lr:3.100209941168534e-05 tokens_per_second_per_gpu:216.7094585272012 mfu:3.5760294362188425 
Step 3090 | loss:1.2875126600265503 lr:3.094711263838257e-05 tokens_per_second_per_gpu:240.3656321965976 mfu:3.9663916011422917 
Step 3091 | loss:1.3498634099960327 lr:3.089216574374586e-05 tokens_per_second_per_gpu:232.64239812760837 mfu:3.83894671451291 
Step 3092 | loss:1.2340723276138306 lr:3.0837258759507524e-05 tokens_per_second_per_gpu:304.04650443536553 mfu:5.017221016699811 
Step 3093 | loss:1.196290135383606 lr:3.078239171737689e-05 tokens_per_second_per_gpu:268.54018087614793 mfu:4.431313695982957 
Step 3094 | loss:1.391855001449585 lr:3.072756464904006e-05 tokens_per_second_per_gpu:122.31627765229632 mfu:2.018401099730613 
Step 3095 | loss:1.1170471906661987 lr:3.067277758616027e-05 tokens_per_second_per_gpu:194.14653635326854 mfu:3.2037075523036074 
Step 3096 | loss:1.3002982139587402 lr:3.0618030560377495e-05 tokens_per_second_per_gpu:256.58810031520665 mfu:4.234086532016691 
Step 3097 | loss:1.2591743469238281 lr:3.056332360330866e-05 tokens_per_second_per_gpu:215.2979028035739 mfu:3.5527366604772572 
Step 3098 | loss:1.223680853843689 lr:3.0508656746547505e-05 tokens_per_second_per_gpu:172.5751666921026 mfu:2.8477477644284286 
Step 3099 | loss:1.3463126420974731 lr:3.045403002166464e-05 tokens_per_second_per_gpu:277.44814401832474 mfu:4.5783083801544295 
Step 3100 | loss:1.2883360385894775 lr:3.0399443460207488e-05 tokens_per_second_per_gpu:239.76231700798846 mfu:3.9564360002725976 
Step 3101 | loss:0.9820067882537842 lr:3.034489709370033e-05 tokens_per_second_per_gpu:266.9135485739579 mfu:4.404471835761125 
Step 3102 | loss:1.0749269723892212 lr:3.0290390953644078e-05 tokens_per_second_per_gpu:235.77444176504713 mfu:3.89063010811798 
Step 3103 | loss:1.2759671211242676 lr:3.0235925071516613e-05 tokens_per_second_per_gpu:193.013517230602 mfu:3.1850110461059056 
Step 3104 | loss:1.2483670711517334 lr:3.0181499478772447e-05 tokens_per_second_per_gpu:270.8410699175766 mfu:4.469281798517759 
Step 3105 | loss:1.0454350709915161 lr:3.0127114206842844e-05 tokens_per_second_per_gpu:274.6271313511014 mfu:4.531757461673543 
Step 3106 | loss:1.2096035480499268 lr:3.0072769287135803e-05 tokens_per_second_per_gpu:252.56108784178116 mfu:4.1676348171591115 
Step 3107 | loss:1.106309413909912 lr:3.001846475103599e-05 tokens_per_second_per_gpu:194.87850259927134 mfu:3.2157860875914253 
Step 3108 | loss:1.2396302223205566 lr:2.9964200629904783e-05 tokens_per_second_per_gpu:251.76299382329088 mfu:4.154465074950406 
Step 3109 | loss:1.4214692115783691 lr:2.9909976955080186e-05 tokens_per_second_per_gpu:246.9606064245469 mfu:4.075218516822537 
Step 3110 | loss:1.3238234519958496 lr:2.9855793757876872e-05 tokens_per_second_per_gpu:253.96912988172556 mfu:4.190869611876864 
Step 3111 | loss:1.1997475624084473 lr:2.980165106958611e-05 tokens_per_second_per_gpu:242.09621983353884 mfu:3.994948879508069 
Step 3112 | loss:1.1445640325546265 lr:2.974754892147581e-05 tokens_per_second_per_gpu:217.05842749625268 mfu:3.5817879449343186 
Step 3113 | loss:1.0712112188339233 lr:2.969348734479045e-05 tokens_per_second_per_gpu:360.9869635256076 mfu:5.956823557365853 
Step 3114 | loss:1.1754502058029175 lr:2.9639466370751068e-05 tokens_per_second_per_gpu:294.8069712950747 mfu:4.864754932795807 
Step 3115 | loss:1.1203068494796753 lr:2.9585486030555265e-05 tokens_per_second_per_gpu:241.35284220189058 mfu:3.9826820393292075 
Step 3116 | loss:1.0686168670654297 lr:2.9531546355377182e-05 tokens_per_second_per_gpu:203.4686342230195 mfu:3.357536077445523 
Step 3117 | loss:1.2545268535614014 lr:2.9477647376367468e-05 tokens_per_second_per_gpu:183.1652603521615 mfu:3.022500112194235 
Step 3118 | loss:0.9631173014640808 lr:2.9423789124653266e-05 tokens_per_second_per_gpu:255.09463994640328 mfu:4.20944220741285 
Step 3119 | loss:1.126570701599121 lr:2.9369971631338202e-05 tokens_per_second_per_gpu:341.97989503358286 mfu:5.643178565192257 
Step 3120 | loss:1.294309377670288 lr:2.931619492750237e-05 tokens_per_second_per_gpu:205.05943610277734 mfu:3.383786682231618 
Step 3121 | loss:1.0368300676345825 lr:2.9262459044202307e-05 tokens_per_second_per_gpu:299.02750040443277 mfu:4.934399960908821 
Step 3122 | loss:1.1858677864074707 lr:2.9208764012470956e-05 tokens_per_second_per_gpu:306.8270496305065 mfu:5.063104161506399 
Step 3123 | loss:1.0796180963516235 lr:2.9155109863317687e-05 tokens_per_second_per_gpu:213.13207310473376 mfu:3.516997238628639 
Step 3124 | loss:1.1578487157821655 lr:2.9101496627728265e-05 tokens_per_second_per_gpu:316.0215392321942 mfu:5.214826959810177 
Step 3125 | loss:1.35248863697052 lr:2.90479243366648e-05 tokens_per_second_per_gpu:155.724266729204 mfu:2.5696827703869216 
Step 3126 | loss:1.1552690267562866 lr:2.899439302106579e-05 tokens_per_second_per_gpu:265.6105162667377 mfu:4.38296985832723 
Step 3127 | loss:1.2673475742340088 lr:2.8940902711846053e-05 tokens_per_second_per_gpu:278.2634649168538 mfu:4.5917623915894605 
Step 3128 | loss:1.2353739738464355 lr:2.8887453439896728e-05 tokens_per_second_per_gpu:234.05839792392555 mfu:3.862312824085256 
Step 3129 | loss:1.1373597383499146 lr:2.8834045236085228e-05 tokens_per_second_per_gpu:208.2875122022445 mfu:3.4370547547583192 
Step 3130 | loss:1.145943284034729 lr:2.87806781312553e-05 tokens_per_second_per_gpu:332.25858384752684 mfu:5.48276242463134 
Step 3131 | loss:1.2226078510284424 lr:2.8727352156226917e-05 tokens_per_second_per_gpu:234.13741669438247 mfu:3.863616751708388 
Step 3132 | loss:1.2719688415527344 lr:2.8674067341796317e-05 tokens_per_second_per_gpu:200.87183490493345 mfu:3.314685013793111 
Step 3133 | loss:1.2640987634658813 lr:2.8620823718735955e-05 tokens_per_second_per_gpu:179.04687236348136 mfu:2.9545405649858156 
Step 3134 | loss:1.2061883211135864 lr:2.85676213177945e-05 tokens_per_second_per_gpu:211.286096198404 mfu:3.486535865135858 
Step 3135 | loss:1.293596863746643 lr:2.8514460169696834e-05 tokens_per_second_per_gpu:268.67142435624106 mfu:4.433479409243995 
Step 3136 | loss:1.1752210855484009 lr:2.846134030514399e-05 tokens_per_second_per_gpu:234.78113669076367 mfu:3.874239092197753 
Step 3137 | loss:1.1642075777053833 lr:2.840826175481318e-05 tokens_per_second_per_gpu:268.37646237517345 mfu:4.42861209641865 
Step 3138 | loss:1.3269312381744385 lr:2.8355224549357727e-05 tokens_per_second_per_gpu:217.95255802156487 mfu:3.5965424328097835 
Step 3139 | loss:1.1584656238555908 lr:2.830222871940711e-05 tokens_per_second_per_gpu:264.2736586727019 mfu:4.360909713187304 
Step 3140 | loss:1.1027743816375732 lr:2.8249274295566864e-05 tokens_per_second_per_gpu:221.17672151978348 mfu:3.649745941577561 
Step 3141 | loss:1.2779923677444458 lr:2.819636130841875e-05 tokens_per_second_per_gpu:191.09816156908477 mfu:3.15340481962662 
Step 3142 | loss:1.1017693281173706 lr:2.8143489788520385e-05 tokens_per_second_per_gpu:318.9608906428414 mfu:5.263330644140809 
Step 3143 | loss:1.163917064666748 lr:2.8090659766405592e-05 tokens_per_second_per_gpu:303.96677661053826 mfu:5.015905388621527 
Step 3144 | loss:1.326183557510376 lr:2.8037871272584183e-05 tokens_per_second_per_gpu:191.94468295835173 mfu:3.167373685715719 
Step 3145 | loss:1.1490206718444824 lr:2.798512433754199e-05 tokens_per_second_per_gpu:250.6170453835822 mfu:4.135555215728581 
Step 3146 | loss:1.2058591842651367 lr:2.793241899174085e-05 tokens_per_second_per_gpu:233.00241596975556 mfu:3.844887546121424 
Step 3147 | loss:1.2100062370300293 lr:2.7879755265618555e-05 tokens_per_second_per_gpu:268.1348317933953 mfu:4.424624831261872 
Step 3148 | loss:1.2561061382293701 lr:2.7827133189588884e-05 tokens_per_second_per_gpu:276.97829727648946 mfu:4.570555207816067 
Step 3149 | loss:1.1715354919433594 lr:2.777455279404163e-05 tokens_per_second_per_gpu:284.58115615180975 mfu:4.696013724127899 
Step 3150 | loss:1.2414525747299194 lr:2.7722014109342363e-05 tokens_per_second_per_gpu:227.89552040177338 mfu:3.7606161488187198 
Step 3151 | loss:1.2288457155227661 lr:2.766951716583267e-05 tokens_per_second_per_gpu:172.71530120595338 mfu:2.850060193013532 
Step 3152 | loss:1.2016654014587402 lr:2.761706199383003e-05 tokens_per_second_per_gpu:279.99343152230335 mfu:4.620309422008932 
Step 3153 | loss:1.2718770503997803 lr:2.756464862362772e-05 tokens_per_second_per_gpu:167.16748275811187 mfu:2.7585129102548103 
Step 3154 | loss:1.2008070945739746 lr:2.751227708549505e-05 tokens_per_second_per_gpu:237.26201927670547 mfu:3.91517735680062 
Step 3155 | loss:0.9691614508628845 lr:2.7459947409676954e-05 tokens_per_second_per_gpu:269.34744939034266 mfu:4.444634831060827 
Step 3156 | loss:1.2270371913909912 lr:2.7407659626394288e-05 tokens_per_second_per_gpu:266.6814449891714 mfu:4.40064178027075 
Step 3157 | loss:1.2721961736679077 lr:2.7355413765843817e-05 tokens_per_second_per_gpu:192.79110039941784 mfu:3.1813408365043934 
Step 3158 | loss:1.2297861576080322 lr:2.730320985819791e-05 tokens_per_second_per_gpu:226.0956114268761 mfu:3.730914964936433 
Step 3159 | loss:1.3748910427093506 lr:2.7251047933604823e-05 tokens_per_second_per_gpu:325.16803243041016 mfu:5.3657577458371755 
Step 3160 | loss:1.3367195129394531 lr:2.719892802218853e-05 tokens_per_second_per_gpu:241.99826614246817 mfu:3.9933324974404125 
Step 3161 | loss:1.3197383880615234 lr:2.714685015404873e-05 tokens_per_second_per_gpu:278.45294336645566 mfu:4.594889068744718 
Step 3162 | loss:1.078179955482483 lr:2.7094814359260946e-05 tokens_per_second_per_gpu:207.67532810734656 mfu:3.426952803700815 
Step 3163 | loss:1.4069880247116089 lr:2.7042820667876235e-05 tokens_per_second_per_gpu:210.92996609772817 mfu:3.4806591870628494 
Step 3164 | loss:1.0072438716888428 lr:2.699086910992141e-05 tokens_per_second_per_gpu:300.0931635405165 mfu:4.95198499282034 
Step 3165 | loss:1.1556307077407837 lr:2.6938959715399083e-05 tokens_per_second_per_gpu:223.4470086822513 mfu:3.6872090674458557 
Step 3166 | loss:1.1915509700775146 lr:2.688709251428725e-05 tokens_per_second_per_gpu:302.3904774980056 mfu:4.989894101135454 
Step 3167 | loss:1.1653094291687012 lr:2.683526753653982e-05 tokens_per_second_per_gpu:219.1956141844172 mfu:3.61705471436613 
Step 3168 | loss:1.0952415466308594 lr:2.678348481208609e-05 tokens_per_second_per_gpu:300.1323472029183 mfu:4.952631581719228 
Step 3169 | loss:1.1804745197296143 lr:2.673174437083107e-05 tokens_per_second_per_gpu:228.61937907580827 mfu:3.772560897071072 
Step 3170 | loss:1.0810290575027466 lr:2.6680046242655398e-05 tokens_per_second_per_gpu:217.02449250425585 mfu:3.5812279669290983 
Step 3171 | loss:1.0449594259262085 lr:2.662839045741512e-05 tokens_per_second_per_gpu:300.2440819480819 mfu:4.954475371743294 
Step 3172 | loss:1.3735029697418213 lr:2.6576777044941935e-05 tokens_per_second_per_gpu:244.06172310256713 mfu:4.027382616340776 
Step 3173 | loss:1.151947021484375 lr:2.652520603504315e-05 tokens_per_second_per_gpu:249.83439779585822 mfu:4.122640362676446 
Step 3174 | loss:1.2595535516738892 lr:2.6473677457501344e-05 tokens_per_second_per_gpu:262.3093622772349 mfu:4.328495891569238 
Step 3175 | loss:1.1781256198883057 lr:2.6422191342074864e-05 tokens_per_second_per_gpu:261.55497297759706 mfu:4.3160473424371055 
Step 3176 | loss:1.1034889221191406 lr:2.6370747718497334e-05 tokens_per_second_per_gpu:243.26908143843264 mfu:4.01430284611486 
Step 3177 | loss:1.1866487264633179 lr:2.631934661647789e-05 tokens_per_second_per_gpu:232.60299402256814 mfu:3.8382964879815473 
Step 3178 | loss:1.2018693685531616 lr:2.6267988065701232e-05 tokens_per_second_per_gpu:259.4973436569317 mfu:4.282093388283312 
Step 3179 | loss:1.1635870933532715 lr:2.6216672095827266e-05 tokens_per_second_per_gpu:239.8703569363567 mfu:3.958218820306193 
Step 3180 | loss:1.2101731300354004 lr:2.616539873649151e-05 tokens_per_second_per_gpu:197.4831512970232 mfu:3.2587666777210456 
Step 3181 | loss:1.1402159929275513 lr:2.611416801730481e-05 tokens_per_second_per_gpu:225.34713755879636 mfu:3.7185640292519264 
Step 3182 | loss:1.232086420059204 lr:2.6062979967853263e-05 tokens_per_second_per_gpu:270.2730672361409 mfu:4.459908906709208 
Step 3183 | loss:1.0978610515594482 lr:2.601183461769856e-05 tokens_per_second_per_gpu:265.81677645573376 mfu:4.386373459223946 
Step 3184 | loss:1.289845585823059 lr:2.596073199637751e-05 tokens_per_second_per_gpu:302.5779318919623 mfu:4.992987378352302 
Step 3185 | loss:1.148221492767334 lr:2.590967213340233e-05 tokens_per_second_per_gpu:278.3327424596361 mfu:4.592905574420252 
Step 3186 | loss:1.0807729959487915 lr:2.585865505826065e-05 tokens_per_second_per_gpu:208.34138132461817 mfu:3.4379436756601605 
Step 3187 | loss:1.3560837507247925 lr:2.580768080041518e-05 tokens_per_second_per_gpu:201.8472591723379 mfu:3.3307809697183703 
Step 3188 | loss:1.0684109926223755 lr:2.575674938930408e-05 tokens_per_second_per_gpu:296.3985799987993 mfu:4.8910188513812844 
Step 3189 | loss:1.0695521831512451 lr:2.5705860854340725e-05 tokens_per_second_per_gpu:271.77995771606436 mfu:4.484774848186736 
Step 3190 | loss:1.3120580911636353 lr:2.5655015224913592e-05 tokens_per_second_per_gpu:250.4719800383309 mfu:4.1331614210676575 
Step 3191 | loss:1.162811040878296 lr:2.5604212530386628e-05 tokens_per_second_per_gpu:227.6141782859627 mfu:3.7559735840934665 
Step 3192 | loss:1.1967076063156128 lr:2.555345280009872e-05 tokens_per_second_per_gpu:200.2356098125546 mfu:3.3041863504035653 
Step 3193 | loss:1.3918187618255615 lr:2.5502736063364174e-05 tokens_per_second_per_gpu:181.93721662120683 mfu:3.0022355581655207 
Step 3194 | loss:1.2238935232162476 lr:2.545206234947234e-05 tokens_per_second_per_gpu:205.29539760803775 mfu:3.387680399166543 
Step 3195 | loss:1.3040034770965576 lr:2.540143168768767e-05 tokens_per_second_per_gpu:309.0093162336329 mfu:5.099114816802637 
Step 3196 | loss:1.091894507408142 lr:2.5350844107249918e-05 tokens_per_second_per_gpu:331.7780038906652 mfu:5.474832138229105 
Step 3197 | loss:1.1997225284576416 lr:2.5300299637373858e-05 tokens_per_second_per_gpu:209.5946406866523 mfu:3.4586243252280626 
Step 3198 | loss:1.1582809686660767 lr:2.5249798307249294e-05 tokens_per_second_per_gpu:207.43993214907877 mfu:3.423068419135169 
Step 3199 | loss:1.1843371391296387 lr:2.519934014604134e-05 tokens_per_second_per_gpu:287.94972886903537 mfu:4.751600200494506 
Step 3200 | loss:1.1881734132766724 lr:2.514892518288988e-05 tokens_per_second_per_gpu:235.35113216600197 mfu:3.8836448680776643 
Step 3201 | loss:1.147910237312317 lr:2.5098553446910143e-05 tokens_per_second_per_gpu:319.40485022191996 mfu:5.270656639665259 
Step 3202 | loss:1.2189162969589233 lr:2.5048224967192225e-05 tokens_per_second_per_gpu:234.46487106551635 mfu:3.869020237454472 
Step 3203 | loss:1.0324976444244385 lr:2.4997939772801216e-05 tokens_per_second_per_gpu:249.2268624215815 mfu:4.11261512244594 
Step 3204 | loss:1.186752438545227 lr:2.4947697892777345e-05 tokens_per_second_per_gpu:250.33635397195948 mfu:4.1309233885934 
Step 3205 | loss:1.210950255393982 lr:2.489749935613571e-05 tokens_per_second_per_gpu:218.38439641296296 mfu:3.603668410650456 
Step 3206 | loss:1.2686859369277954 lr:2.484734419186645e-05 tokens_per_second_per_gpu:352.4866662548563 mfu:5.816555968385643 
Step 3207 | loss:1.1361240148544312 lr:2.4797232428934636e-05 tokens_per_second_per_gpu:212.7097647661815 mfu:3.510028520880521 
Step 3208 | loss:1.3387221097946167 lr:2.4747164096280172e-05 tokens_per_second_per_gpu:236.2721569873312 mfu:3.898843151968665 
Step 3209 | loss:1.2071611881256104 lr:2.4697139222818066e-05 tokens_per_second_per_gpu:271.2474170649943 mfu:4.475987132795113 
Step 3210 | loss:0.9516556859016418 lr:2.464715783743813e-05 tokens_per_second_per_gpu:210.06041592249701 mfu:3.4663103116421414 
Step 3211 | loss:1.1474850177764893 lr:2.459721996900499e-05 tokens_per_second_per_gpu:257.6983797841397 mfu:4.252407799996029 
Step 3212 | loss:1.0873537063598633 lr:2.454732564635829e-05 tokens_per_second_per_gpu:234.2654867163584 mfu:3.8657300981751073 
Step 3213 | loss:1.0638000965118408 lr:2.4497474898312423e-05 tokens_per_second_per_gpu:240.5516522435014 mfu:3.9694612094924557 
Step 3214 | loss:1.2674287557601929 lr:2.4447667753656655e-05 tokens_per_second_per_gpu:226.39945988651394 mfu:3.7359289179184545 
Step 3215 | loss:1.229207992553711 lr:2.439790424115509e-05 tokens_per_second_per_gpu:268.14540249243095 mfu:4.424799263569396 
Step 3216 | loss:1.171203851699829 lr:2.4348184389546513e-05 tokens_per_second_per_gpu:289.4109732382356 mfu:4.775712913032677 
Step 3217 | loss:1.2499110698699951 lr:2.429850822754468e-05 tokens_per_second_per_gpu:268.0462024455969 mfu:4.423162314771851 
Step 3218 | loss:1.2425625324249268 lr:2.4248875783837987e-05 tokens_per_second_per_gpu:211.5378465478156 mfu:3.490690121559148 
Step 3219 | loss:1.1820194721221924 lr:2.419928708708963e-05 tokens_per_second_per_gpu:343.27193412729105 mfu:5.6644991381993 
Step 3220 | loss:1.2120599746704102 lr:2.4149742165937517e-05 tokens_per_second_per_gpu:238.84148096025845 mfu:3.941240831427669 
Step 3221 | loss:1.1321842670440674 lr:2.410024104899429e-05 tokens_per_second_per_gpu:225.10233223634506 mfu:3.7145243761367435 
Step 3222 | loss:1.394465684890747 lr:2.4050783764847296e-05 tokens_per_second_per_gpu:262.50791192484525 mfu:4.331772257027538 
Step 3223 | loss:1.297890543937683 lr:2.4001370342058594e-05 tokens_per_second_per_gpu:249.88000736148763 mfu:4.123392988567223 
Step 3224 | loss:1.1504871845245361 lr:2.3952000809164788e-05 tokens_per_second_per_gpu:210.76453275335052 mfu:3.477929290023527 
Step 3225 | loss:1.3128483295440674 lr:2.3902675194677315e-05 tokens_per_second_per_gpu:151.1096236889228 mfu:2.4935342743229314 
Step 3226 | loss:1.198788046836853 lr:2.3853393527082133e-05 tokens_per_second_per_gpu:263.9953202339697 mfu:4.356316713615887 
Step 3227 | loss:1.088742971420288 lr:2.380415583483986e-05 tokens_per_second_per_gpu:272.3119566809109 mfu:4.493553624947374 
Step 3228 | loss:1.2409946918487549 lr:2.3754962146385706e-05 tokens_per_second_per_gpu:233.07953065490867 mfu:3.8461600534957974 
Step 3229 | loss:1.2425340414047241 lr:2.3705812490129464e-05 tokens_per_second_per_gpu:276.5631438280463 mfu:4.5637045564311665 
Step 3230 | loss:1.0967249870300293 lr:2.3656706894455506e-05 tokens_per_second_per_gpu:195.72154526726814 mfu:3.2296975495886713 
Step 3231 | loss:0.9468562602996826 lr:2.3607645387722756e-05 tokens_per_second_per_gpu:191.299249758602 mfu:3.1567230748143573 
Step 3232 | loss:1.1128981113433838 lr:2.3558627998264682e-05 tokens_per_second_per_gpu:242.80140971880274 mfu:4.006585564888422 
Step 3233 | loss:1.2651076316833496 lr:2.3509654754389265e-05 tokens_per_second_per_gpu:224.4962003455374 mfu:3.7045222954777346 
Step 3234 | loss:1.2265321016311646 lr:2.3460725684379005e-05 tokens_per_second_per_gpu:217.30309942076747 mfu:3.5858253967844944 
Step 3235 | loss:1.1647632122039795 lr:2.341184081649086e-05 tokens_per_second_per_gpu:275.94752562455983 mfu:4.553545937457628 
Step 3236 | loss:1.155615210533142 lr:2.3363000178956306e-05 tokens_per_second_per_gpu:233.4881520225115 mfu:3.852902915799763 
Step 3237 | loss:1.3842270374298096 lr:2.331420379998124e-05 tokens_per_second_per_gpu:244.86166427851688 mfu:4.0405828394038625 
Step 3238 | loss:1.2013658285140991 lr:2.326545170774601e-05 tokens_per_second_per_gpu:183.92186542398795 mfu:3.03498522487382 
Step 3239 | loss:1.169374704360962 lr:2.3216743930405406e-05 tokens_per_second_per_gpu:260.7493987808636 mfu:4.302754166125581 
Step 3240 | loss:1.1586623191833496 lr:2.3168080496088584e-05 tokens_per_second_per_gpu:254.19626167830327 mfu:4.194617625442969 
Step 3241 | loss:1.0112786293029785 lr:2.3119461432899137e-05 tokens_per_second_per_gpu:236.0261998573445 mfu:3.894784492310439 
Step 3242 | loss:1.2214373350143433 lr:2.3070886768915e-05 tokens_per_second_per_gpu:240.94294617124098 mfu:3.9759181431829385 
Step 3243 | loss:1.11994206905365 lr:2.3022356532188495e-05 tokens_per_second_per_gpu:294.913084815898 mfu:4.866505964230355 
Step 3244 | loss:1.0759844779968262 lr:2.297387075074625e-05 tokens_per_second_per_gpu:260.0968219461318 mfu:4.291985674587393 
Step 3245 | loss:1.1882297992706299 lr:2.2925429452589265e-05 tokens_per_second_per_gpu:241.8861239931371 mfu:3.9914819846396594 
Step 3246 | loss:1.1566641330718994 lr:2.287703266569281e-05 tokens_per_second_per_gpu:299.81317904332917 mfu:4.947364830828189 
Step 3247 | loss:1.4252043962478638 lr:2.2828680418006476e-05 tokens_per_second_per_gpu:208.3893923023343 mfu:3.4387359284337187 
Step 3248 | loss:1.2109357118606567 lr:2.2780372737454124e-05 tokens_per_second_per_gpu:274.66302540430786 mfu:4.532349767112003 
Step 3249 | loss:1.278786063194275 lr:2.2732109651933863e-05 tokens_per_second_per_gpu:227.23375769031824 mfu:3.749696076607573 
Step 3250 | loss:1.2958190441131592 lr:2.2683891189318084e-05 tokens_per_second_per_gpu:247.3128751607396 mfu:4.081031476619704 
Step 3251 | loss:1.083239197731018 lr:2.263571737745336e-05 tokens_per_second_per_gpu:244.42524779683856 mfu:4.03338131624221 
Step 3252 | loss:1.1310479640960693 lr:2.2587588244160507e-05 tokens_per_second_per_gpu:214.60844715491834 mfu:3.5413596134793286 
Step 3253 | loss:1.2697843313217163 lr:2.2539503817234553e-05 tokens_per_second_per_gpu:288.8067071994762 mfu:4.765741621716661 
Step 3254 | loss:1.3419904708862305 lr:2.2491464124444662e-05 tokens_per_second_per_gpu:238.3760622612301 mfu:3.9335607284030787 
Step 3255 | loss:1.1136260032653809 lr:2.2443469193534216e-05 tokens_per_second_per_gpu:236.36928847604955 mfu:3.9004459664706306 
Step 3256 | loss:1.1989096403121948 lr:2.2395519052220704e-05 tokens_per_second_per_gpu:271.39327444155856 mfu:4.478393997154557 
Step 3257 | loss:1.1453473567962646 lr:2.234761372819577e-05 tokens_per_second_per_gpu:218.58625986924244 mfu:3.606999458896612 
Step 3258 | loss:1.092060923576355 lr:2.2299753249125167e-05 tokens_per_second_per_gpu:204.01414714565746 mfu:3.3665378546750397 
Step 3259 | loss:1.25429105758667 lr:2.2251937642648767e-05 tokens_per_second_per_gpu:275.3617425845114 mfu:4.543879643200388 
Step 3260 | loss:1.0380882024765015 lr:2.22041669363805e-05 tokens_per_second_per_gpu:279.9287222778436 mfu:4.6192416229172055 
Step 3261 | loss:1.1156446933746338 lr:2.215644115790839e-05 tokens_per_second_per_gpu:232.56217711833153 mfu:3.837622948155287 
Step 3262 | loss:1.2262789011001587 lr:2.2108760334794497e-05 tokens_per_second_per_gpu:275.4278839784304 mfu:4.544971074895222 
Step 3263 | loss:1.0533509254455566 lr:2.2061124494574935e-05 tokens_per_second_per_gpu:268.54082774559913 mfu:4.431324370294151 
Step 3264 | loss:1.202797293663025 lr:2.2013533664759835e-05 tokens_per_second_per_gpu:223.8355988433874 mfu:3.6936213849528614 
Step 3265 | loss:1.3885397911071777 lr:2.1965987872833317e-05 tokens_per_second_per_gpu:235.435641453427 mfu:3.8850393974236352 
Step 3266 | loss:1.1818586587905884 lr:2.1918487146253508e-05 tokens_per_second_per_gpu:221.84122632307597 mfu:3.660711262395731 
Step 3267 | loss:1.2543483972549438 lr:2.1871031512452523e-05 tokens_per_second_per_gpu:164.23060579363442 mfu:2.7100500579783087 
Step 3268 | loss:1.4609320163726807 lr:2.1823620998836393e-05 tokens_per_second_per_gpu:219.42906326477842 mfu:3.6209069725412157 
Step 3269 | loss:1.2105478048324585 lr:2.1776255632785135e-05 tokens_per_second_per_gpu:264.9379112499979 mfu:4.371870871900165 
Step 3270 | loss:1.3247342109680176 lr:2.1728935441652686e-05 tokens_per_second_per_gpu:233.94628278840435 mfu:3.860462757052675 
Step 3271 | loss:0.9582322239875793 lr:2.1681660452766863e-05 tokens_per_second_per_gpu:289.00499731264307 mfu:4.76901370446937 
Step 3272 | loss:1.2181892395019531 lr:2.1634430693429397e-05 tokens_per_second_per_gpu:248.02296179189455 mfu:4.092748965614108 
Step 3273 | loss:1.1646225452423096 lr:2.1587246190915922e-05 tokens_per_second_per_gpu:219.97488816596942 mfu:3.6299138978823877 
Step 3274 | loss:1.119759440422058 lr:2.1540106972475895e-05 tokens_per_second_per_gpu:302.7242084740115 mfu:4.995401160227779 
Step 3275 | loss:1.2859041690826416 lr:2.1493013065332655e-05 tokens_per_second_per_gpu:237.03361359552204 mfu:3.9114083222376497 
Step 3276 | loss:1.0314772129058838 lr:2.1445964496683345e-05 tokens_per_second_per_gpu:343.0366833312391 mfu:5.660617149026825 
Step 3277 | loss:1.1871578693389893 lr:2.139896129369895e-05 tokens_per_second_per_gpu:219.49279937782023 mfu:3.6219587135124534 
Step 3278 | loss:1.0945183038711548 lr:2.135200348352423e-05 tokens_per_second_per_gpu:243.78114722639978 mfu:4.022752695713009 
Step 3279 | loss:1.1037321090698242 lr:2.130509109327776e-05 tokens_per_second_per_gpu:225.94147236476735 mfu:3.728371440407701 
Step 3280 | loss:1.261697769165039 lr:2.1258224150051864e-05 tokens_per_second_per_gpu:220.24413104373704 mfu:3.634356807125633 
Step 3281 | loss:1.041919469833374 lr:2.121140268091262e-05 tokens_per_second_per_gpu:214.65127481243908 mfu:3.5420663337351925 
Step 3282 | loss:1.0796666145324707 lr:2.1164626712899847e-05 tokens_per_second_per_gpu:282.67404514036156 mfu:4.664543546677293 
Step 3283 | loss:1.166911005973816 lr:2.111789627302707e-05 tokens_per_second_per_gpu:241.26123476462476 mfu:3.981170379919113 
Step 3284 | loss:1.2041155099868774 lr:2.107121138828163e-05 tokens_per_second_per_gpu:212.0589683545881 mfu:3.499289408980837 
Step 3285 | loss:1.1068326234817505 lr:2.102457208562436e-05 tokens_per_second_per_gpu:253.47131839794213 mfu:4.1826549795678 
Step 3286 | loss:1.0957375764846802 lr:2.097797839198994e-05 tokens_per_second_per_gpu:193.3980531854398 mfu:3.1913564631593654 
Step 3287 | loss:1.086459755897522 lr:2.0931430334286617e-05 tokens_per_second_per_gpu:298.2730205220219 mfu:4.921949917025769 
Step 3288 | loss:1.0814793109893799 lr:2.0884927939396314e-05 tokens_per_second_per_gpu:235.90593447104186 mfu:3.892799933978286 
Step 3289 | loss:1.239161491394043 lr:2.083847123417464e-05 tokens_per_second_per_gpu:359.95724612449925 mfu:5.939831683719101 
Step 3290 | loss:1.0651271343231201 lr:2.0792060245450708e-05 tokens_per_second_per_gpu:265.5902200528239 mfu:4.382634940511953 
Step 3291 | loss:1.2387727499008179 lr:2.0745695000027254e-05 tokens_per_second_per_gpu:220.2815674066316 mfu:3.634974562975358 
Step 3292 | loss:1.2750450372695923 lr:2.069937552468073e-05 tokens_per_second_per_gpu:267.76612473367504 mfu:4.418540614597487 
Step 3293 | loss:1.0303001403808594 lr:2.065310184616096e-05 tokens_per_second_per_gpu:197.05840539478265 mfu:3.251757736534776 
Step 3294 | loss:1.1821179389953613 lr:2.0606873991191443e-05 tokens_per_second_per_gpu:234.2436152642071 mfu:3.865369186578367 
Step 3295 | loss:1.17599618434906 lr:2.0560691986469173e-05 tokens_per_second_per_gpu:244.30325770391502 mfu:4.031368297677233 
Step 3296 | loss:1.0852948427200317 lr:2.0514555858664663e-05 tokens_per_second_per_gpu:263.94687339481914 mfu:4.355517268478274 
Step 3297 | loss:1.126364827156067 lr:2.046846563442202e-05 tokens_per_second_per_gpu:253.91085388689854 mfu:4.189907971003675 
Step 3298 | loss:1.1015288829803467 lr:2.0422421340358665e-05 tokens_per_second_per_gpu:210.59753639653695 mfu:3.4751736009467082 
Step 3299 | loss:0.9952014088630676 lr:2.0376423003065626e-05 tokens_per_second_per_gpu:223.16520524961217 mfu:3.682558890304563 
Step 3300 | loss:1.1676592826843262 lr:2.0330470649107415e-05 tokens_per_second_per_gpu:388.3114295678447 mfu:6.407718020210617 
Step 3301 | loss:1.1810952425003052 lr:2.0284564305021826e-05 tokens_per_second_per_gpu:271.00360414371414 mfu:4.4719638557801 
Step 3302 | loss:1.2710230350494385 lr:2.0238703997320297e-05 tokens_per_second_per_gpu:297.68187311172886 mfu:4.912195102654862 
Step 3303 | loss:1.3794963359832764 lr:2.0192889752487497e-05 tokens_per_second_per_gpu:203.9759626142207 mfu:3.3659077529279626 
Step 3304 | loss:1.2580831050872803 lr:2.0147121596981567e-05 tokens_per_second_per_gpu:239.91946144794736 mfu:3.959029118020435 
Step 3305 | loss:1.084033489227295 lr:2.010139955723409e-05 tokens_per_second_per_gpu:244.53807441582126 mfu:4.0352431238135695 
Step 3306 | loss:1.071793794631958 lr:2.0055723659649904e-05 tokens_per_second_per_gpu:248.09484157350172 mfu:4.0939350892685304 
Step 3307 | loss:1.17535400390625 lr:2.0010093930607233e-05 tokens_per_second_per_gpu:440.7131487169412 mfu:7.272424579209843 
Step 3308 | loss:1.1685152053833008 lr:1.9964510396457748e-05 tokens_per_second_per_gpu:216.6066243390828 mfu:3.5743325186672954 
Step 3309 | loss:1.2350959777832031 lr:1.9918973083526237e-05 tokens_per_second_per_gpu:283.5385501840709 mfu:4.6788091698996235 
Step 3310 | loss:1.2198314666748047 lr:1.9873482018111024e-05 tokens_per_second_per_gpu:283.37050898800993 mfu:4.6760362394161294 
Step 3311 | loss:1.1842305660247803 lr:1.982803722648352e-05 tokens_per_second_per_gpu:267.0341636235145 mfu:4.40646216405873 
Step 3312 | loss:1.5059303045272827 lr:1.9782638734888516e-05 tokens_per_second_per_gpu:239.80800481839424 mfu:3.957189917318941 
Step 3313 | loss:1.138407588005066 lr:1.973728656954411e-05 tokens_per_second_per_gpu:218.55849417057019 mfu:3.6065412834369712 
Step 3314 | loss:1.1777124404907227 lr:1.9691980756641504e-05 tokens_per_second_per_gpu:204.80531624593513 mfu:3.3795933253999806 
Step 3315 | loss:1.3479692935943604 lr:1.9646721322345287e-05 tokens_per_second_per_gpu:186.42588756434796 mfu:3.076305326653074 
Step 3316 | loss:1.2786637544631958 lr:1.960150829279318e-05 tokens_per_second_per_gpu:245.5939743178727 mfu:4.052667047795008 
Step 3317 | loss:1.0614347457885742 lr:1.9556341694096046e-05 tokens_per_second_per_gpu:237.34106092482017 mfu:3.9164816619392435 
Step 3318 | loss:1.2487540245056152 lr:1.951122155233811e-05 tokens_per_second_per_gpu:344.812392939186 mfu:5.689919007244506 
Step 3319 | loss:1.1845061779022217 lr:1.946614789357658e-05 tokens_per_second_per_gpu:375.41492692800057 mfu:6.1949064826903575 
Step 3320 | loss:0.9886293411254883 lr:1.9421120743841902e-05 tokens_per_second_per_gpu:250.93179833522882 mfu:4.140749109100262 
Step 3321 | loss:1.1317129135131836 lr:1.9376140129137744e-05 tokens_per_second_per_gpu:276.3580370167448 mfu:4.560319987987463 
Step 3322 | loss:1.1229900121688843 lr:1.93312060754407e-05 tokens_per_second_per_gpu:172.9437129869748 mfu:2.853829328232931 
Step 3323 | loss:1.1288009881973267 lr:1.9286318608700683e-05 tokens_per_second_per_gpu:300.9101402183491 mfu:4.965466327084608 
Step 3324 | loss:1.1356899738311768 lr:1.9241477754840596e-05 tokens_per_second_per_gpu:339.87007244608577 mfu:5.608363344253749 
Step 3325 | loss:1.2848786115646362 lr:1.9196683539756376e-05 tokens_per_second_per_gpu:235.5014160063047 mfu:3.8861247756938933 
Step 3326 | loss:1.1290147304534912 lr:1.9151935989317184e-05 tokens_per_second_per_gpu:284.1439811769207 mfu:4.688799684696458 
Step 3327 | loss:1.1769834756851196 lr:1.910723512936502e-05 tokens_per_second_per_gpu:287.1318997827613 mfu:4.738104800219003 
Step 3328 | loss:0.8852739334106445 lr:1.906258098571513e-05 tokens_per_second_per_gpu:263.72413827346884 mfu:4.351841806614073 
Step 3329 | loss:1.233920931816101 lr:1.901797358415568e-05 tokens_per_second_per_gpu:285.4131142969562 mfu:4.709742274957961 
Step 3330 | loss:1.106810450553894 lr:1.8973412950447755e-05 tokens_per_second_per_gpu:257.4894855953979 mfu:4.248960734173094 
Step 3331 | loss:0.9715713262557983 lr:1.8928899110325616e-05 tokens_per_second_per_gpu:299.76985845555635 mfu:4.946649976487623 
Step 3332 | loss:1.3125971555709839 lr:1.8884432089496406e-05 tokens_per_second_per_gpu:324.32090764022524 mfu:5.351778922732545 
Step 3333 | loss:1.0529385805130005 lr:1.8840011913640155e-05 tokens_per_second_per_gpu:245.86769058829154 mfu:4.057183774692127 
Step 3334 | loss:1.111194133758545 lr:1.8795638608410014e-05 tokens_per_second_per_gpu:296.86931144826235 mfu:4.898786622715652 
Step 3335 | loss:1.1789377927780151 lr:1.875131219943187e-05 tokens_per_second_per_gpu:234.13131521791237 mfu:3.863516068242102 
Step 3336 | loss:1.2196002006530762 lr:1.8707032712304696e-05 tokens_per_second_per_gpu:191.92608474664524 mfu:3.1670667874705964 
Step 3337 | loss:1.1809301376342773 lr:1.8662800172600294e-05 tokens_per_second_per_gpu:214.46215326198643 mfu:3.538945545948456 
Step 3338 | loss:1.0884027481079102 lr:1.8618614605863284e-05 tokens_per_second_per_gpu:305.25614007460496 mfu:5.0371818097469525 
Step 3339 | loss:1.2432281970977783 lr:1.85744760376113e-05 tokens_per_second_per_gpu:236.66355490266915 mfu:3.905301801609689 
Step 3340 | loss:1.004568099975586 lr:1.853038449333475e-05 tokens_per_second_per_gpu:290.1766310040834 mfu:4.788347408671904 
Step 3341 | loss:1.3798840045928955 lr:1.848633999849688e-05 tokens_per_second_per_gpu:229.46913331450492 mfu:3.786583109999768 
Step 3342 | loss:1.0290892124176025 lr:1.8442342578533833e-05 tokens_per_second_per_gpu:289.26183090063563 mfu:4.773251841914376 
Step 3343 | loss:1.3122193813323975 lr:1.8398392258854425e-05 tokens_per_second_per_gpu:252.36459173510497 mfu:4.1643923381904875 
Step 3344 | loss:1.122172474861145 lr:1.835448906484043e-05 tokens_per_second_per_gpu:252.5411156894809 mfu:4.167305246844019 
Step 3345 | loss:1.190583348274231 lr:1.831063302184637e-05 tokens_per_second_per_gpu:332.77293054858507 mfu:5.491249912699034 
Step 3346 | loss:1.206847906112671 lr:1.8266824155199392e-05 tokens_per_second_per_gpu:272.2876949210417 mfu:4.493153269706508 
Step 3347 | loss:1.138208270072937 lr:1.8223062490199614e-05 tokens_per_second_per_gpu:287.13201154522034 mfu:4.738106644466348 
Step 3348 | loss:1.2751492261886597 lr:1.817934805211976e-05 tokens_per_second_per_gpu:209.48842668078913 mfu:3.456871635640415 
Step 3349 | loss:1.1580021381378174 lr:1.8135680866205306e-05 tokens_per_second_per_gpu:405.3159564578332 mfu:6.6883180877888435 
Step 3350 | loss:1.236139178276062 lr:1.8092060957674495e-05 tokens_per_second_per_gpu:247.67385337839025 mfu:4.0869881558570835 
Step 3351 | loss:1.1733801364898682 lr:1.8048488351718108e-05 tokens_per_second_per_gpu:205.36402365297283 mfu:3.3888128313107004 
Step 3352 | loss:1.1719096899032593 lr:1.8004963073499814e-05 tokens_per_second_per_gpu:238.03596163675778 mfu:3.927948560606366 
Step 3353 | loss:1.0063903331756592 lr:1.7961485148155834e-05 tokens_per_second_per_gpu:267.61457872458965 mfu:4.4160398793129545 
Step 3354 | loss:1.0176506042480469 lr:1.7918054600795053e-05 tokens_per_second_per_gpu:250.75090085734905 mfu:4.1377640307828125 
Step 3355 | loss:1.3307205438613892 lr:1.7874671456499002e-05 tokens_per_second_per_gpu:243.30404531959744 mfu:4.014879802326644 
Step 3356 | loss:1.194571852684021 lr:1.783133574032184e-05 tokens_per_second_per_gpu:223.17664571254005 mfu:3.682747675014156 
Step 3357 | loss:1.2380131483078003 lr:1.778804747729035e-05 tokens_per_second_per_gpu:261.0870987187403 mfu:4.308326719011199 
Step 3358 | loss:1.1080684661865234 lr:1.7744806692403894e-05 tokens_per_second_per_gpu:331.46587229825593 mfu:5.469681501196391 
Step 3359 | loss:1.1883832216262817 lr:1.7701613410634365e-05 tokens_per_second_per_gpu:196.8882231823463 mfu:3.248949476086297 
Step 3360 | loss:1.1038360595703125 lr:1.7658467656926326e-05 tokens_per_second_per_gpu:209.93452423906257 mfu:3.46423291101184 
Step 3361 | loss:1.2946258783340454 lr:1.761536945619684e-05 tokens_per_second_per_gpu:181.5605234053767 mfu:2.9960195580085025 
Step 3362 | loss:1.196526288986206 lr:1.7572318833335476e-05 tokens_per_second_per_gpu:221.5980448967405 mfu:3.656698405989612 
Step 3363 | loss:1.2623932361602783 lr:1.7529315813204382e-05 tokens_per_second_per_gpu:292.01909750713145 mfu:4.818750855272368 
Step 3364 | loss:1.1598992347717285 lr:1.748636042063819e-05 tokens_per_second_per_gpu:257.9092060435839 mfu:4.2558867478685585 
Step 3365 | loss:1.4519424438476562 lr:1.7443452680444018e-05 tokens_per_second_per_gpu:216.14640259200345 mfu:3.5667381731046754 
Step 3366 | loss:1.1948374509811401 lr:1.7400592617401467e-05 tokens_per_second_per_gpu:184.11291221818914 mfu:3.038137782055226 
Step 3367 | loss:1.024329662322998 lr:1.7357780256262622e-05 tokens_per_second_per_gpu:265.529297763586 mfu:4.381629631832225 
Step 3368 | loss:1.0708818435668945 lr:1.7315015621752006e-05 tokens_per_second_per_gpu:202.53267339787743 mfu:3.3420913272043347 
Step 3369 | loss:1.149878978729248 lr:1.7272298738566582e-05 tokens_per_second_per_gpu:270.2582115046545 mfu:4.459663764972189 
Step 3370 | loss:1.1362004280090332 lr:1.722962963137573e-05 tokens_per_second_per_gpu:232.40865014983802 mfu:3.8350895240845633 
Step 3371 | loss:1.2533209323883057 lr:1.7187008324821254e-05 tokens_per_second_per_gpu:263.9156295131345 mfu:4.355001697808838 
Step 3372 | loss:1.130905032157898 lr:1.714443484351733e-05 tokens_per_second_per_gpu:260.774513797587 mfu:4.303168601377759 
Step 3373 | loss:1.189384937286377 lr:1.710190921205055e-05 tokens_per_second_per_gpu:229.4988340002532 mfu:3.7870732156335216 
Step 3374 | loss:1.1135603189468384 lr:1.7059431454979824e-05 tokens_per_second_per_gpu:245.70437704394377 mfu:4.0544888575164295 
Step 3375 | loss:1.1123663187026978 lr:1.7017001596836456e-05 tokens_per_second_per_gpu:219.45692814125945 mfu:3.621366784582693 
Step 3376 | loss:1.1740753650665283 lr:1.697461966212408e-05 tokens_per_second_per_gpu:187.2141559344134 mfu:3.0893129310010887 
Step 3377 | loss:1.1067097187042236 lr:1.6932285675318626e-05 tokens_per_second_per_gpu:279.94323916799254 mfu:4.619481173266544 
Step 3378 | loss:1.0495907068252563 lr:1.688999966086836e-05 tokens_per_second_per_gpu:312.2456888438878 mfu:5.152519794137262 
Step 3379 | loss:1.1791212558746338 lr:1.684776164319385e-05 tokens_per_second_per_gpu:182.61031545856503 mfu:3.0133426933696605 
Step 3380 | loss:1.1958701610565186 lr:1.680557164668791e-05 tokens_per_second_per_gpu:356.3498089399683 mfu:5.880303587212072 
Step 3381 | loss:1.0483266115188599 lr:1.676342969571567e-05 tokens_per_second_per_gpu:271.0326368206953 mfu:4.472442938272404 
Step 3382 | loss:1.2288259267807007 lr:1.672133581461447e-05 tokens_per_second_per_gpu:232.17251061223695 mfu:3.8311928693503607 
Step 3383 | loss:1.1311615705490112 lr:1.6679290027693906e-05 tokens_per_second_per_gpu:253.749316680972 mfu:4.187242366062554 
Step 3384 | loss:1.3446153402328491 lr:1.6637292359235813e-05 tokens_per_second_per_gpu:206.2990310651472 mfu:3.404241848815253 
Step 3385 | loss:1.1855685710906982 lr:1.6595342833494208e-05 tokens_per_second_per_gpu:329.6778111348502 mfu:5.4401758238828375 
Step 3386 | loss:1.1636815071105957 lr:1.655344147469533e-05 tokens_per_second_per_gpu:181.13923014438126 mfu:2.989067590554755 
Step 3387 | loss:1.2114882469177246 lr:1.6511588307037595e-05 tokens_per_second_per_gpu:197.52843761702425 mfu:3.2595139695766133 
Step 3388 | loss:1.09829843044281 lr:1.646978335469157e-05 tokens_per_second_per_gpu:309.7111929197459 mfu:5.110696829453095 
Step 3389 | loss:1.0463465452194214 lr:1.642802664180001e-05 tokens_per_second_per_gpu:369.27988429863495 mfu:6.093669124689598 
Step 3390 | loss:0.9383924007415771 lr:1.638631819247779e-05 tokens_per_second_per_gpu:263.12420961261256 mfu:4.341942088505626 
Step 3391 | loss:1.1547274589538574 lr:1.63446580308119e-05 tokens_per_second_per_gpu:240.9844800618054 mfu:3.976603514353484 
Step 3392 | loss:1.0554940700531006 lr:1.6303046180861482e-05 tokens_per_second_per_gpu:289.16834148424647 mfu:4.771709127040485 
Step 3393 | loss:1.220808744430542 lr:1.6261482666657746e-05 tokens_per_second_per_gpu:226.76272589512706 mfu:3.74192334912052 
Step 3394 | loss:1.165733814239502 lr:1.621996751220399e-05 tokens_per_second_per_gpu:201.5378466277546 mfu:3.3256752010321065 
Step 3395 | loss:1.1447895765304565 lr:1.617850074147561e-05 tokens_per_second_per_gpu:265.28484802514214 mfu:4.3775958463837625 
Step 3396 | loss:1.2909388542175293 lr:1.6137082378420022e-05 tokens_per_second_per_gpu:196.70915354134524 mfu:3.2459945598048163 
Step 3397 | loss:1.250361442565918 lr:1.60957124469567e-05 tokens_per_second_per_gpu:334.0241598679478 mfu:5.51189706353366 
Step 3398 | loss:1.2057651281356812 lr:1.6054390970977174e-05 tokens_per_second_per_gpu:228.80008414211463 mfu:3.775542800310447 
Step 3399 | loss:1.3427517414093018 lr:1.601311797434496e-05 tokens_per_second_per_gpu:219.51681724698634 mfu:3.6223550441927883 
Step 3400 | loss:1.1642341613769531 lr:1.5971893480895583e-05 tokens_per_second_per_gpu:256.18971590612176 mfu:4.227512594803704 
Step 3401 | loss:1.0100743770599365 lr:1.5930717514436556e-05 tokens_per_second_per_gpu:283.55495821101397 mfu:4.679079926827988 
Step 3402 | loss:1.150918960571289 lr:1.5889590098747386e-05 tokens_per_second_per_gpu:241.221903567892 mfu:3.9805213564836164 
Step 3403 | loss:1.145319938659668 lr:1.5848511257579513e-05 tokens_per_second_per_gpu:238.62660144759815 mfu:3.937694998828871 
Step 3404 | loss:1.204672932624817 lr:1.5807481014656355e-05 tokens_per_second_per_gpu:205.86050138954425 mfu:3.397005454800569 
Step 3405 | loss:1.260869026184082 lr:1.5766499393673205e-05 tokens_per_second_per_gpu:290.2011102194105 mfu:4.78875135225231 
Step 3406 | loss:1.2052249908447266 lr:1.57255664182974e-05 tokens_per_second_per_gpu:230.53240324455348 mfu:3.8041286504406018 
Step 3407 | loss:1.206093430519104 lr:1.5684682112168026e-05 tokens_per_second_per_gpu:174.37798713054158 mfu:2.877496991803594 
Step 3408 | loss:1.2134759426116943 lr:1.5643846498896175e-05 tokens_per_second_per_gpu:188.9842002699245 mfu:3.1185213037699473 
Step 3409 | loss:1.2806413173675537 lr:1.5603059602064772e-05 tokens_per_second_per_gpu:259.6173021463548 mfu:4.284072882359005 
Step 3410 | loss:1.3568837642669678 lr:1.5562321445228624e-05 tokens_per_second_per_gpu:214.61142415881045 mfu:3.541408738485788 
Step 3411 | loss:1.0276858806610107 lr:1.552163205191438e-05 tokens_per_second_per_gpu:229.24223724954794 mfu:3.782838986357161 
Step 3412 | loss:1.126035213470459 lr:1.5480991445620542e-05 tokens_per_second_per_gpu:246.64989952251688 mfu:4.070091389306983 
Step 3413 | loss:0.9468986988067627 lr:1.5440399649817385e-05 tokens_per_second_per_gpu:228.59278296357425 mfu:3.7721220215329017 
Step 3414 | loss:1.1584811210632324 lr:1.5399856687947123e-05 tokens_per_second_per_gpu:251.61535731919335 mfu:4.152028852331877 
Step 3415 | loss:1.0974421501159668 lr:1.53593625834236e-05 tokens_per_second_per_gpu:241.8034991284363 mfu:3.990118551080545 
Step 3416 | loss:1.1920106410980225 lr:1.5318917359632568e-05 tokens_per_second_per_gpu:302.3103118593331 mfu:4.988571248475425 
Step 3417 | loss:1.1309292316436768 lr:1.527852103993149e-05 tokens_per_second_per_gpu:271.81845764787374 mfu:4.485410154510596 
Step 3418 | loss:1.2693995237350464 lr:1.5238173647649601e-05 tokens_per_second_per_gpu:284.73659907324304 mfu:4.698578764281084 
Step 3419 | loss:1.3508129119873047 lr:1.5197875206087941e-05 tokens_per_second_per_gpu:255.53550868963086 mfu:4.21671719953366 
Step 3420 | loss:1.1413993835449219 lr:1.5157625738519165e-05 tokens_per_second_per_gpu:238.00127631067514 mfu:3.9273762009690922 
Step 3421 | loss:1.0988850593566895 lr:1.511742526818769e-05 tokens_per_second_per_gpu:318.49912236222156 mfu:5.255710778467058 
Step 3422 | loss:1.1049561500549316 lr:1.5077273818309723e-05 tokens_per_second_per_gpu:208.4640542616466 mfu:3.439967962171799 
Step 3423 | loss:1.4373855590820312 lr:1.5037171412073026e-05 tokens_per_second_per_gpu:323.7772862913573 mfu:5.342808359292811 
Step 3424 | loss:1.0864038467407227 lr:1.4997118072637129e-05 tokens_per_second_per_gpu:223.1117889265446 mfu:3.681677441266933 
Step 3425 | loss:1.0845832824707031 lr:1.4957113823133184e-05 tokens_per_second_per_gpu:209.59532738221765 mfu:3.4586356567295673 
Step 3426 | loss:1.15516996383667 lr:1.491715868666399e-05 tokens_per_second_per_gpu:340.29743313671185 mfu:5.615415433350127 
Step 3427 | loss:1.2749996185302734 lr:1.4877252686304066e-05 tokens_per_second_per_gpu:206.65807199676217 mfu:3.4101665599422546 
Step 3428 | loss:1.2916529178619385 lr:1.4837395845099423e-05 tokens_per_second_per_gpu:293.6895915676961 mfu:4.846316499957221 
Step 3429 | loss:0.9999440908432007 lr:1.4797588186067735e-05 tokens_per_second_per_gpu:223.09410294698242 mfu:3.6813855962134103 
Step 3430 | loss:1.224237322807312 lr:1.4757829732198369e-05 tokens_per_second_per_gpu:221.4004728627297 mfu:3.653438172614485 
Step 3431 | loss:1.2928688526153564 lr:1.4718120506452094e-05 tokens_per_second_per_gpu:246.38925300777015 mfu:4.065790332880941 
Step 3432 | loss:1.100048542022705 lr:1.467846053176144e-05 tokens_per_second_per_gpu:301.86322819570046 mfu:4.981193700894122 
Step 3433 | loss:1.2600159645080566 lr:1.4638849831030322e-05 tokens_per_second_per_gpu:241.72249584044195 mfu:3.988781875956778 
Step 3434 | loss:1.0854673385620117 lr:1.4599288427134283e-05 tokens_per_second_per_gpu:212.2439752813304 mfu:3.5023422993365747 
Step 3435 | loss:1.3610118627548218 lr:1.4559776342920462e-05 tokens_per_second_per_gpu:190.24606785024497 mfu:3.1393440017846252 
Step 3436 | loss:1.3118259906768799 lr:1.452031360120737e-05 tokens_per_second_per_gpu:237.6995218248901 mfu:3.922396801680238 
Step 3437 | loss:1.2560865879058838 lr:1.448090022478511e-05 tokens_per_second_per_gpu:229.11404151462168 mfu:3.7807235654391746 
Step 3438 | loss:1.1790118217468262 lr:1.4441536236415321e-05 tokens_per_second_per_gpu:217.82128134481786 mfu:3.5943761717544205 
Step 3439 | loss:1.2703766822814941 lr:1.4402221658830961e-05 tokens_per_second_per_gpu:212.66306118254025 mfu:3.5092578420600713 
Step 3440 | loss:1.0431597232818604 lr:1.436295651473667e-05 tokens_per_second_per_gpu:300.12268364060805 mfu:4.952472118521289 
Step 3441 | loss:1.1193493604660034 lr:1.4323740826808329e-05 tokens_per_second_per_gpu:224.00589845799752 mfu:3.6964315827123935 
Step 3442 | loss:1.0471059083938599 lr:1.4284574617693369e-05 tokens_per_second_per_gpu:234.21018918420043 mfu:3.8648176063803743 
Step 3443 | loss:1.1351726055145264 lr:1.4245457910010696e-05 tokens_per_second_per_gpu:240.652662506357 mfu:3.971128029555534 
Step 3444 | loss:1.0948009490966797 lr:1.420639072635046e-05 tokens_per_second_per_gpu:346.3514688719746 mfu:5.715316056720948 
Step 3445 | loss:1.099266767501831 lr:1.4167373089274393e-05 tokens_per_second_per_gpu:230.77682381706904 mfu:3.8081619546077268 
Step 3446 | loss:1.151102066040039 lr:1.4128405021315527e-05 tokens_per_second_per_gpu:230.82026008541987 mfu:3.808878717850446 
Step 3447 | loss:1.2866588830947876 lr:1.4089486544978203e-05 tokens_per_second_per_gpu:201.06271249600655 mfu:3.3178347788704223 
Step 3448 | loss:1.007941722869873 lr:1.4050617682738287e-05 tokens_per_second_per_gpu:244.41684363961028 mfu:4.033242635107389 
Step 3449 | loss:1.213982105255127 lr:1.4011798457042801e-05 tokens_per_second_per_gpu:231.0293148138602 mfu:3.8123284328179614 
Step 3450 | loss:1.008117437362671 lr:1.397302889031028e-05 tokens_per_second_per_gpu:236.36410065697336 mfu:3.90036035971469 
Step 3451 | loss:1.162155032157898 lr:1.393430900493049e-05 tokens_per_second_per_gpu:248.57666441761364 mfu:4.101885885165013 
Step 3452 | loss:1.3591699600219727 lr:1.3895638823264446e-05 tokens_per_second_per_gpu:243.45275212488016 mfu:4.017333686511816 
Step 3453 | loss:1.238526701927185 lr:1.3857018367644592e-05 tokens_per_second_per_gpu:232.63823529396637 mfu:3.838878021546101 
Step 3454 | loss:1.2262612581253052 lr:1.38184476603746e-05 tokens_per_second_per_gpu:362.41230232811546 mfu:5.980343774475865 
Step 3455 | loss:1.1714370250701904 lr:1.3779926723729319e-05 tokens_per_second_per_gpu:193.32596154575683 mfu:3.1901668435305606 
Step 3456 | loss:1.0910015106201172 lr:1.3741455579955054e-05 tokens_per_second_per_gpu:248.70083754519874 mfu:4.103934927059397 
Step 3457 | loss:1.0398740768432617 lr:1.3703034251269109e-05 tokens_per_second_per_gpu:237.3682667107511 mfu:3.9169305980031592 
Step 3458 | loss:1.1948355436325073 lr:1.3664662759860258e-05 tokens_per_second_per_gpu:261.5374855203304 mfu:4.315758773297691 
Step 3459 | loss:1.2013099193572998 lr:1.3626341127888354e-05 tokens_per_second_per_gpu:310.35680669081336 mfu:5.121350420050645 
Step 3460 | loss:1.0696340799331665 lr:1.3588069377484426e-05 tokens_per_second_per_gpu:298.0141964953031 mfu:4.917678934371678 
Step 3461 | loss:1.1519900560379028 lr:1.3549847530750825e-05 tokens_per_second_per_gpu:339.9030574652246 mfu:5.608907646289278 
Step 3462 | loss:1.256615161895752 lr:1.3511675609760987e-05 tokens_per_second_per_gpu:191.33638186996788 mfu:3.15733581005986 
Step 3463 | loss:1.2918962240219116 lr:1.3473553636559555e-05 tokens_per_second_per_gpu:264.21026837970504 mfu:4.359863678762836 
Step 3464 | loss:1.2908074855804443 lr:1.3435481633162317e-05 tokens_per_second_per_gpu:407.7380222790228 mfu:6.728285788007828 
Step 3465 | loss:1.216067910194397 lr:1.339745962155613e-05 tokens_per_second_per_gpu:249.74891944987925 mfu:4.12122984241832 
Step 3466 | loss:1.179091453552246 lr:1.335948762369914e-05 tokens_per_second_per_gpu:247.16104358653908 mfu:4.0785260290846574 
Step 3467 | loss:1.2878334522247314 lr:1.3321565661520496e-05 tokens_per_second_per_gpu:241.78283562470457 mfu:3.9897775724352083 
Step 3468 | loss:1.1623784303665161 lr:1.3283693756920412e-05 tokens_per_second_per_gpu:213.85073887505828 mfu:3.5288562962209995 
Step 3469 | loss:1.179962396621704 lr:1.3245871931770327e-05 tokens_per_second_per_gpu:178.0201090931135 mfu:2.9375974389043904 
Step 3470 | loss:1.0629428625106812 lr:1.3208100207912666e-05 tokens_per_second_per_gpu:339.8452098915463 mfu:5.6079530750043265 
Step 3471 | loss:1.1927545070648193 lr:1.3170378607160926e-05 tokens_per_second_per_gpu:207.9125430160249 mfu:3.430867203662445 
Step 3472 | loss:1.115462064743042 lr:1.3132707151299706e-05 tokens_per_second_per_gpu:295.52526942773204 mfu:4.876607923818076 
Step 3473 | loss:1.0359073877334595 lr:1.3095085862084545e-05 tokens_per_second_per_gpu:241.04595427994133 mfu:3.977617930683609 
Step 3474 | loss:1.2289358377456665 lr:1.3057514761242152e-05 tokens_per_second_per_gpu:205.47726046988635 mfu:3.390681407760009 
Step 3475 | loss:1.1755144596099854 lr:1.3019993870470137e-05 tokens_per_second_per_gpu:272.1071222072674 mfu:4.490173550481407 
Step 3476 | loss:1.2204675674438477 lr:1.2982523211437158e-05 tokens_per_second_per_gpu:206.09347204608392 mfu:3.400849818268703 
Step 3477 | loss:0.9499944448471069 lr:1.2945102805782871e-05 tokens_per_second_per_gpu:270.6730828112896 mfu:4.466509760596248 
Step 3478 | loss:1.2676236629486084 lr:1.290773267511788e-05 tokens_per_second_per_gpu:267.23204938981183 mfu:4.409727574484732 
Step 3479 | loss:1.1373835802078247 lr:1.2870412841023793e-05 tokens_per_second_per_gpu:342.128516779632 mfu:5.6456310457731504 
Step 3480 | loss:1.1301658153533936 lr:1.2833143325053154e-05 tokens_per_second_per_gpu:305.65802702600973 mfu:5.043813544134657 
Step 3481 | loss:1.4137845039367676 lr:1.2795924148729388e-05 tokens_per_second_per_gpu:292.20199406681945 mfu:4.8217689214226525 
Step 3482 | loss:1.2096529006958008 lr:1.275875533354698e-05 tokens_per_second_per_gpu:219.4063122753959 mfu:3.6205315472677277 
Step 3483 | loss:1.2768925428390503 lr:1.2721636900971213e-05 tokens_per_second_per_gpu:251.23612867897552 mfu:4.1457710138891395 
Step 3484 | loss:1.017539143562317 lr:1.268456887243834e-05 tokens_per_second_per_gpu:294.99282411680576 mfu:4.867821781681092 
Step 3485 | loss:1.2894889116287231 lr:1.2647551269355473e-05 tokens_per_second_per_gpu:226.96097818357183 mfu:3.7451948077088733 
Step 3486 | loss:1.223705768585205 lr:1.261058411310061e-05 tokens_per_second_per_gpu:259.23058781827336 mfu:4.27769151889649 
Step 3487 | loss:1.1047390699386597 lr:1.2573667425022606e-05 tokens_per_second_per_gpu:306.0658847703941 mfu:5.050543805516051 
Step 3488 | loss:0.9827439188957214 lr:1.2536801226441208e-05 tokens_per_second_per_gpu:287.30615832024415 mfu:4.740980326113379 
Step 3489 | loss:1.1465747356414795 lr:1.2499985538646963e-05 tokens_per_second_per_gpu:199.88930609237238 mfu:3.298471822271475 
Step 3490 | loss:1.0782052278518677 lr:1.2463220382901263e-05 tokens_per_second_per_gpu:246.44662318449707 mfu:4.066737026403831 
Step 3491 | loss:1.2981692552566528 lr:1.2426505780436326e-05 tokens_per_second_per_gpu:288.24967953491534 mfu:4.756549834063295 
Step 3492 | loss:1.1064939498901367 lr:1.2389841752455156e-05 tokens_per_second_per_gpu:225.39627210562892 mfu:3.7193748225924783 
Step 3493 | loss:1.4929206371307373 lr:1.235322832013156e-05 tokens_per_second_per_gpu:277.95746442223077 mfu:4.58671292681895 
Step 3494 | loss:1.194583535194397 lr:1.2316665504610137e-05 tokens_per_second_per_gpu:259.3588400164381 mfu:4.2798078715421655 
Step 3495 | loss:1.0263102054595947 lr:1.2280153327006227e-05 tokens_per_second_per_gpu:158.48894478088985 mfu:2.6153040836497934 
Step 3496 | loss:1.1942799091339111 lr:1.2243691808405954e-05 tokens_per_second_per_gpu:218.42462805533393 mfu:3.604332292782615 
Step 3497 | loss:1.1673762798309326 lr:1.2207280969866175e-05 tokens_per_second_per_gpu:296.61349120251566 mfu:4.894565206929797 
Step 3498 | loss:1.1575648784637451 lr:1.2170920832414479e-05 tokens_per_second_per_gpu:242.13608265373603 mfu:3.9956066755240096 
Step 3499 | loss:1.4614852666854858 lr:1.213461141704917e-05 tokens_per_second_per_gpu:176.62159404034404 mfu:2.9145198536910484 
Step 3500 | loss:1.2274049520492554 lr:1.2098352744739261e-05 tokens_per_second_per_gpu:245.04164122374033 mfu:4.043552727558878 
Step 3501 | loss:1.379711389541626 lr:1.206214483642446e-05 tokens_per_second_per_gpu:200.84168892757114 mfu:3.314187560183269 
Step 3502 | loss:1.267430305480957 lr:1.2025987713015175e-05 tokens_per_second_per_gpu:233.2529232404796 mfu:3.8490212898914664 
Step 3503 | loss:1.3453670740127563 lr:1.1989881395392455e-05 tokens_per_second_per_gpu:138.40780201070086 mfu:2.283935263169374 
Step 3504 | loss:1.2224600315093994 lr:1.1953825904408034e-05 tokens_per_second_per_gpu:208.0356700034071 mfu:3.4328989826824476 
Step 3505 | loss:1.128283977508545 lr:1.1917821260884276e-05 tokens_per_second_per_gpu:222.35513316930252 mfu:3.669191492202359 
Step 3506 | loss:1.2071480751037598 lr:1.1881867485614196e-05 tokens_per_second_per_gpu:266.171285289846 mfu:4.3922233839794265 
Step 3507 | loss:1.0112172365188599 lr:1.1845964599361426e-05 tokens_per_second_per_gpu:284.8928027074418 mfu:4.7011563573300235 
Step 3508 | loss:1.144587516784668 lr:1.1810112622860193e-05 tokens_per_second_per_gpu:278.8882949891183 mfu:4.602073020143646 
Step 3509 | loss:1.1697770357131958 lr:1.1774311576815356e-05 tokens_per_second_per_gpu:215.3281390839347 mfu:3.553235604221323 
Step 3510 | loss:1.0585644245147705 lr:1.1738561481902322e-05 tokens_per_second_per_gpu:272.01778739799215 mfu:4.488699392824336 
Step 3511 | loss:1.017831563949585 lr:1.1702862358767119e-05 tokens_per_second_per_gpu:254.09537100286656 mfu:4.192952778750749 
Step 3512 | loss:1.002619743347168 lr:1.166721422802628e-05 tokens_per_second_per_gpu:266.72215835035036 mfu:4.4013136114820535 
Step 3513 | loss:1.2916287183761597 lr:1.1631617110266956e-05 tokens_per_second_per_gpu:218.77892027674417 mfu:3.6101786431052862 
Step 3514 | loss:1.3225698471069336 lr:1.1596071026046785e-05 tokens_per_second_per_gpu:222.71958635746864 mfu:3.67520551363854 
Step 3515 | loss:1.2325359582901 lr:1.1560575995893952e-05 tokens_per_second_per_gpu:292.66854844280726 mfu:4.829467764811713 
Step 3516 | loss:1.2713576555252075 lr:1.1525132040307162e-05 tokens_per_second_per_gpu:339.1316598008695 mfu:5.596178433759691 
Step 3517 | loss:0.9753817915916443 lr:1.148973917975562e-05 tokens_per_second_per_gpu:251.95609586355414 mfu:4.157651546758643 
Step 3518 | loss:1.2079188823699951 lr:1.1454397434679021e-05 tokens_per_second_per_gpu:226.3985107851451 mfu:3.735913256329634 
Step 3519 | loss:1.2190792560577393 lr:1.1419106825487536e-05 tokens_per_second_per_gpu:244.08102612878523 mfu:4.027701145077053 
Step 3520 | loss:1.1371748447418213 lr:1.1383867372561819e-05 tokens_per_second_per_gpu:241.84179961968567 mfu:3.9907505663375633 
Step 3521 | loss:1.1621979475021362 lr:1.1348679096252968e-05 tokens_per_second_per_gpu:269.3061772285722 mfu:4.4439537788059305 
Step 3522 | loss:1.277715802192688 lr:1.131354201688254e-05 tokens_per_second_per_gpu:224.67866647763057 mfu:3.707533258930427 
Step 3523 | loss:1.0761916637420654 lr:1.1278456154742501e-05 tokens_per_second_per_gpu:218.95303327339354 mfu:3.6130517673587357 
Step 3524 | loss:1.119425892829895 lr:1.1243421530095266e-05 tokens_per_second_per_gpu:303.3170807443428 mfu:5.005184437363126 
Step 3525 | loss:1.0624096393585205 lr:1.120843816317363e-05 tokens_per_second_per_gpu:239.78753362624823 mfu:3.956852112101734 
Step 3526 | loss:1.1778208017349243 lr:1.1173506074180828e-05 tokens_per_second_per_gpu:167.5295743626929 mfu:2.7644879620379186 
Step 3527 | loss:1.2179969549179077 lr:1.1138625283290415e-05 tokens_per_second_per_gpu:201.9502879893829 mfu:3.3324810989376283 
Step 3528 | loss:1.1099905967712402 lr:1.1103795810646433e-05 tokens_per_second_per_gpu:279.8803102114186 mfu:4.618442751581454 
Step 3529 | loss:1.0519975423812866 lr:1.1069017676363147e-05 tokens_per_second_per_gpu:273.4593968370734 mfu:4.512488099716604 
Step 3530 | loss:1.2597126960754395 lr:1.103429090052528e-05 tokens_per_second_per_gpu:349.52678319282137 mfu:5.767713481170098 
Step 3531 | loss:1.1694350242614746 lr:1.0999615503187854e-05 tokens_per_second_per_gpu:271.77655370978914 mfu:4.484718677003788 
Step 3532 | loss:1.2066258192062378 lr:1.096499150437621e-05 tokens_per_second_per_gpu:237.65437345609422 mfu:3.9216517862254046 
Step 3533 | loss:1.2344977855682373 lr:1.0930418924086039e-05 tokens_per_second_per_gpu:221.948946908365 mfu:3.662488812792 
Step 3534 | loss:1.26003897190094 lr:1.0895897782283305e-05 tokens_per_second_per_gpu:279.21558900401953 mfu:4.60747385977261 
Step 3535 | loss:1.2263914346694946 lr:1.0861428098904258e-05 tokens_per_second_per_gpu:275.74128982642145 mfu:4.550142739046459 
Step 3536 | loss:1.1382174491882324 lr:1.0827009893855522e-05 tokens_per_second_per_gpu:343.7993656986367 mfu:5.67320254615178 
Step 3537 | loss:1.446421504020691 lr:1.0792643187013862e-05 tokens_per_second_per_gpu:244.41775428613673 mfu:4.033257662133929 
Step 3538 | loss:1.2337284088134766 lr:1.0758327998226369e-05 tokens_per_second_per_gpu:288.98700573516055 mfu:4.768716816594153 
Step 3539 | loss:1.048030972480774 lr:1.0724064347310393e-05 tokens_per_second_per_gpu:269.6061054415011 mfu:4.4489030418675215 
Step 3540 | loss:1.117489218711853 lr:1.0689852254053456e-05 tokens_per_second_per_gpu:242.83802636076203 mfu:4.007189794119539 
Step 3541 | loss:1.4544734954833984 lr:1.0655691738213424e-05 tokens_per_second_per_gpu:216.65008456115694 mfu:3.5750496771821934 
Step 3542 | loss:1.1853506565093994 lr:1.062158281951826e-05 tokens_per_second_per_gpu:219.59568183992565 mfu:3.6236564276568197 
Step 3543 | loss:1.0586612224578857 lr:1.0587525517666142e-05 tokens_per_second_per_gpu:338.47800200267966 mfu:5.585392104711449 
Step 3544 | loss:1.3097349405288696 lr:1.0553519852325555e-05 tokens_per_second_per_gpu:244.08527750251255 mfu:4.027771299087388 
Step 3545 | loss:1.082110047340393 lr:1.0519565843135004e-05 tokens_per_second_per_gpu:171.33567902303884 mfu:2.8272943683444454 
Step 3546 | loss:1.0698676109313965 lr:1.048566350970326e-05 tokens_per_second_per_gpu:278.16253090505654 mfu:4.590096829782626 
Step 3547 | loss:1.0359166860580444 lr:1.0451812871609224e-05 tokens_per_second_per_gpu:212.7131257950663 mfu:3.5100839828723958 
Step 3548 | loss:1.2715766429901123 lr:1.0418013948401917e-05 tokens_per_second_per_gpu:253.19935448842537 mfu:4.178167169240412 
Step 3549 | loss:1.3624529838562012 lr:1.0384266759600602e-05 tokens_per_second_per_gpu:250.52918111852824 mfu:4.134105324245486 
Step 3550 | loss:1.1081558465957642 lr:1.0350571324694525e-05 tokens_per_second_per_gpu:273.2832250436303 mfu:4.509581002243952 
Step 3551 | loss:1.1501973867416382 lr:1.0316927663143084e-05 tokens_per_second_per_gpu:342.85566792212836 mfu:5.657630124668089 
Step 3552 | loss:1.2332457304000854 lr:1.028333579437587e-05 tokens_per_second_per_gpu:210.67732702173882 mfu:3.4764902653248826 
Step 3553 | loss:1.1995823383331299 lr:1.0249795737792412e-05 tokens_per_second_per_gpu:302.23895762257496 mfu:4.987393797095221 
Step 3554 | loss:1.2113703489303589 lr:1.0216307512762469e-05 tokens_per_second_per_gpu:270.48958164547565 mfu:4.4634817175427015 
Step 3555 | loss:1.1902527809143066 lr:1.0182871138625727e-05 tokens_per_second_per_gpu:266.11627843650916 mfu:4.391315688818987 
Step 3556 | loss:1.1348578929901123 lr:1.0149486634692018e-05 tokens_per_second_per_gpu:242.0888716927747 mfu:3.9948276242206777 
Step 3557 | loss:1.1489369869232178 lr:1.011615402024123e-05 tokens_per_second_per_gpu:268.53414131631007 mfu:4.431214034233494 
Step 3558 | loss:1.3295316696166992 lr:1.008287331452321e-05 tokens_per_second_per_gpu:204.1019886368407 mfu:3.367987370355285 
Step 3559 | loss:1.243098497390747 lr:1.0049644536757873e-05 tokens_per_second_per_gpu:218.22045328233298 mfu:3.6009631043616444 
Step 3560 | loss:1.1625924110412598 lr:1.0016467706135135e-05 tokens_per_second_per_gpu:351.39658826127584 mfu:5.798568054893954 
Step 3561 | loss:1.2762577533721924 lr:9.983342841814902e-06 tokens_per_second_per_gpu:280.8783403480781 mfu:4.63491173808155 
Step 3562 | loss:1.1758571863174438 lr:9.95026996292714e-06 tokens_per_second_per_gpu:233.2426477835055 mfu:3.848851729518515 
Step 3563 | loss:1.2336978912353516 lr:9.917249088571678e-06 tokens_per_second_per_gpu:242.2862206699911 mfu:3.9980841768258566 
Step 3564 | loss:1.388728141784668 lr:9.884280237818366e-06 tokens_per_second_per_gpu:247.78723736680485 mfu:4.088859160855768 
Step 3565 | loss:1.2987265586853027 lr:9.851363429707072e-06 tokens_per_second_per_gpu:258.0108610192704 mfu:4.257564206655377 
Step 3566 | loss:1.0933784246444702 lr:9.818498683247479e-06 tokens_per_second_per_gpu:217.929698036827 mfu:3.596165208950292 
Step 3567 | loss:1.179119348526001 lr:9.785686017419348e-06 tokens_per_second_per_gpu:287.999781266364 mfu:4.752426139737845 
Step 3568 | loss:1.1841816902160645 lr:9.752925451172224e-06 tokens_per_second_per_gpu:216.37753327187886 mfu:3.5705521742122643 
Step 3569 | loss:1.2732694149017334 lr:9.720217003425647e-06 tokens_per_second_per_gpu:183.10200074720288 mfu:3.0214562343174087 
Step 3570 | loss:1.155610203742981 lr:9.687560693069075e-06 tokens_per_second_per_gpu:241.29763203937756 mfu:3.981770989263988 
Step 3571 | loss:1.208736777305603 lr:9.65495653896179e-06 tokens_per_second_per_gpu:249.85441802293087 mfu:4.122970726297019 
Step 3572 | loss:1.1331323385238647 lr:9.622404559932963e-06 tokens_per_second_per_gpu:215.79939208041515 mfu:3.5610119818597217 
Step 3573 | loss:1.0369123220443726 lr:9.589904774781734e-06 tokens_per_second_per_gpu:410.2235402859428 mfu:6.769300543973739 
Step 3574 | loss:1.1044596433639526 lr:9.557457202276921e-06 tokens_per_second_per_gpu:265.65705787236516 mfu:4.383737864268751 
Step 3575 | loss:1.1288000345230103 lr:9.525061861157392e-06 tokens_per_second_per_gpu:236.34857134648985 mfu:3.900104102919114 
Step 3576 | loss:1.1651084423065186 lr:9.49271877013168e-06 tokens_per_second_per_gpu:235.6427007539909 mfu:3.8884561848536427 
Step 3577 | loss:1.1292694807052612 lr:9.460427947878214e-06 tokens_per_second_per_gpu:250.04705649998976 mfu:4.1261495486206625 
Step 3578 | loss:1.049443006515503 lr:9.428189413045285e-06 tokens_per_second_per_gpu:255.77743231939695 mfu:4.220709300419519 
Step 3579 | loss:1.282549262046814 lr:9.396003184250878e-06 tokens_per_second_per_gpu:274.72902337638436 mfu:4.533438832132424 
Step 3580 | loss:1.2782808542251587 lr:9.363869280082871e-06 tokens_per_second_per_gpu:202.22151643754876 mfu:3.3369567730552823 
Step 3581 | loss:0.9782211780548096 lr:9.331787719098894e-06 tokens_per_second_per_gpu:215.57367240886788 mfu:3.5572872704637706 
Step 3582 | loss:1.2017974853515625 lr:9.299758519826273e-06 tokens_per_second_per_gpu:173.36709768823476 mfu:2.860815807571858 
Step 3583 | loss:1.164826512336731 lr:9.267781700762246e-06 tokens_per_second_per_gpu:252.42158886355858 mfu:4.1653328758602095 
Step 3584 | loss:1.2551391124725342 lr:9.23585728037366e-06 tokens_per_second_per_gpu:272.65627201152256 mfu:4.499235341684505 
Step 3585 | loss:0.9776473045349121 lr:9.203985277097138e-06 tokens_per_second_per_gpu:249.89957703247626 mfu:4.123715917340097 
Step 3586 | loss:1.2000195980072021 lr:9.17216570933912e-06 tokens_per_second_per_gpu:247.0514253395683 mfu:4.0767171644389775 
Step 3587 | loss:1.3476060628890991 lr:9.140398595475618e-06 tokens_per_second_per_gpu:226.05106184207497 mfu:3.730179830311009 
Step 3588 | loss:1.2609914541244507 lr:9.108683953852482e-06 tokens_per_second_per_gpu:274.8475069128474 mfu:4.535393987283374 
Step 3589 | loss:0.8789768815040588 lr:9.077021802785202e-06 tokens_per_second_per_gpu:275.5497803892739 mfu:4.546982547566089 
Step 3590 | loss:1.123345136642456 lr:9.045412160558908e-06 tokens_per_second_per_gpu:233.03303037001658 mfu:3.845392729408068 
Step 3591 | loss:1.3990633487701416 lr:9.01385504542851e-06 tokens_per_second_per_gpu:240.820282762796 mfu:3.9738940139071453 
Step 3592 | loss:1.0751420259475708 lr:8.982350475618474e-06 tokens_per_second_per_gpu:196.70254677093817 mfu:3.2458855382345786 
Step 3593 | loss:1.2800248861312866 lr:8.950898469323022e-06 tokens_per_second_per_gpu:238.91953648263103 mfu:3.9425288640200664 
Step 3594 | loss:1.0965280532836914 lr:8.919499044705959e-06 tokens_per_second_per_gpu:244.2975416948091 mfu:4.031273974997643 
Step 3595 | loss:1.3221365213394165 lr:8.888152219900691e-06 tokens_per_second_per_gpu:252.4501578635458 mfu:4.165804306990221 
Step 3596 | loss:1.3039321899414062 lr:8.85685801301036e-06 tokens_per_second_per_gpu:244.43222157833063 mfu:4.0334963940429995 
Step 3597 | loss:1.243030071258545 lr:8.825616442107632e-06 tokens_per_second_per_gpu:264.09825295653565 mfu:4.35801525713285 
Step 3598 | loss:1.1983634233474731 lr:8.79442752523475e-06 tokens_per_second_per_gpu:192.6792052342925 mfu:3.1794943993115816 
Step 3599 | loss:1.2184090614318848 lr:8.763291280403674e-06 tokens_per_second_per_gpu:301.5391355278652 mfu:4.9758456882687465 
Step 3600 | loss:1.4902701377868652 lr:8.732207725595787e-06 tokens_per_second_per_gpu:237.72784693477925 mfu:3.922864208259702 
Step 3601 | loss:1.1208713054656982 lr:8.701176878762175e-06 tokens_per_second_per_gpu:280.8352042931298 mfu:4.634199928807947 
Step 3602 | loss:1.1603672504425049 lr:8.670198757823434e-06 tokens_per_second_per_gpu:326.9846619509497 mfu:5.395734843672701 
Step 3603 | loss:1.1619291305541992 lr:8.639273380669666e-06 tokens_per_second_per_gpu:201.15569641953354 mfu:3.3193691523577975 
Step 3604 | loss:1.385848879814148 lr:8.608400765160596e-06 tokens_per_second_per_gpu:274.6758895627571 mfu:4.5325620449221145 
Step 3605 | loss:1.2531976699829102 lr:8.577580929125418e-06 tokens_per_second_per_gpu:207.16794785406208 mfu:3.4185802724166128 
Step 3606 | loss:1.16616952419281 lr:8.54681389036287e-06 tokens_per_second_per_gpu:255.968040009441 mfu:4.223854611727109 
Step 3607 | loss:1.0438066720962524 lr:8.51609966664122e-06 tokens_per_second_per_gpu:294.87603441982145 mfu:4.865894577409061 
Step 3608 | loss:1.1494572162628174 lr:8.485438275698154e-06 tokens_per_second_per_gpu:321.72041183022515 mfu:5.3088668614477035 
Step 3609 | loss:1.2072951793670654 lr:8.454829735240943e-06 tokens_per_second_per_gpu:278.4963361504722 mfu:4.595605114431036 
Step 3610 | loss:1.1927176713943481 lr:8.424274062946292e-06 tokens_per_second_per_gpu:188.7685597160553 mfu:3.114962912855589 
Step 3611 | loss:1.1763122081756592 lr:8.393771276460371e-06 tokens_per_second_per_gpu:175.9205009019475 mfu:2.9029507707471103 
Step 3612 | loss:1.16254460811615 lr:8.363321393398827e-06 tokens_per_second_per_gpu:270.88100210048395 mfu:4.4699407391219195 
Step 3613 | loss:1.0982029438018799 lr:8.332924431346722e-06 tokens_per_second_per_gpu:246.75169221539696 mfu:4.071771120632993 
Step 3614 | loss:1.0574822425842285 lr:8.302580407858584e-06 tokens_per_second_per_gpu:303.2892642449947 mfu:5.00472542361653 
Step 3615 | loss:1.1387372016906738 lr:8.272289340458383e-06 tokens_per_second_per_gpu:226.97646512054015 mfu:3.7454503652782196 
Step 3616 | loss:1.3760969638824463 lr:8.242051246639426e-06 tokens_per_second_per_gpu:186.66396580259666 mfu:3.0802339728408623 
Step 3617 | loss:1.122004508972168 lr:8.211866143864533e-06 tokens_per_second_per_gpu:246.7469501662471 mfu:4.071692869746008 
Step 3618 | loss:1.077444076538086 lr:8.18173404956587e-06 tokens_per_second_per_gpu:288.6567613187302 mfu:4.763267290937415 
Step 3619 | loss:1.0726946592330933 lr:8.151654981144996e-06 tokens_per_second_per_gpu:328.5836354315559 mfu:5.42212029206633 
Step 3620 | loss:0.9934683442115784 lr:8.121628955972826e-06 tokens_per_second_per_gpu:192.97288444618383 mfu:3.1843405445313904 
Step 3621 | loss:1.2451601028442383 lr:8.091655991389668e-06 tokens_per_second_per_gpu:193.8501876766014 mfu:3.1988173569316634 
Step 3622 | loss:1.3069063425064087 lr:8.061736104705176e-06 tokens_per_second_per_gpu:240.23342843572945 mfu:3.964210041815549 
Step 3623 | loss:1.3497663736343384 lr:8.031869313198371e-06 tokens_per_second_per_gpu:202.50119100120764 mfu:3.341571820681735 
Step 3624 | loss:1.286146640777588 lr:8.002055634117578e-06 tokens_per_second_per_gpu:200.384211866001 mfu:3.306638506027129 
Step 3625 | loss:1.3670921325683594 lr:7.972295084680482e-06 tokens_per_second_per_gpu:222.07320640309808 mfu:3.664539279873202 
Step 3626 | loss:1.2401881217956543 lr:7.942587682074054e-06 tokens_per_second_per_gpu:389.892446477415 mfu:6.433807158387635 
Step 3627 | loss:1.2281548976898193 lr:7.912933443454584e-06 tokens_per_second_per_gpu:211.57511643489897 mfu:3.4913051303095752 
Step 3628 | loss:1.163456678390503 lr:7.883332385947683e-06 tokens_per_second_per_gpu:247.86418126628377 mfu:4.090128850011673 
Step 3629 | loss:1.1251509189605713 lr:7.85378452664821e-06 tokens_per_second_per_gpu:299.9679572976824 mfu:4.9499189029827475 
Step 3630 | loss:0.9801861643791199 lr:7.824289882620329e-06 tokens_per_second_per_gpu:269.79673839092015 mfu:4.452048769992491 
Step 3631 | loss:1.2384830713272095 lr:7.794848470897464e-06 tokens_per_second_per_gpu:281.11852066722753 mfu:4.638875071740894 
Step 3632 | loss:1.0597012042999268 lr:7.765460308482287e-06 tokens_per_second_per_gpu:241.07387052640505 mfu:3.9780785904064544 
Step 3633 | loss:0.9695963859558105 lr:7.73612541234674e-06 tokens_per_second_per_gpu:292.9879257436883 mfu:4.834737966846146 
Step 3634 | loss:1.1111239194869995 lr:7.706843799431984e-06 tokens_per_second_per_gpu:293.1890670542583 mfu:4.838057098610519 
Step 3635 | loss:1.1291007995605469 lr:7.677615486648414e-06 tokens_per_second_per_gpu:223.38804300990935 mfu:3.6862360458645447 
Step 3636 | loss:1.0732295513153076 lr:7.648440490875653e-06 tokens_per_second_per_gpu:237.93464760841294 mfu:3.9262767279594417 
Step 3637 | loss:1.2530438899993896 lr:7.619318828962507e-06 tokens_per_second_per_gpu:249.04873226938423 mfu:4.109675709131613 
Step 3638 | loss:1.192722201347351 lr:7.590250517727016e-06 tokens_per_second_per_gpu:247.0556706618086 mfu:4.076787218590747 
Step 3639 | loss:1.2185989618301392 lr:7.561235573956382e-06 tokens_per_second_per_gpu:195.69738890789455 mfu:3.229298933613259 
Step 3640 | loss:1.0340207815170288 lr:7.532274014407003e-06 tokens_per_second_per_gpu:252.11438069959846 mfu:4.160263482743571 
Step 3641 | loss:1.145405888557434 lr:7.503365855804445e-06 tokens_per_second_per_gpu:256.4424744028229 mfu:4.231683487161613 
Step 3642 | loss:1.3363678455352783 lr:7.474511114843419e-06 tokens_per_second_per_gpu:191.10832449282623 mfu:3.1535725230333127 
Step 3643 | loss:1.1870499849319458 lr:7.445709808187806e-06 tokens_per_second_per_gpu:283.3685052942509 mfu:4.676003175479225 
Step 3644 | loss:1.2139198780059814 lr:7.4169619524706136e-06 tokens_per_second_per_gpu:255.75452748978117 mfu:4.220331336552624 
Step 3645 | loss:1.3393590450286865 lr:7.388267564293994e-06 tokens_per_second_per_gpu:275.9673269468573 mfu:4.553872688822764 
Step 3646 | loss:1.2165613174438477 lr:7.3596266602292126e-06 tokens_per_second_per_gpu:275.48345148195597 mfu:4.545888021620367 
Step 3647 | loss:1.2006914615631104 lr:7.331039256816663e-06 tokens_per_second_per_gpu:199.77089955402246 mfu:3.296517937704287 
Step 3648 | loss:1.2578221559524536 lr:7.302505370565815e-06 tokens_per_second_per_gpu:208.24693978191357 mfu:3.4363852492813174 
Step 3649 | loss:1.3050119876861572 lr:7.274025017955244e-06 tokens_per_second_per_gpu:257.03748620050084 mfu:4.241502069690749 
Step 3650 | loss:1.1551531553268433 lr:7.245598215432614e-06 tokens_per_second_per_gpu:199.49419892826134 mfu:3.2919519644908113 
Step 3651 | loss:1.099459171295166 lr:7.217224979414661e-06 tokens_per_second_per_gpu:332.76058188090286 mfu:5.4910461412557865 
Step 3652 | loss:1.2560138702392578 lr:7.188905326287198e-06 tokens_per_second_per_gpu:243.4446777066094 mfu:4.0172004465618265 
Step 3653 | loss:0.9880403280258179 lr:7.160639272405056e-06 tokens_per_second_per_gpu:236.39769748205745 mfu:3.900914757461243 
Step 3654 | loss:1.2069604396820068 lr:7.132426834092154e-06 tokens_per_second_per_gpu:186.11513997587184 mfu:3.0711775277504474 
Step 3655 | loss:1.0957096815109253 lr:7.104268027641425e-06 tokens_per_second_per_gpu:251.4497661678495 mfu:4.149296351242135 
Step 3656 | loss:1.1052162647247314 lr:7.076162869314829e-06 tokens_per_second_per_gpu:294.2800663126243 mfu:4.856060214345867 
Step 3657 | loss:1.3590528964996338 lr:7.048111375343358e-06 tokens_per_second_per_gpu:381.66312631884193 mfu:6.2980110961062445 
Step 3658 | loss:1.3592931032180786 lr:7.020113561927e-06 tokens_per_second_per_gpu:245.80270996082086 mfu:4.056111497375768 
Step 3659 | loss:1.0487991571426392 lr:6.992169445234731e-06 tokens_per_second_per_gpu:202.5092391355215 mfu:3.3417046269072164 
Step 3660 | loss:1.2664427757263184 lr:6.964279041404553e-06 tokens_per_second_per_gpu:243.74180597444987 mfu:4.022103506351423 
Step 3661 | loss:1.212463617324829 lr:6.9364423665434165e-06 tokens_per_second_per_gpu:213.61125669757433 mfu:3.5249044829408933 
Step 3662 | loss:1.296388864517212 lr:6.908659436727238e-06 tokens_per_second_per_gpu:189.86879901726593 mfu:3.133118503085723 
Step 3663 | loss:1.335656762123108 lr:6.880930268000951e-06 tokens_per_second_per_gpu:285.5647339396495 mfu:4.712244225306899 
Step 3664 | loss:1.1465234756469727 lr:6.853254876378367e-06 tokens_per_second_per_gpu:281.5389596210627 mfu:4.6458129418517125 
Step 3665 | loss:1.00990629196167 lr:6.825633277842269e-06 tokens_per_second_per_gpu:163.4945764738586 mfu:2.69790447591038 
Step 3666 | loss:1.11471688747406 lr:6.798065488344407e-06 tokens_per_second_per_gpu:276.3378957467778 mfu:4.559987626978515 
Step 3667 | loss:1.035154104232788 lr:6.770551523805402e-06 tokens_per_second_per_gpu:296.70963512905496 mfu:4.8961517251821824 
Step 3668 | loss:1.0671793222427368 lr:6.7430914001148424e-06 tokens_per_second_per_gpu:228.7183399275948 mfu:3.7741938987934103 
Step 3669 | loss:1.1907579898834229 lr:6.7156851331311775e-06 tokens_per_second_per_gpu:310.97154342648065 mfu:5.131494493489854 
Step 3670 | loss:1.092907428741455 lr:6.688332738681757e-06 tokens_per_second_per_gpu:211.5176929206707 mfu:3.4903575566383247 
Step 3671 | loss:1.3447773456573486 lr:6.661034232562902e-06 tokens_per_second_per_gpu:289.08485732726774 mfu:4.770331513876562 
Step 3672 | loss:1.0073747634887695 lr:6.6337896305396885e-06 tokens_per_second_per_gpu:250.05999866475736 mfu:4.126363113651427 
Step 3673 | loss:1.157915711402893 lr:6.606598948346132e-06 tokens_per_second_per_gpu:237.49237921510198 mfu:3.918978639523719 
Step 3674 | loss:1.273655652999878 lr:6.579462201685105e-06 tokens_per_second_per_gpu:230.17762066108736 mfu:3.7982742084122982 
Step 3675 | loss:1.0741947889328003 lr:6.5523794062282925e-06 tokens_per_second_per_gpu:245.64491775830234 mfu:4.053507690579115 
Step 3676 | loss:1.280591368675232 lr:6.525350577616318e-06 tokens_per_second_per_gpu:154.98248468662553 mfu:2.5574422598086244 
Step 3677 | loss:1.1471408605575562 lr:6.498375731458528e-06 tokens_per_second_per_gpu:204.94680155604678 mfu:3.381928044139026 
Step 3678 | loss:1.1785476207733154 lr:6.471454883333128e-06 tokens_per_second_per_gpu:228.89858224317902 mfu:3.7771681659553606 
Step 3679 | loss:1.2436230182647705 lr:6.4445880487872036e-06 tokens_per_second_per_gpu:257.9314539478116 mfu:4.256253871486296 
Step 3680 | loss:1.1722954511642456 lr:6.417775243336544e-06 tokens_per_second_per_gpu:243.84707261677195 mfu:4.023840563027003 
Step 3681 | loss:1.0045280456542969 lr:6.391016482465795e-06 tokens_per_second_per_gpu:244.32386908712166 mfu:4.031708416256131 
Step 3682 | loss:1.1524121761322021 lr:6.364311781628407e-06 tokens_per_second_per_gpu:279.2088885057675 mfu:4.607363291553071 
Step 3683 | loss:1.3359742164611816 lr:6.337661156246544e-06 tokens_per_second_per_gpu:212.29141266156446 mfu:3.5031250868957655 
Step 3684 | loss:1.1844422817230225 lr:6.311064621711249e-06 tokens_per_second_per_gpu:297.11163158887285 mfu:4.902785266622111 
Step 3685 | loss:1.0188496112823486 lr:6.284522193382203e-06 tokens_per_second_per_gpu:198.60453022298822 mfu:3.27727110330385 
Step 3686 | loss:1.2493741512298584 lr:6.258033886587911e-06 tokens_per_second_per_gpu:259.9617500042724 mfu:4.289756785994439 
Step 3687 | loss:1.0691077709197998 lr:6.2315997166256355e-06 tokens_per_second_per_gpu:193.66752182401189 mfu:3.1958030977927616 
Step 3688 | loss:1.1072542667388916 lr:6.2052196987613e-06 tokens_per_second_per_gpu:277.0706637272191 mfu:4.572079392080903 
Step 3689 | loss:1.1072076559066772 lr:6.178893848229661e-06 tokens_per_second_per_gpu:260.24644168049036 mfu:4.294454623464575 
Step 3690 | loss:1.3110915422439575 lr:6.15262218023408e-06 tokens_per_second_per_gpu:264.65844741945784 mfu:4.367259301684625 
Step 3691 | loss:1.2138020992279053 lr:6.12640470994671e-06 tokens_per_second_per_gpu:314.47504667506576 mfu:5.189307524965156 
Step 3692 | loss:1.1338610649108887 lr:6.100241452508393e-06 tokens_per_second_per_gpu:241.50879888682005 mfu:3.98525555734671 
Step 3693 | loss:1.112723708152771 lr:6.0741324230286225e-06 tokens_per_second_per_gpu:311.9259829135996 mfu:5.147244169227236 
Step 3694 | loss:1.1919358968734741 lr:6.0480776365855805e-06 tokens_per_second_per_gpu:250.5118857206197 mfu:4.133819924372068 
Step 3695 | loss:1.0156562328338623 lr:6.022077108226198e-06 tokens_per_second_per_gpu:211.54224170068943 mfu:3.4907626481399454 
Step 3696 | loss:1.2277193069458008 lr:5.996130852965954e-06 tokens_per_second_per_gpu:301.84915517130617 mfu:4.980961474992065 
Step 3697 | loss:1.0791536569595337 lr:5.970238885789092e-06 tokens_per_second_per_gpu:280.3412305568414 mfu:4.626048625059179 
Step 3698 | loss:1.054314136505127 lr:5.944401221648432e-06 tokens_per_second_per_gpu:296.8631997889233 mfu:4.898685771216833 
Step 3699 | loss:1.281036615371704 lr:5.918617875465449e-06 tokens_per_second_per_gpu:193.10451090393346 mfu:3.1865125774952343 
Step 3700 | loss:1.2279657125473022 lr:5.892888862130308e-06 tokens_per_second_per_gpu:213.28542013100991 mfu:3.5195276933842687 
Step 3701 | loss:1.1079788208007812 lr:5.86721419650168e-06 tokens_per_second_per_gpu:262.0432177658935 mfu:4.324104109995358 
Step 3702 | loss:1.137088656425476 lr:5.84159389340696e-06 tokens_per_second_per_gpu:294.1836037604129 mfu:4.854468438294442 
Step 3703 | loss:1.0566508769989014 lr:5.816027967642112e-06 tokens_per_second_per_gpu:375.65817278187814 mfu:6.198920402247058 
Step 3704 | loss:1.3634525537490845 lr:5.790516433971638e-06 tokens_per_second_per_gpu:223.2290393676745 mfu:3.683612248504881 
Step 3705 | loss:1.0092689990997314 lr:5.76505930712874e-06 tokens_per_second_per_gpu:239.70034310204653 mfu:3.9554133383480474 
Step 3706 | loss:1.2038277387619019 lr:5.739656601815102e-06 tokens_per_second_per_gpu:266.89877644118314 mfu:4.404228073527592 
Step 3707 | loss:1.1590313911437988 lr:5.714308332701002e-06 tokens_per_second_per_gpu:206.13881472489408 mfu:3.4015980401287185 
Step 3708 | loss:1.225160002708435 lr:5.689014514425339e-06 tokens_per_second_per_gpu:288.10375407456655 mfu:4.754141846219812 
Step 3709 | loss:1.4163870811462402 lr:5.663775161595486e-06 tokens_per_second_per_gpu:221.83813793309673 mfu:3.660660299352626 
Step 3710 | loss:1.3173468112945557 lr:5.638590288787415e-06 tokens_per_second_per_gpu:230.0287774382484 mfu:3.795818073133888 
Step 3711 | loss:1.1533726453781128 lr:5.613459910545627e-06 tokens_per_second_per_gpu:343.3876875164608 mfu:5.666409241846028 
Step 3712 | loss:1.2044860124588013 lr:5.588384041383088e-06 tokens_per_second_per_gpu:218.2811574367649 mfu:3.601964813491576 
Step 3713 | loss:1.2561620473861694 lr:5.563362695781416e-06 tokens_per_second_per_gpu:266.2621229864227 mfu:4.393722341519554 
Step 3714 | loss:1.1903423070907593 lr:5.538395888190606e-06 tokens_per_second_per_gpu:261.46914663983364 mfu:4.3146310797952685 
Step 3715 | loss:1.1347858905792236 lr:5.513483633029237e-06 tokens_per_second_per_gpu:233.00650313188976 mfu:3.844954990395439 
Step 3716 | loss:1.1334906816482544 lr:5.4886259446843776e-06 tokens_per_second_per_gpu:213.4642417035037 mfu:3.5224785161652155 
Step 3717 | loss:1.1146539449691772 lr:5.463822837511523e-06 tokens_per_second_per_gpu:266.08804992524006 mfu:4.390849876260898 
Step 3718 | loss:1.3579168319702148 lr:5.439074325834726e-06 tokens_per_second_per_gpu:293.7872989909122 mfu:4.847928818237801 
Step 3719 | loss:1.1090246438980103 lr:5.414380423946486e-06 tokens_per_second_per_gpu:187.86039573427288 mfu:3.0999768520078574 
Step 3720 | loss:1.2668113708496094 lr:5.389741146107707e-06 tokens_per_second_per_gpu:293.19863580409555 mfu:4.838214997261176 
Step 3721 | loss:1.2696166038513184 lr:5.365156506547853e-06 tokens_per_second_per_gpu:235.05497529864456 mfu:3.8787578378455456 
Step 3722 | loss:1.2016122341156006 lr:5.34062651946472e-06 tokens_per_second_per_gpu:262.9552818362559 mfu:4.339154528124313 
Step 3723 | loss:1.2369900941848755 lr:5.316151199024632e-06 tokens_per_second_per_gpu:262.6025853313332 mfu:4.33333450950479 
Step 3724 | loss:1.4929267168045044 lr:5.291730559362318e-06 tokens_per_second_per_gpu:222.22895186824297 mfu:3.6671093124490803 
Step 3725 | loss:1.1283941268920898 lr:5.267364614580861e-06 tokens_per_second_per_gpu:264.6076026073988 mfu:4.366420286415805 
Step 3726 | loss:1.2165215015411377 lr:5.243053378751872e-06 tokens_per_second_per_gpu:216.27999961185273 mfu:3.568942723283606 
Step 3727 | loss:1.3749549388885498 lr:5.2187968659152876e-06 tokens_per_second_per_gpu:265.27719579443027 mfu:4.377469573158476 
Step 3728 | loss:1.1265904903411865 lr:5.194595090079457e-06 tokens_per_second_per_gpu:269.0046204723486 mfu:4.438977642349888 
Step 3729 | loss:1.195706844329834 lr:5.170448065221156e-06 tokens_per_second_per_gpu:239.34810182863117 mfu:3.9496008317276843 
Step 3730 | loss:1.1509299278259277 lr:5.146355805285452e-06 tokens_per_second_per_gpu:326.42118933176 mfu:5.3864367046508965 
Step 3731 | loss:1.1436920166015625 lr:5.122318324185882e-06 tokens_per_second_per_gpu:293.3331702444331 mfu:4.840435016276967 
Step 3732 | loss:1.2715634107589722 lr:5.0983356358043295e-06 tokens_per_second_per_gpu:264.9914974997249 mfu:4.372755124981238 
Step 3733 | loss:1.132053017616272 lr:5.07440775399095e-06 tokens_per_second_per_gpu:240.5577954604568 mfu:3.9695625817390336 
Step 3734 | loss:0.9472301006317139 lr:5.050534692564357e-06 tokens_per_second_per_gpu:249.8603291917995 mfu:4.123068269403907 
Step 3735 | loss:1.0796834230422974 lr:5.0267164653114544e-06 tokens_per_second_per_gpu:214.94115703252834 mfu:3.5468498229244543 
Step 3736 | loss:1.3179502487182617 lr:5.002953085987483e-06 tokens_per_second_per_gpu:231.42430350404942 mfu:3.8188463356021307 
Step 3737 | loss:1.2247884273529053 lr:4.979244568316011e-06 tokens_per_second_per_gpu:174.58051141188685 mfu:2.880838944649408 
Step 3738 | loss:1.1464608907699585 lr:4.955590925988895e-06 tokens_per_second_per_gpu:152.2940567952867 mfu:2.513079187970795 
Step 3739 | loss:1.3752193450927734 lr:4.931992172666355e-06 tokens_per_second_per_gpu:259.3190212303388 mfu:4.279150802154548 
Step 3740 | loss:1.2486655712127686 lr:4.908448321976878e-06 tokens_per_second_per_gpu:279.66055080070146 mfu:4.614816393383009 
Step 3741 | loss:1.019819736480713 lr:4.884959387517252e-06 tokens_per_second_per_gpu:224.28983164095445 mfu:3.70111690391191 
Step 3742 | loss:1.1857532262802124 lr:4.8615253828525386e-06 tokens_per_second_per_gpu:293.98191977387364 mfu:4.851140351566803 
Step 3743 | loss:1.0954666137695312 lr:4.8381463215161015e-06 tokens_per_second_per_gpu:226.45456899700955 mfu:3.7368383004745986 
Step 3744 | loss:1.0762763023376465 lr:4.814822217009541e-06 tokens_per_second_per_gpu:265.64910928805085 mfu:4.383606700766809 
Step 3745 | loss:1.0737063884735107 lr:4.7915530828027685e-06 tokens_per_second_per_gpu:171.5279467469101 mfu:2.8304670726872607 
Step 3746 | loss:1.2168389558792114 lr:4.7683389323338825e-06 tokens_per_second_per_gpu:202.28715626300783 mfu:3.338039928122095 
Step 3747 | loss:0.9355383515357971 lr:4.745179779009279e-06 tokens_per_second_per_gpu:299.15823840493226 mfu:4.936557333002296 
Step 3748 | loss:1.2459594011306763 lr:4.722075636203593e-06 tokens_per_second_per_gpu:268.6467248417336 mfu:4.433071830398387 
Step 3749 | loss:1.315387487411499 lr:4.699026517259653e-06 tokens_per_second_per_gpu:203.31580199267734 mfu:3.355014117590974 
Step 3750 | loss:1.2519352436065674 lr:4.676032435488553e-06 tokens_per_second_per_gpu:244.2502936949241 mfu:4.030494312496802 
Step 3751 | loss:1.1223030090332031 lr:4.653093404169573e-06 tokens_per_second_per_gpu:254.5771935679932 mfu:4.2009035700435575 
Step 3752 | loss:0.979023277759552 lr:4.630209436550215e-06 tokens_per_second_per_gpu:226.36864115389452 mfu:3.735420362842995 
Step 3753 | loss:1.276169776916504 lr:4.607380545846162e-06 tokens_per_second_per_gpu:178.06792392190795 mfu:2.9383864549280507 
Step 3754 | loss:1.2218334674835205 lr:4.584606745241327e-06 tokens_per_second_per_gpu:245.77317124864337 mfu:4.055624064547628 
Step 3755 | loss:1.2701295614242554 lr:4.561888047887774e-06 tokens_per_second_per_gpu:270.608209038874 mfu:4.465439246547746 
Step 3756 | loss:1.1823244094848633 lr:4.539224466905745e-06 tokens_per_second_per_gpu:272.0498065264111 mfu:4.4892277562217 
Step 3757 | loss:1.1109144687652588 lr:4.51661601538369e-06 tokens_per_second_per_gpu:233.62166933796982 mfu:3.8551061507373086 
Step 3758 | loss:1.175107717514038 lr:4.494062706378166e-06 tokens_per_second_per_gpu:192.71556571497246 mfu:3.1800944014993506 
Step 3759 | loss:1.2294092178344727 lr:4.4715645529139314e-06 tokens_per_second_per_gpu:208.3470448249564 mfu:3.4380371318667295 
Step 3760 | loss:1.1575512886047363 lr:4.44912156798386e-06 tokens_per_second_per_gpu:256.9133206783296 mfu:4.239453153297043 
Step 3761 | loss:1.0927608013153076 lr:4.4267337645489955e-06 tokens_per_second_per_gpu:275.33839202480107 mfu:4.543494324121822 
Step 3762 | loss:1.1680214405059814 lr:4.404401155538473e-06 tokens_per_second_per_gpu:194.32905687499124 mfu:3.2067194132663466 
Step 3763 | loss:1.2515816688537598 lr:4.382123753849599e-06 tokens_per_second_per_gpu:193.68453590373838 mfu:3.1960838554963966 
Step 3764 | loss:1.11552894115448 lr:4.359901572347758e-06 tokens_per_second_per_gpu:249.07602408445982 mfu:4.110126064804787 
Step 3765 | loss:1.0984693765640259 lr:4.337734623866474e-06 tokens_per_second_per_gpu:214.79781149110147 mfu:3.5444844075928996 
Step 3766 | loss:1.2326834201812744 lr:4.31562292120734e-06 tokens_per_second_per_gpu:202.8398923475783 mfu:3.3471608983017895 
Step 3767 | loss:1.2670222520828247 lr:4.2935664771400875e-06 tokens_per_second_per_gpu:224.28763108107955 mfu:3.7010805913903324 
Step 3768 | loss:1.3057284355163574 lr:4.271565304402492e-06 tokens_per_second_per_gpu:197.4916251334986 mfu:3.2589065086674185 
Step 3769 | loss:1.2160398960113525 lr:4.249619415700445e-06 tokens_per_second_per_gpu:213.20505676332237 mfu:3.5182015779004434 
Step 3770 | loss:1.3060823678970337 lr:4.2277288237078886e-06 tokens_per_second_per_gpu:187.5584896866636 mfu:3.0949949517227444 
Step 3771 | loss:1.238671064376831 lr:4.20589354106683e-06 tokens_per_second_per_gpu:257.68962715858925 mfu:4.252263368613913 
Step 3772 | loss:1.1165143251419067 lr:4.184113580387361e-06 tokens_per_second_per_gpu:211.19990488319368 mfu:3.485113579821533 
Step 3773 | loss:1.2195823192596436 lr:4.1623889542475866e-06 tokens_per_second_per_gpu:316.50695052091635 mfu:5.222836970397349 
Step 3774 | loss:0.9190989136695862 lr:4.140719675193683e-06 tokens_per_second_per_gpu:214.51809820083975 mfu:3.5398687209197126 
Step 3775 | loss:1.3000057935714722 lr:4.119105755739849e-06 tokens_per_second_per_gpu:258.3003012144122 mfu:4.2623404017734225 
Step 3776 | loss:1.2599564790725708 lr:4.097547208368335e-06 tokens_per_second_per_gpu:249.93703188823739 mfu:4.124333978349716 
Step 3777 | loss:1.1797930002212524 lr:4.07604404552937e-06 tokens_per_second_per_gpu:207.71886301334305 mfu:3.4276711946118743 
Step 3778 | loss:1.0888034105300903 lr:4.054596279641254e-06 tokens_per_second_per_gpu:181.8392558983531 mfu:3.0006190600629505 
Step 3779 | loss:1.3350505828857422 lr:4.033203923090245e-06 tokens_per_second_per_gpu:231.0534280252124 mfu:3.8127263367866364 
Step 3780 | loss:1.1449546813964844 lr:4.011866988230628e-06 tokens_per_second_per_gpu:270.68690267862473 mfu:4.4667378090290715 
Step 3781 | loss:1.0122652053833008 lr:3.990585487384668e-06 tokens_per_second_per_gpu:200.27960496644306 mfu:3.3049123360916166 
Step 3782 | loss:1.0994912385940552 lr:3.969359432842645e-06 tokens_per_second_per_gpu:271.0606050881773 mfu:4.472904456419674 
Step 3783 | loss:1.262599229812622 lr:3.948188836862776e-06 tokens_per_second_per_gpu:231.41160569995228 mfu:3.818636802887059 
Step 3784 | loss:1.068498134613037 lr:3.9270737116712695e-06 tokens_per_second_per_gpu:268.0697786161686 mfu:4.423551356766283 
Step 3785 | loss:1.1692081689834595 lr:3.906014069462327e-06 tokens_per_second_per_gpu:269.9748570566761 mfu:4.454987993763397 
Step 3786 | loss:1.2945923805236816 lr:3.885009922398064e-06 tokens_per_second_per_gpu:254.85917128198727 mfu:4.205556623087267 
Step 3787 | loss:1.1866410970687866 lr:3.864061282608567e-06 tokens_per_second_per_gpu:269.4906978320909 mfu:4.446998644102794 
Step 3788 | loss:1.222998023033142 lr:3.843168162191857e-06 tokens_per_second_per_gpu:251.0512568845801 mfu:4.142720353418768 
Step 3789 | loss:1.2255828380584717 lr:3.822330573213917e-06 tokens_per_second_per_gpu:238.63665911038922 mfu:3.9378609652728134 
Step 3790 | loss:1.30643892288208 lr:3.8015485277086205e-06 tokens_per_second_per_gpu:245.17584276446257 mfu:4.04576725323427 
Step 3791 | loss:1.141843557357788 lr:3.7808220376778115e-06 tokens_per_second_per_gpu:224.79788861529752 mfu:3.709500602103372 
Step 3792 | loss:1.236355185508728 lr:3.7601511150911927e-06 tokens_per_second_per_gpu:267.0637130068858 mfu:4.406949772977492 
Step 3793 | loss:1.3520596027374268 lr:3.7395357718864486e-06 tokens_per_second_per_gpu:275.2126817691184 mfu:4.541419917320147 
Step 3794 | loss:1.2206432819366455 lr:3.7189760199691004e-06 tokens_per_second_per_gpu:248.44635479108868 mfu:4.099735581881331 
Step 3795 | loss:1.1236777305603027 lr:3.6984718712125942e-06 tokens_per_second_per_gpu:296.97157208693534 mfu:4.900474075845508 
Step 3796 | loss:1.1779069900512695 lr:3.6780233374582694e-06 tokens_per_second_per_gpu:251.85422222599036 mfu:4.155970479724567 
Step 3797 | loss:0.9748221635818481 lr:3.6576304305153132e-06 tokens_per_second_per_gpu:254.52924049011057 mfu:4.200112272703649 
Step 3798 | loss:1.1771224737167358 lr:3.63729316216086e-06 tokens_per_second_per_gpu:272.3954783665849 mfu:4.494931857390769 
Step 3799 | loss:1.2581804990768433 lr:3.6170115441398254e-06 tokens_per_second_per_gpu:247.1753010010524 mfu:4.078761297698821 
Step 3800 | loss:1.2381874322891235 lr:3.5967855881650302e-06 tokens_per_second_per_gpu:248.93112040368783 mfu:4.107734937849005 
Step 3801 | loss:1.2206487655639648 lr:3.5766153059171746e-06 tokens_per_second_per_gpu:255.2316860852875 mfu:4.211703673202578 
Step 3802 | loss:1.1773701906204224 lr:3.5565007090447522e-06 tokens_per_second_per_gpu:241.4151435267275 mfu:3.9837101041540954 
Step 3803 | loss:1.0478383302688599 lr:3.5364418091641373e-06 tokens_per_second_per_gpu:289.3835429547697 mfu:4.775260272424443 
Step 3804 | loss:1.0935750007629395 lr:3.5164386178595188e-06 tokens_per_second_per_gpu:265.6522597302048 mfu:4.38365868776339 
Step 3805 | loss:1.1048729419708252 lr:3.496491146682912e-06 tokens_per_second_per_gpu:276.5990561360969 mfu:4.564297163101796 
Step 3806 | loss:1.0530717372894287 lr:3.476599407154191e-06 tokens_per_second_per_gpu:221.26371103398887 mfu:3.6511813983663637 
Step 3807 | loss:0.9163037538528442 lr:3.456763410760988e-06 tokens_per_second_per_gpu:262.6480048539986 mfu:4.334083999403082 
Step 3808 | loss:1.2139286994934082 lr:3.4369831689587738e-06 tokens_per_second_per_gpu:320.84419815214 mfu:5.294408028286727 
Step 3809 | loss:1.056199550628662 lr:3.417258693170833e-06 tokens_per_second_per_gpu:248.84905051419358 mfu:4.106380662208925 
Step 3810 | loss:1.0859723091125488 lr:3.3975899947882084e-06 tokens_per_second_per_gpu:273.6282986220733 mfu:4.5152752312017475 
Step 3811 | loss:1.0526151657104492 lr:3.3779770851697703e-06 tokens_per_second_per_gpu:220.18994867606028 mfu:3.6334627172088716 
Step 3812 | loss:1.0334715843200684 lr:3.3584199756421353e-06 tokens_per_second_per_gpu:235.54008718738083 mfu:3.8867629078861916 
Step 3813 | loss:1.1917821168899536 lr:3.3389186774997026e-06 tokens_per_second_per_gpu:215.369639133777 mfu:3.553920416969457 
Step 3814 | loss:1.190481424331665 lr:3.319473202004675e-06 tokens_per_second_per_gpu:212.10951643503157 mfu:3.500123527735222 
Step 3815 | loss:1.2178466320037842 lr:3.3000835603869793e-06 tokens_per_second_per_gpu:253.32876632249807 mfu:4.1803026576089595 
Step 3816 | loss:1.3297897577285767 lr:3.280749763844293e-06 tokens_per_second_per_gpu:260.9665860001534 mfu:4.30633807932729 
Step 3817 | loss:1.1072869300842285 lr:3.2614718235420837e-06 tokens_per_second_per_gpu:231.9782514522505 mfu:3.8279873033400547 
Step 3818 | loss:1.232230305671692 lr:3.242249750613502e-06 tokens_per_second_per_gpu:229.08097363609482 mfu:3.780177896100102 
Step 3819 | loss:1.0411196947097778 lr:3.223083556159523e-06 tokens_per_second_per_gpu:248.06309184060893 mfu:4.093411171299336 
Step 3820 | loss:1.1314451694488525 lr:3.2039732512487484e-06 tokens_per_second_per_gpu:199.20381731072416 mfu:3.2871602344984656 
Step 3821 | loss:1.245577335357666 lr:3.1849188469175507e-06 tokens_per_second_per_gpu:215.7959940654467 mfu:3.560955909542277 
Step 3822 | loss:1.0867087841033936 lr:3.16592035417006e-06 tokens_per_second_per_gpu:259.20017295413504 mfu:4.277189628253615 
Step 3823 | loss:1.2001683712005615 lr:3.1469777839780445e-06 tokens_per_second_per_gpu:230.82810186974396 mfu:3.8090081189931837 
Step 3824 | loss:1.1628398895263672 lr:3.1280911472810205e-06 tokens_per_second_per_gpu:206.96599188402269 mfu:3.4152476975553716 
Step 3825 | loss:1.1473027467727661 lr:3.1092604549861957e-06 tokens_per_second_per_gpu:296.5642452742156 mfu:4.893752575628828 
Step 3826 | loss:1.2983143329620361 lr:3.0904857179684497e-06 tokens_per_second_per_gpu:275.91884035666874 mfu:4.553072587733709 
Step 3827 | loss:1.099782943725586 lr:3.0717669470703868e-06 tokens_per_second_per_gpu:260.4774076431739 mfu:4.298265906492709 
Step 3828 | loss:1.2376534938812256 lr:3.0531041531022485e-06 tokens_per_second_per_gpu:228.67016318653486 mfu:3.7733989106773294 
Step 3829 | loss:1.1640886068344116 lr:3.0344973468419578e-06 tokens_per_second_per_gpu:270.0842759079138 mfu:4.456793568081945 
Step 3830 | loss:1.2064579725265503 lr:3.0159465390351414e-06 tokens_per_second_per_gpu:266.5222488170558 mfu:4.398014805880764 
Step 3831 | loss:1.1452075242996216 lr:2.99745174039503e-06 tokens_per_second_per_gpu:231.62072620732988 mfu:3.822087603305194 
Step 3832 | loss:1.2020788192749023 lr:2.9790129616025565e-06 tokens_per_second_per_gpu:302.3636935959893 mfu:4.9894521267856575 
Step 3833 | loss:1.075458288192749 lr:2.9606302133062925e-06 tokens_per_second_per_gpu:243.384163511225 mfu:4.016201872039632 
Step 3834 | loss:1.2316203117370605 lr:2.9423035061223903e-06 tokens_per_second_per_gpu:316.3188797639717 mfu:5.219733522271473 
Step 3835 | loss:1.1627380847930908 lr:2.9240328506347502e-06 tokens_per_second_per_gpu:246.45579402597878 mfu:4.066888358972868 
Step 3836 | loss:1.1184581518173218 lr:2.905818257394799e-06 tokens_per_second_per_gpu:388.91120331994375 mfu:6.417615182093416 
Step 3837 | loss:1.2304819822311401 lr:2.8876597369216442e-06 tokens_per_second_per_gpu:208.4112761640954 mfu:3.439097044807539 
Step 3838 | loss:1.297884225845337 lr:2.869557299702008e-06 tokens_per_second_per_gpu:185.68670346809338 mfu:3.0641076860657375 
Step 3839 | loss:1.1842879056930542 lr:2.8515109561901734e-06 tokens_per_second_per_gpu:318.68002886097264 mfu:5.258696005642346 
Step 3840 | loss:1.1259291172027588 lr:2.8335207168081023e-06 tokens_per_second_per_gpu:248.44491475761933 mfu:4.099711819180291 
Step 3841 | loss:1.1830053329467773 lr:2.8155865919453294e-06 tokens_per_second_per_gpu:327.18671881440497 mfu:5.399069083425855 
Step 3842 | loss:1.2201226949691772 lr:2.7977085919589254e-06 tokens_per_second_per_gpu:235.00978729897204 mfu:3.8780121684221114 
Step 3843 | loss:0.9747270941734314 lr:2.779886727173642e-06 tokens_per_second_per_gpu:320.77501693415775 mfu:5.293266434958872 
Step 3844 | loss:1.1721057891845703 lr:2.762121007881735e-06 tokens_per_second_per_gpu:260.1027809845779 mfu:4.29208400761374 
Step 3845 | loss:1.1996110677719116 lr:2.744411444343087e-06 tokens_per_second_per_gpu:150.81434177608162 mfu:2.488661682145924 
Step 3846 | loss:1.1021316051483154 lr:2.7267580467851385e-06 tokens_per_second_per_gpu:248.30081311508098 mfu:4.097333927052154 
Step 3847 | loss:1.2063391208648682 lr:2.709160825402857e-06 tokens_per_second_per_gpu:234.82268523288766 mfu:3.874924705140894 
Step 3848 | loss:1.2467750310897827 lr:2.6916197903588127e-06 tokens_per_second_per_gpu:328.858493137229 mfu:5.426655854348376 
Step 3849 | loss:1.168059229850769 lr:2.674134951783125e-06 tokens_per_second_per_gpu:204.23466613428428 mfu:3.370176747042424 
Step 3850 | loss:1.317714810371399 lr:2.6567063197734275e-06 tokens_per_second_per_gpu:227.68893737047452 mfu:3.757207220542267 
Step 3851 | loss:1.2977442741394043 lr:2.639333904394936e-06 tokens_per_second_per_gpu:256.3961495663047 mfu:4.230919058233854 
Step 3852 | loss:1.2884011268615723 lr:2.622017715680336e-06 tokens_per_second_per_gpu:218.83325715421702 mfu:3.6110752826642414 
Step 3853 | loss:1.264994502067566 lr:2.604757763629917e-06 tokens_per_second_per_gpu:260.0981325569841 mfu:4.29200730162213 
Step 3854 | loss:1.085490345954895 lr:2.58755405821145e-06 tokens_per_second_per_gpu:308.9804358680195 mfu:5.098638247675179 
Step 3855 | loss:1.1270281076431274 lr:2.570406609360221e-06 tokens_per_second_per_gpu:219.31623026912587 mfu:3.6190450597452886 
Step 3856 | loss:1.2897803783416748 lr:2.553315426979042e-06 tokens_per_second_per_gpu:227.89863395382886 mfu:3.760667527073629 
Step 3857 | loss:1.0049933195114136 lr:2.5362805209382277e-06 tokens_per_second_per_gpu:370.1124714236273 mfu:6.107408054625671 
Step 3858 | loss:1.0421276092529297 lr:2.519301901075599e-06 tokens_per_second_per_gpu:213.5771069498928 mfu:3.5243409611464203 
Step 3859 | loss:1.2852052450180054 lr:2.5023795771964565e-06 tokens_per_second_per_gpu:208.74470902728788 mfu:3.4445991845936033 
Step 3860 | loss:1.340803623199463 lr:2.48551355907356e-06 tokens_per_second_per_gpu:194.5752578344508 mfu:3.2107820964747136 
Step 3861 | loss:1.0905967950820923 lr:2.468703856447241e-06 tokens_per_second_per_gpu:237.60242251981614 mfu:3.9207945182564288 
Step 3862 | loss:1.2435888051986694 lr:2.4519504790252225e-06 tokens_per_second_per_gpu:278.2053256617997 mfu:4.590803007126565 
Step 3863 | loss:1.243943691253662 lr:2.435253436482743e-06 tokens_per_second_per_gpu:220.23178060258778 mfu:3.6341530064175323 
Step 3864 | loss:1.129202127456665 lr:2.4186127384625e-06 tokens_per_second_per_gpu:251.2917340445873 mfu:4.146688585395205 
Step 3865 | loss:1.098519206047058 lr:2.402028394574629e-06 tokens_per_second_per_gpu:247.5446854038857 mfu:4.084856691535294 
Step 3866 | loss:1.1720551252365112 lr:2.3855004143967573e-06 tokens_per_second_per_gpu:240.5062690121226 mfu:3.9687123184545463 
Step 3867 | loss:1.207865834236145 lr:2.3690288074739387e-06 tokens_per_second_per_gpu:266.9080852484727 mfu:4.404381682738329 
Step 3868 | loss:1.0671651363372803 lr:2.3526135833186525e-06 tokens_per_second_per_gpu:233.0661451659031 mfu:3.845939172953585 
Step 3869 | loss:1.054324746131897 lr:2.33625475141086e-06 tokens_per_second_per_gpu:215.31520333467338 mfu:3.5530221450559853 
Step 3870 | loss:1.3550463914871216 lr:2.319952321197938e-06 tokens_per_second_per_gpu:232.52086291886607 mfu:3.836941202215694 
Step 3871 | loss:1.2665975093841553 lr:2.303706302094677e-06 tokens_per_second_per_gpu:291.48357686162063 mfu:4.809913965525771 
Step 3872 | loss:1.1840535402297974 lr:2.2875167034833054e-06 tokens_per_second_per_gpu:211.49540326452387 mfu:3.48998974405162 
Step 3873 | loss:1.1803691387176514 lr:2.271383534713456e-06 tokens_per_second_per_gpu:269.7025979686483 mfu:4.450495312550116 
Step 3874 | loss:1.2968616485595703 lr:2.2553068051021863e-06 tokens_per_second_per_gpu:173.9113694520766 mfu:2.8697971038292005 
Step 3875 | loss:1.0917112827301025 lr:2.2392865239339477e-06 tokens_per_second_per_gpu:232.74421845576538 mfu:3.8406269018622283 
Step 3876 | loss:1.1225224733352661 lr:2.223322700460606e-06 tokens_per_second_per_gpu:369.83234278780554 mfu:6.1027855141309715 
Step 3877 | loss:1.3006830215454102 lr:2.2074153439014088e-06 tokens_per_second_per_gpu:218.4200320661639 mfu:3.6042564521032454 
Step 3878 | loss:1.171125888824463 lr:2.1915644634429854e-06 tokens_per_second_per_gpu:269.54422270303604 mfu:4.447881884342379 
Step 3879 | loss:1.314882755279541 lr:2.17577006823938e-06 tokens_per_second_per_gpu:196.75864932110548 mfu:3.2468113140277013 
Step 3880 | loss:1.1904133558273315 lr:2.160032167411996e-06 tokens_per_second_per_gpu:193.66455410876742 mfu:3.195754126062849 
Step 3881 | loss:1.225935935974121 lr:2.144350770049597e-06 tokens_per_second_per_gpu:235.47080138037614 mfu:3.885619588683398 
Step 3882 | loss:1.3038567304611206 lr:2.12872588520836e-06 tokens_per_second_per_gpu:193.2310449993427 mfu:3.1886005788817173 
Step 3883 | loss:1.03624427318573 lr:2.113157521911768e-06 tokens_per_second_per_gpu:281.3355200375937 mfu:4.642455885155058 
Step 3884 | loss:1.082484483718872 lr:2.0976456891507067e-06 tokens_per_second_per_gpu:344.2907639135962 mfu:5.681311349955468 
Step 3885 | loss:1.1492177248001099 lr:2.0821903958833988e-06 tokens_per_second_per_gpu:242.50660885059222 mfu:4.001720910665627 
Step 3886 | loss:1.1983739137649536 lr:2.066791651035416e-06 tokens_per_second_per_gpu:233.81960934655285 mfu:3.858372456241964 
Step 3887 | loss:1.1803056001663208 lr:2.0514494634996774e-06 tokens_per_second_per_gpu:150.87841985397702 mfu:2.4897190660475204 
Step 3888 | loss:1.3179137706756592 lr:2.036163842136418e-06 tokens_per_second_per_gpu:231.6644229021342 mfu:3.822808663973001 
Step 3889 | loss:1.1028293371200562 lr:2.0209347957732328e-06 tokens_per_second_per_gpu:233.75702832194563 mfu:3.8573397759535033 
Step 3890 | loss:1.1145402193069458 lr:2.0057623332050302e-06 tokens_per_second_per_gpu:227.29224344846833 mfu:3.7506611788885977 
Step 3891 | loss:1.313987135887146 lr:1.990646463194057e-06 tokens_per_second_per_gpu:254.21814008595229 mfu:4.1949786518158 
Step 3892 | loss:1.178237795829773 lr:1.9755871944698523e-06 tokens_per_second_per_gpu:187.60004452924056 mfu:3.0956806686327614 
Step 3893 | loss:1.2109556198120117 lr:1.9605845357292816e-06 tokens_per_second_per_gpu:236.28217758605408 mfu:3.8990085068001754 
Step 3894 | loss:1.2535368204116821 lr:1.945638495636515e-06 tokens_per_second_per_gpu:158.88855051114058 mfu:2.621898174484453 
Step 3895 | loss:1.1973414421081543 lr:1.9307490828230246e-06 tokens_per_second_per_gpu:294.29897562434286 mfu:4.856372246205407 
Step 3896 | loss:1.1155474185943604 lr:1.9159163058875884e-06 tokens_per_second_per_gpu:308.84426462335745 mfu:5.096391218945619 
Step 3897 | loss:1.1034443378448486 lr:1.9011401733962541e-06 tokens_per_second_per_gpu:360.107542239572 mfu:5.9423117938873515 
Step 3898 | loss:1.2719029188156128 lr:1.8864206938823958e-06 tokens_per_second_per_gpu:244.77506928713532 mfu:4.0391538928303525 
Step 3899 | loss:1.202242374420166 lr:1.8717578758466247e-06 tokens_per_second_per_gpu:297.7847495466881 mfu:4.913892717342323 
Step 3900 | loss:1.1729761362075806 lr:1.8571517277568562e-06 tokens_per_second_per_gpu:237.00831722817549 mfu:3.910990894429582 
Step 3901 | loss:1.2957565784454346 lr:1.842602258048276e-06 tokens_per_second_per_gpu:214.19391991036417 mfu:3.534519295393008 
Step 3902 | loss:1.1291331052780151 lr:1.8281094751233296e-06 tokens_per_second_per_gpu:282.6246168916621 mfu:4.6637279068176785 
Step 3903 | loss:1.1962621212005615 lr:1.8136733873517442e-06 tokens_per_second_per_gpu:259.0710043468798 mfu:4.275058153490496 
Step 3904 | loss:1.144694209098816 lr:1.799294003070462e-06 tokens_per_second_per_gpu:335.4123473254067 mfu:5.5348042280137 
Step 3905 | loss:1.3148337602615356 lr:1.7849713305837402e-06 tokens_per_second_per_gpu:162.859052183263 mfu:2.6874173767959837 
Step 3906 | loss:1.2215269804000854 lr:1.770705378163029e-06 tokens_per_second_per_gpu:256.2638431232398 mfu:4.228735804497644 
Step 3907 | loss:1.3010097742080688 lr:1.7564961540470494e-06 tokens_per_second_per_gpu:333.2162911425773 mfu:5.498566024075764 
Step 3908 | loss:1.1654247045516968 lr:1.7423436664417593e-06 tokens_per_second_per_gpu:279.03556242652934 mfu:4.604503152611132 
Step 3909 | loss:1.0200121402740479 lr:1.728247923520354e-06 tokens_per_second_per_gpu:301.71846974876576 mfu:4.978804970513372 
Step 3910 | loss:1.1049433946609497 lr:1.7142089334232447e-06 tokens_per_second_per_gpu:276.06979194043777 mfu:4.555563514113529 
Step 3911 | loss:1.2976504564285278 lr:1.7002267042580678e-06 tokens_per_second_per_gpu:230.50479367591245 mfu:3.803673051359451 
Step 3912 | loss:1.095646858215332 lr:1.6863012440997084e-06 tokens_per_second_per_gpu:317.2201714186838 mfu:5.234606179467763 
Step 3913 | loss:1.109079122543335 lr:1.6724325609902224e-06 tokens_per_second_per_gpu:298.8067213952542 mfu:4.930756777814334 
Step 3914 | loss:1.2661595344543457 lr:1.6586206629389145e-06 tokens_per_second_per_gpu:325.6992381178299 mfu:5.374523432336555 
Step 3915 | loss:1.1390655040740967 lr:1.6448655579222817e-06 tokens_per_second_per_gpu:271.92937338505556 mfu:4.4872404296808535 
Step 3916 | loss:1.0213667154312134 lr:1.6311672538840028e-06 tokens_per_second_per_gpu:302.22577944146434 mfu:4.987176337442617 
Step 3917 | loss:1.1569538116455078 lr:1.6175257587349947e-06 tokens_per_second_per_gpu:242.27168901212835 mfu:3.997844382787205 
Step 3918 | loss:1.098846673965454 lr:1.6039410803533328e-06 tokens_per_second_per_gpu:261.75249522872053 mfu:4.319306754320308 
Step 3919 | loss:1.2605912685394287 lr:1.5904132265842752e-06 tokens_per_second_per_gpu:251.8309486597698 mfu:4.15558643115347 
Step 3920 | loss:1.3606055974960327 lr:1.576942205240317e-06 tokens_per_second_per_gpu:244.45829885366882 mfu:4.033926707998188 
Step 3921 | loss:1.019434928894043 lr:1.5635280241010798e-06 tokens_per_second_per_gpu:223.1385228986462 mfu:3.6821185916986314 
Step 3922 | loss:1.3688665628433228 lr:1.5501706909133552e-06 tokens_per_second_per_gpu:183.9751767177353 mfu:3.0358649407709435 
Step 3923 | loss:1.3264906406402588 lr:1.5368702133911394e-06 tokens_per_second_per_gpu:272.9484656664918 mfu:4.504056972998375 
Step 3924 | loss:1.3547289371490479 lr:1.5236265992155885e-06 tokens_per_second_per_gpu:206.40430999125988 mfu:3.405979108191706 
Step 3925 | loss:1.2009481191635132 lr:1.510439856034984e-06 tokens_per_second_per_gpu:184.46305861495762 mfu:3.0439157200849727 
Step 3926 | loss:1.2751245498657227 lr:1.4973099914648125e-06 tokens_per_second_per_gpu:259.3214656213544 mfu:4.279191138253786 
Step 3927 | loss:1.2239155769348145 lr:1.4842370130876637e-06 tokens_per_second_per_gpu:277.8513793794186 mfu:4.58496236531408 
Step 3928 | loss:1.36161470413208 lr:1.471220928453343e-06 tokens_per_second_per_gpu:273.541307394824 mfu:4.5138397461451625 
Step 3929 | loss:1.1190505027770996 lr:1.458261745078715e-06 tokens_per_second_per_gpu:223.20808506686822 mfu:3.6832664712738916 
Step 3930 | loss:1.245938777923584 lr:1.4453594704478379e-06 tokens_per_second_per_gpu:253.61094279911924 mfu:4.184958990532606 
Step 3931 | loss:1.2154420614242554 lr:1.4325141120119067e-06 tokens_per_second_per_gpu:291.42616360793807 mfu:4.808966561168834 
Step 3932 | loss:1.4776052236557007 lr:1.4197256771891986e-06 tokens_per_second_per_gpu:196.16764086693235 mfu:3.2370587926401218 
Step 3933 | loss:1.122484564781189 lr:1.4069941733651948e-06 tokens_per_second_per_gpu:304.6335300273143 mfu:5.026907814917523 
Step 3934 | loss:1.3476293087005615 lr:1.3943196078924248e-06 tokens_per_second_per_gpu:230.72734062505802 mfu:3.8073454081014866 
Step 3935 | loss:1.1626427173614502 lr:1.3817019880905557e-06 tokens_per_second_per_gpu:233.31401763255886 mfu:3.8500294385248863 
Step 3936 | loss:1.2255220413208008 lr:1.3691413212464144e-06 tokens_per_second_per_gpu:322.5388953471154 mfu:5.322373060804904 
Step 3937 | loss:1.0937665700912476 lr:1.3566376146138538e-06 tokens_per_second_per_gpu:244.4586215297641 mfu:4.033932032635253 
Step 3938 | loss:1.1362981796264648 lr:1.3441908754139198e-06 tokens_per_second_per_gpu:222.26097773994942 mfu:3.667637787120749 
Step 3939 | loss:1.1513049602508545 lr:1.331801110834685e-06 tokens_per_second_per_gpu:279.60599606169575 mfu:4.613916158783672 
Step 3940 | loss:1.14083993434906 lr:1.3194683280313592e-06 tokens_per_second_per_gpu:352.3279530306452 mfu:5.813936963356728 
Step 3941 | loss:1.320998191833496 lr:1.3071925341262447e-06 tokens_per_second_per_gpu:284.0394303247389 mfu:4.687074439626285 
Step 3942 | loss:1.311928629875183 lr:1.2949737362087156e-06 tokens_per_second_per_gpu:211.58743472281196 mfu:3.4915084004412993 
Step 3943 | loss:1.1356384754180908 lr:1.2828119413352379e-06 tokens_per_second_per_gpu:190.4753428991683 mfu:3.1431273822125614 
Step 3944 | loss:1.192633032798767 lr:1.2707071565293715e-06 tokens_per_second_per_gpu:199.96644860447972 mfu:3.299744788832116 
Step 3945 | loss:1.3467960357666016 lr:1.2586593887817133e-06 tokens_per_second_per_gpu:223.19415503300812 mfu:3.6830366049290175 
Step 3946 | loss:1.332850456237793 lr:1.2466686450499865e-06 tokens_per_second_per_gpu:218.8368169703955 mfu:3.6111340249430883 
Step 3947 | loss:1.0879501104354858 lr:1.2347349322589296e-06 tokens_per_second_per_gpu:252.78378363551184 mfu:4.1713096300589045 
Step 3948 | loss:1.161563515663147 lr:1.2228582573003745e-06 tokens_per_second_per_gpu:243.0935533237871 mfu:4.011406370302856 
Step 3949 | loss:1.3022123575210571 lr:1.211038627033223e-06 tokens_per_second_per_gpu:179.92575419280104 mfu:2.9690434266235353 
Step 3950 | loss:1.308874487876892 lr:1.1992760482834041e-06 tokens_per_second_per_gpu:225.35867786615768 mfu:3.718754461543657 
Step 3951 | loss:1.1708990335464478 lr:1.1875705278439176e-06 tokens_per_second_per_gpu:268.19845525812127 mfu:4.4256747133678065 
Step 3952 | loss:1.190621018409729 lr:1.175922072474811e-06 tokens_per_second_per_gpu:250.7275343136565 mfu:4.1373784479446885 
Step 3953 | loss:1.4356353282928467 lr:1.1643306889031592e-06 tokens_per_second_per_gpu:190.9279101836227 mfu:3.150595417719998 
Step 3954 | loss:1.1155128479003906 lr:1.1527963838231181e-06 tokens_per_second_per_gpu:241.3271959962847 mfu:3.9822588386678373 
Step 3955 | loss:1.264902114868164 lr:1.1413191638958154e-06 tokens_per_second_per_gpu:224.4675329862419 mfu:3.704049241272367 
Step 3956 | loss:1.3031940460205078 lr:1.129899035749482e-06 tokens_per_second_per_gpu:257.9433659073117 mfu:4.256450436592891 
Step 3957 | loss:1.1369316577911377 lr:1.1185360059793315e-06 tokens_per_second_per_gpu:280.81301818384134 mfu:4.6338338248989155 
Step 3958 | loss:0.904731273651123 lr:1.1072300811476032e-06 tokens_per_second_per_gpu:328.3652021606623 mfu:5.4185158171538195 
Step 3959 | loss:1.3212445974349976 lr:1.0959812677835968e-06 tokens_per_second_per_gpu:184.76781297679418 mfu:3.048944621805046 
Step 3960 | loss:1.2499332427978516 lr:1.0847895723836043e-06 tokens_per_second_per_gpu:247.0648379276426 mfu:4.076938492156261 
Step 3961 | loss:0.9647049903869629 lr:1.0736550014108892e-06 tokens_per_second_per_gpu:287.08889872358446 mfu:4.737395218577067 
Step 3962 | loss:1.21147620677948 lr:1.0625775612958189e-06 tokens_per_second_per_gpu:266.9222027816796 mfu:4.404614643102208 
Step 3963 | loss:1.0380566120147705 lr:1.051557258435687e-06 tokens_per_second_per_gpu:250.22523884093468 mfu:4.1290898231272015 
Step 3964 | loss:1.3533991575241089 lr:1.0405940991948137e-06 tokens_per_second_per_gpu:171.21195297520057 mfu:2.825252703933009 
Step 3965 | loss:1.3428417444229126 lr:1.0296880899045458e-06 tokens_per_second_per_gpu:248.42931154179314 mfu:4.099454342836281 
Step 3966 | loss:1.0738708972930908 lr:1.0188392368631671e-06 tokens_per_second_per_gpu:216.45072047898717 mfu:3.571759872338376 
Step 3967 | loss:1.1659786701202393 lr:1.0080475463360218e-06 tokens_per_second_per_gpu:272.2740130488239 mfu:4.492927498399035 
Step 3968 | loss:1.2596962451934814 lr:9.973130245554018e-07 tokens_per_second_per_gpu:271.61906806283326 mfu:4.482119928831358 
Step 3969 | loss:1.2788758277893066 lr:9.86635677720571e-07 tokens_per_second_per_gpu:237.60502007189427 mfu:3.920837381741745 
Step 3970 | loss:1.0894988775253296 lr:9.760155119978187e-07 tokens_per_second_per_gpu:285.9431294126052 mfu:4.71848831524657 
Step 3971 | loss:1.2349610328674316 lr:9.654525335203723e-07 tokens_per_second_per_gpu:163.40533085542833 mfu:2.6964317900353416 
Step 3972 | loss:1.0190622806549072 lr:9.549467483884412e-07 tokens_per_second_per_gpu:273.6334561768238 mfu:4.5153603385511545 
Step 3973 | loss:1.2117445468902588 lr:9.444981626692273e-07 tokens_per_second_per_gpu:322.37387203645073 mfu:5.319649929933692 
Step 3974 | loss:1.3072874546051025 lr:9.341067823968707e-07 tokens_per_second_per_gpu:231.64780283191652 mfu:3.8225344080141963 
Step 3975 | loss:1.245788335800171 lr:9.237726135724934e-07 tokens_per_second_per_gpu:253.22814855960695 mfu:4.178642314380977 
Step 3976 | loss:1.0211665630340576 lr:9.134956621641877e-07 tokens_per_second_per_gpu:244.15636563966206 mfu:4.02894435942698 
Step 3977 | loss:1.2682409286499023 lr:9.032759341069397e-07 tokens_per_second_per_gpu:210.49978710614 mfu:3.4735605917951715 
Step 3978 | loss:1.1091747283935547 lr:8.931134353027837e-07 tokens_per_second_per_gpu:279.0496063274787 mfu:4.60473489793289 
Step 3979 | loss:1.1436262130737305 lr:8.830081716206251e-07 tokens_per_second_per_gpu:259.42408347358895 mfu:4.280884485940438 
Step 3980 | loss:0.9126787781715393 lr:8.729601488963512e-07 tokens_per_second_per_gpu:208.15532433651128 mfu:3.4348734577250215 
Step 3981 | loss:0.9533777832984924 lr:8.629693729327981e-07 tokens_per_second_per_gpu:339.50155438230564 mfu:5.602282246304392 
Step 3982 | loss:1.0664256811141968 lr:8.53035849499706e-07 tokens_per_second_per_gpu:279.5316171155456 mfu:4.612688795185076 
Step 3983 | loss:1.1106719970703125 lr:8.431595843337969e-07 tokens_per_second_per_gpu:227.06109219872735 mfu:3.746846838347533 
Step 3984 | loss:1.3695664405822754 lr:8.333405831386976e-07 tokens_per_second_per_gpu:339.180820412379 mfu:5.596989657206306 
Step 3985 | loss:1.135240077972412 lr:8.235788515849607e-07 tokens_per_second_per_gpu:258.49059414291617 mfu:4.265480519045918 
Step 3986 | loss:1.2339609861373901 lr:8.13874395310088e-07 tokens_per_second_per_gpu:197.0670266103313 mfu:3.251899999455774 
Step 3987 | loss:1.329115867614746 lr:8.042272199184742e-07 tokens_per_second_per_gpu:241.54604207165207 mfu:3.9858701254701456 
Step 3988 | loss:1.2875615358352661 lr:7.946373309814626e-07 tokens_per_second_per_gpu:208.81323077789972 mfu:3.4457298957258007 
Step 3989 | loss:1.1892426013946533 lr:7.851047340373008e-07 tokens_per_second_per_gpu:275.5038691068547 mfu:4.546224942898063 
Step 3990 | loss:1.173731803894043 lr:7.756294345911297e-07 tokens_per_second_per_gpu:241.22688992325217 mfu:3.980603638787622 
Step 3991 | loss:1.3502552509307861 lr:7.662114381150498e-07 tokens_per_second_per_gpu:214.37144683328245 mfu:3.5374487545241027 
Step 3992 | loss:1.158808946609497 lr:7.568507500480216e-07 tokens_per_second_per_gpu:272.1598021452836 mfu:4.491042848066867 
Step 3993 | loss:1.154496431350708 lr:7.475473757959317e-07 tokens_per_second_per_gpu:223.9558969805082 mfu:3.6956064837223837 
Step 3994 | loss:1.2590570449829102 lr:7.383013207315715e-07 tokens_per_second_per_gpu:227.80592603456338 mfu:3.759137708068418 
Step 3995 | loss:1.056182861328125 lr:7.291125901946027e-07 tokens_per_second_per_gpu:292.583995305835 mfu:4.82807251188278 
Step 3996 | loss:1.1363662481307983 lr:7.199811894916031e-07 tokens_per_second_per_gpu:169.23275594945554 mfu:2.7925929996808634 
Step 3997 | loss:1.1813081502914429 lr:7.109071238960541e-07 tokens_per_second_per_gpu:305.7208938406074 mfu:5.044850940384412 
Step 3998 | loss:1.2174667119979858 lr:7.018903986483083e-07 tokens_per_second_per_gpu:267.48445677637324 mfu:4.413892673001414 
Step 3999 | loss:1.0952143669128418 lr:6.929310189555894e-07 tokens_per_second_per_gpu:281.1564483674014 mfu:4.639500935388893 
Step 4000 | loss:1.1663157939910889 lr:6.840289899920249e-07 tokens_per_second_per_gpu:180.9465691284336 mfu:2.9858883963058145 
Step 4001 | loss:1.1393496990203857 lr:6.751843168986361e-07 tokens_per_second_per_gpu:220.8773794530209 mfu:3.644806350802351 
Step 4002 | loss:1.1717028617858887 lr:6.663970047832812e-07 tokens_per_second_per_gpu:308.57687836363397 mfu:5.091978946670518 
Step 4003 | loss:1.1944336891174316 lr:6.576670587207123e-07 tokens_per_second_per_gpu:252.3915892271453 mfu:4.164837837094394 
Step 4004 | loss:1.1760141849517822 lr:6.48994483752563e-07 tokens_per_second_per_gpu:173.95884939621064 mfu:2.8705805937562543 
Step 4005 | loss:1.2105436325073242 lr:6.403792848873269e-07 tokens_per_second_per_gpu:224.14866179400573 mfu:3.6987873907857827 
Step 4006 | loss:1.2645022869110107 lr:6.318214671003464e-07 tokens_per_second_per_gpu:298.00042582642436 mfu:4.917451697786798 
Step 4007 | loss:1.876239538192749 lr:6.233210353338348e-07 tokens_per_second_per_gpu:282.3757228749357 mfu:4.659620784145872 
Step 4008 | loss:1.1776301860809326 lr:6.148779944968875e-07 tokens_per_second_per_gpu:223.4420127630134 mfu:3.6871266273235968 
Step 4009 | loss:1.1306495666503906 lr:6.064923494654262e-07 tokens_per_second_per_gpu:264.33618499435164 mfu:4.361941490795339 
Step 4010 | loss:1.276135802268982 lr:5.981641050822329e-07 tokens_per_second_per_gpu:281.21483725549854 mfu:4.640464439169497 
Step 4011 | loss:1.427370548248291 lr:5.898932661569489e-07 tokens_per_second_per_gpu:256.4743695176393 mfu:4.232209804149482 
Step 4012 | loss:0.9155475497245789 lr:5.816798374660537e-07 tokens_per_second_per_gpu:281.382429329575 mfu:4.643229958470073 
Step 4013 | loss:1.2323638200759888 lr:5.735238237528862e-07 tokens_per_second_per_gpu:188.39934920447493 mfu:3.1088703884842674 
Step 4014 | loss:1.3396004438400269 lr:5.65425229727612e-07 tokens_per_second_per_gpu:194.09750399269373 mfu:3.2028984451887887 
Step 4015 | loss:1.1218836307525635 lr:5.573840600672342e-07 tokens_per_second_per_gpu:244.05389409363457 mfu:4.027253426011062 
Step 4016 | loss:1.267001986503601 lr:5.494003194156161e-07 tokens_per_second_per_gpu:229.14414919450437 mfu:3.7812203870834553 
Step 4017 | loss:1.2254252433776855 lr:5.414740123834361e-07 tokens_per_second_per_gpu:215.95325381222787 mfu:3.563550930024741 
Step 4018 | loss:1.0450893640518188 lr:5.336051435481993e-07 tokens_per_second_per_gpu:247.4322815007557 mfu:4.0830018594062745 
Step 4019 | loss:1.0341668128967285 lr:5.257937174542482e-07 tokens_per_second_per_gpu:381.6133703854129 mfu:6.297190048959627 
Step 4020 | loss:1.1881318092346191 lr:5.180397386127633e-07 tokens_per_second_per_gpu:243.96931101526997 mfu:4.025857679004478 
Step 4021 | loss:1.149707555770874 lr:5.103432115017292e-07 tokens_per_second_per_gpu:255.0443985088368 mfu:4.208613148723502 
Step 4022 | loss:1.4544062614440918 lr:5.027041405659683e-07 tokens_per_second_per_gpu:224.13145752098546 mfu:3.698503494608997 
Step 4023 | loss:1.1153552532196045 lr:4.95122530217107e-07 tokens_per_second_per_gpu:212.3150075685059 mfu:3.5035144380682564 
Step 4024 | loss:0.9849837422370911 lr:4.875983848335874e-07 tokens_per_second_per_gpu:292.30845617829095 mfu:4.823525705123057 
Step 4025 | loss:1.2320747375488281 lr:4.801317087606894e-07 tokens_per_second_per_gpu:246.31567614909122 mfu:4.064576204922483 
Step 4026 | loss:1.2141995429992676 lr:4.7272250631046346e-07 tokens_per_second_per_gpu:250.5219723453475 mfu:4.1339863687311835 
Step 4027 | loss:1.0757864713668823 lr:4.6537078176179805e-07 tokens_per_second_per_gpu:228.61314398738432 mfu:3.772458008808174 
Step 4028 | loss:1.3482147455215454 lr:4.58076539360397e-07 tokens_per_second_per_gpu:224.90912220147322 mfu:3.7113361222563164 
Step 4029 | loss:1.133992314338684 lr:4.50839783318735e-07 tokens_per_second_per_gpu:345.743218450968 mfu:5.705279017152418 
Step 4030 | loss:1.2525932788848877 lr:4.436605178161024e-07 tokens_per_second_per_gpu:205.81635334508118 mfu:3.3962769461898956 
Step 4031 | loss:1.2031232118606567 lr:4.3653874699859374e-07 tokens_per_second_per_gpu:247.97992721049337 mfu:4.092038830805449 
Step 4032 | loss:1.1503185033798218 lr:4.2947447497910796e-07 tokens_per_second_per_gpu:219.97351198071735 mfu:3.629891188772206 
Step 4033 | loss:1.2566852569580078 lr:4.224677058373039e-07 tokens_per_second_per_gpu:256.2518035250407 mfu:4.228537133162056 
Step 4034 | loss:1.3337976932525635 lr:4.155184436196669e-07 tokens_per_second_per_gpu:247.28622563353238 mfu:4.0805917196547705 
Step 4035 | loss:1.1603894233703613 lr:4.086266923394644e-07 tokens_per_second_per_gpu:262.4068215627513 mfu:4.330104115207504 
Step 4036 | loss:1.2839760780334473 lr:4.01792455976735e-07 tokens_per_second_per_gpu:252.92595473481668 mfu:4.173655665342962 
Step 4037 | loss:1.0175377130508423 lr:3.950157384783104e-07 tokens_per_second_per_gpu:343.24330826214157 mfu:5.664026768709258 
Step 4038 | loss:1.179462194442749 lr:3.8829654375781566e-07 tokens_per_second_per_gpu:335.4567026210349 mfu:5.535536156577854 
Step 4039 | loss:1.036980152130127 lr:3.816348756956356e-07 tokens_per_second_per_gpu:286.0805990856729 mfu:4.7207567699823185 
Step 4040 | loss:1.0986199378967285 lr:3.750307381389484e-07 tokens_per_second_per_gpu:205.0617154630894 mfu:3.3838242950779938 
Step 4041 | loss:1.2439956665039062 lr:3.684841349017032e-07 tokens_per_second_per_gpu:241.75980140790287 mfu:3.9893974734866764 
Step 4042 | loss:1.0511507987976074 lr:3.6199506976463124e-07 tokens_per_second_per_gpu:292.452530624099 mfu:4.825903148464561 
Step 4043 | loss:1.0694797039031982 lr:3.5556354647521274e-07 tokens_per_second_per_gpu:269.09795026878913 mfu:4.440517723256443 
Step 4044 | loss:1.0097723007202148 lr:3.491895687477209e-07 tokens_per_second_per_gpu:228.93789604095497 mfu:3.777816902282108 
Step 4045 | loss:1.0590015649795532 lr:3.4287314026316684e-07 tokens_per_second_per_gpu:355.3845038471524 mfu:5.864374612767202 
Step 4046 | loss:1.2349432706832886 lr:3.3661426466937705e-07 tokens_per_second_per_gpu:213.73824516055527 mfu:3.5269999820703095 
Step 4047 | loss:1.2361245155334473 lr:3.3041294558088243e-07 tokens_per_second_per_gpu:277.00312994898707 mfu:4.57096498396721 
Step 4048 | loss:1.0881998538970947 lr:3.2426918657900704e-07 tokens_per_second_per_gpu:241.55883657744099 mfu:3.986081253907427 
Step 4049 | loss:1.0842963457107544 lr:3.1818299121182394e-07 tokens_per_second_per_gpu:275.5724971918799 mfu:4.547357408706752 
Step 4050 | loss:1.1976791620254517 lr:3.12154362994177e-07 tokens_per_second_per_gpu:217.66249628596313 mfu:3.591755981346696 
Step 4051 | loss:1.2443846464157104 lr:3.061833054076479e-07 tokens_per_second_per_gpu:279.1029332035285 mfu:4.605614870961255 
Step 4052 | loss:1.2934486865997314 lr:3.002698219005673e-07 tokens_per_second_per_gpu:297.5861452182016 mfu:4.910615449567972 
Step 4053 | loss:1.2093697786331177 lr:2.9441391588804767e-07 tokens_per_second_per_gpu:268.4049696610747 mfu:4.429082509174153 
Step 4054 | loss:1.150982141494751 lr:2.8861559075190616e-07 tokens_per_second_per_gpu:277.78682095437046 mfu:4.583897054967697 
Step 4055 | loss:1.5216009616851807 lr:2.8287484984073076e-07 tokens_per_second_per_gpu:148.62389282719502 mfu:2.4525160059350735 
Step 4056 | loss:1.1824122667312622 lr:2.771916964698584e-07 tokens_per_second_per_gpu:246.91846237907083 mfu:4.074523077185486 
Step 4057 | loss:1.0884324312210083 lr:2.715661339213638e-07 tokens_per_second_per_gpu:306.65250479933223 mfu:5.0602239113389125 
Step 4058 | loss:1.1212369203567505 lr:2.659981654440591e-07 tokens_per_second_per_gpu:279.5519536956902 mfu:4.613024379103393 
Step 4059 | loss:1.111606478691101 lr:2.6048779425348336e-07 tokens_per_second_per_gpu:241.8583474106745 mfu:3.991023629581238 
Step 4060 | loss:0.8871002793312073 lr:2.550350235319354e-07 tokens_per_second_per_gpu:221.0715698283319 mfu:3.6480107817628724 
Step 4061 | loss:1.1142327785491943 lr:2.4963985642844076e-07 tokens_per_second_per_gpu:273.79763976469644 mfu:4.518069612743276 
Step 4062 | loss:1.426342487335205 lr:2.4430229605875153e-07 tokens_per_second_per_gpu:352.0132288888811 mfu:5.808743545391097 
Step 4063 | loss:1.1642740964889526 lr:2.390223455053686e-07 tokens_per_second_per_gpu:240.638724176236 mfu:3.970898026309975 
Step 4064 | loss:1.238951325416565 lr:2.3380000781749735e-07 tokens_per_second_per_gpu:223.3955427901854 mfu:3.686359803430156 
Step 4065 | loss:1.2359209060668945 lr:2.2863528601109186e-07 tokens_per_second_per_gpu:272.27820987305165 mfu:4.492996752261229 
Step 4066 | loss:1.1394462585449219 lr:2.2352818306882184e-07 tokens_per_second_per_gpu:285.0532380660088 mfu:4.703803780145553 
Step 4067 | loss:1.1630685329437256 lr:2.1847870194009466e-07 tokens_per_second_per_gpu:286.0482393087981 mfu:4.720222785377123 
Step 4068 | loss:1.1603652238845825 lr:2.1348684554102216e-07 tokens_per_second_per_gpu:184.8016424602922 mfu:3.0495028587625983 
Step 4069 | loss:1.1185506582260132 lr:2.0855261675445382e-07 tokens_per_second_per_gpu:270.79763189343583 mfu:4.468565006301885 
Step 4070 | loss:0.9973759651184082 lr:2.0367601842993245e-07 tokens_per_second_per_gpu:292.883149436354 mfu:4.833009001429535 
Step 4071 | loss:1.136293888092041 lr:1.988570533837719e-07 tokens_per_second_per_gpu:160.98458996335376 mfu:2.6564859531237945 
Step 4072 | loss:1.3008166551589966 lr:1.9409572439893497e-07 tokens_per_second_per_gpu:341.2367170203609 mfu:5.630915019015298 
Step 4073 | loss:1.2268801927566528 lr:1.893920342251443e-07 tokens_per_second_per_gpu:208.24098359610136 mfu:3.436286963327687 
Step 4074 | loss:1.2275304794311523 lr:1.8474598557882693e-07 tokens_per_second_per_gpu:221.12393258339412 mfu:3.648874845356297 
Step 4075 | loss:1.22614586353302 lr:1.8015758114311443e-07 tokens_per_second_per_gpu:187.40976261303226 mfu:3.092540733079576 
Step 4076 | loss:1.0718224048614502 lr:1.7562682356786487e-07 tokens_per_second_per_gpu:190.02912054090532 mfu:3.1357640474550843 
Step 4077 | loss:1.0806221961975098 lr:1.7115371546960745e-07 tokens_per_second_per_gpu:253.53239371543933 mfu:4.183662813442153 
Step 4078 | loss:0.996636152267456 lr:1.6673825943160914e-07 tokens_per_second_per_gpu:227.05365942070983 mfu:3.7467241864191667 
Step 4079 | loss:1.2245758771896362 lr:1.6238045800385238e-07 tokens_per_second_per_gpu:220.56444217896583 mfu:3.6396424188202565 
Step 4080 | loss:1.2328482866287231 lr:1.580803137029907e-07 tokens_per_second_per_gpu:202.08594954868636 mfu:3.334719717098227 
Step 4081 | loss:1.1600182056427002 lr:1.538378290123932e-07 tokens_per_second_per_gpu:248.48236247407357 mfu:4.100329762380692 
Step 4082 | loss:1.1272435188293457 lr:1.496530063821555e-07 tokens_per_second_per_gpu:283.7287937837272 mfu:4.6819484731725245 
Step 4083 | loss:1.0697616338729858 lr:1.4552584822902226e-07 tokens_per_second_per_gpu:195.04101007632903 mfu:3.218467703454034 
Step 4084 | loss:0.957577645778656 lr:1.4145635693649796e-07 tokens_per_second_per_gpu:216.4603137845849 mfu:3.5719181761957217 
Step 4085 | loss:1.1971909999847412 lr:1.3744453485471376e-07 tokens_per_second_per_gpu:255.48411758351827 mfu:4.215869169597784 
Step 4086 | loss:0.9638705849647522 lr:1.334903843005497e-07 tokens_per_second_per_gpu:236.0435917067594 mfu:3.8950714837776355 
Step 4087 | loss:1.1577469110488892 lr:1.2959390755756806e-07 tokens_per_second_per_gpu:228.23055638088317 mfu:3.766144742409565 
Step 4088 | loss:1.0621474981307983 lr:1.2575510687601322e-07 tokens_per_second_per_gpu:175.48251688409732 mfu:2.8957233808995695 
Step 4089 | loss:1.1719709634780884 lr:1.2197398447283404e-07 tokens_per_second_per_gpu:253.38110813423788 mfu:4.1811663756063115 
Step 4090 | loss:1.0804520845413208 lr:1.1825054253166156e-07 tokens_per_second_per_gpu:290.71667489441734 mfu:4.797258938707599 
Step 4091 | loss:1.115520715713501 lr:1.1458478320280908e-07 tokens_per_second_per_gpu:276.38989884322933 mfu:4.560845755668186 
Step 4092 | loss:1.239301323890686 lr:1.1097670860329423e-07 tokens_per_second_per_gpu:285.6497281676645 mfu:4.713646756896225 
Step 4093 | loss:1.1354990005493164 lr:1.0742632081679471e-07 tokens_per_second_per_gpu:251.21408781109824 mfu:4.14540730668012 
Step 4094 | loss:1.1991702318191528 lr:1.0393362189371481e-07 tokens_per_second_per_gpu:275.0842218761691 mfu:4.539300137400609 
Step 4095 | loss:1.0658262968063354 lr:1.004986138511188e-07 tokens_per_second_per_gpu:204.2027081001189 mfu:3.369649391791409 
Step 4096 | loss:1.1717395782470703 lr:9.7121298672731e-08 tokens_per_second_per_gpu:325.86700607925115 mfu:5.377291854040777 
Step 4097 | loss:1.1986362934112549 lr:9.380167830900232e-08 tokens_per_second_per_gpu:265.3997477338043 mfu:4.379491863028266 
Step 4098 | loss:1.4296278953552246 lr:9.053975467704368e-08 tokens_per_second_per_gpu:285.1494552158102 mfu:4.705391506691027 
Step 4099 | loss:1.3210562467575073 lr:8.733552966063707e-08 tokens_per_second_per_gpu:253.78882776884623 mfu:4.187894357970316 
Step 4100 | loss:1.1543173789978027 lr:8.418900511024674e-08 tokens_per_second_per_gpu:250.0050661502367 mfu:4.125456645192383 
Step 4101 | loss:1.1717512607574463 lr:8.110018284304133e-08 tokens_per_second_per_gpu:273.2717557056792 mfu:4.50939174105339 
Step 4102 | loss:1.1664633750915527 lr:7.806906464281615e-08 tokens_per_second_per_gpu:255.38422388776627 mfu:4.214220774558041 
Step 4103 | loss:1.1615198850631714 lr:7.509565226008208e-08 tokens_per_second_per_gpu:213.197981990428 mfu:3.518084833590819 
Step 4104 | loss:1.1662148237228394 lr:7.217994741202105e-08 tokens_per_second_per_gpu:283.0583346336616 mfu:4.670884896747614 
Step 4105 | loss:1.1507422924041748 lr:6.932195178246393e-08 tokens_per_second_per_gpu:268.0625892065523 mfu:4.423432720779687 
Step 4106 | loss:1.0287716388702393 lr:6.652166702193485e-08 tokens_per_second_per_gpu:294.93004382913387 mfu:4.866785813254725 
Step 4107 | loss:1.2516335248947144 lr:6.3779094747618e-08 tokens_per_second_per_gpu:243.09826312891184 mfu:4.011484089115314 
Step 4108 | loss:1.3226170539855957 lr:6.109423654337976e-08 tokens_per_second_per_gpu:241.94265678400478 mfu:3.9924148600463374 
Step 4109 | loss:1.2459946870803833 lr:5.846709395975758e-08 tokens_per_second_per_gpu:229.105319408333 mfu:3.780579637670418 
Step 4110 | loss:1.2461344003677368 lr:5.589766851393785e-08 tokens_per_second_per_gpu:238.9450207894285 mfu:3.942949393109515 
Step 4111 | loss:1.1899622678756714 lr:5.338596168978915e-08 tokens_per_second_per_gpu:274.05495767245463 mfu:4.522315742187111 
Step 4112 | loss:1.0133116245269775 lr:5.0931974937840075e-08 tokens_per_second_per_gpu:266.4024404207875 mfu:4.39603778856609 
Step 4113 | loss:1.2798337936401367 lr:4.853570967530141e-08 tokens_per_second_per_gpu:272.2657720487709 mfu:4.492791509601067 
Step 4114 | loss:1.1696791648864746 lr:4.619716728603285e-08 tokens_per_second_per_gpu:275.353239162416 mfu:4.543739324047139 
Step 4115 | loss:1.1656157970428467 lr:4.391634912056519e-08 tokens_per_second_per_gpu:302.24059083398976 mfu:4.987420747520619 
Step 4116 | loss:1.2017552852630615 lr:4.169325649608924e-08 tokens_per_second_per_gpu:253.05028966070853 mfu:4.175707377150841 
Step 4117 | loss:1.190941333770752 lr:3.95278906964669e-08 tokens_per_second_per_gpu:229.50887547519392 mfu:3.787238914953778 
Step 4118 | loss:1.293121576309204 lr:3.742025297219787e-08 tokens_per_second_per_gpu:236.2686853838256 mfu:3.8987858653305496 
Step 4119 | loss:1.192134976387024 lr:3.5370344540486266e-08 tokens_per_second_per_gpu:197.07738609755197 mfu:3.2520709464531823 
Step 4120 | loss:1.4075571298599243 lr:3.337816658516291e-08 tokens_per_second_per_gpu:211.7045968674899 mfu:3.4934417506560353 
Step 4121 | loss:1.2825475931167603 lr:3.1443720256718604e-08 tokens_per_second_per_gpu:248.85675697837533 mfu:4.1065078303673905 
Step 4122 | loss:1.1570043563842773 lr:2.9567006672337472e-08 tokens_per_second_per_gpu:295.5996440023978 mfu:4.877835215280657 
Step 4123 | loss:1.340097188949585 lr:2.7748026915808135e-08 tokens_per_second_per_gpu:268.5094551443219 mfu:4.430806675559363 
Step 4124 | loss:1.2370177507400513 lr:2.5986782037634716e-08 tokens_per_second_per_gpu:290.1540917765553 mfu:4.787975477785001 
Step 4125 | loss:1.0702688694000244 lr:2.428327305493694e-08 tokens_per_second_per_gpu:337.5407614489538 mfu:5.569926237039037 
Step 4126 | loss:1.1854966878890991 lr:2.263750095150563e-08 tokens_per_second_per_gpu:184.07280361310086 mfu:3.0374759302218264 
Step 4127 | loss:1.314978003501892 lr:2.104946667780272e-08 tokens_per_second_per_gpu:251.46540699121843 mfu:4.149554448166718 
Step 4128 | loss:1.293553113937378 lr:1.951917115091684e-08 tokens_per_second_per_gpu:205.66768154019908 mfu:3.393823639563561 
Step 4129 | loss:1.359985589981079 lr:1.8046615254618814e-08 tokens_per_second_per_gpu:259.368926226191 mfu:4.279974309053575 
Step 4130 | loss:1.157039999961853 lr:1.6631799839317286e-08 tokens_per_second_per_gpu:250.30439038945676 mfu:4.130395941786539 
Step 4131 | loss:1.1789684295654297 lr:1.5274725722069784e-08 tokens_per_second_per_gpu:225.0040632668083 mfu:3.712902791503942 
Step 4132 | loss:1.1071491241455078 lr:1.3975393686627147e-08 tokens_per_second_per_gpu:290.7902932355604 mfu:4.798473751188616 
Step 4133 | loss:1.1535725593566895 lr:1.2733804483344714e-08 tokens_per_second_per_gpu:246.59738893867964 mfu:4.069224886318183 
Step 4134 | loss:1.1273120641708374 lr:1.1549958829248919e-08 tokens_per_second_per_gpu:274.80804476101923 mfu:4.534742802893393 
Step 4135 | loss:1.1130919456481934 lr:1.0423857408037307e-08 tokens_per_second_per_gpu:226.36936823212932 mfu:3.7354323607188036 
Step 4136 | loss:1.186476230621338 lr:9.355500870034118e-09 tokens_per_second_per_gpu:344.69470319261063 mfu:5.687976950811184 
Step 4137 | loss:1.1641526222229004 lr:8.344889832223591e-09 tokens_per_second_per_gpu:215.75483950241227 mfu:3.5602767978420027 
Step 4138 | loss:1.2496821880340576 lr:7.392024878238868e-09 tokens_per_second_per_gpu:174.56665110668402 mfu:2.880610228931427 
Step 4139 | loss:1.1244282722473145 lr:6.496906558384197e-09 tokens_per_second_per_gpu:267.92120821856656 mfu:4.421099723511387 
Step 4140 | loss:1.1732358932495117 lr:5.6595353895794176e-09 tokens_per_second_per_gpu:218.28886964501405 mfu:3.6020920764357256 
Step 4141 | loss:1.1343662738800049 lr:4.8799118554265775e-09 tokens_per_second_per_gpu:230.21287576629015 mfu:3.798855970255269 
Step 4142 | loss:1.1348897218704224 lr:4.158036406165522e-09 tokens_per_second_per_gpu:249.74638095233965 mfu:4.12118795342101 
Step 4143 | loss:1.269087791442871 lr:3.493909458673894e-09 tokens_per_second_per_gpu:229.41062507062168 mfu:3.785617636670594 
Step 4144 | loss:1.2514928579330444 lr:2.8875313965004423e-09 tokens_per_second_per_gpu:243.24806512095174 mfu:4.013956045516199 
Step 4145 | loss:1.1618478298187256 lr:2.3389025698317133e-09 tokens_per_second_per_gpu:184.1525208049189 mfu:3.0387913828395914 
Step 4146 | loss:1.2764923572540283 lr:1.8480232955142562e-09 tokens_per_second_per_gpu:248.53882760129574 mfu:4.101261521236252 
Step 4147 | loss:1.221461534500122 lr:1.4148938570213155e-09 tokens_per_second_per_gpu:249.54795557118857 mfu:4.1179136385447155 
Step 4148 | loss:1.0648581981658936 lr:1.039514504497241e-09 tokens_per_second_per_gpu:270.30744174153347 mfu:4.460476137341293 
Step 4149 | loss:1.2924714088439941 lr:7.218854547130782e-10 tokens_per_second_per_gpu:143.1915678684523 mfu:2.362874538084089 
Step 4150 | loss:1.376705527305603 lr:4.6200689113318206e-10 tokens_per_second_per_gpu:227.27114412324414 mfu:3.7503130085383103 
Step 4151 | loss:1.2299785614013672 lr:2.598789638041943e-10 tokens_per_second_per_gpu:248.86221772269502 mfu:4.106597940797104 
Step 4152 | loss:1.0532519817352295 lr:1.1550178948827039e-10 tokens_per_second_per_gpu:315.77866176152344 mfu:5.210819119126084 
Step 4153 | loss:1.1012293100357056 lr:2.8875451540955056e-11 tokens_per_second_per_gpu:247.49355279111262 mfu:4.08401292712524 
Step 4154 | loss:0.9844874739646912 lr:0.0 tokens_per_second_per_gpu:252.71697103925828 mfu:4.170207122523993